diff options
645 files changed, 36853 insertions, 14573 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index b3f35e5..057602d 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -604,6 +604,13 @@ Who: Jean Delvare <khali@linux-fr.org> ---------------------------- +What: xt_connlimit rev 0 +When: 2012 +Who: Jan Engelhardt <jengelh@medozas.de> +Files: net/netfilter/xt_connlimit.c + +---------------------------- + What: noswapaccount kernel command line parameter When: 2.6.40 Why: The original implementation of memsw feature enabled by diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt index 77f0cdd..18afcd8 100644 --- a/Documentation/networking/batman-adv.txt +++ b/Documentation/networking/batman-adv.txt @@ -1,4 +1,4 @@ -[state: 21-11-2010] +[state: 27-01-2011] BATMAN-ADV ---------- @@ -67,15 +67,16 @@ All mesh wide settings can be found in batman's own interface folder: # ls /sys/class/net/bat0/mesh/ -# aggregated_ogms bonding fragmentation orig_interval -# vis_mode +# aggregated_ogms gw_bandwidth hop_penalty +# bonding gw_mode orig_interval +# fragmentation gw_sel_class vis_mode There is a special folder for debugging informations: # ls /sys/kernel/debug/batman_adv/bat0/ -# originators socket transtable_global transtable_local -# vis_data +# gateways socket transtable_global vis_data +# originators softif_neigh transtable_local Some of the files contain all sort of status information regard- @@ -230,9 +231,8 @@ CONTACT Please send us comments, experiences, questions, anything :) IRC: #batman on irc.freenode.org -Mailing-list: b.a.t.m.a.n@b.a.t.m.a.n@lists.open-mesh.org - (optional subscription at - https://lists.open-mesh.org/mm/listinfo/b.a.t.m.a.n) +Mailing-list: b.a.t.m.a.n@open-mesh.org (optional subscription + at https://lists.open-mesh.org/mm/listinfo/b.a.t.m.a.n) You can also contact the Authors: diff --git a/MAINTAINERS b/MAINTAINERS index 5dd6c75..1eacf29 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1693,6 +1693,7 @@ S: Supported F: scripts/checkpatch.pl CISCO VIC ETHERNET NIC DRIVER +M: Christian Benvenuti <benve@cisco.com> M: Vasanthy Kolluri <vkolluri@cisco.com> M: Roopa Prabhu <roprabhu@cisco.com> M: David Wang <dwang2@cisco.com> @@ -5145,6 +5146,7 @@ RALINK RT2X00 WIRELESS LAN DRIVER P: rt2x00 project M: Ivo van Doorn <IvDoorn@gmail.com> M: Gertjan van Wingerde <gwingerde@gmail.com> +M: Helmut Schaa <helmut.schaa@googlemail.com> L: linux-wireless@vger.kernel.org L: users@rt2x00.serialmonkey.com (moderated for non-subscribers) W: http://rt2x00.serialmonkey.com/ diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c index 3b4ec32..3d7f366 100644 --- a/drivers/infiniband/hw/nes/nes.c +++ b/drivers/infiniband/hw/nes/nes.c @@ -153,7 +153,8 @@ static int nes_inetaddr_event(struct notifier_block *notifier, nesdev, nesdev->netdev[0]->name); netdev = nesdev->netdev[0]; nesvnic = netdev_priv(netdev); - is_bonded = (netdev->master == event_netdev); + is_bonded = netif_is_bond_slave(netdev) && + (netdev->master == event_netdev); if ((netdev == event_netdev) || is_bonded) { if (nesvnic->rdma_enabled == 0) { nes_debug(NES_DBG_NETDEV, "Returning without processing event for %s since" diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 009ec81..ec3aa11 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -1118,7 +1118,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi return rc; } - if (nesvnic->netdev->master) + if (netif_is_bond_slave(netdev)) netdev = nesvnic->netdev->master; else netdev = nesvnic->netdev; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 0382332..65027a7 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -1944,7 +1944,8 @@ config 68360_ENET config FEC bool "FEC ethernet controller (of ColdFire and some i.MX CPUs)" depends on M523x || M527x || M5272 || M528x || M520x || M532x || \ - MACH_MX27 || ARCH_MX35 || ARCH_MX25 || ARCH_MX5 || SOC_IMX28 + IMX_HAVE_PLATFORM_FEC || MXS_HAVE_PLATFORM_FEC + default IMX_HAVE_PLATFORM_FEC || MXS_HAVE_PLATFORM_FEC if ARM select PHYLIB help Say Y here if you want to use the built-in 10/100 Fast ethernet diff --git a/drivers/net/atl1c/atl1c_hw.c b/drivers/net/atl1c/atl1c_hw.c index 1bf6720..23f2ab0 100644 --- a/drivers/net/atl1c/atl1c_hw.c +++ b/drivers/net/atl1c/atl1c_hw.c @@ -345,7 +345,7 @@ int atl1c_write_phy_reg(struct atl1c_hw *hw, u32 reg_addr, u16 phy_data) */ static int atl1c_phy_setup_adv(struct atl1c_hw *hw) { - u16 mii_adv_data = ADVERTISE_DEFAULT_CAP & ~ADVERTISE_SPEED_MASK; + u16 mii_adv_data = ADVERTISE_DEFAULT_CAP & ~ADVERTISE_ALL; u16 mii_giga_ctrl_data = GIGA_CR_1000T_DEFAULT_CAP & ~GIGA_CR_1000T_SPEED_MASK; @@ -373,7 +373,7 @@ static int atl1c_phy_setup_adv(struct atl1c_hw *hw) } if (atl1c_write_phy_reg(hw, MII_ADVERTISE, mii_adv_data) != 0 || - atl1c_write_phy_reg(hw, MII_GIGA_CR, mii_giga_ctrl_data) != 0) + atl1c_write_phy_reg(hw, MII_CTRL1000, mii_giga_ctrl_data) != 0) return -1; return 0; } @@ -517,19 +517,18 @@ int atl1c_phy_init(struct atl1c_hw *hw) "Error Setting up Auto-Negotiation\n"); return ret_val; } - mii_bmcr_data |= BMCR_AUTO_NEG_EN | BMCR_RESTART_AUTO_NEG; + mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART; break; case MEDIA_TYPE_100M_FULL: - mii_bmcr_data |= BMCR_SPEED_100 | BMCR_FULL_DUPLEX; + mii_bmcr_data |= BMCR_SPEED100 | BMCR_FULLDPLX; break; case MEDIA_TYPE_100M_HALF: - mii_bmcr_data |= BMCR_SPEED_100; + mii_bmcr_data |= BMCR_SPEED100; break; case MEDIA_TYPE_10M_FULL: - mii_bmcr_data |= BMCR_SPEED_10 | BMCR_FULL_DUPLEX; + mii_bmcr_data |= BMCR_FULLDPLX; break; case MEDIA_TYPE_10M_HALF: - mii_bmcr_data |= BMCR_SPEED_10; break; default: if (netif_msg_link(adapter)) @@ -657,7 +656,7 @@ int atl1c_restart_autoneg(struct atl1c_hw *hw) err = atl1c_phy_setup_adv(hw); if (err) return err; - mii_bmcr_data |= BMCR_AUTO_NEG_EN | BMCR_RESTART_AUTO_NEG; + mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART; return atl1c_write_phy_reg(hw, MII_BMCR, mii_bmcr_data); } diff --git a/drivers/net/atl1c/atl1c_hw.h b/drivers/net/atl1c/atl1c_hw.h index 3dd6759..655fc6c 100644 --- a/drivers/net/atl1c/atl1c_hw.h +++ b/drivers/net/atl1c/atl1c_hw.h @@ -736,55 +736,16 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw); #define REG_DEBUG_DATA0 0x1900 #define REG_DEBUG_DATA1 0x1904 -/* PHY Control Register */ -#define MII_BMCR 0x00 -#define BMCR_SPEED_SELECT_MSB 0x0040 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define BMCR_COLL_TEST_ENABLE 0x0080 /* Collision test enable */ -#define BMCR_FULL_DUPLEX 0x0100 /* FDX =1, half duplex =0 */ -#define BMCR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */ -#define BMCR_ISOLATE 0x0400 /* Isolate PHY from MII */ -#define BMCR_POWER_DOWN 0x0800 /* Power down */ -#define BMCR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */ -#define BMCR_SPEED_SELECT_LSB 0x2000 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define BMCR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */ -#define BMCR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */ -#define BMCR_SPEED_MASK 0x2040 -#define BMCR_SPEED_1000 0x0040 -#define BMCR_SPEED_100 0x2000 -#define BMCR_SPEED_10 0x0000 - -/* PHY Status Register */ -#define MII_BMSR 0x01 -#define BMMSR_EXTENDED_CAPS 0x0001 /* Extended register capabilities */ -#define BMSR_JABBER_DETECT 0x0002 /* Jabber Detected */ -#define BMSR_LINK_STATUS 0x0004 /* Link Status 1 = link */ -#define BMSR_AUTONEG_CAPS 0x0008 /* Auto Neg Capable */ -#define BMSR_REMOTE_FAULT 0x0010 /* Remote Fault Detect */ -#define BMSR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */ -#define BMSR_PREAMBLE_SUPPRESS 0x0040 /* Preamble may be suppressed */ -#define BMSR_EXTENDED_STATUS 0x0100 /* Ext. status info in Reg 0x0F */ -#define BMSR_100T2_HD_CAPS 0x0200 /* 100T2 Half Duplex Capable */ -#define BMSR_100T2_FD_CAPS 0x0400 /* 100T2 Full Duplex Capable */ -#define BMSR_10T_HD_CAPS 0x0800 /* 10T Half Duplex Capable */ -#define BMSR_10T_FD_CAPS 0x1000 /* 10T Full Duplex Capable */ -#define BMSR_100X_HD_CAPS 0x2000 /* 100X Half Duplex Capable */ -#define BMMII_SR_100X_FD_CAPS 0x4000 /* 100X Full Duplex Capable */ -#define BMMII_SR_100T4_CAPS 0x8000 /* 100T4 Capable */ - -#define MII_PHYSID1 0x02 -#define MII_PHYSID2 0x03 #define L1D_MPW_PHYID1 0xD01C /* V7 */ #define L1D_MPW_PHYID2 0xD01D /* V1-V6 */ #define L1D_MPW_PHYID3 0xD01E /* V8 */ /* Autoneg Advertisement Register */ -#define MII_ADVERTISE 0x04 -#define ADVERTISE_SPEED_MASK 0x01E0 -#define ADVERTISE_DEFAULT_CAP 0x0DE0 +#define ADVERTISE_DEFAULT_CAP \ + (ADVERTISE_ALL | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM) /* 1000BASE-T Control Register */ -#define MII_GIGA_CR 0x09 #define GIGA_CR_1000T_REPEATER_DTE 0x0400 /* 1=Repeater/switch device port 0=DTE device */ #define GIGA_CR_1000T_MS_VALUE 0x0800 /* 1=Configure PHY as Master 0=Configure PHY as Slave */ diff --git a/drivers/net/atl1c/atl1c_main.c b/drivers/net/atl1c/atl1c_main.c index 3824382..e60595f 100644 --- a/drivers/net/atl1c/atl1c_main.c +++ b/drivers/net/atl1c/atl1c_main.c @@ -2718,7 +2718,6 @@ static int __devinit atl1c_probe(struct pci_dev *pdev, goto err_reset; } - device_init_wakeup(&pdev->dev, 1); /* reset the controller to * put the device in a known good starting state */ err = atl1c_phy_init(&adapter->hw); diff --git a/drivers/net/atl1e/atl1e_ethtool.c b/drivers/net/atl1e/atl1e_ethtool.c index 6943a6c..1209297 100644 --- a/drivers/net/atl1e/atl1e_ethtool.c +++ b/drivers/net/atl1e/atl1e_ethtool.c @@ -95,18 +95,18 @@ static int atl1e_set_settings(struct net_device *netdev, ecmd->advertising = hw->autoneg_advertised | ADVERTISED_TP | ADVERTISED_Autoneg; - adv4 = hw->mii_autoneg_adv_reg & ~MII_AR_SPEED_MASK; + adv4 = hw->mii_autoneg_adv_reg & ~ADVERTISE_ALL; adv9 = hw->mii_1000t_ctrl_reg & ~MII_AT001_CR_1000T_SPEED_MASK; if (hw->autoneg_advertised & ADVERTISE_10_HALF) - adv4 |= MII_AR_10T_HD_CAPS; + adv4 |= ADVERTISE_10HALF; if (hw->autoneg_advertised & ADVERTISE_10_FULL) - adv4 |= MII_AR_10T_FD_CAPS; + adv4 |= ADVERTISE_10FULL; if (hw->autoneg_advertised & ADVERTISE_100_HALF) - adv4 |= MII_AR_100TX_HD_CAPS; + adv4 |= ADVERTISE_100HALF; if (hw->autoneg_advertised & ADVERTISE_100_FULL) - adv4 |= MII_AR_100TX_FD_CAPS; + adv4 |= ADVERTISE_100FULL; if (hw->autoneg_advertised & ADVERTISE_1000_FULL) - adv9 |= MII_AT001_CR_1000T_FD_CAPS; + adv9 |= ADVERTISE_1000FULL; if (adv4 != hw->mii_autoneg_adv_reg || adv9 != hw->mii_1000t_ctrl_reg) { diff --git a/drivers/net/atl1e/atl1e_hw.c b/drivers/net/atl1e/atl1e_hw.c index 76cc043..923063d 100644 --- a/drivers/net/atl1e/atl1e_hw.c +++ b/drivers/net/atl1e/atl1e_hw.c @@ -318,7 +318,7 @@ static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw) * Advertisement Register (Address 4) and the 1000 mb speed bits in * the 1000Base-T control Register (Address 9). */ - mii_autoneg_adv_reg &= ~MII_AR_SPEED_MASK; + mii_autoneg_adv_reg &= ~ADVERTISE_ALL; mii_1000t_ctrl_reg &= ~MII_AT001_CR_1000T_SPEED_MASK; /* @@ -327,44 +327,37 @@ static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw) */ switch (hw->media_type) { case MEDIA_TYPE_AUTO_SENSOR: - mii_autoneg_adv_reg |= (MII_AR_10T_HD_CAPS | - MII_AR_10T_FD_CAPS | - MII_AR_100TX_HD_CAPS | - MII_AR_100TX_FD_CAPS); - hw->autoneg_advertised = ADVERTISE_10_HALF | - ADVERTISE_10_FULL | - ADVERTISE_100_HALF | - ADVERTISE_100_FULL; + mii_autoneg_adv_reg |= ADVERTISE_ALL; + hw->autoneg_advertised = ADVERTISE_ALL; if (hw->nic_type == athr_l1e) { - mii_1000t_ctrl_reg |= - MII_AT001_CR_1000T_FD_CAPS; + mii_1000t_ctrl_reg |= ADVERTISE_1000FULL; hw->autoneg_advertised |= ADVERTISE_1000_FULL; } break; case MEDIA_TYPE_100M_FULL: - mii_autoneg_adv_reg |= MII_AR_100TX_FD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_100FULL; hw->autoneg_advertised = ADVERTISE_100_FULL; break; case MEDIA_TYPE_100M_HALF: - mii_autoneg_adv_reg |= MII_AR_100TX_HD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_100_HALF; hw->autoneg_advertised = ADVERTISE_100_HALF; break; case MEDIA_TYPE_10M_FULL: - mii_autoneg_adv_reg |= MII_AR_10T_FD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_10_FULL; hw->autoneg_advertised = ADVERTISE_10_FULL; break; default: - mii_autoneg_adv_reg |= MII_AR_10T_HD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_10_HALF; hw->autoneg_advertised = ADVERTISE_10_HALF; break; } /* flow control fixed to enable all */ - mii_autoneg_adv_reg |= (MII_AR_ASM_DIR | MII_AR_PAUSE); + mii_autoneg_adv_reg |= (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP); hw->mii_autoneg_adv_reg = mii_autoneg_adv_reg; hw->mii_1000t_ctrl_reg = mii_1000t_ctrl_reg; @@ -374,7 +367,7 @@ static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw) return ret_val; if (hw->nic_type == athr_l1e || hw->nic_type == athr_l2e_revA) { - ret_val = atl1e_write_phy_reg(hw, MII_AT001_CR, + ret_val = atl1e_write_phy_reg(hw, MII_CTRL1000, mii_1000t_ctrl_reg); if (ret_val) return ret_val; @@ -397,7 +390,7 @@ int atl1e_phy_commit(struct atl1e_hw *hw) int ret_val; u16 phy_data; - phy_data = MII_CR_RESET | MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG; + phy_data = BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART; ret_val = atl1e_write_phy_reg(hw, MII_BMCR, phy_data); if (ret_val) { @@ -645,15 +638,14 @@ int atl1e_restart_autoneg(struct atl1e_hw *hw) return err; if (hw->nic_type == athr_l1e || hw->nic_type == athr_l2e_revA) { - err = atl1e_write_phy_reg(hw, MII_AT001_CR, + err = atl1e_write_phy_reg(hw, MII_CTRL1000, hw->mii_1000t_ctrl_reg); if (err) return err; } err = atl1e_write_phy_reg(hw, MII_BMCR, - MII_CR_RESET | MII_CR_AUTO_NEG_EN | - MII_CR_RESTART_AUTO_NEG); + BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART); return err; } diff --git a/drivers/net/atl1e/atl1e_hw.h b/drivers/net/atl1e/atl1e_hw.h index 5ea2f4d..74df16a 100644 --- a/drivers/net/atl1e/atl1e_hw.h +++ b/drivers/net/atl1e/atl1e_hw.h @@ -629,127 +629,24 @@ s32 atl1e_restart_autoneg(struct atl1e_hw *hw); /***************************** MII definition ***************************************/ /* PHY Common Register */ -#define MII_BMCR 0x00 -#define MII_BMSR 0x01 -#define MII_PHYSID1 0x02 -#define MII_PHYSID2 0x03 -#define MII_ADVERTISE 0x04 -#define MII_LPA 0x05 -#define MII_EXPANSION 0x06 -#define MII_AT001_CR 0x09 -#define MII_AT001_SR 0x0A -#define MII_AT001_ESR 0x0F #define MII_AT001_PSCR 0x10 #define MII_AT001_PSSR 0x11 #define MII_INT_CTRL 0x12 #define MII_INT_STATUS 0x13 #define MII_SMARTSPEED 0x14 -#define MII_RERRCOUNTER 0x15 -#define MII_SREVISION 0x16 -#define MII_RESV1 0x17 #define MII_LBRERROR 0x18 -#define MII_PHYADDR 0x19 #define MII_RESV2 0x1a -#define MII_TPISTATUS 0x1b -#define MII_NCONFIG 0x1c #define MII_DBG_ADDR 0x1D #define MII_DBG_DATA 0x1E - -/* PHY Control Register */ -#define MII_CR_SPEED_SELECT_MSB 0x0040 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define MII_CR_COLL_TEST_ENABLE 0x0080 /* Collision test enable */ -#define MII_CR_FULL_DUPLEX 0x0100 /* FDX =1, half duplex =0 */ -#define MII_CR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */ -#define MII_CR_ISOLATE 0x0400 /* Isolate PHY from MII */ -#define MII_CR_POWER_DOWN 0x0800 /* Power down */ -#define MII_CR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */ -#define MII_CR_SPEED_SELECT_LSB 0x2000 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define MII_CR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */ -#define MII_CR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */ -#define MII_CR_SPEED_MASK 0x2040 -#define MII_CR_SPEED_1000 0x0040 -#define MII_CR_SPEED_100 0x2000 -#define MII_CR_SPEED_10 0x0000 - - -/* PHY Status Register */ -#define MII_SR_EXTENDED_CAPS 0x0001 /* Extended register capabilities */ -#define MII_SR_JABBER_DETECT 0x0002 /* Jabber Detected */ -#define MII_SR_LINK_STATUS 0x0004 /* Link Status 1 = link */ -#define MII_SR_AUTONEG_CAPS 0x0008 /* Auto Neg Capable */ -#define MII_SR_REMOTE_FAULT 0x0010 /* Remote Fault Detect */ -#define MII_SR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */ -#define MII_SR_PREAMBLE_SUPPRESS 0x0040 /* Preamble may be suppressed */ -#define MII_SR_EXTENDED_STATUS 0x0100 /* Ext. status info in Reg 0x0F */ -#define MII_SR_100T2_HD_CAPS 0x0200 /* 100T2 Half Duplex Capable */ -#define MII_SR_100T2_FD_CAPS 0x0400 /* 100T2 Full Duplex Capable */ -#define MII_SR_10T_HD_CAPS 0x0800 /* 10T Half Duplex Capable */ -#define MII_SR_10T_FD_CAPS 0x1000 /* 10T Full Duplex Capable */ -#define MII_SR_100X_HD_CAPS 0x2000 /* 100X Half Duplex Capable */ -#define MII_SR_100X_FD_CAPS 0x4000 /* 100X Full Duplex Capable */ -#define MII_SR_100T4_CAPS 0x8000 /* 100T4 Capable */ - -/* Link partner ability register. */ -#define MII_LPA_SLCT 0x001f /* Same as advertise selector */ -#define MII_LPA_10HALF 0x0020 /* Can do 10mbps half-duplex */ -#define MII_LPA_10FULL 0x0040 /* Can do 10mbps full-duplex */ -#define MII_LPA_100HALF 0x0080 /* Can do 100mbps half-duplex */ -#define MII_LPA_100FULL 0x0100 /* Can do 100mbps full-duplex */ -#define MII_LPA_100BASE4 0x0200 /* 100BASE-T4 */ -#define MII_LPA_PAUSE 0x0400 /* PAUSE */ -#define MII_LPA_ASYPAUSE 0x0800 /* Asymmetrical PAUSE */ -#define MII_LPA_RFAULT 0x2000 /* Link partner faulted */ -#define MII_LPA_LPACK 0x4000 /* Link partner acked us */ -#define MII_LPA_NPAGE 0x8000 /* Next page bit */ - /* Autoneg Advertisement Register */ -#define MII_AR_SELECTOR_FIELD 0x0001 /* indicates IEEE 802.3 CSMA/CD */ -#define MII_AR_10T_HD_CAPS 0x0020 /* 10T Half Duplex Capable */ -#define MII_AR_10T_FD_CAPS 0x0040 /* 10T Full Duplex Capable */ -#define MII_AR_100TX_HD_CAPS 0x0080 /* 100TX Half Duplex Capable */ -#define MII_AR_100TX_FD_CAPS 0x0100 /* 100TX Full Duplex Capable */ -#define MII_AR_100T4_CAPS 0x0200 /* 100T4 Capable */ -#define MII_AR_PAUSE 0x0400 /* Pause operation desired */ -#define MII_AR_ASM_DIR 0x0800 /* Asymmetric Pause Direction bit */ -#define MII_AR_REMOTE_FAULT 0x2000 /* Remote Fault detected */ -#define MII_AR_NEXT_PAGE 0x8000 /* Next Page ability supported */ -#define MII_AR_SPEED_MASK 0x01E0 -#define MII_AR_DEFAULT_CAP_MASK 0x0DE0 +#define MII_AR_DEFAULT_CAP_MASK 0 /* 1000BASE-T Control Register */ -#define MII_AT001_CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */ -#define MII_AT001_CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */ -#define MII_AT001_CR_1000T_REPEATER_DTE 0x0400 /* 1=Repeater/switch device port */ -/* 0=DTE device */ -#define MII_AT001_CR_1000T_MS_VALUE 0x0800 /* 1=Configure PHY as Master */ -/* 0=Configure PHY as Slave */ -#define MII_AT001_CR_1000T_MS_ENABLE 0x1000 /* 1=Master/Slave manual config value */ -/* 0=Automatic Master/Slave config */ -#define MII_AT001_CR_1000T_TEST_MODE_NORMAL 0x0000 /* Normal Operation */ -#define MII_AT001_CR_1000T_TEST_MODE_1 0x2000 /* Transmit Waveform test */ -#define MII_AT001_CR_1000T_TEST_MODE_2 0x4000 /* Master Transmit Jitter test */ -#define MII_AT001_CR_1000T_TEST_MODE_3 0x6000 /* Slave Transmit Jitter test */ -#define MII_AT001_CR_1000T_TEST_MODE_4 0x8000 /* Transmitter Distortion test */ -#define MII_AT001_CR_1000T_SPEED_MASK 0x0300 -#define MII_AT001_CR_1000T_DEFAULT_CAP_MASK 0x0300 - -/* 1000BASE-T Status Register */ -#define MII_AT001_SR_1000T_LP_HD_CAPS 0x0400 /* LP is 1000T HD capable */ -#define MII_AT001_SR_1000T_LP_FD_CAPS 0x0800 /* LP is 1000T FD capable */ -#define MII_AT001_SR_1000T_REMOTE_RX_STATUS 0x1000 /* Remote receiver OK */ -#define MII_AT001_SR_1000T_LOCAL_RX_STATUS 0x2000 /* Local receiver OK */ -#define MII_AT001_SR_1000T_MS_CONFIG_RES 0x4000 /* 1=Local TX is Master, 0=Slave */ -#define MII_AT001_SR_1000T_MS_CONFIG_FAULT 0x8000 /* Master/Slave config fault */ -#define MII_AT001_SR_1000T_REMOTE_RX_STATUS_SHIFT 12 -#define MII_AT001_SR_1000T_LOCAL_RX_STATUS_SHIFT 13 - -/* Extended Status Register */ -#define MII_AT001_ESR_1000T_HD_CAPS 0x1000 /* 1000T HD capable */ -#define MII_AT001_ESR_1000T_FD_CAPS 0x2000 /* 1000T FD capable */ -#define MII_AT001_ESR_1000X_HD_CAPS 0x4000 /* 1000X HD capable */ -#define MII_AT001_ESR_1000X_FD_CAPS 0x8000 /* 1000X FD capable */ +#define MII_AT001_CR_1000T_SPEED_MASK \ + (ADVERTISE_1000FULL | ADVERTISE_1000HALF) +#define MII_AT001_CR_1000T_DEFAULT_CAP_MASK MII_AT001_CR_1000T_SPEED_MASK /* AT001 PHY Specific Control Register */ #define MII_AT001_PSCR_JABBER_DISABLE 0x0001 /* 1=Jabber Function disabled */ diff --git a/drivers/net/atl1e/atl1e_main.c b/drivers/net/atl1e/atl1e_main.c index e28f8ba..bf7500c 100644 --- a/drivers/net/atl1e/atl1e_main.c +++ b/drivers/net/atl1e/atl1e_main.c @@ -2051,9 +2051,9 @@ static int atl1e_suspend(struct pci_dev *pdev, pm_message_t state) atl1e_read_phy_reg(hw, MII_BMSR, (u16 *)&mii_bmsr_data); atl1e_read_phy_reg(hw, MII_BMSR, (u16 *)&mii_bmsr_data); - mii_advertise_data = MII_AR_10T_HD_CAPS; + mii_advertise_data = ADVERTISE_10HALF; - if ((atl1e_write_phy_reg(hw, MII_AT001_CR, 0) != 0) || + if ((atl1e_write_phy_reg(hw, MII_CTRL1000, 0) != 0) || (atl1e_write_phy_reg(hw, MII_ADVERTISE, mii_advertise_data) != 0) || (atl1e_phy_commit(hw)) != 0) { diff --git a/drivers/net/atlx/atl1.c b/drivers/net/atlx/atl1.c index 3b52768..67f40b9 100644 --- a/drivers/net/atlx/atl1.c +++ b/drivers/net/atlx/atl1.c @@ -950,6 +950,7 @@ static int __devinit atl1_sw_init(struct atl1_adapter *adapter) hw->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; adapter->wol = 0; + device_set_wakeup_enable(&adapter->pdev->dev, false); adapter->rx_buffer_len = (hw->max_frame_size + 7) & ~7; adapter->ict = 50000; /* 100ms */ adapter->link_speed = SPEED_0; /* hardware init */ @@ -2735,15 +2736,15 @@ static int atl1_close(struct net_device *netdev) } #ifdef CONFIG_PM -static int atl1_suspend(struct pci_dev *pdev, pm_message_t state) +static int atl1_suspend(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct atl1_adapter *adapter = netdev_priv(netdev); struct atl1_hw *hw = &adapter->hw; u32 ctrl = 0; u32 wufc = adapter->wol; u32 val; - int retval; u16 speed; u16 duplex; @@ -2751,17 +2752,15 @@ static int atl1_suspend(struct pci_dev *pdev, pm_message_t state) if (netif_running(netdev)) atl1_down(adapter); - retval = pci_save_state(pdev); - if (retval) - return retval; - atl1_read_phy_reg(hw, MII_BMSR, (u16 *) & ctrl); atl1_read_phy_reg(hw, MII_BMSR, (u16 *) & ctrl); val = ctrl & BMSR_LSTATUS; if (val) wufc &= ~ATLX_WUFC_LNKC; + if (!wufc) + goto disable_wol; - if (val && wufc) { + if (val) { val = atl1_get_speed_and_duplex(hw, &speed, &duplex); if (val) { if (netif_msg_ifdown(adapter)) @@ -2798,23 +2797,18 @@ static int atl1_suspend(struct pci_dev *pdev, pm_message_t state) ctrl |= PCIE_PHYMISC_FORCE_RCV_DET; iowrite32(ctrl, hw->hw_addr + REG_PCIE_PHYMISC); ioread32(hw->hw_addr + REG_PCIE_PHYMISC); - - pci_enable_wake(pdev, pci_choose_state(pdev, state), 1); - goto exit; - } - - if (!val && wufc) { + } else { ctrl |= (WOL_LINK_CHG_EN | WOL_LINK_CHG_PME_EN); iowrite32(ctrl, hw->hw_addr + REG_WOL_CTRL); ioread32(hw->hw_addr + REG_WOL_CTRL); iowrite32(0, hw->hw_addr + REG_MAC_CTRL); ioread32(hw->hw_addr + REG_MAC_CTRL); hw->phy_configured = false; - pci_enable_wake(pdev, pci_choose_state(pdev, state), 1); - goto exit; } -disable_wol: + return 0; + + disable_wol: iowrite32(0, hw->hw_addr + REG_WOL_CTRL); ioread32(hw->hw_addr + REG_WOL_CTRL); ctrl = ioread32(hw->hw_addr + REG_PCIE_PHYMISC); @@ -2822,37 +2816,17 @@ disable_wol: iowrite32(ctrl, hw->hw_addr + REG_PCIE_PHYMISC); ioread32(hw->hw_addr + REG_PCIE_PHYMISC); hw->phy_configured = false; - pci_enable_wake(pdev, pci_choose_state(pdev, state), 0); -exit: - if (netif_running(netdev)) - pci_disable_msi(adapter->pdev); - pci_disable_device(pdev); - pci_set_power_state(pdev, pci_choose_state(pdev, state)); return 0; } -static int atl1_resume(struct pci_dev *pdev) +static int atl1_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct atl1_adapter *adapter = netdev_priv(netdev); - u32 err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - err = pci_enable_device(pdev); - if (err) { - if (netif_msg_ifup(adapter)) - dev_printk(KERN_DEBUG, &pdev->dev, - "error enabling pci device\n"); - return err; - } - - pci_set_master(pdev); iowrite32(0, adapter->hw.hw_addr + REG_WOL_CTRL); - pci_enable_wake(pdev, PCI_D3hot, 0); - pci_enable_wake(pdev, PCI_D3cold, 0); atl1_reset_hw(&adapter->hw); @@ -2864,16 +2838,25 @@ static int atl1_resume(struct pci_dev *pdev) return 0; } + +static SIMPLE_DEV_PM_OPS(atl1_pm_ops, atl1_suspend, atl1_resume); +#define ATL1_PM_OPS (&atl1_pm_ops) + #else -#define atl1_suspend NULL -#define atl1_resume NULL + +static int atl1_suspend(struct device *dev) { return 0; } + +#define ATL1_PM_OPS NULL #endif static void atl1_shutdown(struct pci_dev *pdev) { -#ifdef CONFIG_PM - atl1_suspend(pdev, PMSG_SUSPEND); -#endif + struct net_device *netdev = pci_get_drvdata(pdev); + struct atl1_adapter *adapter = netdev_priv(netdev); + + atl1_suspend(&pdev->dev); + pci_wake_from_d3(pdev, adapter->wol); + pci_set_power_state(pdev, PCI_D3hot); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -3117,9 +3100,8 @@ static struct pci_driver atl1_driver = { .id_table = atl1_pci_tbl, .probe = atl1_probe, .remove = __devexit_p(atl1_remove), - .suspend = atl1_suspend, - .resume = atl1_resume, - .shutdown = atl1_shutdown + .shutdown = atl1_shutdown, + .driver.pm = ATL1_PM_OPS, }; /* @@ -3409,6 +3391,9 @@ static int atl1_set_wol(struct net_device *netdev, adapter->wol = 0; if (wol->wolopts & WAKE_MAGIC) adapter->wol |= ATLX_WUFC_MAG; + + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + return 0; } diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index add0b93..3a800e2 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -450,9 +450,8 @@ static inline void be_vf_eth_addr_generate(struct be_adapter *adapter, u8 *mac) mac[5] = (u8)(addr & 0xFF); mac[4] = (u8)((addr >> 8) & 0xFF); mac[3] = (u8)((addr >> 16) & 0xFF); - mac[2] = 0xC9; - mac[1] = 0x00; - mac[0] = 0x00; + /* Use the OUI from the current MAC address */ + memcpy(mac, adapter->netdev->dev_addr, 3); } extern void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index a179cc6..619ebc2 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -23,6 +23,12 @@ static void be_mcc_notify(struct be_adapter *adapter) struct be_queue_info *mccq = &adapter->mcc_obj.q; u32 val = 0; + if (adapter->eeh_err) { + dev_info(&adapter->pdev->dev, + "Error in Card Detected! Cannot issue commands\n"); + return; + } + val |= mccq->id & DB_MCCQ_RING_ID_MASK; val |= 1 << DB_MCCQ_NUM_POSTED_SHIFT; @@ -102,6 +108,7 @@ static void be_async_grp5_cos_priority_process(struct be_adapter *adapter, { if (evt->valid) { adapter->vlan_prio_bmap = evt->available_priority_bmap; + adapter->recommended_prio &= ~VLAN_PRIO_MASK; adapter->recommended_prio = evt->reco_default_priority << VLAN_PRIO_SHIFT; } @@ -216,6 +223,9 @@ static int be_mcc_wait_compl(struct be_adapter *adapter) int i, num, status = 0; struct be_mcc_obj *mcc_obj = &adapter->mcc_obj; + if (adapter->eeh_err) + return -EIO; + for (i = 0; i < mcc_timeout; i++) { num = be_process_mcc(adapter, &status); if (num) @@ -245,6 +255,12 @@ static int be_mbox_db_ready_wait(struct be_adapter *adapter, void __iomem *db) int msecs = 0; u32 ready; + if (adapter->eeh_err) { + dev_err(&adapter->pdev->dev, + "Error detected in card.Cannot issue commands\n"); + return -EIO; + } + do { ready = ioread32(db); if (ready == 0xffffffff) { @@ -598,7 +614,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, /* Uses synchronous MCCQ */ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, - u32 if_id, u32 *pmac_id) + u32 if_id, u32 *pmac_id, u32 domain) { struct be_mcc_wrb *wrb; struct be_cmd_req_pmac_add *req; @@ -619,6 +635,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_PMAC_ADD, sizeof(*req)); + req->hdr.domain = domain; req->if_id = cpu_to_le32(if_id); memcpy(req->mac_address, mac_addr, ETH_ALEN); @@ -634,7 +651,7 @@ err: } /* Uses synchronous MCCQ */ -int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id) +int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id, u32 dom) { struct be_mcc_wrb *wrb; struct be_cmd_req_pmac_del *req; @@ -655,6 +672,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id) be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_PMAC_DEL, sizeof(*req)); + req->hdr.domain = dom; req->if_id = cpu_to_le32(if_id); req->pmac_id = cpu_to_le32(pmac_id); @@ -995,7 +1013,7 @@ int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags, } /* Uses mbox */ -int be_cmd_if_destroy(struct be_adapter *adapter, u32 interface_id) +int be_cmd_if_destroy(struct be_adapter *adapter, u32 interface_id, u32 domain) { struct be_mcc_wrb *wrb; struct be_cmd_req_if_destroy *req; @@ -1016,6 +1034,7 @@ int be_cmd_if_destroy(struct be_adapter *adapter, u32 interface_id) be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_INTERFACE_DESTROY, sizeof(*req)); + req->hdr.domain = domain; req->interface_id = cpu_to_le32(interface_id); status = be_mbox_notify_wait(adapter); @@ -1868,8 +1887,8 @@ int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain) OPCODE_COMMON_SET_QOS, sizeof(*req)); req->hdr.domain = domain; - req->valid_bits = BE_QOS_BITS_NIC; - req->max_bps_nic = bps; + req->valid_bits = cpu_to_le32(BE_QOS_BITS_NIC); + req->max_bps_nic = cpu_to_le32(bps); status = be_mcc_notify_wait(adapter); diff --git a/drivers/net/benet/be_cmds.h b/drivers/net/benet/be_cmds.h index 83d15c8..91c5d2b 100644 --- a/drivers/net/benet/be_cmds.h +++ b/drivers/net/benet/be_cmds.h @@ -999,12 +999,14 @@ extern int be_cmd_POST(struct be_adapter *adapter); extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, u8 type, bool permanent, u32 if_handle); extern int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, - u32 if_id, u32 *pmac_id); -extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id); + u32 if_id, u32 *pmac_id, u32 domain); +extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, + u32 pmac_id, u32 domain); extern int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags, u8 *mac, bool pmac_invalid, u32 *if_handle, u32 *pmac_id, u32 domain); -extern int be_cmd_if_destroy(struct be_adapter *adapter, u32 if_handle); +extern int be_cmd_if_destroy(struct be_adapter *adapter, u32 if_handle, + u32 domain); extern int be_cmd_eq_create(struct be_adapter *adapter, struct be_queue_info *eq, int eq_delay); extern int be_cmd_cq_create(struct be_adapter *adapter, diff --git a/drivers/net/benet/be_ethtool.c b/drivers/net/benet/be_ethtool.c index b4be027..07b4ab9 100644 --- a/drivers/net/benet/be_ethtool.c +++ b/drivers/net/benet/be_ethtool.c @@ -376,8 +376,9 @@ static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) } phy_cmd.size = sizeof(struct be_cmd_req_get_phy_info); - phy_cmd.va = pci_alloc_consistent(adapter->pdev, phy_cmd.size, - &phy_cmd.dma); + phy_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, + phy_cmd.size, &phy_cmd.dma, + GFP_KERNEL); if (!phy_cmd.va) { dev_err(&adapter->pdev->dev, "Memory alloc failure\n"); return -ENOMEM; @@ -416,8 +417,8 @@ static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) adapter->port_type = ecmd->port; adapter->transceiver = ecmd->transceiver; adapter->autoneg = ecmd->autoneg; - pci_free_consistent(adapter->pdev, phy_cmd.size, - phy_cmd.va, phy_cmd.dma); + dma_free_coherent(&adapter->pdev->dev, phy_cmd.size, phy_cmd.va, + phy_cmd.dma); } else { ecmd->speed = adapter->link_speed; ecmd->port = adapter->port_type; @@ -515,12 +516,23 @@ be_phys_id(struct net_device *netdev, u32 data) return status; } +static bool +be_is_wol_supported(struct be_adapter *adapter) +{ + if (!be_physfn(adapter)) + return false; + else + return true; +} + static void be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct be_adapter *adapter = netdev_priv(netdev); - wol->supported = WAKE_MAGIC; + if (be_is_wol_supported(adapter)) + wol->supported = WAKE_MAGIC; + if (adapter->wol) wol->wolopts = WAKE_MAGIC; else @@ -536,7 +548,7 @@ be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) if (wol->wolopts & ~WAKE_MAGIC) return -EINVAL; - if (wol->wolopts & WAKE_MAGIC) + if ((wol->wolopts & WAKE_MAGIC) && be_is_wol_supported(adapter)) adapter->wol = true; else adapter->wol = false; @@ -554,8 +566,8 @@ be_test_ddr_dma(struct be_adapter *adapter) }; ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test); - ddrdma_cmd.va = pci_alloc_consistent(adapter->pdev, ddrdma_cmd.size, - &ddrdma_cmd.dma); + ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size, + &ddrdma_cmd.dma, GFP_KERNEL); if (!ddrdma_cmd.va) { dev_err(&adapter->pdev->dev, "Memory allocation failure\n"); return -ENOMEM; @@ -569,8 +581,8 @@ be_test_ddr_dma(struct be_adapter *adapter) } err: - pci_free_consistent(adapter->pdev, ddrdma_cmd.size, - ddrdma_cmd.va, ddrdma_cmd.dma); + dma_free_coherent(&adapter->pdev->dev, ddrdma_cmd.size, ddrdma_cmd.va, + ddrdma_cmd.dma); return ret; } @@ -662,8 +674,8 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem)); eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read); - eeprom_cmd.va = pci_alloc_consistent(adapter->pdev, eeprom_cmd.size, - &eeprom_cmd.dma); + eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size, + &eeprom_cmd.dma, GFP_KERNEL); if (!eeprom_cmd.va) { dev_err(&adapter->pdev->dev, @@ -677,8 +689,8 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, resp = (struct be_cmd_resp_seeprom_read *) eeprom_cmd.va; memcpy(data, resp->seeprom_data + eeprom->offset, eeprom->len); } - pci_free_consistent(adapter->pdev, eeprom_cmd.size, eeprom_cmd.va, - eeprom_cmd.dma); + dma_free_coherent(&adapter->pdev->dev, eeprom_cmd.size, eeprom_cmd.va, + eeprom_cmd.dma); return status; } diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 28a32a6..aad7ea3 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -125,8 +125,8 @@ static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q) { struct be_dma_mem *mem = &q->dma_mem; if (mem->va) - pci_free_consistent(adapter->pdev, mem->size, - mem->va, mem->dma); + dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va, + mem->dma); } static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q, @@ -138,7 +138,8 @@ static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q, q->len = len; q->entry_size = entry_size; mem->size = len * entry_size; - mem->va = pci_alloc_consistent(adapter->pdev, mem->size, &mem->dma); + mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma, + GFP_KERNEL); if (!mem->va) return -1; memset(mem->va, 0, mem->size); @@ -235,12 +236,13 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) if (!be_physfn(adapter)) goto netdev_addr; - status = be_cmd_pmac_del(adapter, adapter->if_handle, adapter->pmac_id); + status = be_cmd_pmac_del(adapter, adapter->if_handle, + adapter->pmac_id, 0); if (status) return status; status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data, - adapter->if_handle, &adapter->pmac_id); + adapter->if_handle, &adapter->pmac_id, 0); netdev_addr: if (!status) memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); @@ -484,7 +486,7 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr, AMAP_SET_BITS(struct amap_eth_hdr_wrb, len, hdr, len); } -static void unmap_tx_frag(struct pci_dev *pdev, struct be_eth_wrb *wrb, +static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb, bool unmap_single) { dma_addr_t dma; @@ -494,11 +496,10 @@ static void unmap_tx_frag(struct pci_dev *pdev, struct be_eth_wrb *wrb, dma = (u64)wrb->frag_pa_hi << 32 | (u64)wrb->frag_pa_lo; if (wrb->frag_len) { if (unmap_single) - pci_unmap_single(pdev, dma, wrb->frag_len, - PCI_DMA_TODEVICE); + dma_unmap_single(dev, dma, wrb->frag_len, + DMA_TO_DEVICE); else - pci_unmap_page(pdev, dma, wrb->frag_len, - PCI_DMA_TODEVICE); + dma_unmap_page(dev, dma, wrb->frag_len, DMA_TO_DEVICE); } } @@ -507,7 +508,7 @@ static int make_tx_wrbs(struct be_adapter *adapter, { dma_addr_t busaddr; int i, copied = 0; - struct pci_dev *pdev = adapter->pdev; + struct device *dev = &adapter->pdev->dev; struct sk_buff *first_skb = skb; struct be_queue_info *txq = &adapter->tx_obj.q; struct be_eth_wrb *wrb; @@ -521,9 +522,8 @@ static int make_tx_wrbs(struct be_adapter *adapter, if (skb->len > skb->data_len) { int len = skb_headlen(skb); - busaddr = pci_map_single(pdev, skb->data, len, - PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(pdev, busaddr)) + busaddr = dma_map_single(dev, skb->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(dev, busaddr)) goto dma_err; map_single = true; wrb = queue_head_node(txq); @@ -536,10 +536,9 @@ static int make_tx_wrbs(struct be_adapter *adapter, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; - busaddr = pci_map_page(pdev, frag->page, - frag->page_offset, - frag->size, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(pdev, busaddr)) + busaddr = dma_map_page(dev, frag->page, frag->page_offset, + frag->size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, busaddr)) goto dma_err; wrb = queue_head_node(txq); wrb_fill(wrb, busaddr, frag->size); @@ -563,7 +562,7 @@ dma_err: txq->head = map_head; while (copied) { wrb = queue_head_node(txq); - unmap_tx_frag(pdev, wrb, map_single); + unmap_tx_frag(dev, wrb, map_single); map_single = false; copied -= wrb->frag_len; queue_head_inc(txq); @@ -743,11 +742,11 @@ static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (adapter->vf_cfg[vf].vf_pmac_id != BE_INVALID_PMAC_ID) status = be_cmd_pmac_del(adapter, adapter->vf_cfg[vf].vf_if_handle, - adapter->vf_cfg[vf].vf_pmac_id); + adapter->vf_cfg[vf].vf_pmac_id, vf + 1); status = be_cmd_pmac_add(adapter, mac, adapter->vf_cfg[vf].vf_if_handle, - &adapter->vf_cfg[vf].vf_pmac_id); + &adapter->vf_cfg[vf].vf_pmac_id, vf + 1); if (status) dev_err(&adapter->pdev->dev, "MAC %pM set on VF %d Failed\n", @@ -822,7 +821,7 @@ static int be_set_vf_tx_rate(struct net_device *netdev, rate = 10000; adapter->vf_cfg[vf].vf_tx_rate = rate; - status = be_cmd_set_qos(adapter, rate / 10, vf); + status = be_cmd_set_qos(adapter, rate / 10, vf + 1); if (status) dev_info(&adapter->pdev->dev, @@ -888,8 +887,9 @@ get_rx_page_info(struct be_adapter *adapter, BUG_ON(!rx_page_info->page); if (rx_page_info->last_page_user) { - pci_unmap_page(adapter->pdev, dma_unmap_addr(rx_page_info, bus), - adapter->big_page_size, PCI_DMA_FROMDEVICE); + dma_unmap_page(&adapter->pdev->dev, + dma_unmap_addr(rx_page_info, bus), + adapter->big_page_size, DMA_FROM_DEVICE); rx_page_info->last_page_user = false; } @@ -1195,9 +1195,9 @@ static void be_post_rx_frags(struct be_rx_obj *rxo) rxo->stats.rx_post_fail++; break; } - page_dmaaddr = pci_map_page(adapter->pdev, pagep, 0, - adapter->big_page_size, - PCI_DMA_FROMDEVICE); + page_dmaaddr = dma_map_page(&adapter->pdev->dev, pagep, + 0, adapter->big_page_size, + DMA_FROM_DEVICE); page_info->page_offset = 0; } else { get_page(pagep); @@ -1270,8 +1270,8 @@ static void be_tx_compl_process(struct be_adapter *adapter, u16 last_index) do { cur_index = txq->tail; wrb = queue_tail_node(txq); - unmap_tx_frag(adapter->pdev, wrb, (unmap_skb_hdr && - skb_headlen(sent_skb))); + unmap_tx_frag(&adapter->pdev->dev, wrb, + (unmap_skb_hdr && skb_headlen(sent_skb))); unmap_skb_hdr = false; num_wrbs++; @@ -1827,6 +1827,7 @@ void be_detect_dump_ue(struct be_adapter *adapter) if (ue_status_lo || ue_status_hi) { adapter->ue_detected = true; + adapter->eeh_err = true; dev_err(&adapter->pdev->dev, "UE Detected!!\n"); } @@ -1865,6 +1866,10 @@ static void be_worker(struct work_struct *work) struct be_mcc_obj *mcc_obj = &adapter->mcc_obj; be_cq_notify(adapter, mcc_obj->cq.id, false, mcc_compl); } + + if (!adapter->ue_detected && !lancer_chip(adapter)) + be_detect_dump_ue(adapter); + goto reschedule; } @@ -2179,7 +2184,8 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable) memset(mac, 0, ETH_ALEN); cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config); - cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma); + cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma, + GFP_KERNEL); if (cmd.va == NULL) return -1; memset(cmd.va, 0, cmd.size); @@ -2190,8 +2196,8 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable) if (status) { dev_err(&adapter->pdev->dev, "Could not enable Wake-on-lan\n"); - pci_free_consistent(adapter->pdev, cmd.size, cmd.va, - cmd.dma); + dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, + cmd.dma); return status; } status = be_cmd_enable_magic_wol(adapter, @@ -2204,7 +2210,7 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable) pci_enable_wake(adapter->pdev, PCI_D3cold, 0); } - pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma); + dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma); return status; } @@ -2225,7 +2231,8 @@ static inline int be_vf_eth_addr_config(struct be_adapter *adapter) for (vf = 0; vf < num_vfs; vf++) { status = be_cmd_pmac_add(adapter, mac, adapter->vf_cfg[vf].vf_if_handle, - &adapter->vf_cfg[vf].vf_pmac_id); + &adapter->vf_cfg[vf].vf_pmac_id, + vf + 1); if (status) dev_err(&adapter->pdev->dev, "Mac address add failed for VF %d\n", vf); @@ -2245,7 +2252,7 @@ static inline void be_vf_eth_addr_rem(struct be_adapter *adapter) if (adapter->vf_cfg[vf].vf_pmac_id != BE_INVALID_PMAC_ID) be_cmd_pmac_del(adapter, adapter->vf_cfg[vf].vf_if_handle, - adapter->vf_cfg[vf].vf_pmac_id); + adapter->vf_cfg[vf].vf_pmac_id, vf + 1); } } @@ -2277,22 +2284,26 @@ static int be_setup(struct be_adapter *adapter) goto do_none; if (be_physfn(adapter)) { - while (vf < num_vfs) { - cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED - | BE_IF_FLAGS_BROADCAST; - status = be_cmd_if_create(adapter, cap_flags, en_flags, - mac, true, + if (adapter->sriov_enabled) { + while (vf < num_vfs) { + cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED | + BE_IF_FLAGS_BROADCAST; + status = be_cmd_if_create(adapter, cap_flags, + en_flags, mac, true, &adapter->vf_cfg[vf].vf_if_handle, NULL, vf+1); - if (status) { - dev_err(&adapter->pdev->dev, - "Interface Create failed for VF %d\n", vf); - goto if_destroy; + if (status) { + dev_err(&adapter->pdev->dev, + "Interface Create failed for VF %d\n", + vf); + goto if_destroy; + } + adapter->vf_cfg[vf].vf_pmac_id = + BE_INVALID_PMAC_ID; + vf++; } - adapter->vf_cfg[vf].vf_pmac_id = BE_INVALID_PMAC_ID; - vf++; } - } else if (!be_physfn(adapter)) { + } else { status = be_cmd_mac_addr_query(adapter, mac, MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle); if (!status) { @@ -2313,44 +2324,46 @@ static int be_setup(struct be_adapter *adapter) if (status != 0) goto rx_qs_destroy; - if (be_physfn(adapter)) { - status = be_vf_eth_addr_config(adapter); - if (status) - goto mcc_q_destroy; - } - adapter->link_speed = -1; return 0; -mcc_q_destroy: - if (be_physfn(adapter)) - be_vf_eth_addr_rem(adapter); be_mcc_queues_destroy(adapter); rx_qs_destroy: be_rx_queues_destroy(adapter); tx_qs_destroy: be_tx_queues_destroy(adapter); if_destroy: - for (vf = 0; vf < num_vfs; vf++) - if (adapter->vf_cfg[vf].vf_if_handle) - be_cmd_if_destroy(adapter, - adapter->vf_cfg[vf].vf_if_handle); - be_cmd_if_destroy(adapter, adapter->if_handle); + if (be_physfn(adapter) && adapter->sriov_enabled) + for (vf = 0; vf < num_vfs; vf++) + if (adapter->vf_cfg[vf].vf_if_handle) + be_cmd_if_destroy(adapter, + adapter->vf_cfg[vf].vf_if_handle, + vf + 1); + be_cmd_if_destroy(adapter, adapter->if_handle, 0); do_none: return status; } static int be_clear(struct be_adapter *adapter) { - if (be_physfn(adapter)) + int vf; + + if (be_physfn(adapter) && adapter->sriov_enabled) be_vf_eth_addr_rem(adapter); be_mcc_queues_destroy(adapter); be_rx_queues_destroy(adapter); be_tx_queues_destroy(adapter); - be_cmd_if_destroy(adapter, adapter->if_handle); + if (be_physfn(adapter) && adapter->sriov_enabled) + for (vf = 0; vf < num_vfs; vf++) + if (adapter->vf_cfg[vf].vf_if_handle) + be_cmd_if_destroy(adapter, + adapter->vf_cfg[vf].vf_if_handle, + vf + 1); + + be_cmd_if_destroy(adapter, adapter->if_handle, 0); /* tell fw we're done with firing cmds */ be_cmd_fw_clean(adapter); @@ -2453,8 +2466,8 @@ static int be_flash_data(struct be_adapter *adapter, continue; if ((pflashcomp[i].optype == IMG_TYPE_REDBOOT) && (!be_flash_redboot(adapter, fw->data, - pflashcomp[i].offset, pflashcomp[i].size, - filehdr_size))) + pflashcomp[i].offset, pflashcomp[i].size, filehdr_size + + (num_of_images * sizeof(struct image_hdr))))) continue; p = fw->data; p += filehdr_size + pflashcomp[i].offset @@ -2528,8 +2541,8 @@ int be_load_fw(struct be_adapter *adapter, u8 *func) dev_info(&adapter->pdev->dev, "Flashing firmware file %s\n", fw_file); flash_cmd.size = sizeof(struct be_cmd_write_flashrom) + 32*1024; - flash_cmd.va = pci_alloc_consistent(adapter->pdev, flash_cmd.size, - &flash_cmd.dma); + flash_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, flash_cmd.size, + &flash_cmd.dma, GFP_KERNEL); if (!flash_cmd.va) { status = -ENOMEM; dev_err(&adapter->pdev->dev, @@ -2558,8 +2571,8 @@ int be_load_fw(struct be_adapter *adapter, u8 *func) status = -1; } - pci_free_consistent(adapter->pdev, flash_cmd.size, flash_cmd.va, - flash_cmd.dma); + dma_free_coherent(&adapter->pdev->dev, flash_cmd.size, flash_cmd.va, + flash_cmd.dma); if (status) { dev_err(&adapter->pdev->dev, "Firmware load error\n"); goto fw_exit; @@ -2700,13 +2713,13 @@ static void be_ctrl_cleanup(struct be_adapter *adapter) be_unmap_pci_bars(adapter); if (mem->va) - pci_free_consistent(adapter->pdev, mem->size, - mem->va, mem->dma); + dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va, + mem->dma); mem = &adapter->mc_cmd_mem; if (mem->va) - pci_free_consistent(adapter->pdev, mem->size, - mem->va, mem->dma); + dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va, + mem->dma); } static int be_ctrl_init(struct be_adapter *adapter) @@ -2721,8 +2734,10 @@ static int be_ctrl_init(struct be_adapter *adapter) goto done; mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16; - mbox_mem_alloc->va = pci_alloc_consistent(adapter->pdev, - mbox_mem_alloc->size, &mbox_mem_alloc->dma); + mbox_mem_alloc->va = dma_alloc_coherent(&adapter->pdev->dev, + mbox_mem_alloc->size, + &mbox_mem_alloc->dma, + GFP_KERNEL); if (!mbox_mem_alloc->va) { status = -ENOMEM; goto unmap_pci_bars; @@ -2734,8 +2749,9 @@ static int be_ctrl_init(struct be_adapter *adapter) memset(mbox_mem_align->va, 0, sizeof(struct be_mcc_mailbox)); mc_cmd_mem->size = sizeof(struct be_cmd_req_mcast_mac_config); - mc_cmd_mem->va = pci_alloc_consistent(adapter->pdev, mc_cmd_mem->size, - &mc_cmd_mem->dma); + mc_cmd_mem->va = dma_alloc_coherent(&adapter->pdev->dev, + mc_cmd_mem->size, &mc_cmd_mem->dma, + GFP_KERNEL); if (mc_cmd_mem->va == NULL) { status = -ENOMEM; goto free_mbox; @@ -2751,8 +2767,8 @@ static int be_ctrl_init(struct be_adapter *adapter) return 0; free_mbox: - pci_free_consistent(adapter->pdev, mbox_mem_alloc->size, - mbox_mem_alloc->va, mbox_mem_alloc->dma); + dma_free_coherent(&adapter->pdev->dev, mbox_mem_alloc->size, + mbox_mem_alloc->va, mbox_mem_alloc->dma); unmap_pci_bars: be_unmap_pci_bars(adapter); @@ -2766,8 +2782,8 @@ static void be_stats_cleanup(struct be_adapter *adapter) struct be_dma_mem *cmd = &adapter->stats_cmd; if (cmd->va) - pci_free_consistent(adapter->pdev, cmd->size, - cmd->va, cmd->dma); + dma_free_coherent(&adapter->pdev->dev, cmd->size, + cmd->va, cmd->dma); } static int be_stats_init(struct be_adapter *adapter) @@ -2775,7 +2791,8 @@ static int be_stats_init(struct be_adapter *adapter) struct be_dma_mem *cmd = &adapter->stats_cmd; cmd->size = sizeof(struct be_cmd_req_get_stats); - cmd->va = pci_alloc_consistent(adapter->pdev, cmd->size, &cmd->dma); + cmd->va = dma_alloc_coherent(&adapter->pdev->dev, cmd->size, &cmd->dma, + GFP_KERNEL); if (cmd->va == NULL) return -1; memset(cmd->va, 0, cmd->size); @@ -2918,11 +2935,11 @@ static int __devinit be_probe(struct pci_dev *pdev, adapter->netdev = netdev; SET_NETDEV_DEV(netdev, &pdev->dev); - status = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (!status) { netdev->features |= NETIF_F_HIGHDMA; } else { - status = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (status) { dev_err(&pdev->dev, "Could not set PCI DMA Mask\n"); goto free_netdev; @@ -2947,11 +2964,9 @@ static int __devinit be_probe(struct pci_dev *pdev, if (status) goto ctrl_clean; - if (be_physfn(adapter)) { - status = be_cmd_reset_function(adapter); - if (status) - goto ctrl_clean; - } + status = be_cmd_reset_function(adapter); + if (status) + goto ctrl_clean; status = be_stats_init(adapter); if (status) @@ -2975,10 +2990,18 @@ static int __devinit be_probe(struct pci_dev *pdev, goto unsetup; netif_carrier_off(netdev); + if (be_physfn(adapter) && adapter->sriov_enabled) { + status = be_vf_eth_addr_config(adapter); + if (status) + goto unreg_netdev; + } + dev_info(&pdev->dev, "%s port %d\n", nic_name(pdev), adapter->port_num); schedule_delayed_work(&adapter->work, msecs_to_jiffies(100)); return 0; +unreg_netdev: + unregister_netdev(netdev); unsetup: be_clear(adapter); msix_disable: @@ -3005,6 +3028,7 @@ static int be_suspend(struct pci_dev *pdev, pm_message_t state) struct be_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; + cancel_delayed_work_sync(&adapter->work); if (adapter->wol) be_setup_wol(adapter, true); @@ -3017,6 +3041,7 @@ static int be_suspend(struct pci_dev *pdev, pm_message_t state) be_cmd_get_flow_control(adapter, &adapter->tx_fc, &adapter->rx_fc); be_clear(adapter); + be_msix_disable(adapter); pci_save_state(pdev); pci_disable_device(pdev); pci_set_power_state(pdev, pci_choose_state(pdev, state)); @@ -3038,6 +3063,7 @@ static int be_resume(struct pci_dev *pdev) pci_set_power_state(pdev, 0); pci_restore_state(pdev); + be_msix_enable(adapter); /* tell fw we're ready to fire cmds */ status = be_cmd_fw_init(adapter); if (status) @@ -3053,6 +3079,8 @@ static int be_resume(struct pci_dev *pdev) if (adapter->wol) be_setup_wol(adapter, false); + + schedule_delayed_work(&adapter->work, msecs_to_jiffies(100)); return 0; } @@ -3064,6 +3092,9 @@ static void be_shutdown(struct pci_dev *pdev) struct be_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; + if (netif_running(netdev)) + cancel_delayed_work_sync(&adapter->work); + netif_device_detach(netdev); be_cmd_reset_function(adapter); diff --git a/drivers/net/bna/bnad.c b/drivers/net/bna/bnad.c index fad9126..9f356d5 100644 --- a/drivers/net/bna/bnad.c +++ b/drivers/net/bna/bnad.c @@ -126,22 +126,22 @@ bnad_free_all_txbufs(struct bnad *bnad, } unmap_array[unmap_cons].skb = NULL; - pci_unmap_single(bnad->pcidev, - pci_unmap_addr(&unmap_array[unmap_cons], + dma_unmap_single(&bnad->pcidev->dev, + dma_unmap_addr(&unmap_array[unmap_cons], dma_addr), skb_headlen(skb), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); - pci_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, 0); + dma_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, 0); if (++unmap_cons >= unmap_q->q_depth) break; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - pci_unmap_page(bnad->pcidev, - pci_unmap_addr(&unmap_array[unmap_cons], + dma_unmap_page(&bnad->pcidev->dev, + dma_unmap_addr(&unmap_array[unmap_cons], dma_addr), skb_shinfo(skb)->frags[i].size, - PCI_DMA_TODEVICE); - pci_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, + DMA_TO_DEVICE); + dma_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, 0); if (++unmap_cons >= unmap_q->q_depth) break; @@ -199,23 +199,23 @@ bnad_free_txbufs(struct bnad *bnad, sent_bytes += skb->len; wis -= BNA_TXQ_WI_NEEDED(1 + skb_shinfo(skb)->nr_frags); - pci_unmap_single(bnad->pcidev, - pci_unmap_addr(&unmap_array[unmap_cons], + dma_unmap_single(&bnad->pcidev->dev, + dma_unmap_addr(&unmap_array[unmap_cons], dma_addr), skb_headlen(skb), - PCI_DMA_TODEVICE); - pci_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, 0); + DMA_TO_DEVICE); + dma_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, 0); BNA_QE_INDX_ADD(unmap_cons, 1, unmap_q->q_depth); prefetch(&unmap_array[unmap_cons + 1]); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { prefetch(&unmap_array[unmap_cons + 1]); - pci_unmap_page(bnad->pcidev, - pci_unmap_addr(&unmap_array[unmap_cons], + dma_unmap_page(&bnad->pcidev->dev, + dma_unmap_addr(&unmap_array[unmap_cons], dma_addr), skb_shinfo(skb)->frags[i].size, - PCI_DMA_TODEVICE); - pci_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, + DMA_TO_DEVICE); + dma_unmap_addr_set(&unmap_array[unmap_cons], dma_addr, 0); BNA_QE_INDX_ADD(unmap_cons, 1, unmap_q->q_depth); } @@ -340,19 +340,22 @@ static void bnad_free_all_rxbufs(struct bnad *bnad, struct bna_rcb *rcb) { struct bnad_unmap_q *unmap_q; + struct bnad_skb_unmap *unmap_array; struct sk_buff *skb; int unmap_cons; unmap_q = rcb->unmap_q; + unmap_array = unmap_q->unmap_array; for (unmap_cons = 0; unmap_cons < unmap_q->q_depth; unmap_cons++) { - skb = unmap_q->unmap_array[unmap_cons].skb; + skb = unmap_array[unmap_cons].skb; if (!skb) continue; - unmap_q->unmap_array[unmap_cons].skb = NULL; - pci_unmap_single(bnad->pcidev, pci_unmap_addr(&unmap_q-> - unmap_array[unmap_cons], - dma_addr), rcb->rxq->buffer_size, - PCI_DMA_FROMDEVICE); + unmap_array[unmap_cons].skb = NULL; + dma_unmap_single(&bnad->pcidev->dev, + dma_unmap_addr(&unmap_array[unmap_cons], + dma_addr), + rcb->rxq->buffer_size, + DMA_FROM_DEVICE); dev_kfree_skb(skb); } bnad_reset_rcb(bnad, rcb); @@ -391,9 +394,10 @@ bnad_alloc_n_post_rxbufs(struct bnad *bnad, struct bna_rcb *rcb) skb->dev = bnad->netdev; skb_reserve(skb, NET_IP_ALIGN); unmap_array[unmap_prod].skb = skb; - dma_addr = pci_map_single(bnad->pcidev, skb->data, - rcb->rxq->buffer_size, PCI_DMA_FROMDEVICE); - pci_unmap_addr_set(&unmap_array[unmap_prod], dma_addr, + dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data, + rcb->rxq->buffer_size, + DMA_FROM_DEVICE); + dma_unmap_addr_set(&unmap_array[unmap_prod], dma_addr, dma_addr); BNA_SET_DMA_ADDR(dma_addr, &rxent->host_addr); BNA_QE_INDX_ADD(unmap_prod, 1, unmap_q->q_depth); @@ -434,8 +438,9 @@ bnad_poll_cq(struct bnad *bnad, struct bna_ccb *ccb, int budget) struct bna_rcb *rcb = NULL; unsigned int wi_range, packets = 0, wis = 0; struct bnad_unmap_q *unmap_q; + struct bnad_skb_unmap *unmap_array; struct sk_buff *skb; - u32 flags; + u32 flags, unmap_cons; u32 qid0 = ccb->rcb[0]->rxq->rxq_id; struct bna_pkt_rate *pkt_rt = &ccb->pkt_rate; @@ -456,17 +461,17 @@ bnad_poll_cq(struct bnad *bnad, struct bna_ccb *ccb, int budget) rcb = ccb->rcb[1]; unmap_q = rcb->unmap_q; + unmap_array = unmap_q->unmap_array; + unmap_cons = unmap_q->consumer_index; - skb = unmap_q->unmap_array[unmap_q->consumer_index].skb; + skb = unmap_array[unmap_cons].skb; BUG_ON(!(skb)); - unmap_q->unmap_array[unmap_q->consumer_index].skb = NULL; - pci_unmap_single(bnad->pcidev, - pci_unmap_addr(&unmap_q-> - unmap_array[unmap_q-> - consumer_index], + unmap_array[unmap_cons].skb = NULL; + dma_unmap_single(&bnad->pcidev->dev, + dma_unmap_addr(&unmap_array[unmap_cons], dma_addr), - rcb->rxq->buffer_size, - PCI_DMA_FROMDEVICE); + rcb->rxq->buffer_size, + DMA_FROM_DEVICE); BNA_QE_INDX_ADD(unmap_q->consumer_index, 1, unmap_q->q_depth); /* Should be more efficient ? Performance ? */ @@ -1015,9 +1020,9 @@ bnad_mem_free(struct bnad *bnad, if (mem_info->mem_type == BNA_MEM_T_DMA) { BNA_GET_DMA_ADDR(&(mem_info->mdl[i].dma), dma_pa); - pci_free_consistent(bnad->pcidev, - mem_info->mdl[i].len, - mem_info->mdl[i].kva, dma_pa); + dma_free_coherent(&bnad->pcidev->dev, + mem_info->mdl[i].len, + mem_info->mdl[i].kva, dma_pa); } else kfree(mem_info->mdl[i].kva); } @@ -1047,8 +1052,9 @@ bnad_mem_alloc(struct bnad *bnad, for (i = 0; i < mem_info->num; i++) { mem_info->mdl[i].len = mem_info->len; mem_info->mdl[i].kva = - pci_alloc_consistent(bnad->pcidev, - mem_info->len, &dma_pa); + dma_alloc_coherent(&bnad->pcidev->dev, + mem_info->len, &dma_pa, + GFP_KERNEL); if (mem_info->mdl[i].kva == NULL) goto err_return; @@ -2600,9 +2606,9 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) unmap_q->unmap_array[unmap_prod].skb = skb; BUG_ON(!(skb_headlen(skb) <= BFI_TX_MAX_DATA_PER_VECTOR)); txqent->vector[vect_id].length = htons(skb_headlen(skb)); - dma_addr = pci_map_single(bnad->pcidev, skb->data, skb_headlen(skb), - PCI_DMA_TODEVICE); - pci_unmap_addr_set(&unmap_q->unmap_array[unmap_prod], dma_addr, + dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); + dma_unmap_addr_set(&unmap_q->unmap_array[unmap_prod], dma_addr, dma_addr); BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[vect_id].host_addr); @@ -2630,11 +2636,9 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) BUG_ON(!(size <= BFI_TX_MAX_DATA_PER_VECTOR)); txqent->vector[vect_id].length = htons(size); - dma_addr = - pci_map_page(bnad->pcidev, frag->page, - frag->page_offset, size, - PCI_DMA_TODEVICE); - pci_unmap_addr_set(&unmap_q->unmap_array[unmap_prod], dma_addr, + dma_addr = dma_map_page(&bnad->pcidev->dev, frag->page, + frag->page_offset, size, DMA_TO_DEVICE); + dma_unmap_addr_set(&unmap_q->unmap_array[unmap_prod], dma_addr, dma_addr); BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[vect_id].host_addr); BNA_QE_INDX_ADD(unmap_prod, 1, unmap_q->q_depth); @@ -3022,14 +3026,14 @@ bnad_pci_init(struct bnad *bnad, err = pci_request_regions(pdev, BNAD_NAME); if (err) goto disable_device; - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) && - !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && + !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { *using_dac = 1; } else { - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = pci_set_consistent_dma_mask(pdev, - DMA_BIT_MASK(32)); + err = dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32)); if (err) goto release_regions; } diff --git a/drivers/net/bna/bnad.h b/drivers/net/bna/bnad.h index 8b1d515..a89117f 100644 --- a/drivers/net/bna/bnad.h +++ b/drivers/net/bna/bnad.h @@ -181,7 +181,7 @@ struct bnad_rx_info { /* Unmap queues for Tx / Rx cleanup */ struct bnad_skb_unmap { struct sk_buff *skb; - DECLARE_PCI_UNMAP_ADDR(dma_addr) + DEFINE_DMA_UNMAP_ADDR(dma_addr); }; struct bnad_unmap_q { diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 0ba59d5..2a961b7 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -435,7 +435,8 @@ bnx2_cnic_stop(struct bnx2 *bp) struct cnic_ctl_info info; mutex_lock(&bp->cnic_lock); - c_ops = bp->cnic_ops; + c_ops = rcu_dereference_protected(bp->cnic_ops, + lockdep_is_held(&bp->cnic_lock)); if (c_ops) { info.cmd = CNIC_CTL_STOP_CMD; c_ops->cnic_ctl(bp->cnic_data, &info); @@ -450,7 +451,8 @@ bnx2_cnic_start(struct bnx2 *bp) struct cnic_ctl_info info; mutex_lock(&bp->cnic_lock); - c_ops = bp->cnic_ops; + c_ops = rcu_dereference_protected(bp->cnic_ops, + lockdep_is_held(&bp->cnic_lock)); if (c_ops) { if (!(bp->flags & BNX2_FLAG_USING_MSIX)) { struct bnx2_napi *bnapi = &bp->bnx2_napi[0]; @@ -8315,7 +8317,7 @@ static const struct net_device_ops bnx2_netdev_ops = { #endif }; -static void inline vlan_features_add(struct net_device *dev, unsigned long flags) +static void inline vlan_features_add(struct net_device *dev, u32 flags) { dev->vlan_features |= flags; } diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h index f459fb2..7a5e88f 100644 --- a/drivers/net/bnx2.h +++ b/drivers/net/bnx2.h @@ -6207,6 +6207,8 @@ struct l2_fhdr { #define BNX2_CP_SCRATCH 0x001a0000 +#define BNX2_FW_MAX_ISCSI_CONN 0x001a0080 + /* * mcp_reg definition @@ -6759,7 +6761,7 @@ struct bnx2 { u32 tx_wake_thresh; #ifdef BCM_CNIC - struct cnic_ops *cnic_ops; + struct cnic_ops __rcu *cnic_ops; void *cnic_data; #endif diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h index 653c624..c0dd30d 100644 --- a/drivers/net/bnx2x/bnx2x.h +++ b/drivers/net/bnx2x/bnx2x.h @@ -22,8 +22,8 @@ * (you will need to reboot afterwards) */ /* #define BNX2X_STOP_ON_ERROR */ -#define DRV_MODULE_VERSION "1.62.00-5" -#define DRV_MODULE_RELDATE "2011/01/30" +#define DRV_MODULE_VERSION "1.62.11-0" +#define DRV_MODULE_RELDATE "2011/01/31" #define BNX2X_BC_VER 0x040200 #define BNX2X_MULTI_QUEUE @@ -129,6 +129,7 @@ void bnx2x_panic_dump(struct bnx2x *bp); #endif #define bnx2x_mc_addr(ha) ((ha)->addr) +#define bnx2x_uc_addr(ha) ((ha)->addr) #define U64_LO(x) (u32)(((u64)(x)) & 0xffffffff) #define U64_HI(x) (u32)(((u64)(x)) >> 32) @@ -341,6 +342,8 @@ struct bnx2x_fastpath { /* chip independed shortcut into rx_prods_offset memory */ u32 ustorm_rx_prods_offset; + u32 rx_buf_size; + dma_addr_t status_blk_mapping; struct sw_tx_bd *tx_buf_ring; @@ -428,6 +431,10 @@ struct bnx2x_fastpath { }; #define bnx2x_fp(bp, nr, var) (bp->fp[nr].var) + +/* Use 2500 as a mini-jumbo MTU for FCoE */ +#define BNX2X_FCOE_MINI_JUMBO_MTU 2500 + #ifdef BCM_CNIC /* FCoE L2 `fastpath' is right after the eth entries */ #define FCOE_IDX BNX2X_NUM_ETH_QUEUES(bp) @@ -810,6 +817,7 @@ struct bnx2x_slowpath { struct eth_stats_query fw_stats; struct mac_configuration_cmd mac_config; struct mac_configuration_cmd mcast_config; + struct mac_configuration_cmd uc_mac_config; struct client_init_ramrod_data client_init_data; /* used by dmae command executer */ @@ -911,7 +919,6 @@ struct bnx2x { int tx_ring_size; u32 rx_csum; - u32 rx_buf_size; /* L2 header size + 2*VLANs (8 bytes) + LLC SNAP (8 bytes) */ #define ETH_OVREHEAD (ETH_HLEN + 8 + 8) #define ETH_MIN_PACKET_SIZE 60 @@ -939,7 +946,7 @@ struct bnx2x { struct eth_spe *spq_prod_bd; struct eth_spe *spq_last_bd; __le16 *dsb_sp_prod; - atomic_t spq_left; /* serialize spq */ + atomic_t cq_spq_left; /* ETH_XXX ramrods credit */ /* used to synchronize spq accesses */ spinlock_t spq_lock; @@ -949,6 +956,7 @@ struct bnx2x { u16 eq_prod; u16 eq_cons; __le16 *eq_cons_sb; + atomic_t eq_spq_left; /* COMMON_XXX ramrods credit */ /* Flags for marking that there is a STAT_QUERY or SET_MAC ramrod pending */ @@ -976,8 +984,12 @@ struct bnx2x { #define MF_FUNC_DIS 0x1000 #define FCOE_MACS_SET 0x2000 #define NO_FCOE_FLAG 0x4000 +#define NO_ISCSI_OOO_FLAG 0x8000 +#define NO_ISCSI_FLAG 0x10000 #define NO_FCOE(bp) ((bp)->flags & NO_FCOE_FLAG) +#define NO_ISCSI(bp) ((bp)->flags & NO_ISCSI_FLAG) +#define NO_ISCSI_OOO(bp) ((bp)->flags & NO_ISCSI_OOO_FLAG) int pf_num; /* absolute PF number */ int pfid; /* per-path PF number */ @@ -1064,6 +1076,7 @@ struct bnx2x { int num_queues; int disable_tpa; int int_mode; + u32 *rx_indir_table; struct tstorm_eth_mac_filter_config mac_filters; #define BNX2X_ACCEPT_NONE 0x0000 @@ -1110,7 +1123,7 @@ struct bnx2x { #define BNX2X_CNIC_FLAG_MAC_SET 1 void *t2; dma_addr_t t2_mapping; - struct cnic_ops *cnic_ops; + struct cnic_ops __rcu *cnic_ops; void *cnic_data; u32 cnic_tag; struct cnic_eth_dev cnic_eth_dev; @@ -1125,13 +1138,12 @@ struct bnx2x { u16 cnic_kwq_pending; u16 cnic_spq_pending; struct mutex cnic_mutex; - u8 iscsi_mac[ETH_ALEN]; u8 fip_mac[ETH_ALEN]; #endif int dmae_ready; /* used to synchronize dmae accesses */ - struct mutex dmae_mutex; + spinlock_t dmae_lock; /* used to protect the FW mail box */ struct mutex fw_mb_mutex; @@ -1447,6 +1459,12 @@ u32 bnx2x_fw_command(struct bnx2x *bp, u32 command, u32 param); void bnx2x_calc_fc_adv(struct bnx2x *bp); int bnx2x_sp_post(struct bnx2x *bp, int command, int cid, u32 data_hi, u32 data_lo, int common); + +/* Clears multicast and unicast list configuration in the chip. */ +void bnx2x_invalidate_e1_mc_list(struct bnx2x *bp); +void bnx2x_invalidate_e1h_mc_list(struct bnx2x *bp); +void bnx2x_invalidate_uc_list(struct bnx2x *bp); + void bnx2x_update_coalesce(struct bnx2x *bp); int bnx2x_get_link_cfg_idx(struct bnx2x *bp); @@ -1782,5 +1800,6 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms, BNX2X_EXTERN int load_count[2][3]; /* per path: 0-common, 1-port0, 2-port1 */ extern void bnx2x_set_ethtool_ops(struct net_device *netdev); +void bnx2x_push_indir_table(struct bnx2x *bp); #endif /* bnx2x.h */ diff --git a/drivers/net/bnx2x/bnx2x_cmn.c b/drivers/net/bnx2x/bnx2x_cmn.c index 710ce5d..6fac8e1 100644 --- a/drivers/net/bnx2x/bnx2x_cmn.c +++ b/drivers/net/bnx2x/bnx2x_cmn.c @@ -232,7 +232,7 @@ static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue, /* move empty skb from pool to prod and map it */ prod_rx_buf->skb = fp->tpa_pool[queue].skb; mapping = dma_map_single(&bp->pdev->dev, fp->tpa_pool[queue].skb->data, - bp->rx_buf_size, DMA_FROM_DEVICE); + fp->rx_buf_size, DMA_FROM_DEVICE); dma_unmap_addr_set(prod_rx_buf, mapping, mapping); /* move partial skb from cons to pool (don't unmap yet) */ @@ -333,13 +333,13 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp, struct sw_rx_bd *rx_buf = &fp->tpa_pool[queue]; struct sk_buff *skb = rx_buf->skb; /* alloc new skb */ - struct sk_buff *new_skb = netdev_alloc_skb(bp->dev, bp->rx_buf_size); + struct sk_buff *new_skb = netdev_alloc_skb(bp->dev, fp->rx_buf_size); /* Unmap skb in the pool anyway, as we are going to change pool entry status to BNX2X_TPA_STOP even if new skb allocation fails. */ dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping), - bp->rx_buf_size, DMA_FROM_DEVICE); + fp->rx_buf_size, DMA_FROM_DEVICE); if (likely(new_skb)) { /* fix ip xsum and give it to the stack */ @@ -349,10 +349,10 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp, prefetch(((char *)(skb)) + L1_CACHE_BYTES); #ifdef BNX2X_STOP_ON_ERROR - if (pad + len > bp->rx_buf_size) { + if (pad + len > fp->rx_buf_size) { BNX2X_ERR("skb_put is about to fail... " "pad %d len %d rx_buf_size %d\n", - pad, len, bp->rx_buf_size); + pad, len, fp->rx_buf_size); bnx2x_panic(); return; } @@ -582,7 +582,7 @@ int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget) if (likely(bnx2x_alloc_rx_skb(bp, fp, bd_prod) == 0)) { dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping), - bp->rx_buf_size, + fp->rx_buf_size, DMA_FROM_DEVICE); skb_reserve(skb, pad); skb_put(skb, len); @@ -821,19 +821,16 @@ void bnx2x_init_rx_rings(struct bnx2x *bp) u16 ring_prod; int i, j; - bp->rx_buf_size = bp->dev->mtu + ETH_OVREHEAD + BNX2X_RX_ALIGN + - IP_HEADER_ALIGNMENT_PADDING; - - DP(NETIF_MSG_IFUP, - "mtu %d rx_buf_size %d\n", bp->dev->mtu, bp->rx_buf_size); - for_each_rx_queue(bp, j) { struct bnx2x_fastpath *fp = &bp->fp[j]; + DP(NETIF_MSG_IFUP, + "mtu %d rx_buf_size %d\n", bp->dev->mtu, fp->rx_buf_size); + if (!fp->disable_tpa) { for (i = 0; i < max_agg_queues; i++) { fp->tpa_pool[i].skb = - netdev_alloc_skb(bp->dev, bp->rx_buf_size); + netdev_alloc_skb(bp->dev, fp->rx_buf_size); if (!fp->tpa_pool[i].skb) { BNX2X_ERR("Failed to allocate TPA " "skb pool for queue[%d] - " @@ -941,7 +938,7 @@ static void bnx2x_free_rx_skbs(struct bnx2x *bp) dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping), - bp->rx_buf_size, DMA_FROM_DEVICE); + fp->rx_buf_size, DMA_FROM_DEVICE); rx_buf->skb = NULL; dev_kfree_skb(skb); @@ -1249,6 +1246,31 @@ static inline int bnx2x_set_real_num_queues(struct bnx2x *bp) return rc; } +static inline void bnx2x_set_rx_buf_size(struct bnx2x *bp) +{ + int i; + + for_each_queue(bp, i) { + struct bnx2x_fastpath *fp = &bp->fp[i]; + + /* Always use a mini-jumbo MTU for the FCoE L2 ring */ + if (IS_FCOE_IDX(i)) + /* + * Although there are no IP frames expected to arrive to + * this ring we still want to add an + * IP_HEADER_ALIGNMENT_PADDING to prevent a buffer + * overrun attack. + */ + fp->rx_buf_size = + BNX2X_FCOE_MINI_JUMBO_MTU + ETH_OVREHEAD + + BNX2X_RX_ALIGN + IP_HEADER_ALIGNMENT_PADDING; + else + fp->rx_buf_size = + bp->dev->mtu + ETH_OVREHEAD + BNX2X_RX_ALIGN + + IP_HEADER_ALIGNMENT_PADDING; + } +} + /* must be called with rtnl_lock */ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) { @@ -1272,6 +1294,9 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) /* must be called before memory allocation and HW init */ bnx2x_ilt_set_info(bp); + /* Set the receive queues buffer size */ + bnx2x_set_rx_buf_size(bp); + if (bnx2x_alloc_mem(bp)) return -ENOMEM; @@ -1427,28 +1452,35 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) bnx2x_set_eth_mac(bp, 1); + /* Clear MC configuration */ + if (CHIP_IS_E1(bp)) + bnx2x_invalidate_e1_mc_list(bp); + else + bnx2x_invalidate_e1h_mc_list(bp); + + /* Clear UC lists configuration */ + bnx2x_invalidate_uc_list(bp); + if (bp->port.pmf) bnx2x_initial_phy_init(bp, load_mode); + /* Initialize Rx filtering */ + bnx2x_set_rx_mode(bp->dev); + /* Start fast path */ switch (load_mode) { case LOAD_NORMAL: /* Tx queue should be only reenabled */ netif_tx_wake_all_queues(bp->dev); /* Initialize the receive filter. */ - bnx2x_set_rx_mode(bp->dev); break; case LOAD_OPEN: netif_tx_start_all_queues(bp->dev); smp_mb__after_clear_bit(); - /* Initialize the receive filter. */ - bnx2x_set_rx_mode(bp->dev); break; case LOAD_DIAG: - /* Initialize the receive filter. */ - bnx2x_set_rx_mode(bp->dev); bp->state = BNX2X_STATE_DIAG; break; diff --git a/drivers/net/bnx2x/bnx2x_cmn.h b/drivers/net/bnx2x/bnx2x_cmn.h index 03eb4d6..f062d5d 100644 --- a/drivers/net/bnx2x/bnx2x_cmn.h +++ b/drivers/net/bnx2x/bnx2x_cmn.h @@ -822,11 +822,11 @@ static inline int bnx2x_alloc_rx_skb(struct bnx2x *bp, struct eth_rx_bd *rx_bd = &fp->rx_desc_ring[index]; dma_addr_t mapping; - skb = netdev_alloc_skb(bp->dev, bp->rx_buf_size); + skb = netdev_alloc_skb(bp->dev, fp->rx_buf_size); if (unlikely(skb == NULL)) return -ENOMEM; - mapping = dma_map_single(&bp->pdev->dev, skb->data, bp->rx_buf_size, + mapping = dma_map_single(&bp->pdev->dev, skb->data, fp->rx_buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) { dev_kfree_skb(skb); @@ -892,7 +892,7 @@ static inline void bnx2x_free_tpa_pool(struct bnx2x *bp, if (fp->tpa_state[i] == BNX2X_TPA_START) dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping), - bp->rx_buf_size, DMA_FROM_DEVICE); + fp->rx_buf_size, DMA_FROM_DEVICE); dev_kfree_skb(skb); rx_buf->skb = NULL; diff --git a/drivers/net/bnx2x/bnx2x_ethtool.c b/drivers/net/bnx2x/bnx2x_ethtool.c index 5b44a8b..8d19d12 100644 --- a/drivers/net/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/bnx2x/bnx2x_ethtool.c @@ -1618,7 +1618,7 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode, u8 link_up) /* prepare the loopback packet */ pkt_size = (((bp->dev->mtu < ETH_MAX_PACKET_SIZE) ? bp->dev->mtu : ETH_MAX_PACKET_SIZE) + ETH_HLEN); - skb = netdev_alloc_skb(bp->dev, bp->rx_buf_size); + skb = netdev_alloc_skb(bp->dev, fp_rx->rx_buf_size); if (!skb) { rc = -ENOMEM; goto test_loopback_exit; @@ -2134,6 +2134,59 @@ static int bnx2x_phys_id(struct net_device *dev, u32 data) return 0; } +static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, + void *rules __always_unused) +{ + struct bnx2x *bp = netdev_priv(dev); + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = BNX2X_NUM_ETH_QUEUES(bp); + return 0; + + default: + return -EOPNOTSUPP; + } +} + +static int bnx2x_get_rxfh_indir(struct net_device *dev, + struct ethtool_rxfh_indir *indir) +{ + struct bnx2x *bp = netdev_priv(dev); + size_t copy_size = + min_t(size_t, indir->size, TSTORM_INDIRECTION_TABLE_SIZE); + + if (bp->multi_mode == ETH_RSS_MODE_DISABLED) + return -EOPNOTSUPP; + + indir->size = TSTORM_INDIRECTION_TABLE_SIZE; + memcpy(indir->ring_index, bp->rx_indir_table, + copy_size * sizeof(bp->rx_indir_table[0])); + return 0; +} + +static int bnx2x_set_rxfh_indir(struct net_device *dev, + const struct ethtool_rxfh_indir *indir) +{ + struct bnx2x *bp = netdev_priv(dev); + size_t i; + + if (bp->multi_mode == ETH_RSS_MODE_DISABLED) + return -EOPNOTSUPP; + + /* Validate size and indices */ + if (indir->size != TSTORM_INDIRECTION_TABLE_SIZE) + return -EINVAL; + for (i = 0; i < TSTORM_INDIRECTION_TABLE_SIZE; i++) + if (indir->ring_index[i] >= BNX2X_NUM_ETH_QUEUES(bp)) + return -EINVAL; + + memcpy(bp->rx_indir_table, indir->ring_index, + indir->size * sizeof(bp->rx_indir_table[0])); + bnx2x_push_indir_table(bp); + return 0; +} + static const struct ethtool_ops bnx2x_ethtool_ops = { .get_settings = bnx2x_get_settings, .set_settings = bnx2x_set_settings, @@ -2170,6 +2223,9 @@ static const struct ethtool_ops bnx2x_ethtool_ops = { .get_strings = bnx2x_get_strings, .phys_id = bnx2x_phys_id, .get_ethtool_stats = bnx2x_get_ethtool_stats, + .get_rxnfc = bnx2x_get_rxnfc, + .get_rxfh_indir = bnx2x_get_rxfh_indir, + .set_rxfh_indir = bnx2x_set_rxfh_indir, }; void bnx2x_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/bnx2x/bnx2x_hsi.h b/drivers/net/bnx2x/bnx2x_hsi.h index 548f563..be503cc 100644 --- a/drivers/net/bnx2x/bnx2x_hsi.h +++ b/drivers/net/bnx2x/bnx2x_hsi.h @@ -11,20 +11,27 @@ #include "bnx2x_fw_defs.h" +#define FW_ENCODE_32BIT_PATTERN 0x1e1e1e1e + struct license_key { u32 reserved[6]; -#if defined(__BIG_ENDIAN) - u16 max_iscsi_init_conn; - u16 max_iscsi_trgt_conn; -#elif defined(__LITTLE_ENDIAN) - u16 max_iscsi_trgt_conn; - u16 max_iscsi_init_conn; -#endif + u32 max_iscsi_conn; +#define BNX2X_MAX_ISCSI_TRGT_CONN_MASK 0xFFFF +#define BNX2X_MAX_ISCSI_TRGT_CONN_SHIFT 0 +#define BNX2X_MAX_ISCSI_INIT_CONN_MASK 0xFFFF0000 +#define BNX2X_MAX_ISCSI_INIT_CONN_SHIFT 16 - u32 reserved_a[6]; -}; + u32 reserved_a; + + u32 max_fcoe_conn; +#define BNX2X_MAX_FCOE_TRGT_CONN_MASK 0xFFFF +#define BNX2X_MAX_FCOE_TRGT_CONN_SHIFT 0 +#define BNX2X_MAX_FCOE_INIT_CONN_MASK 0xFFFF0000 +#define BNX2X_MAX_FCOE_INIT_CONN_SHIFT 16 + u32 reserved_b[4]; +}; #define PORT_0 0 #define PORT_1 1 @@ -237,8 +244,26 @@ struct port_hw_cfg { /* port 0: 0x12c port 1: 0x2bc */ #define PORT_HW_CFG_SERDES_RX_DRV_EQUALIZER_SHIFT 16 - u32 Reserved0[16]; /* 0x158 */ - + u32 Reserved0[3]; /* 0x158 */ + /* Controls the TX laser of the SFP+ module */ + u32 sfp_ctrl; /* 0x164 */ +#define PORT_HW_CFG_TX_LASER_MASK 0x000000FF +#define PORT_HW_CFG_TX_LASER_SHIFT 0 +#define PORT_HW_CFG_TX_LASER_MDIO 0x00000000 +#define PORT_HW_CFG_TX_LASER_GPIO0 0x00000001 +#define PORT_HW_CFG_TX_LASER_GPIO1 0x00000002 +#define PORT_HW_CFG_TX_LASER_GPIO2 0x00000003 +#define PORT_HW_CFG_TX_LASER_GPIO3 0x00000004 + + /* Controls the fault module LED of the SFP+ */ +#define PORT_HW_CFG_FAULT_MODULE_LED_MASK 0x0000FF00 +#define PORT_HW_CFG_FAULT_MODULE_LED_SHIFT 8 +#define PORT_HW_CFG_FAULT_MODULE_LED_GPIO0 0x00000000 +#define PORT_HW_CFG_FAULT_MODULE_LED_GPIO1 0x00000100 +#define PORT_HW_CFG_FAULT_MODULE_LED_GPIO2 0x00000200 +#define PORT_HW_CFG_FAULT_MODULE_LED_GPIO3 0x00000300 +#define PORT_HW_CFG_FAULT_MODULE_LED_DISABLED 0x00000400 + u32 Reserved01[12]; /* 0x158 */ /* for external PHY, or forced mode or during AN */ u16 xgxs_config_rx[4]; /* 0x198 */ @@ -246,12 +271,78 @@ struct port_hw_cfg { /* port 0: 0x12c port 1: 0x2bc */ u32 Reserved1[56]; /* 0x1A8 */ u32 default_cfg; /* 0x288 */ +#define PORT_HW_CFG_GPIO0_CONFIG_MASK 0x00000003 +#define PORT_HW_CFG_GPIO0_CONFIG_SHIFT 0 +#define PORT_HW_CFG_GPIO0_CONFIG_NA 0x00000000 +#define PORT_HW_CFG_GPIO0_CONFIG_LOW 0x00000001 +#define PORT_HW_CFG_GPIO0_CONFIG_HIGH 0x00000002 +#define PORT_HW_CFG_GPIO0_CONFIG_INPUT 0x00000003 + +#define PORT_HW_CFG_GPIO1_CONFIG_MASK 0x0000000C +#define PORT_HW_CFG_GPIO1_CONFIG_SHIFT 2 +#define PORT_HW_CFG_GPIO1_CONFIG_NA 0x00000000 +#define PORT_HW_CFG_GPIO1_CONFIG_LOW 0x00000004 +#define PORT_HW_CFG_GPIO1_CONFIG_HIGH 0x00000008 +#define PORT_HW_CFG_GPIO1_CONFIG_INPUT 0x0000000c + +#define PORT_HW_CFG_GPIO2_CONFIG_MASK 0x00000030 +#define PORT_HW_CFG_GPIO2_CONFIG_SHIFT 4 +#define PORT_HW_CFG_GPIO2_CONFIG_NA 0x00000000 +#define PORT_HW_CFG_GPIO2_CONFIG_LOW 0x00000010 +#define PORT_HW_CFG_GPIO2_CONFIG_HIGH 0x00000020 +#define PORT_HW_CFG_GPIO2_CONFIG_INPUT 0x00000030 + +#define PORT_HW_CFG_GPIO3_CONFIG_MASK 0x000000C0 +#define PORT_HW_CFG_GPIO3_CONFIG_SHIFT 6 +#define PORT_HW_CFG_GPIO3_CONFIG_NA 0x00000000 +#define PORT_HW_CFG_GPIO3_CONFIG_LOW 0x00000040 +#define PORT_HW_CFG_GPIO3_CONFIG_HIGH 0x00000080 +#define PORT_HW_CFG_GPIO3_CONFIG_INPUT 0x000000c0 + + /* + * When KR link is required to be set to force which is not + * KR-compliant, this parameter determine what is the trigger for it. + * When GPIO is selected, low input will force the speed. Currently + * default speed is 1G. In the future, it may be widen to select the + * forced speed in with another parameter. Note when force-1G is + * enabled, it override option 56: Link Speed option. + */ +#define PORT_HW_CFG_FORCE_KR_ENABLER_MASK 0x00000F00 +#define PORT_HW_CFG_FORCE_KR_ENABLER_SHIFT 8 +#define PORT_HW_CFG_FORCE_KR_ENABLER_NOT_FORCED 0x00000000 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO0_P0 0x00000100 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO1_P0 0x00000200 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO2_P0 0x00000300 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO3_P0 0x00000400 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO0_P1 0x00000500 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO1_P1 0x00000600 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO2_P1 0x00000700 +#define PORT_HW_CFG_FORCE_KR_ENABLER_GPIO3_P1 0x00000800 +#define PORT_HW_CFG_FORCE_KR_ENABLER_FORCED 0x00000900 + /* Enable to determine with which GPIO to reset the external phy */ +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_MASK 0x000F0000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_SHIFT 16 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_PHY_TYPE 0x00000000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO0_P0 0x00010000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO1_P0 0x00020000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO2_P0 0x00030000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO3_P0 0x00040000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO0_P1 0x00050000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO1_P1 0x00060000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO2_P1 0x00070000 +#define PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO3_P1 0x00080000 /* Enable BAM on KR */ #define PORT_HW_CFG_ENABLE_BAM_ON_KR_MASK 0x00100000 #define PORT_HW_CFG_ENABLE_BAM_ON_KR_SHIFT 20 #define PORT_HW_CFG_ENABLE_BAM_ON_KR_DISABLED 0x00000000 #define PORT_HW_CFG_ENABLE_BAM_ON_KR_ENABLED 0x00100000 + /* Enable Common Mode Sense */ +#define PORT_HW_CFG_ENABLE_CMS_MASK 0x00200000 +#define PORT_HW_CFG_ENABLE_CMS_SHIFT 21 +#define PORT_HW_CFG_ENABLE_CMS_DISABLED 0x00000000 +#define PORT_HW_CFG_ENABLE_CMS_ENABLED 0x00200000 + u32 speed_capability_mask2; /* 0x28C */ #define PORT_HW_CFG_SPEED_CAPABILITY2_D3_MASK 0x0000FFFF #define PORT_HW_CFG_SPEED_CAPABILITY2_D3_SHIFT 0 @@ -381,6 +472,7 @@ struct port_hw_cfg { /* port 0: 0x12c port 1: 0x2bc */ #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727 0x00000900 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727_NOC 0x00000a00 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84823 0x00000b00 +#define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833 0x00000d00 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_FAILURE 0x0000fd00 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_NOT_CONN 0x0000ff00 diff --git a/drivers/net/bnx2x/bnx2x_link.c b/drivers/net/bnx2x/bnx2x_link.c index dd1210f..f2f367d 100644 --- a/drivers/net/bnx2x/bnx2x_link.c +++ b/drivers/net/bnx2x/bnx2x_link.c @@ -1,4 +1,4 @@ -/* Copyright 2008-2009 Broadcom Corporation +/* Copyright 2008-2011 Broadcom Corporation * * Unless you and Broadcom execute a separate written software license * agreement governing use of this software, this software is licensed to you @@ -28,12 +28,13 @@ /********************************************************/ #define ETH_HLEN 14 -#define ETH_OVREHEAD (ETH_HLEN + 8 + 8)/* 16 for CRC + VLAN + LLC */ +/* L2 header size + 2*VLANs (8 bytes) + LLC SNAP (8 bytes) */ +#define ETH_OVREHEAD (ETH_HLEN + 8 + 8) #define ETH_MIN_PACKET_SIZE 60 #define ETH_MAX_PACKET_SIZE 1500 #define ETH_MAX_JUMBO_PACKET_SIZE 9600 #define MDIO_ACCESS_TIMEOUT 1000 -#define BMAC_CONTROL_RX_ENABLE 2 +#define BMAC_CONTROL_RX_ENABLE 2 /***********************************************************/ /* Shortcut definitions */ @@ -79,7 +80,7 @@ #define AUTONEG_CL37 SHARED_HW_CFG_AN_ENABLE_CL37 #define AUTONEG_CL73 SHARED_HW_CFG_AN_ENABLE_CL73 -#define AUTONEG_BAM SHARED_HW_CFG_AN_ENABLE_BAM +#define AUTONEG_BAM SHARED_HW_CFG_AN_ENABLE_BAM #define AUTONEG_PARALLEL \ SHARED_HW_CFG_AN_ENABLE_PARALLEL_DETECTION #define AUTONEG_SGMII_FIBER_AUTODET \ @@ -112,10 +113,10 @@ #define GP_STATUS_10G_KX4 \ MDIO_GP_STATUS_TOP_AN_STATUS1_ACTUAL_SPEED_10G_KX4 -#define LINK_10THD LINK_STATUS_SPEED_AND_DUPLEX_10THD -#define LINK_10TFD LINK_STATUS_SPEED_AND_DUPLEX_10TFD +#define LINK_10THD LINK_STATUS_SPEED_AND_DUPLEX_10THD +#define LINK_10TFD LINK_STATUS_SPEED_AND_DUPLEX_10TFD #define LINK_100TXHD LINK_STATUS_SPEED_AND_DUPLEX_100TXHD -#define LINK_100T4 LINK_STATUS_SPEED_AND_DUPLEX_100T4 +#define LINK_100T4 LINK_STATUS_SPEED_AND_DUPLEX_100T4 #define LINK_100TXFD LINK_STATUS_SPEED_AND_DUPLEX_100TXFD #define LINK_1000THD LINK_STATUS_SPEED_AND_DUPLEX_1000THD #define LINK_1000TFD LINK_STATUS_SPEED_AND_DUPLEX_1000TFD @@ -123,18 +124,18 @@ #define LINK_2500THD LINK_STATUS_SPEED_AND_DUPLEX_2500THD #define LINK_2500TFD LINK_STATUS_SPEED_AND_DUPLEX_2500TFD #define LINK_2500XFD LINK_STATUS_SPEED_AND_DUPLEX_2500XFD -#define LINK_10GTFD LINK_STATUS_SPEED_AND_DUPLEX_10GTFD -#define LINK_10GXFD LINK_STATUS_SPEED_AND_DUPLEX_10GXFD -#define LINK_12GTFD LINK_STATUS_SPEED_AND_DUPLEX_12GTFD -#define LINK_12GXFD LINK_STATUS_SPEED_AND_DUPLEX_12GXFD +#define LINK_10GTFD LINK_STATUS_SPEED_AND_DUPLEX_10GTFD +#define LINK_10GXFD LINK_STATUS_SPEED_AND_DUPLEX_10GXFD +#define LINK_12GTFD LINK_STATUS_SPEED_AND_DUPLEX_12GTFD +#define LINK_12GXFD LINK_STATUS_SPEED_AND_DUPLEX_12GXFD #define LINK_12_5GTFD LINK_STATUS_SPEED_AND_DUPLEX_12_5GTFD #define LINK_12_5GXFD LINK_STATUS_SPEED_AND_DUPLEX_12_5GXFD -#define LINK_13GTFD LINK_STATUS_SPEED_AND_DUPLEX_13GTFD -#define LINK_13GXFD LINK_STATUS_SPEED_AND_DUPLEX_13GXFD -#define LINK_15GTFD LINK_STATUS_SPEED_AND_DUPLEX_15GTFD -#define LINK_15GXFD LINK_STATUS_SPEED_AND_DUPLEX_15GXFD -#define LINK_16GTFD LINK_STATUS_SPEED_AND_DUPLEX_16GTFD -#define LINK_16GXFD LINK_STATUS_SPEED_AND_DUPLEX_16GXFD +#define LINK_13GTFD LINK_STATUS_SPEED_AND_DUPLEX_13GTFD +#define LINK_13GXFD LINK_STATUS_SPEED_AND_DUPLEX_13GXFD +#define LINK_15GTFD LINK_STATUS_SPEED_AND_DUPLEX_15GTFD +#define LINK_15GXFD LINK_STATUS_SPEED_AND_DUPLEX_15GXFD +#define LINK_16GTFD LINK_STATUS_SPEED_AND_DUPLEX_16GTFD +#define LINK_16GXFD LINK_STATUS_SPEED_AND_DUPLEX_16GXFD #define PHY_XGXS_FLAG 0x1 #define PHY_SGMII_FLAG 0x2 @@ -142,7 +143,7 @@ /* */ #define SFP_EEPROM_CON_TYPE_ADDR 0x2 - #define SFP_EEPROM_CON_TYPE_VAL_LC 0x7 + #define SFP_EEPROM_CON_TYPE_VAL_LC 0x7 #define SFP_EEPROM_CON_TYPE_VAL_COPPER 0x21 @@ -153,15 +154,15 @@ #define SFP_EEPROM_FC_TX_TECH_ADDR 0x8 #define SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_PASSIVE 0x4 - #define SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_ACTIVE 0x8 + #define SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_ACTIVE 0x8 -#define SFP_EEPROM_OPTIONS_ADDR 0x40 +#define SFP_EEPROM_OPTIONS_ADDR 0x40 #define SFP_EEPROM_OPTIONS_LINEAR_RX_OUT_MASK 0x1 -#define SFP_EEPROM_OPTIONS_SIZE 2 +#define SFP_EEPROM_OPTIONS_SIZE 2 -#define EDC_MODE_LINEAR 0x0022 -#define EDC_MODE_LIMITING 0x0044 -#define EDC_MODE_PASSIVE_DAC 0x0055 +#define EDC_MODE_LINEAR 0x0022 +#define EDC_MODE_LIMITING 0x0044 +#define EDC_MODE_PASSIVE_DAC 0x0055 #define ETS_BW_LIMIT_CREDIT_UPPER_BOUND (0x5000) @@ -170,24 +171,18 @@ /* INTERFACE */ /**********************************************************/ -#define CL45_WR_OVER_CL22(_bp, _phy, _bank, _addr, _val) \ +#define CL22_WR_OVER_CL45(_bp, _phy, _bank, _addr, _val) \ bnx2x_cl45_write(_bp, _phy, \ (_phy)->def_md_devad, \ (_bank + (_addr & 0xf)), \ _val) -#define CL45_RD_OVER_CL22(_bp, _phy, _bank, _addr, _val) \ +#define CL22_RD_OVER_CL45(_bp, _phy, _bank, _addr, _val) \ bnx2x_cl45_read(_bp, _phy, \ (_phy)->def_md_devad, \ (_bank + (_addr & 0xf)), \ _val) -static u8 bnx2x_cl45_read(struct bnx2x *bp, struct bnx2x_phy *phy, - u8 devad, u16 reg, u16 *ret_val); - -static u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, - u8 devad, u16 reg, u16 val); - static u32 bnx2x_bits_en(struct bnx2x *bp, u32 reg, u32 bits) { u32 val = REG_RD(bp, reg); @@ -216,7 +211,7 @@ void bnx2x_ets_disabled(struct link_params *params) DP(NETIF_MSG_LINK, "ETS disabled configuration\n"); - /** + /* * mapping between entry priority to client number (0,1,2 -debug and * management clients, 3 - COS0 client, 4 - COS client)(HIGHEST) * 3bits client num. @@ -225,7 +220,7 @@ void bnx2x_ets_disabled(struct link_params *params) */ REG_WR(bp, NIG_REG_P0_TX_ARB_PRIORITY_CLIENT, 0x4688); - /** + /* * Bitmap of 5bits length. Each bit specifies whether the entry behaves * as strict. Bits 0,1,2 - debug and management entries, 3 - * COS0 entry, 4 - COS1 entry. @@ -237,12 +232,12 @@ void bnx2x_ets_disabled(struct link_params *params) REG_WR(bp, NIG_REG_P0_TX_ARB_CLIENT_IS_STRICT, 0x7); /* defines which entries (clients) are subjected to WFQ arbitration */ REG_WR(bp, NIG_REG_P0_TX_ARB_CLIENT_IS_SUBJECT2WFQ, 0); - /** - * For strict priority entries defines the number of consecutive - * slots for the highest priority. - */ + /* + * For strict priority entries defines the number of consecutive + * slots for the highest priority. + */ REG_WR(bp, NIG_REG_P0_TX_ARB_NUM_STRICT_ARB_SLOTS, 0x100); - /** + /* * mapping between the CREDIT_WEIGHT registers and actual client * numbers */ @@ -255,7 +250,7 @@ void bnx2x_ets_disabled(struct link_params *params) REG_WR(bp, PBF_REG_HIGH_PRIORITY_COS_NUM, 0); /* ETS mode disable */ REG_WR(bp, PBF_REG_ETS_ENABLED, 0); - /** + /* * If ETS mode is enabled (there is no strict priority) defines a WFQ * weight for COS0/COS1. */ @@ -268,24 +263,24 @@ void bnx2x_ets_disabled(struct link_params *params) REG_WR(bp, PBF_REG_NUM_STRICT_ARB_SLOTS, 0); } -void bnx2x_ets_bw_limit_common(const struct link_params *params) +static void bnx2x_ets_bw_limit_common(const struct link_params *params) { /* ETS disabled configuration */ struct bnx2x *bp = params->bp; DP(NETIF_MSG_LINK, "ETS enabled BW limit configuration\n"); - /** - * defines which entries (clients) are subjected to WFQ arbitration - * COS0 0x8 - * COS1 0x10 - */ + /* + * defines which entries (clients) are subjected to WFQ arbitration + * COS0 0x8 + * COS1 0x10 + */ REG_WR(bp, NIG_REG_P0_TX_ARB_CLIENT_IS_SUBJECT2WFQ, 0x18); - /** - * mapping between the ARB_CREDIT_WEIGHT registers and actual - * client numbers (WEIGHT_0 does not actually have to represent - * client 0) - * PRI4 | PRI3 | PRI2 | PRI1 | PRI0 - * cos1-001 cos0-000 dbg1-100 dbg0-011 MCP-010 - */ + /* + * mapping between the ARB_CREDIT_WEIGHT registers and actual + * client numbers (WEIGHT_0 does not actually have to represent + * client 0) + * PRI4 | PRI3 | PRI2 | PRI1 | PRI0 + * cos1-001 cos0-000 dbg1-100 dbg0-011 MCP-010 + */ REG_WR(bp, NIG_REG_P0_TX_ARB_CLIENT_CREDIT_MAP, 0x111A); REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_0, @@ -298,14 +293,14 @@ void bnx2x_ets_bw_limit_common(const struct link_params *params) /* Defines the number of consecutive slots for the strict priority */ REG_WR(bp, PBF_REG_NUM_STRICT_ARB_SLOTS, 0); - /** - * Bitmap of 5bits length. Each bit specifies whether the entry behaves - * as strict. Bits 0,1,2 - debug and management entries, 3 - COS0 - * entry, 4 - COS1 entry. - * COS1 | COS0 | DEBUG21 | DEBUG0 | MGMT - * bit4 bit3 bit2 bit1 bit0 - * MCP and debug are strict - */ + /* + * Bitmap of 5bits length. Each bit specifies whether the entry behaves + * as strict. Bits 0,1,2 - debug and management entries, 3 - COS0 + * entry, 4 - COS1 entry. + * COS1 | COS0 | DEBUG21 | DEBUG0 | MGMT + * bit4 bit3 bit2 bit1 bit0 + * MCP and debug are strict + */ REG_WR(bp, NIG_REG_P0_TX_ARB_CLIENT_IS_STRICT, 0x7); /* Upper bound that COS0_WEIGHT can reach in the WFQ arbiter.*/ @@ -329,8 +324,7 @@ void bnx2x_ets_bw_limit(const struct link_params *params, const u32 cos0_bw, if ((0 == total_bw) || (0 == cos0_bw) || (0 == cos1_bw)) { - DP(NETIF_MSG_LINK, - "bnx2x_ets_bw_limit: Total BW can't be zero\n"); + DP(NETIF_MSG_LINK, "Total BW can't be zero\n"); return; } @@ -355,7 +349,7 @@ u8 bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos) u32 val = 0; DP(NETIF_MSG_LINK, "ETS enabled strict configuration\n"); - /** + /* * Bitmap of 5bits length. Each bit specifies whether the entry behaves * as strict. Bits 0,1,2 - debug and management entries, * 3 - COS0 entry, 4 - COS1 entry. @@ -364,7 +358,7 @@ u8 bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos) * MCP and debug are strict */ REG_WR(bp, NIG_REG_P0_TX_ARB_CLIENT_IS_STRICT, 0x1F); - /** + /* * For strict priority entries defines the number of consecutive slots * for the highest priority. */ @@ -377,14 +371,14 @@ u8 bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos) /* Defines the number of consecutive slots for the strict priority */ REG_WR(bp, PBF_REG_HIGH_PRIORITY_COS_NUM, strict_cos); - /** - * mapping between entry priority to client number (0,1,2 -debug and - * management clients, 3 - COS0 client, 4 - COS client)(HIGHEST) - * 3bits client num. - * PRI4 | PRI3 | PRI2 | PRI1 | PRI0 - * dbg0-010 dbg1-001 cos1-100 cos0-011 MCP-000 - * dbg0-010 dbg1-001 cos0-011 cos1-100 MCP-000 - */ + /* + * mapping between entry priority to client number (0,1,2 -debug and + * management clients, 3 - COS0 client, 4 - COS client)(HIGHEST) + * 3bits client num. + * PRI4 | PRI3 | PRI2 | PRI1 | PRI0 + * dbg0-010 dbg1-001 cos1-100 cos0-011 MCP-000 + * dbg0-010 dbg1-001 cos0-011 cos1-100 MCP-000 + */ val = (0 == strict_cos) ? 0x2318 : 0x22E0; REG_WR(bp, NIG_REG_P0_TX_ARB_PRIORITY_CLIENT, val); @@ -471,7 +465,7 @@ void bnx2x_pfc_statistic(struct link_params *params, struct link_vars *vars, /* MAC/PBF section */ /******************************************************************/ static void bnx2x_emac_init(struct link_params *params, - struct link_vars *vars) + struct link_vars *vars) { /* reset and unreset the emac core */ struct bnx2x *bp = params->bp; @@ -481,10 +475,10 @@ static void bnx2x_emac_init(struct link_params *params, u16 timeout; REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR, - (MISC_REGISTERS_RESET_REG_2_RST_EMAC0_HARD_CORE << port)); + (MISC_REGISTERS_RESET_REG_2_RST_EMAC0_HARD_CORE << port)); udelay(5); REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET, - (MISC_REGISTERS_RESET_REG_2_RST_EMAC0_HARD_CORE << port)); + (MISC_REGISTERS_RESET_REG_2_RST_EMAC0_HARD_CORE << port)); /* init emac - use read-modify-write */ /* self clear reset */ @@ -515,7 +509,7 @@ static void bnx2x_emac_init(struct link_params *params, } static u8 bnx2x_emac_enable(struct link_params *params, - struct link_vars *vars, u8 lb) + struct link_vars *vars, u8 lb) { struct bnx2x *bp = params->bp; u8 port = params->port; @@ -527,55 +521,33 @@ static u8 bnx2x_emac_enable(struct link_params *params, /* enable emac and not bmac */ REG_WR(bp, NIG_REG_EGRESS_EMAC0_PORT + port*4, 1); - /* for paladium */ - if (CHIP_REV_IS_EMUL(bp)) { - /* Use lane 1 (of lanes 0-3) */ - REG_WR(bp, NIG_REG_XGXS_LANE_SEL_P0 + port*4, 1); - REG_WR(bp, NIG_REG_XGXS_SERDES0_MODE_SEL + - port*4, 1); - } - /* for fpga */ - else - - if (CHIP_REV_IS_FPGA(bp)) { - /* Use lane 1 (of lanes 0-3) */ - DP(NETIF_MSG_LINK, "bnx2x_emac_enable: Setting FPGA\n"); - - REG_WR(bp, NIG_REG_XGXS_LANE_SEL_P0 + port*4, 1); - REG_WR(bp, NIG_REG_XGXS_SERDES0_MODE_SEL + port*4, - 0); - } else /* ASIC */ if (vars->phy_flags & PHY_XGXS_FLAG) { u32 ser_lane = ((params->lane_config & - PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >> - PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT); + PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >> + PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT); DP(NETIF_MSG_LINK, "XGXS\n"); /* select the master lanes (out of 0-3) */ - REG_WR(bp, NIG_REG_XGXS_LANE_SEL_P0 + - port*4, ser_lane); + REG_WR(bp, NIG_REG_XGXS_LANE_SEL_P0 + port*4, ser_lane); /* select XGXS */ - REG_WR(bp, NIG_REG_XGXS_SERDES0_MODE_SEL + - port*4, 1); + REG_WR(bp, NIG_REG_XGXS_SERDES0_MODE_SEL + port*4, 1); } else { /* SerDes */ DP(NETIF_MSG_LINK, "SerDes\n"); /* select SerDes */ - REG_WR(bp, NIG_REG_XGXS_SERDES0_MODE_SEL + - port*4, 0); + REG_WR(bp, NIG_REG_XGXS_SERDES0_MODE_SEL + port*4, 0); } bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_RX_MODE, - EMAC_RX_MODE_RESET); + EMAC_RX_MODE_RESET); bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE, - EMAC_TX_MODE_RESET); + EMAC_TX_MODE_RESET); if (CHIP_REV_IS_SLOW(bp)) { /* config GMII mode */ val = REG_RD(bp, emac_base + EMAC_REG_EMAC_MODE); - EMAC_WR(bp, EMAC_REG_EMAC_MODE, - (val | EMAC_MODE_PORT_GMII)); + EMAC_WR(bp, EMAC_REG_EMAC_MODE, (val | EMAC_MODE_PORT_GMII)); } else { /* ASIC */ /* pause enable/disable */ bnx2x_bits_dis(bp, emac_base + EMAC_REG_EMAC_RX_MODE, @@ -605,14 +577,14 @@ static u8 bnx2x_emac_enable(struct link_params *params, val = REG_RD(bp, emac_base + EMAC_REG_EMAC_RX_MODE); val |= EMAC_RX_MODE_KEEP_VLAN_TAG | EMAC_RX_MODE_PROMISCUOUS; - /** - * Setting this bit causes MAC control frames (except for pause - * frames) to be passed on for processing. This setting has no - * affect on the operation of the pause frames. This bit effects - * all packets regardless of RX Parser packet sorting logic. - * Turn the PFC off to make sure we are in Xon state before - * enabling it. - */ + /* + * Setting this bit causes MAC control frames (except for pause + * frames) to be passed on for processing. This setting has no + * affect on the operation of the pause frames. This bit effects + * all packets regardless of RX Parser packet sorting logic. + * Turn the PFC off to make sure we are in Xon state before + * enabling it. + */ EMAC_WR(bp, EMAC_REG_RX_PFC_MODE, 0); if (params->feature_config_flags & FEATURE_CONFIG_PFC_ENABLED) { DP(NETIF_MSG_LINK, "PFC is enabled\n"); @@ -666,16 +638,7 @@ static u8 bnx2x_emac_enable(struct link_params *params, REG_WR(bp, NIG_REG_EMAC0_PAUSE_OUT_EN + port*4, val); REG_WR(bp, NIG_REG_EGRESS_EMAC0_OUT_EN + port*4, 0x1); - if (CHIP_REV_IS_EMUL(bp)) { - /* take the BigMac out of reset */ - REG_WR(bp, - GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET, - (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); - - /* enable access for bmac registers */ - REG_WR(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4, 0x1); - } else - REG_WR(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4, 0x0); + REG_WR(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4, 0x0); vars->mac_type = MAC_TYPE_EMAC; return 0; @@ -731,8 +694,7 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params, val |= (1<<5); wb_data[0] = val; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_RX_CONTROL, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_RX_CONTROL, wb_data, 2); udelay(30); /* Tx control */ @@ -768,12 +730,12 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params, REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_PFC_CONTROL, wb_data, 2); - /** - * Set Time (based unit is 512 bit time) between automatic - * re-sending of PP packets amd enable automatic re-send of - * Per-Priroity Packet as long as pp_gen is asserted and - * pp_disable is low. - */ + /* + * Set Time (based unit is 512 bit time) between automatic + * re-sending of PP packets amd enable automatic re-send of + * Per-Priroity Packet as long as pp_gen is asserted and + * pp_disable is low. + */ val = 0x8000; if (params->feature_config_flags & FEATURE_CONFIG_PFC_ENABLED) val |= (1<<16); /* enable automatic re-send */ @@ -781,7 +743,7 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params, wb_data[0] = val; wb_data[1] = 0; REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_TX_PAUSE_CONTROL, - wb_data, 2); + wb_data, 2); /* mac control */ val = 0x3; /* Enable RX and TX */ @@ -795,8 +757,7 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params, wb_data[0] = val; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, wb_data, 2); } static void bnx2x_update_pfc_brb(struct link_params *params, @@ -825,17 +786,25 @@ static void bnx2x_update_pfc_brb(struct link_params *params, full_xon_th = PFC_BRB_MAC_FULL_XON_THRESHOLD_NON_PAUSEABLE; } - /* The number of free blocks below which the pause signal to class 0 - of MAC #n is asserted. n=0,1 */ + /* + * The number of free blocks below which the pause signal to class 0 + * of MAC #n is asserted. n=0,1 + */ REG_WR(bp, BRB1_REG_PAUSE_0_XOFF_THRESHOLD_0 , pause_xoff_th); - /* The number of free blocks above which the pause signal to class 0 - of MAC #n is de-asserted. n=0,1 */ + /* + * The number of free blocks above which the pause signal to class 0 + * of MAC #n is de-asserted. n=0,1 + */ REG_WR(bp, BRB1_REG_PAUSE_0_XON_THRESHOLD_0 , pause_xon_th); - /* The number of free blocks below which the full signal to class 0 - of MAC #n is asserted. n=0,1 */ + /* + * The number of free blocks below which the full signal to class 0 + * of MAC #n is asserted. n=0,1 + */ REG_WR(bp, BRB1_REG_FULL_0_XOFF_THRESHOLD_0 , full_xoff_th); - /* The number of free blocks above which the full signal to class 0 - of MAC #n is de-asserted. n=0,1 */ + /* + * The number of free blocks above which the full signal to class 0 + * of MAC #n is de-asserted. n=0,1 + */ REG_WR(bp, BRB1_REG_FULL_0_XON_THRESHOLD_0 , full_xon_th); if (set_pfc && pfc_params) { @@ -859,25 +828,25 @@ static void bnx2x_update_pfc_brb(struct link_params *params, full_xon_th = PFC_BRB_MAC_FULL_XON_THRESHOLD_NON_PAUSEABLE; } - /** + /* * The number of free blocks below which the pause signal to * class 1 of MAC #n is asserted. n=0,1 - **/ + */ REG_WR(bp, BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0, pause_xoff_th); - /** + /* * The number of free blocks above which the pause signal to * class 1 of MAC #n is de-asserted. n=0,1 - **/ + */ REG_WR(bp, BRB1_REG_PAUSE_1_XON_THRESHOLD_0, pause_xon_th); - /** + /* * The number of free blocks below which the full signal to * class 1 of MAC #n is asserted. n=0,1 - **/ + */ REG_WR(bp, BRB1_REG_FULL_1_XOFF_THRESHOLD_0, full_xoff_th); - /** + /* * The number of free blocks above which the full signal to * class 1 of MAC #n is de-asserted. n=0,1 - **/ + */ REG_WR(bp, BRB1_REG_FULL_1_XON_THRESHOLD_0, full_xon_th); } } @@ -896,7 +865,7 @@ static void bnx2x_update_pfc_nig(struct link_params *params, FEATURE_CONFIG_PFC_ENABLED; DP(NETIF_MSG_LINK, "updating pfc nig parameters\n"); - /** + /* * When NIG_LLH0_XCM_MASK_REG_LLHX_XCM_MASK_BCN bit is set * MAC control frames (that are not pause packets) * will be forwarded to the XCM. @@ -904,7 +873,7 @@ static void bnx2x_update_pfc_nig(struct link_params *params, xcm_mask = REG_RD(bp, port ? NIG_REG_LLH1_XCM_MASK : NIG_REG_LLH0_XCM_MASK); - /** + /* * nig params will override non PFC params, since it's possible to * do transition from PFC to SAFC */ @@ -994,7 +963,7 @@ void bnx2x_update_pfc(struct link_params *params, struct link_vars *vars, struct bnx2x_nig_brb_pfc_port_params *pfc_params) { - /** + /* * The PFC and pause are orthogonal to one another, meaning when * PFC is enabled, the pause are disabled, and when PFC is * disabled, pause are set according to the pause result. @@ -1035,7 +1004,7 @@ void bnx2x_update_pfc(struct link_params *params, static u8 bnx2x_bmac1_enable(struct link_params *params, struct link_vars *vars, - u8 is_lb) + u8 is_lb) { struct bnx2x *bp = params->bp; u8 port = params->port; @@ -1049,9 +1018,8 @@ static u8 bnx2x_bmac1_enable(struct link_params *params, /* XGXS control */ wb_data[0] = 0x3c; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + - BIGMAC_REGISTER_BMAC_XGXS_CONTROL, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_BMAC_XGXS_CONTROL, + wb_data, 2); /* tx MAC SA */ wb_data[0] = ((params->mac_addr[2] << 24) | @@ -1060,8 +1028,7 @@ static u8 bnx2x_bmac1_enable(struct link_params *params, params->mac_addr[5]); wb_data[1] = ((params->mac_addr[0] << 8) | params->mac_addr[1]); - REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_TX_SOURCE_ADDR, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_TX_SOURCE_ADDR, wb_data, 2); /* mac control */ val = 0x3; @@ -1071,43 +1038,30 @@ static u8 bnx2x_bmac1_enable(struct link_params *params, } wb_data[0] = val; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_BMAC_CONTROL, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_BMAC_CONTROL, wb_data, 2); /* set rx mtu */ wb_data[0] = ETH_MAX_JUMBO_PACKET_SIZE + ETH_OVREHEAD; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_RX_MAX_SIZE, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_RX_MAX_SIZE, wb_data, 2); bnx2x_update_pfc_bmac1(params, vars); /* set tx mtu */ wb_data[0] = ETH_MAX_JUMBO_PACKET_SIZE + ETH_OVREHEAD; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_TX_MAX_SIZE, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_TX_MAX_SIZE, wb_data, 2); /* set cnt max size */ wb_data[0] = ETH_MAX_JUMBO_PACKET_SIZE + ETH_OVREHEAD; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_CNT_MAX_SIZE, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_CNT_MAX_SIZE, wb_data, 2); /* configure safc */ wb_data[0] = 0x1000200; wb_data[1] = 0; REG_WR_DMAE(bp, bmac_addr + BIGMAC_REGISTER_RX_LLFC_MSG_FLDS, wb_data, 2); - /* fix for emulation */ - if (CHIP_REV_IS_EMUL(bp)) { - wb_data[0] = 0xf000; - wb_data[1] = 0; - REG_WR_DMAE(bp, - bmac_addr + BIGMAC_REGISTER_TX_PAUSE_THRESHOLD, - wb_data, 2); - } - return 0; } @@ -1126,16 +1080,14 @@ static u8 bnx2x_bmac2_enable(struct link_params *params, wb_data[0] = 0; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, wb_data, 2); udelay(30); /* XGXS control: Reset phy HW, MDIO registers, PHY PLL and BMAC */ wb_data[0] = 0x3c; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + - BIGMAC2_REGISTER_BMAC_XGXS_CONTROL, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_XGXS_CONTROL, + wb_data, 2); udelay(30); @@ -1147,7 +1099,7 @@ static u8 bnx2x_bmac2_enable(struct link_params *params, wb_data[1] = ((params->mac_addr[0] << 8) | params->mac_addr[1]); REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_TX_SOURCE_ADDR, - wb_data, 2); + wb_data, 2); udelay(30); @@ -1155,27 +1107,24 @@ static u8 bnx2x_bmac2_enable(struct link_params *params, wb_data[0] = 0x1000200; wb_data[1] = 0; REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_RX_LLFC_MSG_FLDS, - wb_data, 2); + wb_data, 2); udelay(30); /* set rx mtu */ wb_data[0] = ETH_MAX_JUMBO_PACKET_SIZE + ETH_OVREHEAD; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_RX_MAX_SIZE, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_RX_MAX_SIZE, wb_data, 2); udelay(30); /* set tx mtu */ wb_data[0] = ETH_MAX_JUMBO_PACKET_SIZE + ETH_OVREHEAD; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_TX_MAX_SIZE, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_TX_MAX_SIZE, wb_data, 2); udelay(30); /* set cnt max size */ wb_data[0] = ETH_MAX_JUMBO_PACKET_SIZE + ETH_OVREHEAD - 2; wb_data[1] = 0; - REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_CNT_MAX_SIZE, - wb_data, 2); + REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_CNT_MAX_SIZE, wb_data, 2); udelay(30); bnx2x_update_pfc_bmac2(params, vars, is_lb); @@ -1191,11 +1140,11 @@ static u8 bnx2x_bmac_enable(struct link_params *params, u32 val; /* reset and unreset the BigMac */ REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR, - (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); + (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); msleep(1); REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET, - (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); + (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); /* enable access for bmac registers */ REG_WR(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4, 0x1); @@ -1230,15 +1179,14 @@ static void bnx2x_update_mng(struct link_params *params, u32 link_status) struct bnx2x *bp = params->bp; REG_WR(bp, params->shmem_base + - offsetof(struct shmem_region, - port_mb[params->port].link_status), - link_status); + offsetof(struct shmem_region, + port_mb[params->port].link_status), link_status); } static void bnx2x_bmac_rx_disable(struct bnx2x *bp, u8 port) { u32 bmac_addr = port ? NIG_REG_INGRESS_BMAC1_MEM : - NIG_REG_INGRESS_BMAC0_MEM; + NIG_REG_INGRESS_BMAC0_MEM; u32 wb_data[2]; u32 nig_bmac_enable = REG_RD(bp, NIG_REG_BMAC0_REGS_OUT_EN + port*4); @@ -1250,12 +1198,12 @@ static void bnx2x_bmac_rx_disable(struct bnx2x *bp, u8 port) if (CHIP_IS_E2(bp)) { /* Clear Rx Enable bit in BMAC_CONTROL register */ REG_RD_DMAE(bp, bmac_addr + - BIGMAC2_REGISTER_BMAC_CONTROL, - wb_data, 2); + BIGMAC2_REGISTER_BMAC_CONTROL, + wb_data, 2); wb_data[0] &= ~BMAC_CONTROL_RX_ENABLE; REG_WR_DMAE(bp, bmac_addr + - BIGMAC2_REGISTER_BMAC_CONTROL, - wb_data, 2); + BIGMAC2_REGISTER_BMAC_CONTROL, + wb_data, 2); } else { /* Clear Rx Enable bit in BMAC_CONTROL register */ REG_RD_DMAE(bp, bmac_addr + @@ -1271,7 +1219,7 @@ static void bnx2x_bmac_rx_disable(struct bnx2x *bp, u8 port) } static u8 bnx2x_pbf_update(struct link_params *params, u32 flow_ctrl, - u32 line_speed) + u32 line_speed) { struct bnx2x *bp = params->bp; u8 port = params->port; @@ -1308,7 +1256,7 @@ static u8 bnx2x_pbf_update(struct link_params *params, u32 flow_ctrl, /* update threshold */ REG_WR(bp, PBF_REG_P0_ARB_THRSH + port*4, 0); /* update init credit */ - init_crd = 778; /* (800-18-4) */ + init_crd = 778; /* (800-18-4) */ } else { u32 thresh = (ETH_MAX_JUMBO_PACKET_SIZE + @@ -1353,6 +1301,23 @@ static u8 bnx2x_pbf_update(struct link_params *params, u32 flow_ctrl, return 0; } +/* + * get_emac_base + * + * @param cb + * @param mdc_mdio_access + * @param port + * + * @return u32 + * + * This function selects the MDC/MDIO access (through emac0 or + * emac1) depend on the mdc_mdio_access, port, port swapped. Each + * phy has a default access mode, which could also be overridden + * by nvram configuration. This parameter, whether this is the + * default phy configuration, or the nvram overrun + * configuration, is passed here as mdc_mdio_access and selects + * the emac_base for the CL45 read/writes operations + */ static u32 bnx2x_get_emac_base(struct bnx2x *bp, u32 mdc_mdio_access, u8 port) { @@ -1385,13 +1350,16 @@ static u32 bnx2x_get_emac_base(struct bnx2x *bp, } -u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, - u8 devad, u16 reg, u16 val) +/******************************************************************/ +/* CL45 access functions */ +/******************************************************************/ +static u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, + u8 devad, u16 reg, u16 val) { u32 tmp, saved_mode; u8 i, rc = 0; - - /* set clause 45 mode, slow down the MDIO clock to 2.5MHz + /* + * Set clause 45 mode, slow down the MDIO clock to 2.5MHz * (a value of 49==0x31) and make sure that the AUTO poll is off */ @@ -1414,8 +1382,7 @@ u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, for (i = 0; i < 50; i++) { udelay(10); - tmp = REG_RD(bp, phy->mdio_ctrl + - EMAC_REG_EMAC_MDIO_COMM); + tmp = REG_RD(bp, phy->mdio_ctrl + EMAC_REG_EMAC_MDIO_COMM); if (!(tmp & EMAC_MDIO_COMM_START_BUSY)) { udelay(5); break; @@ -1423,6 +1390,7 @@ u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, } if (tmp & EMAC_MDIO_COMM_START_BUSY) { DP(NETIF_MSG_LINK, "write phy register failed\n"); + netdev_err(bp->dev, "MDC/MDIO access timeout\n"); rc = -EFAULT; } else { /* data */ @@ -1435,7 +1403,7 @@ u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, udelay(10); tmp = REG_RD(bp, phy->mdio_ctrl + - EMAC_REG_EMAC_MDIO_COMM); + EMAC_REG_EMAC_MDIO_COMM); if (!(tmp & EMAC_MDIO_COMM_START_BUSY)) { udelay(5); break; @@ -1443,6 +1411,7 @@ u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, } if (tmp & EMAC_MDIO_COMM_START_BUSY) { DP(NETIF_MSG_LINK, "write phy register failed\n"); + netdev_err(bp->dev, "MDC/MDIO access timeout\n"); rc = -EFAULT; } } @@ -1453,20 +1422,20 @@ u8 bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy, return rc; } -u8 bnx2x_cl45_read(struct bnx2x *bp, struct bnx2x_phy *phy, - u8 devad, u16 reg, u16 *ret_val) +static u8 bnx2x_cl45_read(struct bnx2x *bp, struct bnx2x_phy *phy, + u8 devad, u16 reg, u16 *ret_val) { u32 val, saved_mode; u16 i; u8 rc = 0; - - /* set clause 45 mode, slow down the MDIO clock to 2.5MHz + /* + * Set clause 45 mode, slow down the MDIO clock to 2.5MHz * (a value of 49==0x31) and make sure that the AUTO poll is off */ saved_mode = REG_RD(bp, phy->mdio_ctrl + EMAC_REG_EMAC_MDIO_MODE); val = saved_mode & ~((EMAC_MDIO_MODE_AUTO_POLL | - EMAC_MDIO_MODE_CLOCK_CNT)); + EMAC_MDIO_MODE_CLOCK_CNT)); val |= (EMAC_MDIO_MODE_CLAUSE_45 | (49L << EMAC_MDIO_MODE_CLOCK_CNT_BITSHIFT)); REG_WR(bp, phy->mdio_ctrl + EMAC_REG_EMAC_MDIO_MODE, val); @@ -1490,7 +1459,7 @@ u8 bnx2x_cl45_read(struct bnx2x *bp, struct bnx2x_phy *phy, } if (val & EMAC_MDIO_COMM_START_BUSY) { DP(NETIF_MSG_LINK, "read phy register failed\n"); - + netdev_err(bp->dev, "MDC/MDIO access timeout\n"); *ret_val = 0; rc = -EFAULT; @@ -1505,7 +1474,7 @@ u8 bnx2x_cl45_read(struct bnx2x *bp, struct bnx2x_phy *phy, udelay(10); val = REG_RD(bp, phy->mdio_ctrl + - EMAC_REG_EMAC_MDIO_COMM); + EMAC_REG_EMAC_MDIO_COMM); if (!(val & EMAC_MDIO_COMM_START_BUSY)) { *ret_val = (u16)(val & EMAC_MDIO_COMM_DATA); break; @@ -1513,7 +1482,7 @@ u8 bnx2x_cl45_read(struct bnx2x *bp, struct bnx2x_phy *phy, } if (val & EMAC_MDIO_COMM_START_BUSY) { DP(NETIF_MSG_LINK, "read phy register failed\n"); - + netdev_err(bp->dev, "MDC/MDIO access timeout\n"); *ret_val = 0; rc = -EFAULT; } @@ -1529,7 +1498,7 @@ u8 bnx2x_phy_read(struct link_params *params, u8 phy_addr, u8 devad, u16 reg, u16 *ret_val) { u8 phy_index; - /** + /* * Probe for the phy according to the given phy_addr, and execute * the read request on it */ @@ -1547,7 +1516,7 @@ u8 bnx2x_phy_write(struct link_params *params, u8 phy_addr, u8 devad, u16 reg, u16 val) { u8 phy_index; - /** + /* * Probe for the phy according to the given phy_addr, and execute * the write request on it */ @@ -1576,16 +1545,15 @@ static void bnx2x_set_aer_mmd_xgxs(struct link_params *params, aer_val = 0x3800 + offset - 1; else aer_val = 0x3800 + offset; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_AER_BLOCK, - MDIO_AER_BLOCK_AER_REG, aer_val); + CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK, + MDIO_AER_BLOCK_AER_REG, aer_val); } static void bnx2x_set_aer_mmd_serdes(struct bnx2x *bp, struct bnx2x_phy *phy) { - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_AER_BLOCK, - MDIO_AER_BLOCK_AER_REG, 0x3800); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_AER_BLOCK, + MDIO_AER_BLOCK_AER_REG, 0x3800); } /******************************************************************/ @@ -1621,9 +1589,8 @@ static void bnx2x_serdes_deassert(struct bnx2x *bp, u8 port) bnx2x_set_serdes_access(bp, port); - REG_WR(bp, NIG_REG_SERDES0_CTRL_MD_DEVAD + - port*0x10, - DEFAULT_PHY_DEV_ADDR); + REG_WR(bp, NIG_REG_SERDES0_CTRL_MD_DEVAD + port*0x10, + DEFAULT_PHY_DEV_ADDR); } static void bnx2x_xgxs_deassert(struct link_params *params) @@ -1641,23 +1608,22 @@ static void bnx2x_xgxs_deassert(struct link_params *params) udelay(500); REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_3_SET, val); - REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_ST + - port*0x18, 0); + REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_ST + port*0x18, 0); REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_DEVAD + port*0x18, - params->phy[INT_PHY].def_md_devad); + params->phy[INT_PHY].def_md_devad); } void bnx2x_link_status_update(struct link_params *params, - struct link_vars *vars) + struct link_vars *vars) { struct bnx2x *bp = params->bp; u8 link_10g; u8 port = params->port; vars->link_status = REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, - port_mb[port].link_status)); + offsetof(struct shmem_region, + port_mb[port].link_status)); vars->link_up = (vars->link_status & LINK_STATUS_LINK_UP); @@ -1667,7 +1633,7 @@ void bnx2x_link_status_update(struct link_params *params, vars->phy_link_up = 1; vars->duplex = DUPLEX_FULL; switch (vars->link_status & - LINK_STATUS_SPEED_AND_DUPLEX_MASK) { + LINK_STATUS_SPEED_AND_DUPLEX_MASK) { case LINK_10THD: vars->duplex = DUPLEX_HALF; /* fall thru */ @@ -1779,20 +1745,20 @@ static void bnx2x_set_master_ln(struct link_params *params, { struct bnx2x *bp = params->bp; u16 new_master_ln, ser_lane; - ser_lane = ((params->lane_config & + ser_lane = ((params->lane_config & PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >> - PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT); + PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT); /* set the master_ln for AN */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2, - MDIO_XGXS_BLOCK2_TEST_MODE_LANE, - &new_master_ln); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2, + MDIO_XGXS_BLOCK2_TEST_MODE_LANE, + &new_master_ln); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2 , - MDIO_XGXS_BLOCK2_TEST_MODE_LANE, - (new_master_ln | ser_lane)); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2 , + MDIO_XGXS_BLOCK2_TEST_MODE_LANE, + (new_master_ln | ser_lane)); } static u8 bnx2x_reset_unicore(struct link_params *params, @@ -1802,17 +1768,16 @@ static u8 bnx2x_reset_unicore(struct link_params *params, struct bnx2x *bp = params->bp; u16 mii_control; u16 i; - - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, &mii_control); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, &mii_control); /* reset the unicore */ - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, - (mii_control | - MDIO_COMBO_IEEO_MII_CONTROL_RESET)); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, + (mii_control | + MDIO_COMBO_IEEO_MII_CONTROL_RESET)); if (set_serdes) bnx2x_set_serdes_access(bp, params->port); @@ -1821,10 +1786,10 @@ static u8 bnx2x_reset_unicore(struct link_params *params, udelay(5); /* the reset erased the previous bank value */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, - &mii_control); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, + &mii_control); if (!(mii_control & MDIO_COMBO_IEEO_MII_CONTROL_RESET)) { udelay(5); @@ -1832,6 +1797,9 @@ static u8 bnx2x_reset_unicore(struct link_params *params, } } + netdev_err(bp->dev, "Warning: PHY was not initialized," + " Port %d\n", + params->port); DP(NETIF_MSG_LINK, "BUG! XGXS is still in reset!\n"); return -EINVAL; @@ -1841,43 +1809,45 @@ static void bnx2x_set_swap_lanes(struct link_params *params, struct bnx2x_phy *phy) { struct bnx2x *bp = params->bp; - /* Each two bits represents a lane number: - No swap is 0123 => 0x1b no need to enable the swap */ + /* + * Each two bits represents a lane number: + * No swap is 0123 => 0x1b no need to enable the swap + */ u16 ser_lane, rx_lane_swap, tx_lane_swap; ser_lane = ((params->lane_config & - PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >> - PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT); + PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >> + PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT); rx_lane_swap = ((params->lane_config & - PORT_HW_CFG_LANE_SWAP_CFG_RX_MASK) >> - PORT_HW_CFG_LANE_SWAP_CFG_RX_SHIFT); + PORT_HW_CFG_LANE_SWAP_CFG_RX_MASK) >> + PORT_HW_CFG_LANE_SWAP_CFG_RX_SHIFT); tx_lane_swap = ((params->lane_config & - PORT_HW_CFG_LANE_SWAP_CFG_TX_MASK) >> - PORT_HW_CFG_LANE_SWAP_CFG_TX_SHIFT); + PORT_HW_CFG_LANE_SWAP_CFG_TX_MASK) >> + PORT_HW_CFG_LANE_SWAP_CFG_TX_SHIFT); if (rx_lane_swap != 0x1b) { - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2, - MDIO_XGXS_BLOCK2_RX_LN_SWAP, - (rx_lane_swap | - MDIO_XGXS_BLOCK2_RX_LN_SWAP_ENABLE | - MDIO_XGXS_BLOCK2_RX_LN_SWAP_FORCE_ENABLE)); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2, + MDIO_XGXS_BLOCK2_RX_LN_SWAP, + (rx_lane_swap | + MDIO_XGXS_BLOCK2_RX_LN_SWAP_ENABLE | + MDIO_XGXS_BLOCK2_RX_LN_SWAP_FORCE_ENABLE)); } else { - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2, - MDIO_XGXS_BLOCK2_RX_LN_SWAP, 0); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2, + MDIO_XGXS_BLOCK2_RX_LN_SWAP, 0); } if (tx_lane_swap != 0x1b) { - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2, - MDIO_XGXS_BLOCK2_TX_LN_SWAP, - (tx_lane_swap | - MDIO_XGXS_BLOCK2_TX_LN_SWAP_ENABLE)); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2, + MDIO_XGXS_BLOCK2_TX_LN_SWAP, + (tx_lane_swap | + MDIO_XGXS_BLOCK2_TX_LN_SWAP_ENABLE)); } else { - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2, - MDIO_XGXS_BLOCK2_TX_LN_SWAP, 0); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2, + MDIO_XGXS_BLOCK2_TX_LN_SWAP, 0); } } @@ -1886,66 +1856,66 @@ static void bnx2x_set_parallel_detection(struct bnx2x_phy *phy, { struct bnx2x *bp = params->bp; u16 control2; - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_CONTROL2, - &control2); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_CONTROL2, + &control2); if (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_1G) control2 |= MDIO_SERDES_DIGITAL_A_1000X_CONTROL2_PRL_DT_EN; else control2 &= ~MDIO_SERDES_DIGITAL_A_1000X_CONTROL2_PRL_DT_EN; DP(NETIF_MSG_LINK, "phy->speed_cap_mask = 0x%x, control2 = 0x%x\n", phy->speed_cap_mask, control2); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_CONTROL2, - control2); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_CONTROL2, + control2); if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT) && (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_10G)) { DP(NETIF_MSG_LINK, "XGXS\n"); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_10G_PARALLEL_DETECT, - MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_LINK, - MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_LINK_CNT); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_10G_PARALLEL_DETECT, + MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_LINK, + MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_LINK_CNT); - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_10G_PARALLEL_DETECT, - MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_CONTROL, - &control2); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_10G_PARALLEL_DETECT, + MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_CONTROL, + &control2); control2 |= MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_CONTROL_PARDET10G_EN; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_10G_PARALLEL_DETECT, - MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_CONTROL, - control2); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_10G_PARALLEL_DETECT, + MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_CONTROL, + control2); /* Disable parallel detection of HiG */ - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_XGXS_BLOCK2, - MDIO_XGXS_BLOCK2_UNICORE_MODE_10G, - MDIO_XGXS_BLOCK2_UNICORE_MODE_10G_CX4_XGXS | - MDIO_XGXS_BLOCK2_UNICORE_MODE_10G_HIGIG_XGXS); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_XGXS_BLOCK2, + MDIO_XGXS_BLOCK2_UNICORE_MODE_10G, + MDIO_XGXS_BLOCK2_UNICORE_MODE_10G_CX4_XGXS | + MDIO_XGXS_BLOCK2_UNICORE_MODE_10G_HIGIG_XGXS); } } static void bnx2x_set_autoneg(struct bnx2x_phy *phy, struct link_params *params, - struct link_vars *vars, - u8 enable_cl73) + struct link_vars *vars, + u8 enable_cl73) { struct bnx2x *bp = params->bp; u16 reg_val; /* CL37 Autoneg */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, ®_val); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, ®_val); /* CL37 Autoneg Enabled */ if (vars->line_speed == SPEED_AUTO_NEG) @@ -1954,15 +1924,15 @@ static void bnx2x_set_autoneg(struct bnx2x_phy *phy, reg_val &= ~(MDIO_COMBO_IEEO_MII_CONTROL_AN_EN | MDIO_COMBO_IEEO_MII_CONTROL_RESTART_AN); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, reg_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, reg_val); /* Enable/Disable Autodetection */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, ®_val); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, ®_val); reg_val &= ~(MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_SIGNAL_DETECT_EN | MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_INVERT_SIGNAL_DETECT); reg_val |= MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_FIBER_MODE; @@ -1971,14 +1941,14 @@ static void bnx2x_set_autoneg(struct bnx2x_phy *phy, else reg_val &= ~MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_AUTODET; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, reg_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, reg_val); /* Enable TetonII and BAM autoneg */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_BAM_NEXT_PAGE, - MDIO_BAM_NEXT_PAGE_MP5_NEXT_PAGE_CTRL, + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_BAM_NEXT_PAGE, + MDIO_BAM_NEXT_PAGE_MP5_NEXT_PAGE_CTRL, ®_val); if (vars->line_speed == SPEED_AUTO_NEG) { /* Enable BAM aneg Mode and TetonII aneg Mode */ @@ -1989,20 +1959,20 @@ static void bnx2x_set_autoneg(struct bnx2x_phy *phy, reg_val &= ~(MDIO_BAM_NEXT_PAGE_MP5_NEXT_PAGE_CTRL_BAM_MODE | MDIO_BAM_NEXT_PAGE_MP5_NEXT_PAGE_CTRL_TETON_AN); } - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_BAM_NEXT_PAGE, - MDIO_BAM_NEXT_PAGE_MP5_NEXT_PAGE_CTRL, - reg_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_BAM_NEXT_PAGE, + MDIO_BAM_NEXT_PAGE_MP5_NEXT_PAGE_CTRL, + reg_val); if (enable_cl73) { /* Enable Cl73 FSM status bits */ - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_USERB0, - MDIO_CL73_USERB0_CL73_UCTRL, - 0xe); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_USERB0, + MDIO_CL73_USERB0_CL73_UCTRL, + 0xe); /* Enable BAM Station Manager*/ - CL45_WR_OVER_CL22(bp, phy, + CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_CL73_USERB0, MDIO_CL73_USERB0_CL73_BAM_CTRL1, MDIO_CL73_USERB0_CL73_BAM_CTRL1_BAM_EN | @@ -2010,10 +1980,10 @@ static void bnx2x_set_autoneg(struct bnx2x_phy *phy, MDIO_CL73_USERB0_CL73_BAM_CTRL1_BAM_NP_AFTER_BP_EN); /* Advertise CL73 link speeds */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB1, - MDIO_CL73_IEEEB1_AN_ADV2, - ®_val); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB1, + MDIO_CL73_IEEEB1_AN_ADV2, + ®_val); if (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_10G) reg_val |= MDIO_CL73_IEEEB1_AN_ADV2_ADVR_10G_KX4; @@ -2021,10 +1991,10 @@ static void bnx2x_set_autoneg(struct bnx2x_phy *phy, PORT_HW_CFG_SPEED_CAPABILITY_D0_1G) reg_val |= MDIO_CL73_IEEEB1_AN_ADV2_ADVR_1000M_KX; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB1, - MDIO_CL73_IEEEB1_AN_ADV2, - reg_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB1, + MDIO_CL73_IEEEB1_AN_ADV2, + reg_val); /* CL73 Autoneg Enabled */ reg_val = MDIO_CL73_IEEEB0_CL73_AN_CONTROL_AN_EN; @@ -2032,37 +2002,39 @@ static void bnx2x_set_autoneg(struct bnx2x_phy *phy, } else /* CL73 Autoneg Disabled */ reg_val = 0; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB0, - MDIO_CL73_IEEEB0_CL73_AN_CONTROL, reg_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB0, + MDIO_CL73_IEEEB0_CL73_AN_CONTROL, reg_val); } /* program SerDes, forced speed */ static void bnx2x_program_serdes(struct bnx2x_phy *phy, struct link_params *params, - struct link_vars *vars) + struct link_vars *vars) { struct bnx2x *bp = params->bp; u16 reg_val; /* program duplex, disable autoneg and sgmii*/ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, ®_val); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, ®_val); reg_val &= ~(MDIO_COMBO_IEEO_MII_CONTROL_FULL_DUPLEX | MDIO_COMBO_IEEO_MII_CONTROL_AN_EN | MDIO_COMBO_IEEO_MII_CONTROL_MAN_SGMII_SP_MASK); if (phy->req_duplex == DUPLEX_FULL) reg_val |= MDIO_COMBO_IEEO_MII_CONTROL_FULL_DUPLEX; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, reg_val); - - /* program speed - - needed only if the speed is greater than 1G (2.5G or 10G) */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_MISC1, ®_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, reg_val); + + /* + * program speed + * - needed only if the speed is greater than 1G (2.5G or 10G) + */ + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_MISC1, ®_val); /* clearing the speed value before setting the right speed */ DP(NETIF_MSG_LINK, "MDIO_REG_BANK_SERDES_DIGITAL = 0x%x\n", reg_val); @@ -2083,9 +2055,9 @@ static void bnx2x_program_serdes(struct bnx2x_phy *phy, MDIO_SERDES_DIGITAL_MISC1_FORCE_SPEED_13G; } - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_MISC1, reg_val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_MISC1, reg_val); } @@ -2102,13 +2074,13 @@ static void bnx2x_set_brcm_cl37_advertisment(struct bnx2x_phy *phy, val |= MDIO_OVER_1G_UP1_2_5G; if (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_10G) val |= MDIO_OVER_1G_UP1_10G; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_OVER_1G, - MDIO_OVER_1G_UP1, val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_OVER_1G, + MDIO_OVER_1G_UP1, val); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_OVER_1G, - MDIO_OVER_1G_UP3, 0x400); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_OVER_1G, + MDIO_OVER_1G_UP3, 0x400); } static void bnx2x_calc_ieee_aneg_adv(struct bnx2x_phy *phy, @@ -2116,22 +2088,21 @@ static void bnx2x_calc_ieee_aneg_adv(struct bnx2x_phy *phy, { struct bnx2x *bp = params->bp; *ieee_fc = MDIO_COMBO_IEEE0_AUTO_NEG_ADV_FULL_DUPLEX; - /* resolve pause mode and advertisement - * Please refer to Table 28B-3 of the 802.3ab-1999 spec */ + /* + * Resolve pause mode and advertisement. + * Please refer to Table 28B-3 of the 802.3ab-1999 spec + */ switch (phy->req_flow_ctrl) { case BNX2X_FLOW_CTRL_AUTO: - if (params->req_fc_auto_adv == BNX2X_FLOW_CTRL_BOTH) { - *ieee_fc |= - MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH; - } else { + if (params->req_fc_auto_adv == BNX2X_FLOW_CTRL_BOTH) + *ieee_fc |= MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH; + else *ieee_fc |= - MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC; - } + MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC; break; case BNX2X_FLOW_CTRL_TX: - *ieee_fc |= - MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC; + *ieee_fc |= MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC; break; case BNX2X_FLOW_CTRL_RX: @@ -2149,23 +2120,23 @@ static void bnx2x_calc_ieee_aneg_adv(struct bnx2x_phy *phy, static void bnx2x_set_ieee_aneg_advertisment(struct bnx2x_phy *phy, struct link_params *params, - u16 ieee_fc) + u16 ieee_fc) { struct bnx2x *bp = params->bp; u16 val; /* for AN, we are always publishing full duplex */ - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_AUTO_NEG_ADV, ieee_fc); - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB1, - MDIO_CL73_IEEEB1_AN_ADV1, &val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_AUTO_NEG_ADV, ieee_fc); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB1, + MDIO_CL73_IEEEB1_AN_ADV1, &val); val &= ~MDIO_CL73_IEEEB1_AN_ADV1_PAUSE_BOTH; val |= ((ieee_fc<<3) & MDIO_CL73_IEEEB1_AN_ADV1_PAUSE_MASK); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB1, - MDIO_CL73_IEEEB1_AN_ADV1, val); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB1, + MDIO_CL73_IEEEB1_AN_ADV1, val); } static void bnx2x_restart_autoneg(struct bnx2x_phy *phy, @@ -2179,67 +2150,67 @@ static void bnx2x_restart_autoneg(struct bnx2x_phy *phy, /* Enable and restart BAM/CL37 aneg */ if (enable_cl73) { - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB0, - MDIO_CL73_IEEEB0_CL73_AN_CONTROL, - &mii_control); - - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB0, - MDIO_CL73_IEEEB0_CL73_AN_CONTROL, - (mii_control | - MDIO_CL73_IEEEB0_CL73_AN_CONTROL_AN_EN | - MDIO_CL73_IEEEB0_CL73_AN_CONTROL_RESTART_AN)); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB0, + MDIO_CL73_IEEEB0_CL73_AN_CONTROL, + &mii_control); + + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB0, + MDIO_CL73_IEEEB0_CL73_AN_CONTROL, + (mii_control | + MDIO_CL73_IEEEB0_CL73_AN_CONTROL_AN_EN | + MDIO_CL73_IEEEB0_CL73_AN_CONTROL_RESTART_AN)); } else { - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, - &mii_control); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, + &mii_control); DP(NETIF_MSG_LINK, "bnx2x_restart_autoneg mii_control before = 0x%x\n", mii_control); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, - (mii_control | - MDIO_COMBO_IEEO_MII_CONTROL_AN_EN | - MDIO_COMBO_IEEO_MII_CONTROL_RESTART_AN)); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, + (mii_control | + MDIO_COMBO_IEEO_MII_CONTROL_AN_EN | + MDIO_COMBO_IEEO_MII_CONTROL_RESTART_AN)); } } static void bnx2x_initialize_sgmii_process(struct bnx2x_phy *phy, struct link_params *params, - struct link_vars *vars) + struct link_vars *vars) { struct bnx2x *bp = params->bp; u16 control1; /* in SGMII mode, the unicore is always slave */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, - &control1); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, + &control1); control1 |= MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_INVERT_SIGNAL_DETECT; /* set sgmii mode (and not fiber) */ control1 &= ~(MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_FIBER_MODE | MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_AUTODET | MDIO_SERDES_DIGITAL_A_1000X_CONTROL1_MSTR_MODE); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, - control1); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_CONTROL1, + control1); /* if forced speed */ if (!(vars->line_speed == SPEED_AUTO_NEG)) { /* set speed, disable autoneg */ u16 mii_control; - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, - &mii_control); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, + &mii_control); mii_control &= ~(MDIO_COMBO_IEEO_MII_CONTROL_AN_EN | MDIO_COMBO_IEEO_MII_CONTROL_MAN_SGMII_SP_MASK| MDIO_COMBO_IEEO_MII_CONTROL_FULL_DUPLEX); @@ -2267,10 +2238,10 @@ static void bnx2x_initialize_sgmii_process(struct bnx2x_phy *phy, if (phy->req_duplex == DUPLEX_FULL) mii_control |= MDIO_COMBO_IEEO_MII_CONTROL_FULL_DUPLEX; - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_MII_CONTROL, - mii_control); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_MII_CONTROL, + mii_control); } else { /* AN mode */ /* enable and restart AN */ @@ -2285,19 +2256,19 @@ static void bnx2x_initialize_sgmii_process(struct bnx2x_phy *phy, static void bnx2x_pause_resolve(struct link_vars *vars, u32 pause_result) { /* LD LP */ - switch (pause_result) { /* ASYM P ASYM P */ - case 0xb: /* 1 0 1 1 */ + switch (pause_result) { /* ASYM P ASYM P */ + case 0xb: /* 1 0 1 1 */ vars->flow_ctrl = BNX2X_FLOW_CTRL_TX; break; - case 0xe: /* 1 1 1 0 */ + case 0xe: /* 1 1 1 0 */ vars->flow_ctrl = BNX2X_FLOW_CTRL_RX; break; - case 0x5: /* 0 1 0 1 */ - case 0x7: /* 0 1 1 1 */ - case 0xd: /* 1 1 0 1 */ - case 0xf: /* 1 1 1 1 */ + case 0x5: /* 0 1 0 1 */ + case 0x7: /* 0 1 1 1 */ + case 0xd: /* 1 1 0 1 */ + case 0xf: /* 1 1 1 1 */ vars->flow_ctrl = BNX2X_FLOW_CTRL_BOTH; break; @@ -2317,24 +2288,24 @@ static u8 bnx2x_direct_parallel_detect_used(struct bnx2x_phy *phy, u16 pd_10g, status2_1000x; if (phy->req_line_speed != SPEED_AUTO_NEG) return 0; - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_STATUS2, - &status2_1000x); - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_SERDES_DIGITAL, - MDIO_SERDES_DIGITAL_A_1000X_STATUS2, - &status2_1000x); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_STATUS2, + &status2_1000x); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_SERDES_DIGITAL, + MDIO_SERDES_DIGITAL_A_1000X_STATUS2, + &status2_1000x); if (status2_1000x & MDIO_SERDES_DIGITAL_A_1000X_STATUS2_AN_DISABLED) { DP(NETIF_MSG_LINK, "1G parallel detect link on port %d\n", params->port); return 1; } - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_10G_PARALLEL_DETECT, - MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_STATUS, - &pd_10g); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_10G_PARALLEL_DETECT, + MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_STATUS, + &pd_10g); if (pd_10g & MDIO_10G_PARALLEL_DETECT_PAR_DET_10G_STATUS_PD_LINK) { DP(NETIF_MSG_LINK, "10G parallel detect link on port %d\n", @@ -2373,14 +2344,14 @@ static void bnx2x_flow_ctrl_resolve(struct bnx2x_phy *phy, (MDIO_GP_STATUS_TOP_AN_STATUS1_CL73_AUTONEG_COMPLETE | MDIO_GP_STATUS_TOP_AN_STATUS1_CL73_MR_LP_NP_AN_ABLE)) { - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB1, - MDIO_CL73_IEEEB1_AN_ADV1, - &ld_pause); - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB1, - MDIO_CL73_IEEEB1_AN_LP_ADV1, - &lp_pause); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB1, + MDIO_CL73_IEEEB1_AN_ADV1, + &ld_pause); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB1, + MDIO_CL73_IEEEB1_AN_LP_ADV1, + &lp_pause); pause_result = (ld_pause & MDIO_CL73_IEEEB1_AN_ADV1_PAUSE_MASK) >> 8; @@ -2390,18 +2361,18 @@ static void bnx2x_flow_ctrl_resolve(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "pause_result CL73 0x%x\n", pause_result); } else { - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_AUTO_NEG_ADV, - &ld_pause); - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_COMBO_IEEE0, - MDIO_COMBO_IEEE0_AUTO_NEG_LINK_PARTNER_ABILITY1, - &lp_pause); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_AUTO_NEG_ADV, + &ld_pause); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_COMBO_IEEE0, + MDIO_COMBO_IEEE0_AUTO_NEG_LINK_PARTNER_ABILITY1, + &lp_pause); pause_result = (ld_pause & MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_MASK)>>5; pause_result |= (lp_pause & - MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_MASK)>>7; + MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_MASK)>>7; DP(NETIF_MSG_LINK, "pause_result CL37 0x%x\n", pause_result); } @@ -2417,25 +2388,25 @@ static void bnx2x_check_fallback_to_cl37(struct bnx2x_phy *phy, u16 rx_status, ustat_val, cl37_fsm_recieved; DP(NETIF_MSG_LINK, "bnx2x_check_fallback_to_cl37\n"); /* Step 1: Make sure signal is detected */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_RX0, - MDIO_RX0_RX_STATUS, - &rx_status); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_RX0, + MDIO_RX0_RX_STATUS, + &rx_status); if ((rx_status & MDIO_RX0_RX_STATUS_SIGDET) != (MDIO_RX0_RX_STATUS_SIGDET)) { DP(NETIF_MSG_LINK, "Signal is not detected. Restoring CL73." "rx_status(0x80b0) = 0x%x\n", rx_status); - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB0, - MDIO_CL73_IEEEB0_CL73_AN_CONTROL, - MDIO_CL73_IEEEB0_CL73_AN_CONTROL_AN_EN); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB0, + MDIO_CL73_IEEEB0_CL73_AN_CONTROL, + MDIO_CL73_IEEEB0_CL73_AN_CONTROL_AN_EN); return; } /* Step 2: Check CL73 state machine */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_USERB0, - MDIO_CL73_USERB0_CL73_USTAT1, - &ustat_val); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_USERB0, + MDIO_CL73_USERB0_CL73_USTAT1, + &ustat_val); if ((ustat_val & (MDIO_CL73_USERB0_CL73_USTAT1_LINK_STATUS_CHECK | MDIO_CL73_USERB0_CL73_USTAT1_AN_GOOD_CHECK_BAM37)) != @@ -2445,12 +2416,14 @@ static void bnx2x_check_fallback_to_cl37(struct bnx2x_phy *phy, "ustat_val(0x8371) = 0x%x\n", ustat_val); return; } - /* Step 3: Check CL37 Message Pages received to indicate LP - supports only CL37 */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_REMOTE_PHY, - MDIO_REMOTE_PHY_MISC_RX_STATUS, - &cl37_fsm_recieved); + /* + * Step 3: Check CL37 Message Pages received to indicate LP + * supports only CL37 + */ + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_REMOTE_PHY, + MDIO_REMOTE_PHY_MISC_RX_STATUS, + &cl37_fsm_recieved); if ((cl37_fsm_recieved & (MDIO_REMOTE_PHY_MISC_RX_STATUS_CL37_FSM_RECEIVED_OVER1G_MSG | MDIO_REMOTE_PHY_MISC_RX_STATUS_CL37_FSM_RECEIVED_BRCM_OUI_MSG)) != @@ -2461,14 +2434,18 @@ static void bnx2x_check_fallback_to_cl37(struct bnx2x_phy *phy, cl37_fsm_recieved); return; } - /* The combined cl37/cl73 fsm state information indicating that we are - connected to a device which does not support cl73, but does support - cl37 BAM. In this case we disable cl73 and restart cl37 auto-neg */ + /* + * The combined cl37/cl73 fsm state information indicating that + * we are connected to a device which does not support cl73, but + * does support cl37 BAM. In this case we disable cl73 and + * restart cl37 auto-neg + */ + /* Disable CL73 */ - CL45_WR_OVER_CL22(bp, phy, - MDIO_REG_BANK_CL73_IEEEB0, - MDIO_CL73_IEEEB0_CL73_AN_CONTROL, - 0); + CL22_WR_OVER_CL45(bp, phy, + MDIO_REG_BANK_CL73_IEEEB0, + MDIO_CL73_IEEEB0_CL73_AN_CONTROL, + 0); /* Restart CL37 autoneg */ bnx2x_restart_autoneg(phy, params, 0); DP(NETIF_MSG_LINK, "Disabling CL73, and restarting CL37 autoneg\n"); @@ -2493,14 +2470,14 @@ static u8 bnx2x_link_settings_status(struct bnx2x_phy *phy, struct link_vars *vars) { struct bnx2x *bp = params->bp; - u16 new_line_speed , gp_status; + u16 new_line_speed, gp_status; u8 rc = 0; /* Read gp_status */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_GP_STATUS, - MDIO_GP_STATUS_TOP_AN_STATUS1, - &gp_status); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_GP_STATUS, + MDIO_GP_STATUS_TOP_AN_STATUS1, + &gp_status); if (phy->req_line_speed == SPEED_AUTO_NEG) vars->link_status |= LINK_STATUS_AUTO_NEGOTIATE_ENABLED; @@ -2637,9 +2614,9 @@ static void bnx2x_set_gmii_tx_driver(struct link_params *params) u16 bank; /* read precomp */ - CL45_RD_OVER_CL22(bp, phy, - MDIO_REG_BANK_OVER_1G, - MDIO_OVER_1G_LP_UP2, &lp_up2); + CL22_RD_OVER_CL45(bp, phy, + MDIO_REG_BANK_OVER_1G, + MDIO_OVER_1G_LP_UP2, &lp_up2); /* bits [10:7] at lp_up2, positioned at [15:12] */ lp_up2 = (((lp_up2 & MDIO_OVER_1G_LP_UP2_PREEMPHASIS_MASK) >> @@ -2651,18 +2628,18 @@ static void bnx2x_set_gmii_tx_driver(struct link_params *params) for (bank = MDIO_REG_BANK_TX0; bank <= MDIO_REG_BANK_TX3; bank += (MDIO_REG_BANK_TX1 - MDIO_REG_BANK_TX0)) { - CL45_RD_OVER_CL22(bp, phy, - bank, - MDIO_TX0_TX_DRIVER, &tx_driver); + CL22_RD_OVER_CL45(bp, phy, + bank, + MDIO_TX0_TX_DRIVER, &tx_driver); /* replace tx_driver bits [15:12] */ if (lp_up2 != (tx_driver & MDIO_TX0_TX_DRIVER_PREEMPHASIS_MASK)) { tx_driver &= ~MDIO_TX0_TX_DRIVER_PREEMPHASIS_MASK; tx_driver |= lp_up2; - CL45_WR_OVER_CL22(bp, phy, - bank, - MDIO_TX0_TX_DRIVER, tx_driver); + CL22_WR_OVER_CL45(bp, phy, + bank, + MDIO_TX0_TX_DRIVER, tx_driver); } } } @@ -2676,10 +2653,10 @@ static u8 bnx2x_emac_program(struct link_params *params, DP(NETIF_MSG_LINK, "setting link speed & duplex\n"); bnx2x_bits_dis(bp, GRCBASE_EMAC0 + port*0x400 + - EMAC_REG_EMAC_MODE, - (EMAC_MODE_25G_MODE | - EMAC_MODE_PORT_MII_10M | - EMAC_MODE_HALF_DUPLEX)); + EMAC_REG_EMAC_MODE, + (EMAC_MODE_25G_MODE | + EMAC_MODE_PORT_MII_10M | + EMAC_MODE_HALF_DUPLEX)); switch (vars->line_speed) { case SPEED_10: mode |= EMAC_MODE_PORT_MII_10M; @@ -2707,8 +2684,8 @@ static u8 bnx2x_emac_program(struct link_params *params, if (vars->duplex == DUPLEX_HALF) mode |= EMAC_MODE_HALF_DUPLEX; bnx2x_bits_en(bp, - GRCBASE_EMAC0 + port*0x400 + EMAC_REG_EMAC_MODE, - mode); + GRCBASE_EMAC0 + port*0x400 + EMAC_REG_EMAC_MODE, + mode); bnx2x_set_led(params, vars, LED_MODE_OPER, vars->line_speed); return 0; @@ -2723,7 +2700,7 @@ static void bnx2x_set_preemphasis(struct bnx2x_phy *phy, for (bank = MDIO_REG_BANK_RX0, i = 0; bank <= MDIO_REG_BANK_RX3; bank += (MDIO_REG_BANK_RX1-MDIO_REG_BANK_RX0), i++) { - CL45_WR_OVER_CL22(bp, phy, + CL22_WR_OVER_CL45(bp, phy, bank, MDIO_RX0_RX_EQ_BOOST, phy->rx_preemphasis[i]); @@ -2731,7 +2708,7 @@ static void bnx2x_set_preemphasis(struct bnx2x_phy *phy, for (bank = MDIO_REG_BANK_TX0, i = 0; bank <= MDIO_REG_BANK_TX3; bank += (MDIO_REG_BANK_TX1 - MDIO_REG_BANK_TX0), i++) { - CL45_WR_OVER_CL22(bp, phy, + CL22_WR_OVER_CL45(bp, phy, bank, MDIO_TX0_TX_DRIVER, phy->tx_preemphasis[i]); @@ -2754,7 +2731,7 @@ static void bnx2x_init_internal_phy(struct bnx2x_phy *phy, /* forced speed requested? */ if (vars->line_speed != SPEED_AUTO_NEG || (SINGLE_MEDIA_DIRECT(params) && - params->loopback_mode == LOOPBACK_EXT)) { + params->loopback_mode == LOOPBACK_EXT)) { DP(NETIF_MSG_LINK, "not SGMII, no AN\n"); /* disable autoneg */ @@ -2771,7 +2748,7 @@ static void bnx2x_init_internal_phy(struct bnx2x_phy *phy, /* program duplex & pause advertisement (for aneg) */ bnx2x_set_ieee_aneg_advertisment(phy, params, - vars->ieee_fc); + vars->ieee_fc); /* enable autoneg */ bnx2x_set_autoneg(phy, params, vars, enable_cl73); @@ -2842,7 +2819,8 @@ static u8 bnx2x_init_xgxs(struct bnx2x_phy *phy, } static u16 bnx2x_wait_reset_complete(struct bnx2x *bp, - struct bnx2x_phy *phy) + struct bnx2x_phy *phy, + struct link_params *params) { u16 cnt, ctrl; /* Wait for soft reset to get cleared upto 1 sec */ @@ -2853,6 +2831,11 @@ static u16 bnx2x_wait_reset_complete(struct bnx2x *bp, break; msleep(1); } + + if (cnt == 1000) + netdev_err(bp->dev, "Warning: PHY was not initialized," + " Port %d\n", + params->port); DP(NETIF_MSG_LINK, "control reg 0x%x (after %d ms)\n", ctrl, cnt); return cnt; } @@ -2863,9 +2846,7 @@ static void bnx2x_link_int_enable(struct link_params *params) u32 mask; struct bnx2x *bp = params->bp; - /* setting the status to report on link up - for either XGXS or SerDes */ - + /* Setting the status to report on link up for either XGXS or SerDes */ if (params->switch_cfg == SWITCH_CFG_10G) { mask = (NIG_MASK_XGXS0_LINK10G | NIG_MASK_XGXS0_LINK_STATUS); @@ -2908,7 +2889,7 @@ static void bnx2x_rearm_latch_signal(struct bnx2x *bp, u8 port, { u32 latch_status = 0; - /** + /* * Disable the MI INT ( external phy int ) by writing 1 to the * status register. Link down indication is high-active-signal, * so in this case we need to write the status to clear the XOR @@ -2933,27 +2914,30 @@ static void bnx2x_rearm_latch_signal(struct bnx2x *bp, u8 port, /* For all latched-signal=up : Re-Arm Latch signals */ REG_WR(bp, NIG_REG_LATCH_STATUS_0 + port*8, - (latch_status & 0xfffe) | (latch_status & 1)); + (latch_status & 0xfffe) | (latch_status & 1)); } /* For all latched-signal=up,Write original_signal to status */ } static void bnx2x_link_int_ack(struct link_params *params, - struct link_vars *vars, u8 is_10g) + struct link_vars *vars, u8 is_10g) { struct bnx2x *bp = params->bp; u8 port = params->port; - /* first reset all status - * we assume only one line will be change at a time */ + /* + * First reset all status we assume only one line will be + * change at a time + */ bnx2x_bits_dis(bp, NIG_REG_STATUS_INTERRUPT_PORT0 + port*4, - (NIG_STATUS_XGXS0_LINK10G | - NIG_STATUS_XGXS0_LINK_STATUS | - NIG_STATUS_SERDES0_LINK_STATUS)); + (NIG_STATUS_XGXS0_LINK10G | + NIG_STATUS_XGXS0_LINK_STATUS | + NIG_STATUS_SERDES0_LINK_STATUS)); if (vars->phy_link_up) { if (is_10g) { - /* Disable the 10G link interrupt - * by writing 1 to the status register + /* + * Disable the 10G link interrupt by writing 1 to the + * status register */ DP(NETIF_MSG_LINK, "10G XGXS phy link up\n"); bnx2x_bits_en(bp, @@ -2961,9 +2945,9 @@ static void bnx2x_link_int_ack(struct link_params *params, NIG_STATUS_XGXS0_LINK10G); } else if (params->switch_cfg == SWITCH_CFG_10G) { - /* Disable the link interrupt - * by writing 1 to the relevant lane - * in the status register + /* + * Disable the link interrupt by writing 1 to the + * relevant lane in the status register */ u32 ser_lane = ((params->lane_config & PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >> @@ -2978,8 +2962,9 @@ static void bnx2x_link_int_ack(struct link_params *params, } else { /* SerDes */ DP(NETIF_MSG_LINK, "SerDes phy link up\n"); - /* Disable the link interrupt - * by writing 1 to the status register + /* + * Disable the link interrupt by writing 1 to the status + * register */ bnx2x_bits_en(bp, NIG_REG_STATUS_INTERRUPT_PORT0 + port*4, @@ -3059,8 +3044,7 @@ u8 bnx2x_get_ext_phy_fw_version(struct link_params *params, u8 driver_loaded, } if ((params->num_phys == MAX_PHYS) && (params->phy[EXT_PHY2].ver_addr != 0)) { - spirom_ver = REG_RD(bp, - params->phy[EXT_PHY2].ver_addr); + spirom_ver = REG_RD(bp, params->phy[EXT_PHY2].ver_addr); if (params->phy[EXT_PHY2].format_fw_ver) { *ver_p = '/'; ver_p++; @@ -3089,29 +3073,27 @@ static void bnx2x_set_xgxs_loopback(struct bnx2x_phy *phy, /* change the uni_phy_addr in the nig */ md_devad = REG_RD(bp, (NIG_REG_XGXS0_CTRL_MD_DEVAD + - port*0x18)); + port*0x18)); REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_DEVAD + port*0x18, 0x5); bnx2x_cl45_write(bp, phy, - 5, - (MDIO_REG_BANK_AER_BLOCK + - (MDIO_AER_BLOCK_AER_REG & 0xf)), - 0x2800); + 5, + (MDIO_REG_BANK_AER_BLOCK + + (MDIO_AER_BLOCK_AER_REG & 0xf)), + 0x2800); bnx2x_cl45_write(bp, phy, - 5, - (MDIO_REG_BANK_CL73_IEEEB0 + - (MDIO_CL73_IEEEB0_CL73_AN_CONTROL & 0xf)), - 0x6041); + 5, + (MDIO_REG_BANK_CL73_IEEEB0 + + (MDIO_CL73_IEEEB0_CL73_AN_CONTROL & 0xf)), + 0x6041); msleep(200); /* set aer mmd back */ bnx2x_set_aer_mmd_xgxs(params, phy); /* and md_devad */ - REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_DEVAD + port*0x18, - md_devad); - + REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_DEVAD + port*0x18, md_devad); } else { u16 mii_ctrl; DP(NETIF_MSG_LINK, "XGXS 1G loopback enable\n"); @@ -3152,26 +3134,26 @@ u8 bnx2x_set_led(struct link_params *params, case LED_MODE_OFF: REG_WR(bp, NIG_REG_LED_10G_P0 + port*4, 0); REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4, - SHARED_HW_CFG_LED_MAC1); + SHARED_HW_CFG_LED_MAC1); tmp = EMAC_RD(bp, EMAC_REG_EMAC_LED); EMAC_WR(bp, EMAC_REG_EMAC_LED, (tmp | EMAC_LED_OVERRIDE)); break; case LED_MODE_OPER: - /** + /* * For all other phys, OPER mode is same as ON, so in case * link is down, do nothing - **/ + */ if (!vars->link_up) break; case LED_MODE_ON: if (params->phy[EXT_PHY1].type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727 && CHIP_IS_E2(bp) && params->num_phys == 2) { - /** - * This is a work-around for E2+8727 Configurations - */ + /* + * This is a work-around for E2+8727 Configurations + */ if (mode == LED_MODE_ON || speed == SPEED_10000){ REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4, 0); @@ -3183,41 +3165,40 @@ u8 bnx2x_set_led(struct link_params *params, return rc; } } else if (SINGLE_MEDIA_DIRECT(params)) { - /** - * This is a work-around for HW issue found when link - * is up in CL73 - */ + /* + * This is a work-around for HW issue found when link + * is up in CL73 + */ REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4, 0); REG_WR(bp, NIG_REG_LED_10G_P0 + port*4, 1); } else { - REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4, - hw_led_mode); + REG_WR(bp, NIG_REG_LED_MODE_P0 + port*4, hw_led_mode); } - REG_WR(bp, NIG_REG_LED_CONTROL_OVERRIDE_TRAFFIC_P0 + - port*4, 0); + REG_WR(bp, NIG_REG_LED_CONTROL_OVERRIDE_TRAFFIC_P0 + port*4, 0); /* Set blinking rate to ~15.9Hz */ REG_WR(bp, NIG_REG_LED_CONTROL_BLINK_RATE_P0 + port*4, - LED_BLINK_RATE_VAL); + LED_BLINK_RATE_VAL); REG_WR(bp, NIG_REG_LED_CONTROL_BLINK_RATE_ENA_P0 + - port*4, 1); + port*4, 1); tmp = EMAC_RD(bp, EMAC_REG_EMAC_LED); - EMAC_WR(bp, EMAC_REG_EMAC_LED, - (tmp & (~EMAC_LED_OVERRIDE))); + EMAC_WR(bp, EMAC_REG_EMAC_LED, (tmp & (~EMAC_LED_OVERRIDE))); if (CHIP_IS_E1(bp) && ((speed == SPEED_2500) || (speed == SPEED_1000) || (speed == SPEED_100) || (speed == SPEED_10))) { - /* On Everest 1 Ax chip versions for speeds less than - 10G LED scheme is different */ + /* + * On Everest 1 Ax chip versions for speeds less than + * 10G LED scheme is different + */ REG_WR(bp, NIG_REG_LED_CONTROL_OVERRIDE_TRAFFIC_P0 - + port*4, 1); + + port*4, 1); REG_WR(bp, NIG_REG_LED_CONTROL_TRAFFIC_P0 + - port*4, 0); + port*4, 0); REG_WR(bp, NIG_REG_LED_CONTROL_BLINK_TRAFFIC_P0 + - port*4, 1); + port*4, 1); } break; @@ -3231,7 +3212,7 @@ u8 bnx2x_set_led(struct link_params *params, } -/** +/* * This function comes to reflect the actual link state read DIRECTLY from the * HW */ @@ -3243,10 +3224,10 @@ u8 bnx2x_test_link(struct link_params *params, struct link_vars *vars, u8 ext_phy_link_up = 0, serdes_phy_type; struct link_vars temp_vars; - CL45_RD_OVER_CL22(bp, ¶ms->phy[INT_PHY], - MDIO_REG_BANK_GP_STATUS, - MDIO_GP_STATUS_TOP_AN_STATUS1, - &gp_status); + CL22_RD_OVER_CL45(bp, ¶ms->phy[INT_PHY], + MDIO_REG_BANK_GP_STATUS, + MDIO_GP_STATUS_TOP_AN_STATUS1, + &gp_status); /* link is up only if both local phy and external phy are up */ if (!(gp_status & MDIO_GP_STATUS_TOP_AN_STATUS1_LINK_STATUS)) return -ESRCH; @@ -3290,15 +3271,15 @@ static u8 bnx2x_link_initialize(struct link_params *params, u8 rc = 0; u8 phy_index, non_ext_phy; struct bnx2x *bp = params->bp; - /** - * In case of external phy existence, the line speed would be the - * line speed linked up by the external phy. In case it is direct - * only, then the line_speed during initialization will be - * equal to the req_line_speed - */ + /* + * In case of external phy existence, the line speed would be the + * line speed linked up by the external phy. In case it is direct + * only, then the line_speed during initialization will be + * equal to the req_line_speed + */ vars->line_speed = params->phy[INT_PHY].req_line_speed; - /** + /* * Initialize the internal phy in case this is a direct board * (no external phys), or this board has external phy which requires * to first. @@ -3326,17 +3307,16 @@ static u8 bnx2x_link_initialize(struct link_params *params, if (!non_ext_phy) for (phy_index = EXT_PHY1; phy_index < params->num_phys; phy_index++) { - /** + /* * No need to initialize second phy in case of first * phy only selection. In case of second phy, we do * need to initialize the first phy, since they are * connected. - **/ + */ if (phy_index == EXT_PHY2 && (bnx2x_phy_selection(params) == PORT_HW_CFG_PHY_SELECTION_FIRST_PHY)) { - DP(NETIF_MSG_LINK, "Not initializing" - "second phy\n"); + DP(NETIF_MSG_LINK, "Ignoring second phy\n"); continue; } params->phy[phy_index].config_init( @@ -3358,9 +3338,8 @@ static void bnx2x_int_link_reset(struct bnx2x_phy *phy, struct link_params *params) { /* reset the SerDes/XGXS */ - REG_WR(params->bp, GRCBASE_MISC + - MISC_REGISTERS_RESET_REG_3_CLEAR, - (0x1ff << (params->port*16))); + REG_WR(params->bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_3_CLEAR, + (0x1ff << (params->port*16))); } static void bnx2x_common_ext_link_reset(struct bnx2x_phy *phy, @@ -3374,11 +3353,11 @@ static void bnx2x_common_ext_link_reset(struct bnx2x_phy *phy, else gpio_port = params->port; bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_LOW, - gpio_port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, + gpio_port); bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_LOW, - gpio_port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, + gpio_port); DP(NETIF_MSG_LINK, "reset external PHY\n"); } @@ -3409,9 +3388,8 @@ static u8 bnx2x_update_link_down(struct link_params *params, /* reset BigMac */ bnx2x_bmac_rx_disable(bp, params->port); - REG_WR(bp, GRCBASE_MISC + - MISC_REGISTERS_RESET_REG_2_CLEAR, - (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); + REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_CLEAR, + (MISC_REGISTERS_RESET_REG_2_RST_BMAC0 << port)); return 0; } @@ -3462,7 +3440,7 @@ static u8 bnx2x_update_link_up(struct link_params *params, msleep(20); return rc; } -/** +/* * The bnx2x_link_update function should be called upon link * interrupt. * Link is considered up as follows: @@ -3501,12 +3479,11 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) REG_RD(bp, NIG_REG_STATUS_INTERRUPT_PORT0 + port*4)); is_mi_int = (u8)(REG_RD(bp, NIG_REG_EMAC0_STATUS_MISC_MI_INT + - port*0x18) > 0); + port*0x18) > 0); DP(NETIF_MSG_LINK, "int_mask 0x%x MI_INT %x, SERDES_LINK %x\n", REG_RD(bp, NIG_REG_MASK_INTERRUPT_PORT0 + port*4), is_mi_int, - REG_RD(bp, - NIG_REG_SERDES0_STATUS_LINK_STATUS + port*0x3c)); + REG_RD(bp, NIG_REG_SERDES0_STATUS_LINK_STATUS + port*0x3c)); DP(NETIF_MSG_LINK, " 10G %x, XGXS_LINK %x\n", REG_RD(bp, NIG_REG_XGXS0_STATUS_LINK10G + port*0x68), @@ -3515,14 +3492,14 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) /* disable emac */ REG_WR(bp, NIG_REG_NIG_EMAC0_EN + port*4, 0); - /** - * Step 1: - * Check external link change only for external phys, and apply - * priority selection between them in case the link on both phys - * is up. Note that the instead of the common vars, a temporary - * vars argument is used since each phy may have different link/ - * speed/duplex result - */ + /* + * Step 1: + * Check external link change only for external phys, and apply + * priority selection between them in case the link on both phys + * is up. Note that the instead of the common vars, a temporary + * vars argument is used since each phy may have different link/ + * speed/duplex result + */ for (phy_index = EXT_PHY1; phy_index < params->num_phys; phy_index++) { struct bnx2x_phy *phy = ¶ms->phy[phy_index]; @@ -3547,22 +3524,22 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) switch (bnx2x_phy_selection(params)) { case PORT_HW_CFG_PHY_SELECTION_HARDWARE_DEFAULT: case PORT_HW_CFG_PHY_SELECTION_FIRST_PHY_PRIORITY: - /** + /* * In this option, the first PHY makes sure to pass the * traffic through itself only. * Its not clear how to reset the link on the second phy - **/ + */ active_external_phy = EXT_PHY1; break; case PORT_HW_CFG_PHY_SELECTION_SECOND_PHY_PRIORITY: - /** + /* * In this option, the first PHY makes sure to pass the * traffic through the second PHY. - **/ + */ active_external_phy = EXT_PHY2; break; default: - /** + /* * Link indication on both PHYs with the following cases * is invalid: * - FIRST_PHY means that second phy wasn't initialized, @@ -3570,7 +3547,7 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) * - SECOND_PHY means that first phy should not be able * to link up by itself (using configuration) * - DEFAULT should be overriden during initialiazation - **/ + */ DP(NETIF_MSG_LINK, "Invalid link indication" "mpc=0x%x. DISABLING LINK !!!\n", params->multi_phy_config); @@ -3580,18 +3557,18 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) } } prev_line_speed = vars->line_speed; - /** - * Step 2: - * Read the status of the internal phy. In case of - * DIRECT_SINGLE_MEDIA board, this link is the external link, - * otherwise this is the link between the 577xx and the first - * external phy - */ + /* + * Step 2: + * Read the status of the internal phy. In case of + * DIRECT_SINGLE_MEDIA board, this link is the external link, + * otherwise this is the link between the 577xx and the first + * external phy + */ if (params->phy[INT_PHY].read_status) params->phy[INT_PHY].read_status( ¶ms->phy[INT_PHY], params, vars); - /** + /* * The INT_PHY flow control reside in the vars. This include the * case where the speed or flow control are not set to AUTO. * Otherwise, the active external phy flow control result is set @@ -3601,13 +3578,13 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) */ if (active_external_phy > INT_PHY) { vars->flow_ctrl = phy_vars[active_external_phy].flow_ctrl; - /** + /* * Link speed is taken from the XGXS. AN and FC result from * the external phy. */ vars->link_status |= phy_vars[active_external_phy].link_status; - /** + /* * if active_external_phy is first PHY and link is up - disable * disable TX on second external PHY */ @@ -3643,7 +3620,7 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) DP(NETIF_MSG_LINK, "vars->flow_ctrl = 0x%x, vars->link_status = 0x%x," " ext_phy_line_speed = %d\n", vars->flow_ctrl, vars->link_status, ext_phy_line_speed); - /** + /* * Upon link speed change set the NIG into drain mode. Comes to * deals with possible FIFO glitch due to clk change when speed * is decreased without link down indicator @@ -3658,8 +3635,8 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) ext_phy_line_speed); vars->phy_link_up = 0; } else if (prev_line_speed != vars->line_speed) { - REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE - + params->port*4, 0); + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, + 0); msleep(1); } } @@ -3674,14 +3651,14 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) bnx2x_link_int_ack(params, vars, link_10g); - /** - * In case external phy link is up, and internal link is down - * (not initialized yet probably after link initialization, it - * needs to be initialized. - * Note that after link down-up as result of cable plug, the xgxs - * link would probably become up again without the need - * initialize it - */ + /* + * In case external phy link is up, and internal link is down + * (not initialized yet probably after link initialization, it + * needs to be initialized. + * Note that after link down-up as result of cable plug, the xgxs + * link would probably become up again without the need + * initialize it + */ if (!(SINGLE_MEDIA_DIRECT(params))) { DP(NETIF_MSG_LINK, "ext_phy_link_up = %d, int_link_up = %d," " init_preceding = %d\n", ext_phy_link_up, @@ -3701,9 +3678,9 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) vars); } } - /** - * Link is up only if both local phy and external phy (in case of - * non-direct board) are up + /* + * Link is up only if both local phy and external phy (in case of + * non-direct board) are up */ vars->link_up = (vars->phy_link_up && (ext_phy_link_up || @@ -3724,10 +3701,10 @@ u8 bnx2x_link_update(struct link_params *params, struct link_vars *vars) void bnx2x_ext_phy_hw_reset(struct bnx2x *bp, u8 port) { bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_LOW, port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, port); msleep(1); bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, port); } static void bnx2x_save_spirom_version(struct bnx2x *bp, u8 port, @@ -3747,9 +3724,9 @@ static void bnx2x_save_bcm_spirom_ver(struct bnx2x *bp, u16 fw_ver1, fw_ver2; bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER1, &fw_ver1); + MDIO_PMA_REG_ROM_VER1, &fw_ver1); bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER2, &fw_ver2); + MDIO_PMA_REG_ROM_VER2, &fw_ver2); bnx2x_save_spirom_version(bp, port, (u32)(fw_ver1<<16 | fw_ver2), phy->ver_addr); } @@ -3770,7 +3747,7 @@ static void bnx2x_ext_phy_set_pause(struct link_params *params, if ((vars->ieee_fc & MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC) == MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_ASYMMETRIC) { - val |= MDIO_AN_REG_ADV_PAUSE_ASYMMETRIC; + val |= MDIO_AN_REG_ADV_PAUSE_ASYMMETRIC; } if ((vars->ieee_fc & MDIO_COMBO_IEEE0_AUTO_NEG_ADV_PAUSE_BOTH) == @@ -3801,11 +3778,11 @@ static u8 bnx2x_ext_phy_resolve_fc(struct bnx2x_phy *phy, else if (vars->link_status & LINK_STATUS_AUTO_NEGOTIATE_COMPLETE) { ret = 1; bnx2x_cl45_read(bp, phy, - MDIO_AN_DEVAD, - MDIO_AN_REG_ADV_PAUSE, &ld_pause); + MDIO_AN_DEVAD, + MDIO_AN_REG_ADV_PAUSE, &ld_pause); bnx2x_cl45_read(bp, phy, - MDIO_AN_DEVAD, - MDIO_AN_REG_LP_AUTO_NEG, &lp_pause); + MDIO_AN_DEVAD, + MDIO_AN_REG_LP_AUTO_NEG, &lp_pause); pause_result = (ld_pause & MDIO_AN_REG_ADV_PAUSE_MASK) >> 8; pause_result |= (lp_pause & @@ -3881,31 +3858,31 @@ static u8 bnx2x_8073_8727_external_rom_boot(struct bnx2x *bp, /* Boot port from external ROM */ /* EDC grst */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_GEN_CTRL, - 0x0001); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_GEN_CTRL, + 0x0001); /* ucode reboot and rst */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_GEN_CTRL, - 0x008c); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_GEN_CTRL, + 0x008c); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_MISC_CTRL1, 0x0001); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_MISC_CTRL1, 0x0001); /* Reset internal microprocessor */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_GEN_CTRL, - MDIO_PMA_REG_GEN_CTRL_ROM_MICRO_RESET); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_GEN_CTRL, + MDIO_PMA_REG_GEN_CTRL_ROM_MICRO_RESET); /* Release srst bit */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_GEN_CTRL, - MDIO_PMA_REG_GEN_CTRL_ROM_RESET_INTERNAL_MP); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_GEN_CTRL, + MDIO_PMA_REG_GEN_CTRL_ROM_RESET_INTERNAL_MP); /* Delay 100ms per the PHY specifications */ msleep(100); @@ -3936,8 +3913,8 @@ static u8 bnx2x_8073_8727_external_rom_boot(struct bnx2x *bp, /* Clear ser_boot_ctl bit */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_MISC_CTRL1, 0x0000); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_MISC_CTRL1, 0x0000); bnx2x_save_bcm_spirom_ver(bp, phy, port); DP(NETIF_MSG_LINK, @@ -3958,8 +3935,8 @@ static u8 bnx2x_8073_is_snr_needed(struct bnx2x *bp, struct bnx2x_phy *phy) /* Read 8073 HW revision*/ bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8073_CHIP_REV, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8073_CHIP_REV, &val); if (val != 1) { /* No need to workaround in 8073 A1 */ @@ -3967,8 +3944,8 @@ static u8 bnx2x_8073_is_snr_needed(struct bnx2x *bp, struct bnx2x_phy *phy) } bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER2, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_ROM_VER2, &val); /* SNR should be applied only for version 0x102 */ if (val != 0x102) @@ -3982,8 +3959,8 @@ static u8 bnx2x_8073_xaui_wa(struct bnx2x *bp, struct bnx2x_phy *phy) u16 val, cnt, cnt1 ; bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8073_CHIP_REV, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8073_CHIP_REV, &val); if (val > 0) { /* No need to workaround in 8073 A1 */ @@ -3991,26 +3968,32 @@ static u8 bnx2x_8073_xaui_wa(struct bnx2x *bp, struct bnx2x_phy *phy) } /* XAUI workaround in 8073 A0: */ - /* After loading the boot ROM and restarting Autoneg, - poll Dev1, Reg $C820: */ + /* + * After loading the boot ROM and restarting Autoneg, poll + * Dev1, Reg $C820: + */ for (cnt = 0; cnt < 1000; cnt++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8073_SPEED_LINK_STATUS, - &val); - /* If bit [14] = 0 or bit [13] = 0, continue on with - system initialization (XAUI work-around not required, - as these bits indicate 2.5G or 1G link up). */ + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8073_SPEED_LINK_STATUS, + &val); + /* + * If bit [14] = 0 or bit [13] = 0, continue on with + * system initialization (XAUI work-around not required, as + * these bits indicate 2.5G or 1G link up). + */ if (!(val & (1<<14)) || !(val & (1<<13))) { DP(NETIF_MSG_LINK, "XAUI work-around not required\n"); return 0; } else if (!(val & (1<<15))) { - DP(NETIF_MSG_LINK, "clc bit 15 went off\n"); - /* If bit 15 is 0, then poll Dev1, Reg $C841 until - it's MSB (bit 15) goes to 1 (indicating that the - XAUI workaround has completed), - then continue on with system initialization.*/ + DP(NETIF_MSG_LINK, "bit 15 went off\n"); + /* + * If bit 15 is 0, then poll Dev1, Reg $C841 until it's + * MSB (bit15) goes to 1 (indicating that the XAUI + * workaround has completed), then continue on with + * system initialization. + */ for (cnt1 = 0; cnt1 < 1000; cnt1++) { bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, @@ -4093,10 +4076,10 @@ static u8 bnx2x_8073_config_init(struct bnx2x_phy *phy, gpio_port = params->port; /* Restore normal power mode*/ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, gpio_port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, gpio_port); bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, gpio_port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, gpio_port); /* enable LASI */ bnx2x_cl45_write(bp, phy, @@ -4114,10 +4097,6 @@ static u8 bnx2x_8073_config_init(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Before rom RX_ALARM(port1): 0x%x\n", tmp1); - /** - * If this is forced speed, set to KR or KX (all other are not - * supported) - */ /* Swap polarity if required - Must be done only in non-1G mode */ if (params->lane_config & PORT_HW_CFG_SWAP_PHY_POLARITY_ENABLED) { /* Configure the 8073 to swap _P and _N of the KR lines */ @@ -4160,8 +4139,10 @@ static u8 bnx2x_8073_config_init(struct bnx2x_phy *phy, val = (1<<7); } else if (phy->req_line_speed == SPEED_2500) { val = (1<<5); - /* Note that 2.5G works only - when used with 1G advertisment */ + /* + * Note that 2.5G works only when used with 1G + * advertisment + */ } else val = (1<<5); } else { @@ -4170,8 +4151,7 @@ static u8 bnx2x_8073_config_init(struct bnx2x_phy *phy, PORT_HW_CFG_SPEED_CAPABILITY_D0_10G) val |= (1<<7); - /* Note that 2.5G works only when - used with 1G advertisment */ + /* Note that 2.5G works only when used with 1G advertisment */ if (phy->speed_cap_mask & (PORT_HW_CFG_SPEED_CAPABILITY_D0_1G | PORT_HW_CFG_SPEED_CAPABILITY_D0_2_5G)) @@ -4211,9 +4191,11 @@ static u8 bnx2x_8073_config_init(struct bnx2x_phy *phy, /* Add support for CL37 (passive mode) III */ bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_CL37_AN, 0x1000); - /* The SNR will improve about 2db by changing - BW and FEE main tap. Rest commands are executed - after link is up*/ + /* + * The SNR will improve about 2db by changing BW and FEE main + * tap. Rest commands are executed after link is up + * Change FFE main cursor to 5 in EDC register + */ if (bnx2x_8073_is_snr_needed(bp, phy)) bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_EDC_FFE_MAIN, @@ -4297,12 +4279,11 @@ static u8 bnx2x_8073_read_status(struct bnx2x_phy *phy, link_up = (((val1 & 4) == 4) || (an1000_status & (1<<1))); if (link_up && bnx2x_8073_is_snr_needed(bp, phy)) { - /* The SNR will improve about 2dbby - changing the BW and FEE main tap.*/ - /* The 1st write to change FFE main - tap is set before restart AN */ - /* Change PLL Bandwidth in EDC - register */ + /* + * The SNR will improve about 2dbby changing the BW and FEE main + * tap. The 1st write to change FFE main tap is set before + * restart AN. Change PLL Bandwidth in EDC register + */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_PLL_BANDWIDTH, 0x26BC); @@ -4346,10 +4327,10 @@ static u8 bnx2x_8073_read_status(struct bnx2x_phy *phy, bnx2x_cl45_read(bp, phy, MDIO_XS_DEVAD, MDIO_XS_REG_8073_RX_CTRL_PCIE, &val1); - /** - * Set bit 3 to invert Rx in 1G mode and clear this bit - * when it`s in 10G mode. - */ + /* + * Set bit 3 to invert Rx in 1G mode and clear this bit + * when it`s in 10G mode. + */ if (vars->line_speed == SPEED_1000) { DP(NETIF_MSG_LINK, "Swapping 1G polarity for" "the 8073\n"); @@ -4381,8 +4362,8 @@ static void bnx2x_8073_link_reset(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Setting 8073 port %d into low power mode\n", gpio_port); bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_LOW, - gpio_port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, + gpio_port); } /******************************************************************/ @@ -4396,11 +4377,11 @@ static u8 bnx2x_8705_config_init(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "init 8705\n"); /* Restore normal power mode*/ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); /* HW reset */ bnx2x_ext_phy_hw_reset(bp, params->port); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 0xa040); - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_MISC_CTRL, 0x8288); @@ -4451,35 +4432,79 @@ static u8 bnx2x_8705_read_status(struct bnx2x_phy *phy, /******************************************************************/ /* SFP+ module Section */ /******************************************************************/ -static void bnx2x_sfp_set_transmitter(struct bnx2x *bp, +static u8 bnx2x_get_gpio_port(struct link_params *params) +{ + u8 gpio_port; + u32 swap_val, swap_override; + struct bnx2x *bp = params->bp; + if (CHIP_IS_E2(bp)) + gpio_port = BP_PATH(bp); + else + gpio_port = params->port; + swap_val = REG_RD(bp, NIG_REG_PORT_SWAP); + swap_override = REG_RD(bp, NIG_REG_STRAP_OVERRIDE); + return gpio_port ^ (swap_val && swap_override); +} +static void bnx2x_sfp_set_transmitter(struct link_params *params, struct bnx2x_phy *phy, - u8 port, u8 tx_en) { u16 val; + u8 port = params->port; + struct bnx2x *bp = params->bp; + u32 tx_en_mode; - DP(NETIF_MSG_LINK, "Setting transmitter tx_en=%x for port %x\n", - tx_en, port); /* Disable/Enable transmitter ( TX laser of the SFP+ module.)*/ - bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, - &val); + tx_en_mode = REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, + dev_info.port_hw_config[port].sfp_ctrl)) & + PORT_HW_CFG_TX_LASER_MASK; + DP(NETIF_MSG_LINK, "Setting transmitter tx_en=%x for port %x " + "mode = %x\n", tx_en, port, tx_en_mode); + switch (tx_en_mode) { + case PORT_HW_CFG_TX_LASER_MDIO: - if (tx_en) - val &= ~(1<<15); - else - val |= (1<<15); + bnx2x_cl45_read(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, + &val); - bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, - val); + if (tx_en) + val &= ~(1<<15); + else + val |= (1<<15); + + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, + val); + break; + case PORT_HW_CFG_TX_LASER_GPIO0: + case PORT_HW_CFG_TX_LASER_GPIO1: + case PORT_HW_CFG_TX_LASER_GPIO2: + case PORT_HW_CFG_TX_LASER_GPIO3: + { + u16 gpio_pin; + u8 gpio_port, gpio_mode; + if (tx_en) + gpio_mode = MISC_REGISTERS_GPIO_OUTPUT_HIGH; + else + gpio_mode = MISC_REGISTERS_GPIO_OUTPUT_LOW; + + gpio_pin = tx_en_mode - PORT_HW_CFG_TX_LASER_GPIO0; + gpio_port = bnx2x_get_gpio_port(params); + bnx2x_set_gpio(bp, gpio_pin, gpio_mode, gpio_port); + break; + } + default: + DP(NETIF_MSG_LINK, "Invalid TX_LASER_MDIO 0x%x\n", tx_en_mode); + break; + } } static u8 bnx2x_8726_read_sfp_module_eeprom(struct bnx2x_phy *phy, struct link_params *params, - u16 addr, u8 byte_cnt, u8 *o_buf) + u16 addr, u8 byte_cnt, u8 *o_buf) { struct bnx2x *bp = params->bp; u16 val = 0; @@ -4492,23 +4517,23 @@ static u8 bnx2x_8726_read_sfp_module_eeprom(struct bnx2x_phy *phy, /* Set the read command byte count */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_SFP_TWO_WIRE_BYTE_CNT, - (byte_cnt | 0xa000)); + (byte_cnt | 0xa000)); /* Set the read command address */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_SFP_TWO_WIRE_MEM_ADDR, - addr); + addr); /* Activate read command */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, - 0x2c0f); + 0x2c0f); /* Wait up to 500us for command complete status */ for (i = 0; i < 100; i++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); if ((val & MDIO_PMA_REG_SFP_TWO_WIRE_CTRL_STATUS_MASK) == MDIO_PMA_REG_SFP_TWO_WIRE_STATUS_COMPLETE) break; @@ -4526,15 +4551,15 @@ static u8 bnx2x_8726_read_sfp_module_eeprom(struct bnx2x_phy *phy, /* Read the buffer */ for (i = 0; i < byte_cnt; i++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8726_TWO_WIRE_DATA_BUF + i, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8726_TWO_WIRE_DATA_BUF + i, &val); o_buf[i] = (u8)(val & MDIO_PMA_REG_8726_TWO_WIRE_DATA_MASK); } for (i = 0; i < 100; i++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); if ((val & MDIO_PMA_REG_SFP_TWO_WIRE_CTRL_STATUS_MASK) == MDIO_PMA_REG_SFP_TWO_WIRE_STATUS_IDLE) return 0; @@ -4545,7 +4570,7 @@ static u8 bnx2x_8726_read_sfp_module_eeprom(struct bnx2x_phy *phy, static u8 bnx2x_8727_read_sfp_module_eeprom(struct bnx2x_phy *phy, struct link_params *params, - u16 addr, u8 byte_cnt, u8 *o_buf) + u16 addr, u8 byte_cnt, u8 *o_buf) { struct bnx2x *bp = params->bp; u16 val, i; @@ -4558,41 +4583,43 @@ static u8 bnx2x_8727_read_sfp_module_eeprom(struct bnx2x_phy *phy, /* Need to read from 1.8000 to clear it */ bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, - &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, + &val); /* Set the read command byte count */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_BYTE_CNT, - ((byte_cnt < 2) ? 2 : byte_cnt)); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_BYTE_CNT, + ((byte_cnt < 2) ? 2 : byte_cnt)); /* Set the read command address */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_MEM_ADDR, - addr); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_MEM_ADDR, + addr); /* Set the destination address */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - 0x8004, - MDIO_PMA_REG_8727_TWO_WIRE_DATA_BUF); + MDIO_PMA_DEVAD, + 0x8004, + MDIO_PMA_REG_8727_TWO_WIRE_DATA_BUF); /* Activate read command */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, - 0x8002); - /* Wait appropriate time for two-wire command to finish before - polling the status register */ + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, + 0x8002); + /* + * Wait appropriate time for two-wire command to finish before + * polling the status register + */ msleep(1); /* Wait up to 500us for command complete status */ for (i = 0; i < 100; i++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); if ((val & MDIO_PMA_REG_SFP_TWO_WIRE_CTRL_STATUS_MASK) == MDIO_PMA_REG_SFP_TWO_WIRE_STATUS_COMPLETE) break; @@ -4604,21 +4631,21 @@ static u8 bnx2x_8727_read_sfp_module_eeprom(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Got bad status 0x%x when reading from SFP+ EEPROM\n", (val & MDIO_PMA_REG_SFP_TWO_WIRE_CTRL_STATUS_MASK)); - return -EINVAL; + return -EFAULT; } /* Read the buffer */ for (i = 0; i < byte_cnt; i++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8727_TWO_WIRE_DATA_BUF + i, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8727_TWO_WIRE_DATA_BUF + i, &val); o_buf[i] = (u8)(val & MDIO_PMA_REG_8727_TWO_WIRE_DATA_MASK); } for (i = 0; i < 100; i++) { bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_SFP_TWO_WIRE_CTRL, &val); if ((val & MDIO_PMA_REG_SFP_TWO_WIRE_CTRL_STATUS_MASK) == MDIO_PMA_REG_SFP_TWO_WIRE_STATUS_IDLE) return 0; @@ -4628,22 +4655,22 @@ static u8 bnx2x_8727_read_sfp_module_eeprom(struct bnx2x_phy *phy, return -EINVAL; } -static u8 bnx2x_read_sfp_module_eeprom(struct bnx2x_phy *phy, - struct link_params *params, u16 addr, - u8 byte_cnt, u8 *o_buf) +u8 bnx2x_read_sfp_module_eeprom(struct bnx2x_phy *phy, + struct link_params *params, u16 addr, + u8 byte_cnt, u8 *o_buf) { if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8726) return bnx2x_8726_read_sfp_module_eeprom(phy, params, addr, - byte_cnt, o_buf); + byte_cnt, o_buf); else if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) return bnx2x_8727_read_sfp_module_eeprom(phy, params, addr, - byte_cnt, o_buf); + byte_cnt, o_buf); return -EINVAL; } static u8 bnx2x_get_edc_mode(struct bnx2x_phy *phy, struct link_params *params, - u16 *edc_mode) + u16 *edc_mode) { struct bnx2x *bp = params->bp; u8 val, check_limiting_mode = 0; @@ -4664,8 +4691,10 @@ static u8 bnx2x_get_edc_mode(struct bnx2x_phy *phy, { u8 copper_module_type; - /* Check if its active cable( includes SFP+ module) - of passive cable*/ + /* + * Check if its active cable (includes SFP+ module) + * of passive cable + */ if (bnx2x_read_sfp_module_eeprom(phy, params, SFP_EEPROM_FC_TX_TECH_ADDR, @@ -4724,8 +4753,10 @@ static u8 bnx2x_get_edc_mode(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "EDC mode is set to 0x%x\n", *edc_mode); return 0; } -/* This function read the relevant field from the module ( SFP+ ), - and verify it is compliant with this board */ +/* + * This function read the relevant field from the module (SFP+), and verify it + * is compliant with this board + */ static u8 bnx2x_verify_sfp_module(struct bnx2x_phy *phy, struct link_params *params) { @@ -4774,24 +4805,24 @@ static u8 bnx2x_verify_sfp_module(struct bnx2x_phy *phy, /* format the warning message */ if (bnx2x_read_sfp_module_eeprom(phy, params, - SFP_EEPROM_VENDOR_NAME_ADDR, - SFP_EEPROM_VENDOR_NAME_SIZE, - (u8 *)vendor_name)) + SFP_EEPROM_VENDOR_NAME_ADDR, + SFP_EEPROM_VENDOR_NAME_SIZE, + (u8 *)vendor_name)) vendor_name[0] = '\0'; else vendor_name[SFP_EEPROM_VENDOR_NAME_SIZE] = '\0'; if (bnx2x_read_sfp_module_eeprom(phy, params, - SFP_EEPROM_PART_NO_ADDR, - SFP_EEPROM_PART_NO_SIZE, - (u8 *)vendor_pn)) + SFP_EEPROM_PART_NO_ADDR, + SFP_EEPROM_PART_NO_SIZE, + (u8 *)vendor_pn)) vendor_pn[0] = '\0'; else vendor_pn[SFP_EEPROM_PART_NO_SIZE] = '\0'; - netdev_info(bp->dev, "Warning: Unqualified SFP+ module detected," - " Port %d from %s part number %s\n", - params->port, vendor_name, vendor_pn); + netdev_err(bp->dev, "Warning: Unqualified SFP+ module detected," + " Port %d from %s part number %s\n", + params->port, vendor_name, vendor_pn); phy->flags |= FLAGS_SFP_NOT_APPROVED; return -EINVAL; } @@ -4803,8 +4834,11 @@ static u8 bnx2x_wait_for_sfp_module_initialized(struct bnx2x_phy *phy, u8 val; struct bnx2x *bp = params->bp; u16 timeout; - /* Initialization time after hot-plug may take up to 300ms for some - phys type ( e.g. JDSU ) */ + /* + * Initialization time after hot-plug may take up to 300ms for + * some phys type ( e.g. JDSU ) + */ + for (timeout = 0; timeout < 60; timeout++) { if (bnx2x_read_sfp_module_eeprom(phy, params, 1, 1, &val) == 0) { @@ -4823,16 +4857,14 @@ static void bnx2x_8727_power_module(struct bnx2x *bp, /* Make sure GPIOs are not using for LED mode */ u16 val; /* - * In the GPIO register, bit 4 is use to detemine if the GPIOs are + * In the GPIO register, bit 4 is use to determine if the GPIOs are * operating as INPUT or as OUTPUT. Bit 1 is for input, and 0 for * output * Bits 0-1 determine the gpios value for OUTPUT in case bit 4 val is 0 * Bits 8-9 determine the gpios value for INPUT in case bit 4 val is 1 * where the 1st bit is the over-current(only input), and 2nd bit is * for power( only output ) - */ - - /* + * * In case of NOC feature is disabled and power is up, set GPIO control * as input to enable listening of over-current indication */ @@ -4861,15 +4893,14 @@ static u8 bnx2x_8726_set_limiting_mode(struct bnx2x *bp, u16 cur_limiting_mode; bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER2, - &cur_limiting_mode); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_ROM_VER2, + &cur_limiting_mode); DP(NETIF_MSG_LINK, "Current Limiting mode is 0x%x\n", cur_limiting_mode); if (edc_mode == EDC_MODE_LIMITING) { - DP(NETIF_MSG_LINK, - "Setting LIMITING MODE\n"); + DP(NETIF_MSG_LINK, "Setting LIMITING MODE\n"); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_ROM_VER2, @@ -4878,62 +4909,63 @@ static u8 bnx2x_8726_set_limiting_mode(struct bnx2x *bp, DP(NETIF_MSG_LINK, "Setting LRM MODE\n"); - /* Changing to LRM mode takes quite few seconds. - So do it only if current mode is limiting - ( default is LRM )*/ + /* + * Changing to LRM mode takes quite few seconds. So do it only + * if current mode is limiting (default is LRM) + */ if (cur_limiting_mode != EDC_MODE_LIMITING) return 0; bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_LRM_MODE, - 0); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_LRM_MODE, + 0); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER2, - 0x128); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_ROM_VER2, + 0x128); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_MISC_CTRL0, - 0x4008); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_MISC_CTRL0, + 0x4008); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_LRM_MODE, - 0xaaaa); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_LRM_MODE, + 0xaaaa); } return 0; } static u8 bnx2x_8727_set_limiting_mode(struct bnx2x *bp, struct bnx2x_phy *phy, - u16 edc_mode) + u16 edc_mode) { u16 phy_identifier; u16 rom_ver2_val; bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, - &phy_identifier); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, + &phy_identifier); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, - (phy_identifier & ~(1<<9))); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, + (phy_identifier & ~(1<<9))); bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER2, - &rom_ver2_val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_ROM_VER2, + &rom_ver2_val); /* Keep the MSB 8-bits, and set the LSB 8-bits with the edc_mode */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_ROM_VER2, - (rom_ver2_val & 0xff00) | (edc_mode & 0x00ff)); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_ROM_VER2, + (rom_ver2_val & 0xff00) | (edc_mode & 0x00ff)); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, - (phy_identifier | (1<<9))); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, + (phy_identifier | (1<<9))); return 0; } @@ -4946,11 +4978,11 @@ static void bnx2x_8727_specific_func(struct bnx2x_phy *phy, switch (action) { case DISABLE_TX: - bnx2x_sfp_set_transmitter(bp, phy, params->port, 0); + bnx2x_sfp_set_transmitter(params, phy, 0); break; case ENABLE_TX: if (!(phy->flags & FLAGS_SFP_NOT_APPROVED)) - bnx2x_sfp_set_transmitter(bp, phy, params->port, 1); + bnx2x_sfp_set_transmitter(params, phy, 1); break; default: DP(NETIF_MSG_LINK, "Function 0x%x not supported by 8727\n", @@ -4959,6 +4991,38 @@ static void bnx2x_8727_specific_func(struct bnx2x_phy *phy, } } +static void bnx2x_set_sfp_module_fault_led(struct link_params *params, + u8 gpio_mode) +{ + struct bnx2x *bp = params->bp; + + u32 fault_led_gpio = REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, + dev_info.port_hw_config[params->port].sfp_ctrl)) & + PORT_HW_CFG_FAULT_MODULE_LED_MASK; + switch (fault_led_gpio) { + case PORT_HW_CFG_FAULT_MODULE_LED_DISABLED: + return; + case PORT_HW_CFG_FAULT_MODULE_LED_GPIO0: + case PORT_HW_CFG_FAULT_MODULE_LED_GPIO1: + case PORT_HW_CFG_FAULT_MODULE_LED_GPIO2: + case PORT_HW_CFG_FAULT_MODULE_LED_GPIO3: + { + u8 gpio_port = bnx2x_get_gpio_port(params); + u16 gpio_pin = fault_led_gpio - + PORT_HW_CFG_FAULT_MODULE_LED_GPIO0; + DP(NETIF_MSG_LINK, "Set fault module-detected led " + "pin %x port %x mode %x\n", + gpio_pin, gpio_port, gpio_mode); + bnx2x_set_gpio(bp, gpio_pin, gpio_mode, gpio_port); + } + break; + default: + DP(NETIF_MSG_LINK, "Error: Invalid fault led mode 0x%x\n", + fault_led_gpio); + } +} + static u8 bnx2x_sfp_module_detection(struct bnx2x_phy *phy, struct link_params *params) { @@ -4976,15 +5040,14 @@ static u8 bnx2x_sfp_module_detection(struct bnx2x_phy *phy, if (bnx2x_get_edc_mode(phy, params, &edc_mode) != 0) { DP(NETIF_MSG_LINK, "Failed to get valid module type\n"); return -EINVAL; - } else if (bnx2x_verify_sfp_module(phy, params) != - 0) { + } else if (bnx2x_verify_sfp_module(phy, params) != 0) { /* check SFP+ module compatibility */ DP(NETIF_MSG_LINK, "Module verification failed!!\n"); rc = -EINVAL; /* Turn on fault module-detected led */ - bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_0, - MISC_REGISTERS_GPIO_HIGH, - params->port); + bnx2x_set_sfp_module_fault_led(params, + MISC_REGISTERS_GPIO_HIGH); + if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) && ((val & PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_MASK) == PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_POWER_DOWN)) { @@ -4995,18 +5058,17 @@ static u8 bnx2x_sfp_module_detection(struct bnx2x_phy *phy, } } else { /* Turn off fault module-detected led */ - DP(NETIF_MSG_LINK, "Turn off fault module-detected led\n"); - bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_0, - MISC_REGISTERS_GPIO_LOW, - params->port); + bnx2x_set_sfp_module_fault_led(params, MISC_REGISTERS_GPIO_LOW); } /* power up the SFP module */ if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) bnx2x_8727_power_module(bp, phy, 1); - /* Check and set limiting mode / LRM mode on 8726. - On 8727 it is done automatically */ + /* + * Check and set limiting mode / LRM mode on 8726. On 8727 it + * is done automatically + */ if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8726) bnx2x_8726_set_limiting_mode(bp, phy, edc_mode); else @@ -5018,9 +5080,9 @@ static u8 bnx2x_sfp_module_detection(struct bnx2x_phy *phy, if (rc == 0 || (val & PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_MASK) != PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_DISABLE_TX_LASER) - bnx2x_sfp_set_transmitter(bp, phy, params->port, 1); + bnx2x_sfp_set_transmitter(params, phy, 1); else - bnx2x_sfp_set_transmitter(bp, phy, params->port, 0); + bnx2x_sfp_set_transmitter(params, phy, 0); return rc; } @@ -5033,11 +5095,9 @@ void bnx2x_handle_module_detect_int(struct link_params *params) u8 port = params->port; /* Set valid module led off */ - bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_0, - MISC_REGISTERS_GPIO_HIGH, - params->port); + bnx2x_set_sfp_module_fault_led(params, MISC_REGISTERS_GPIO_HIGH); - /* Get current gpio val refelecting module plugged in / out*/ + /* Get current gpio val reflecting module plugged in / out*/ gpio_val = bnx2x_get_gpio(bp, MISC_REGISTERS_GPIO_3, port); /* Call the handling function in case module is detected */ @@ -5053,18 +5113,20 @@ void bnx2x_handle_module_detect_int(struct link_params *params) DP(NETIF_MSG_LINK, "SFP+ module is not initialized\n"); } else { u32 val = REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, dev_info. - port_feature_config[params->port]. - config)); + offsetof(struct shmem_region, dev_info. + port_feature_config[params->port]. + config)); bnx2x_set_gpio_int(bp, MISC_REGISTERS_GPIO_3, MISC_REGISTERS_GPIO_INT_OUTPUT_SET, port); - /* Module was plugged out. */ - /* Disable transmit for this module */ + /* + * Module was plugged out. + * Disable transmit for this module + */ if ((val & PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_MASK) == PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_DISABLE_TX_LASER) - bnx2x_sfp_set_transmitter(bp, phy, params->port, 0); + bnx2x_sfp_set_transmitter(params, phy, 0); } } @@ -5100,9 +5162,9 @@ static u8 bnx2x_8706_8726_read_status(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "8706/8726 rx_sd 0x%x pcs_status 0x%x 1Gbps" " link_status 0x%x\n", rx_sd, pcs_status, val2); - /* link is up if both bit 0 of pmd_rx_sd and - * bit 0 of pcs_status are set, or if the autoneg bit - * 1 is set + /* + * link is up if both bit 0 of pmd_rx_sd and bit 0 of pcs_status + * are set, or if the autoneg bit 1 is set */ link_up = ((rx_sd & pcs_status & 0x1) || (val2 & (1<<1))); if (link_up) { @@ -5123,14 +5185,15 @@ static u8 bnx2x_8706_config_init(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) { - u16 cnt, val; + u32 tx_en_mode; + u16 cnt, val, tmp1; struct bnx2x *bp = params->bp; bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); /* HW reset */ bnx2x_ext_phy_hw_reset(bp, params->port); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 0xa040); - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); /* Wait until fw is loaded */ for (cnt = 0; cnt < 100; cnt++) { @@ -5197,6 +5260,26 @@ static u8 bnx2x_8706_config_init(struct bnx2x_phy *phy, 0x0004); } bnx2x_save_bcm_spirom_ver(bp, phy, params->port); + + /* + * If TX Laser is controlled by GPIO_0, do not let PHY go into low + * power mode, if TX Laser is disabled + */ + + tx_en_mode = REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, + dev_info.port_hw_config[params->port].sfp_ctrl)) + & PORT_HW_CFG_TX_LASER_MASK; + + if (tx_en_mode == PORT_HW_CFG_TX_LASER_GPIO0) { + DP(NETIF_MSG_LINK, "Enabling TXONOFF_PWRDN_DIS\n"); + bnx2x_cl45_read(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_REG_DIGITAL_CTRL, &tmp1); + tmp1 |= 0x1; + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_REG_DIGITAL_CTRL, tmp1); + } + return 0; } @@ -5231,26 +5314,26 @@ static void bnx2x_8726_external_rom_boot(struct bnx2x_phy *phy, /* Set soft reset */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_GEN_CTRL, - MDIO_PMA_REG_GEN_CTRL_ROM_MICRO_RESET); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_GEN_CTRL, + MDIO_PMA_REG_GEN_CTRL_ROM_MICRO_RESET); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_MISC_CTRL1, 0x0001); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_MISC_CTRL1, 0x0001); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_GEN_CTRL, - MDIO_PMA_REG_GEN_CTRL_ROM_RESET_INTERNAL_MP); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_GEN_CTRL, + MDIO_PMA_REG_GEN_CTRL_ROM_RESET_INTERNAL_MP); /* wait for 150ms for microcode load */ msleep(150); /* Disable serial boot control, tristates pins SS_N, SCK, MOSI, MISO */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_MISC_CTRL1, 0x0000); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_MISC_CTRL1, 0x0000); msleep(200); bnx2x_save_bcm_spirom_ver(bp, phy, params->port); @@ -5285,23 +5368,18 @@ static u8 bnx2x_8726_config_init(struct bnx2x_phy *phy, u32 val; u32 swap_val, swap_override, aeu_gpio_mask, offset; DP(NETIF_MSG_LINK, "Initializing BCM8726\n"); - /* Restore normal power mode*/ - bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); - - bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 1<<15); - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); bnx2x_8726_external_rom_boot(phy, params); - /* Need to call module detected on initialization since - the module detection triggered by actual module - insertion might occur before driver is loaded, and when - driver is loaded, it reset all registers, including the - transmitter */ + /* + * Need to call module detected on initialization since the module + * detection triggered by actual module insertion might occur before + * driver is loaded, and when driver is loaded, it reset all + * registers, including the transmitter + */ bnx2x_sfp_module_detection(phy, params); if (phy->req_line_speed == SPEED_1000) { @@ -5334,8 +5412,10 @@ static u8 bnx2x_8726_config_init(struct bnx2x_phy *phy, MDIO_AN_DEVAD, MDIO_AN_REG_CL37_AN, 0x1000); bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_CTRL, 0x1200); - /* Enable RX-ALARM control to receive - interrupt for 1G speed change */ + /* + * Enable RX-ALARM control to receive interrupt for 1G speed + * change + */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_LASI_CTRL, 0x4); bnx2x_cl45_write(bp, phy, @@ -5367,7 +5447,7 @@ static u8 bnx2x_8726_config_init(struct bnx2x_phy *phy, /* Set GPIO3 to trigger SFP+ module insertion/removal */ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_3, - MISC_REGISTERS_GPIO_INPUT_HI_Z, params->port); + MISC_REGISTERS_GPIO_INPUT_HI_Z, params->port); /* The GPIO should be swapped if the swap register is set and active */ swap_val = REG_RD(bp, NIG_REG_PORT_SWAP); @@ -5458,7 +5538,7 @@ static void bnx2x_8727_hw_reset(struct bnx2x_phy *phy, struct link_params *params) { u32 swap_val, swap_override; u8 port; - /** + /* * The PHY reset is controlled by GPIO 1. Fake the port number * to cancel the swap done in set_gpio() */ @@ -5467,20 +5547,21 @@ static void bnx2x_8727_hw_reset(struct bnx2x_phy *phy, swap_override = REG_RD(bp, NIG_REG_STRAP_OVERRIDE); port = (swap_val && swap_override) ^ 1; bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_LOW, port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, port); } static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, struct link_params *params, struct link_vars *vars) { - u16 tmp1, val, mod_abs; + u32 tx_en_mode; + u16 tmp1, val, mod_abs, tmp2; u16 rx_alarm_ctrl_val; u16 lasi_ctrl_val; struct bnx2x *bp = params->bp; /* Enable PMD link, MOD_ABS_FLT, and 1G link alarm */ - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); rx_alarm_ctrl_val = (1<<2) | (1<<5) ; lasi_ctrl_val = 0x0004; @@ -5493,14 +5574,17 @@ static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_LASI_CTRL, lasi_ctrl_val); - /* Initially configure MOD_ABS to interrupt when - module is presence( bit 8) */ + /* + * Initially configure MOD_ABS to interrupt when module is + * presence( bit 8) + */ bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER, &mod_abs); - /* Set EDC off by setting OPTXLOS signal input to low - (bit 9). - When the EDC is off it locks onto a reference clock and - avoids becoming 'lost'.*/ + /* + * Set EDC off by setting OPTXLOS signal input to low (bit 9). + * When the EDC is off it locks onto a reference clock and avoids + * becoming 'lost' + */ mod_abs &= ~(1<<8); if (!(phy->flags & FLAGS_NOC)) mod_abs &= ~(1<<9); @@ -5515,7 +5599,7 @@ static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, if (phy->flags & FLAGS_NOC) val |= (3<<5); - /** + /* * Set 8727 GPIOs to input to allow reading from the 8727 GPIO0 * status which reflect SFP+ module over-current */ @@ -5542,7 +5626,7 @@ static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_10G_CTRL2, &tmp1); DP(NETIF_MSG_LINK, "1.7 = 0x%x\n", tmp1); - /** + /* * Power down the XAUI until link is up in case of dual-media * and 1G */ @@ -5568,7 +5652,7 @@ static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_CL37_AN, 0x1300); } else { - /** + /* * Since the 8727 has only single reset pin, need to set the 10G * registers although it is default */ @@ -5584,7 +5668,8 @@ static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, 0x0008); } - /* Set 2-wire transfer rate of SFP+ module EEPROM + /* + * Set 2-wire transfer rate of SFP+ module EEPROM * to 100Khz since some DACs(direct attached cables) do * not work at 400Khz. */ @@ -5607,6 +5692,26 @@ static u8 bnx2x_8727_config_init(struct bnx2x_phy *phy, phy->tx_preemphasis[1]); } + /* + * If TX Laser is controlled by GPIO_0, do not let PHY go into low + * power mode, if TX Laser is disabled + */ + tx_en_mode = REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, + dev_info.port_hw_config[params->port].sfp_ctrl)) + & PORT_HW_CFG_TX_LASER_MASK; + + if (tx_en_mode == PORT_HW_CFG_TX_LASER_GPIO0) { + + DP(NETIF_MSG_LINK, "Enabling TXONOFF_PWRDN_DIS\n"); + bnx2x_cl45_read(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_OPT_CFG_REG, &tmp2); + tmp2 |= 0x1000; + tmp2 &= 0xFFEF; + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_OPT_CFG_REG, tmp2); + } + return 0; } @@ -5620,46 +5725,49 @@ static void bnx2x_8727_handle_mod_abs(struct bnx2x_phy *phy, port_feature_config[params->port]. config)); bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, &mod_abs); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, &mod_abs); if (mod_abs & (1<<8)) { /* Module is absent */ DP(NETIF_MSG_LINK, "MOD_ABS indication " "show module is absent\n"); - /* 1. Set mod_abs to detect next module - presence event - 2. Set EDC off by setting OPTXLOS signal input to low - (bit 9). - When the EDC is off it locks onto a reference clock and - avoids becoming 'lost'.*/ + /* + * 1. Set mod_abs to detect next module + * presence event + * 2. Set EDC off by setting OPTXLOS signal input to low + * (bit 9). + * When the EDC is off it locks onto a reference clock and + * avoids becoming 'lost'. + */ mod_abs &= ~(1<<8); if (!(phy->flags & FLAGS_NOC)) mod_abs &= ~(1<<9); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_PHY_IDENTIFIER, mod_abs); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_PHY_IDENTIFIER, mod_abs); - /* Clear RX alarm since it stays up as long as - the mod_abs wasn't changed */ + /* + * Clear RX alarm since it stays up as long as + * the mod_abs wasn't changed + */ bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_RX_ALARM, &rx_alarm_status); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_RX_ALARM, &rx_alarm_status); } else { /* Module is present */ DP(NETIF_MSG_LINK, "MOD_ABS indication " "show module is present\n"); - /* First thing, disable transmitter, - and if the module is ok, the - module_detection will enable it*/ - - /* 1. Set mod_abs to detect next module - absent event ( bit 8) - 2. Restore the default polarity of the OPRXLOS signal and - this signal will then correctly indicate the presence or - absence of the Rx signal. (bit 9) */ + /* + * First disable transmitter, and if the module is ok, the + * module_detection will enable it + * 1. Set mod_abs to detect next module absent event ( bit 8) + * 2. Restore the default polarity of the OPRXLOS signal and + * this signal will then correctly indicate the presence or + * absence of the Rx signal. (bit 9) + */ mod_abs |= (1<<8); if (!(phy->flags & FLAGS_NOC)) mod_abs |= (1<<9); @@ -5667,10 +5775,12 @@ static void bnx2x_8727_handle_mod_abs(struct bnx2x_phy *phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_PHY_IDENTIFIER, mod_abs); - /* Clear RX alarm since it stays up as long as - the mod_abs wasn't changed. This is need to be done - before calling the module detection, otherwise it will clear - the link update alarm */ + /* + * Clear RX alarm since it stays up as long as the mod_abs + * wasn't changed. This is need to be done before calling the + * module detection, otherwise it will clear* the link update + * alarm + */ bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_RX_ALARM, &rx_alarm_status); @@ -5678,7 +5788,7 @@ static void bnx2x_8727_handle_mod_abs(struct bnx2x_phy *phy, if ((val & PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_MASK) == PORT_FEAT_CFG_OPT_MDL_ENFRCMNT_DISABLE_TX_LASER) - bnx2x_sfp_set_transmitter(bp, phy, params->port, 0); + bnx2x_sfp_set_transmitter(params, phy, 0); if (bnx2x_wait_for_sfp_module_initialized(phy, params) == 0) bnx2x_sfp_module_detection(phy, params); @@ -5687,9 +5797,8 @@ static void bnx2x_8727_handle_mod_abs(struct bnx2x_phy *phy, } DP(NETIF_MSG_LINK, "8727 RX_ALARM_STATUS 0x%x\n", - rx_alarm_status); - /* No need to check link status in case of - module plugged in/out */ + rx_alarm_status); + /* No need to check link status in case of module plugged in/out */ } static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy, @@ -5725,7 +5834,7 @@ static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy, bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_M8051_MSGOUT_REG, &val1); - /** + /* * If a module is present and there is need to check * for over current */ @@ -5745,12 +5854,8 @@ static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy, " Please remove the SFP+ module and" " restart the system to clear this" " error.\n", - params->port); - - /* - * Disable all RX_ALARMs except for - * mod_abs - */ + params->port); + /* Disable all RX_ALARMs except for mod_abs */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_RX_ALARM_CTRL, (1<<5)); @@ -5793,11 +5898,15 @@ static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8073_SPEED_LINK_STATUS, &link_status); - /* Bits 0..2 --> speed detected, - bits 13..15--> link is down */ + /* + * Bits 0..2 --> speed detected, + * Bits 13..15--> link is down + */ if ((link_status & (1<<2)) && (!(link_status & (1<<15)))) { link_up = 1; vars->line_speed = SPEED_10000; + DP(NETIF_MSG_LINK, "port %x: External link up in 10G\n", + params->port); } else if ((link_status & (1<<0)) && (!(link_status & (1<<13)))) { link_up = 1; vars->line_speed = SPEED_1000; @@ -5819,7 +5928,7 @@ static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy, bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8727_PCS_GP, &val1); - /** + /* * In case of dual-media board and 1G, power up the XAUI side, * otherwise power it down. For 10G it is done automatically */ @@ -5839,7 +5948,7 @@ static void bnx2x_8727_link_reset(struct bnx2x_phy *phy, { struct bnx2x *bp = params->bp; /* Disable Transmitter */ - bnx2x_sfp_set_transmitter(bp, phy, params->port, 0); + bnx2x_sfp_set_transmitter(params, phy, 0); /* Clear LASI */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_LASI_CTRL, 0); @@ -5851,19 +5960,23 @@ static void bnx2x_8727_link_reset(struct bnx2x_phy *phy, static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, struct link_params *params) { - u16 val, fw_ver1, fw_ver2, cnt; + u16 val, fw_ver1, fw_ver2, cnt, adj; struct bnx2x *bp = params->bp; + adj = 0; + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) + adj = -1; + /* For the 32 bits registers in 848xx, access via MDIO2ARM interface.*/ /* (1) set register 0xc200_0014(SPI_BRIDGE_CTRL_2) to 0x03000000 */ - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA819, 0x0014); - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81A, 0xc200); - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81B, 0x0000); - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81C, 0x0300); - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA817, 0x0009); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA819 + adj, 0x0014); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81A + adj, 0xc200); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81B + adj, 0x0000); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81C + adj, 0x0300); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA817 + adj, 0x0009); for (cnt = 0; cnt < 100; cnt++) { - bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA818, &val); + bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA818 + adj, &val); if (val & 1) break; udelay(5); @@ -5877,11 +5990,11 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, /* 2) read register 0xc200_0000 (SPI_FW_STATUS) */ - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA819, 0x0000); - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81A, 0xc200); - bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA817, 0x000A); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA819 + adj, 0x0000); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA81A + adj, 0xc200); + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, 0xA817 + adj, 0x000A); for (cnt = 0; cnt < 100; cnt++) { - bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA818, &val); + bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA818 + adj, &val); if (val & 1) break; udelay(5); @@ -5894,9 +6007,9 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, } /* lower 16 bits of the register SPI_FW_STATUS */ - bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA81B, &fw_ver1); + bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA81B + adj, &fw_ver1); /* upper 16 bits of register SPI_FW_STATUS */ - bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA81C, &fw_ver2); + bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, 0xA81C + adj, &fw_ver2); bnx2x_save_spirom_version(bp, params->port, (fw_ver2<<16) | fw_ver1, phy->ver_addr); @@ -5905,49 +6018,53 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, static void bnx2x_848xx_set_led(struct bnx2x *bp, struct bnx2x_phy *phy) { - u16 val; + u16 val, adj; + + adj = 0; + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) + adj = -1; /* PHYC_CTL_LED_CTL */ bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LINK_SIGNAL, &val); + MDIO_PMA_REG_8481_LINK_SIGNAL + adj, &val); val &= 0xFE00; val |= 0x0092; bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LINK_SIGNAL, val); + MDIO_PMA_REG_8481_LINK_SIGNAL + adj, val); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED1_MASK, + MDIO_PMA_REG_8481_LED1_MASK + adj, 0x80); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED2_MASK, + MDIO_PMA_REG_8481_LED2_MASK + adj, 0x18); /* Select activity source by Tx and Rx, as suggested by PHY AE */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED3_MASK, + MDIO_PMA_REG_8481_LED3_MASK + adj, 0x0006); /* Select the closest activity blink rate to that in 10/100/1000 */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED3_BLINK, + MDIO_PMA_REG_8481_LED3_BLINK + adj, 0); bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_84823_CTL_LED_CTL_1, &val); + MDIO_PMA_REG_84823_CTL_LED_CTL_1 + adj, &val); val |= MDIO_PMA_REG_84823_LED3_STRETCH_EN; /* stretch_en for LED3*/ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, - MDIO_PMA_REG_84823_CTL_LED_CTL_1, val); + MDIO_PMA_REG_84823_CTL_LED_CTL_1 + adj, val); /* 'Interrupt Mask' */ bnx2x_cl45_write(bp, phy, @@ -5961,7 +6078,11 @@ static u8 bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy, { struct bnx2x *bp = params->bp; u16 autoneg_val, an_1000_val, an_10_100_val; - + /* + * This phy uses the NIG latch mechanism since link indication + * arrives through its LED4 and not via its LASI signal, so we + * get steady signal instead of clear on read + */ bnx2x_bits_en(bp, NIG_REG_LATCH_BC_0 + params->port*4, 1 << NIG_LATCH_BC_ENABLE_MI_INT); @@ -6086,11 +6207,11 @@ static u8 bnx2x_8481_config_init(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; /* Restore normal power mode*/ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); /* HW reset */ bnx2x_ext_phy_hw_reset(bp, params->port); - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 1<<15); return bnx2x_848xx_cmn_config_init(phy, params, vars); @@ -6102,12 +6223,15 @@ static u8 bnx2x_848x3_config_init(struct bnx2x_phy *phy, { struct bnx2x *bp = params->bp; u8 port, initialize = 1; - u16 val; + u16 val, adj; u16 temp; - u32 actual_phy_selection; + u32 actual_phy_selection, cms_enable; u8 rc = 0; /* This is just for MDIO_CTL_REG_84823_MEDIA register. */ + adj = 0; + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) + adj = 3; msleep(1); if (CHIP_IS_E2(bp)) @@ -6117,11 +6241,12 @@ static u8 bnx2x_848x3_config_init(struct bnx2x_phy *phy, bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_3, MISC_REGISTERS_GPIO_OUTPUT_HIGH, port); - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); /* Wait for GPHY to come out of reset */ msleep(50); - /* BCM84823 requires that XGXS links up first @ 10G for normal - behavior */ + /* + * BCM84823 requires that XGXS links up first @ 10G for normal behavior + */ temp = vars->line_speed; vars->line_speed = SPEED_10000; bnx2x_set_autoneg(¶ms->phy[INT_PHY], params, vars, 0); @@ -6131,7 +6256,7 @@ static u8 bnx2x_848x3_config_init(struct bnx2x_phy *phy, /* Set dual-media configuration according to configuration */ bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, - MDIO_CTL_REG_84823_MEDIA, &val); + MDIO_CTL_REG_84823_MEDIA + adj, &val); val &= ~(MDIO_CTL_REG_84823_MEDIA_MAC_MASK | MDIO_CTL_REG_84823_MEDIA_LINE_MASK | MDIO_CTL_REG_84823_MEDIA_COPPER_CORE_DOWN | @@ -6164,7 +6289,7 @@ static u8 bnx2x_848x3_config_init(struct bnx2x_phy *phy, val |= MDIO_CTL_REG_84823_MEDIA_FIBER_1G; bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_CTL_REG_84823_MEDIA, val); + MDIO_CTL_REG_84823_MEDIA + adj, val); DP(NETIF_MSG_LINK, "Multi_phy config = 0x%x, Media control = 0x%x\n", params->multi_phy_config, val); @@ -6172,23 +6297,43 @@ static u8 bnx2x_848x3_config_init(struct bnx2x_phy *phy, rc = bnx2x_848xx_cmn_config_init(phy, params, vars); else bnx2x_save_848xx_spirom_version(phy, params); + cms_enable = REG_RD(bp, params->shmem_base + + offsetof(struct shmem_region, + dev_info.port_hw_config[params->port].default_cfg)) & + PORT_HW_CFG_ENABLE_CMS_MASK; + + bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, + MDIO_CTL_REG_84823_USER_CTRL_REG, &val); + if (cms_enable) + val |= MDIO_CTL_REG_84823_USER_CTRL_CMS; + else + val &= ~MDIO_CTL_REG_84823_USER_CTRL_CMS; + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_CTL_REG_84823_USER_CTRL_REG, val); + + return rc; } static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy, - struct link_params *params, - struct link_vars *vars) + struct link_params *params, + struct link_vars *vars) { struct bnx2x *bp = params->bp; - u16 val, val1, val2; + u16 val, val1, val2, adj; u8 link_up = 0; + /* Reg offset adjustment for 84833 */ + adj = 0; + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) + adj = -1; + /* Check 10G-BaseT link status */ /* Check PMD signal ok */ bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, 0xFFFA, &val1); bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_PMD_SIGNAL, + MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_PMD_SIGNAL + adj, &val2); DP(NETIF_MSG_LINK, "BCM848xx: PMD_SIGNAL 1.a811 = 0x%x\n", val2); @@ -6273,9 +6418,9 @@ static void bnx2x_8481_hw_reset(struct bnx2x_phy *phy, struct link_params *params) { bnx2x_set_gpio(params->bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_LOW, 0); + MISC_REGISTERS_GPIO_OUTPUT_LOW, 0); bnx2x_set_gpio(params->bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_LOW, 1); + MISC_REGISTERS_GPIO_OUTPUT_LOW, 1); } static void bnx2x_8481_link_reset(struct bnx2x_phy *phy, @@ -6297,8 +6442,8 @@ static void bnx2x_848x3_link_reset(struct bnx2x_phy *phy, else port = params->port; bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_3, - MISC_REGISTERS_GPIO_OUTPUT_LOW, - port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, + port); } static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, @@ -6353,24 +6498,24 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, /* Set LED masks */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED1_MASK, - 0x0); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED1_MASK, + 0x0); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED2_MASK, - 0x0); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED2_MASK, + 0x0); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED3_MASK, - 0x0); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x0); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED5_MASK, - 0x20); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED5_MASK, + 0x20); } else { bnx2x_cl45_write(bp, phy, @@ -6394,35 +6539,35 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, val |= 0x2492; bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LINK_SIGNAL, - val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LINK_SIGNAL, + val); /* Set LED masks */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED1_MASK, - 0x0); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED1_MASK, + 0x0); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED2_MASK, - 0x20); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED2_MASK, + 0x20); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED3_MASK, - 0x20); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x20); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED5_MASK, - 0x0); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED5_MASK, + 0x0); } else { bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED1_MASK, - 0x20); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED1_MASK, + 0x20); } break; @@ -6440,9 +6585,9 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, &val); if (!((val & - MDIO_PMA_REG_8481_LINK_SIGNAL_LED4_ENABLE_MASK) - >> MDIO_PMA_REG_8481_LINK_SIGNAL_LED4_ENABLE_SHIFT)){ - DP(NETIF_MSG_LINK, "Seting LINK_SIGNAL\n"); + MDIO_PMA_REG_8481_LINK_SIGNAL_LED4_ENABLE_MASK) + >> MDIO_PMA_REG_8481_LINK_SIGNAL_LED4_ENABLE_SHIFT)) { + DP(NETIF_MSG_LINK, "Setting LINK_SIGNAL\n"); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LINK_SIGNAL, @@ -6451,24 +6596,24 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, /* Set LED masks */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED1_MASK, - 0x10); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED1_MASK, + 0x10); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED2_MASK, - 0x80); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED2_MASK, + 0x80); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED3_MASK, - 0x98); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x98); bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_8481_LED5_MASK, - 0x40); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED5_MASK, + 0x40); } else { bnx2x_cl45_write(bp, phy, @@ -6513,10 +6658,10 @@ static u8 bnx2x_7101_config_init(struct bnx2x_phy *phy, /* Restore normal power mode*/ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, params->port); /* HW reset */ bnx2x_ext_phy_hw_reset(bp, params->port); - bnx2x_wait_reset_complete(bp, phy); + bnx2x_wait_reset_complete(bp, phy, params); bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_LASI_CTRL, 0x1); @@ -6563,9 +6708,7 @@ static u8 bnx2x_7101_read_status(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "10G-base-T PMA status 0x%x->0x%x\n", val2, val1); link_up = ((val1 & 4) == 4); - /* if link is up - * print the AN outcome of the SFX7101 PHY - */ + /* if link is up print the AN outcome of the SFX7101 PHY */ if (link_up) { bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, MDIO_AN_REG_MASTER_STATUS, @@ -6599,20 +6742,20 @@ void bnx2x_sfx7101_sp_sw_reset(struct bnx2x *bp, struct bnx2x_phy *phy) u16 val, cnt; bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_7101_RESET, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_7101_RESET, &val); for (cnt = 0; cnt < 10; cnt++) { msleep(50); /* Writes a self-clearing reset */ bnx2x_cl45_write(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_7101_RESET, - (val | (1<<15))); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_7101_RESET, + (val | (1<<15))); /* Wait for clear */ bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, - MDIO_PMA_REG_7101_RESET, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_7101_RESET, &val); if ((val & (1<<15)) == 0) break; @@ -6623,10 +6766,10 @@ static void bnx2x_7101_hw_reset(struct bnx2x_phy *phy, struct link_params *params) { /* Low power mode is controlled by GPIO 2 */ bnx2x_set_gpio(params->bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_LOW, params->port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, params->port); /* The PHY reset is controlled by GPIO 1 */ bnx2x_set_gpio(params->bp, MISC_REGISTERS_GPIO_1, - MISC_REGISTERS_GPIO_OUTPUT_LOW, params->port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, params->port); } static void bnx2x_7101_set_link_led(struct bnx2x_phy *phy, @@ -6668,9 +6811,9 @@ static struct bnx2x_phy phy_null = { .supported = 0, .media_type = ETH_PHY_NOT_PRESENT, .ver_addr = 0, - .req_flow_ctrl = 0, - .req_line_speed = 0, - .speed_cap_mask = 0, + .req_flow_ctrl = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, .req_duplex = 0, .rsrv = 0, .config_init = (config_init_t)NULL, @@ -6705,8 +6848,8 @@ static struct bnx2x_phy phy_serdes = { .media_type = ETH_PHY_UNSPECIFIED, .ver_addr = 0, .req_flow_ctrl = 0, - .req_line_speed = 0, - .speed_cap_mask = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, .req_duplex = 0, .rsrv = 0, .config_init = (config_init_t)bnx2x_init_serdes, @@ -6742,8 +6885,8 @@ static struct bnx2x_phy phy_xgxs = { .media_type = ETH_PHY_UNSPECIFIED, .ver_addr = 0, .req_flow_ctrl = 0, - .req_line_speed = 0, - .speed_cap_mask = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, .req_duplex = 0, .rsrv = 0, .config_init = (config_init_t)bnx2x_init_xgxs, @@ -6773,8 +6916,8 @@ static struct bnx2x_phy phy_7101 = { .media_type = ETH_PHY_BASE_T, .ver_addr = 0, .req_flow_ctrl = 0, - .req_line_speed = 0, - .speed_cap_mask = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, .req_duplex = 0, .rsrv = 0, .config_init = (config_init_t)bnx2x_7101_config_init, @@ -6804,9 +6947,9 @@ static struct bnx2x_phy phy_8073 = { SUPPORTED_Asym_Pause), .media_type = ETH_PHY_UNSPECIFIED, .ver_addr = 0, - .req_flow_ctrl = 0, - .req_line_speed = 0, - .speed_cap_mask = 0, + .req_flow_ctrl = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, .req_duplex = 0, .rsrv = 0, .config_init = (config_init_t)bnx2x_8073_config_init, @@ -7015,6 +7158,43 @@ static struct bnx2x_phy phy_84823 = { .phy_specific_func = (phy_specific_func_t)NULL }; +static struct bnx2x_phy phy_84833 = { + .type = PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833, + .addr = 0xff, + .flags = FLAGS_FAN_FAILURE_DET_REQ | + FLAGS_REARM_LATCH_SIGNAL, + .def_md_devad = 0, + .reserved = 0, + .rx_preemphasis = {0xffff, 0xffff, 0xffff, 0xffff}, + .tx_preemphasis = {0xffff, 0xffff, 0xffff, 0xffff}, + .mdio_ctrl = 0, + .supported = (SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full | + SUPPORTED_10000baseT_Full | + SUPPORTED_TP | + SUPPORTED_Autoneg | + SUPPORTED_Pause | + SUPPORTED_Asym_Pause), + .media_type = ETH_PHY_BASE_T, + .ver_addr = 0, + .req_flow_ctrl = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, + .req_duplex = 0, + .rsrv = 0, + .config_init = (config_init_t)bnx2x_848x3_config_init, + .read_status = (read_status_t)bnx2x_848xx_read_status, + .link_reset = (link_reset_t)bnx2x_848x3_link_reset, + .config_loopback = (config_loopback_t)NULL, + .format_fw_ver = (format_fw_ver_t)bnx2x_848xx_format_ver, + .hw_reset = (hw_reset_t)NULL, + .set_link_led = (set_link_led_t)bnx2x_848xx_set_link_led, + .phy_specific_func = (phy_specific_func_t)NULL +}; + /*****************************************************************/ /* */ /* Populate the phy according. Main function: bnx2x_populate_phy */ @@ -7028,7 +7208,7 @@ static void bnx2x_populate_preemphasis(struct bnx2x *bp, u32 shmem_base, /* Get the 4 lanes xgxs config rx and tx */ u32 rx = 0, tx = 0, i; for (i = 0; i < 2; i++) { - /** + /* * INT_PHY and EXT_PHY1 share the same value location in the * shmem. When num_phys is greater than 1, than this value * applies only to EXT_PHY1 @@ -7036,19 +7216,19 @@ static void bnx2x_populate_preemphasis(struct bnx2x *bp, u32 shmem_base, if (phy_index == INT_PHY || phy_index == EXT_PHY1) { rx = REG_RD(bp, shmem_base + offsetof(struct shmem_region, - dev_info.port_hw_config[port].xgxs_config_rx[i<<1])); + dev_info.port_hw_config[port].xgxs_config_rx[i<<1])); tx = REG_RD(bp, shmem_base + offsetof(struct shmem_region, - dev_info.port_hw_config[port].xgxs_config_tx[i<<1])); + dev_info.port_hw_config[port].xgxs_config_tx[i<<1])); } else { rx = REG_RD(bp, shmem_base + offsetof(struct shmem_region, - dev_info.port_hw_config[port].xgxs_config2_rx[i<<1])); + dev_info.port_hw_config[port].xgxs_config2_rx[i<<1])); tx = REG_RD(bp, shmem_base + offsetof(struct shmem_region, - dev_info.port_hw_config[port].xgxs_config2_rx[i<<1])); + dev_info.port_hw_config[port].xgxs_config2_rx[i<<1])); } phy->rx_preemphasis[i << 1] = ((rx>>16) & 0xffff); @@ -7168,6 +7348,9 @@ static u8 bnx2x_populate_ext_phy(struct bnx2x *bp, case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84823: *phy = phy_84823; break; + case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833: + *phy = phy_84833; + break; case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_SFX7101: *phy = phy_7101; break; @@ -7182,21 +7365,21 @@ static u8 bnx2x_populate_ext_phy(struct bnx2x *bp, phy->addr = XGXS_EXT_PHY_ADDR(ext_phy_config); bnx2x_populate_preemphasis(bp, shmem_base, phy, port, phy_index); - /** - * The shmem address of the phy version is located on different - * structures. In case this structure is too old, do not set - * the address - */ + /* + * The shmem address of the phy version is located on different + * structures. In case this structure is too old, do not set + * the address + */ config2 = REG_RD(bp, shmem_base + offsetof(struct shmem_region, dev_info.shared_hw_config.config2)); if (phy_index == EXT_PHY1) { phy->ver_addr = shmem_base + offsetof(struct shmem_region, port_mb[port].ext_phy_fw_version); - /* Check specific mdc mdio settings */ - if (config2 & SHARED_HW_CFG_MDC_MDIO_ACCESS1_MASK) - mdc_mdio_access = config2 & - SHARED_HW_CFG_MDC_MDIO_ACCESS1_MASK; + /* Check specific mdc mdio settings */ + if (config2 & SHARED_HW_CFG_MDC_MDIO_ACCESS1_MASK) + mdc_mdio_access = config2 & + SHARED_HW_CFG_MDC_MDIO_ACCESS1_MASK; } else { u32 size = REG_RD(bp, shmem2_base); @@ -7215,7 +7398,7 @@ static u8 bnx2x_populate_ext_phy(struct bnx2x *bp, } phy->mdio_ctrl = bnx2x_get_emac_base(bp, mdc_mdio_access, port); - /** + /* * In case mdc/mdio_access of the external phy is different than the * mdc/mdio access of the XGXS, a HW lock must be taken in each access * to prevent one port interfere with another port's CL45 operations. @@ -7250,18 +7433,20 @@ static void bnx2x_phy_def_cfg(struct link_params *params, /* Populate the default phy configuration for MF mode */ if (phy_index == EXT_PHY2) { link_config = REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, dev_info. + offsetof(struct shmem_region, dev_info. port_feature_config[params->port].link_config2)); phy->speed_cap_mask = REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, dev_info. + offsetof(struct shmem_region, + dev_info. port_hw_config[params->port].speed_capability_mask2)); } else { link_config = REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, dev_info. + offsetof(struct shmem_region, dev_info. port_feature_config[params->port].link_config)); phy->speed_cap_mask = REG_RD(bp, params->shmem_base + - offsetof(struct shmem_region, dev_info. - port_hw_config[params->port].speed_capability_mask)); + offsetof(struct shmem_region, + dev_info. + port_hw_config[params->port].speed_capability_mask)); } DP(NETIF_MSG_LINK, "Default config phy idx %x cfg 0x%x speed_cap_mask" " 0x%x\n", phy_index, link_config, phy->speed_cap_mask); @@ -7408,7 +7593,7 @@ static void set_phy_vars(struct link_params *params) else if (phy_index == EXT_PHY2) actual_phy_idx = EXT_PHY1; } - params->phy[actual_phy_idx].req_flow_ctrl = + params->phy[actual_phy_idx].req_flow_ctrl = params->req_flow_ctrl[link_cfg_idx]; params->phy[actual_phy_idx].req_line_speed = @@ -7461,57 +7646,6 @@ u8 bnx2x_phy_init(struct link_params *params, struct link_vars *vars) set_phy_vars(params); DP(NETIF_MSG_LINK, "Num of phys on board: %d\n", params->num_phys); - if (CHIP_REV_IS_FPGA(bp)) { - - vars->link_up = 1; - vars->line_speed = SPEED_10000; - vars->duplex = DUPLEX_FULL; - vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE; - vars->link_status = (LINK_STATUS_LINK_UP | LINK_10GTFD); - /* enable on E1.5 FPGA */ - if (CHIP_IS_E1H(bp)) { - vars->flow_ctrl |= - (BNX2X_FLOW_CTRL_TX | - BNX2X_FLOW_CTRL_RX); - vars->link_status |= - (LINK_STATUS_TX_FLOW_CONTROL_ENABLED | - LINK_STATUS_RX_FLOW_CONTROL_ENABLED); - } - - bnx2x_emac_enable(params, vars, 0); - if (!(CHIP_IS_E2(bp))) - bnx2x_pbf_update(params, vars->flow_ctrl, - vars->line_speed); - /* disable drain */ - REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); - - /* update shared memory */ - bnx2x_update_mng(params, vars->link_status); - - return 0; - - } else - if (CHIP_REV_IS_EMUL(bp)) { - - vars->link_up = 1; - vars->line_speed = SPEED_10000; - vars->duplex = DUPLEX_FULL; - vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE; - vars->link_status = (LINK_STATUS_LINK_UP | LINK_10GTFD); - - bnx2x_bmac_enable(params, vars, 0); - - bnx2x_pbf_update(params, vars->flow_ctrl, vars->line_speed); - /* Disable drain */ - REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE - + params->port*4, 0); - - /* update shared memory */ - bnx2x_update_mng(params, vars->link_status); - - return 0; - - } else if (params->loopback_mode == LOOPBACK_BMAC) { vars->link_up = 1; @@ -7527,8 +7661,7 @@ u8 bnx2x_phy_init(struct link_params *params, struct link_vars *vars) /* set bmac loopback */ bnx2x_bmac_enable(params, vars, 1); - REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + - params->port*4, 0); + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); } else if (params->loopback_mode == LOOPBACK_EMAC) { @@ -7544,8 +7677,7 @@ u8 bnx2x_phy_init(struct link_params *params, struct link_vars *vars) /* set bmac loopback */ bnx2x_emac_enable(params, vars, 1); bnx2x_emac_program(params, vars); - REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + - params->port*4, 0); + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); } else if ((params->loopback_mode == LOOPBACK_XGXS) || (params->loopback_mode == LOOPBACK_EXT_PHY)) { @@ -7568,8 +7700,7 @@ u8 bnx2x_phy_init(struct link_params *params, struct link_vars *vars) bnx2x_emac_program(params, vars); bnx2x_emac_enable(params, vars, 0); } else - bnx2x_bmac_enable(params, vars, 0); - + bnx2x_bmac_enable(params, vars, 0); if (params->loopback_mode == LOOPBACK_XGXS) { /* set 10G XGXS loopback */ params->phy[INT_PHY].config_loopback( @@ -7587,9 +7718,7 @@ u8 bnx2x_phy_init(struct link_params *params, struct link_vars *vars) params); } } - - REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + - params->port*4, 0); + REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0); bnx2x_set_led(params, vars, LED_MODE_OPER, vars->line_speed); @@ -7608,7 +7737,7 @@ u8 bnx2x_phy_init(struct link_params *params, struct link_vars *vars) return 0; } u8 bnx2x_link_reset(struct link_params *params, struct link_vars *vars, - u8 reset_ext_phy) + u8 reset_ext_phy) { struct bnx2x *bp = params->bp; u8 phy_index, port = params->port, clear_latch_ind = 0; @@ -7617,10 +7746,10 @@ u8 bnx2x_link_reset(struct link_params *params, struct link_vars *vars, vars->link_status = 0; bnx2x_update_mng(params, vars->link_status); bnx2x_bits_dis(bp, NIG_REG_MASK_INTERRUPT_PORT0 + port*4, - (NIG_MASK_XGXS0_LINK_STATUS | - NIG_MASK_XGXS0_LINK10G | - NIG_MASK_SERDES0_LINK_STATUS | - NIG_MASK_MI_INT)); + (NIG_MASK_XGXS0_LINK_STATUS | + NIG_MASK_XGXS0_LINK10G | + NIG_MASK_SERDES0_LINK_STATUS | + NIG_MASK_MI_INT)); /* activate nig drain */ REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + port*4, 1); @@ -7719,21 +7848,22 @@ static u8 bnx2x_8073_common_init_phy(struct bnx2x *bp, /* disable attentions */ bnx2x_bits_dis(bp, NIG_REG_MASK_INTERRUPT_PORT0 + port_of_path*4, - (NIG_MASK_XGXS0_LINK_STATUS | - NIG_MASK_XGXS0_LINK10G | - NIG_MASK_SERDES0_LINK_STATUS | - NIG_MASK_MI_INT)); + (NIG_MASK_XGXS0_LINK_STATUS | + NIG_MASK_XGXS0_LINK10G | + NIG_MASK_SERDES0_LINK_STATUS | + NIG_MASK_MI_INT)); /* Need to take the phy out of low power mode in order to write to access its registers */ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_HIGH, port); + MISC_REGISTERS_GPIO_OUTPUT_HIGH, + port); /* Reset the phy */ bnx2x_cl45_write(bp, &phy[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_CTRL, - 1<<15); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_CTRL, + 1<<15); } /* Add delay of 150ms after reset */ @@ -7762,18 +7892,20 @@ static u8 bnx2x_8073_common_init_phy(struct bnx2x *bp, /* Only set bit 10 = 1 (Tx power down) */ bnx2x_cl45_read(bp, phy_blk[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_TX_POWER_DOWN, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_TX_POWER_DOWN, &val); /* Phase1 of TX_POWER_DOWN reset */ bnx2x_cl45_write(bp, phy_blk[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_TX_POWER_DOWN, - (val | 1<<10)); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_TX_POWER_DOWN, + (val | 1<<10)); } - /* Toggle Transmitter: Power down and then up with 600ms - delay between */ + /* + * Toggle Transmitter: Power down and then up with 600ms delay + * between + */ msleep(600); /* PART3 - complete TX_POWER_DOWN process, and set GPIO2 back to low */ @@ -7781,25 +7913,25 @@ static u8 bnx2x_8073_common_init_phy(struct bnx2x *bp, /* Phase2 of POWER_DOWN_RESET */ /* Release bit 10 (Release Tx power down) */ bnx2x_cl45_read(bp, phy_blk[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_TX_POWER_DOWN, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_TX_POWER_DOWN, &val); bnx2x_cl45_write(bp, phy_blk[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_TX_POWER_DOWN, (val & (~(1<<10)))); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_TX_POWER_DOWN, (val & (~(1<<10)))); msleep(15); /* Read modify write the SPI-ROM version select register */ bnx2x_cl45_read(bp, phy_blk[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_EDC_FFE_MAIN, &val); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_EDC_FFE_MAIN, &val); bnx2x_cl45_write(bp, phy_blk[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_EDC_FFE_MAIN, (val | (1<<12))); + MDIO_PMA_DEVAD, + MDIO_PMA_REG_EDC_FFE_MAIN, (val | (1<<12))); /* set GPIO2 back to LOW */ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_2, - MISC_REGISTERS_GPIO_OUTPUT_LOW, port); + MISC_REGISTERS_GPIO_OUTPUT_LOW, port); } return 0; } @@ -7846,32 +7978,90 @@ static u8 bnx2x_8726_common_init_phy(struct bnx2x *bp, /* Set fault module detected LED on */ bnx2x_set_gpio(bp, MISC_REGISTERS_GPIO_0, - MISC_REGISTERS_GPIO_HIGH, - port); + MISC_REGISTERS_GPIO_HIGH, + port); } return 0; } +static void bnx2x_get_ext_phy_reset_gpio(struct bnx2x *bp, u32 shmem_base, + u8 *io_gpio, u8 *io_port) +{ + + u32 phy_gpio_reset = REG_RD(bp, shmem_base + + offsetof(struct shmem_region, + dev_info.port_hw_config[PORT_0].default_cfg)); + switch (phy_gpio_reset) { + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO0_P0: + *io_gpio = 0; + *io_port = 0; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO1_P0: + *io_gpio = 1; + *io_port = 0; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO2_P0: + *io_gpio = 2; + *io_port = 0; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO3_P0: + *io_gpio = 3; + *io_port = 0; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO0_P1: + *io_gpio = 0; + *io_port = 1; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO1_P1: + *io_gpio = 1; + *io_port = 1; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO2_P1: + *io_gpio = 2; + *io_port = 1; + break; + case PORT_HW_CFG_EXT_PHY_GPIO_RST_GPIO3_P1: + *io_gpio = 3; + *io_port = 1; + break; + default: + /* Don't override the io_gpio and io_port */ + break; + } +} static u8 bnx2x_8727_common_init_phy(struct bnx2x *bp, u32 shmem_base_path[], u32 shmem2_base_path[], u8 phy_index, u32 chip_id) { - s8 port; + s8 port, reset_gpio; u32 swap_val, swap_override; struct bnx2x_phy phy[PORT_MAX]; struct bnx2x_phy *phy_blk[PORT_MAX]; s8 port_of_path; - swap_val = REG_RD(bp, NIG_REG_PORT_SWAP); - swap_override = REG_RD(bp, NIG_REG_STRAP_OVERRIDE); + swap_val = REG_RD(bp, NIG_REG_PORT_SWAP); + swap_override = REG_RD(bp, NIG_REG_STRAP_OVERRIDE); + reset_gpio = MISC_REGISTERS_GPIO_1; port = 1; - bnx2x_ext_phy_hw_reset(bp, port ^ (swap_val && swap_override)); + /* + * Retrieve the reset gpio/port which control the reset. + * Default is GPIO1, PORT1 + */ + bnx2x_get_ext_phy_reset_gpio(bp, shmem_base_path[0], + (u8 *)&reset_gpio, (u8 *)&port); /* Calculate the port based on port swap */ port ^= (swap_val && swap_override); + /* Initiate PHY reset*/ + bnx2x_set_gpio(bp, reset_gpio, MISC_REGISTERS_GPIO_OUTPUT_LOW, + port); + msleep(1); + bnx2x_set_gpio(bp, reset_gpio, MISC_REGISTERS_GPIO_OUTPUT_HIGH, + port); + msleep(5); /* PART1 - Reset both phys */ @@ -7907,9 +8097,7 @@ static u8 bnx2x_8727_common_init_phy(struct bnx2x *bp, /* Reset the phy */ bnx2x_cl45_write(bp, &phy[port], - MDIO_PMA_DEVAD, - MDIO_PMA_REG_CTRL, - 1<<15); + MDIO_PMA_DEVAD, MDIO_PMA_REG_CTRL, 1<<15); } /* Add delay of 150ms after reset */ @@ -7923,7 +8111,7 @@ static u8 bnx2x_8727_common_init_phy(struct bnx2x *bp, } /* PART2 - Download firmware to both phys */ for (port = PORT_MAX - 1; port >= PORT_0; port--) { - if (CHIP_IS_E2(bp)) + if (CHIP_IS_E2(bp)) port_of_path = 0; else port_of_path = port; @@ -7958,8 +8146,10 @@ static u8 bnx2x_ext_phy_common_init(struct bnx2x *bp, u32 shmem_base_path[], break; case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8726: - /* GPIO1 affects both ports, so there's need to pull - it for single port alone */ + /* + * GPIO1 affects both ports, so there's need to pull + * it for single port alone + */ rc = bnx2x_8726_common_init_phy(bp, shmem_base_path, shmem2_base_path, phy_index, chip_id); @@ -7969,11 +8159,15 @@ static u8 bnx2x_ext_phy_common_init(struct bnx2x *bp, u32 shmem_base_path[], break; default: DP(NETIF_MSG_LINK, - "bnx2x_common_init_phy: ext_phy 0x%x not required\n", - ext_phy_type); + "ext_phy 0x%x common init not required\n", + ext_phy_type); break; } + if (rc != 0) + netdev_err(bp->dev, "Warning: PHY was not initialized," + " Port %d\n", + 0); return rc; } @@ -7986,9 +8180,6 @@ u8 bnx2x_common_init_phy(struct bnx2x *bp, u32 shmem_base_path[], u32 ext_phy_type, ext_phy_config; DP(NETIF_MSG_LINK, "Begin common phy init\n"); - if (CHIP_REV_IS_EMUL(bp)) - return 0; - /* Check if common init was already done */ phy_ver = REG_RD(bp, shmem_base_path[0] + offsetof(struct shmem_region, diff --git a/drivers/net/bnx2x/bnx2x_link.h b/drivers/net/bnx2x/bnx2x_link.h index bedab1a..92f36b6 100644 --- a/drivers/net/bnx2x/bnx2x_link.h +++ b/drivers/net/bnx2x/bnx2x_link.h @@ -1,4 +1,4 @@ -/* Copyright 2008-2010 Broadcom Corporation +/* Copyright 2008-2011 Broadcom Corporation * * Unless you and Broadcom execute a separate written software license * agreement governing use of this software, this software is licensed to you @@ -33,7 +33,7 @@ #define BNX2X_FLOW_CTRL_BOTH PORT_FEATURE_FLOW_CONTROL_BOTH #define BNX2X_FLOW_CTRL_NONE PORT_FEATURE_FLOW_CONTROL_NONE -#define SPEED_AUTO_NEG 0 +#define SPEED_AUTO_NEG 0 #define SPEED_12000 12000 #define SPEED_12500 12500 #define SPEED_13000 13000 @@ -44,8 +44,8 @@ #define SFP_EEPROM_VENDOR_NAME_SIZE 16 #define SFP_EEPROM_VENDOR_OUI_ADDR 0x25 #define SFP_EEPROM_VENDOR_OUI_SIZE 3 -#define SFP_EEPROM_PART_NO_ADDR 0x28 -#define SFP_EEPROM_PART_NO_SIZE 16 +#define SFP_EEPROM_PART_NO_ADDR 0x28 +#define SFP_EEPROM_PART_NO_SIZE 16 #define PWR_FLT_ERR_MSG_LEN 250 #define XGXS_EXT_PHY_TYPE(ext_phy_config) \ @@ -62,7 +62,7 @@ #define SINGLE_MEDIA(params) (params->num_phys == 2) /* Dual Media board contains two external phy with different media */ #define DUAL_MEDIA(params) (params->num_phys == 3) -#define FW_PARAM_MDIO_CTRL_OFFSET 16 +#define FW_PARAM_MDIO_CTRL_OFFSET 16 #define FW_PARAM_SET(phy_addr, phy_type, mdio_access) \ (phy_addr | phy_type | mdio_access << FW_PARAM_MDIO_CTRL_OFFSET) @@ -201,12 +201,14 @@ struct link_params { /* Default / User Configuration */ u8 loopback_mode; -#define LOOPBACK_NONE 0 -#define LOOPBACK_EMAC 1 -#define LOOPBACK_BMAC 2 +#define LOOPBACK_NONE 0 +#define LOOPBACK_EMAC 1 +#define LOOPBACK_BMAC 2 #define LOOPBACK_XGXS 3 #define LOOPBACK_EXT_PHY 4 -#define LOOPBACK_EXT 5 +#define LOOPBACK_EXT 5 +#define LOOPBACK_UMAC 6 +#define LOOPBACK_XMAC 7 /* Device parameters */ u8 mac_addr[6]; @@ -230,10 +232,11 @@ struct link_params { /* Phy register parameter */ u32 chip_id; + /* features */ u32 feature_config_flags; -#define FEATURE_CONFIG_OVERRIDE_PREEMPHASIS_ENABLED (1<<0) -#define FEATURE_CONFIG_PFC_ENABLED (1<<1) -#define FEATURE_CONFIG_BC_SUPPORTS_OPT_MDL_VRFY (1<<2) +#define FEATURE_CONFIG_OVERRIDE_PREEMPHASIS_ENABLED (1<<0) +#define FEATURE_CONFIG_PFC_ENABLED (1<<1) +#define FEATURE_CONFIG_BC_SUPPORTS_OPT_MDL_VRFY (1<<2) #define FEATURE_CONFIG_BC_SUPPORTS_DUAL_PHY_OPT_MDL_VRFY (1<<3) /* Will be populated during common init */ struct bnx2x_phy phy[MAX_PHYS]; @@ -334,6 +337,11 @@ void bnx2x_ext_phy_hw_reset(struct bnx2x *bp, u8 port); /* Reset the external of SFX7101 */ void bnx2x_sfx7101_sp_sw_reset(struct bnx2x *bp, struct bnx2x_phy *phy); +/* Read "byte_cnt" bytes from address "addr" from the SFP+ EEPROM */ +u8 bnx2x_read_sfp_module_eeprom(struct bnx2x_phy *phy, + struct link_params *params, u16 addr, + u8 byte_cnt, u8 *o_buf); + void bnx2x_hw_reset_phy(struct link_params *params); /* Checks if HW lock is required for this phy/board type */ @@ -379,7 +387,7 @@ void bnx2x_ets_disabled(struct link_params *params); /* Used to configure the ETS to BW limited */ void bnx2x_ets_bw_limit(const struct link_params *params, const u32 cos0_bw, - const u32 cos1_bw); + const u32 cos1_bw); /* Used to configure the ETS to strict */ u8 bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos); diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c index d584d32..6c7745e 100644 --- a/drivers/net/bnx2x/bnx2x_main.c +++ b/drivers/net/bnx2x/bnx2x_main.c @@ -586,7 +586,7 @@ static int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, bp->slowpath->wb_data[2], bp->slowpath->wb_data[3]); /* lock the dmae channel */ - mutex_lock(&bp->dmae_mutex); + spin_lock_bh(&bp->dmae_lock); /* reset completion */ *wb_comp = 0; @@ -617,7 +617,7 @@ static int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, bp->slowpath->wb_data[2], bp->slowpath->wb_data[3]); unlock: - mutex_unlock(&bp->dmae_mutex); + spin_unlock_bh(&bp->dmae_lock); return rc; } @@ -1397,7 +1397,7 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, } smp_mb__before_atomic_inc(); - atomic_inc(&bp->spq_left); + atomic_inc(&bp->cq_spq_left); /* push the change in fp->state and towards the memory */ smp_wmb(); @@ -2473,8 +2473,14 @@ static void bnx2x_pf_rx_cl_prep(struct bnx2x *bp, rxq_init->sge_map = fp->rx_sge_mapping; rxq_init->rcq_map = fp->rx_comp_mapping; rxq_init->rcq_np_map = fp->rx_comp_mapping + BCM_PAGE_SIZE; - rxq_init->mtu = bp->dev->mtu; - rxq_init->buf_sz = bp->rx_buf_size; + + /* Always use mini-jumbo MTU for FCoE L2 ring */ + if (IS_FCOE_FP(fp)) + rxq_init->mtu = BNX2X_FCOE_MINI_JUMBO_MTU; + else + rxq_init->mtu = bp->dev->mtu; + + rxq_init->buf_sz = fp->rx_buf_size; rxq_init->cl_qzone_id = fp->cl_qzone_id; rxq_init->cl_id = fp->cl_id; rxq_init->spcl_id = fp->cl_id; @@ -2726,11 +2732,18 @@ int bnx2x_sp_post(struct bnx2x *bp, int command, int cid, spin_lock_bh(&bp->spq_lock); - if (!atomic_read(&bp->spq_left)) { - BNX2X_ERR("BUG! SPQ ring full!\n"); - spin_unlock_bh(&bp->spq_lock); - bnx2x_panic(); - return -EBUSY; + if (common) { + if (!atomic_read(&bp->eq_spq_left)) { + BNX2X_ERR("BUG! EQ ring full!\n"); + spin_unlock_bh(&bp->spq_lock); + bnx2x_panic(); + return -EBUSY; + } + } else if (!atomic_read(&bp->cq_spq_left)) { + BNX2X_ERR("BUG! SPQ ring full!\n"); + spin_unlock_bh(&bp->spq_lock); + bnx2x_panic(); + return -EBUSY; } spe = bnx2x_sp_get_next(bp); @@ -2761,20 +2774,26 @@ int bnx2x_sp_post(struct bnx2x *bp, int command, int cid, spe->data.update_data_addr.lo = cpu_to_le32(data_lo); /* stats ramrod has it's own slot on the spq */ - if (command != RAMROD_CMD_ID_COMMON_STAT_QUERY) + if (command != RAMROD_CMD_ID_COMMON_STAT_QUERY) { /* It's ok if the actual decrement is issued towards the memory * somewhere between the spin_lock and spin_unlock. Thus no * more explict memory barrier is needed. */ - atomic_dec(&bp->spq_left); + if (common) + atomic_dec(&bp->eq_spq_left); + else + atomic_dec(&bp->cq_spq_left); + } + DP(BNX2X_MSG_SP/*NETIF_MSG_TIMER*/, "SPQE[%x] (%x:%x) command %d hw_cid %x data (%x:%x) " - "type(0x%x) left %x\n", + "type(0x%x) left (ETH, COMMON) (%x,%x)\n", bp->spq_prod_idx, (u32)U64_HI(bp->spq_mapping), (u32)(U64_LO(bp->spq_mapping) + (void *)bp->spq_prod_bd - (void *)bp->spq), command, - HW_CID(bp, cid), data_hi, data_lo, type, atomic_read(&bp->spq_left)); + HW_CID(bp, cid), data_hi, data_lo, type, + atomic_read(&bp->cq_spq_left), atomic_read(&bp->eq_spq_left)); bnx2x_sp_prod_update(bp); spin_unlock_bh(&bp->spq_lock); @@ -3686,8 +3705,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) sw_cons = bp->eq_cons; sw_prod = bp->eq_prod; - DP(BNX2X_MSG_SP, "EQ: hw_cons %u sw_cons %u bp->spq_left %u\n", - hw_cons, sw_cons, atomic_read(&bp->spq_left)); + DP(BNX2X_MSG_SP, "EQ: hw_cons %u sw_cons %u bp->cq_spq_left %u\n", + hw_cons, sw_cons, atomic_read(&bp->eq_spq_left)); for (; sw_cons != hw_cons; sw_prod = NEXT_EQ_IDX(sw_prod), sw_cons = NEXT_EQ_IDX(sw_cons)) { @@ -3752,13 +3771,15 @@ static void bnx2x_eq_int(struct bnx2x *bp) case (EVENT_RING_OPCODE_SET_MAC | BNX2X_STATE_OPEN): case (EVENT_RING_OPCODE_SET_MAC | BNX2X_STATE_DIAG): DP(NETIF_MSG_IFUP, "got set mac ramrod\n"); - bp->set_mac_pending = 0; + if (elem->message.data.set_mac_event.echo) + bp->set_mac_pending = 0; break; case (EVENT_RING_OPCODE_SET_MAC | BNX2X_STATE_CLOSING_WAIT4_HALT): DP(NETIF_MSG_IFDOWN, "got (un)set mac ramrod\n"); - bp->set_mac_pending = 0; + if (elem->message.data.set_mac_event.echo) + bp->set_mac_pending = 0; break; default: /* unknown event log error and continue */ @@ -3770,7 +3791,7 @@ next_spqe: } /* for */ smp_mb__before_atomic_inc(); - atomic_add(spqe_cnt, &bp->spq_left); + atomic_add(spqe_cnt, &bp->eq_spq_left); bp->eq_cons = sw_cons; bp->eq_prod = sw_prod; @@ -4203,7 +4224,7 @@ void bnx2x_update_coalesce(struct bnx2x *bp) static void bnx2x_init_sp_ring(struct bnx2x *bp) { spin_lock_init(&bp->spq_lock); - atomic_set(&bp->spq_left, MAX_SPQ_PENDING); + atomic_set(&bp->cq_spq_left, MAX_SPQ_PENDING); bp->spq_prod_idx = 0; bp->dsb_sp_prod = BNX2X_SP_DSB_INDEX; @@ -4228,9 +4249,12 @@ static void bnx2x_init_eq_ring(struct bnx2x *bp) bp->eq_cons = 0; bp->eq_prod = NUM_EQ_DESC; bp->eq_cons_sb = BNX2X_EQ_INDEX; + /* we want a warning message before it gets rought... */ + atomic_set(&bp->eq_spq_left, + min_t(int, MAX_SP_DESC_CNT - MAX_SPQ_PENDING, NUM_EQ_DESC) - 1); } -static void bnx2x_init_ind_table(struct bnx2x *bp) +void bnx2x_push_indir_table(struct bnx2x *bp) { int func = BP_FUNC(bp); int i; @@ -4238,13 +4262,20 @@ static void bnx2x_init_ind_table(struct bnx2x *bp) if (bp->multi_mode == ETH_RSS_MODE_DISABLED) return; - DP(NETIF_MSG_IFUP, - "Initializing indirection table multi_mode %d\n", bp->multi_mode); for (i = 0; i < TSTORM_INDIRECTION_TABLE_SIZE; i++) REG_WR8(bp, BAR_TSTRORM_INTMEM + TSTORM_INDIRECTION_TABLE_OFFSET(func) + i, - bp->fp->cl_id + (i % (bp->num_queues - - NONE_ETH_CONTEXT_USE))); + bp->fp->cl_id + bp->rx_indir_table[i]); +} + +static void bnx2x_init_ind_table(struct bnx2x *bp) +{ + int i; + + for (i = 0; i < TSTORM_INDIRECTION_TABLE_SIZE; i++) + bp->rx_indir_table[i] = i % BNX2X_NUM_ETH_QUEUES(bp); + + bnx2x_push_indir_table(bp); } void bnx2x_set_storm_rx_mode(struct bnx2x *bp) @@ -5840,7 +5871,7 @@ int bnx2x_init_hw(struct bnx2x *bp, u32 load_code) BP_ABS_FUNC(bp), load_code); bp->dmae_ready = 0; - mutex_init(&bp->dmae_mutex); + spin_lock_init(&bp->dmae_lock); rc = bnx2x_gunzip_init(bp); if (rc) return rc; @@ -5992,6 +6023,8 @@ void bnx2x_free_mem(struct bnx2x *bp) BNX2X_PCI_FREE(bp->eq_ring, bp->eq_mapping, BCM_PAGE_SIZE * NUM_EQ_PAGES); + BNX2X_FREE(bp->rx_indir_table); + #undef BNX2X_PCI_FREE #undef BNX2X_KFREE } @@ -6122,6 +6155,9 @@ int bnx2x_alloc_mem(struct bnx2x *bp) /* EQ */ BNX2X_PCI_ALLOC(bp->eq_ring, &bp->eq_mapping, BCM_PAGE_SIZE * NUM_EQ_PAGES); + + BNX2X_ALLOC(bp->rx_indir_table, sizeof(bp->rx_indir_table[0]) * + TSTORM_INDIRECTION_TABLE_SIZE); return 0; alloc_mem_err: @@ -6175,12 +6211,14 @@ static void bnx2x_set_mac_addr_gen(struct bnx2x *bp, int set, const u8 *mac, int ramrod_flags = WAIT_RAMROD_COMMON; bp->set_mac_pending = 1; - smp_wmb(); config->hdr.length = 1; config->hdr.offset = cam_offset; config->hdr.client_id = 0xff; - config->hdr.reserved1 = 0; + /* Mark the single MAC configuration ramrod as opposed to a + * UC/MC list configuration). + */ + config->hdr.echo = 1; /* primary MAC */ config->config_table[0].msb_mac_addr = @@ -6212,6 +6250,8 @@ static void bnx2x_set_mac_addr_gen(struct bnx2x *bp, int set, const u8 *mac, config->config_table[0].middle_mac_addr, config->config_table[0].lsb_mac_addr, BP_FUNC(bp), cl_bit_vec); + mb(); + bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_SET_MAC, 0, U64_HI(bnx2x_sp_mapping(bp, mac_config)), U64_LO(bnx2x_sp_mapping(bp, mac_config)), 1); @@ -6276,20 +6316,15 @@ static u8 bnx2x_e1h_cam_offset(struct bnx2x *bp, u8 rel_offset) if (CHIP_IS_E1H(bp)) return E1H_FUNC_MAX * rel_offset + BP_FUNC(bp); else if (CHIP_MODE_IS_4_PORT(bp)) - return BP_FUNC(bp) * 32 + rel_offset; + return E2_FUNC_MAX * rel_offset + BP_FUNC(bp); else - return BP_VN(bp) * 32 + rel_offset; + return E2_FUNC_MAX * rel_offset + BP_VN(bp); } /** * LLH CAM line allocations: currently only iSCSI and ETH macs are * relevant. In addition, current implementation is tuned for a * single ETH MAC. - * - * When multiple unicast ETH MACs PF configuration in switch - * independent mode is required (NetQ, multiple netdev MACs, - * etc.), consider better utilisation of 16 per function MAC - * entries in the LLH memory. */ enum { LLH_CAM_ISCSI_ETH_LINE = 0, @@ -6364,14 +6399,37 @@ void bnx2x_set_eth_mac(struct bnx2x *bp, int set) bnx2x_set_mac_addr_gen(bp, set, bcast, 0, cam_offset + 1, 1); } } -static void bnx2x_set_e1_mc_list(struct bnx2x *bp, u8 offset) + +static inline u8 bnx2x_e1_cam_mc_offset(struct bnx2x *bp) +{ + return CHIP_REV_IS_SLOW(bp) ? + (BNX2X_MAX_EMUL_MULTI * (1 + BP_PORT(bp))) : + (BNX2X_MAX_MULTICAST * (1 + BP_PORT(bp))); +} + +/* set mc list, do not wait as wait implies sleep and + * set_rx_mode can be invoked from non-sleepable context. + * + * Instead we use the same ramrod data buffer each time we need + * to configure a list of addresses, and use the fact that the + * list of MACs is changed in an incremental way and that the + * function is called under the netif_addr_lock. A temporary + * inconsistent CAM configuration (possible in case of a very fast + * sequence of add/del/add on the host side) will shortly be + * restored by the handler of the last ramrod. + */ +static int bnx2x_set_e1_mc_list(struct bnx2x *bp) { int i = 0, old; struct net_device *dev = bp->dev; + u8 offset = bnx2x_e1_cam_mc_offset(bp); struct netdev_hw_addr *ha; struct mac_configuration_cmd *config_cmd = bnx2x_sp(bp, mcast_config); dma_addr_t config_cmd_map = bnx2x_sp_mapping(bp, mcast_config); + if (netdev_mc_count(dev) > BNX2X_MAX_MULTICAST) + return -EINVAL; + netdev_for_each_mc_addr(ha, dev) { /* copy mac */ config_cmd->config_table[i].msb_mac_addr = @@ -6412,32 +6470,47 @@ static void bnx2x_set_e1_mc_list(struct bnx2x *bp, u8 offset) } } + wmb(); + config_cmd->hdr.length = i; config_cmd->hdr.offset = offset; config_cmd->hdr.client_id = 0xff; - config_cmd->hdr.reserved1 = 0; + /* Mark that this ramrod doesn't use bp->set_mac_pending for + * synchronization. + */ + config_cmd->hdr.echo = 0; - bp->set_mac_pending = 1; - smp_wmb(); + mb(); - bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_SET_MAC, 0, + return bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_SET_MAC, 0, U64_HI(config_cmd_map), U64_LO(config_cmd_map), 1); } -static void bnx2x_invlidate_e1_mc_list(struct bnx2x *bp) + +void bnx2x_invalidate_e1_mc_list(struct bnx2x *bp) { int i; struct mac_configuration_cmd *config_cmd = bnx2x_sp(bp, mcast_config); dma_addr_t config_cmd_map = bnx2x_sp_mapping(bp, mcast_config); int ramrod_flags = WAIT_RAMROD_COMMON; + u8 offset = bnx2x_e1_cam_mc_offset(bp); - bp->set_mac_pending = 1; - smp_wmb(); - - for (i = 0; i < config_cmd->hdr.length; i++) + for (i = 0; i < BNX2X_MAX_MULTICAST; i++) SET_FLAG(config_cmd->config_table[i].flags, MAC_CONFIGURATION_ENTRY_ACTION_TYPE, T_ETH_MAC_COMMAND_INVALIDATE); + wmb(); + + config_cmd->hdr.length = BNX2X_MAX_MULTICAST; + config_cmd->hdr.offset = offset; + config_cmd->hdr.client_id = 0xff; + /* We'll wait for a completion this time... */ + config_cmd->hdr.echo = 1; + + bp->set_mac_pending = 1; + + mb(); + bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_SET_MAC, 0, U64_HI(config_cmd_map), U64_LO(config_cmd_map), 1); @@ -6447,6 +6520,44 @@ static void bnx2x_invlidate_e1_mc_list(struct bnx2x *bp) } +/* Accept one or more multicasts */ +static int bnx2x_set_e1h_mc_list(struct bnx2x *bp) +{ + struct net_device *dev = bp->dev; + struct netdev_hw_addr *ha; + u32 mc_filter[MC_HASH_SIZE]; + u32 crc, bit, regidx; + int i; + + memset(mc_filter, 0, 4 * MC_HASH_SIZE); + + netdev_for_each_mc_addr(ha, dev) { + DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n", + bnx2x_mc_addr(ha)); + + crc = crc32c_le(0, bnx2x_mc_addr(ha), + ETH_ALEN); + bit = (crc >> 24) & 0xff; + regidx = bit >> 5; + bit &= 0x1f; + mc_filter[regidx] |= (1 << bit); + } + + for (i = 0; i < MC_HASH_SIZE; i++) + REG_WR(bp, MC_HASH_OFFSET(bp, i), + mc_filter[i]); + + return 0; +} + +void bnx2x_invalidate_e1h_mc_list(struct bnx2x *bp) +{ + int i; + + for (i = 0; i < MC_HASH_SIZE; i++) + REG_WR(bp, MC_HASH_OFFSET(bp, i), 0); +} + #ifdef BCM_CNIC /** * Set iSCSI MAC(s) at the next enties in the CAM after the ETH @@ -6465,12 +6576,13 @@ static int bnx2x_set_iscsi_eth_mac_addr(struct bnx2x *bp, int set) u32 iscsi_l2_cl_id = BNX2X_ISCSI_ETH_CL_ID + BP_E1HVN(bp) * NONE_ETH_CONTEXT_USE; u32 cl_bit_vec = (1 << iscsi_l2_cl_id); + u8 *iscsi_mac = bp->cnic_eth_dev.iscsi_mac; /* Send a SET_MAC ramrod */ - bnx2x_set_mac_addr_gen(bp, set, bp->iscsi_mac, cl_bit_vec, + bnx2x_set_mac_addr_gen(bp, set, iscsi_mac, cl_bit_vec, cam_offset, 0); - bnx2x_set_mac_in_nig(bp, set, bp->iscsi_mac, LLH_CAM_ISCSI_ETH_LINE); + bnx2x_set_mac_in_nig(bp, set, iscsi_mac, LLH_CAM_ISCSI_ETH_LINE); return 0; } @@ -7112,20 +7224,15 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode) /* Give HW time to discard old tx messages */ msleep(1); - if (CHIP_IS_E1(bp)) { - /* invalidate mc list, - * wait and poll (interrupts are off) - */ - bnx2x_invlidate_e1_mc_list(bp); - bnx2x_set_eth_mac(bp, 0); - - } else { - REG_WR(bp, NIG_REG_LLH0_FUNC_EN + port*8, 0); + bnx2x_set_eth_mac(bp, 0); - bnx2x_set_eth_mac(bp, 0); + bnx2x_invalidate_uc_list(bp); - for (i = 0; i < MC_HASH_SIZE; i++) - REG_WR(bp, MC_HASH_OFFSET(bp, i), 0); + if (CHIP_IS_E1(bp)) + bnx2x_invalidate_e1_mc_list(bp); + else { + bnx2x_invalidate_e1h_mc_list(bp); + REG_WR(bp, NIG_REG_LLH0_FUNC_EN + port*8, 0); } #ifdef BCM_CNIC @@ -8394,11 +8501,47 @@ static void __devinit bnx2x_get_port_hwinfo(struct bnx2x *bp) bp->common.shmem2_base); } +#ifdef BCM_CNIC +static void __devinit bnx2x_get_cnic_info(struct bnx2x *bp) +{ + u32 max_iscsi_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp, + drv_lic_key[BP_PORT(bp)].max_iscsi_conn); + u32 max_fcoe_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp, + drv_lic_key[BP_PORT(bp)].max_fcoe_conn); + + /* Get the number of maximum allowed iSCSI and FCoE connections */ + bp->cnic_eth_dev.max_iscsi_conn = + (max_iscsi_conn & BNX2X_MAX_ISCSI_INIT_CONN_MASK) >> + BNX2X_MAX_ISCSI_INIT_CONN_SHIFT; + + bp->cnic_eth_dev.max_fcoe_conn = + (max_fcoe_conn & BNX2X_MAX_FCOE_INIT_CONN_MASK) >> + BNX2X_MAX_FCOE_INIT_CONN_SHIFT; + + BNX2X_DEV_INFO("max_iscsi_conn 0x%x max_fcoe_conn 0x%x\n", + bp->cnic_eth_dev.max_iscsi_conn, + bp->cnic_eth_dev.max_fcoe_conn); + + /* If mamimum allowed number of connections is zero - + * disable the feature. + */ + if (!bp->cnic_eth_dev.max_iscsi_conn) + bp->flags |= NO_ISCSI_OOO_FLAG | NO_ISCSI_FLAG; + + if (!bp->cnic_eth_dev.max_fcoe_conn) + bp->flags |= NO_FCOE_FLAG; +} +#endif + static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp) { u32 val, val2; int func = BP_ABS_FUNC(bp); int port = BP_PORT(bp); +#ifdef BCM_CNIC + u8 *iscsi_mac = bp->cnic_eth_dev.iscsi_mac; + u8 *fip_mac = bp->fip_mac; +#endif if (BP_NOMCP(bp)) { BNX2X_ERROR("warning: random MAC workaround active\n"); @@ -8411,7 +8554,9 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp) bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2); #ifdef BCM_CNIC - /* iSCSI NPAR MAC */ + /* iSCSI and FCoE NPAR MACs: if there is no either iSCSI or + * FCoE MAC then the appropriate feature should be disabled. + */ if (IS_MF_SI(bp)) { u32 cfg = MF_CFG_RD(bp, func_ext_config[func].func_cfg); if (cfg & MACP_FUNC_CFG_FLAGS_ISCSI_OFFLOAD) { @@ -8419,8 +8564,39 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp) iscsi_mac_addr_upper); val = MF_CFG_RD(bp, func_ext_config[func]. iscsi_mac_addr_lower); - bnx2x_set_mac_buf(bp->iscsi_mac, val, val2); - } + BNX2X_DEV_INFO("Read iSCSI MAC: " + "0x%x:0x%04x\n", val2, val); + bnx2x_set_mac_buf(iscsi_mac, val, val2); + + /* Disable iSCSI OOO if MAC configuration is + * invalid. + */ + if (!is_valid_ether_addr(iscsi_mac)) { + bp->flags |= NO_ISCSI_OOO_FLAG | + NO_ISCSI_FLAG; + memset(iscsi_mac, 0, ETH_ALEN); + } + } else + bp->flags |= NO_ISCSI_OOO_FLAG | NO_ISCSI_FLAG; + + if (cfg & MACP_FUNC_CFG_FLAGS_FCOE_OFFLOAD) { + val2 = MF_CFG_RD(bp, func_ext_config[func]. + fcoe_mac_addr_upper); + val = MF_CFG_RD(bp, func_ext_config[func]. + fcoe_mac_addr_lower); + BNX2X_DEV_INFO("Read FCoE MAC to " + "0x%x:0x%04x\n", val2, val); + bnx2x_set_mac_buf(fip_mac, val, val2); + + /* Disable FCoE if MAC configuration is + * invalid. + */ + if (!is_valid_ether_addr(fip_mac)) { + bp->flags |= NO_FCOE_FLAG; + memset(bp->fip_mac, 0, ETH_ALEN); + } + } else + bp->flags |= NO_FCOE_FLAG; } #endif } else { @@ -8434,7 +8610,7 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp) iscsi_mac_upper); val = SHMEM_RD(bp, dev_info.port_hw_config[port]. iscsi_mac_lower); - bnx2x_set_mac_buf(bp->iscsi_mac, val, val2); + bnx2x_set_mac_buf(iscsi_mac, val, val2); #endif } @@ -8442,14 +8618,12 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp) memcpy(bp->dev->perm_addr, bp->dev->dev_addr, ETH_ALEN); #ifdef BCM_CNIC - /* Inform the upper layers about FCoE MAC */ + /* Set the FCoE MAC in modes other then MF_SI */ if (!CHIP_IS_E1x(bp)) { if (IS_MF_SD(bp)) - memcpy(bp->fip_mac, bp->dev->dev_addr, - sizeof(bp->fip_mac)); - else - memcpy(bp->fip_mac, bp->iscsi_mac, - sizeof(bp->fip_mac)); + memcpy(fip_mac, bp->dev->dev_addr, ETH_ALEN); + else if (!IS_MF(bp)) + memcpy(fip_mac, iscsi_mac, ETH_ALEN); } #endif } @@ -8612,6 +8786,10 @@ static int __devinit bnx2x_get_hwinfo(struct bnx2x *bp) /* Get MAC addresses */ bnx2x_get_mac_hwinfo(bp); +#ifdef BCM_CNIC + bnx2x_get_cnic_info(bp); +#endif + return rc; } @@ -8826,12 +9004,197 @@ static int bnx2x_close(struct net_device *dev) return 0; } +#define E1_MAX_UC_LIST 29 +#define E1H_MAX_UC_LIST 30 +#define E2_MAX_UC_LIST 14 +static inline u8 bnx2x_max_uc_list(struct bnx2x *bp) +{ + if (CHIP_IS_E1(bp)) + return E1_MAX_UC_LIST; + else if (CHIP_IS_E1H(bp)) + return E1H_MAX_UC_LIST; + else + return E2_MAX_UC_LIST; +} + + +static inline u8 bnx2x_uc_list_cam_offset(struct bnx2x *bp) +{ + if (CHIP_IS_E1(bp)) + /* CAM Entries for Port0: + * 0 - prim ETH MAC + * 1 - BCAST MAC + * 2 - iSCSI L2 ring ETH MAC + * 3-31 - UC MACs + * + * Port1 entries are allocated the same way starting from + * entry 32. + */ + return 3 + 32 * BP_PORT(bp); + else if (CHIP_IS_E1H(bp)) { + /* CAM Entries: + * 0-7 - prim ETH MAC for each function + * 8-15 - iSCSI L2 ring ETH MAC for each function + * 16 till 255 UC MAC lists for each function + * + * Remark: There is no FCoE support for E1H, thus FCoE related + * MACs are not considered. + */ + return E1H_FUNC_MAX * (CAM_ISCSI_ETH_LINE + 1) + + bnx2x_max_uc_list(bp) * BP_FUNC(bp); + } else { + /* CAM Entries (there is a separate CAM per engine): + * 0-4 - prim ETH MAC for each function + * 4-7 - iSCSI L2 ring ETH MAC for each function + * 8-11 - FIP ucast L2 MAC for each function + * 12-15 - ALL_ENODE_MACS mcast MAC for each function + * 16 till 71 UC MAC lists for each function + */ + u8 func_idx = + (CHIP_MODE_IS_4_PORT(bp) ? BP_FUNC(bp) : BP_VN(bp)); + + return E2_FUNC_MAX * (CAM_MAX_PF_LINE + 1) + + bnx2x_max_uc_list(bp) * func_idx; + } +} + +/* set uc list, do not wait as wait implies sleep and + * set_rx_mode can be invoked from non-sleepable context. + * + * Instead we use the same ramrod data buffer each time we need + * to configure a list of addresses, and use the fact that the + * list of MACs is changed in an incremental way and that the + * function is called under the netif_addr_lock. A temporary + * inconsistent CAM configuration (possible in case of very fast + * sequence of add/del/add on the host side) will shortly be + * restored by the handler of the last ramrod. + */ +static int bnx2x_set_uc_list(struct bnx2x *bp) +{ + int i = 0, old; + struct net_device *dev = bp->dev; + u8 offset = bnx2x_uc_list_cam_offset(bp); + struct netdev_hw_addr *ha; + struct mac_configuration_cmd *config_cmd = bnx2x_sp(bp, uc_mac_config); + dma_addr_t config_cmd_map = bnx2x_sp_mapping(bp, uc_mac_config); + + if (netdev_uc_count(dev) > bnx2x_max_uc_list(bp)) + return -EINVAL; + + netdev_for_each_uc_addr(ha, dev) { + /* copy mac */ + config_cmd->config_table[i].msb_mac_addr = + swab16(*(u16 *)&bnx2x_uc_addr(ha)[0]); + config_cmd->config_table[i].middle_mac_addr = + swab16(*(u16 *)&bnx2x_uc_addr(ha)[2]); + config_cmd->config_table[i].lsb_mac_addr = + swab16(*(u16 *)&bnx2x_uc_addr(ha)[4]); + + config_cmd->config_table[i].vlan_id = 0; + config_cmd->config_table[i].pf_id = BP_FUNC(bp); + config_cmd->config_table[i].clients_bit_vector = + cpu_to_le32(1 << BP_L_ID(bp)); + + SET_FLAG(config_cmd->config_table[i].flags, + MAC_CONFIGURATION_ENTRY_ACTION_TYPE, + T_ETH_MAC_COMMAND_SET); + + DP(NETIF_MSG_IFUP, + "setting UCAST[%d] (%04x:%04x:%04x)\n", i, + config_cmd->config_table[i].msb_mac_addr, + config_cmd->config_table[i].middle_mac_addr, + config_cmd->config_table[i].lsb_mac_addr); + + i++; + + /* Set uc MAC in NIG */ + bnx2x_set_mac_in_nig(bp, 1, bnx2x_uc_addr(ha), + LLH_CAM_ETH_LINE + i); + } + old = config_cmd->hdr.length; + if (old > i) { + for (; i < old; i++) { + if (CAM_IS_INVALID(config_cmd-> + config_table[i])) { + /* already invalidated */ + break; + } + /* invalidate */ + SET_FLAG(config_cmd->config_table[i].flags, + MAC_CONFIGURATION_ENTRY_ACTION_TYPE, + T_ETH_MAC_COMMAND_INVALIDATE); + } + } + + wmb(); + + config_cmd->hdr.length = i; + config_cmd->hdr.offset = offset; + config_cmd->hdr.client_id = 0xff; + /* Mark that this ramrod doesn't use bp->set_mac_pending for + * synchronization. + */ + config_cmd->hdr.echo = 0; + + mb(); + + return bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_SET_MAC, 0, + U64_HI(config_cmd_map), U64_LO(config_cmd_map), 1); + +} + +void bnx2x_invalidate_uc_list(struct bnx2x *bp) +{ + int i; + struct mac_configuration_cmd *config_cmd = bnx2x_sp(bp, uc_mac_config); + dma_addr_t config_cmd_map = bnx2x_sp_mapping(bp, uc_mac_config); + int ramrod_flags = WAIT_RAMROD_COMMON; + u8 offset = bnx2x_uc_list_cam_offset(bp); + u8 max_list_size = bnx2x_max_uc_list(bp); + + for (i = 0; i < max_list_size; i++) { + SET_FLAG(config_cmd->config_table[i].flags, + MAC_CONFIGURATION_ENTRY_ACTION_TYPE, + T_ETH_MAC_COMMAND_INVALIDATE); + bnx2x_set_mac_in_nig(bp, 0, NULL, LLH_CAM_ETH_LINE + 1 + i); + } + + wmb(); + + config_cmd->hdr.length = max_list_size; + config_cmd->hdr.offset = offset; + config_cmd->hdr.client_id = 0xff; + /* We'll wait for a completion this time... */ + config_cmd->hdr.echo = 1; + + bp->set_mac_pending = 1; + + mb(); + + bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_SET_MAC, 0, + U64_HI(config_cmd_map), U64_LO(config_cmd_map), 1); + + /* Wait for a completion */ + bnx2x_wait_ramrod(bp, 0, 0, &bp->set_mac_pending, + ramrod_flags); + +} + +static inline int bnx2x_set_mc_list(struct bnx2x *bp) +{ + /* some multicasts */ + if (CHIP_IS_E1(bp)) { + return bnx2x_set_e1_mc_list(bp); + } else { /* E1H and newer */ + return bnx2x_set_e1h_mc_list(bp); + } +} + /* called with netif_tx_lock from dev_mcast.c */ void bnx2x_set_rx_mode(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); u32 rx_mode = BNX2X_RX_MODE_NORMAL; - int port = BP_PORT(bp); if (bp->state != BNX2X_STATE_OPEN) { DP(NETIF_MSG_IFUP, "state is %x, returning\n", bp->state); @@ -8842,47 +9205,16 @@ void bnx2x_set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) rx_mode = BNX2X_RX_MODE_PROMISC; - else if ((dev->flags & IFF_ALLMULTI) || - ((netdev_mc_count(dev) > BNX2X_MAX_MULTICAST) && - CHIP_IS_E1(bp))) + else if (dev->flags & IFF_ALLMULTI) rx_mode = BNX2X_RX_MODE_ALLMULTI; - else { /* some multicasts */ - if (CHIP_IS_E1(bp)) { - /* - * set mc list, do not wait as wait implies sleep - * and set_rx_mode can be invoked from non-sleepable - * context - */ - u8 offset = (CHIP_REV_IS_SLOW(bp) ? - BNX2X_MAX_EMUL_MULTI*(1 + port) : - BNX2X_MAX_MULTICAST*(1 + port)); - - bnx2x_set_e1_mc_list(bp, offset); - } else { /* E1H */ - /* Accept one or more multicasts */ - struct netdev_hw_addr *ha; - u32 mc_filter[MC_HASH_SIZE]; - u32 crc, bit, regidx; - int i; - - memset(mc_filter, 0, 4 * MC_HASH_SIZE); - - netdev_for_each_mc_addr(ha, dev) { - DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n", - bnx2x_mc_addr(ha)); - - crc = crc32c_le(0, bnx2x_mc_addr(ha), - ETH_ALEN); - bit = (crc >> 24) & 0xff; - regidx = bit >> 5; - bit &= 0x1f; - mc_filter[regidx] |= (1 << bit); - } + else { + /* some multicasts */ + if (bnx2x_set_mc_list(bp)) + rx_mode = BNX2X_RX_MODE_ALLMULTI; - for (i = 0; i < MC_HASH_SIZE; i++) - REG_WR(bp, MC_HASH_OFFSET(bp, i), - mc_filter[i]); - } + /* some unicasts */ + if (bnx2x_set_uc_list(bp)) + rx_mode = BNX2X_RX_MODE_PROMISC; } bp->rx_mode = rx_mode; @@ -8963,7 +9295,7 @@ static const struct net_device_ops bnx2x_netdev_ops = { .ndo_stop = bnx2x_close, .ndo_start_xmit = bnx2x_start_xmit, .ndo_select_queue = bnx2x_select_queue, - .ndo_set_multicast_list = bnx2x_set_rx_mode, + .ndo_set_rx_mode = bnx2x_set_rx_mode, .ndo_set_mac_address = bnx2x_change_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_do_ioctl = bnx2x_ioctl, @@ -9789,15 +10121,21 @@ static void bnx2x_cnic_sp_post(struct bnx2x *bp, int count) HW_CID(bp, BNX2X_ISCSI_ETH_CID)); } - /* There may be not more than 8 L2 and COMMON SPEs and not more - * than 8 L5 SPEs in the air. + /* There may be not more than 8 L2 and not more than 8 L5 SPEs + * We also check that the number of outstanding + * COMMON ramrods is not more than the EQ and SPQ can + * accommodate. */ - if ((type == NONE_CONNECTION_TYPE) || - (type == ETH_CONNECTION_TYPE)) { - if (!atomic_read(&bp->spq_left)) + if (type == ETH_CONNECTION_TYPE) { + if (!atomic_read(&bp->cq_spq_left)) break; else - atomic_dec(&bp->spq_left); + atomic_dec(&bp->cq_spq_left); + } else if (type == NONE_CONNECTION_TYPE) { + if (!atomic_read(&bp->eq_spq_left)) + break; + else + atomic_dec(&bp->eq_spq_left); } else if ((type == ISCSI_CONNECTION_TYPE) || (type == FCOE_CONNECTION_TYPE)) { if (bp->cnic_spq_pending >= @@ -9875,7 +10213,8 @@ static int bnx2x_cnic_ctl_send(struct bnx2x *bp, struct cnic_ctl_info *ctl) int rc = 0; mutex_lock(&bp->cnic_mutex); - c_ops = bp->cnic_ops; + c_ops = rcu_dereference_protected(bp->cnic_ops, + lockdep_is_held(&bp->cnic_mutex)); if (c_ops) rc = c_ops->cnic_ctl(bp->cnic_data, ctl); mutex_unlock(&bp->cnic_mutex); @@ -9989,7 +10328,7 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl) int count = ctl->data.credit.credit_count; smp_mb__before_atomic_inc(); - atomic_add(count, &bp->spq_left); + atomic_add(count, &bp->cq_spq_left); smp_mb__after_atomic_inc(); break; } @@ -10085,6 +10424,13 @@ struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev) struct bnx2x *bp = netdev_priv(dev); struct cnic_eth_dev *cp = &bp->cnic_eth_dev; + /* If both iSCSI and FCoE are disabled - return NULL in + * order to indicate CNIC that it should not try to work + * with this device. + */ + if (NO_ISCSI(bp) && NO_FCOE(bp)) + return NULL; + cp->drv_owner = THIS_MODULE; cp->chip_id = CHIP_ID(bp); cp->pdev = bp->pdev; @@ -10105,6 +10451,15 @@ struct cnic_eth_dev *bnx2x_cnic_probe(struct net_device *dev) BP_E1HVN(bp) * NONE_ETH_CONTEXT_USE; cp->iscsi_l2_cid = BNX2X_ISCSI_ETH_CID; + if (NO_ISCSI_OOO(bp)) + cp->drv_state |= CNIC_DRV_STATE_NO_ISCSI_OOO; + + if (NO_ISCSI(bp)) + cp->drv_state |= CNIC_DRV_STATE_NO_ISCSI; + + if (NO_FCOE(bp)) + cp->drv_state |= CNIC_DRV_STATE_NO_FCOE; + DP(BNX2X_MSG_SP, "page_size %d, tbl_offset %d, tbl_lines %d, " "starting cid %d\n", cp->ctx_blk_size, diff --git a/drivers/net/bnx2x/bnx2x_reg.h b/drivers/net/bnx2x/bnx2x_reg.h index e01330b..1c89f19 100644 --- a/drivers/net/bnx2x/bnx2x_reg.h +++ b/drivers/net/bnx2x/bnx2x_reg.h @@ -6083,6 +6083,7 @@ Theotherbitsarereservedandshouldbezero*/ #define MDIO_PMA_REG_8727_PCS_OPT_CTRL 0xc808 #define MDIO_PMA_REG_8727_GPIO_CTRL 0xc80e #define MDIO_PMA_REG_8727_PCS_GP 0xc842 +#define MDIO_PMA_REG_8727_OPT_CFG_REG 0xc8e4 #define MDIO_AN_REG_8727_MISC_CTRL 0x8309 diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 163e0b0..77e3c6a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1372,8 +1372,8 @@ static int bond_compute_features(struct bonding *bond) { struct slave *slave; struct net_device *bond_dev = bond->dev; - unsigned long features = bond_dev->features; - unsigned long vlan_features = 0; + u32 features = bond_dev->features; + u32 vlan_features = 0; unsigned short max_hard_header_len = max((u16)ETH_HLEN, bond_dev->hard_header_len); int i; @@ -1400,8 +1400,8 @@ static int bond_compute_features(struct bonding *bond) done: features |= (bond_dev->features & BOND_VLAN_FEATURES); - bond_dev->features = netdev_fix_features(features, NULL); - bond_dev->vlan_features = netdev_fix_features(vlan_features, NULL); + bond_dev->features = netdev_fix_features(bond_dev, features); + bond_dev->vlan_features = netdev_fix_features(bond_dev, vlan_features); bond_dev->hard_header_len = max_hard_header_len; return 0; @@ -1594,9 +1594,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } - res = netdev_set_master(slave_dev, bond_dev); + res = netdev_set_bond_master(slave_dev, bond_dev); if (res) { - pr_debug("Error %d calling netdev_set_master\n", res); + pr_debug("Error %d calling netdev_set_bond_master\n", res); goto err_restore_mac; } /* open the slave since the application closed it */ @@ -1812,7 +1812,7 @@ err_close: dev_close(slave_dev); err_unset_master: - netdev_set_master(slave_dev, NULL); + netdev_set_bond_master(slave_dev, NULL); err_restore_mac: if (!bond->params.fail_over_mac) { @@ -1992,7 +1992,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) netif_addr_unlock_bh(bond_dev); } - netdev_set_master(slave_dev, NULL); + netdev_set_bond_master(slave_dev, NULL); #ifdef CONFIG_NET_POLL_CONTROLLER read_lock_bh(&bond->lock); @@ -2114,7 +2114,7 @@ static int bond_release_all(struct net_device *bond_dev) netif_addr_unlock_bh(bond_dev); } - netdev_set_master(slave_dev, NULL); + netdev_set_bond_master(slave_dev, NULL); /* close slave before restoring its mac address */ dev_close(slave_dev); @@ -4657,6 +4657,8 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_netpoll_cleanup = bond_netpoll_cleanup, .ndo_poll_controller = bond_poll_controller, #endif + .ndo_add_slave = bond_enslave, + .ndo_del_slave = bond_release, }; static void bond_destructor(struct net_device *bond_dev) diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8fd0174..72bb0f6 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1198,7 +1198,7 @@ static ssize_t bonding_store_carrier(struct device *d, bond->dev->name, new_value); } out: - return count; + return ret; } static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR, bonding_show_carrier, bonding_store_carrier); @@ -1595,7 +1595,7 @@ static ssize_t bonding_store_slaves_active(struct device *d, } } out: - return count; + return ret; } static DEVICE_ATTR(all_slaves_active, S_IRUGO | S_IWUSR, bonding_show_slaves_active, bonding_store_slaves_active); diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 5dec456..1d699e3 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -115,6 +115,8 @@ source "drivers/net/can/mscan/Kconfig" source "drivers/net/can/sja1000/Kconfig" +source "drivers/net/can/c_can/Kconfig" + source "drivers/net/can/usb/Kconfig" source "drivers/net/can/softing/Kconfig" diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index 53c82a7..24ebfe8 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -13,6 +13,7 @@ obj-y += softing/ obj-$(CONFIG_CAN_SJA1000) += sja1000/ obj-$(CONFIG_CAN_MSCAN) += mscan/ +obj-$(CONFIG_CAN_C_CAN) += c_can/ obj-$(CONFIG_CAN_AT91) += at91_can.o obj-$(CONFIG_CAN_TI_HECC) += ti_hecc.o obj-$(CONFIG_CAN_MCP251X) += mcp251x.o diff --git a/drivers/net/can/c_can/Kconfig b/drivers/net/can/c_can/Kconfig new file mode 100644 index 0000000..ffb9773 --- /dev/null +++ b/drivers/net/can/c_can/Kconfig @@ -0,0 +1,15 @@ +menuconfig CAN_C_CAN + tristate "Bosch C_CAN devices" + depends on CAN_DEV && HAS_IOMEM + +if CAN_C_CAN + +config CAN_C_CAN_PLATFORM + tristate "Generic Platform Bus based C_CAN driver" + ---help--- + This driver adds support for the C_CAN chips connected to + the "platform bus" (Linux abstraction for directly to the + processor attached devices) which can be found on various + boards from ST Microelectronics (http://www.st.com) + like the SPEAr1310 and SPEAr320 evaluation boards. +endif diff --git a/drivers/net/can/c_can/Makefile b/drivers/net/can/c_can/Makefile new file mode 100644 index 0000000..9273f6d --- /dev/null +++ b/drivers/net/can/c_can/Makefile @@ -0,0 +1,8 @@ +# +# Makefile for the Bosch C_CAN controller drivers. +# + +obj-$(CONFIG_CAN_C_CAN) += c_can.o +obj-$(CONFIG_CAN_C_CAN_PLATFORM) += c_can_platform.o + +ccflags-$(CONFIG_CAN_DEBUG_DEVICES) := -DDEBUG diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c new file mode 100644 index 0000000..1405078 --- /dev/null +++ b/drivers/net/can/c_can/c_can.c @@ -0,0 +1,1158 @@ +/* + * CAN bus driver for Bosch C_CAN controller + * + * Copyright (C) 2010 ST Microelectronics + * Bhupesh Sharma <bhupesh.sharma@st.com> + * + * Borrowed heavily from the C_CAN driver originally written by: + * Copyright (C) 2007 + * - Sascha Hauer, Marc Kleine-Budde, Pengutronix <s.hauer@pengutronix.de> + * - Simon Kallweit, intefo AG <simon.kallweit@intefo.ch> + * + * TX and RX NAPI implementation has been borrowed from at91 CAN driver + * written by: + * Copyright + * (C) 2007 by Hans J. Koch <hjk@hansjkoch.de> + * (C) 2008, 2009 by Marc Kleine-Budde <kernel@pengutronix.de> + * + * Bosch C_CAN controller is compliant to CAN protocol version 2.0 part A and B. + * Bosch C_CAN user manual can be obtained from: + * http://www.semiconductors.bosch.de/media/en/pdf/ipmodules_1/c_can/ + * users_manual_c_can.pdf + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include <linux/kernel.h> +#include <linux/version.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/if_ether.h> +#include <linux/list.h> +#include <linux/delay.h> +#include <linux/io.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> + +#include "c_can.h" + +/* control register */ +#define CONTROL_TEST BIT(7) +#define CONTROL_CCE BIT(6) +#define CONTROL_DISABLE_AR BIT(5) +#define CONTROL_ENABLE_AR (0 << 5) +#define CONTROL_EIE BIT(3) +#define CONTROL_SIE BIT(2) +#define CONTROL_IE BIT(1) +#define CONTROL_INIT BIT(0) + +/* test register */ +#define TEST_RX BIT(7) +#define TEST_TX1 BIT(6) +#define TEST_TX2 BIT(5) +#define TEST_LBACK BIT(4) +#define TEST_SILENT BIT(3) +#define TEST_BASIC BIT(2) + +/* status register */ +#define STATUS_BOFF BIT(7) +#define STATUS_EWARN BIT(6) +#define STATUS_EPASS BIT(5) +#define STATUS_RXOK BIT(4) +#define STATUS_TXOK BIT(3) + +/* error counter register */ +#define ERR_CNT_TEC_MASK 0xff +#define ERR_CNT_TEC_SHIFT 0 +#define ERR_CNT_REC_SHIFT 8 +#define ERR_CNT_REC_MASK (0x7f << ERR_CNT_REC_SHIFT) +#define ERR_CNT_RP_SHIFT 15 +#define ERR_CNT_RP_MASK (0x1 << ERR_CNT_RP_SHIFT) + +/* bit-timing register */ +#define BTR_BRP_MASK 0x3f +#define BTR_BRP_SHIFT 0 +#define BTR_SJW_SHIFT 6 +#define BTR_SJW_MASK (0x3 << BTR_SJW_SHIFT) +#define BTR_TSEG1_SHIFT 8 +#define BTR_TSEG1_MASK (0xf << BTR_TSEG1_SHIFT) +#define BTR_TSEG2_SHIFT 12 +#define BTR_TSEG2_MASK (0x7 << BTR_TSEG2_SHIFT) + +/* brp extension register */ +#define BRP_EXT_BRPE_MASK 0x0f +#define BRP_EXT_BRPE_SHIFT 0 + +/* IFx command request */ +#define IF_COMR_BUSY BIT(15) + +/* IFx command mask */ +#define IF_COMM_WR BIT(7) +#define IF_COMM_MASK BIT(6) +#define IF_COMM_ARB BIT(5) +#define IF_COMM_CONTROL BIT(4) +#define IF_COMM_CLR_INT_PND BIT(3) +#define IF_COMM_TXRQST BIT(2) +#define IF_COMM_DATAA BIT(1) +#define IF_COMM_DATAB BIT(0) +#define IF_COMM_ALL (IF_COMM_MASK | IF_COMM_ARB | \ + IF_COMM_CONTROL | IF_COMM_TXRQST | \ + IF_COMM_DATAA | IF_COMM_DATAB) + +/* IFx arbitration */ +#define IF_ARB_MSGVAL BIT(15) +#define IF_ARB_MSGXTD BIT(14) +#define IF_ARB_TRANSMIT BIT(13) + +/* IFx message control */ +#define IF_MCONT_NEWDAT BIT(15) +#define IF_MCONT_MSGLST BIT(14) +#define IF_MCONT_CLR_MSGLST (0 << 14) +#define IF_MCONT_INTPND BIT(13) +#define IF_MCONT_UMASK BIT(12) +#define IF_MCONT_TXIE BIT(11) +#define IF_MCONT_RXIE BIT(10) +#define IF_MCONT_RMTEN BIT(9) +#define IF_MCONT_TXRQST BIT(8) +#define IF_MCONT_EOB BIT(7) +#define IF_MCONT_DLC_MASK 0xf + +/* + * IFx register masks: + * allow easy operation on 16-bit registers when the + * argument is 32-bit instead + */ +#define IFX_WRITE_LOW_16BIT(x) ((x) & 0xFFFF) +#define IFX_WRITE_HIGH_16BIT(x) (((x) & 0xFFFF0000) >> 16) + +/* message object split */ +#define C_CAN_NO_OF_OBJECTS 32 +#define C_CAN_MSG_OBJ_RX_NUM 16 +#define C_CAN_MSG_OBJ_TX_NUM 16 + +#define C_CAN_MSG_OBJ_RX_FIRST 1 +#define C_CAN_MSG_OBJ_RX_LAST (C_CAN_MSG_OBJ_RX_FIRST + \ + C_CAN_MSG_OBJ_RX_NUM - 1) + +#define C_CAN_MSG_OBJ_TX_FIRST (C_CAN_MSG_OBJ_RX_LAST + 1) +#define C_CAN_MSG_OBJ_TX_LAST (C_CAN_MSG_OBJ_TX_FIRST + \ + C_CAN_MSG_OBJ_TX_NUM - 1) + +#define C_CAN_MSG_OBJ_RX_SPLIT 9 +#define C_CAN_MSG_RX_LOW_LAST (C_CAN_MSG_OBJ_RX_SPLIT - 1) + +#define C_CAN_NEXT_MSG_OBJ_MASK (C_CAN_MSG_OBJ_TX_NUM - 1) +#define RECEIVE_OBJECT_BITS 0x0000ffff + +/* status interrupt */ +#define STATUS_INTERRUPT 0x8000 + +/* global interrupt masks */ +#define ENABLE_ALL_INTERRUPTS 1 +#define DISABLE_ALL_INTERRUPTS 0 + +/* minimum timeout for checking BUSY status */ +#define MIN_TIMEOUT_VALUE 6 + +/* napi related */ +#define C_CAN_NAPI_WEIGHT C_CAN_MSG_OBJ_RX_NUM + +/* c_can lec values */ +enum c_can_lec_type { + LEC_NO_ERROR = 0, + LEC_STUFF_ERROR, + LEC_FORM_ERROR, + LEC_ACK_ERROR, + LEC_BIT1_ERROR, + LEC_BIT0_ERROR, + LEC_CRC_ERROR, + LEC_UNUSED, +}; + +/* + * c_can error types: + * Bus errors (BUS_OFF, ERROR_WARNING, ERROR_PASSIVE) are supported + */ +enum c_can_bus_error_types { + C_CAN_NO_ERROR = 0, + C_CAN_BUS_OFF, + C_CAN_ERROR_WARNING, + C_CAN_ERROR_PASSIVE, +}; + +static struct can_bittiming_const c_can_bittiming_const = { + .name = KBUILD_MODNAME, + .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_max = 16, + .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 1024, /* 6-bit BRP field + 4-bit BRPE field*/ + .brp_inc = 1, +}; + +static inline int get_tx_next_msg_obj(const struct c_can_priv *priv) +{ + return (priv->tx_next & C_CAN_NEXT_MSG_OBJ_MASK) + + C_CAN_MSG_OBJ_TX_FIRST; +} + +static inline int get_tx_echo_msg_obj(const struct c_can_priv *priv) +{ + return (priv->tx_echo & C_CAN_NEXT_MSG_OBJ_MASK) + + C_CAN_MSG_OBJ_TX_FIRST; +} + +static u32 c_can_read_reg32(struct c_can_priv *priv, void *reg) +{ + u32 val = priv->read_reg(priv, reg); + val |= ((u32) priv->read_reg(priv, reg + 2)) << 16; + return val; +} + +static void c_can_enable_all_interrupts(struct c_can_priv *priv, + int enable) +{ + unsigned int cntrl_save = priv->read_reg(priv, + &priv->regs->control); + + if (enable) + cntrl_save |= (CONTROL_SIE | CONTROL_EIE | CONTROL_IE); + else + cntrl_save &= ~(CONTROL_EIE | CONTROL_IE | CONTROL_SIE); + + priv->write_reg(priv, &priv->regs->control, cntrl_save); +} + +static inline int c_can_msg_obj_is_busy(struct c_can_priv *priv, int iface) +{ + int count = MIN_TIMEOUT_VALUE; + + while (count && priv->read_reg(priv, + &priv->regs->ifregs[iface].com_req) & + IF_COMR_BUSY) { + count--; + udelay(1); + } + + if (!count) + return 1; + + return 0; +} + +static inline void c_can_object_get(struct net_device *dev, + int iface, int objno, int mask) +{ + struct c_can_priv *priv = netdev_priv(dev); + + /* + * As per specs, after writting the message object number in the + * IF command request register the transfer b/w interface + * register and message RAM must be complete in 6 CAN-CLK + * period. + */ + priv->write_reg(priv, &priv->regs->ifregs[iface].com_mask, + IFX_WRITE_LOW_16BIT(mask)); + priv->write_reg(priv, &priv->regs->ifregs[iface].com_req, + IFX_WRITE_LOW_16BIT(objno)); + + if (c_can_msg_obj_is_busy(priv, iface)) + netdev_err(dev, "timed out in object get\n"); +} + +static inline void c_can_object_put(struct net_device *dev, + int iface, int objno, int mask) +{ + struct c_can_priv *priv = netdev_priv(dev); + + /* + * As per specs, after writting the message object number in the + * IF command request register the transfer b/w interface + * register and message RAM must be complete in 6 CAN-CLK + * period. + */ + priv->write_reg(priv, &priv->regs->ifregs[iface].com_mask, + (IF_COMM_WR | IFX_WRITE_LOW_16BIT(mask))); + priv->write_reg(priv, &priv->regs->ifregs[iface].com_req, + IFX_WRITE_LOW_16BIT(objno)); + + if (c_can_msg_obj_is_busy(priv, iface)) + netdev_err(dev, "timed out in object put\n"); +} + +static void c_can_write_msg_object(struct net_device *dev, + int iface, struct can_frame *frame, int objno) +{ + int i; + u16 flags = 0; + unsigned int id; + struct c_can_priv *priv = netdev_priv(dev); + + if (!(frame->can_id & CAN_RTR_FLAG)) + flags |= IF_ARB_TRANSMIT; + + if (frame->can_id & CAN_EFF_FLAG) { + id = frame->can_id & CAN_EFF_MASK; + flags |= IF_ARB_MSGXTD; + } else + id = ((frame->can_id & CAN_SFF_MASK) << 18); + + flags |= IF_ARB_MSGVAL; + + priv->write_reg(priv, &priv->regs->ifregs[iface].arb1, + IFX_WRITE_LOW_16BIT(id)); + priv->write_reg(priv, &priv->regs->ifregs[iface].arb2, flags | + IFX_WRITE_HIGH_16BIT(id)); + + for (i = 0; i < frame->can_dlc; i += 2) { + priv->write_reg(priv, &priv->regs->ifregs[iface].data[i / 2], + frame->data[i] | (frame->data[i + 1] << 8)); + } + + /* enable interrupt for this message object */ + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, + IF_MCONT_TXIE | IF_MCONT_TXRQST | IF_MCONT_EOB | + frame->can_dlc); + c_can_object_put(dev, iface, objno, IF_COMM_ALL); +} + +static inline void c_can_mark_rx_msg_obj(struct net_device *dev, + int iface, int ctrl_mask, + int obj) +{ + struct c_can_priv *priv = netdev_priv(dev); + + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, + ctrl_mask & ~(IF_MCONT_MSGLST | IF_MCONT_INTPND)); + c_can_object_put(dev, iface, obj, IF_COMM_CONTROL); + +} + +static inline void c_can_activate_all_lower_rx_msg_obj(struct net_device *dev, + int iface, + int ctrl_mask) +{ + int i; + struct c_can_priv *priv = netdev_priv(dev); + + for (i = C_CAN_MSG_OBJ_RX_FIRST; i <= C_CAN_MSG_RX_LOW_LAST; i++) { + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, + ctrl_mask & ~(IF_MCONT_MSGLST | + IF_MCONT_INTPND | IF_MCONT_NEWDAT)); + c_can_object_put(dev, iface, i, IF_COMM_CONTROL); + } +} + +static inline void c_can_activate_rx_msg_obj(struct net_device *dev, + int iface, int ctrl_mask, + int obj) +{ + struct c_can_priv *priv = netdev_priv(dev); + + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, + ctrl_mask & ~(IF_MCONT_MSGLST | + IF_MCONT_INTPND | IF_MCONT_NEWDAT)); + c_can_object_put(dev, iface, obj, IF_COMM_CONTROL); +} + +static void c_can_handle_lost_msg_obj(struct net_device *dev, + int iface, int objno) +{ + struct c_can_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct sk_buff *skb; + struct can_frame *frame; + + netdev_err(dev, "msg lost in buffer %d\n", objno); + + c_can_object_get(dev, iface, objno, IF_COMM_ALL & ~IF_COMM_TXRQST); + + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, + IF_MCONT_CLR_MSGLST); + + c_can_object_put(dev, 0, objno, IF_COMM_CONTROL); + + /* create an error msg */ + skb = alloc_can_err_skb(dev, &frame); + if (unlikely(!skb)) + return; + + frame->can_id |= CAN_ERR_CRTL; + frame->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; + stats->rx_errors++; + stats->rx_over_errors++; + + netif_receive_skb(skb); +} + +static int c_can_read_msg_object(struct net_device *dev, int iface, int ctrl) +{ + u16 flags, data; + int i; + unsigned int val; + struct c_can_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct sk_buff *skb; + struct can_frame *frame; + + skb = alloc_can_skb(dev, &frame); + if (!skb) { + stats->rx_dropped++; + return -ENOMEM; + } + + frame->can_dlc = get_can_dlc(ctrl & 0x0F); + + flags = priv->read_reg(priv, &priv->regs->ifregs[iface].arb2); + val = priv->read_reg(priv, &priv->regs->ifregs[iface].arb1) | + (flags << 16); + + if (flags & IF_ARB_MSGXTD) + frame->can_id = (val & CAN_EFF_MASK) | CAN_EFF_FLAG; + else + frame->can_id = (val >> 18) & CAN_SFF_MASK; + + if (flags & IF_ARB_TRANSMIT) + frame->can_id |= CAN_RTR_FLAG; + else { + for (i = 0; i < frame->can_dlc; i += 2) { + data = priv->read_reg(priv, + &priv->regs->ifregs[iface].data[i / 2]); + frame->data[i] = data; + frame->data[i + 1] = data >> 8; + } + } + + netif_receive_skb(skb); + + stats->rx_packets++; + stats->rx_bytes += frame->can_dlc; + + return 0; +} + +static void c_can_setup_receive_object(struct net_device *dev, int iface, + int objno, unsigned int mask, + unsigned int id, unsigned int mcont) +{ + struct c_can_priv *priv = netdev_priv(dev); + + priv->write_reg(priv, &priv->regs->ifregs[iface].mask1, + IFX_WRITE_LOW_16BIT(mask)); + priv->write_reg(priv, &priv->regs->ifregs[iface].mask2, + IFX_WRITE_HIGH_16BIT(mask)); + + priv->write_reg(priv, &priv->regs->ifregs[iface].arb1, + IFX_WRITE_LOW_16BIT(id)); + priv->write_reg(priv, &priv->regs->ifregs[iface].arb2, + (IF_ARB_MSGVAL | IFX_WRITE_HIGH_16BIT(id))); + + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, mcont); + c_can_object_put(dev, iface, objno, IF_COMM_ALL & ~IF_COMM_TXRQST); + + netdev_dbg(dev, "obj no:%d, msgval:0x%08x\n", objno, + c_can_read_reg32(priv, &priv->regs->msgval1)); +} + +static void c_can_inval_msg_object(struct net_device *dev, int iface, int objno) +{ + struct c_can_priv *priv = netdev_priv(dev); + + priv->write_reg(priv, &priv->regs->ifregs[iface].arb1, 0); + priv->write_reg(priv, &priv->regs->ifregs[iface].arb2, 0); + priv->write_reg(priv, &priv->regs->ifregs[iface].msg_cntrl, 0); + + c_can_object_put(dev, iface, objno, IF_COMM_ARB | IF_COMM_CONTROL); + + netdev_dbg(dev, "obj no:%d, msgval:0x%08x\n", objno, + c_can_read_reg32(priv, &priv->regs->msgval1)); +} + +static inline int c_can_is_next_tx_obj_busy(struct c_can_priv *priv, int objno) +{ + int val = c_can_read_reg32(priv, &priv->regs->txrqst1); + + /* + * as transmission request register's bit n-1 corresponds to + * message object n, we need to handle the same properly. + */ + if (val & (1 << (objno - 1))) + return 1; + + return 0; +} + +static netdev_tx_t c_can_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + u32 msg_obj_no; + struct c_can_priv *priv = netdev_priv(dev); + struct can_frame *frame = (struct can_frame *)skb->data; + + if (can_dropped_invalid_skb(dev, skb)) + return NETDEV_TX_OK; + + msg_obj_no = get_tx_next_msg_obj(priv); + + /* prepare message object for transmission */ + c_can_write_msg_object(dev, 0, frame, msg_obj_no); + can_put_echo_skb(skb, dev, msg_obj_no - C_CAN_MSG_OBJ_TX_FIRST); + + /* + * we have to stop the queue in case of a wrap around or + * if the next TX message object is still in use + */ + priv->tx_next++; + if (c_can_is_next_tx_obj_busy(priv, get_tx_next_msg_obj(priv)) || + (priv->tx_next & C_CAN_NEXT_MSG_OBJ_MASK) == 0) + netif_stop_queue(dev); + + return NETDEV_TX_OK; +} + +static int c_can_set_bittiming(struct net_device *dev) +{ + unsigned int reg_btr, reg_brpe, ctrl_save; + u8 brp, brpe, sjw, tseg1, tseg2; + u32 ten_bit_brp; + struct c_can_priv *priv = netdev_priv(dev); + const struct can_bittiming *bt = &priv->can.bittiming; + + /* c_can provides a 6-bit brp and 4-bit brpe fields */ + ten_bit_brp = bt->brp - 1; + brp = ten_bit_brp & BTR_BRP_MASK; + brpe = ten_bit_brp >> 6; + + sjw = bt->sjw - 1; + tseg1 = bt->prop_seg + bt->phase_seg1 - 1; + tseg2 = bt->phase_seg2 - 1; + reg_btr = brp | (sjw << BTR_SJW_SHIFT) | (tseg1 << BTR_TSEG1_SHIFT) | + (tseg2 << BTR_TSEG2_SHIFT); + reg_brpe = brpe & BRP_EXT_BRPE_MASK; + + netdev_info(dev, + "setting BTR=%04x BRPE=%04x\n", reg_btr, reg_brpe); + + ctrl_save = priv->read_reg(priv, &priv->regs->control); + priv->write_reg(priv, &priv->regs->control, + ctrl_save | CONTROL_CCE | CONTROL_INIT); + priv->write_reg(priv, &priv->regs->btr, reg_btr); + priv->write_reg(priv, &priv->regs->brp_ext, reg_brpe); + priv->write_reg(priv, &priv->regs->control, ctrl_save); + + return 0; +} + +/* + * Configure C_CAN message objects for Tx and Rx purposes: + * C_CAN provides a total of 32 message objects that can be configured + * either for Tx or Rx purposes. Here the first 16 message objects are used as + * a reception FIFO. The end of reception FIFO is signified by the EoB bit + * being SET. The remaining 16 message objects are kept aside for Tx purposes. + * See user guide document for further details on configuring message + * objects. + */ +static void c_can_configure_msg_objects(struct net_device *dev) +{ + int i; + + /* first invalidate all message objects */ + for (i = C_CAN_MSG_OBJ_RX_FIRST; i <= C_CAN_NO_OF_OBJECTS; i++) + c_can_inval_msg_object(dev, 0, i); + + /* setup receive message objects */ + for (i = C_CAN_MSG_OBJ_RX_FIRST; i < C_CAN_MSG_OBJ_RX_LAST; i++) + c_can_setup_receive_object(dev, 0, i, 0, 0, + (IF_MCONT_RXIE | IF_MCONT_UMASK) & ~IF_MCONT_EOB); + + c_can_setup_receive_object(dev, 0, C_CAN_MSG_OBJ_RX_LAST, 0, 0, + IF_MCONT_EOB | IF_MCONT_RXIE | IF_MCONT_UMASK); +} + +/* + * Configure C_CAN chip: + * - enable/disable auto-retransmission + * - set operating mode + * - configure message objects + */ +static void c_can_chip_config(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + + if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + /* disable automatic retransmission */ + priv->write_reg(priv, &priv->regs->control, + CONTROL_DISABLE_AR); + else + /* enable automatic retransmission */ + priv->write_reg(priv, &priv->regs->control, + CONTROL_ENABLE_AR); + + if (priv->can.ctrlmode & (CAN_CTRLMODE_LISTENONLY & + CAN_CTRLMODE_LOOPBACK)) { + /* loopback + silent mode : useful for hot self-test */ + priv->write_reg(priv, &priv->regs->control, CONTROL_EIE | + CONTROL_SIE | CONTROL_IE | CONTROL_TEST); + priv->write_reg(priv, &priv->regs->test, + TEST_LBACK | TEST_SILENT); + } else if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) { + /* loopback mode : useful for self-test function */ + priv->write_reg(priv, &priv->regs->control, CONTROL_EIE | + CONTROL_SIE | CONTROL_IE | CONTROL_TEST); + priv->write_reg(priv, &priv->regs->test, TEST_LBACK); + } else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) { + /* silent mode : bus-monitoring mode */ + priv->write_reg(priv, &priv->regs->control, CONTROL_EIE | + CONTROL_SIE | CONTROL_IE | CONTROL_TEST); + priv->write_reg(priv, &priv->regs->test, TEST_SILENT); + } else + /* normal mode*/ + priv->write_reg(priv, &priv->regs->control, + CONTROL_EIE | CONTROL_SIE | CONTROL_IE); + + /* configure message objects */ + c_can_configure_msg_objects(dev); + + /* set a `lec` value so that we can check for updates later */ + priv->write_reg(priv, &priv->regs->status, LEC_UNUSED); + + /* set bittiming params */ + c_can_set_bittiming(dev); +} + +static void c_can_start(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + + /* enable status change, error and module interrupts */ + c_can_enable_all_interrupts(priv, ENABLE_ALL_INTERRUPTS); + + /* basic c_can configuration */ + c_can_chip_config(dev); + + priv->can.state = CAN_STATE_ERROR_ACTIVE; + + /* reset tx helper pointers */ + priv->tx_next = priv->tx_echo = 0; +} + +static void c_can_stop(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + + /* disable all interrupts */ + c_can_enable_all_interrupts(priv, DISABLE_ALL_INTERRUPTS); + + /* set the state as STOPPED */ + priv->can.state = CAN_STATE_STOPPED; +} + +static int c_can_set_mode(struct net_device *dev, enum can_mode mode) +{ + switch (mode) { + case CAN_MODE_START: + c_can_start(dev); + netif_wake_queue(dev); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int c_can_get_berr_counter(const struct net_device *dev, + struct can_berr_counter *bec) +{ + unsigned int reg_err_counter; + struct c_can_priv *priv = netdev_priv(dev); + + reg_err_counter = priv->read_reg(priv, &priv->regs->err_cnt); + bec->rxerr = (reg_err_counter & ERR_CNT_REC_MASK) >> + ERR_CNT_REC_SHIFT; + bec->txerr = reg_err_counter & ERR_CNT_TEC_MASK; + + return 0; +} + +/* + * theory of operation: + * + * priv->tx_echo holds the number of the oldest can_frame put for + * transmission into the hardware, but not yet ACKed by the CAN tx + * complete IRQ. + * + * We iterate from priv->tx_echo to priv->tx_next and check if the + * packet has been transmitted, echo it back to the CAN framework. + * If we discover a not yet transmitted package, stop looking for more. + */ +static void c_can_do_tx(struct net_device *dev) +{ + u32 val; + u32 msg_obj_no; + struct c_can_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + + for (/* nix */; (priv->tx_next - priv->tx_echo) > 0; priv->tx_echo++) { + msg_obj_no = get_tx_echo_msg_obj(priv); + c_can_inval_msg_object(dev, 0, msg_obj_no); + val = c_can_read_reg32(priv, &priv->regs->txrqst1); + if (!(val & (1 << msg_obj_no))) { + can_get_echo_skb(dev, + msg_obj_no - C_CAN_MSG_OBJ_TX_FIRST); + stats->tx_bytes += priv->read_reg(priv, + &priv->regs->ifregs[0].msg_cntrl) + & IF_MCONT_DLC_MASK; + stats->tx_packets++; + } + } + + /* restart queue if wrap-up or if queue stalled on last pkt */ + if (((priv->tx_next & C_CAN_NEXT_MSG_OBJ_MASK) != 0) || + ((priv->tx_echo & C_CAN_NEXT_MSG_OBJ_MASK) == 0)) + netif_wake_queue(dev); +} + +/* + * theory of operation: + * + * c_can core saves a received CAN message into the first free message + * object it finds free (starting with the lowest). Bits NEWDAT and + * INTPND are set for this message object indicating that a new message + * has arrived. To work-around this issue, we keep two groups of message + * objects whose partitioning is defined by C_CAN_MSG_OBJ_RX_SPLIT. + * + * To ensure in-order frame reception we use the following + * approach while re-activating a message object to receive further + * frames: + * - if the current message object number is lower than + * C_CAN_MSG_RX_LOW_LAST, do not clear the NEWDAT bit while clearing + * the INTPND bit. + * - if the current message object number is equal to + * C_CAN_MSG_RX_LOW_LAST then clear the NEWDAT bit of all lower + * receive message objects. + * - if the current message object number is greater than + * C_CAN_MSG_RX_LOW_LAST then clear the NEWDAT bit of + * only this message object. + */ +static int c_can_do_rx_poll(struct net_device *dev, int quota) +{ + u32 num_rx_pkts = 0; + unsigned int msg_obj, msg_ctrl_save; + struct c_can_priv *priv = netdev_priv(dev); + u32 val = c_can_read_reg32(priv, &priv->regs->intpnd1); + + for (msg_obj = C_CAN_MSG_OBJ_RX_FIRST; + msg_obj <= C_CAN_MSG_OBJ_RX_LAST && quota > 0; + val = c_can_read_reg32(priv, &priv->regs->intpnd1), + msg_obj++) { + /* + * as interrupt pending register's bit n-1 corresponds to + * message object n, we need to handle the same properly. + */ + if (val & (1 << (msg_obj - 1))) { + c_can_object_get(dev, 0, msg_obj, IF_COMM_ALL & + ~IF_COMM_TXRQST); + msg_ctrl_save = priv->read_reg(priv, + &priv->regs->ifregs[0].msg_cntrl); + + if (msg_ctrl_save & IF_MCONT_EOB) + return num_rx_pkts; + + if (msg_ctrl_save & IF_MCONT_MSGLST) { + c_can_handle_lost_msg_obj(dev, 0, msg_obj); + num_rx_pkts++; + quota--; + continue; + } + + if (!(msg_ctrl_save & IF_MCONT_NEWDAT)) + continue; + + /* read the data from the message object */ + c_can_read_msg_object(dev, 0, msg_ctrl_save); + + if (msg_obj < C_CAN_MSG_RX_LOW_LAST) + c_can_mark_rx_msg_obj(dev, 0, + msg_ctrl_save, msg_obj); + else if (msg_obj > C_CAN_MSG_RX_LOW_LAST) + /* activate this msg obj */ + c_can_activate_rx_msg_obj(dev, 0, + msg_ctrl_save, msg_obj); + else if (msg_obj == C_CAN_MSG_RX_LOW_LAST) + /* activate all lower message objects */ + c_can_activate_all_lower_rx_msg_obj(dev, + 0, msg_ctrl_save); + + num_rx_pkts++; + quota--; + } + } + + return num_rx_pkts; +} + +static inline int c_can_has_and_handle_berr(struct c_can_priv *priv) +{ + return (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) && + (priv->current_status & LEC_UNUSED); +} + +static int c_can_handle_state_change(struct net_device *dev, + enum c_can_bus_error_types error_type) +{ + unsigned int reg_err_counter; + unsigned int rx_err_passive; + struct c_can_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct can_frame *cf; + struct sk_buff *skb; + struct can_berr_counter bec; + + /* propogate the error condition to the CAN stack */ + skb = alloc_can_err_skb(dev, &cf); + if (unlikely(!skb)) + return 0; + + c_can_get_berr_counter(dev, &bec); + reg_err_counter = priv->read_reg(priv, &priv->regs->err_cnt); + rx_err_passive = (reg_err_counter & ERR_CNT_RP_MASK) >> + ERR_CNT_RP_SHIFT; + + switch (error_type) { + case C_CAN_ERROR_WARNING: + /* error warning state */ + priv->can.can_stats.error_warning++; + priv->can.state = CAN_STATE_ERROR_WARNING; + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = (bec.txerr > bec.rxerr) ? + CAN_ERR_CRTL_TX_WARNING : + CAN_ERR_CRTL_RX_WARNING; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + + break; + case C_CAN_ERROR_PASSIVE: + /* error passive state */ + priv->can.can_stats.error_passive++; + priv->can.state = CAN_STATE_ERROR_PASSIVE; + cf->can_id |= CAN_ERR_CRTL; + if (rx_err_passive) + cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; + if (bec.txerr > 127) + cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE; + + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + break; + case C_CAN_BUS_OFF: + /* bus-off state */ + priv->can.state = CAN_STATE_BUS_OFF; + cf->can_id |= CAN_ERR_BUSOFF; + /* + * disable all interrupts in bus-off mode to ensure that + * the CPU is not hogged down + */ + c_can_enable_all_interrupts(priv, DISABLE_ALL_INTERRUPTS); + can_bus_off(dev); + break; + default: + break; + } + + netif_receive_skb(skb); + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + + return 1; +} + +static int c_can_handle_bus_err(struct net_device *dev, + enum c_can_lec_type lec_type) +{ + struct c_can_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct can_frame *cf; + struct sk_buff *skb; + + /* + * early exit if no lec update or no error. + * no lec update means that no CAN bus event has been detected + * since CPU wrote 0x7 value to status reg. + */ + if (lec_type == LEC_UNUSED || lec_type == LEC_NO_ERROR) + return 0; + + /* propogate the error condition to the CAN stack */ + skb = alloc_can_err_skb(dev, &cf); + if (unlikely(!skb)) + return 0; + + /* + * check for 'last error code' which tells us the + * type of the last error to occur on the CAN bus + */ + + /* common for all type of bus errors */ + priv->can.can_stats.bus_error++; + stats->rx_errors++; + cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR; + cf->data[2] |= CAN_ERR_PROT_UNSPEC; + + switch (lec_type) { + case LEC_STUFF_ERROR: + netdev_dbg(dev, "stuff error\n"); + cf->data[2] |= CAN_ERR_PROT_STUFF; + break; + case LEC_FORM_ERROR: + netdev_dbg(dev, "form error\n"); + cf->data[2] |= CAN_ERR_PROT_FORM; + break; + case LEC_ACK_ERROR: + netdev_dbg(dev, "ack error\n"); + cf->data[2] |= (CAN_ERR_PROT_LOC_ACK | + CAN_ERR_PROT_LOC_ACK_DEL); + break; + case LEC_BIT1_ERROR: + netdev_dbg(dev, "bit1 error\n"); + cf->data[2] |= CAN_ERR_PROT_BIT1; + break; + case LEC_BIT0_ERROR: + netdev_dbg(dev, "bit0 error\n"); + cf->data[2] |= CAN_ERR_PROT_BIT0; + break; + case LEC_CRC_ERROR: + netdev_dbg(dev, "CRC error\n"); + cf->data[2] |= (CAN_ERR_PROT_LOC_CRC_SEQ | + CAN_ERR_PROT_LOC_CRC_DEL); + break; + default: + break; + } + + /* set a `lec` value so that we can check for updates later */ + priv->write_reg(priv, &priv->regs->status, LEC_UNUSED); + + netif_receive_skb(skb); + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + + return 1; +} + +static int c_can_poll(struct napi_struct *napi, int quota) +{ + u16 irqstatus; + int lec_type = 0; + int work_done = 0; + struct net_device *dev = napi->dev; + struct c_can_priv *priv = netdev_priv(dev); + + irqstatus = priv->read_reg(priv, &priv->regs->interrupt); + if (!irqstatus) + goto end; + + /* status events have the highest priority */ + if (irqstatus == STATUS_INTERRUPT) { + priv->current_status = priv->read_reg(priv, + &priv->regs->status); + + /* handle Tx/Rx events */ + if (priv->current_status & STATUS_TXOK) + priv->write_reg(priv, &priv->regs->status, + priv->current_status & ~STATUS_TXOK); + + if (priv->current_status & STATUS_RXOK) + priv->write_reg(priv, &priv->regs->status, + priv->current_status & ~STATUS_RXOK); + + /* handle state changes */ + if ((priv->current_status & STATUS_EWARN) && + (!(priv->last_status & STATUS_EWARN))) { + netdev_dbg(dev, "entered error warning state\n"); + work_done += c_can_handle_state_change(dev, + C_CAN_ERROR_WARNING); + } + if ((priv->current_status & STATUS_EPASS) && + (!(priv->last_status & STATUS_EPASS))) { + netdev_dbg(dev, "entered error passive state\n"); + work_done += c_can_handle_state_change(dev, + C_CAN_ERROR_PASSIVE); + } + if ((priv->current_status & STATUS_BOFF) && + (!(priv->last_status & STATUS_BOFF))) { + netdev_dbg(dev, "entered bus off state\n"); + work_done += c_can_handle_state_change(dev, + C_CAN_BUS_OFF); + } + + /* handle bus recovery events */ + if ((!(priv->current_status & STATUS_BOFF)) && + (priv->last_status & STATUS_BOFF)) { + netdev_dbg(dev, "left bus off state\n"); + priv->can.state = CAN_STATE_ERROR_ACTIVE; + } + if ((!(priv->current_status & STATUS_EPASS)) && + (priv->last_status & STATUS_EPASS)) { + netdev_dbg(dev, "left error passive state\n"); + priv->can.state = CAN_STATE_ERROR_ACTIVE; + } + + priv->last_status = priv->current_status; + + /* handle lec errors on the bus */ + lec_type = c_can_has_and_handle_berr(priv); + if (lec_type) + work_done += c_can_handle_bus_err(dev, lec_type); + } else if ((irqstatus >= C_CAN_MSG_OBJ_RX_FIRST) && + (irqstatus <= C_CAN_MSG_OBJ_RX_LAST)) { + /* handle events corresponding to receive message objects */ + work_done += c_can_do_rx_poll(dev, (quota - work_done)); + } else if ((irqstatus >= C_CAN_MSG_OBJ_TX_FIRST) && + (irqstatus <= C_CAN_MSG_OBJ_TX_LAST)) { + /* handle events corresponding to transmit message objects */ + c_can_do_tx(dev); + } + +end: + if (work_done < quota) { + napi_complete(napi); + /* enable all IRQs */ + c_can_enable_all_interrupts(priv, ENABLE_ALL_INTERRUPTS); + } + + return work_done; +} + +static irqreturn_t c_can_isr(int irq, void *dev_id) +{ + u16 irqstatus; + struct net_device *dev = (struct net_device *)dev_id; + struct c_can_priv *priv = netdev_priv(dev); + + irqstatus = priv->read_reg(priv, &priv->regs->interrupt); + if (!irqstatus) + return IRQ_NONE; + + /* disable all interrupts and schedule the NAPI */ + c_can_enable_all_interrupts(priv, DISABLE_ALL_INTERRUPTS); + napi_schedule(&priv->napi); + + return IRQ_HANDLED; +} + +static int c_can_open(struct net_device *dev) +{ + int err; + struct c_can_priv *priv = netdev_priv(dev); + + /* open the can device */ + err = open_candev(dev); + if (err) { + netdev_err(dev, "failed to open can device\n"); + return err; + } + + /* register interrupt handler */ + err = request_irq(dev->irq, &c_can_isr, IRQF_SHARED, dev->name, + dev); + if (err < 0) { + netdev_err(dev, "failed to request interrupt\n"); + goto exit_irq_fail; + } + + /* start the c_can controller */ + c_can_start(dev); + + napi_enable(&priv->napi); + netif_start_queue(dev); + + return 0; + +exit_irq_fail: + close_candev(dev); + return err; +} + +static int c_can_close(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + + netif_stop_queue(dev); + napi_disable(&priv->napi); + c_can_stop(dev); + free_irq(dev->irq, dev); + close_candev(dev); + + return 0; +} + +struct net_device *alloc_c_can_dev(void) +{ + struct net_device *dev; + struct c_can_priv *priv; + + dev = alloc_candev(sizeof(struct c_can_priv), C_CAN_MSG_OBJ_TX_NUM); + if (!dev) + return NULL; + + priv = netdev_priv(dev); + netif_napi_add(dev, &priv->napi, c_can_poll, C_CAN_NAPI_WEIGHT); + + priv->dev = dev; + priv->can.bittiming_const = &c_can_bittiming_const; + priv->can.do_set_mode = c_can_set_mode; + priv->can.do_get_berr_counter = c_can_get_berr_counter; + priv->can.ctrlmode_supported = CAN_CTRLMODE_ONE_SHOT | + CAN_CTRLMODE_LOOPBACK | + CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_BERR_REPORTING; + + return dev; +} +EXPORT_SYMBOL_GPL(alloc_c_can_dev); + +void free_c_can_dev(struct net_device *dev) +{ + free_candev(dev); +} +EXPORT_SYMBOL_GPL(free_c_can_dev); + +static const struct net_device_ops c_can_netdev_ops = { + .ndo_open = c_can_open, + .ndo_stop = c_can_close, + .ndo_start_xmit = c_can_start_xmit, +}; + +int register_c_can_dev(struct net_device *dev) +{ + dev->flags |= IFF_ECHO; /* we support local echo */ + dev->netdev_ops = &c_can_netdev_ops; + + return register_candev(dev); +} +EXPORT_SYMBOL_GPL(register_c_can_dev); + +void unregister_c_can_dev(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + + /* disable all interrupts */ + c_can_enable_all_interrupts(priv, DISABLE_ALL_INTERRUPTS); + + unregister_candev(dev); +} +EXPORT_SYMBOL_GPL(unregister_c_can_dev); + +MODULE_AUTHOR("Bhupesh Sharma <bhupesh.sharma@st.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("CAN bus driver for Bosch C_CAN controller"); diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h new file mode 100644 index 0000000..9b7fbef --- /dev/null +++ b/drivers/net/can/c_can/c_can.h @@ -0,0 +1,86 @@ +/* + * CAN bus driver for Bosch C_CAN controller + * + * Copyright (C) 2010 ST Microelectronics + * Bhupesh Sharma <bhupesh.sharma@st.com> + * + * Borrowed heavily from the C_CAN driver originally written by: + * Copyright (C) 2007 + * - Sascha Hauer, Marc Kleine-Budde, Pengutronix <s.hauer@pengutronix.de> + * - Simon Kallweit, intefo AG <simon.kallweit@intefo.ch> + * + * Bosch C_CAN controller is compliant to CAN protocol version 2.0 part A and B. + * Bosch C_CAN user manual can be obtained from: + * http://www.semiconductors.bosch.de/media/en/pdf/ipmodules_1/c_can/ + * users_manual_c_can.pdf + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef C_CAN_H +#define C_CAN_H + +/* c_can IF registers */ +struct c_can_if_regs { + u16 com_req; + u16 com_mask; + u16 mask1; + u16 mask2; + u16 arb1; + u16 arb2; + u16 msg_cntrl; + u16 data[4]; + u16 _reserved[13]; +}; + +/* c_can hardware registers */ +struct c_can_regs { + u16 control; + u16 status; + u16 err_cnt; + u16 btr; + u16 interrupt; + u16 test; + u16 brp_ext; + u16 _reserved1; + struct c_can_if_regs ifregs[2]; /* [0] = IF1 and [1] = IF2 */ + u16 _reserved2[8]; + u16 txrqst1; + u16 txrqst2; + u16 _reserved3[6]; + u16 newdat1; + u16 newdat2; + u16 _reserved4[6]; + u16 intpnd1; + u16 intpnd2; + u16 _reserved5[6]; + u16 msgval1; + u16 msgval2; + u16 _reserved6[6]; +}; + +/* c_can private data structure */ +struct c_can_priv { + struct can_priv can; /* must be the first member */ + struct napi_struct napi; + struct net_device *dev; + int tx_object; + int current_status; + int last_status; + u16 (*read_reg) (struct c_can_priv *priv, void *reg); + void (*write_reg) (struct c_can_priv *priv, void *reg, u16 val); + struct c_can_regs __iomem *regs; + unsigned long irq_flags; /* for request_irq() */ + unsigned int tx_next; + unsigned int tx_echo; + void *priv; /* for board-specific data */ +}; + +struct net_device *alloc_c_can_dev(void); +void free_c_can_dev(struct net_device *dev); +int register_c_can_dev(struct net_device *dev); +void unregister_c_can_dev(struct net_device *dev); + +#endif /* C_CAN_H */ diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c new file mode 100644 index 0000000..e629b96 --- /dev/null +++ b/drivers/net/can/c_can/c_can_platform.c @@ -0,0 +1,215 @@ +/* + * Platform CAN bus driver for Bosch C_CAN controller + * + * Copyright (C) 2010 ST Microelectronics + * Bhupesh Sharma <bhupesh.sharma@st.com> + * + * Borrowed heavily from the C_CAN driver originally written by: + * Copyright (C) 2007 + * - Sascha Hauer, Marc Kleine-Budde, Pengutronix <s.hauer@pengutronix.de> + * - Simon Kallweit, intefo AG <simon.kallweit@intefo.ch> + * + * Bosch C_CAN controller is compliant to CAN protocol version 2.0 part A and B. + * Bosch C_CAN user manual can be obtained from: + * http://www.semiconductors.bosch.de/media/en/pdf/ipmodules_1/c_can/ + * users_manual_c_can.pdf + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include <linux/kernel.h> +#include <linux/version.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/if_ether.h> +#include <linux/list.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/clk.h> + +#include <linux/can/dev.h> + +#include "c_can.h" + +/* + * 16-bit c_can registers can be arranged differently in the memory + * architecture of different implementations. For example: 16-bit + * registers can be aligned to a 16-bit boundary or 32-bit boundary etc. + * Handle the same by providing a common read/write interface. + */ +static u16 c_can_plat_read_reg_aligned_to_16bit(struct c_can_priv *priv, + void *reg) +{ + return readw(reg); +} + +static void c_can_plat_write_reg_aligned_to_16bit(struct c_can_priv *priv, + void *reg, u16 val) +{ + writew(val, reg); +} + +static u16 c_can_plat_read_reg_aligned_to_32bit(struct c_can_priv *priv, + void *reg) +{ + return readw(reg + (long)reg - (long)priv->regs); +} + +static void c_can_plat_write_reg_aligned_to_32bit(struct c_can_priv *priv, + void *reg, u16 val) +{ + writew(val, reg + (long)reg - (long)priv->regs); +} + +static int __devinit c_can_plat_probe(struct platform_device *pdev) +{ + int ret; + void __iomem *addr; + struct net_device *dev; + struct c_can_priv *priv; + struct resource *mem, *irq; +#ifdef CONFIG_HAVE_CLK + struct clk *clk; + + /* get the appropriate clk */ + clk = clk_get(&pdev->dev, NULL); + if (IS_ERR(clk)) { + dev_err(&pdev->dev, "no clock defined\n"); + ret = -ENODEV; + goto exit; + } +#endif + + /* get the platform data */ + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!mem || (irq <= 0)) { + ret = -ENODEV; + goto exit_free_clk; + } + + if (!request_mem_region(mem->start, resource_size(mem), + KBUILD_MODNAME)) { + dev_err(&pdev->dev, "resource unavailable\n"); + ret = -ENODEV; + goto exit_free_clk; + } + + addr = ioremap(mem->start, resource_size(mem)); + if (!addr) { + dev_err(&pdev->dev, "failed to map can port\n"); + ret = -ENOMEM; + goto exit_release_mem; + } + + /* allocate the c_can device */ + dev = alloc_c_can_dev(); + if (!dev) { + ret = -ENOMEM; + goto exit_iounmap; + } + + priv = netdev_priv(dev); + + dev->irq = irq->start; + priv->regs = addr; +#ifdef CONFIG_HAVE_CLK + priv->can.clock.freq = clk_get_rate(clk); + priv->priv = clk; +#endif + + switch (mem->flags & IORESOURCE_MEM_TYPE_MASK) { + case IORESOURCE_MEM_32BIT: + priv->read_reg = c_can_plat_read_reg_aligned_to_32bit; + priv->write_reg = c_can_plat_write_reg_aligned_to_32bit; + break; + case IORESOURCE_MEM_16BIT: + default: + priv->read_reg = c_can_plat_read_reg_aligned_to_16bit; + priv->write_reg = c_can_plat_write_reg_aligned_to_16bit; + break; + } + + platform_set_drvdata(pdev, dev); + SET_NETDEV_DEV(dev, &pdev->dev); + + ret = register_c_can_dev(dev); + if (ret) { + dev_err(&pdev->dev, "registering %s failed (err=%d)\n", + KBUILD_MODNAME, ret); + goto exit_free_device; + } + + dev_info(&pdev->dev, "%s device registered (regs=%p, irq=%d)\n", + KBUILD_MODNAME, priv->regs, dev->irq); + return 0; + +exit_free_device: + platform_set_drvdata(pdev, NULL); + free_c_can_dev(dev); +exit_iounmap: + iounmap(addr); +exit_release_mem: + release_mem_region(mem->start, resource_size(mem)); +exit_free_clk: +#ifdef CONFIG_HAVE_CLK + clk_put(clk); +exit: +#endif + dev_err(&pdev->dev, "probe failed\n"); + + return ret; +} + +static int __devexit c_can_plat_remove(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + struct c_can_priv *priv = netdev_priv(dev); + struct resource *mem; + + unregister_c_can_dev(dev); + platform_set_drvdata(pdev, NULL); + + free_c_can_dev(dev); + iounmap(priv->regs); + + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + release_mem_region(mem->start, resource_size(mem)); + +#ifdef CONFIG_HAVE_CLK + clk_put(priv->priv); +#endif + + return 0; +} + +static struct platform_driver c_can_plat_driver = { + .driver = { + .name = KBUILD_MODNAME, + .owner = THIS_MODULE, + }, + .probe = c_can_plat_probe, + .remove = __devexit_p(c_can_plat_remove), +}; + +static int __init c_can_plat_init(void) +{ + return platform_driver_register(&c_can_plat_driver); +} +module_init(c_can_plat_init); + +static void __exit c_can_plat_exit(void) +{ + platform_driver_unregister(&c_can_plat_driver); +} +module_exit(c_can_plat_exit); + +MODULE_AUTHOR("Bhupesh Sharma <bhupesh.sharma@st.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Platform CAN bus driver for Bosch C_CAN controller"); diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c index 7ff170c..2d2d28f 100644 --- a/drivers/net/cnic.c +++ b/drivers/net/cnic.c @@ -65,7 +65,14 @@ static LIST_HEAD(cnic_udev_list); static DEFINE_RWLOCK(cnic_dev_lock); static DEFINE_MUTEX(cnic_lock); -static struct cnic_ulp_ops *cnic_ulp_tbl[MAX_CNIC_ULP_TYPE]; +static struct cnic_ulp_ops __rcu *cnic_ulp_tbl[MAX_CNIC_ULP_TYPE]; + +/* helper function, assuming cnic_lock is held */ +static inline struct cnic_ulp_ops *cnic_ulp_tbl_prot(int type) +{ + return rcu_dereference_protected(cnic_ulp_tbl[type], + lockdep_is_held(&cnic_lock)); +} static int cnic_service_bnx2(void *, void *); static int cnic_service_bnx2x(void *, void *); @@ -435,7 +442,7 @@ int cnic_register_driver(int ulp_type, struct cnic_ulp_ops *ulp_ops) return -EINVAL; } mutex_lock(&cnic_lock); - if (cnic_ulp_tbl[ulp_type]) { + if (cnic_ulp_tbl_prot(ulp_type)) { pr_err("%s: Type %d has already been registered\n", __func__, ulp_type); mutex_unlock(&cnic_lock); @@ -478,7 +485,7 @@ int cnic_unregister_driver(int ulp_type) return -EINVAL; } mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl[ulp_type]; + ulp_ops = cnic_ulp_tbl_prot(ulp_type); if (!ulp_ops) { pr_err("%s: Type %d has not been registered\n", __func__, ulp_type); @@ -529,7 +536,7 @@ static int cnic_register_device(struct cnic_dev *dev, int ulp_type, return -EINVAL; } mutex_lock(&cnic_lock); - if (cnic_ulp_tbl[ulp_type] == NULL) { + if (cnic_ulp_tbl_prot(ulp_type) == NULL) { pr_err("%s: Driver with type %d has not been registered\n", __func__, ulp_type); mutex_unlock(&cnic_lock); @@ -544,7 +551,7 @@ static int cnic_register_device(struct cnic_dev *dev, int ulp_type, clear_bit(ULP_F_START, &cp->ulp_flags[ulp_type]); cp->ulp_handle[ulp_type] = ulp_ctx; - ulp_ops = cnic_ulp_tbl[ulp_type]; + ulp_ops = cnic_ulp_tbl_prot(ulp_type); rcu_assign_pointer(cp->ulp_ops[ulp_type], ulp_ops); cnic_hold(dev); @@ -2953,7 +2960,8 @@ static void cnic_ulp_stop(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cp->ulp_ops[if_type]; + ulp_ops = rcu_dereference_protected(cp->ulp_ops[if_type], + lockdep_is_held(&cnic_lock)); if (!ulp_ops) { mutex_unlock(&cnic_lock); continue; @@ -2977,7 +2985,8 @@ static void cnic_ulp_start(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cp->ulp_ops[if_type]; + ulp_ops = rcu_dereference_protected(cp->ulp_ops[if_type], + lockdep_is_held(&cnic_lock)); if (!ulp_ops || !ulp_ops->cnic_start) { mutex_unlock(&cnic_lock); continue; @@ -3041,7 +3050,7 @@ static void cnic_ulp_init(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl[i]; + ulp_ops = cnic_ulp_tbl_prot(i); if (!ulp_ops || !ulp_ops->cnic_init) { mutex_unlock(&cnic_lock); continue; @@ -3065,7 +3074,7 @@ static void cnic_ulp_exit(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl[i]; + ulp_ops = cnic_ulp_tbl_prot(i); if (!ulp_ops || !ulp_ops->cnic_exit) { mutex_unlock(&cnic_lock); continue; @@ -4170,6 +4179,14 @@ static void cnic_enable_bnx2_int(struct cnic_dev *dev) BNX2_PCICFG_INT_ACK_CMD_INDEX_VALID | cp->last_status_idx); } +static void cnic_get_bnx2_iscsi_info(struct cnic_dev *dev) +{ + u32 max_conn; + + max_conn = cnic_reg_rd_ind(dev, BNX2_FW_MAX_ISCSI_CONN); + dev->max_iscsi_conn = max_conn; +} + static void cnic_disable_bnx2_int_sync(struct cnic_dev *dev) { struct cnic_local *cp = dev->cnic_priv; @@ -4494,6 +4511,8 @@ static int cnic_start_bnx2_hw(struct cnic_dev *dev) return err; } + cnic_get_bnx2_iscsi_info(dev); + return 0; } @@ -4705,129 +4724,6 @@ static void cnic_init_bnx2x_rx_ring(struct cnic_dev *dev, cp->rx_cons = *cp->rx_cons_ptr; } -static int cnic_read_bnx2x_iscsi_mac(struct cnic_dev *dev, u32 upper_addr, - u32 lower_addr) -{ - u32 val; - u8 mac[6]; - - val = CNIC_RD(dev, upper_addr); - - mac[0] = (u8) (val >> 8); - mac[1] = (u8) val; - - val = CNIC_RD(dev, lower_addr); - - mac[2] = (u8) (val >> 24); - mac[3] = (u8) (val >> 16); - mac[4] = (u8) (val >> 8); - mac[5] = (u8) val; - - if (is_valid_ether_addr(mac)) { - memcpy(dev->mac_addr, mac, 6); - return 0; - } else { - return -EINVAL; - } -} - -static void cnic_get_bnx2x_iscsi_info(struct cnic_dev *dev) -{ - struct cnic_local *cp = dev->cnic_priv; - u32 base, base2, addr, addr1, val; - int port = CNIC_PORT(cp); - - dev->max_iscsi_conn = 0; - base = CNIC_RD(dev, MISC_REG_SHARED_MEM_ADDR); - if (base == 0) - return; - - base2 = CNIC_RD(dev, (CNIC_PATH(cp) ? MISC_REG_GENERIC_CR_1 : - MISC_REG_GENERIC_CR_0)); - addr = BNX2X_SHMEM_ADDR(base, - dev_info.port_hw_config[port].iscsi_mac_upper); - - addr1 = BNX2X_SHMEM_ADDR(base, - dev_info.port_hw_config[port].iscsi_mac_lower); - - cnic_read_bnx2x_iscsi_mac(dev, addr, addr1); - - addr = BNX2X_SHMEM_ADDR(base, validity_map[port]); - val = CNIC_RD(dev, addr); - - if (!(val & SHR_MEM_VALIDITY_LIC_NO_KEY_IN_EFFECT)) { - u16 val16; - - addr = BNX2X_SHMEM_ADDR(base, - drv_lic_key[port].max_iscsi_init_conn); - val16 = CNIC_RD16(dev, addr); - - if (val16) - val16 ^= 0x1e1e; - dev->max_iscsi_conn = val16; - } - - if (BNX2X_CHIP_IS_E2(cp->chip_id)) - dev->max_fcoe_conn = BNX2X_FCOE_NUM_CONNECTIONS; - - if (BNX2X_CHIP_IS_E1H(cp->chip_id) || BNX2X_CHIP_IS_E2(cp->chip_id)) { - int func = CNIC_FUNC(cp); - u32 mf_cfg_addr; - - if (BNX2X_SHMEM2_HAS(base2, mf_cfg_addr)) - mf_cfg_addr = CNIC_RD(dev, BNX2X_SHMEM2_ADDR(base2, - mf_cfg_addr)); - else - mf_cfg_addr = base + BNX2X_SHMEM_MF_BLK_OFFSET; - - if (BNX2X_CHIP_IS_E2(cp->chip_id)) { - /* Must determine if the MF is SD vs SI mode */ - addr = BNX2X_SHMEM_ADDR(base, - dev_info.shared_feature_config.config); - val = CNIC_RD(dev, addr); - if ((val & SHARED_FEAT_CFG_FORCE_SF_MODE_MASK) == - SHARED_FEAT_CFG_FORCE_SF_MODE_SWITCH_INDEPT) { - int rc; - - /* MULTI_FUNCTION_SI mode */ - addr = BNX2X_MF_CFG_ADDR(mf_cfg_addr, - func_ext_config[func].func_cfg); - val = CNIC_RD(dev, addr); - if (!(val & MACP_FUNC_CFG_FLAGS_ISCSI_OFFLOAD)) - dev->max_iscsi_conn = 0; - - if (!(val & MACP_FUNC_CFG_FLAGS_FCOE_OFFLOAD)) - dev->max_fcoe_conn = 0; - - addr = BNX2X_MF_CFG_ADDR(mf_cfg_addr, - func_ext_config[func]. - iscsi_mac_addr_upper); - addr1 = BNX2X_MF_CFG_ADDR(mf_cfg_addr, - func_ext_config[func]. - iscsi_mac_addr_lower); - rc = cnic_read_bnx2x_iscsi_mac(dev, addr, - addr1); - if (rc && func > 1) - dev->max_iscsi_conn = 0; - - return; - } - } - - addr = BNX2X_MF_CFG_ADDR(mf_cfg_addr, - func_mf_config[func].e1hov_tag); - - val = CNIC_RD(dev, addr); - val &= FUNC_MF_CFG_E1HOV_TAG_MASK; - if (val != FUNC_MF_CFG_E1HOV_TAG_DEFAULT) { - dev->max_fcoe_conn = 0; - dev->max_iscsi_conn = 0; - } - } - if (!is_valid_ether_addr(dev->mac_addr)) - dev->max_iscsi_conn = 0; -} - static void cnic_init_bnx2x_kcq(struct cnic_dev *dev) { struct cnic_local *cp = dev->cnic_priv; @@ -4909,8 +4805,6 @@ static int cnic_start_bnx2x_hw(struct cnic_dev *dev) cnic_init_bnx2x_kcq(dev); - cnic_get_bnx2x_iscsi_info(dev); - /* Only 1 EQ */ CNIC_WR16(dev, cp->kcq1.io_addr, MAX_KCQ_IDX); CNIC_WR(dev, BAR_CSTRORM_INTMEM + @@ -5343,6 +5237,14 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev) cdev->pcidev = pdev; cp->chip_id = ethdev->chip_id; + if (!(ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI)) + cdev->max_iscsi_conn = ethdev->max_iscsi_conn; + if (BNX2X_CHIP_IS_E2(cp->chip_id) && + !(ethdev->drv_state & CNIC_DRV_STATE_NO_FCOE)) + cdev->max_fcoe_conn = ethdev->max_fcoe_conn; + + memcpy(cdev->mac_addr, ethdev->iscsi_mac, 6); + cp->cnic_ops = &cnic_bnx2x_ops; cp->start_hw = cnic_start_bnx2x_hw; cp->stop_hw = cnic_stop_bnx2x_hw; diff --git a/drivers/net/cnic.h b/drivers/net/cnic.h index b328f6c..4456260 100644 --- a/drivers/net/cnic.h +++ b/drivers/net/cnic.h @@ -220,7 +220,7 @@ struct cnic_local { #define ULP_F_INIT 0 #define ULP_F_START 1 #define ULP_F_CALL_PENDING 2 - struct cnic_ulp_ops *ulp_ops[MAX_CNIC_ULP_TYPE]; + struct cnic_ulp_ops __rcu *ulp_ops[MAX_CNIC_ULP_TYPE]; unsigned long cnic_local_flags; #define CNIC_LCL_FL_KWQ_INIT 0x0 diff --git a/drivers/net/cnic_if.h b/drivers/net/cnic_if.h index 9f44e0f..e01b49e 100644 --- a/drivers/net/cnic_if.h +++ b/drivers/net/cnic_if.h @@ -12,8 +12,8 @@ #ifndef CNIC_IF_H #define CNIC_IF_H -#define CNIC_MODULE_VERSION "2.2.12" -#define CNIC_MODULE_RELDATE "Jan 03, 2011" +#define CNIC_MODULE_VERSION "2.2.13" +#define CNIC_MODULE_RELDATE "Jan 31, 2011" #define CNIC_ULP_RDMA 0 #define CNIC_ULP_ISCSI 1 @@ -159,6 +159,9 @@ struct cnic_eth_dev { u32 drv_state; #define CNIC_DRV_STATE_REGD 0x00000001 #define CNIC_DRV_STATE_USING_MSIX 0x00000002 +#define CNIC_DRV_STATE_NO_ISCSI_OOO 0x00000004 +#define CNIC_DRV_STATE_NO_ISCSI 0x00000008 +#define CNIC_DRV_STATE_NO_FCOE 0x00000010 u32 chip_id; u32 max_kwqe_pending; struct pci_dev *pdev; @@ -176,6 +179,7 @@ struct cnic_eth_dev { u32 fcoe_init_cid; u16 iscsi_l2_client_id; u16 iscsi_l2_cid; + u8 iscsi_mac[ETH_ALEN]; int num_irq; struct cnic_irq irq_arr[MAX_CNIC_VEC]; diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c index ef02aa6..862804f 100644 --- a/drivers/net/cxgb3/cxgb3_offload.c +++ b/drivers/net/cxgb3/cxgb3_offload.c @@ -186,9 +186,10 @@ static struct net_device *get_iff_from_mac(struct adapter *adapter, dev = NULL; if (grp) dev = vlan_group_get_device(grp, vlan); - } else + } else if (netif_is_bond_slave(dev)) { while (dev->master) dev = dev->master; + } return dev; } } @@ -967,8 +968,6 @@ static int nb_callback(struct notifier_block *self, unsigned long event, cxgb_neigh_update((struct neighbour *)ctx); break; } - case (NETEVENT_PMTU_UPDATE): - break; case (NETEVENT_REDIRECT):{ struct netevent_redirect *nr = ctx; cxgb_redirect(nr->old, nr->new); diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c index ec35d45..5352c8a 100644 --- a/drivers/net/cxgb4/cxgb4_main.c +++ b/drivers/net/cxgb4/cxgb4_main.c @@ -2471,7 +2471,6 @@ static int netevent_cb(struct notifier_block *nb, unsigned long event, case NETEVENT_NEIGH_UPDATE: check_neigh_update(data); break; - case NETEVENT_PMTU_UPDATE: case NETEVENT_REDIRECT: default: break; diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h index e610e136..00bf595 100644 --- a/drivers/net/e1000e/e1000.h +++ b/drivers/net/e1000e/e1000.h @@ -364,6 +364,7 @@ struct e1000_adapter { /* structs defined in e1000_hw.h */ struct e1000_hw hw; + spinlock_t stats64_lock; struct e1000_hw_stats stats; struct e1000_phy_info phy_info; struct e1000_phy_stats phy_stats; @@ -494,7 +495,9 @@ extern int e1000e_setup_rx_resources(struct e1000_adapter *adapter); extern int e1000e_setup_tx_resources(struct e1000_adapter *adapter); extern void e1000e_free_rx_resources(struct e1000_adapter *adapter); extern void e1000e_free_tx_resources(struct e1000_adapter *adapter); -extern void e1000e_update_stats(struct e1000_adapter *adapter); +extern struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 + *stats); extern void e1000e_set_interrupt_capability(struct e1000_adapter *adapter); extern void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter); extern void e1000e_get_hw_control(struct e1000_adapter *adapter); diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c index fa08b63..65ef9b5 100644 --- a/drivers/net/e1000e/ethtool.c +++ b/drivers/net/e1000e/ethtool.c @@ -46,15 +46,15 @@ struct e1000_stats { }; #define E1000_STAT(str, m) { \ - .stat_string = str, \ - .type = E1000_STATS, \ - .sizeof_stat = sizeof(((struct e1000_adapter *)0)->m), \ - .stat_offset = offsetof(struct e1000_adapter, m) } + .stat_string = str, \ + .type = E1000_STATS, \ + .sizeof_stat = sizeof(((struct e1000_adapter *)0)->m), \ + .stat_offset = offsetof(struct e1000_adapter, m) } #define E1000_NETDEV_STAT(str, m) { \ - .stat_string = str, \ - .type = NETDEV_STATS, \ - .sizeof_stat = sizeof(((struct net_device *)0)->m), \ - .stat_offset = offsetof(struct net_device, m) } + .stat_string = str, \ + .type = NETDEV_STATS, \ + .sizeof_stat = sizeof(((struct rtnl_link_stats64 *)0)->m), \ + .stat_offset = offsetof(struct rtnl_link_stats64, m) } static const struct e1000_stats e1000_gstrings_stats[] = { E1000_STAT("rx_packets", stats.gprc), @@ -65,21 +65,21 @@ static const struct e1000_stats e1000_gstrings_stats[] = { E1000_STAT("tx_broadcast", stats.bptc), E1000_STAT("rx_multicast", stats.mprc), E1000_STAT("tx_multicast", stats.mptc), - E1000_NETDEV_STAT("rx_errors", stats.rx_errors), - E1000_NETDEV_STAT("tx_errors", stats.tx_errors), - E1000_NETDEV_STAT("tx_dropped", stats.tx_dropped), + E1000_NETDEV_STAT("rx_errors", rx_errors), + E1000_NETDEV_STAT("tx_errors", tx_errors), + E1000_NETDEV_STAT("tx_dropped", tx_dropped), E1000_STAT("multicast", stats.mprc), E1000_STAT("collisions", stats.colc), - E1000_NETDEV_STAT("rx_length_errors", stats.rx_length_errors), - E1000_NETDEV_STAT("rx_over_errors", stats.rx_over_errors), + E1000_NETDEV_STAT("rx_length_errors", rx_length_errors), + E1000_NETDEV_STAT("rx_over_errors", rx_over_errors), E1000_STAT("rx_crc_errors", stats.crcerrs), - E1000_NETDEV_STAT("rx_frame_errors", stats.rx_frame_errors), + E1000_NETDEV_STAT("rx_frame_errors", rx_frame_errors), E1000_STAT("rx_no_buffer_count", stats.rnbc), E1000_STAT("rx_missed_errors", stats.mpc), E1000_STAT("tx_aborted_errors", stats.ecol), E1000_STAT("tx_carrier_errors", stats.tncrs), - E1000_NETDEV_STAT("tx_fifo_errors", stats.tx_fifo_errors), - E1000_NETDEV_STAT("tx_heartbeat_errors", stats.tx_heartbeat_errors), + E1000_NETDEV_STAT("tx_fifo_errors", tx_fifo_errors), + E1000_NETDEV_STAT("tx_heartbeat_errors", tx_heartbeat_errors), E1000_STAT("tx_window_errors", stats.latecol), E1000_STAT("tx_abort_late_coll", stats.latecol), E1000_STAT("tx_deferred_ok", stats.dc), @@ -684,20 +684,13 @@ static int e1000_set_ringparam(struct net_device *netdev, rx_old = adapter->rx_ring; err = -ENOMEM; - tx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL); + tx_ring = kmemdup(tx_old, sizeof(struct e1000_ring), GFP_KERNEL); if (!tx_ring) goto err_alloc_tx; - /* - * use a memcpy to save any previously configured - * items like napi structs from having to be - * reinitialized - */ - memcpy(tx_ring, tx_old, sizeof(struct e1000_ring)); - rx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL); + rx_ring = kmemdup(rx_old, sizeof(struct e1000_ring), GFP_KERNEL); if (!rx_ring) goto err_alloc_rx; - memcpy(rx_ring, rx_old, sizeof(struct e1000_ring)); adapter->tx_ring = tx_ring; adapter->rx_ring = rx_ring; @@ -1255,7 +1248,6 @@ static int e1000_integrated_phy_loopback(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 ctrl_reg = 0; - u32 stat_reg = 0; u16 phy_reg = 0; s32 ret_val = 0; @@ -1363,8 +1355,7 @@ static int e1000_integrated_phy_loopback(struct e1000_adapter *adapter) * Set the ILOS bit on the fiber Nic if half duplex link is * detected. */ - stat_reg = er32(STATUS); - if ((stat_reg & E1000_STATUS_FD) == 0) + if ((er32(STATUS) & E1000_STATUS_FD) == 0) ctrl_reg |= (E1000_CTRL_ILOS | E1000_CTRL_SLU); } @@ -1972,8 +1963,15 @@ static int e1000_set_coalesce(struct net_device *netdev, static int e1000_nway_reset(struct net_device *netdev) { struct e1000_adapter *adapter = netdev_priv(netdev); - if (netif_running(netdev)) - e1000e_reinit_locked(adapter); + + if (!netif_running(netdev)) + return -EAGAIN; + + if (!adapter->hw.mac.autoneg) + return -EINVAL; + + e1000e_reinit_locked(adapter); + return 0; } @@ -1982,14 +1980,15 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, u64 *data) { struct e1000_adapter *adapter = netdev_priv(netdev); + struct rtnl_link_stats64 net_stats; int i; char *p = NULL; - e1000e_update_stats(adapter); + e1000e_get_stats64(netdev, &net_stats); for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { switch (e1000_gstrings_stats[i].type) { case NETDEV_STATS: - p = (char *) netdev + + p = (char *) &net_stats + e1000_gstrings_stats[i].stat_offset; break; case E1000_STATS: @@ -2014,7 +2013,7 @@ static void e1000_get_strings(struct net_device *netdev, u32 stringset, switch (stringset) { case ETH_SS_TEST: - memcpy(data, *e1000_gstrings_test, sizeof(e1000_gstrings_test)); + memcpy(data, e1000_gstrings_test, sizeof(e1000_gstrings_test)); break; case ETH_SS_STATS: for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index fb46974..232b42b 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -2104,7 +2104,6 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) { union ich8_hws_flash_status hsfsts; s32 ret_val = -E1000_ERR_NVM; - s32 i = 0; hsfsts.regval = er16flash(ICH_FLASH_HSFSTS); @@ -2140,6 +2139,8 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) ew16flash(ICH_FLASH_HSFSTS, hsfsts.regval); ret_val = 0; } else { + s32 i = 0; + /* * Otherwise poll for sometime so the current * cycle has a chance to end before giving up. diff --git a/drivers/net/e1000e/lib.c b/drivers/net/e1000e/lib.c index 68aa174..96921de5 100644 --- a/drivers/net/e1000e/lib.c +++ b/drivers/net/e1000e/lib.c @@ -1978,15 +1978,15 @@ static s32 e1000_ready_nvm_eeprom(struct e1000_hw *hw) { struct e1000_nvm_info *nvm = &hw->nvm; u32 eecd = er32(EECD); - u16 timeout = 0; u8 spi_stat_reg; if (nvm->type == e1000_nvm_eeprom_spi) { + u16 timeout = NVM_MAX_RETRY_SPI; + /* Clear SK and CS */ eecd &= ~(E1000_EECD_CS | E1000_EECD_SK); ew32(EECD, eecd); udelay(1); - timeout = NVM_MAX_RETRY_SPI; /* * Read "Status Register" repeatedly until the LSB is cleared. diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 3fa110d..ec0b803 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -900,8 +900,6 @@ next_desc: adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; - netdev->stats.rx_bytes += total_rx_bytes; - netdev->stats.rx_packets += total_rx_packets; return cleaned; } @@ -1060,8 +1058,6 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter) } adapter->total_tx_bytes += total_tx_bytes; adapter->total_tx_packets += total_tx_packets; - netdev->stats.tx_bytes += total_tx_bytes; - netdev->stats.tx_packets += total_tx_packets; return count < tx_ring->count; } @@ -1248,8 +1244,6 @@ next_desc: adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; - netdev->stats.rx_bytes += total_rx_bytes; - netdev->stats.rx_packets += total_rx_packets; return cleaned; } @@ -1429,8 +1423,6 @@ next_desc: adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; - netdev->stats.rx_bytes += total_rx_bytes; - netdev->stats.rx_packets += total_rx_packets; return cleaned; } @@ -1857,7 +1849,9 @@ static int e1000_request_msix(struct e1000_adapter *adapter) int err = 0, vector = 0; if (strlen(netdev->name) < (IFNAMSIZ - 5)) - sprintf(adapter->rx_ring->name, "%s-rx-0", netdev->name); + snprintf(adapter->rx_ring->name, + sizeof(adapter->rx_ring->name) - 1, + "%s-rx-0", netdev->name); else memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ); err = request_irq(adapter->msix_entries[vector].vector, @@ -1870,7 +1864,9 @@ static int e1000_request_msix(struct e1000_adapter *adapter) vector++; if (strlen(netdev->name) < (IFNAMSIZ - 5)) - sprintf(adapter->tx_ring->name, "%s-tx-0", netdev->name); + snprintf(adapter->tx_ring->name, + sizeof(adapter->tx_ring->name) - 1, + "%s-tx-0", netdev->name); else memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ); err = request_irq(adapter->msix_entries[vector].vector, @@ -2734,7 +2730,6 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 rctl, rfctl; - u32 psrctl = 0; u32 pages = 0; /* Workaround Si errata on 82579 - configure jumbo frame flow */ @@ -2833,6 +2828,8 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) adapter->rx_ps_pages = 0; if (adapter->rx_ps_pages) { + u32 psrctl = 0; + /* Configure extra packet-split registers */ rfctl = er32(RFCTL); rfctl |= E1000_RFCTL_EXTEN; @@ -3034,7 +3031,6 @@ static void e1000_set_multi(struct net_device *netdev) struct netdev_hw_addr *ha; u8 *mta_list; u32 rctl; - int i; /* Check for Promiscuous and All Multicast modes */ @@ -3057,12 +3053,13 @@ static void e1000_set_multi(struct net_device *netdev) ew32(RCTL, rctl); if (!netdev_mc_empty(netdev)) { + int i = 0; + mta_list = kmalloc(netdev_mc_count(netdev) * 6, GFP_ATOMIC); if (!mta_list) return; /* prepare a packed array of only addresses. */ - i = 0; netdev_for_each_mc_addr(ha, netdev) memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); @@ -3359,6 +3356,8 @@ static void e1000e_flush_descriptors(struct e1000_adapter *adapter) e1e_flush(); } +static void e1000e_update_stats(struct e1000_adapter *adapter); + void e1000e_down(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -3393,6 +3392,11 @@ void e1000e_down(struct e1000_adapter *adapter) del_timer_sync(&adapter->phy_info_timer); netif_carrier_off(netdev); + + spin_lock(&adapter->stats64_lock); + e1000e_update_stats(adapter); + spin_unlock(&adapter->stats64_lock); + adapter->link_speed = 0; adapter->link_duplex = 0; @@ -3437,6 +3441,8 @@ static int __devinit e1000_sw_init(struct e1000_adapter *adapter) adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; + spin_lock_init(&adapter->stats64_lock); + e1000e_set_interrupt_capability(adapter); if (e1000_alloc_queues(adapter)) @@ -3918,7 +3924,7 @@ release: * e1000e_update_stats - Update the board statistics counters * @adapter: board private structure **/ -void e1000e_update_stats(struct e1000_adapter *adapter) +static void e1000e_update_stats(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; @@ -4030,10 +4036,11 @@ static void e1000_phy_read_status(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_phy_regs *phy = &adapter->phy_regs; - int ret_val; if ((er32(STATUS) & E1000_STATUS_LU) && (adapter->hw.phy.media_type == e1000_media_type_copper)) { + int ret_val; + ret_val = e1e_rphy(hw, PHY_CONTROL, &phy->bmcr); ret_val |= e1e_rphy(hw, PHY_STATUS, &phy->bmsr); ret_val |= e1e_rphy(hw, PHY_AUTONEG_ADV, &phy->advertise); @@ -4179,7 +4186,6 @@ static void e1000_watchdog_task(struct work_struct *work) struct e1000_ring *tx_ring = adapter->tx_ring; struct e1000_hw *hw = &adapter->hw; u32 link, tctl; - int tx_pending = 0; if (test_bit(__E1000_DOWN, &adapter->state)) return; @@ -4320,7 +4326,9 @@ static void e1000_watchdog_task(struct work_struct *work) } link_up: + spin_lock(&adapter->stats64_lock); e1000e_update_stats(adapter); + spin_unlock(&adapter->stats64_lock); mac->tx_packet_delta = adapter->stats.tpt - adapter->tpt_old; adapter->tpt_old = adapter->stats.tpt; @@ -4334,20 +4342,17 @@ link_up: e1000e_update_adaptive(&adapter->hw); - if (!netif_carrier_ok(netdev)) { - tx_pending = (e1000_desc_unused(tx_ring) + 1 < - tx_ring->count); - if (tx_pending) { - /* - * We've lost link, so the controller stops DMA, - * but we've got queued Tx work that's never going - * to get done, so reset controller to flush Tx. - * (Do the reset outside of interrupt context). - */ - schedule_work(&adapter->reset_task); - /* return immediately since reset is imminent */ - return; - } + if (!netif_carrier_ok(netdev) && + (e1000_desc_unused(tx_ring) + 1 < tx_ring->count)) { + /* + * We've lost link, so the controller stops DMA, + * but we've got queued Tx work that's never going + * to get done, so reset controller to flush Tx. + * (Do the reset outside of interrupt context). + */ + schedule_work(&adapter->reset_task); + /* return immediately since reset is imminent */ + return; } /* Simple mode for Interrupt Throttle Rate (ITR) */ @@ -4411,13 +4416,13 @@ static int e1000_tso(struct e1000_adapter *adapter, u32 cmd_length = 0; u16 ipcse = 0, tucse, mss; u8 ipcss, ipcso, tucss, tucso, hdr_len; - int err; if (!skb_is_gso(skb)) return 0; if (skb_header_cloned(skb)) { - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (err) return err; } @@ -4928,16 +4933,55 @@ static void e1000_reset_task(struct work_struct *work) } /** - * e1000_get_stats - Get System Network Statistics + * e1000_get_stats64 - Get System Network Statistics * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer * * Returns the address of the device statistics structure. - * The statistics are actually updated from the timer callback. **/ -static struct net_device_stats *e1000_get_stats(struct net_device *netdev) +struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { - /* only return the current stats */ - return &netdev->stats; + struct e1000_adapter *adapter = netdev_priv(netdev); + + memset(stats, 0, sizeof(struct rtnl_link_stats64)); + spin_lock(&adapter->stats64_lock); + e1000e_update_stats(adapter); + /* Fill out the OS statistics structure */ + stats->rx_bytes = adapter->stats.gorc; + stats->rx_packets = adapter->stats.gprc; + stats->tx_bytes = adapter->stats.gotc; + stats->tx_packets = adapter->stats.gptc; + stats->multicast = adapter->stats.mprc; + stats->collisions = adapter->stats.colc; + + /* Rx Errors */ + + /* + * RLEC on some newer hardware can be incorrect so build + * our own version based on RUC and ROC + */ + stats->rx_errors = adapter->stats.rxerrc + + adapter->stats.crcerrs + adapter->stats.algnerrc + + adapter->stats.ruc + adapter->stats.roc + + adapter->stats.cexterr; + stats->rx_length_errors = adapter->stats.ruc + + adapter->stats.roc; + stats->rx_crc_errors = adapter->stats.crcerrs; + stats->rx_frame_errors = adapter->stats.algnerrc; + stats->rx_missed_errors = adapter->stats.mpc; + + /* Tx Errors */ + stats->tx_errors = adapter->stats.ecol + + adapter->stats.latecol; + stats->tx_aborted_errors = adapter->stats.ecol; + stats->tx_window_errors = adapter->stats.latecol; + stats->tx_carrier_errors = adapter->stats.tncrs; + + /* Tx Dropped needs to be maintained elsewhere */ + + spin_unlock(&adapter->stats64_lock); + return stats; } /** @@ -5507,9 +5551,10 @@ static irqreturn_t e1000_intr_msix(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); - int vector, msix_irq; if (adapter->msix_entries) { + int vector, msix_irq; + vector = 0; msix_irq = adapter->msix_entries[vector].vector; disable_irq(msix_irq); @@ -5706,7 +5751,7 @@ static const struct net_device_ops e1000e_netdev_ops = { .ndo_open = e1000_open, .ndo_stop = e1000_close, .ndo_start_xmit = e1000_xmit_frame, - .ndo_get_stats = e1000_get_stats, + .ndo_get_stats64 = e1000e_get_stats64, .ndo_set_multicast_list = e1000_set_multi, .ndo_set_mac_address = e1000_set_mac, .ndo_change_mtu = e1000_change_mtu, diff --git a/drivers/net/e1000e/phy.c b/drivers/net/e1000e/phy.c index 6bea051..6ae31fc 100644 --- a/drivers/net/e1000e/phy.c +++ b/drivers/net/e1000e/phy.c @@ -2409,9 +2409,7 @@ static u32 e1000_get_phy_addr_for_bm_page(u32 page, u32 reg) s32 e1000e_write_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 data) { s32 ret_val; - u32 page_select = 0; u32 page = offset >> IGP_PAGE_SHIFT; - u32 page_shift = 0; ret_val = hw->phy.ops.acquire(hw); if (ret_val) @@ -2427,6 +2425,8 @@ s32 e1000e_write_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 data) hw->phy.addr = e1000_get_phy_addr_for_bm_page(page, offset); if (offset > MAX_PHY_MULTI_PAGE_REG) { + u32 page_shift, page_select; + /* * Page select is register 31 for phy address 1 and 22 for * phy address 2 and 3. Page select is shifted only for @@ -2468,9 +2468,7 @@ out: s32 e1000e_read_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 *data) { s32 ret_val; - u32 page_select = 0; u32 page = offset >> IGP_PAGE_SHIFT; - u32 page_shift = 0; ret_val = hw->phy.ops.acquire(hw); if (ret_val) @@ -2486,6 +2484,8 @@ s32 e1000e_read_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 *data) hw->phy.addr = e1000_get_phy_addr_for_bm_page(page, offset); if (offset > MAX_PHY_MULTI_PAGE_REG) { + u32 page_shift, page_select; + /* * Page select is register 31 for phy address 1 and 22 for * phy address 2 and 3. Page select is shifted only for diff --git a/drivers/net/enic/Makefile b/drivers/net/enic/Makefile index e7b6c31..2e573be 100644 --- a/drivers/net/enic/Makefile +++ b/drivers/net/enic/Makefile @@ -1,5 +1,5 @@ obj-$(CONFIG_ENIC) := enic.o enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \ - enic_res.o vnic_dev.o vnic_rq.o vnic_vic.o + enic_res.o enic_dev.o vnic_dev.o vnic_rq.o vnic_vic.o diff --git a/drivers/net/enic/enic.h b/drivers/net/enic/enic.h index a937f49..aee5256 100644 --- a/drivers/net/enic/enic.h +++ b/drivers/net/enic/enic.h @@ -32,13 +32,13 @@ #define DRV_NAME "enic" #define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver" -#define DRV_VERSION "1.4.1.10" -#define DRV_COPYRIGHT "Copyright 2008-2010 Cisco Systems, Inc" +#define DRV_VERSION "2.1.1.9" +#define DRV_COPYRIGHT "Copyright 2008-2011 Cisco Systems, Inc" #define ENIC_BARS_MAX 6 -#define ENIC_WQ_MAX 8 -#define ENIC_RQ_MAX 8 +#define ENIC_WQ_MAX 1 +#define ENIC_RQ_MAX 1 #define ENIC_CQ_MAX (ENIC_WQ_MAX + ENIC_RQ_MAX) #define ENIC_INTR_MAX (ENIC_CQ_MAX + 2) @@ -49,7 +49,7 @@ struct enic_msix_entry { void *devid; }; -#define ENIC_SET_APPLIED (1 << 0) +#define ENIC_PORT_REQUEST_APPLIED (1 << 0) #define ENIC_SET_REQUEST (1 << 1) #define ENIC_SET_NAME (1 << 2) #define ENIC_SET_INSTANCE (1 << 3) @@ -101,7 +101,6 @@ struct enic { /* receive queue cache line section */ ____cacheline_aligned struct vnic_rq rq[ENIC_RQ_MAX]; unsigned int rq_count; - int (*rq_alloc_buf)(struct vnic_rq *rq); u64 rq_truncated_pkts; u64 rq_bad_fcs; struct napi_struct napi[ENIC_RQ_MAX]; diff --git a/drivers/net/enic/enic_dev.c b/drivers/net/enic/enic_dev.c new file mode 100644 index 0000000..37ad3a1 --- /dev/null +++ b/drivers/net/enic/enic_dev.c @@ -0,0 +1,221 @@ +/* + * Copyright 2011 Cisco Systems, Inc. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/pci.h> +#include <linux/etherdevice.h> + +#include "vnic_dev.h" +#include "vnic_vic.h" +#include "enic_res.h" +#include "enic.h" +#include "enic_dev.h" + +int enic_dev_fw_info(struct enic *enic, struct vnic_devcmd_fw_info **fw_info) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_fw_info(enic->vdev, fw_info); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_stats_dump(struct enic *enic, struct vnic_stats **vstats) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_stats_dump(enic->vdev, vstats); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_add_station_addr(struct enic *enic) +{ + int err; + + if (!is_valid_ether_addr(enic->netdev->dev_addr)) + return -EADDRNOTAVAIL; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_add_addr(enic->vdev, enic->netdev->dev_addr); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_del_station_addr(struct enic *enic) +{ + int err; + + if (!is_valid_ether_addr(enic->netdev->dev_addr)) + return -EADDRNOTAVAIL; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_del_addr(enic->vdev, enic->netdev->dev_addr); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_packet_filter(struct enic *enic, int directed, int multicast, + int broadcast, int promisc, int allmulti) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_packet_filter(enic->vdev, directed, + multicast, broadcast, promisc, allmulti); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_add_addr(struct enic *enic, u8 *addr) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_add_addr(enic->vdev, addr); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_del_addr(struct enic *enic, u8 *addr) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_del_addr(enic->vdev, addr); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_notify_unset(struct enic *enic) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_notify_unset(enic->vdev); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_hang_notify(struct enic *enic) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_hang_notify(enic->vdev); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_set_ig_vlan_rewrite_mode(struct enic *enic) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_set_ig_vlan_rewrite_mode(enic->vdev, + IG_VLAN_REWRITE_MODE_PRIORITY_TAG_DEFAULT_VLAN); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_enable(struct enic *enic) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_enable_wait(enic->vdev); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_disable(struct enic *enic) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_disable(enic->vdev); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_vnic_dev_deinit(struct enic *enic) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_deinit(enic->vdev); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_init_prov(struct enic *enic, struct vic_provinfo *vp) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_init_prov(enic->vdev, + (u8 *)vp, vic_provinfo_size(vp)); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +int enic_dev_init_done(struct enic *enic, int *done, int *error) +{ + int err; + + spin_lock(&enic->devcmd_lock); + err = vnic_dev_init_done(enic->vdev, done, error); + spin_unlock(&enic->devcmd_lock); + + return err; +} + +/* rtnl lock is held */ +void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +{ + struct enic *enic = netdev_priv(netdev); + + spin_lock(&enic->devcmd_lock); + enic_add_vlan(enic, vid); + spin_unlock(&enic->devcmd_lock); +} + +/* rtnl lock is held */ +void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +{ + struct enic *enic = netdev_priv(netdev); + + spin_lock(&enic->devcmd_lock); + enic_del_vlan(enic, vid); + spin_unlock(&enic->devcmd_lock); +} diff --git a/drivers/net/enic/enic_dev.h b/drivers/net/enic/enic_dev.h new file mode 100644 index 0000000..495f57f --- /dev/null +++ b/drivers/net/enic/enic_dev.h @@ -0,0 +1,41 @@ +/* + * Copyright 2011 Cisco Systems, Inc. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef _ENIC_DEV_H_ +#define _ENIC_DEV_H_ + +int enic_dev_fw_info(struct enic *enic, struct vnic_devcmd_fw_info **fw_info); +int enic_dev_stats_dump(struct enic *enic, struct vnic_stats **vstats); +int enic_dev_add_station_addr(struct enic *enic); +int enic_dev_del_station_addr(struct enic *enic); +int enic_dev_packet_filter(struct enic *enic, int directed, int multicast, + int broadcast, int promisc, int allmulti); +int enic_dev_add_addr(struct enic *enic, u8 *addr); +int enic_dev_del_addr(struct enic *enic, u8 *addr); +void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid); +void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid); +int enic_dev_notify_unset(struct enic *enic); +int enic_dev_hang_notify(struct enic *enic); +int enic_dev_set_ig_vlan_rewrite_mode(struct enic *enic); +int enic_dev_enable(struct enic *enic); +int enic_dev_disable(struct enic *enic); +int enic_vnic_dev_deinit(struct enic *enic); +int enic_dev_init_prov(struct enic *enic, struct vic_provinfo *vp); +int enic_dev_init_done(struct enic *enic, int *done, int *error); + +#endif /* _ENIC_DEV_H_ */ diff --git a/drivers/net/enic/enic_main.c b/drivers/net/enic/enic_main.c index a0af48c..4f1710e 100644 --- a/drivers/net/enic/enic_main.c +++ b/drivers/net/enic/enic_main.c @@ -44,6 +44,7 @@ #include "vnic_vic.h" #include "enic_res.h" #include "enic.h" +#include "enic_dev.h" #define ENIC_NOTIFY_TIMER_PERIOD (2 * HZ) #define WQ_ENET_MAX_DESC_LEN (1 << WQ_ENET_LEN_BITS) @@ -190,18 +191,6 @@ static int enic_get_settings(struct net_device *netdev, return 0; } -static int enic_dev_fw_info(struct enic *enic, - struct vnic_devcmd_fw_info **fw_info) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_fw_info(enic->vdev, fw_info); - spin_unlock(&enic->devcmd_lock); - - return err; -} - static void enic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { @@ -246,17 +235,6 @@ static int enic_get_sset_count(struct net_device *netdev, int sset) } } -static int enic_dev_stats_dump(struct enic *enic, struct vnic_stats **vstats) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_stats_dump(enic->vdev, vstats); - spin_unlock(&enic->devcmd_lock); - - return err; -} - static void enic_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { @@ -896,9 +874,10 @@ static struct net_device_stats *enic_get_stats(struct net_device *netdev) return net_stats; } -static void enic_reset_multicast_list(struct enic *enic) +static void enic_reset_addr_lists(struct enic *enic) { enic->mc_count = 0; + enic->uc_count = 0; enic->flags = 0; } @@ -919,32 +898,6 @@ static int enic_set_mac_addr(struct net_device *netdev, char *addr) return 0; } -static int enic_dev_add_station_addr(struct enic *enic) -{ - int err = 0; - - if (is_valid_ether_addr(enic->netdev->dev_addr)) { - spin_lock(&enic->devcmd_lock); - err = vnic_dev_add_addr(enic->vdev, enic->netdev->dev_addr); - spin_unlock(&enic->devcmd_lock); - } - - return err; -} - -static int enic_dev_del_station_addr(struct enic *enic) -{ - int err = 0; - - if (is_valid_ether_addr(enic->netdev->dev_addr)) { - spin_lock(&enic->devcmd_lock); - err = vnic_dev_del_addr(enic->vdev, enic->netdev->dev_addr); - spin_unlock(&enic->devcmd_lock); - } - - return err; -} - static int enic_set_mac_address_dynamic(struct net_device *netdev, void *p) { struct enic *enic = netdev_priv(netdev); @@ -989,42 +942,7 @@ static int enic_set_mac_address(struct net_device *netdev, void *p) return enic_dev_add_station_addr(enic); } -static int enic_dev_packet_filter(struct enic *enic, int directed, - int multicast, int broadcast, int promisc, int allmulti) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_packet_filter(enic->vdev, directed, - multicast, broadcast, promisc, allmulti); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_add_addr(struct enic *enic, u8 *addr) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_add_addr(enic->vdev, addr); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_del_addr(struct enic *enic, u8 *addr) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_del_addr(enic->vdev, addr); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static void enic_add_multicast_addr_list(struct enic *enic) +static void enic_update_multicast_addr_list(struct enic *enic) { struct net_device *netdev = enic->netdev; struct netdev_hw_addr *ha; @@ -1079,7 +997,7 @@ static void enic_add_multicast_addr_list(struct enic *enic) enic->mc_count = mc_count; } -static void enic_add_unicast_addr_list(struct enic *enic) +static void enic_update_unicast_addr_list(struct enic *enic) { struct net_device *netdev = enic->netdev; struct netdev_hw_addr *ha; @@ -1156,9 +1074,9 @@ static void enic_set_rx_mode(struct net_device *netdev) } if (!promisc) { - enic_add_unicast_addr_list(enic); + enic_update_unicast_addr_list(enic); if (!allmulti) - enic_add_multicast_addr_list(enic); + enic_update_multicast_addr_list(enic); } } @@ -1170,26 +1088,6 @@ static void enic_vlan_rx_register(struct net_device *netdev, enic->vlan_group = vlan_group; } -/* rtnl lock is held */ -static void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid) -{ - struct enic *enic = netdev_priv(netdev); - - spin_lock(&enic->devcmd_lock); - enic_add_vlan(enic, vid); - spin_unlock(&enic->devcmd_lock); -} - -/* rtnl lock is held */ -static void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) -{ - struct enic *enic = netdev_priv(netdev); - - spin_lock(&enic->devcmd_lock); - enic_del_vlan(enic, vid); - spin_unlock(&enic->devcmd_lock); -} - /* netif_tx_lock held, BHs disabled */ static void enic_tx_timeout(struct net_device *netdev) { @@ -1197,40 +1095,6 @@ static void enic_tx_timeout(struct net_device *netdev) schedule_work(&enic->reset); } -static int enic_vnic_dev_deinit(struct enic *enic) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_deinit(enic->vdev); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_init_prov(struct enic *enic, struct vic_provinfo *vp) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_init_prov(enic->vdev, - (u8 *)vp, vic_provinfo_size(vp)); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_init_done(struct enic *enic, int *done, int *error) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_init_done(enic->vdev, done, error); - spin_unlock(&enic->devcmd_lock); - - return err; -} - static int enic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { struct enic *enic = netdev_priv(netdev); @@ -1318,18 +1182,20 @@ static int enic_set_port_profile(struct enic *enic, u8 *mac) vic_provinfo_free(vp); if (err) return err; - - enic->pp.set |= ENIC_SET_APPLIED; break; case PORT_REQUEST_DISASSOCIATE: - enic->pp.set &= ~ENIC_SET_APPLIED; break; default: return -EINVAL; } + /* Set flag to indicate that the port assoc/disassoc + * request has been sent out to fw + */ + enic->pp.set |= ENIC_PORT_REQUEST_APPLIED; + return 0; } @@ -1379,9 +1245,6 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, if (is_zero_ether_addr(netdev->dev_addr)) random_ether_addr(netdev->dev_addr); - } else if (new_pp.request == PORT_REQUEST_DISASSOCIATE) { - if (!is_zero_ether_addr(enic->pp.mac_addr)) - enic_dev_del_addr(enic, enic->pp.mac_addr); } memcpy(&enic->pp, &new_pp, sizeof(struct enic_port_profile)); @@ -1390,9 +1253,6 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, if (err) goto set_port_profile_cleanup; - if (!is_zero_ether_addr(enic->pp.mac_addr)) - enic_dev_add_addr(enic, enic->pp.mac_addr); - set_port_profile_cleanup: memset(enic->pp.vf_mac, 0, ETH_ALEN); @@ -1411,7 +1271,7 @@ static int enic_get_vf_port(struct net_device *netdev, int vf, int err, error, done; u16 response = PORT_PROFILE_RESPONSE_SUCCESS; - if (!(enic->pp.set & ENIC_SET_APPLIED)) + if (!(enic->pp.set & ENIC_PORT_REQUEST_APPLIED)) return -ENODATA; err = enic_dev_init_done(enic, &done, &error); @@ -1489,62 +1349,6 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq) return 0; } -static int enic_rq_alloc_buf_a1(struct vnic_rq *rq) -{ - struct rq_enet_desc *desc = vnic_rq_next_desc(rq); - - if (vnic_rq_posting_soon(rq)) { - - /* SW workaround for A0 HW erratum: if we're just about - * to write posted_index, insert a dummy desc - * of type resvd - */ - - rq_enet_desc_enc(desc, 0, RQ_ENET_TYPE_RESV2, 0); - vnic_rq_post(rq, 0, 0, 0, 0); - } else { - return enic_rq_alloc_buf(rq); - } - - return 0; -} - -static int enic_dev_hw_version(struct enic *enic, - enum vnic_dev_hw_version *hw_ver) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_hw_version(enic->vdev, hw_ver); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_set_rq_alloc_buf(struct enic *enic) -{ - enum vnic_dev_hw_version hw_ver; - int err; - - err = enic_dev_hw_version(enic, &hw_ver); - if (err) - return err; - - switch (hw_ver) { - case VNIC_DEV_HW_VER_A1: - enic->rq_alloc_buf = enic_rq_alloc_buf_a1; - break; - case VNIC_DEV_HW_VER_A2: - case VNIC_DEV_HW_VER_UNKNOWN: - enic->rq_alloc_buf = enic_rq_alloc_buf; - break; - default: - return -ENODEV; - } - - return 0; -} - static void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc, struct vnic_rq_buf *buf, int skipped, void *opaque) @@ -1681,7 +1485,7 @@ static int enic_poll(struct napi_struct *napi, int budget) 0 /* don't unmask intr */, 0 /* don't reset intr timer */); - err = vnic_rq_fill(&enic->rq[0], enic->rq_alloc_buf); + err = vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf); /* Buffer allocation failed. Stay in polling * mode so we can try to fill the ring again. @@ -1731,7 +1535,7 @@ static int enic_poll_msix(struct napi_struct *napi, int budget) 0 /* don't unmask intr */, 0 /* don't reset intr timer */); - err = vnic_rq_fill(&enic->rq[rq], enic->rq_alloc_buf); + err = vnic_rq_fill(&enic->rq[rq], enic_rq_alloc_buf); /* Buffer allocation failed. Stay in polling mode * so we can try to fill the ring again. @@ -1901,39 +1705,6 @@ static int enic_dev_notify_set(struct enic *enic) return err; } -static int enic_dev_notify_unset(struct enic *enic) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_notify_unset(enic->vdev); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_enable(struct enic *enic) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_enable_wait(enic->vdev); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_disable(struct enic *enic) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_disable(enic->vdev); - spin_unlock(&enic->devcmd_lock); - - return err; -} - static void enic_notify_timer_start(struct enic *enic) { switch (vnic_dev_get_intr_mode(enic->vdev)) { @@ -1967,7 +1738,7 @@ static int enic_open(struct net_device *netdev) } for (i = 0; i < enic->rq_count; i++) { - vnic_rq_fill(&enic->rq[i], enic->rq_alloc_buf); + vnic_rq_fill(&enic->rq[i], enic_rq_alloc_buf); /* Need at least one buffer on ring to get going */ if (vnic_rq_desc_used(&enic->rq[i]) == 0) { netdev_err(netdev, "Unable to alloc receive buffers\n"); @@ -2285,29 +2056,6 @@ static int enic_set_rss_nic_cfg(struct enic *enic) rss_hash_bits, rss_base_cpu, rss_enable); } -static int enic_dev_hang_notify(struct enic *enic) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_hang_notify(enic->vdev); - spin_unlock(&enic->devcmd_lock); - - return err; -} - -static int enic_dev_set_ig_vlan_rewrite_mode(struct enic *enic) -{ - int err; - - spin_lock(&enic->devcmd_lock); - err = vnic_dev_set_ig_vlan_rewrite_mode(enic->vdev, - IG_VLAN_REWRITE_MODE_PRIORITY_TAG_DEFAULT_VLAN); - spin_unlock(&enic->devcmd_lock); - - return err; -} - static void enic_reset(struct work_struct *work) { struct enic *enic = container_of(work, struct enic, reset); @@ -2320,7 +2068,7 @@ static void enic_reset(struct work_struct *work) enic_dev_hang_notify(enic); enic_stop(enic->netdev); enic_dev_hang_reset(enic); - enic_reset_multicast_list(enic); + enic_reset_addr_lists(enic); enic_init_vnic_resources(enic); enic_set_rss_nic_cfg(enic); enic_dev_set_ig_vlan_rewrite_mode(enic); @@ -2332,7 +2080,7 @@ static void enic_reset(struct work_struct *work) static int enic_set_intr_mode(struct enic *enic) { unsigned int n = min_t(unsigned int, enic->rq_count, ENIC_RQ_MAX); - unsigned int m = 1; + unsigned int m = min_t(unsigned int, enic->wq_count, ENIC_WQ_MAX); unsigned int i; /* Set interrupt mode (INTx, MSI, MSI-X) depending @@ -2475,9 +2223,7 @@ static const struct net_device_ops enic_netdev_dynamic_ops = { .ndo_tx_timeout = enic_tx_timeout, .ndo_set_vf_port = enic_set_vf_port, .ndo_get_vf_port = enic_get_vf_port, -#ifdef IFLA_VF_MAX .ndo_set_vf_mac = enic_set_vf_mac, -#endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = enic_poll_controller, #endif @@ -2556,25 +2302,12 @@ static int enic_dev_init(struct enic *enic) enic_init_vnic_resources(enic); - err = enic_set_rq_alloc_buf(enic); - if (err) { - dev_err(dev, "Failed to set RQ buffer allocator, aborting\n"); - goto err_out_free_vnic_resources; - } - err = enic_set_rss_nic_cfg(enic); if (err) { dev_err(dev, "Failed to config nic, aborting\n"); goto err_out_free_vnic_resources; } - err = enic_dev_set_ig_vlan_rewrite_mode(enic); - if (err) { - dev_err(dev, - "Failed to set ingress vlan rewrite mode, aborting.\n"); - goto err_out_free_vnic_resources; - } - switch (vnic_dev_get_intr_mode(enic->vdev)) { default: netif_napi_add(netdev, &enic->napi[0], enic_poll, 64); @@ -2713,6 +2446,22 @@ static int __devinit enic_probe(struct pci_dev *pdev, goto err_out_vnic_unregister; } + /* Setup devcmd lock + */ + + spin_lock_init(&enic->devcmd_lock); + + /* + * Set ingress vlan rewrite mode before vnic initialization + */ + + err = enic_dev_set_ig_vlan_rewrite_mode(enic); + if (err) { + dev_err(dev, + "Failed to set ingress vlan rewrite mode, aborting.\n"); + goto err_out_dev_close; + } + /* Issue device init to initialize the vnic-to-switch link. * We'll start with carrier off and wait for link UP * notification later to turn on carrier. We don't need @@ -2736,11 +2485,6 @@ static int __devinit enic_probe(struct pci_dev *pdev, } } - /* Setup devcmd lock - */ - - spin_lock_init(&enic->devcmd_lock); - err = enic_dev_init(enic); if (err) { dev_err(dev, "Device initialization failed, aborting\n"); diff --git a/drivers/net/enic/vnic_dev.c b/drivers/net/enic/vnic_dev.c index fb35d8b..c489e72 100644 --- a/drivers/net/enic/vnic_dev.c +++ b/drivers/net/enic/vnic_dev.c @@ -419,25 +419,6 @@ int vnic_dev_fw_info(struct vnic_dev *vdev, return err; } -int vnic_dev_hw_version(struct vnic_dev *vdev, enum vnic_dev_hw_version *hw_ver) -{ - struct vnic_devcmd_fw_info *fw_info; - int err; - - err = vnic_dev_fw_info(vdev, &fw_info); - if (err) - return err; - - if (strncmp(fw_info->hw_version, "A1", sizeof("A1")) == 0) - *hw_ver = VNIC_DEV_HW_VER_A1; - else if (strncmp(fw_info->hw_version, "A2", sizeof("A2")) == 0) - *hw_ver = VNIC_DEV_HW_VER_A2; - else - *hw_ver = VNIC_DEV_HW_VER_UNKNOWN; - - return 0; -} - int vnic_dev_spec(struct vnic_dev *vdev, unsigned int offset, unsigned int size, void *value) { diff --git a/drivers/net/enic/vnic_dev.h b/drivers/net/enic/vnic_dev.h index 05f9a24..e837546 100644 --- a/drivers/net/enic/vnic_dev.h +++ b/drivers/net/enic/vnic_dev.h @@ -44,12 +44,6 @@ static inline void writeq(u64 val, void __iomem *reg) #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -enum vnic_dev_hw_version { - VNIC_DEV_HW_VER_UNKNOWN, - VNIC_DEV_HW_VER_A1, - VNIC_DEV_HW_VER_A2, -}; - enum vnic_dev_intr_mode { VNIC_DEV_INTR_MODE_UNKNOWN, VNIC_DEV_INTR_MODE_INTX, @@ -93,8 +87,6 @@ int vnic_dev_cmd(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, u64 *a0, u64 *a1, int wait); int vnic_dev_fw_info(struct vnic_dev *vdev, struct vnic_devcmd_fw_info **fw_info); -int vnic_dev_hw_version(struct vnic_dev *vdev, - enum vnic_dev_hw_version *hw_ver); int vnic_dev_spec(struct vnic_dev *vdev, unsigned int offset, unsigned int size, void *value); int vnic_dev_stats_dump(struct vnic_dev *vdev, struct vnic_stats **stats); diff --git a/drivers/net/enic/vnic_rq.h b/drivers/net/enic/vnic_rq.h index 37f08de..2056586 100644 --- a/drivers/net/enic/vnic_rq.h +++ b/drivers/net/enic/vnic_rq.h @@ -141,11 +141,6 @@ static inline void vnic_rq_post(struct vnic_rq *rq, } } -static inline int vnic_rq_posting_soon(struct vnic_rq *rq) -{ - return (rq->to_use->index & VNIC_RQ_RETURN_RATE) == 0; -} - static inline void vnic_rq_return_descs(struct vnic_rq *rq, unsigned int count) { rq->ring.desc_avail += count; diff --git a/drivers/net/fec.c b/drivers/net/fec.c index 2a71373..74798be 100644 --- a/drivers/net/fec.c +++ b/drivers/net/fec.c @@ -54,7 +54,7 @@ #include "fec.h" -#if defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) +#if defined(CONFIG_ARM) #define FEC_ALIGNMENT 0xf #else #define FEC_ALIGNMENT 0x3 @@ -147,8 +147,7 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); * account when setting it. */ #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || \ - defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) #define OPT_FRAME_SIZE (PKT_MAXBUF_SIZE << 16) #else #define OPT_FRAME_SIZE 0 @@ -183,7 +182,7 @@ struct fec_enet_private { struct bufdesc *rx_bd_base; struct bufdesc *tx_bd_base; /* The next free ring entry */ - struct bufdesc *cur_rx, *cur_tx; + struct bufdesc *cur_rx, *cur_tx; /* The ring entries to be free()ed */ struct bufdesc *dirty_tx; @@ -191,28 +190,21 @@ struct fec_enet_private { /* hold while accessing the HW like ringbuffer for tx/rx but not MAC */ spinlock_t hw_lock; - struct platform_device *pdev; + struct platform_device *pdev; int opened; /* Phylib and MDIO interface */ - struct mii_bus *mii_bus; - struct phy_device *phy_dev; - int mii_timeout; - uint phy_speed; + struct mii_bus *mii_bus; + struct phy_device *phy_dev; + int mii_timeout; + uint phy_speed; phy_interface_t phy_interface; int link; int full_duplex; struct completion mdio_done; }; -static irqreturn_t fec_enet_interrupt(int irq, void * dev_id); -static void fec_enet_tx(struct net_device *dev); -static void fec_enet_rx(struct net_device *dev); -static int fec_enet_close(struct net_device *dev); -static void fec_restart(struct net_device *dev, int duplex); -static void fec_stop(struct net_device *dev); - /* FEC MII MMFR bits definition */ #define FEC_MMFR_ST (1 << 30) #define FEC_MMFR_OP_READ (2 << 28) @@ -239,9 +231,9 @@ static void *swap_buffer(void *bufaddr, int len) } static netdev_tx_t -fec_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) +fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); const struct platform_device_id *id_entry = platform_get_device_id(fep->pdev); struct bufdesc *bdp; @@ -262,9 +254,9 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) if (status & BD_ENET_TX_READY) { /* Ooops. All transmit buffers are full. Bail out. - * This should not happen, since dev->tbusy should be set. + * This should not happen, since ndev->tbusy should be set. */ - printk("%s: tx queue full!.\n", dev->name); + printk("%s: tx queue full!.\n", ndev->name); spin_unlock_irqrestore(&fep->hw_lock, flags); return NETDEV_TX_BUSY; } @@ -284,7 +276,7 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) if (((unsigned long) bufaddr) & FEC_ALIGNMENT) { unsigned int index; index = bdp - fep->tx_bd_base; - memcpy(fep->tx_bounce[index], (void *)skb->data, skb->len); + memcpy(fep->tx_bounce[index], skb->data, skb->len); bufaddr = fep->tx_bounce[index]; } @@ -299,13 +291,13 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Save skb pointer */ fep->tx_skbuff[fep->skb_cur] = skb; - dev->stats.tx_bytes += skb->len; + ndev->stats.tx_bytes += skb->len; fep->skb_cur = (fep->skb_cur+1) & TX_RING_MOD_MASK; /* Push the data cache so the CPM does not get stale memory * data. */ - bdp->cbd_bufaddr = dma_map_single(&dev->dev, bufaddr, + bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr, FEC_ENET_TX_FRSIZE, DMA_TO_DEVICE); /* Send it on its way. Tell FEC it's ready, interrupt when done, @@ -326,7 +318,7 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) if (bdp == fep->dirty_tx) { fep->tx_full = 1; - netif_stop_queue(dev); + netif_stop_queue(ndev); } fep->cur_tx = bdp; @@ -336,62 +328,170 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +/* This function is called to start or restart the FEC during a link + * change. This only happens when switching between half and full + * duplex. + */ static void -fec_timeout(struct net_device *dev) +fec_restart(struct net_device *ndev, int duplex) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); + const struct platform_device_id *id_entry = + platform_get_device_id(fep->pdev); + int i; + u32 temp_mac[2]; + u32 rcntl = OPT_FRAME_SIZE | 0x04; - dev->stats.tx_errors++; + /* Whack a reset. We should wait for this. */ + writel(1, fep->hwp + FEC_ECNTRL); + udelay(10); - fec_restart(dev, fep->full_duplex); - netif_wake_queue(dev); -} + /* + * enet-mac reset will reset mac address registers too, + * so need to reconfigure it. + */ + if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) { + memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN); + writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW); + writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH); + } -static irqreturn_t -fec_enet_interrupt(int irq, void * dev_id) -{ - struct net_device *dev = dev_id; - struct fec_enet_private *fep = netdev_priv(dev); - uint int_events; - irqreturn_t ret = IRQ_NONE; + /* Clear any outstanding interrupt. */ + writel(0xffc00000, fep->hwp + FEC_IEVENT); - do { - int_events = readl(fep->hwp + FEC_IEVENT); - writel(int_events, fep->hwp + FEC_IEVENT); + /* Reset all multicast. */ + writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); + writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW); +#ifndef CONFIG_M5272 + writel(0, fep->hwp + FEC_HASH_TABLE_HIGH); + writel(0, fep->hwp + FEC_HASH_TABLE_LOW); +#endif - if (int_events & FEC_ENET_RXF) { - ret = IRQ_HANDLED; - fec_enet_rx(dev); - } + /* Set maximum receive buffer size. */ + writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE); - /* Transmit OK, or non-fatal error. Update the buffer - * descriptors. FEC handles all errors, we just discover - * them as part of the transmit process. - */ - if (int_events & FEC_ENET_TXF) { - ret = IRQ_HANDLED; - fec_enet_tx(dev); + /* Set receive and transmit descriptor base. */ + writel(fep->bd_dma, fep->hwp + FEC_R_DES_START); + writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc) * RX_RING_SIZE, + fep->hwp + FEC_X_DES_START); + + fep->dirty_tx = fep->cur_tx = fep->tx_bd_base; + fep->cur_rx = fep->rx_bd_base; + + /* Reset SKB transmit buffers. */ + fep->skb_cur = fep->skb_dirty = 0; + for (i = 0; i <= TX_RING_MOD_MASK; i++) { + if (fep->tx_skbuff[i]) { + dev_kfree_skb_any(fep->tx_skbuff[i]); + fep->tx_skbuff[i] = NULL; } + } - if (int_events & FEC_ENET_MII) { - ret = IRQ_HANDLED; - complete(&fep->mdio_done); + /* Enable MII mode */ + if (duplex) { + /* FD enable */ + writel(0x04, fep->hwp + FEC_X_CNTRL); + } else { + /* No Rcv on Xmit */ + rcntl |= 0x02; + writel(0x0, fep->hwp + FEC_X_CNTRL); + } + + fep->full_duplex = duplex; + + /* Set MII speed */ + writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); + + /* + * The phy interface and speed need to get configured + * differently on enet-mac. + */ + if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) { + /* Enable flow control and length check */ + rcntl |= 0x40000000 | 0x00000020; + + /* MII or RMII */ + if (fep->phy_interface == PHY_INTERFACE_MODE_RMII) + rcntl |= (1 << 8); + else + rcntl &= ~(1 << 8); + + /* 10M or 100M */ + if (fep->phy_dev && fep->phy_dev->speed == SPEED_100) + rcntl &= ~(1 << 9); + else + rcntl |= (1 << 9); + + } else { +#ifdef FEC_MIIGSK_ENR + if (fep->phy_interface == PHY_INTERFACE_MODE_RMII) { + /* disable the gasket and wait */ + writel(0, fep->hwp + FEC_MIIGSK_ENR); + while (readl(fep->hwp + FEC_MIIGSK_ENR) & 4) + udelay(1); + + /* + * configure the gasket: + * RMII, 50 MHz, no loopback, no echo + */ + writel(1, fep->hwp + FEC_MIIGSK_CFGR); + + /* re-enable the gasket */ + writel(2, fep->hwp + FEC_MIIGSK_ENR); } - } while (int_events); +#endif + } + writel(rcntl, fep->hwp + FEC_R_CNTRL); - return ret; + /* And last, enable the transmit and receive processing */ + writel(2, fep->hwp + FEC_ECNTRL); + writel(0, fep->hwp + FEC_R_DES_ACTIVE); + + /* Enable interrupts we wish to service */ + writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); +} + +static void +fec_stop(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + /* We cannot expect a graceful transmit stop without link !!! */ + if (fep->link) { + writel(1, fep->hwp + FEC_X_CNTRL); /* Graceful transmit stop */ + udelay(10); + if (!(readl(fep->hwp + FEC_IEVENT) & FEC_ENET_GRA)) + printk("fec_stop : Graceful transmit stop did not complete !\n"); + } + + /* Whack a reset. We should wait for this. */ + writel(1, fep->hwp + FEC_ECNTRL); + udelay(10); + writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); + writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); } static void -fec_enet_tx(struct net_device *dev) +fec_timeout(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + ndev->stats.tx_errors++; + + fec_restart(ndev, fep->full_duplex); + netif_wake_queue(ndev); +} + +static void +fec_enet_tx(struct net_device *ndev) { struct fec_enet_private *fep; struct bufdesc *bdp; unsigned short status; struct sk_buff *skb; - fep = netdev_priv(dev); + fep = netdev_priv(ndev); spin_lock(&fep->hw_lock); bdp = fep->dirty_tx; @@ -399,7 +499,8 @@ fec_enet_tx(struct net_device *dev) if (bdp == fep->cur_tx && fep->tx_full == 0) break; - dma_unmap_single(&dev->dev, bdp->cbd_bufaddr, FEC_ENET_TX_FRSIZE, DMA_TO_DEVICE); + dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, + FEC_ENET_TX_FRSIZE, DMA_TO_DEVICE); bdp->cbd_bufaddr = 0; skb = fep->tx_skbuff[fep->skb_dirty]; @@ -407,19 +508,19 @@ fec_enet_tx(struct net_device *dev) if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC | BD_ENET_TX_RL | BD_ENET_TX_UN | BD_ENET_TX_CSL)) { - dev->stats.tx_errors++; + ndev->stats.tx_errors++; if (status & BD_ENET_TX_HB) /* No heartbeat */ - dev->stats.tx_heartbeat_errors++; + ndev->stats.tx_heartbeat_errors++; if (status & BD_ENET_TX_LC) /* Late collision */ - dev->stats.tx_window_errors++; + ndev->stats.tx_window_errors++; if (status & BD_ENET_TX_RL) /* Retrans limit */ - dev->stats.tx_aborted_errors++; + ndev->stats.tx_aborted_errors++; if (status & BD_ENET_TX_UN) /* Underrun */ - dev->stats.tx_fifo_errors++; + ndev->stats.tx_fifo_errors++; if (status & BD_ENET_TX_CSL) /* Carrier lost */ - dev->stats.tx_carrier_errors++; + ndev->stats.tx_carrier_errors++; } else { - dev->stats.tx_packets++; + ndev->stats.tx_packets++; } if (status & BD_ENET_TX_READY) @@ -429,7 +530,7 @@ fec_enet_tx(struct net_device *dev) * but we eventually sent the packet OK. */ if (status & BD_ENET_TX_DEF) - dev->stats.collisions++; + ndev->stats.collisions++; /* Free the sk buffer associated with this last transmit */ dev_kfree_skb_any(skb); @@ -446,8 +547,8 @@ fec_enet_tx(struct net_device *dev) */ if (fep->tx_full) { fep->tx_full = 0; - if (netif_queue_stopped(dev)) - netif_wake_queue(dev); + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); } } fep->dirty_tx = bdp; @@ -461,9 +562,9 @@ fec_enet_tx(struct net_device *dev) * effectively tossing the packet. */ static void -fec_enet_rx(struct net_device *dev) +fec_enet_rx(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); const struct platform_device_id *id_entry = platform_get_device_id(fep->pdev); struct bufdesc *bdp; @@ -497,17 +598,17 @@ fec_enet_rx(struct net_device *dev) /* Check for errors. */ if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO | BD_ENET_RX_CR | BD_ENET_RX_OV)) { - dev->stats.rx_errors++; + ndev->stats.rx_errors++; if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH)) { /* Frame too long or too short. */ - dev->stats.rx_length_errors++; + ndev->stats.rx_length_errors++; } if (status & BD_ENET_RX_NO) /* Frame alignment */ - dev->stats.rx_frame_errors++; + ndev->stats.rx_frame_errors++; if (status & BD_ENET_RX_CR) /* CRC Error */ - dev->stats.rx_crc_errors++; + ndev->stats.rx_crc_errors++; if (status & BD_ENET_RX_OV) /* FIFO overrun */ - dev->stats.rx_fifo_errors++; + ndev->stats.rx_fifo_errors++; } /* Report late collisions as a frame error. @@ -515,19 +616,19 @@ fec_enet_rx(struct net_device *dev) * have in the buffer. So, just drop this frame on the floor. */ if (status & BD_ENET_RX_CL) { - dev->stats.rx_errors++; - dev->stats.rx_frame_errors++; + ndev->stats.rx_errors++; + ndev->stats.rx_frame_errors++; goto rx_processing_done; } /* Process the incoming frame. */ - dev->stats.rx_packets++; + ndev->stats.rx_packets++; pkt_len = bdp->cbd_datlen; - dev->stats.rx_bytes += pkt_len; + ndev->stats.rx_bytes += pkt_len; data = (__u8*)__va(bdp->cbd_bufaddr); - dma_unmap_single(NULL, bdp->cbd_bufaddr, bdp->cbd_datlen, - DMA_FROM_DEVICE); + dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, + FEC_ENET_TX_FRSIZE, DMA_FROM_DEVICE); if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) swap_buffer(data, pkt_len); @@ -541,18 +642,18 @@ fec_enet_rx(struct net_device *dev) if (unlikely(!skb)) { printk("%s: Memory squeeze, dropping packet.\n", - dev->name); - dev->stats.rx_dropped++; + ndev->name); + ndev->stats.rx_dropped++; } else { skb_reserve(skb, NET_IP_ALIGN); skb_put(skb, pkt_len - 4); /* Make room */ skb_copy_to_linear_data(skb, data, pkt_len - 4); - skb->protocol = eth_type_trans(skb, dev); + skb->protocol = eth_type_trans(skb, ndev); netif_rx(skb); } - bdp->cbd_bufaddr = dma_map_single(NULL, data, bdp->cbd_datlen, - DMA_FROM_DEVICE); + bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, data, + FEC_ENET_TX_FRSIZE, DMA_FROM_DEVICE); rx_processing_done: /* Clear the status flags for this buffer */ status &= ~BD_ENET_RX_STATS; @@ -577,10 +678,47 @@ rx_processing_done: spin_unlock(&fep->hw_lock); } +static irqreturn_t +fec_enet_interrupt(int irq, void *dev_id) +{ + struct net_device *ndev = dev_id; + struct fec_enet_private *fep = netdev_priv(ndev); + uint int_events; + irqreturn_t ret = IRQ_NONE; + + do { + int_events = readl(fep->hwp + FEC_IEVENT); + writel(int_events, fep->hwp + FEC_IEVENT); + + if (int_events & FEC_ENET_RXF) { + ret = IRQ_HANDLED; + fec_enet_rx(ndev); + } + + /* Transmit OK, or non-fatal error. Update the buffer + * descriptors. FEC handles all errors, we just discover + * them as part of the transmit process. + */ + if (int_events & FEC_ENET_TXF) { + ret = IRQ_HANDLED; + fec_enet_tx(ndev); + } + + if (int_events & FEC_ENET_MII) { + ret = IRQ_HANDLED; + complete(&fep->mdio_done); + } + } while (int_events); + + return ret; +} + + + /* ------------------------------------------------------------------------- */ -static void __inline__ fec_get_mac(struct net_device *dev) +static void __inline__ fec_get_mac(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct fec_platform_data *pdata = fep->pdev->dev.platform_data; unsigned char *iap, tmpaddr[ETH_ALEN]; @@ -616,11 +754,11 @@ static void __inline__ fec_get_mac(struct net_device *dev) iap = &tmpaddr[0]; } - memcpy(dev->dev_addr, iap, ETH_ALEN); + memcpy(ndev->dev_addr, iap, ETH_ALEN); /* Adjust MAC if using macaddr */ if (iap == macaddr) - dev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->pdev->id; + ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->pdev->id; } /* ------------------------------------------------------------------------- */ @@ -628,9 +766,9 @@ static void __inline__ fec_get_mac(struct net_device *dev) /* * Phy section */ -static void fec_enet_adjust_link(struct net_device *dev) +static void fec_enet_adjust_link(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct phy_device *phy_dev = fep->phy_dev; unsigned long flags; @@ -647,7 +785,7 @@ static void fec_enet_adjust_link(struct net_device *dev) /* Duplex link change */ if (phy_dev->link) { if (fep->full_duplex != phy_dev->duplex) { - fec_restart(dev, phy_dev->duplex); + fec_restart(ndev, phy_dev->duplex); status_change = 1; } } @@ -656,9 +794,9 @@ static void fec_enet_adjust_link(struct net_device *dev) if (phy_dev->link != fep->link) { fep->link = phy_dev->link; if (phy_dev->link) - fec_restart(dev, phy_dev->duplex); + fec_restart(ndev, phy_dev->duplex); else - fec_stop(dev); + fec_stop(ndev); status_change = 1; } @@ -727,9 +865,9 @@ static int fec_enet_mdio_reset(struct mii_bus *bus) return 0; } -static int fec_enet_mii_probe(struct net_device *dev) +static int fec_enet_mii_probe(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct phy_device *phy_dev = NULL; char mdio_bus_id[MII_BUS_ID_SIZE]; char phy_name[MII_BUS_ID_SIZE + 3]; @@ -754,16 +892,16 @@ static int fec_enet_mii_probe(struct net_device *dev) if (phy_id >= PHY_MAX_ADDR) { printk(KERN_INFO "%s: no PHY, assuming direct connection " - "to switch\n", dev->name); + "to switch\n", ndev->name); strncpy(mdio_bus_id, "0", MII_BUS_ID_SIZE); phy_id = 0; } snprintf(phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT, mdio_bus_id, phy_id); - phy_dev = phy_connect(dev, phy_name, &fec_enet_adjust_link, 0, + phy_dev = phy_connect(ndev, phy_name, &fec_enet_adjust_link, 0, PHY_INTERFACE_MODE_MII); if (IS_ERR(phy_dev)) { - printk(KERN_ERR "%s: could not attach to PHY\n", dev->name); + printk(KERN_ERR "%s: could not attach to PHY\n", ndev->name); return PTR_ERR(phy_dev); } @@ -776,7 +914,7 @@ static int fec_enet_mii_probe(struct net_device *dev) fep->full_duplex = 0; printk(KERN_INFO "%s: Freescale FEC PHY driver [%s] " - "(mii_bus:phy_addr=%s, irq=%d)\n", dev->name, + "(mii_bus:phy_addr=%s, irq=%d)\n", ndev->name, fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev), fep->phy_dev->irq); @@ -786,8 +924,8 @@ static int fec_enet_mii_probe(struct net_device *dev) static int fec_enet_mii_init(struct platform_device *pdev) { static struct mii_bus *fec0_mii_bus; - struct net_device *dev = platform_get_drvdata(pdev); - struct fec_enet_private *fep = netdev_priv(dev); + struct net_device *ndev = platform_get_drvdata(pdev); + struct fec_enet_private *fep = netdev_priv(ndev); const struct platform_device_id *id_entry = platform_get_device_id(fep->pdev); int err = -ENXIO, i; @@ -845,7 +983,7 @@ static int fec_enet_mii_init(struct platform_device *pdev) for (i = 0; i < PHY_MAX_ADDR; i++) fep->mii_bus->irq[i] = PHY_POLL; - platform_set_drvdata(dev, fep->mii_bus); + platform_set_drvdata(ndev, fep->mii_bus); if (mdiobus_register(fep->mii_bus)) goto err_out_free_mdio_irq; @@ -873,10 +1011,10 @@ static void fec_enet_mii_remove(struct fec_enet_private *fep) mdiobus_free(fep->mii_bus); } -static int fec_enet_get_settings(struct net_device *dev, +static int fec_enet_get_settings(struct net_device *ndev, struct ethtool_cmd *cmd) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct phy_device *phydev = fep->phy_dev; if (!phydev) @@ -885,10 +1023,10 @@ static int fec_enet_get_settings(struct net_device *dev, return phy_ethtool_gset(phydev, cmd); } -static int fec_enet_set_settings(struct net_device *dev, +static int fec_enet_set_settings(struct net_device *ndev, struct ethtool_cmd *cmd) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct phy_device *phydev = fep->phy_dev; if (!phydev) @@ -897,14 +1035,14 @@ static int fec_enet_set_settings(struct net_device *dev, return phy_ethtool_sset(phydev, cmd); } -static void fec_enet_get_drvinfo(struct net_device *dev, +static void fec_enet_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); strcpy(info->driver, fep->pdev->dev.driver->name); strcpy(info->version, "Revision: 1.0"); - strcpy(info->bus_info, dev_name(&dev->dev)); + strcpy(info->bus_info, dev_name(&ndev->dev)); } static struct ethtool_ops fec_enet_ethtool_ops = { @@ -914,12 +1052,12 @@ static struct ethtool_ops fec_enet_ethtool_ops = { .get_link = ethtool_op_get_link, }; -static int fec_enet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct phy_device *phydev = fep->phy_dev; - if (!netif_running(dev)) + if (!netif_running(ndev)) return -EINVAL; if (!phydev) @@ -928,9 +1066,9 @@ static int fec_enet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return phy_mii_ioctl(phydev, rq, cmd); } -static void fec_enet_free_buffers(struct net_device *dev) +static void fec_enet_free_buffers(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); int i; struct sk_buff *skb; struct bufdesc *bdp; @@ -940,7 +1078,7 @@ static void fec_enet_free_buffers(struct net_device *dev) skb = fep->rx_skbuff[i]; if (bdp->cbd_bufaddr) - dma_unmap_single(&dev->dev, bdp->cbd_bufaddr, + dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE); if (skb) dev_kfree_skb(skb); @@ -952,9 +1090,9 @@ static void fec_enet_free_buffers(struct net_device *dev) kfree(fep->tx_bounce[i]); } -static int fec_enet_alloc_buffers(struct net_device *dev) +static int fec_enet_alloc_buffers(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); int i; struct sk_buff *skb; struct bufdesc *bdp; @@ -963,12 +1101,12 @@ static int fec_enet_alloc_buffers(struct net_device *dev) for (i = 0; i < RX_RING_SIZE; i++) { skb = dev_alloc_skb(FEC_ENET_RX_FRSIZE); if (!skb) { - fec_enet_free_buffers(dev); + fec_enet_free_buffers(ndev); return -ENOMEM; } fep->rx_skbuff[i] = skb; - bdp->cbd_bufaddr = dma_map_single(&dev->dev, skb->data, + bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data, FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE); bdp->cbd_sc = BD_ENET_RX_EMPTY; bdp++; @@ -995,45 +1133,47 @@ static int fec_enet_alloc_buffers(struct net_device *dev) } static int -fec_enet_open(struct net_device *dev) +fec_enet_open(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); int ret; /* I should reset the ring buffers here, but I don't yet know * a simple way to do that. */ - ret = fec_enet_alloc_buffers(dev); + ret = fec_enet_alloc_buffers(ndev); if (ret) return ret; /* Probe and connect to PHY when open the interface */ - ret = fec_enet_mii_probe(dev); + ret = fec_enet_mii_probe(ndev); if (ret) { - fec_enet_free_buffers(dev); + fec_enet_free_buffers(ndev); return ret; } phy_start(fep->phy_dev); - netif_start_queue(dev); + netif_start_queue(ndev); fep->opened = 1; return 0; } static int -fec_enet_close(struct net_device *dev) +fec_enet_close(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); /* Don't know what to do yet. */ fep->opened = 0; - netif_stop_queue(dev); - fec_stop(dev); + netif_stop_queue(ndev); + fec_stop(ndev); - if (fep->phy_dev) + if (fep->phy_dev) { + phy_stop(fep->phy_dev); phy_disconnect(fep->phy_dev); + } - fec_enet_free_buffers(dev); + fec_enet_free_buffers(ndev); return 0; } @@ -1051,14 +1191,14 @@ fec_enet_close(struct net_device *dev) #define HASH_BITS 6 /* #bits in hash */ #define CRC32_POLY 0xEDB88320 -static void set_multicast_list(struct net_device *dev) +static void set_multicast_list(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct netdev_hw_addr *ha; unsigned int i, bit, data, crc, tmp; unsigned char hash; - if (dev->flags & IFF_PROMISC) { + if (ndev->flags & IFF_PROMISC) { tmp = readl(fep->hwp + FEC_R_CNTRL); tmp |= 0x8; writel(tmp, fep->hwp + FEC_R_CNTRL); @@ -1069,7 +1209,7 @@ static void set_multicast_list(struct net_device *dev) tmp &= ~0x8; writel(tmp, fep->hwp + FEC_R_CNTRL); - if (dev->flags & IFF_ALLMULTI) { + if (ndev->flags & IFF_ALLMULTI) { /* Catch all multicast addresses, so set the * filter to all 1's */ @@ -1084,7 +1224,7 @@ static void set_multicast_list(struct net_device *dev) writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW); - netdev_for_each_mc_addr(ha, dev) { + netdev_for_each_mc_addr(ha, ndev) { /* Only support group multicast for now */ if (!(ha->addr[0] & 1)) continue; @@ -1092,7 +1232,7 @@ static void set_multicast_list(struct net_device *dev) /* calculate crc32 value of mac address */ crc = 0xffffffff; - for (i = 0; i < dev->addr_len; i++) { + for (i = 0; i < ndev->addr_len; i++) { data = ha->addr[i]; for (bit = 0; bit < 8; bit++, data >>= 1) { crc = (crc >> 1) ^ @@ -1119,20 +1259,20 @@ static void set_multicast_list(struct net_device *dev) /* Set a MAC change in hardware. */ static int -fec_set_mac_address(struct net_device *dev, void *p) +fec_set_mac_address(struct net_device *ndev, void *p) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + memcpy(ndev->dev_addr, addr->sa_data, ndev->addr_len); - writel(dev->dev_addr[3] | (dev->dev_addr[2] << 8) | - (dev->dev_addr[1] << 16) | (dev->dev_addr[0] << 24), + writel(ndev->dev_addr[3] | (ndev->dev_addr[2] << 8) | + (ndev->dev_addr[1] << 16) | (ndev->dev_addr[0] << 24), fep->hwp + FEC_ADDR_LOW); - writel((dev->dev_addr[5] << 16) | (dev->dev_addr[4] << 24), + writel((ndev->dev_addr[5] << 16) | (ndev->dev_addr[4] << 24), fep->hwp + FEC_ADDR_HIGH); return 0; } @@ -1146,16 +1286,16 @@ static const struct net_device_ops fec_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = fec_timeout, .ndo_set_mac_address = fec_set_mac_address, - .ndo_do_ioctl = fec_enet_ioctl, + .ndo_do_ioctl = fec_enet_ioctl, }; /* * XXX: We need to clean up on failure exits here. * */ -static int fec_enet_init(struct net_device *dev) +static int fec_enet_init(struct net_device *ndev) { - struct fec_enet_private *fep = netdev_priv(dev); + struct fec_enet_private *fep = netdev_priv(ndev); struct bufdesc *cbd_base; struct bufdesc *bdp; int i; @@ -1170,20 +1310,19 @@ static int fec_enet_init(struct net_device *dev) spin_lock_init(&fep->hw_lock); - fep->hwp = (void __iomem *)dev->base_addr; - fep->netdev = dev; + fep->netdev = ndev; /* Get the Ethernet address */ - fec_get_mac(dev); + fec_get_mac(ndev); /* Set receive and transmit descriptor base. */ fep->rx_bd_base = cbd_base; fep->tx_bd_base = cbd_base + RX_RING_SIZE; /* The FEC Ethernet specific entries in the device structure */ - dev->watchdog_timeo = TX_TIMEOUT; - dev->netdev_ops = &fec_netdev_ops; - dev->ethtool_ops = &fec_enet_ethtool_ops; + ndev->watchdog_timeo = TX_TIMEOUT; + ndev->netdev_ops = &fec_netdev_ops; + ndev->ethtool_ops = &fec_enet_ethtool_ops; /* Initialize the receive buffer descriptors. */ bdp = fep->rx_bd_base; @@ -1212,152 +1351,11 @@ static int fec_enet_init(struct net_device *dev) bdp--; bdp->cbd_sc |= BD_SC_WRAP; - fec_restart(dev, 0); + fec_restart(ndev, 0); return 0; } -/* This function is called to start or restart the FEC during a link - * change. This only happens when switching between half and full - * duplex. - */ -static void -fec_restart(struct net_device *dev, int duplex) -{ - struct fec_enet_private *fep = netdev_priv(dev); - const struct platform_device_id *id_entry = - platform_get_device_id(fep->pdev); - int i; - u32 val, temp_mac[2]; - - /* Whack a reset. We should wait for this. */ - writel(1, fep->hwp + FEC_ECNTRL); - udelay(10); - - /* - * enet-mac reset will reset mac address registers too, - * so need to reconfigure it. - */ - if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) { - memcpy(&temp_mac, dev->dev_addr, ETH_ALEN); - writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW); - writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH); - } - - /* Clear any outstanding interrupt. */ - writel(0xffc00000, fep->hwp + FEC_IEVENT); - - /* Reset all multicast. */ - writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); - writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW); -#ifndef CONFIG_M5272 - writel(0, fep->hwp + FEC_HASH_TABLE_HIGH); - writel(0, fep->hwp + FEC_HASH_TABLE_LOW); -#endif - - /* Set maximum receive buffer size. */ - writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE); - - /* Set receive and transmit descriptor base. */ - writel(fep->bd_dma, fep->hwp + FEC_R_DES_START); - writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc) * RX_RING_SIZE, - fep->hwp + FEC_X_DES_START); - - fep->dirty_tx = fep->cur_tx = fep->tx_bd_base; - fep->cur_rx = fep->rx_bd_base; - - /* Reset SKB transmit buffers. */ - fep->skb_cur = fep->skb_dirty = 0; - for (i = 0; i <= TX_RING_MOD_MASK; i++) { - if (fep->tx_skbuff[i]) { - dev_kfree_skb_any(fep->tx_skbuff[i]); - fep->tx_skbuff[i] = NULL; - } - } - - /* Enable MII mode */ - if (duplex) { - /* MII enable / FD enable */ - writel(OPT_FRAME_SIZE | 0x04, fep->hwp + FEC_R_CNTRL); - writel(0x04, fep->hwp + FEC_X_CNTRL); - } else { - /* MII enable / No Rcv on Xmit */ - writel(OPT_FRAME_SIZE | 0x06, fep->hwp + FEC_R_CNTRL); - writel(0x0, fep->hwp + FEC_X_CNTRL); - } - fep->full_duplex = duplex; - - /* Set MII speed */ - writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); - - /* - * The phy interface and speed need to get configured - * differently on enet-mac. - */ - if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) { - val = readl(fep->hwp + FEC_R_CNTRL); - - /* MII or RMII */ - if (fep->phy_interface == PHY_INTERFACE_MODE_RMII) - val |= (1 << 8); - else - val &= ~(1 << 8); - - /* 10M or 100M */ - if (fep->phy_dev && fep->phy_dev->speed == SPEED_100) - val &= ~(1 << 9); - else - val |= (1 << 9); - - writel(val, fep->hwp + FEC_R_CNTRL); - } else { -#ifdef FEC_MIIGSK_ENR - if (fep->phy_interface == PHY_INTERFACE_MODE_RMII) { - /* disable the gasket and wait */ - writel(0, fep->hwp + FEC_MIIGSK_ENR); - while (readl(fep->hwp + FEC_MIIGSK_ENR) & 4) - udelay(1); - - /* - * configure the gasket: - * RMII, 50 MHz, no loopback, no echo - */ - writel(1, fep->hwp + FEC_MIIGSK_CFGR); - - /* re-enable the gasket */ - writel(2, fep->hwp + FEC_MIIGSK_ENR); - } -#endif - } - - /* And last, enable the transmit and receive processing */ - writel(2, fep->hwp + FEC_ECNTRL); - writel(0, fep->hwp + FEC_R_DES_ACTIVE); - - /* Enable interrupts we wish to service */ - writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); -} - -static void -fec_stop(struct net_device *dev) -{ - struct fec_enet_private *fep = netdev_priv(dev); - - /* We cannot expect a graceful transmit stop without link !!! */ - if (fep->link) { - writel(1, fep->hwp + FEC_X_CNTRL); /* Graceful transmit stop */ - udelay(10); - if (!(readl(fep->hwp + FEC_IEVENT) & FEC_ENET_GRA)) - printk("fec_stop : Graceful transmit stop did not complete !\n"); - } - - /* Whack a reset. We should wait for this. */ - writel(1, fep->hwp + FEC_ECNTRL); - udelay(10); - writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); - writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); -} - static int __devinit fec_probe(struct platform_device *pdev) { @@ -1377,19 +1375,20 @@ fec_probe(struct platform_device *pdev) /* Init network device */ ndev = alloc_etherdev(sizeof(struct fec_enet_private)); - if (!ndev) - return -ENOMEM; + if (!ndev) { + ret = -ENOMEM; + goto failed_alloc_etherdev; + } SET_NETDEV_DEV(ndev, &pdev->dev); /* setup board info structure */ fep = netdev_priv(ndev); - memset(fep, 0, sizeof(*fep)); - ndev->base_addr = (unsigned long)ioremap(r->start, resource_size(r)); + fep->hwp = ioremap(r->start, resource_size(r)); fep->pdev = pdev; - if (!ndev->base_addr) { + if (!fep->hwp) { ret = -ENOMEM; goto failed_ioremap; } @@ -1407,10 +1406,9 @@ fec_probe(struct platform_device *pdev) break; ret = request_irq(irq, fec_enet_interrupt, IRQF_DISABLED, pdev->name, ndev); if (ret) { - while (i >= 0) { + while (--i >= 0) { irq = platform_get_irq(pdev, i); free_irq(irq, ndev); - i--; } goto failed_irq; } @@ -1453,9 +1451,11 @@ failed_clk: free_irq(irq, ndev); } failed_irq: - iounmap((void __iomem *)ndev->base_addr); + iounmap(fep->hwp); failed_ioremap: free_netdev(ndev); +failed_alloc_etherdev: + release_mem_region(r->start, resource_size(r)); return ret; } @@ -1465,16 +1465,22 @@ fec_drv_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - - platform_set_drvdata(pdev, NULL); + struct resource *r; fec_stop(ndev); fec_enet_mii_remove(fep); clk_disable(fep->clk); clk_put(fep->clk); - iounmap((void __iomem *)ndev->base_addr); + iounmap(fep->hwp); unregister_netdev(ndev); free_netdev(ndev); + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + BUG_ON(!r); + release_mem_region(r->start, resource_size(r)); + + platform_set_drvdata(pdev, NULL); + return 0; } @@ -1483,16 +1489,14 @@ static int fec_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); - struct fec_enet_private *fep; + struct fec_enet_private *fep = netdev_priv(ndev); - if (ndev) { - fep = netdev_priv(ndev); - if (netif_running(ndev)) { - fec_stop(ndev); - netif_device_detach(ndev); - } - clk_disable(fep->clk); + if (netif_running(ndev)) { + fec_stop(ndev); + netif_device_detach(ndev); } + clk_disable(fep->clk); + return 0; } @@ -1500,16 +1504,14 @@ static int fec_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); - struct fec_enet_private *fep; + struct fec_enet_private *fep = netdev_priv(ndev); - if (ndev) { - fep = netdev_priv(ndev); - clk_enable(fep->clk); - if (netif_running(ndev)) { - fec_restart(ndev, fep->full_duplex); - netif_device_attach(ndev); - } + clk_enable(fep->clk); + if (netif_running(ndev)) { + fec_restart(ndev, fep->full_duplex); + netif_device_attach(ndev); } + return 0; } diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index ac1d323..8931168 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -400,13 +400,14 @@ static void *bpq_seq_start(struct seq_file *seq, loff_t *pos) static void *bpq_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct list_head *p; + struct bpqdev *bpqdev = v; ++*pos; if (v == SEQ_START_TOKEN) - p = rcu_dereference(bpq_devices.next); + p = rcu_dereference(list_next_rcu(&bpq_devices)); else - p = rcu_dereference(((struct bpqdev *)v)->bpq_list.next); + p = rcu_dereference(list_next_rcu(&bpqdev->bpq_list)); return (p == &bpq_devices) ? NULL : list_entry(p, struct bpqdev, bpq_list); diff --git a/drivers/net/igb/e1000_82575.c b/drivers/net/igb/e1000_82575.c index 0a2368f..65c1833 100644 --- a/drivers/net/igb/e1000_82575.c +++ b/drivers/net/igb/e1000_82575.c @@ -129,6 +129,7 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) break; case E1000_DEV_ID_82580_COPPER: case E1000_DEV_ID_82580_FIBER: + case E1000_DEV_ID_82580_QUAD_FIBER: case E1000_DEV_ID_82580_SERDES: case E1000_DEV_ID_82580_SGMII: case E1000_DEV_ID_82580_COPPER_DUAL: @@ -237,9 +238,15 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) size = 14; nvm->word_size = 1 << size; - /* if 82576 then initialize mailbox parameters */ - if (mac->type == e1000_82576) + /* if part supports SR-IOV then initialize mailbox parameters */ + switch (mac->type) { + case e1000_82576: + case e1000_i350: igb_init_mbx_params_pf(hw); + break; + default: + break; + } /* setup PHY parameters */ if (phy->media_type != e1000_media_type_copper) { diff --git a/drivers/net/igb/e1000_hw.h b/drivers/net/igb/e1000_hw.h index e2638af..281324e 100644 --- a/drivers/net/igb/e1000_hw.h +++ b/drivers/net/igb/e1000_hw.h @@ -54,6 +54,7 @@ struct e1000_hw; #define E1000_DEV_ID_82580_SERDES 0x1510 #define E1000_DEV_ID_82580_SGMII 0x1511 #define E1000_DEV_ID_82580_COPPER_DUAL 0x1516 +#define E1000_DEV_ID_82580_QUAD_FIBER 0x1527 #define E1000_DEV_ID_DH89XXCC_SGMII 0x0438 #define E1000_DEV_ID_DH89XXCC_SERDES 0x043A #define E1000_DEV_ID_DH89XXCC_BACKPLANE 0x043C diff --git a/drivers/net/igb/e1000_mbx.c b/drivers/net/igb/e1000_mbx.c index c474cdb..78d48c7 100644 --- a/drivers/net/igb/e1000_mbx.c +++ b/drivers/net/igb/e1000_mbx.c @@ -422,26 +422,24 @@ s32 igb_init_mbx_params_pf(struct e1000_hw *hw) { struct e1000_mbx_info *mbx = &hw->mbx; - if (hw->mac.type == e1000_82576) { - mbx->timeout = 0; - mbx->usec_delay = 0; - - mbx->size = E1000_VFMAILBOX_SIZE; - - mbx->ops.read = igb_read_mbx_pf; - mbx->ops.write = igb_write_mbx_pf; - mbx->ops.read_posted = igb_read_posted_mbx; - mbx->ops.write_posted = igb_write_posted_mbx; - mbx->ops.check_for_msg = igb_check_for_msg_pf; - mbx->ops.check_for_ack = igb_check_for_ack_pf; - mbx->ops.check_for_rst = igb_check_for_rst_pf; - - mbx->stats.msgs_tx = 0; - mbx->stats.msgs_rx = 0; - mbx->stats.reqs = 0; - mbx->stats.acks = 0; - mbx->stats.rsts = 0; - } + mbx->timeout = 0; + mbx->usec_delay = 0; + + mbx->size = E1000_VFMAILBOX_SIZE; + + mbx->ops.read = igb_read_mbx_pf; + mbx->ops.write = igb_write_mbx_pf; + mbx->ops.read_posted = igb_read_posted_mbx; + mbx->ops.write_posted = igb_write_posted_mbx; + mbx->ops.check_for_msg = igb_check_for_msg_pf; + mbx->ops.check_for_ack = igb_check_for_ack_pf; + mbx->ops.check_for_rst = igb_check_for_rst_pf; + + mbx->stats.msgs_tx = 0; + mbx->stats.msgs_rx = 0; + mbx->stats.reqs = 0; + mbx->stats.acks = 0; + mbx->stats.rsts = 0; return 0; } diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 58c665b..cb6bf7b 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -68,6 +68,7 @@ static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SGMII), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_QUAD_FIBER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SERDES), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SGMII), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER_DUAL), board_82575 }, @@ -2286,9 +2287,14 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter) spin_lock_init(&adapter->stats64_lock); #ifdef CONFIG_PCI_IOV - if (hw->mac.type == e1000_82576) + switch (hw->mac.type) { + case e1000_82576: + case e1000_i350: adapter->vfs_allocated_count = (max_vfs > 7) ? 7 : max_vfs; - + break; + default: + break; + } #endif /* CONFIG_PCI_IOV */ adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES, num_online_cpus()); diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h index 3b8c924..12769b5 100644 --- a/drivers/net/ixgbe/ixgbe.h +++ b/drivers/net/ixgbe/ixgbe.h @@ -334,6 +334,10 @@ struct ixgbe_adapter { u16 bd_number; struct work_struct reset_task; struct ixgbe_q_vector *q_vector[MAX_MSIX_Q_VECTORS]; + + /* DCB parameters */ + struct ieee_pfc *ixgbe_ieee_pfc; + struct ieee_ets *ixgbe_ieee_ets; struct ixgbe_dcb_config dcb_cfg; struct ixgbe_dcb_config temp_dcb_cfg; u8 dcb_set_bitmap; @@ -521,7 +525,6 @@ extern void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *, extern void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16); extern void ixgbe_write_eitr(struct ixgbe_q_vector *); extern int ethtool_ioctl(struct ifreq *ifr); -extern u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 index); extern s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw); extern s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 pballoc); extern s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 pballoc); diff --git a/drivers/net/ixgbe/ixgbe_common.h b/drivers/net/ixgbe/ixgbe_common.h index 66ed045..90cceb4 100644 --- a/drivers/net/ixgbe/ixgbe_common.h +++ b/drivers/net/ixgbe/ixgbe_common.h @@ -29,6 +29,7 @@ #define _IXGBE_COMMON_H_ #include "ixgbe_type.h" +#include "ixgbe.h" u32 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw); s32 ixgbe_init_ops_generic(struct ixgbe_hw *hw); @@ -110,9 +111,8 @@ void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf); #define IXGBE_WRITE_FLUSH(a) IXGBE_READ_REG(a, IXGBE_STATUS) -extern struct net_device *ixgbe_get_hw_dev(struct ixgbe_hw *hw); #define hw_dbg(hw, format, arg...) \ - netdev_dbg(ixgbe_get_hw_dev(hw), format, ##arg) + netdev_dbg(((struct ixgbe_adapter *)(hw->back))->netdev, format, ##arg) #define e_dev_info(format, arg...) \ dev_info(&adapter->pdev->dev, format, ## arg) #define e_dev_warn(format, arg...) \ diff --git a/drivers/net/ixgbe/ixgbe_dcb.c b/drivers/net/ixgbe/ixgbe_dcb.c index d16c260..13c962e 100644 --- a/drivers/net/ixgbe/ixgbe_dcb.c +++ b/drivers/net/ixgbe/ixgbe_dcb.c @@ -34,6 +34,42 @@ #include "ixgbe_dcb_82599.h" /** + * ixgbe_ieee_credits - This calculates the ieee traffic class + * credits from the configured bandwidth percentages. Credits + * are the smallest unit programable into the underlying + * hardware. The IEEE 802.1Qaz specification do not use bandwidth + * groups so this is much simplified from the CEE case. + */ +s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame) +{ + int min_percent = 100; + int min_credit, multiplier; + int i; + + min_credit = ((max_frame / 2) + DCB_CREDIT_QUANTUM - 1) / + DCB_CREDIT_QUANTUM; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if (bw[i] < min_percent && bw[i]) + min_percent = bw[i]; + } + + multiplier = (min_credit / min_percent) + 1; + + /* Find out the hw credits for each TC */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + int val = min(bw[i] * multiplier, MAX_CREDIT_REFILL); + + if (val < min_credit) + val = min_credit; + refill[i] = val; + + max[i] = (bw[i] * MAX_CREDIT)/100; + } + return 0; +} + +/** * ixgbe_dcb_calculate_tc_credits - Calculates traffic class credits * @ixgbe_dcb_config: Struct containing DCB settings. * @direction: Configuring either Tx or Rx. @@ -141,6 +177,59 @@ out: return ret_val; } +void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en) +{ + int i; + + *pfc_en = 0; + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) + *pfc_en |= (cfg->tc_config[i].dcb_pfc & 0xF) << i; +} + +void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *cfg, int direction, + u16 *refill) +{ + struct tc_bw_alloc *p; + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &cfg->tc_config[i].path[direction]; + refill[i] = p->data_credits_refill; + } +} + +void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *cfg, u16 *max) +{ + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) + max[i] = cfg->tc_config[i].desc_credits_max; +} + +void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *cfg, int direction, + u8 *bwgid) +{ + struct tc_bw_alloc *p; + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &cfg->tc_config[i].path[direction]; + bwgid[i] = p->bwg_id; + } +} + +void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *cfg, int direction, + u8 *ptype) +{ + struct tc_bw_alloc *p; + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &cfg->tc_config[i].path[direction]; + ptype[i] = p->prio_type; + } +} + /** * ixgbe_dcb_hw_config - Config and enable DCB * @hw: pointer to hardware structure @@ -152,13 +241,30 @@ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw, struct ixgbe_dcb_config *dcb_config) { s32 ret = 0; + u8 pfc_en; + u8 ptype[MAX_TRAFFIC_CLASS]; + u8 bwgid[MAX_TRAFFIC_CLASS]; + u16 refill[MAX_TRAFFIC_CLASS]; + u16 max[MAX_TRAFFIC_CLASS]; + + /* Unpack CEE standard containers */ + ixgbe_dcb_unpack_pfc(dcb_config, &pfc_en); + ixgbe_dcb_unpack_refill(dcb_config, DCB_TX_CONFIG, refill); + ixgbe_dcb_unpack_max(dcb_config, max); + ixgbe_dcb_unpack_bwgid(dcb_config, DCB_TX_CONFIG, bwgid); + ixgbe_dcb_unpack_prio(dcb_config, DCB_TX_CONFIG, ptype); + switch (hw->mac.type) { case ixgbe_mac_82598EB: - ret = ixgbe_dcb_hw_config_82598(hw, dcb_config); + ret = ixgbe_dcb_hw_config_82598(hw, dcb_config->rx_pba_cfg, + pfc_en, refill, max, bwgid, + ptype); break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: - ret = ixgbe_dcb_hw_config_82599(hw, dcb_config); + ret = ixgbe_dcb_hw_config_82599(hw, dcb_config->rx_pba_cfg, + pfc_en, refill, max, bwgid, + ptype); break; default: break; @@ -166,3 +272,70 @@ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw, return ret; } +/* Helper routines to abstract HW specifics from DCB netlink ops */ +s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en) +{ + int ret = -EINVAL; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + ret = ixgbe_dcb_config_pfc_82598(hw, pfc_en); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + ret = ixgbe_dcb_config_pfc_82599(hw, pfc_en); + break; + default: + break; + } + return ret; +} + +s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw, + u16 *refill, u16 *max, u8 *bwg_id, u8 *tsa) +{ + int i; + u8 prio_type[IEEE_8021QAZ_MAX_TCS]; + + /* Map TSA onto CEE prio type */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + switch (tsa[i]) { + case IEEE_8021QAZ_TSA_STRICT: + prio_type[i] = 2; + break; + case IEEE_8021QAZ_TSA_ETS: + prio_type[i] = 0; + break; + default: + /* Hardware only supports priority strict or + * ETS transmission selection algorithms if + * we receive some other value from dcbnl + * throw an error + */ + return -EINVAL; + } + } + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max, + prio_type); + ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + break; + default: + break; + } + return 0; +} diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h index 1cfe38e..e593511 100644 --- a/drivers/net/ixgbe/ixgbe_dcb.h +++ b/drivers/net/ixgbe/ixgbe_dcb.h @@ -139,7 +139,6 @@ struct ixgbe_dcb_config { struct tc_configuration tc_config[MAX_TRAFFIC_CLASS]; u8 bw_percentage[2][MAX_BW_GROUP]; /* One each for Tx/Rx */ bool pfc_mode_enable; - bool round_robin_enable; enum dcb_rx_pba_cfg rx_pba_cfg; @@ -148,12 +147,21 @@ struct ixgbe_dcb_config { }; /* DCB driver APIs */ +void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en); +void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *, int, u16 *); +void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *, u16 *); +void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *, int, u8 *); +void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *, int, u8 *); /* DCB credits calculation */ +s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame); s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *, struct ixgbe_dcb_config *, int, u8); /* DCB hw initialization */ +s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw, + u16 *refill, u16 *max, u8 *bwg_id, u8 *prio_type); +s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en); s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *); /* DCB definitions for credit calculation */ diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ixgbe/ixgbe_dcb_82598.c index 9a5e89c..2965edc 100644 --- a/drivers/net/ixgbe/ixgbe_dcb_82598.c +++ b/drivers/net/ixgbe/ixgbe_dcb_82598.c @@ -38,15 +38,14 @@ * * Configure packet buffers for DCB mode. */ -static s32 ixgbe_dcb_config_packet_buffers_82598(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +static s32 ixgbe_dcb_config_packet_buffers_82598(struct ixgbe_hw *hw, u8 rx_pba) { s32 ret_val = 0; u32 value = IXGBE_RXPBSIZE_64KB; u8 i = 0; /* Setup Rx packet buffer sizes */ - switch (dcb_config->rx_pba_cfg) { + switch (rx_pba) { case pba_80_48: /* Setup the first four at 80KB */ value = IXGBE_RXPBSIZE_80KB; @@ -78,10 +77,11 @@ static s32 ixgbe_dcb_config_packet_buffers_82598(struct ixgbe_hw *hw, * * Configure Rx Data Arbiter and credits for each traffic class. */ -static s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *prio_type) { - struct tc_bw_alloc *p; u32 reg = 0; u32 credit_refill = 0; u32 credit_max = 0; @@ -102,13 +102,12 @@ static s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, /* Configure traffic class credits and priority */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &dcb_config->tc_config[i].path[DCB_RX_CONFIG]; - credit_refill = p->data_credits_refill; - credit_max = p->data_credits_max; + credit_refill = refill[i]; + credit_max = max[i]; reg = credit_refill | (credit_max << IXGBE_RT2CR_MCL_SHIFT); - if (p->prio_type == prio_link) + if (prio_type[i] == prio_link) reg |= IXGBE_RT2CR_LSP; IXGBE_WRITE_REG(hw, IXGBE_RT2CR(i), reg); @@ -135,10 +134,12 @@ static s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, * * Configure Tx Descriptor Arbiter and credits for each traffic class. */ -static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) { - struct tc_bw_alloc *p; u32 reg, max_credits; u8 i; @@ -146,10 +147,8 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, /* Enable arbiter */ reg &= ~IXGBE_DPMCS_ARBDIS; - if (!(dcb_config->round_robin_enable)) { - /* Enable DFP and Recycle mode */ - reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM); - } + /* Enable DFP and Recycle mode */ + reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM); reg |= IXGBE_DPMCS_TSOEF; /* Configure Max TSO packet size 34KB including payload and headers */ reg |= (0x4 << IXGBE_DPMCS_MTSOS_SHIFT); @@ -158,16 +157,15 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, /* Configure traffic class credits and priority */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG]; - max_credits = dcb_config->tc_config[i].desc_credits_max; + max_credits = max[i]; reg = max_credits << IXGBE_TDTQ2TCCR_MCL_SHIFT; - reg |= p->data_credits_refill; - reg |= (u32)(p->bwg_id) << IXGBE_TDTQ2TCCR_BWG_SHIFT; + reg |= refill[i]; + reg |= (u32)(bwg_id[i]) << IXGBE_TDTQ2TCCR_BWG_SHIFT; - if (p->prio_type == prio_group) + if (prio_type[i] == prio_group) reg |= IXGBE_TDTQ2TCCR_GSP; - if (p->prio_type == prio_link) + if (prio_type[i] == prio_link) reg |= IXGBE_TDTQ2TCCR_LSP; IXGBE_WRITE_REG(hw, IXGBE_TDTQ2TCCR(i), reg); @@ -183,10 +181,12 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, * * Configure Tx Data Arbiter and credits for each traffic class. */ -static s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) { - struct tc_bw_alloc *p; u32 reg; u8 i; @@ -200,15 +200,14 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, /* Configure traffic class credits and priority */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG]; - reg = p->data_credits_refill; - reg |= (u32)(p->data_credits_max) << IXGBE_TDPT2TCCR_MCL_SHIFT; - reg |= (u32)(p->bwg_id) << IXGBE_TDPT2TCCR_BWG_SHIFT; + reg = refill[i]; + reg |= (u32)(max[i]) << IXGBE_TDPT2TCCR_MCL_SHIFT; + reg |= (u32)(bwg_id[i]) << IXGBE_TDPT2TCCR_BWG_SHIFT; - if (p->prio_type == prio_group) + if (prio_type[i] == prio_group) reg |= IXGBE_TDPT2TCCR_GSP; - if (p->prio_type == prio_link) + if (prio_type[i] == prio_link) reg |= IXGBE_TDPT2TCCR_LSP; IXGBE_WRITE_REG(hw, IXGBE_TDPT2TCCR(i), reg); @@ -229,13 +228,12 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, * * Configure Priority Flow Control for each traffic class. */ -s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en) { u32 reg, rx_pba_size; u8 i; - if (!dcb_config->pfc_mode_enable) + if (!pfc_en) goto out; /* Enable Transmit Priority Flow Control */ @@ -256,19 +254,20 @@ s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, * for each traffic class. */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + int enabled = pfc_en & (1 << i); rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT; reg = (rx_pba_size - hw->fc.low_water) << 10; - if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx || - dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full) + if (enabled == pfc_enabled_tx || + enabled == pfc_enabled_full) reg |= IXGBE_FCRTL_XONE; IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), reg); reg = (rx_pba_size - hw->fc.high_water) << 10; - if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx || - dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full) + if (enabled == pfc_enabled_tx || + enabled == pfc_enabled_full) reg |= IXGBE_FCRTH_FCEN; IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg); @@ -292,7 +291,7 @@ out: * Configure queue statistics registers, all queues belonging to same traffic * class uses a single set of queue statistics counters. */ -static s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw) +s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw) { u32 reg = 0; u8 i = 0; @@ -325,13 +324,16 @@ static s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw) * Configure dcb settings and enable dcb mode. */ s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) + u8 rx_pba, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type) { - ixgbe_dcb_config_packet_buffers_82598(hw, dcb_config); - ixgbe_dcb_config_rx_arbiter_82598(hw, dcb_config); - ixgbe_dcb_config_tx_desc_arbiter_82598(hw, dcb_config); - ixgbe_dcb_config_tx_data_arbiter_82598(hw, dcb_config); - ixgbe_dcb_config_pfc_82598(hw, dcb_config); + ixgbe_dcb_config_packet_buffers_82598(hw, rx_pba); + ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max, prio_type); + ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_pfc_82598(hw, pfc_en); ixgbe_dcb_config_tc_stats_82598(hw); return 0; diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.h b/drivers/net/ixgbe/ixgbe_dcb_82598.h index abc03cc..0d2a758 100644 --- a/drivers/net/ixgbe/ixgbe_dcb_82598.h +++ b/drivers/net/ixgbe/ixgbe_dcb_82598.h @@ -71,9 +71,28 @@ /* DCB hardware-specific driver APIs */ /* DCB PFC functions */ -s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *, struct ixgbe_dcb_config *); +s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *, u8 pfc_en); /* DCB hw initialization */ -s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *, struct ixgbe_dcb_config *); +s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *hw, + u8 rx_pba, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type); #endif /* _DCB_82598_CONFIG_H */ diff --git a/drivers/net/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ixgbe/ixgbe_dcb_82599.c index 374e1f7..b0d97a9 100644 --- a/drivers/net/ixgbe/ixgbe_dcb_82599.c +++ b/drivers/net/ixgbe/ixgbe_dcb_82599.c @@ -33,19 +33,18 @@ /** * ixgbe_dcb_config_packet_buffers_82599 - Configure DCB packet buffers * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure + * @rx_pba: method to distribute packet buffer * * Configure packet buffers for DCB mode. */ -static s32 ixgbe_dcb_config_packet_buffers_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +static s32 ixgbe_dcb_config_packet_buffers_82599(struct ixgbe_hw *hw, u8 rx_pba) { s32 ret_val = 0; u32 value = IXGBE_RXPBSIZE_64KB; u8 i = 0; /* Setup Rx packet buffer sizes */ - switch (dcb_config->rx_pba_cfg) { + switch (rx_pba) { case pba_80_48: /* Setup the first four at 80KB */ value = IXGBE_RXPBSIZE_80KB; @@ -75,14 +74,19 @@ static s32 ixgbe_dcb_config_packet_buffers_82599(struct ixgbe_hw *hw, /** * ixgbe_dcb_config_rx_arbiter_82599 - Config Rx Data arbiter * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class * * Configure Rx Packet Arbiter and credits for each traffic class. */ -static s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) { - struct tc_bw_alloc *p; u32 reg = 0; u32 credit_refill = 0; u32 credit_max = 0; @@ -103,15 +107,13 @@ static s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, /* Configure traffic class credits and priority */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &dcb_config->tc_config[i].path[DCB_RX_CONFIG]; - - credit_refill = p->data_credits_refill; - credit_max = p->data_credits_max; + credit_refill = refill[i]; + credit_max = max[i]; reg = credit_refill | (credit_max << IXGBE_RTRPT4C_MCL_SHIFT); - reg |= (u32)(p->bwg_id) << IXGBE_RTRPT4C_BWG_SHIFT; + reg |= (u32)(bwg_id[i]) << IXGBE_RTRPT4C_BWG_SHIFT; - if (p->prio_type == prio_link) + if (prio_type[i] == prio_link) reg |= IXGBE_RTRPT4C_LSP; IXGBE_WRITE_REG(hw, IXGBE_RTRPT4C(i), reg); @@ -130,14 +132,19 @@ static s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, /** * ixgbe_dcb_config_tx_desc_arbiter_82599 - Config Tx Desc. arbiter * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class * * Configure Tx Descriptor Arbiter and credits for each traffic class. */ -static s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) { - struct tc_bw_alloc *p; u32 reg, max_credits; u8 i; @@ -149,16 +156,15 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, /* Configure traffic class credits and priority */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG]; - max_credits = dcb_config->tc_config[i].desc_credits_max; + max_credits = max[i]; reg = max_credits << IXGBE_RTTDT2C_MCL_SHIFT; - reg |= p->data_credits_refill; - reg |= (u32)(p->bwg_id) << IXGBE_RTTDT2C_BWG_SHIFT; + reg |= refill[i]; + reg |= (u32)(bwg_id[i]) << IXGBE_RTTDT2C_BWG_SHIFT; - if (p->prio_type == prio_group) + if (prio_type[i] == prio_group) reg |= IXGBE_RTTDT2C_GSP; - if (p->prio_type == prio_link) + if (prio_type[i] == prio_link) reg |= IXGBE_RTTDT2C_LSP; IXGBE_WRITE_REG(hw, IXGBE_RTTDT2C(i), reg); @@ -177,14 +183,19 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, /** * ixgbe_dcb_config_tx_data_arbiter_82599 - Config Tx Data arbiter * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class * * Configure Tx Packet Arbiter and credits for each traffic class. */ -static s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) { - struct tc_bw_alloc *p; u32 reg; u8 i; @@ -205,15 +216,14 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, /* Configure traffic class credits and priority */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG]; - reg = p->data_credits_refill; - reg |= (u32)(p->data_credits_max) << IXGBE_RTTPT2C_MCL_SHIFT; - reg |= (u32)(p->bwg_id) << IXGBE_RTTPT2C_BWG_SHIFT; + reg = refill[i]; + reg |= (u32)(max[i]) << IXGBE_RTTPT2C_MCL_SHIFT; + reg |= (u32)(bwg_id[i]) << IXGBE_RTTPT2C_BWG_SHIFT; - if (p->prio_type == prio_group) + if (prio_type[i] == prio_group) reg |= IXGBE_RTTPT2C_GSP; - if (p->prio_type == prio_link) + if (prio_type[i] == prio_link) reg |= IXGBE_RTTPT2C_LSP; IXGBE_WRITE_REG(hw, IXGBE_RTTPT2C(i), reg); @@ -233,17 +243,16 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, /** * ixgbe_dcb_config_pfc_82599 - Configure priority flow control * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure + * @pfc_en: enabled pfc bitmask * * Configure Priority Flow Control (PFC) for each traffic class. */ -s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) +s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en) { u32 i, reg, rx_pba_size; /* If PFC is disabled globally then fall back to LFC. */ - if (!dcb_config->pfc_mode_enable) { + if (!pfc_en) { for (i = 0; i < MAX_TRAFFIC_CLASS; i++) hw->mac.ops.fc_enable(hw, i); goto out; @@ -251,19 +260,18 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, /* Configure PFC Tx thresholds per TC */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + int enabled = pfc_en & (1 << i); rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT; reg = (rx_pba_size - hw->fc.low_water) << 10; - if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full || - dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx) + if (enabled) reg |= IXGBE_FCRTL_XONE; IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), reg); reg = (rx_pba_size - hw->fc.high_water) << 10; - if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full || - dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx) + if (enabled) reg |= IXGBE_FCRTH_FCEN; IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), reg); } @@ -349,7 +357,6 @@ static s32 ixgbe_dcb_config_tc_stats_82599(struct ixgbe_hw *hw) /** * ixgbe_dcb_config_82599 - Configure general DCB parameters * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure * * Configure general DCB parameters. */ @@ -406,19 +413,27 @@ static s32 ixgbe_dcb_config_82599(struct ixgbe_hw *hw) /** * ixgbe_dcb_hw_config_82599 - Configure and enable DCB * @hw: pointer to hardware structure - * @dcb_config: pointer to ixgbe_dcb_config structure + * @rx_pba: method to distribute packet buffer + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * @pfc_en: enabled pfc bitmask * * Configure dcb settings and enable dcb mode. */ s32 ixgbe_dcb_hw_config_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) + u8 rx_pba, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type) { - ixgbe_dcb_config_packet_buffers_82599(hw, dcb_config); + ixgbe_dcb_config_packet_buffers_82599(hw, rx_pba); ixgbe_dcb_config_82599(hw); - ixgbe_dcb_config_rx_arbiter_82599(hw, dcb_config); - ixgbe_dcb_config_tx_desc_arbiter_82599(hw, dcb_config); - ixgbe_dcb_config_tx_data_arbiter_82599(hw, dcb_config); - ixgbe_dcb_config_pfc_82599(hw, dcb_config); + ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max, bwg_id, prio_type); + ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_pfc_82599(hw, pfc_en); ixgbe_dcb_config_tc_stats_82599(hw); return 0; diff --git a/drivers/net/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ixgbe/ixgbe_dcb_82599.h index 3841649..5b0ca85 100644 --- a/drivers/net/ixgbe/ixgbe_dcb_82599.h +++ b/drivers/net/ixgbe/ixgbe_dcb_82599.h @@ -102,11 +102,29 @@ /* DCB hardware-specific driver APIs */ /* DCB PFC functions */ -s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config); +s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en); /* DCB hw initialization */ +s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + s32 ixgbe_dcb_hw_config_82599(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *config); + u8 rx_pba, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type); #endif /* _DCB_82599_CONFIG_H */ diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c index bf566e8..a977df3 100644 --- a/drivers/net/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c @@ -37,7 +37,6 @@ #define BIT_PG_RX 0x04 #define BIT_PG_TX 0x08 #define BIT_APP_UPCHG 0x10 -#define BIT_RESETLINK 0x40 #define BIT_LINKSPEED 0x80 /* Responses for the DCB_C_SET_ALL command */ @@ -225,10 +224,8 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, (adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_percent != adapter->dcb_cfg.tc_config[tc].path[0].bwg_percent) || (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap != - adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)) { + adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)) adapter->dcb_set_bitmap |= BIT_PG_TX; - adapter->dcb_set_bitmap |= BIT_RESETLINK; - } } static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, @@ -239,10 +236,8 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct; if (adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] != - adapter->dcb_cfg.bw_percentage[0][bwg_id]) { + adapter->dcb_cfg.bw_percentage[0][bwg_id]) adapter->dcb_set_bitmap |= BIT_PG_TX; - adapter->dcb_set_bitmap |= BIT_RESETLINK; - } } static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc, @@ -269,10 +264,8 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc, (adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_percent != adapter->dcb_cfg.tc_config[tc].path[1].bwg_percent) || (adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap != - adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap)) { + adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap)) adapter->dcb_set_bitmap |= BIT_PG_RX; - adapter->dcb_set_bitmap |= BIT_RESETLINK; - } } static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, @@ -283,10 +276,8 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct; if (adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] != - adapter->dcb_cfg.bw_percentage[1][bwg_id]) { + adapter->dcb_cfg.bw_percentage[1][bwg_id]) adapter->dcb_set_bitmap |= BIT_PG_RX; - adapter->dcb_set_bitmap |= BIT_RESETLINK; - } } static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, @@ -365,21 +356,17 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) return DCB_NO_HW_CHG; /* - * Only take down the adapter if the configuration change - * requires a reset. + * Only take down the adapter if an app change occured. FCoE + * may shuffle tx rings in this case and this can not be done + * without a reset currently. */ - if (adapter->dcb_set_bitmap & BIT_RESETLINK) { + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) msleep(1); - if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { - if (netif_running(netdev)) - netdev->netdev_ops->ndo_stop(netdev); - ixgbe_clear_interrupt_scheme(adapter); - } else { - if (netif_running(netdev)) - ixgbe_down(adapter); - } + if (netif_running(netdev)) + netdev->netdev_ops->ndo_stop(netdev); + ixgbe_clear_interrupt_scheme(adapter); } if (adapter->dcb_cfg.pfc_mode_enable) { @@ -408,29 +395,51 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) } } - if (adapter->dcb_set_bitmap & BIT_RESETLINK) { - if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { - ixgbe_init_interrupt_scheme(adapter); - if (netif_running(netdev)) - netdev->netdev_ops->ndo_open(netdev); - } else { - if (netif_running(netdev)) - ixgbe_up(adapter); - } + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { + ixgbe_init_interrupt_scheme(adapter); + if (netif_running(netdev)) + netdev->netdev_ops->ndo_open(netdev); ret = DCB_HW_CHG_RST; - } else if (adapter->dcb_set_bitmap & BIT_PFC) { - if (adapter->hw.mac.type == ixgbe_mac_82598EB) - ixgbe_dcb_config_pfc_82598(&adapter->hw, - &adapter->dcb_cfg); - else if (adapter->hw.mac.type == ixgbe_mac_82599EB) - ixgbe_dcb_config_pfc_82599(&adapter->hw, - &adapter->dcb_cfg); + } + + if (adapter->dcb_set_bitmap & BIT_PFC) { + u8 pfc_en; + ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en); + ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc_en); ret = DCB_HW_CHG; } + + if (adapter->dcb_set_bitmap & (BIT_PG_TX|BIT_PG_RX)) { + u16 refill[MAX_TRAFFIC_CLASS], max[MAX_TRAFFIC_CLASS]; + u8 bwg_id[MAX_TRAFFIC_CLASS], prio_type[MAX_TRAFFIC_CLASS]; + int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + +#ifdef CONFIG_FCOE + if (adapter->netdev->features & NETIF_F_FCOE_MTU) + max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); +#endif + + ixgbe_dcb_calculate_tc_credits(&adapter->hw, &adapter->dcb_cfg, + max_frame, DCB_TX_CONFIG); + ixgbe_dcb_calculate_tc_credits(&adapter->hw, &adapter->dcb_cfg, + max_frame, DCB_RX_CONFIG); + + ixgbe_dcb_unpack_refill(&adapter->dcb_cfg, + DCB_TX_CONFIG, refill); + ixgbe_dcb_unpack_max(&adapter->dcb_cfg, max); + ixgbe_dcb_unpack_bwgid(&adapter->dcb_cfg, + DCB_TX_CONFIG, bwg_id); + ixgbe_dcb_unpack_prio(&adapter->dcb_cfg, + DCB_TX_CONFIG, prio_type); + + ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max, + bwg_id, prio_type); + } + if (adapter->dcb_cfg.pfc_mode_enable) adapter->hw.fc.current_mode = ixgbe_fc_pfc; - if (adapter->dcb_set_bitmap & BIT_RESETLINK) + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) clear_bit(__IXGBE_RESETTING, &adapter->state); adapter->dcb_set_bitmap = 0x00; return ret; @@ -568,18 +577,29 @@ static u8 ixgbe_dcbnl_setapp(struct net_device *netdev, case DCB_APP_IDTYPE_ETHTYPE: #ifdef IXGBE_FCOE if (id == ETH_P_FCOE) { - u8 tc; - struct ixgbe_adapter *adapter; + u8 old_tc; + struct ixgbe_adapter *adapter = netdev_priv(netdev); - adapter = netdev_priv(netdev); - tc = adapter->fcoe.tc; + /* Get current programmed tc */ + old_tc = adapter->fcoe.tc; rval = ixgbe_fcoe_setapp(adapter, up); - if ((!rval) && (tc != adapter->fcoe.tc) && - (adapter->flags & IXGBE_FLAG_DCB_ENABLED) && - (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) { + + if (rval || + !(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || + !(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + break; + + /* The FCoE application priority may be changed multiple + * times in quick sucession with switches that build up + * TLVs. To avoid creating uneeded device resets this + * checks the actual HW configuration and clears + * BIT_APP_UPCHG if a HW configuration change is not + * need + */ + if (old_tc == adapter->fcoe.tc) + adapter->dcb_set_bitmap &= ~BIT_APP_UPCHG; + else adapter->dcb_set_bitmap |= BIT_APP_UPCHG; - adapter->dcb_set_bitmap |= BIT_RESETLINK; - } } #endif break; @@ -591,7 +611,98 @@ static u8 ixgbe_dcbnl_setapp(struct net_device *netdev, return rval; } +static int ixgbe_dcbnl_ieee_getets(struct net_device *dev, + struct ieee_ets *ets) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets; + + /* No IEEE PFC settings available */ + if (!my_ets) + return -EINVAL; + + ets->ets_cap = MAX_TRAFFIC_CLASS; + ets->cbs = my_ets->cbs; + memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw)); + memcpy(ets->tc_rx_bw, my_ets->tc_rx_bw, sizeof(ets->tc_rx_bw)); + memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa)); + memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc)); + return 0; +} + +static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, + struct ieee_ets *ets) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + __u16 refill[IEEE_8021QAZ_MAX_TCS], max[IEEE_8021QAZ_MAX_TCS]; + int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN; + int err; + /* naively give each TC a bwg to map onto CEE hardware */ + __u8 bwg_id[IEEE_8021QAZ_MAX_TCS] = {0, 1, 2, 3, 4, 5, 6, 7}; + + if (!adapter->ixgbe_ieee_ets) { + adapter->ixgbe_ieee_ets = kmalloc(sizeof(struct ieee_ets), + GFP_KERNEL); + if (!adapter->ixgbe_ieee_ets) + return -ENOMEM; + } + + + memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets)); + + ixgbe_ieee_credits(ets->tc_tx_bw, refill, max, max_frame); + err = ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max, + bwg_id, ets->tc_tsa); + return err; +} + +static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev, + struct ieee_pfc *pfc) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc; + int i; + + /* No IEEE PFC settings available */ + if (!my_pfc) + return -EINVAL; + + pfc->pfc_cap = MAX_TRAFFIC_CLASS; + pfc->pfc_en = my_pfc->pfc_en; + pfc->mbc = my_pfc->mbc; + pfc->delay = my_pfc->delay; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + pfc->requests[i] = adapter->stats.pxoffrxc[i]; + pfc->indications[i] = adapter->stats.pxofftxc[i]; + } + + return 0; +} + +static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev, + struct ieee_pfc *pfc) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int err; + + if (!adapter->ixgbe_ieee_pfc) { + adapter->ixgbe_ieee_pfc = kmalloc(sizeof(struct ieee_pfc), + GFP_KERNEL); + if (!adapter->ixgbe_ieee_pfc) + return -ENOMEM; + } + + memcpy(adapter->ixgbe_ieee_pfc, pfc, sizeof(*adapter->ixgbe_ieee_pfc)); + err = ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en); + return err; +} + const struct dcbnl_rtnl_ops dcbnl_ops = { + .ieee_getets = ixgbe_dcbnl_ieee_getets, + .ieee_setets = ixgbe_dcbnl_ieee_setets, + .ieee_getpfc = ixgbe_dcbnl_ieee_getpfc, + .ieee_setpfc = ixgbe_dcbnl_ieee_setpfc, .getstate = ixgbe_dcbnl_get_state, .setstate = ixgbe_dcbnl_set_state, .getpermhwaddr = ixgbe_dcbnl_get_perm_hw_addr, diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c index 2002ea8..309272f8 100644 --- a/drivers/net/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ixgbe/ixgbe_ethtool.c @@ -152,7 +152,17 @@ static int ixgbe_get_settings(struct net_device *netdev, ecmd->supported |= (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg); + switch (hw->mac.type) { + case ixgbe_mac_X540: + ecmd->supported |= SUPPORTED_100baseT_Full; + break; + default: + break; + } + ecmd->advertising = ADVERTISED_Autoneg; + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) + ecmd->advertising |= ADVERTISED_100baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) ecmd->advertising |= ADVERTISED_10000baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) @@ -167,6 +177,15 @@ static int ixgbe_get_settings(struct net_device *netdev, ecmd->advertising |= (ADVERTISED_10000baseT_Full | ADVERTISED_1000baseT_Full); + switch (hw->mac.type) { + case ixgbe_mac_X540: + if (!(ecmd->advertising & ADVERTISED_100baseT_Full)) + ecmd->advertising |= (ADVERTISED_100baseT_Full); + break; + default: + break; + } + if (hw->phy.media_type == ixgbe_media_type_copper) { ecmd->supported |= SUPPORTED_TP; ecmd->advertising |= ADVERTISED_TP; @@ -271,8 +290,19 @@ static int ixgbe_get_settings(struct net_device *netdev, hw->mac.ops.check_link(hw, &link_speed, &link_up, false); if (link_up) { - ecmd->speed = (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ? - SPEED_10000 : SPEED_1000; + switch (link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + ecmd->speed = SPEED_10000; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + ecmd->speed = SPEED_1000; + break; + case IXGBE_LINK_SPEED_100_FULL: + ecmd->speed = SPEED_100; + break; + default: + break; + } ecmd->duplex = DUPLEX_FULL; } else { ecmd->speed = -1; diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 30f9ccf..eca762d 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -648,7 +648,7 @@ void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring, * * Returns : a tc index for use in range 0-7, or 0-3 */ -u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 reg_idx) +static u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 reg_idx) { int tc = -1; int dcb_i = adapter->ring_feature[RING_F_DCB].indices; @@ -5174,7 +5174,6 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) adapter->dcb_cfg.bw_percentage[DCB_RX_CONFIG][0] = 100; adapter->dcb_cfg.rx_pba_cfg = pba_equal; adapter->dcb_cfg.pfc_mode_enable = false; - adapter->dcb_cfg.round_robin_enable = false; adapter->dcb_set_bitmap = 0x00; ixgbe_copy_dcb_cfg(&adapter->dcb_cfg, &adapter->temp_dcb_cfg, adapter->ring_feature[RING_F_DCB].indices); @@ -5611,6 +5610,10 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) } ixgbe_clear_interrupt_scheme(adapter); +#ifdef CONFIG_DCB + kfree(adapter->ixgbe_ieee_pfc); + kfree(adapter->ixgbe_ieee_ets); +#endif #ifdef CONFIG_PM retval = pci_save_state(pdev); @@ -6101,7 +6104,10 @@ static void ixgbe_watchdog_task(struct work_struct *work) (link_speed == IXGBE_LINK_SPEED_10GB_FULL ? "10 Gbps" : (link_speed == IXGBE_LINK_SPEED_1GB_FULL ? - "1 Gbps" : "unknown speed")), + "1 Gbps" : + (link_speed == IXGBE_LINK_SPEED_100_FULL ? + "100 Mbps" : + "unknown speed"))), ((flow_rx && flow_tx) ? "RX/TX" : (flow_rx ? "RX" : (flow_tx ? "TX" : "None")))); @@ -7706,16 +7712,6 @@ static int ixgbe_notify_dca(struct notifier_block *nb, unsigned long event, #endif /* CONFIG_IXGBE_DCA */ -/** - * ixgbe_get_hw_dev return device - * used by hardware layer to print debugging information - **/ -struct net_device *ixgbe_get_hw_dev(struct ixgbe_hw *hw) -{ - struct ixgbe_adapter *adapter = hw->back; - return adapter->netdev; -} - module_exit(ixgbe_exit_module); /* ixgbe_main.c */ diff --git a/drivers/net/ixgbe/ixgbe_mbx.c b/drivers/net/ixgbe/ixgbe_mbx.c index ea82c5a..f215c4c 100644 --- a/drivers/net/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ixgbe/ixgbe_mbx.c @@ -437,6 +437,7 @@ out_no_read: return ret_val; } +#ifdef CONFIG_PCI_IOV /** * ixgbe_init_mbx_params_pf - set initial values for pf mailbox * @hw: pointer to the HW structure @@ -465,6 +466,7 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw) break; } } +#endif /* CONFIG_PCI_IOV */ struct ixgbe_mbx_operations mbx_ops_generic = { .read = ixgbe_read_mbx_pf, diff --git a/drivers/net/ixgbe/ixgbe_mbx.h b/drivers/net/ixgbe/ixgbe_mbx.h index 3df9b15..ada0ce3 100644 --- a/drivers/net/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ixgbe/ixgbe_mbx.h @@ -86,7 +86,9 @@ s32 ixgbe_write_mbx(struct ixgbe_hw *, u32 *, u16, u16); s32 ixgbe_check_for_msg(struct ixgbe_hw *, u16); s32 ixgbe_check_for_ack(struct ixgbe_hw *, u16); s32 ixgbe_check_for_rst(struct ixgbe_hw *, u16); +#ifdef CONFIG_PCI_IOV void ixgbe_init_mbx_params_pf(struct ixgbe_hw *); +#endif /* CONFIG_PCI_IOV */ extern struct ixgbe_mbx_operations mbx_ops_generic; diff --git a/drivers/net/jme.c b/drivers/net/jme.c index e97ebef..5b441b7 100644 --- a/drivers/net/jme.c +++ b/drivers/net/jme.c @@ -161,6 +161,67 @@ jme_setup_wakeup_frame(struct jme_adapter *jme, } static inline void +jme_mac_rxclk_off(struct jme_adapter *jme) +{ + jme->reg_gpreg1 |= GPREG1_RXCLKOFF; + jwrite32f(jme, JME_GPREG1, jme->reg_gpreg1); +} + +static inline void +jme_mac_rxclk_on(struct jme_adapter *jme) +{ + jme->reg_gpreg1 &= ~GPREG1_RXCLKOFF; + jwrite32f(jme, JME_GPREG1, jme->reg_gpreg1); +} + +static inline void +jme_mac_txclk_off(struct jme_adapter *jme) +{ + jme->reg_ghc &= ~(GHC_TO_CLK_SRC | GHC_TXMAC_CLK_SRC); + jwrite32f(jme, JME_GHC, jme->reg_ghc); +} + +static inline void +jme_mac_txclk_on(struct jme_adapter *jme) +{ + u32 speed = jme->reg_ghc & GHC_SPEED; + if (speed == GHC_SPEED_1000M) + jme->reg_ghc |= GHC_TO_CLK_GPHY | GHC_TXMAC_CLK_GPHY; + else + jme->reg_ghc |= GHC_TO_CLK_PCIE | GHC_TXMAC_CLK_PCIE; + jwrite32f(jme, JME_GHC, jme->reg_ghc); +} + +static inline void +jme_reset_ghc_speed(struct jme_adapter *jme) +{ + jme->reg_ghc &= ~(GHC_SPEED | GHC_DPX); + jwrite32f(jme, JME_GHC, jme->reg_ghc); +} + +static inline void +jme_reset_250A2_workaround(struct jme_adapter *jme) +{ + jme->reg_gpreg1 &= ~(GPREG1_HALFMODEPATCH | + GPREG1_RSSPATCH); + jwrite32(jme, JME_GPREG1, jme->reg_gpreg1); +} + +static inline void +jme_assert_ghc_reset(struct jme_adapter *jme) +{ + jme->reg_ghc |= GHC_SWRST; + jwrite32f(jme, JME_GHC, jme->reg_ghc); +} + +static inline void +jme_clear_ghc_reset(struct jme_adapter *jme) +{ + jme->reg_ghc &= ~GHC_SWRST; + jwrite32f(jme, JME_GHC, jme->reg_ghc); +} + +static inline void jme_reset_mac_processor(struct jme_adapter *jme) { static const u32 mask[WAKEUP_FRAME_MASK_DWNR] = {0, 0, 0, 0}; @@ -168,9 +229,24 @@ jme_reset_mac_processor(struct jme_adapter *jme) u32 gpreg0; int i; - jwrite32(jme, JME_GHC, jme->reg_ghc | GHC_SWRST); - udelay(2); - jwrite32(jme, JME_GHC, jme->reg_ghc); + jme_reset_ghc_speed(jme); + jme_reset_250A2_workaround(jme); + + jme_mac_rxclk_on(jme); + jme_mac_txclk_on(jme); + udelay(1); + jme_assert_ghc_reset(jme); + udelay(1); + jme_mac_rxclk_off(jme); + jme_mac_txclk_off(jme); + udelay(1); + jme_clear_ghc_reset(jme); + udelay(1); + jme_mac_rxclk_on(jme); + jme_mac_txclk_on(jme); + udelay(1); + jme_mac_rxclk_off(jme); + jme_mac_txclk_off(jme); jwrite32(jme, JME_RXDBA_LO, 0x00000000); jwrite32(jme, JME_RXDBA_HI, 0x00000000); @@ -190,14 +266,6 @@ jme_reset_mac_processor(struct jme_adapter *jme) else gpreg0 = GPREG0_DEFAULT; jwrite32(jme, JME_GPREG0, gpreg0); - jwrite32(jme, JME_GPREG1, GPREG1_DEFAULT); -} - -static inline void -jme_reset_ghc_speed(struct jme_adapter *jme) -{ - jme->reg_ghc &= ~(GHC_SPEED_1000M | GHC_DPX); - jwrite32(jme, JME_GHC, jme->reg_ghc); } static inline void @@ -336,13 +404,13 @@ jme_linkstat_from_phy(struct jme_adapter *jme) } static inline void -jme_set_phyfifoa(struct jme_adapter *jme) +jme_set_phyfifo_5level(struct jme_adapter *jme) { jme_mdio_write(jme->dev, jme->mii_if.phy_id, 27, 0x0004); } static inline void -jme_set_phyfifob(struct jme_adapter *jme) +jme_set_phyfifo_8level(struct jme_adapter *jme) { jme_mdio_write(jme->dev, jme->mii_if.phy_id, 27, 0x0000); } @@ -351,7 +419,7 @@ static int jme_check_link(struct net_device *netdev, int testonly) { struct jme_adapter *jme = netdev_priv(netdev); - u32 phylink, ghc, cnt = JME_SPDRSV_TIMEOUT, bmcr, gpreg1; + u32 phylink, cnt = JME_SPDRSV_TIMEOUT, bmcr; char linkmsg[64]; int rc = 0; @@ -414,23 +482,21 @@ jme_check_link(struct net_device *netdev, int testonly) jme->phylink = phylink; - ghc = jme->reg_ghc & ~(GHC_SPEED | GHC_DPX | - GHC_TO_CLK_PCIE | GHC_TXMAC_CLK_PCIE | - GHC_TO_CLK_GPHY | GHC_TXMAC_CLK_GPHY); + /* + * The speed/duplex setting of jme->reg_ghc already cleared + * by jme_reset_mac_processor() + */ switch (phylink & PHY_LINK_SPEED_MASK) { case PHY_LINK_SPEED_10M: - ghc |= GHC_SPEED_10M | - GHC_TO_CLK_PCIE | GHC_TXMAC_CLK_PCIE; + jme->reg_ghc |= GHC_SPEED_10M; strcat(linkmsg, "10 Mbps, "); break; case PHY_LINK_SPEED_100M: - ghc |= GHC_SPEED_100M | - GHC_TO_CLK_PCIE | GHC_TXMAC_CLK_PCIE; + jme->reg_ghc |= GHC_SPEED_100M; strcat(linkmsg, "100 Mbps, "); break; case PHY_LINK_SPEED_1000M: - ghc |= GHC_SPEED_1000M | - GHC_TO_CLK_GPHY | GHC_TXMAC_CLK_GPHY; + jme->reg_ghc |= GHC_SPEED_1000M; strcat(linkmsg, "1000 Mbps, "); break; default: @@ -439,42 +505,40 @@ jme_check_link(struct net_device *netdev, int testonly) if (phylink & PHY_LINK_DUPLEX) { jwrite32(jme, JME_TXMCS, TXMCS_DEFAULT); - ghc |= GHC_DPX; + jwrite32(jme, JME_TXTRHD, TXTRHD_FULLDUPLEX); + jme->reg_ghc |= GHC_DPX; } else { jwrite32(jme, JME_TXMCS, TXMCS_DEFAULT | TXMCS_BACKOFF | TXMCS_CARRIERSENSE | TXMCS_COLLISION); - jwrite32(jme, JME_TXTRHD, TXTRHD_TXPEN | - ((0x2000 << TXTRHD_TXP_SHIFT) & TXTRHD_TXP) | - TXTRHD_TXREN | - ((8 << TXTRHD_TXRL_SHIFT) & TXTRHD_TXRL)); + jwrite32(jme, JME_TXTRHD, TXTRHD_HALFDUPLEX); } - gpreg1 = GPREG1_DEFAULT; + jwrite32(jme, JME_GHC, jme->reg_ghc); + if (is_buggy250(jme->pdev->device, jme->chiprev)) { + jme->reg_gpreg1 &= ~(GPREG1_HALFMODEPATCH | + GPREG1_RSSPATCH); if (!(phylink & PHY_LINK_DUPLEX)) - gpreg1 |= GPREG1_HALFMODEPATCH; + jme->reg_gpreg1 |= GPREG1_HALFMODEPATCH; switch (phylink & PHY_LINK_SPEED_MASK) { case PHY_LINK_SPEED_10M: - jme_set_phyfifoa(jme); - gpreg1 |= GPREG1_RSSPATCH; + jme_set_phyfifo_8level(jme); + jme->reg_gpreg1 |= GPREG1_RSSPATCH; break; case PHY_LINK_SPEED_100M: - jme_set_phyfifob(jme); - gpreg1 |= GPREG1_RSSPATCH; + jme_set_phyfifo_5level(jme); + jme->reg_gpreg1 |= GPREG1_RSSPATCH; break; case PHY_LINK_SPEED_1000M: - jme_set_phyfifoa(jme); + jme_set_phyfifo_8level(jme); break; default: break; } } - - jwrite32(jme, JME_GPREG1, gpreg1); - jwrite32(jme, JME_GHC, ghc); - jme->reg_ghc = ghc; + jwrite32(jme, JME_GPREG1, jme->reg_gpreg1); strcat(linkmsg, (phylink & PHY_LINK_DUPLEX) ? "Full-Duplex, " : @@ -613,10 +677,14 @@ jme_enable_tx_engine(struct jme_adapter *jme) * Enable TX Engine */ wmb(); - jwrite32(jme, JME_TXCS, jme->reg_txcs | + jwrite32f(jme, JME_TXCS, jme->reg_txcs | TXCS_SELECT_QUEUE0 | TXCS_ENABLE); + /* + * Start clock for TX MAC Processor + */ + jme_mac_txclk_on(jme); } static inline void @@ -651,6 +719,11 @@ jme_disable_tx_engine(struct jme_adapter *jme) if (!i) pr_err("Disable TX engine timeout\n"); + + /* + * Stop clock for TX MAC Processor + */ + jme_mac_txclk_off(jme); } static void @@ -825,16 +898,22 @@ jme_enable_rx_engine(struct jme_adapter *jme) /* * Setup Unicast Filter */ + jme_set_unicastaddr(jme->dev); jme_set_multi(jme->dev); /* * Enable RX Engine */ wmb(); - jwrite32(jme, JME_RXCS, jme->reg_rxcs | + jwrite32f(jme, JME_RXCS, jme->reg_rxcs | RXCS_QUEUESEL_Q0 | RXCS_ENABLE | RXCS_QST); + + /* + * Start clock for RX MAC Processor + */ + jme_mac_rxclk_on(jme); } static inline void @@ -871,10 +950,40 @@ jme_disable_rx_engine(struct jme_adapter *jme) if (!i) pr_err("Disable RX engine timeout\n"); + /* + * Stop clock for RX MAC Processor + */ + jme_mac_rxclk_off(jme); +} + +static u16 +jme_udpsum(struct sk_buff *skb) +{ + u16 csum = 0xFFFFu; + + if (skb->len < (ETH_HLEN + sizeof(struct iphdr))) + return csum; + if (skb->protocol != htons(ETH_P_IP)) + return csum; + skb_set_network_header(skb, ETH_HLEN); + if ((ip_hdr(skb)->protocol != IPPROTO_UDP) || + (skb->len < (ETH_HLEN + + (ip_hdr(skb)->ihl << 2) + + sizeof(struct udphdr)))) { + skb_reset_network_header(skb); + return csum; + } + skb_set_transport_header(skb, + ETH_HLEN + (ip_hdr(skb)->ihl << 2)); + csum = udp_hdr(skb)->check; + skb_reset_transport_header(skb); + skb_reset_network_header(skb); + + return csum; } static int -jme_rxsum_ok(struct jme_adapter *jme, u16 flags) +jme_rxsum_ok(struct jme_adapter *jme, u16 flags, struct sk_buff *skb) { if (!(flags & (RXWBFLAG_TCPON | RXWBFLAG_UDPON | RXWBFLAG_IPV4))) return false; @@ -887,7 +996,7 @@ jme_rxsum_ok(struct jme_adapter *jme, u16 flags) } if (unlikely((flags & (RXWBFLAG_MF | RXWBFLAG_UDPON | RXWBFLAG_UDPCS)) - == RXWBFLAG_UDPON)) { + == RXWBFLAG_UDPON) && jme_udpsum(skb)) { if (flags & RXWBFLAG_IPV4) netif_err(jme, rx_err, jme->dev, "UDP Checksum error\n"); return false; @@ -935,7 +1044,7 @@ jme_alloc_and_feed_skb(struct jme_adapter *jme, int idx) skb_put(skb, framesize); skb->protocol = eth_type_trans(skb, jme->dev); - if (jme_rxsum_ok(jme, le16_to_cpu(rxdesc->descwb.flags))) + if (jme_rxsum_ok(jme, le16_to_cpu(rxdesc->descwb.flags), skb)) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); @@ -1207,7 +1316,6 @@ jme_link_change_tasklet(unsigned long arg) tasklet_disable(&jme->rxempty_task); if (netif_carrier_ok(netdev)) { - jme_reset_ghc_speed(jme); jme_disable_rx_engine(jme); jme_disable_tx_engine(jme); jme_reset_mac_processor(jme); @@ -1577,6 +1685,38 @@ jme_free_irq(struct jme_adapter *jme) } static inline void +jme_new_phy_on(struct jme_adapter *jme) +{ + u32 reg; + + reg = jread32(jme, JME_PHY_PWR); + reg &= ~(PHY_PWR_DWN1SEL | PHY_PWR_DWN1SW | + PHY_PWR_DWN2 | PHY_PWR_CLKSEL); + jwrite32(jme, JME_PHY_PWR, reg); + + pci_read_config_dword(jme->pdev, PCI_PRIV_PE1, ®); + reg &= ~PE1_GPREG0_PBG; + reg |= PE1_GPREG0_ENBG; + pci_write_config_dword(jme->pdev, PCI_PRIV_PE1, reg); +} + +static inline void +jme_new_phy_off(struct jme_adapter *jme) +{ + u32 reg; + + reg = jread32(jme, JME_PHY_PWR); + reg |= PHY_PWR_DWN1SEL | PHY_PWR_DWN1SW | + PHY_PWR_DWN2 | PHY_PWR_CLKSEL; + jwrite32(jme, JME_PHY_PWR, reg); + + pci_read_config_dword(jme->pdev, PCI_PRIV_PE1, ®); + reg &= ~PE1_GPREG0_PBG; + reg |= PE1_GPREG0_PDD3COLD; + pci_write_config_dword(jme->pdev, PCI_PRIV_PE1, reg); +} + +static inline void jme_phy_on(struct jme_adapter *jme) { u32 bmcr; @@ -1584,6 +1724,22 @@ jme_phy_on(struct jme_adapter *jme) bmcr = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_BMCR); bmcr &= ~BMCR_PDOWN; jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_BMCR, bmcr); + + if (new_phy_power_ctrl(jme->chip_main_rev)) + jme_new_phy_on(jme); +} + +static inline void +jme_phy_off(struct jme_adapter *jme) +{ + u32 bmcr; + + bmcr = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_BMCR); + bmcr |= BMCR_PDOWN; + jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_BMCR, bmcr); + + if (new_phy_power_ctrl(jme->chip_main_rev)) + jme_new_phy_off(jme); } static int @@ -1606,12 +1762,11 @@ jme_open(struct net_device *netdev) jme_start_irq(jme); - if (test_bit(JME_FLAG_SSET, &jme->flags)) { - jme_phy_on(jme); + jme_phy_on(jme); + if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); - } else { + else jme_reset_phy_processor(jme); - } jme_reset_link(jme); @@ -1657,12 +1812,6 @@ jme_wait_link(struct jme_adapter *jme) } } -static inline void -jme_phy_off(struct jme_adapter *jme) -{ - jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_BMCR, BMCR_PDOWN); -} - static void jme_powersave_phy(struct jme_adapter *jme) { @@ -1696,7 +1845,6 @@ jme_close(struct net_device *netdev) tasklet_disable(&jme->rxclean_task); tasklet_disable(&jme->rxempty_task); - jme_reset_ghc_speed(jme); jme_disable_rx_engine(jme); jme_disable_tx_engine(jme); jme_reset_mac_processor(jme); @@ -1993,27 +2141,34 @@ jme_start_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } +static void +jme_set_unicastaddr(struct net_device *netdev) +{ + struct jme_adapter *jme = netdev_priv(netdev); + u32 val; + + val = (netdev->dev_addr[3] & 0xff) << 24 | + (netdev->dev_addr[2] & 0xff) << 16 | + (netdev->dev_addr[1] & 0xff) << 8 | + (netdev->dev_addr[0] & 0xff); + jwrite32(jme, JME_RXUMA_LO, val); + val = (netdev->dev_addr[5] & 0xff) << 8 | + (netdev->dev_addr[4] & 0xff); + jwrite32(jme, JME_RXUMA_HI, val); +} + static int jme_set_macaddr(struct net_device *netdev, void *p) { struct jme_adapter *jme = netdev_priv(netdev); struct sockaddr *addr = p; - u32 val; if (netif_running(netdev)) return -EBUSY; spin_lock_bh(&jme->macaddr_lock); memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); - - val = (addr->sa_data[3] & 0xff) << 24 | - (addr->sa_data[2] & 0xff) << 16 | - (addr->sa_data[1] & 0xff) << 8 | - (addr->sa_data[0] & 0xff); - jwrite32(jme, JME_RXUMA_LO, val); - val = (addr->sa_data[5] & 0xff) << 8 | - (addr->sa_data[4] & 0xff); - jwrite32(jme, JME_RXUMA_HI, val); + jme_set_unicastaddr(netdev); spin_unlock_bh(&jme->macaddr_lock); return 0; @@ -2731,6 +2886,8 @@ jme_check_hw_ver(struct jme_adapter *jme) jme->fpgaver = (chipmode & CM_FPGAVER_MASK) >> CM_FPGAVER_SHIFT; jme->chiprev = (chipmode & CM_CHIPREV_MASK) >> CM_CHIPREV_SHIFT; + jme->chip_main_rev = jme->chiprev & 0xF; + jme->chip_sub_rev = (jme->chiprev >> 4) & 0xF; } static const struct net_device_ops jme_netdev_ops = { @@ -2880,6 +3037,7 @@ jme_init_one(struct pci_dev *pdev, jme->reg_rxmcs = RXMCS_DEFAULT; jme->reg_txpfc = 0; jme->reg_pmcs = PMCS_MFEN; + jme->reg_gpreg1 = GPREG1_DEFAULT; set_bit(JME_FLAG_TXCSUM, &jme->flags); set_bit(JME_FLAG_TSO, &jme->flags); @@ -2936,8 +3094,8 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_write = jme_mdio_write; jme_clear_pm(jme); - jme_set_phyfifoa(jme); - pci_read_config_byte(pdev, PCI_REVISION_ID, &jme->rev); + jme_set_phyfifo_5level(jme); + pci_read_config_byte(pdev, PCI_REVISION_ID, &jme->pcirev); if (!jme->fpgaver) jme_phy_init(jme); jme_phy_off(jme); @@ -2964,14 +3122,14 @@ jme_init_one(struct pci_dev *pdev, goto err_out_unmap; } - netif_info(jme, probe, jme->dev, "%s%s ver:%x rev:%x macaddr:%pM\n", + netif_info(jme, probe, jme->dev, "%s%s chiprev:%x pcirev:%x macaddr:%pM\n", (jme->pdev->device == PCI_DEVICE_ID_JMICRON_JMC250) ? "JMC250 Gigabit Ethernet" : (jme->pdev->device == PCI_DEVICE_ID_JMICRON_JMC260) ? "JMC260 Fast Ethernet" : "Unknown", (jme->fpgaver != 0) ? " (FPGA)" : "", (jme->fpgaver != 0) ? jme->fpgaver : jme->chiprev, - jme->rev, netdev->dev_addr); + jme->pcirev, netdev->dev_addr); return 0; @@ -3035,7 +3193,6 @@ jme_suspend(struct pci_dev *pdev, pm_message_t state) jme_polling_mode(jme); jme_stop_pcc_timer(jme); - jme_reset_ghc_speed(jme); jme_disable_rx_engine(jme); jme_disable_tx_engine(jme); jme_reset_mac_processor(jme); @@ -3066,12 +3223,11 @@ jme_resume(struct pci_dev *pdev) jme_clear_pm(jme); pci_restore_state(pdev); - if (test_bit(JME_FLAG_SSET, &jme->flags)) { - jme_phy_on(jme); + jme_phy_on(jme); + if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); - } else { + else jme_reset_phy_processor(jme); - } jme_start_irq(jme); netif_device_attach(netdev); diff --git a/drivers/net/jme.h b/drivers/net/jme.h index eac0926..8bf3045 100644 --- a/drivers/net/jme.h +++ b/drivers/net/jme.h @@ -26,7 +26,7 @@ #define __JME_H_INCLUDED__ #define DRV_NAME "jme" -#define DRV_VERSION "1.0.7" +#define DRV_VERSION "1.0.8" #define PFX DRV_NAME ": " #define PCI_DEVICE_ID_JMICRON_JMC250 0x0250 @@ -103,6 +103,37 @@ enum jme_spi_op_bits { #define HALF_US 500 /* 500 ns */ #define JMESPIIOCTL SIOCDEVPRIVATE +#define PCI_PRIV_PE1 0xE4 + +enum pci_priv_pe1_bit_masks { + PE1_ASPMSUPRT = 0x00000003, /* + * RW: + * Aspm_support[1:0] + * (R/W Port of 5C[11:10]) + */ + PE1_MULTIFUN = 0x00000004, /* RW: Multi_fun_bit */ + PE1_RDYDMA = 0x00000008, /* RO: ~link.rdy_for_dma */ + PE1_ASPMOPTL = 0x00000030, /* RW: link.rx10s_option[1:0] */ + PE1_ASPMOPTH = 0x000000C0, /* RW: 10_req=[3]?HW:[2] */ + PE1_GPREG0 = 0x0000FF00, /* + * SRW: + * Cfg_gp_reg0 + * [7:6] phy_giga BG control + * [5] CREQ_N as CREQ_N1 (CPPE# as CREQ#) + * [4:0] Reserved + */ + PE1_GPREG0_PBG = 0x0000C000, /* phy_giga BG control */ + PE1_GPREG1 = 0x00FF0000, /* RW: Cfg_gp_reg1 */ + PE1_REVID = 0xFF000000, /* RO: Rev ID */ +}; + +enum pci_priv_pe1_values { + PE1_GPREG0_ENBG = 0x00000000, /* en BG */ + PE1_GPREG0_PDD3COLD = 0x00004000, /* giga_PD + d3cold */ + PE1_GPREG0_PDPCIESD = 0x00008000, /* giga_PD + pcie_shutdown */ + PE1_GPREG0_PDPCIEIDDQ = 0x0000C000, /* giga_PD + pcie_iddq */ +}; + /* * Dynamic(adaptive)/Static PCC values */ @@ -403,6 +434,7 @@ struct jme_adapter { u32 reg_rxmcs; u32 reg_ghc; u32 reg_pmcs; + u32 reg_gpreg1; u32 phylink; u32 tx_ring_size; u32 tx_ring_mask; @@ -411,8 +443,10 @@ struct jme_adapter { u32 rx_ring_mask; u8 mrrs; unsigned int fpgaver; - unsigned int chiprev; - u8 rev; + u8 chiprev; + u8 chip_main_rev; + u8 chip_sub_rev; + u8 pcirev; u32 msg_enable; struct ethtool_cmd old_ecmd; unsigned int old_mtu; @@ -497,6 +531,7 @@ enum jme_iomap_regs { JME_PMCS = JME_MAC | 0x60, /* Power Management Control/Stat */ + JME_PHY_PWR = JME_PHY | 0x24, /* New PHY Power Ctrl Register */ JME_PHY_CS = JME_PHY | 0x28, /* PHY Ctrl and Status Register */ JME_PHY_LINK = JME_PHY | 0x30, /* PHY Link Status Register */ JME_SMBCSR = JME_PHY | 0x40, /* SMB Control and Status */ @@ -624,6 +659,14 @@ enum jme_txtrhd_shifts { TXTRHD_TXRL_SHIFT = 0, }; +enum jme_txtrhd_values { + TXTRHD_FULLDUPLEX = 0x00000000, + TXTRHD_HALFDUPLEX = TXTRHD_TXPEN | + ((0x2000 << TXTRHD_TXP_SHIFT) & TXTRHD_TXP) | + TXTRHD_TXREN | + ((8 << TXTRHD_TXRL_SHIFT) & TXTRHD_TXRL), +}; + /* * RX Control/Status Bits */ @@ -779,6 +822,8 @@ static inline u32 smi_phy_addr(int x) */ enum jme_ghc_bit_mask { GHC_SWRST = 0x40000000, + GHC_TO_CLK_SRC = 0x00C00000, + GHC_TXMAC_CLK_SRC = 0x00300000, GHC_DPX = 0x00000040, GHC_SPEED = 0x00000030, GHC_LINK_POLL = 0x00000001, @@ -833,6 +878,21 @@ enum jme_pmcs_bit_masks { }; /* + * New PHY Power Control Register + */ +enum jme_phy_pwr_bit_masks { + PHY_PWR_DWN1SEL = 0x01000000, /* Phy_giga.p_PWR_DOWN1_SEL */ + PHY_PWR_DWN1SW = 0x02000000, /* Phy_giga.p_PWR_DOWN1_SW */ + PHY_PWR_DWN2 = 0x04000000, /* Phy_giga.p_PWR_DOWN2 */ + PHY_PWR_CLKSEL = 0x08000000, /* + * XTL_OUT Clock select + * (an internal free-running clock) + * 0: xtl_out = phy_giga.A_XTL25_O + * 1: xtl_out = phy_giga.PD_OSC + */ +}; + +/* * Giga PHY Status Registers */ enum jme_phy_link_bit_mask { @@ -942,18 +1002,17 @@ enum jme_gpreg0_vals { /* * General Purpose REG-1 - * Note: All theses bits defined here are for - * Chip mode revision 0x11 only */ -enum jme_gpreg1_masks { +enum jme_gpreg1_bit_masks { + GPREG1_RXCLKOFF = 0x04000000, + GPREG1_PCREQN = 0x00020000, + GPREG1_HALFMODEPATCH = 0x00000040, /* For Chip revision 0x11 only */ + GPREG1_RSSPATCH = 0x00000020, /* For Chip revision 0x11 only */ GPREG1_INTRDELAYUNIT = 0x00000018, GPREG1_INTRDELAYENABLE = 0x00000007, }; enum jme_gpreg1_vals { - GPREG1_RSSPATCH = 0x00000040, - GPREG1_HALFMODEPATCH = 0x00000020, - GPREG1_INTDLYUNIT_16NS = 0x00000000, GPREG1_INTDLYUNIT_256NS = 0x00000008, GPREG1_INTDLYUNIT_1US = 0x00000010, @@ -967,7 +1026,7 @@ enum jme_gpreg1_vals { GPREG1_INTDLYEN_6U = 0x00000006, GPREG1_INTDLYEN_7U = 0x00000007, - GPREG1_DEFAULT = 0x00000000, + GPREG1_DEFAULT = GPREG1_PCREQN, }; /* @@ -1184,16 +1243,22 @@ enum jme_phy_reg17_vals { /* * Workaround */ -static inline int is_buggy250(unsigned short device, unsigned int chiprev) +static inline int is_buggy250(unsigned short device, u8 chiprev) { return device == PCI_DEVICE_ID_JMICRON_JMC250 && chiprev == 0x11; } +static inline int new_phy_power_ctrl(u8 chip_main_rev) +{ + return chip_main_rev >= 5; +} + /* * Function prototypes */ static int jme_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd); +static void jme_set_unicastaddr(struct net_device *netdev); static void jme_set_multi(struct net_device *netdev); #endif diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 2d9663a..ea0dc45 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -129,10 +129,6 @@ static u32 always_on(struct net_device *dev) static const struct ethtool_ops loopback_ethtool_ops = { .get_link = always_on, - .set_tso = ethtool_op_set_tso, - .get_tx_csum = always_on, - .get_sg = always_on, - .get_rx_csum = always_on, }; static int loopback_dev_init(struct net_device *dev) @@ -169,9 +165,12 @@ static void loopback_setup(struct net_device *dev) dev->type = ARPHRD_LOOPBACK; /* 0x0001*/ dev->flags = IFF_LOOPBACK; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + dev->hw_features = NETIF_F_ALL_TSO | NETIF_F_UFO; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST - | NETIF_F_TSO + | NETIF_F_ALL_TSO + | NETIF_F_UFO | NETIF_F_NO_CSUM + | NETIF_F_RXCSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 5933621..2300e45 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -39,7 +39,7 @@ struct macvtap_queue { struct socket sock; struct socket_wq wq; int vnet_hdr_sz; - struct macvlan_dev *vlan; + struct macvlan_dev __rcu *vlan; struct file *file; unsigned int flags; }; @@ -141,7 +141,8 @@ static void macvtap_put_queue(struct macvtap_queue *q) struct macvlan_dev *vlan; spin_lock(&macvtap_lock); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_protected(q->vlan, + lockdep_is_held(&macvtap_lock)); if (vlan) { int index = get_slot(vlan, q); @@ -219,7 +220,8 @@ static void macvtap_del_queues(struct net_device *dev) /* macvtap_put_queue can free some slots, so go through all slots */ spin_lock(&macvtap_lock); for (i = 0; i < MAX_MACVTAP_QUEUES && vlan->numvtaps; i++) { - q = rcu_dereference(vlan->taps[i]); + q = rcu_dereference_protected(vlan->taps[i], + lockdep_is_held(&macvtap_lock)); if (q) { qlist[j++] = q; rcu_assign_pointer(vlan->taps[i], NULL); @@ -569,7 +571,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, } rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) macvlan_start_xmit(skb, vlan->dev); else @@ -583,7 +585,7 @@ err_kfree: err: rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) vlan->dev->stats.tx_dropped++; rcu_read_unlock_bh(); @@ -631,7 +633,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len); rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) macvlan_count_rx(vlan, len, ret == 0, 0); rcu_read_unlock_bh(); @@ -727,7 +729,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNGETIFF: rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) dev_hold(vlan->dev); rcu_read_unlock_bh(); @@ -736,7 +738,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, return -ENOLINK; ret = 0; - if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || + if (copy_to_user(&ifr->ifr_name, vlan->dev->name, IFNAMSIZ) || put_user(q->flags, &ifr->ifr_flags)) ret = -EFAULT; dev_put(vlan->dev); diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index ea5cfe2..a7f2eed 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -253,7 +253,7 @@ struct myri10ge_priv { unsigned long serial_number; int vendor_specific_offset; int fw_multicast_support; - unsigned long features; + u32 features; u32 max_tso6; u32 read_dma; u32 write_dma; @@ -1776,7 +1776,7 @@ static int myri10ge_set_rx_csum(struct net_device *netdev, u32 csum_enabled) static int myri10ge_set_tso(struct net_device *netdev, u32 tso_enabled) { struct myri10ge_priv *mgp = netdev_priv(netdev); - unsigned long flags = mgp->features & (NETIF_F_TSO6 | NETIF_F_TSO); + u32 flags = mgp->features & (NETIF_F_TSO6 | NETIF_F_TSO); if (tso_enabled) netdev->features |= flags; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 35fda5a..392a6c4 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -77,7 +77,6 @@ config NATIONAL_PHY Currently supports the DP83865 PHY. config STE10XP - depends on PHYLIB tristate "Driver for STMicroelectronics STe10Xp PHYs" ---help--- This is the driver for the STe100p and STe101p PHYs. diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 0fd1678..590f902 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -19,13 +19,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/phy.h> - -#define PHY_ID_KSZ9021 0x00221611 -#define PHY_ID_KS8737 0x00221720 -#define PHY_ID_KS8041 0x00221510 -#define PHY_ID_KS8051 0x00221550 -/* both for ks8001 Rev. A/B, and for ks8721 Rev 3. */ -#define PHY_ID_KS8001 0x0022161A +#include <linux/micrel_phy.h> /* general Interrupt control/status reg in vendor specific block. */ #define MII_KSZPHY_INTCS 0x1B @@ -46,6 +40,7 @@ #define KSZPHY_CTRL_INT_ACTIVE_HIGH (1 << 9) #define KSZ9021_CTRL_INT_ACTIVE_HIGH (1 << 14) #define KS8737_CTRL_INT_ACTIVE_HIGH (1 << 14) +#define KSZ8051_RMII_50MHZ_CLK (1 << 7) static int kszphy_ack_interrupt(struct phy_device *phydev) { @@ -106,6 +101,19 @@ static int kszphy_config_init(struct phy_device *phydev) return 0; } +static int ks8051_config_init(struct phy_device *phydev) +{ + int regval; + + if (phydev->dev_flags & MICREL_PHY_50MHZ_CLK) { + regval = phy_read(phydev, MII_KSZPHY_CTRL); + regval |= KSZ8051_RMII_50MHZ_CLK; + phy_write(phydev, MII_KSZPHY_CTRL, regval); + } + + return 0; +} + static struct phy_driver ks8737_driver = { .phy_id = PHY_ID_KS8737, .phy_id_mask = 0x00fffff0, @@ -142,7 +150,7 @@ static struct phy_driver ks8051_driver = { .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, - .config_init = kszphy_config_init, + .config_init = ks8051_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index c7a6c44..9f6d670 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -592,8 +592,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ppp_release(NULL, file); err = 0; } else - printk(KERN_DEBUG "PPPIOCDETACH file->f_count=%ld\n", - atomic_long_read(&file->f_count)); + pr_warn("PPPIOCDETACH file->f_count=%ld\n", + atomic_long_read(&file->f_count)); mutex_unlock(&ppp_mutex); return err; } @@ -630,7 +630,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (pf->kind != INTERFACE) { /* can't happen */ - printk(KERN_ERR "PPP: not interface or channel??\n"); + pr_err("PPP: not interface or channel??\n"); return -EINVAL; } @@ -704,7 +704,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } vj = slhc_init(val2+1, val+1); if (!vj) { - printk(KERN_ERR "PPP: no memory (VJ compressor)\n"); + netdev_err(ppp->dev, + "PPP: no memory (VJ compressor)\n"); err = -ENOMEM; break; } @@ -898,17 +899,17 @@ static int __init ppp_init(void) { int err; - printk(KERN_INFO "PPP generic driver version " PPP_VERSION "\n"); + pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { - printk(KERN_ERR "failed to register PPP pernet device (%d)\n", err); + pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { - printk(KERN_ERR "failed to register PPP device (%d)\n", err); + pr_err("failed to register PPP device (%d)\n", err); goto out_net; } @@ -1078,7 +1079,7 @@ pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) - printk(KERN_ERR "PPP: no memory (comp pkt)\n"); + netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) @@ -1108,7 +1109,7 @@ pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) * the same number. */ if (net_ratelimit()) - printk(KERN_ERR "ppp: compressor dropped pkt\n"); + netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); kfree_skb(new_skb); new_skb = NULL; @@ -1138,7 +1139,9 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) if (ppp->pass_filter && sk_run_filter(skb, ppp->pass_filter) == 0) { if (ppp->debug & 1) - printk(KERN_DEBUG "PPP: outbound frame not passed\n"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: outbound frame " + "not passed\n"); kfree_skb(skb); return; } @@ -1164,7 +1167,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { - printk(KERN_ERR "PPP: no memory (VJ comp pkt)\n"); + netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); @@ -1202,7 +1205,9 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) - printk(KERN_ERR "ppp: compression required but down - pkt dropped.\n"); + netdev_err(ppp->dev, + "ppp: compression required but " + "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); @@ -1505,7 +1510,7 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) noskb: spin_unlock_bh(&pch->downl); if (ppp->debug & 1) - printk(KERN_ERR "PPP: no memory (fragment)\n"); + netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ @@ -1686,7 +1691,8 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { - printk(KERN_ERR"PPP: no memory (VJ decomp)\n"); + netdev_err(ppp->dev, "PPP: no memory " + "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); @@ -1699,7 +1705,8 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { - printk(KERN_DEBUG "PPP: VJ decompression error\n"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: VJ decompression error\n"); goto err; } len += 2; @@ -1721,7 +1728,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { - printk(KERN_ERR "PPP: VJ uncompressed error\n"); + netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; @@ -1762,8 +1769,9 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) if (ppp->pass_filter && sk_run_filter(skb, ppp->pass_filter) == 0) { if (ppp->debug & 1) - printk(KERN_DEBUG "PPP: inbound frame " - "not passed\n"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: inbound frame " + "not passed\n"); kfree_skb(skb); return; } @@ -1821,7 +1829,8 @@ ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) ns = dev_alloc_skb(obuff_size); if (!ns) { - printk(KERN_ERR "ppp_decompress_frame: no memory\n"); + netdev_err(ppp->dev, "ppp_decompress_frame: " + "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ @@ -1989,7 +1998,7 @@ ppp_mp_reconstruct(struct ppp *ppp) u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; - struct sk_buff *p, *next; + struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; @@ -1998,13 +2007,15 @@ ppp_mp_reconstruct(struct ppp *ppp) return NULL; head = list->next; tail = NULL; - for (p = head; p != (struct sk_buff *) list; p = next) { - next = p->next; + skb_queue_walk_safe(list, p, tmp) { + again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ - printk(KERN_ERR "ppp_mp_reconstruct bad seq %u < %u\n", - PPP_MP_CB(p)->sequence, seq); - head = next; + netdev_err(ppp->dev, "ppp_mp_reconstruct bad " + "seq %u < %u\n", + PPP_MP_CB(p)->sequence, seq); + __skb_unlink(p, list); + kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { @@ -2016,8 +2027,7 @@ ppp_mp_reconstruct(struct ppp *ppp) lost = 1; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; - next = p; - continue; + goto again; } /* @@ -2042,17 +2052,9 @@ ppp_mp_reconstruct(struct ppp *ppp) (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; - printk(KERN_DEBUG "PPP: reconstructed packet" - " is too long (%d)\n", len); - } else if (p == head) { - /* fragment is complete packet - reuse skb */ - tail = p; - skb = skb_get(p); - break; - } else if ((skb = dev_alloc_skb(len)) == NULL) { - ++ppp->dev->stats.rx_missed_errors; - printk(KERN_DEBUG "PPP: no memory for " - "reconstructed packet"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: reconstructed packet" + " is too long (%d)\n", len); } else { tail = p; break; @@ -2065,9 +2067,17 @@ ppp_mp_reconstruct(struct ppp *ppp) * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ - if (PPP_MP_CB(p)->BEbits & E) - head = next; + if (PPP_MP_CB(p)->BEbits & E) { + struct sk_buff *tmp2; + skb_queue_reverse_walk_from_safe(list, p, tmp2) { + __skb_unlink(p, list); + kfree_skb(p); + } + head = skb_peek(list); + if (!head) + break; + } ++seq; } @@ -2077,26 +2087,37 @@ ppp_mp_reconstruct(struct ppp *ppp) signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { if (ppp->debug & 1) - printk(KERN_DEBUG " missed pkts %u..%u\n", - ppp->nextseq, - PPP_MP_CB(head)->sequence-1); + netdev_printk(KERN_DEBUG, ppp->dev, + " missed pkts %u..%u\n", + ppp->nextseq, + PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } - if (head != tail) - /* copy to a single skb */ - for (p = head; p != tail->next; p = p->next) - skb_copy_bits(p, 0, skb_put(skb, p->len), p->len); - ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; - head = tail->next; - } + skb = head; + if (head != tail) { + struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; + p = skb_queue_next(list, head); + __skb_unlink(skb, list); + skb_queue_walk_from_safe(list, p, tmp) { + __skb_unlink(p, list); + *fragpp = p; + p->next = NULL; + fragpp = &p->next; + + skb->len += p->len; + skb->data_len += p->len; + skb->truesize += p->len; + + if (p == tail) + break; + } + } else { + __skb_unlink(skb, list); + } - /* Discard all the skbuffs that we have copied the data out of - or that we can't use. */ - while ((p = list->next) != head) { - __skb_unlink(p, list); - kfree_skb(p); + ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; @@ -2617,8 +2638,8 @@ ppp_create_interface(struct net *net, int unit, int *retp) ret = register_netdev(dev); if (ret != 0) { unit_put(&pn->units_idr, unit); - printk(KERN_ERR "PPP: couldn't register device %s (%d)\n", - dev->name, ret); + netdev_err(ppp->dev, "PPP: couldn't register device %s (%d)\n", + dev->name, ret); goto out2; } @@ -2690,9 +2711,9 @@ static void ppp_destroy_interface(struct ppp *ppp) if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ - printk(KERN_ERR "ppp: destroying ppp struct %p but dead=%d " - "n_channels=%d !\n", ppp, ppp->file.dead, - ppp->n_channels); + netdev_err(ppp->dev, "ppp: destroying ppp struct %p " + "but dead=%d n_channels=%d !\n", + ppp, ppp->file.dead, ppp->n_channels); return; } @@ -2834,8 +2855,7 @@ static void ppp_destroy_channel(struct channel *pch) if (!pch->file.dead) { /* "can't happen" */ - printk(KERN_ERR "ppp: destroying undead channel %p !\n", - pch); + pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); @@ -2847,7 +2867,7 @@ static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) - printk(KERN_ERR "PPP: removing module but units remain!\n"); + pr_err("PPP: removing module but units remain!\n"); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(ppp_class, MKDEV(PPP_MAJOR, 0)); class_destroy(ppp_class); @@ -2865,7 +2885,7 @@ static int __unit_alloc(struct idr *p, void *ptr, int n) again: if (!idr_pre_get(p, GFP_KERNEL)) { - printk(KERN_ERR "PPP: No free memory for idr\n"); + pr_err("PPP: No free memory for idr\n"); return -ENOMEM; } diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index 002bac7..d4e0425 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -673,7 +673,7 @@ static void efx_fini_channels(struct efx_nic *efx) efx_for_each_channel_rx_queue(rx_queue, channel) efx_fini_rx_queue(rx_queue); - efx_for_each_channel_tx_queue(tx_queue, channel) + efx_for_each_possible_channel_tx_queue(tx_queue, channel) efx_fini_tx_queue(tx_queue); efx_fini_eventq(channel); } @@ -689,7 +689,7 @@ static void efx_remove_channel(struct efx_channel *channel) efx_for_each_channel_rx_queue(rx_queue, channel) efx_remove_rx_queue(rx_queue); - efx_for_each_channel_tx_queue(tx_queue, channel) + efx_for_each_possible_channel_tx_queue(tx_queue, channel) efx_remove_tx_queue(tx_queue); efx_remove_eventq(channel); } @@ -1271,21 +1271,8 @@ static void efx_remove_interrupts(struct efx_nic *efx) static void efx_set_channels(struct efx_nic *efx) { - struct efx_channel *channel; - struct efx_tx_queue *tx_queue; - efx->tx_channel_offset = separate_tx_channels ? efx->n_channels - efx->n_tx_channels : 0; - - /* Channel pointers were set in efx_init_struct() but we now - * need to clear them for TX queues in any RX-only channels. */ - efx_for_each_channel(channel, efx) { - if (channel->channel - efx->tx_channel_offset >= - efx->n_tx_channels) { - efx_for_each_channel_tx_queue(tx_queue, channel) - tx_queue->channel = NULL; - } - } } static int efx_probe_nic(struct efx_nic *efx) @@ -1531,9 +1518,9 @@ void efx_init_irq_moderation(struct efx_nic *efx, int tx_usecs, int rx_usecs, efx->irq_rx_adaptive = rx_adaptive; efx->irq_rx_moderation = rx_ticks; efx_for_each_channel(channel, efx) { - if (efx_channel_get_rx_queue(channel)) + if (efx_channel_has_rx_queue(channel)) channel->irq_moderation = rx_ticks; - else if (efx_channel_get_tx_queue(channel, 0)) + else if (efx_channel_has_tx_queues(channel)) channel->irq_moderation = tx_ticks; } } @@ -1849,6 +1836,7 @@ static const struct net_device_ops efx_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = efx_netpoll, #endif + .ndo_setup_tc = efx_setup_tc, }; static void efx_update_name(struct efx_nic *efx) @@ -1910,10 +1898,8 @@ static int efx_register_netdev(struct efx_nic *efx) efx_for_each_channel(channel, efx) { struct efx_tx_queue *tx_queue; - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->core_txq = netdev_get_tx_queue( - efx->net_dev, tx_queue->queue / EFX_TXQ_TYPES); - } + efx_for_each_channel_tx_queue(tx_queue, channel) + efx_init_tx_queue_core_txq(tx_queue); } /* Always start with carrier off; PHY events will detect the link */ @@ -2401,7 +2387,8 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, int i, rc; /* Allocate and initialise a struct net_device and struct efx_nic */ - net_dev = alloc_etherdev_mq(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES); + net_dev = alloc_etherdev_mqs(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES, + EFX_MAX_RX_QUEUES); if (!net_dev) return -ENOMEM; net_dev->features |= (type->offload_features | NETIF_F_SG | diff --git a/drivers/net/sfc/efx.h b/drivers/net/sfc/efx.h index d43a7e5..0cb198a 100644 --- a/drivers/net/sfc/efx.h +++ b/drivers/net/sfc/efx.h @@ -29,6 +29,7 @@ extern int efx_probe_tx_queue(struct efx_tx_queue *tx_queue); extern void efx_remove_tx_queue(struct efx_tx_queue *tx_queue); extern void efx_init_tx_queue(struct efx_tx_queue *tx_queue); +extern void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue); extern void efx_fini_tx_queue(struct efx_tx_queue *tx_queue); extern void efx_release_tx_buffers(struct efx_tx_queue *tx_queue); extern netdev_tx_t @@ -36,6 +37,7 @@ efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); extern netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); extern void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); +extern int efx_setup_tc(struct net_device *net_dev, u8 num_tc); /* RX */ extern int efx_probe_rx_queue(struct efx_rx_queue *rx_queue); diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index 0e8bb19..272cfe7 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -502,7 +502,7 @@ static void efx_ethtool_get_stats(struct net_device *net_dev, static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable) { struct efx_nic *efx __attribute__ ((unused)) = netdev_priv(net_dev); - unsigned long features; + u32 features; features = NETIF_F_TSO; if (efx->type->offload_features & NETIF_F_V6_CSUM) @@ -519,7 +519,7 @@ static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable) static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable) { struct efx_nic *efx = netdev_priv(net_dev); - unsigned long features = efx->type->offload_features & NETIF_F_ALL_CSUM; + u32 features = efx->type->offload_features & NETIF_F_ALL_CSUM; if (enable) net_dev->features |= features; @@ -631,7 +631,7 @@ static int efx_ethtool_get_coalesce(struct net_device *net_dev, /* Find lowest IRQ moderation across all used TX queues */ coalesce->tx_coalesce_usecs_irq = ~((u32) 0); efx_for_each_channel(channel, efx) { - if (!efx_channel_get_tx_queue(channel, 0)) + if (!efx_channel_has_tx_queues(channel)) continue; if (channel->irq_moderation < coalesce->tx_coalesce_usecs_irq) { if (channel->channel < efx->n_rx_channels) @@ -676,8 +676,8 @@ static int efx_ethtool_set_coalesce(struct net_device *net_dev, /* If the channel is shared only allow RX parameters to be set */ efx_for_each_channel(channel, efx) { - if (efx_channel_get_rx_queue(channel) && - efx_channel_get_tx_queue(channel, 0) && + if (efx_channel_has_rx_queue(channel) && + efx_channel_has_tx_queues(channel) && tx_usecs) { netif_err(efx, drv, efx->net_dev, "Channel is shared. " "Only RX coalescing may be set\n"); diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index 28df866..96e22ad 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -63,10 +63,12 @@ /* Checksum generation is a per-queue option in hardware, so each * queue visible to the networking core is backed by two hardware TX * queues. */ -#define EFX_MAX_CORE_TX_QUEUES EFX_MAX_CHANNELS -#define EFX_TXQ_TYPE_OFFLOAD 1 -#define EFX_TXQ_TYPES 2 -#define EFX_MAX_TX_QUEUES (EFX_TXQ_TYPES * EFX_MAX_CORE_TX_QUEUES) +#define EFX_MAX_TX_TC 2 +#define EFX_MAX_CORE_TX_QUEUES (EFX_MAX_TX_TC * EFX_MAX_CHANNELS) +#define EFX_TXQ_TYPE_OFFLOAD 1 /* flag */ +#define EFX_TXQ_TYPE_HIGHPRI 2 /* flag */ +#define EFX_TXQ_TYPES 4 +#define EFX_MAX_TX_QUEUES (EFX_TXQ_TYPES * EFX_MAX_CHANNELS) /** * struct efx_special_buffer - An Efx special buffer @@ -140,6 +142,7 @@ struct efx_tx_buffer { * @buffer: The software buffer ring * @txd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. + * @initialised: Has hardware queue been initialised? * @flushed: Used when handling queue flushing * @read_count: Current read pointer. * This is the number of buffers that have been removed from both rings. @@ -182,6 +185,7 @@ struct efx_tx_queue { struct efx_tx_buffer *buffer; struct efx_special_buffer txd; unsigned int ptr_mask; + bool initialised; enum efx_flush_state flushed; /* Members used mainly on the completion path */ @@ -377,7 +381,7 @@ struct efx_channel { bool rx_pkt_csummed; struct efx_rx_queue rx_queue; - struct efx_tx_queue tx_queue[2]; + struct efx_tx_queue tx_queue[EFX_TXQ_TYPES]; }; enum efx_led_mode { @@ -906,7 +910,7 @@ struct efx_nic_type { unsigned int phys_addr_channels; unsigned int tx_dc_base; unsigned int rx_dc_base; - unsigned long offload_features; + u32 offload_features; u32 reset_world_flags; }; @@ -938,18 +942,40 @@ efx_get_tx_queue(struct efx_nic *efx, unsigned index, unsigned type) return &efx->channel[efx->tx_channel_offset + index]->tx_queue[type]; } +static inline bool efx_channel_has_tx_queues(struct efx_channel *channel) +{ + return channel->channel - channel->efx->tx_channel_offset < + channel->efx->n_tx_channels; +} + static inline struct efx_tx_queue * efx_channel_get_tx_queue(struct efx_channel *channel, unsigned type) { - struct efx_tx_queue *tx_queue = channel->tx_queue; - EFX_BUG_ON_PARANOID(type >= EFX_TXQ_TYPES); - return tx_queue->channel ? tx_queue + type : NULL; + EFX_BUG_ON_PARANOID(!efx_channel_has_tx_queues(channel) || + type >= EFX_TXQ_TYPES); + return &channel->tx_queue[type]; +} + +static inline bool efx_tx_queue_used(struct efx_tx_queue *tx_queue) +{ + return !(tx_queue->efx->net_dev->num_tc < 2 && + tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI); } /* Iterate over all TX queues belonging to a channel */ #define efx_for_each_channel_tx_queue(_tx_queue, _channel) \ - for (_tx_queue = efx_channel_get_tx_queue(channel, 0); \ - _tx_queue && _tx_queue < (_channel)->tx_queue + EFX_TXQ_TYPES; \ + if (!efx_channel_has_tx_queues(_channel)) \ + ; \ + else \ + for (_tx_queue = (_channel)->tx_queue; \ + _tx_queue < (_channel)->tx_queue + EFX_TXQ_TYPES && \ + efx_tx_queue_used(_tx_queue); \ + _tx_queue++) + +/* Iterate over all possible TX queues belonging to a channel */ +#define efx_for_each_possible_channel_tx_queue(_tx_queue, _channel) \ + for (_tx_queue = (_channel)->tx_queue; \ + _tx_queue < (_channel)->tx_queue + EFX_TXQ_TYPES; \ _tx_queue++) static inline struct efx_rx_queue * @@ -959,18 +985,26 @@ efx_get_rx_queue(struct efx_nic *efx, unsigned index) return &efx->channel[index]->rx_queue; } +static inline bool efx_channel_has_rx_queue(struct efx_channel *channel) +{ + return channel->channel < channel->efx->n_rx_channels; +} + static inline struct efx_rx_queue * efx_channel_get_rx_queue(struct efx_channel *channel) { - return channel->channel < channel->efx->n_rx_channels ? - &channel->rx_queue : NULL; + EFX_BUG_ON_PARANOID(!efx_channel_has_rx_queue(channel)); + return &channel->rx_queue; } /* Iterate over all RX queues belonging to a channel */ #define efx_for_each_channel_rx_queue(_rx_queue, _channel) \ - for (_rx_queue = efx_channel_get_rx_queue(channel); \ - _rx_queue; \ - _rx_queue = NULL) + if (!efx_channel_has_rx_queue(_channel)) \ + ; \ + else \ + for (_rx_queue = &(_channel)->rx_queue; \ + _rx_queue; \ + _rx_queue = NULL) static inline struct efx_channel * efx_rx_queue_channel(struct efx_rx_queue *rx_queue) diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c index da38659..1d0b8b6 100644 --- a/drivers/net/sfc/nic.c +++ b/drivers/net/sfc/nic.c @@ -445,8 +445,8 @@ int efx_nic_probe_tx(struct efx_tx_queue *tx_queue) void efx_nic_init_tx(struct efx_tx_queue *tx_queue) { - efx_oword_t tx_desc_ptr; struct efx_nic *efx = tx_queue->efx; + efx_oword_t reg; tx_queue->flushed = FLUSH_NONE; @@ -454,7 +454,7 @@ void efx_nic_init_tx(struct efx_tx_queue *tx_queue) efx_init_special_buffer(efx, &tx_queue->txd); /* Push TX descriptor ring to card */ - EFX_POPULATE_OWORD_10(tx_desc_ptr, + EFX_POPULATE_OWORD_10(reg, FRF_AZ_TX_DESCQ_EN, 1, FRF_AZ_TX_ISCSI_DDIG_EN, 0, FRF_AZ_TX_ISCSI_HDIG_EN, 0, @@ -470,17 +470,15 @@ void efx_nic_init_tx(struct efx_tx_queue *tx_queue) if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { int csum = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD; - EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_IP_CHKSM_DIS, !csum); - EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_TCP_CHKSM_DIS, + EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_IP_CHKSM_DIS, !csum); + EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_TCP_CHKSM_DIS, !csum); } - efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base, + efx_writeo_table(efx, ®, efx->type->txd_ptr_tbl_base, tx_queue->queue); if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) { - efx_oword_t reg; - /* Only 128 bits in this register */ BUILD_BUG_ON(EFX_MAX_TX_QUEUES > 128); @@ -491,6 +489,16 @@ void efx_nic_init_tx(struct efx_tx_queue *tx_queue) set_bit_le(tx_queue->queue, (void *)®); efx_writeo(efx, ®, FR_AA_TX_CHKSM_CFG); } + + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { + EFX_POPULATE_OWORD_1(reg, + FRF_BZ_TX_PACE, + (tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI) ? + FFE_BZ_TX_PACE_OFF : + FFE_BZ_TX_PACE_RESERVED); + efx_writeo_table(efx, ®, FR_BZ_TX_PACE_TBL, + tx_queue->queue); + } } static void efx_flush_tx_queue(struct efx_tx_queue *tx_queue) @@ -1238,8 +1246,10 @@ int efx_nic_flush_queues(struct efx_nic *efx) /* Flush all tx queues in parallel */ efx_for_each_channel(channel, efx) { - efx_for_each_channel_tx_queue(tx_queue, channel) - efx_flush_tx_queue(tx_queue); + efx_for_each_possible_channel_tx_queue(tx_queue, channel) { + if (tx_queue->initialised) + efx_flush_tx_queue(tx_queue); + } } /* The hardware supports four concurrent rx flushes, each of which may @@ -1262,8 +1272,9 @@ int efx_nic_flush_queues(struct efx_nic *efx) ++rx_pending; } } - efx_for_each_channel_tx_queue(tx_queue, channel) { - if (tx_queue->flushed != FLUSH_DONE) + efx_for_each_possible_channel_tx_queue(tx_queue, channel) { + if (tx_queue->initialised && + tx_queue->flushed != FLUSH_DONE) ++tx_pending; } } @@ -1278,8 +1289,9 @@ int efx_nic_flush_queues(struct efx_nic *efx) /* Mark the queues as all flushed. We're going to return failure * leading to a reset, or fake up success anyway */ efx_for_each_channel(channel, efx) { - efx_for_each_channel_tx_queue(tx_queue, channel) { - if (tx_queue->flushed != FLUSH_DONE) + efx_for_each_possible_channel_tx_queue(tx_queue, channel) { + if (tx_queue->initialised && + tx_queue->flushed != FLUSH_DONE) netif_err(efx, hw, efx->net_dev, "tx queue %d flush command timed out\n", tx_queue->queue); @@ -1682,6 +1694,19 @@ void efx_nic_init_common(struct efx_nic *efx) if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1); efx_writeo(efx, &temp, FR_AZ_TX_RESERVED); + + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { + EFX_POPULATE_OWORD_4(temp, + /* Default values */ + FRF_BZ_TX_PACE_SB_NOT_AF, 0x15, + FRF_BZ_TX_PACE_SB_AF, 0xb, + FRF_BZ_TX_PACE_FB_BASE, 0, + /* Allow large pace values in the + * fast bin. */ + FRF_BZ_TX_PACE_BIN_TH, + FFE_BZ_TX_PACE_RESERVED); + efx_writeo(efx, &temp, FR_BZ_TX_PACE); + } } /* Register dump */ diff --git a/drivers/net/sfc/regs.h b/drivers/net/sfc/regs.h index 96430ed..8227de6 100644 --- a/drivers/net/sfc/regs.h +++ b/drivers/net/sfc/regs.h @@ -2907,6 +2907,12 @@ #define FRF_CZ_TMFT_SRC_MAC_HI_LBN 44 #define FRF_CZ_TMFT_SRC_MAC_HI_WIDTH 16 +/* TX_PACE_TBL */ +/* Values >20 are documented as reserved, but will result in a queue going + * into the fast bin with a pace value of zero. */ +#define FFE_BZ_TX_PACE_OFF 0 +#define FFE_BZ_TX_PACE_RESERVED 21 + /* DRIVER_EV */ /* Sub-fields of an RX flush completion event */ #define FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL_LBN 12 diff --git a/drivers/net/sfc/selftest.c b/drivers/net/sfc/selftest.c index 0ebfb99..f936892 100644 --- a/drivers/net/sfc/selftest.c +++ b/drivers/net/sfc/selftest.c @@ -644,7 +644,7 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests, goto out; } - /* Test both types of TX queue */ + /* Test all enabled types of TX queue */ efx_for_each_channel_tx_queue(tx_queue, channel) { state->offload_csum = (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD); diff --git a/drivers/net/sfc/tx.c b/drivers/net/sfc/tx.c index 2f5e9da..1a51653 100644 --- a/drivers/net/sfc/tx.c +++ b/drivers/net/sfc/tx.c @@ -336,17 +336,91 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, { struct efx_nic *efx = netdev_priv(net_dev); struct efx_tx_queue *tx_queue; + unsigned index, type; if (unlikely(efx->port_inhibited)) return NETDEV_TX_BUSY; - tx_queue = efx_get_tx_queue(efx, skb_get_queue_mapping(skb), - skb->ip_summed == CHECKSUM_PARTIAL ? - EFX_TXQ_TYPE_OFFLOAD : 0); + index = skb_get_queue_mapping(skb); + type = skb->ip_summed == CHECKSUM_PARTIAL ? EFX_TXQ_TYPE_OFFLOAD : 0; + if (index >= efx->n_tx_channels) { + index -= efx->n_tx_channels; + type |= EFX_TXQ_TYPE_HIGHPRI; + } + tx_queue = efx_get_tx_queue(efx, index, type); return efx_enqueue_skb(tx_queue, skb); } +void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue) +{ + struct efx_nic *efx = tx_queue->efx; + + /* Must be inverse of queue lookup in efx_hard_start_xmit() */ + tx_queue->core_txq = + netdev_get_tx_queue(efx->net_dev, + tx_queue->queue / EFX_TXQ_TYPES + + ((tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI) ? + efx->n_tx_channels : 0)); +} + +int efx_setup_tc(struct net_device *net_dev, u8 num_tc) +{ + struct efx_nic *efx = netdev_priv(net_dev); + struct efx_channel *channel; + struct efx_tx_queue *tx_queue; + unsigned tc; + int rc; + + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0 || num_tc > EFX_MAX_TX_TC) + return -EINVAL; + + if (num_tc == net_dev->num_tc) + return 0; + + for (tc = 0; tc < num_tc; tc++) { + net_dev->tc_to_txq[tc].offset = tc * efx->n_tx_channels; + net_dev->tc_to_txq[tc].count = efx->n_tx_channels; + } + + if (num_tc > net_dev->num_tc) { + /* Initialise high-priority queues as necessary */ + efx_for_each_channel(channel, efx) { + efx_for_each_possible_channel_tx_queue(tx_queue, + channel) { + if (!(tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI)) + continue; + if (!tx_queue->buffer) { + rc = efx_probe_tx_queue(tx_queue); + if (rc) + return rc; + } + if (!tx_queue->initialised) + efx_init_tx_queue(tx_queue); + efx_init_tx_queue_core_txq(tx_queue); + } + } + } else { + /* Reduce number of classes before number of queues */ + net_dev->num_tc = num_tc; + } + + rc = netif_set_real_num_tx_queues(net_dev, + max_t(int, num_tc, 1) * + efx->n_tx_channels); + if (rc) + return rc; + + /* Do not destroy high-priority queues when they become + * unused. We would have to flush them first, and it is + * fairly difficult to flush a subset of TX queues. Leave + * it to efx_fini_channels(). + */ + + net_dev->num_tc = num_tc; + return 0; +} + void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) { unsigned fill_level; @@ -430,6 +504,8 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) /* Set up TX descriptor ring */ efx_nic_init_tx(tx_queue); + + tx_queue->initialised = true; } void efx_release_tx_buffers(struct efx_tx_queue *tx_queue) @@ -452,9 +528,14 @@ void efx_release_tx_buffers(struct efx_tx_queue *tx_queue) void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) { + if (!tx_queue->initialised) + return; + netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev, "shutting down TX queue %d\n", tx_queue->queue); + tx_queue->initialised = false; + /* Flush TX queue, remove descriptor ring */ efx_nic_fini_tx(tx_queue); @@ -466,6 +547,9 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) { + if (!tx_queue->buffer) + return; + netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev, "destroying TX queue %d\n", tx_queue->queue); efx_nic_remove_tx(tx_queue); diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c index 726df61..43654a3 100644 --- a/drivers/net/smc91x.c +++ b/drivers/net/smc91x.c @@ -81,6 +81,7 @@ static const char version[] = #include <linux/ethtool.h> #include <linux/mii.h> #include <linux/workqueue.h> +#include <linux/of.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -2394,6 +2395,15 @@ static int smc_drv_resume(struct device *dev) return 0; } +#ifdef CONFIG_OF +static const struct of_device_id smc91x_match[] = { + { .compatible = "smsc,lan91c94", }, + { .compatible = "smsc,lan91c111", }, + {}, +} +MODULE_DEVICE_TABLE(of, smc91x_match); +#endif + static struct dev_pm_ops smc_drv_pm_ops = { .suspend = smc_drv_suspend, .resume = smc_drv_resume, @@ -2406,6 +2416,9 @@ static struct platform_driver smc_driver = { .name = CARDNAME, .owner = THIS_MODULE, .pm = &smc_drv_pm_ops, +#ifdef CONFIG_OF + .of_match_table = smc91x_match, +#endif }, }; diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index 1c5408f..c1a3448 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -320,28 +320,28 @@ static int gem_txmac_interrupt(struct net_device *dev, struct gem *gp, u32 gem_s if (txmac_stat & MAC_TXSTAT_URUN) { netdev_err(dev, "TX MAC xmit underrun\n"); - gp->net_stats.tx_fifo_errors++; + dev->stats.tx_fifo_errors++; } if (txmac_stat & MAC_TXSTAT_MPE) { netdev_err(dev, "TX MAC max packet size error\n"); - gp->net_stats.tx_errors++; + dev->stats.tx_errors++; } /* The rest are all cases of one of the 16-bit TX * counters expiring. */ if (txmac_stat & MAC_TXSTAT_NCE) - gp->net_stats.collisions += 0x10000; + dev->stats.collisions += 0x10000; if (txmac_stat & MAC_TXSTAT_ECE) { - gp->net_stats.tx_aborted_errors += 0x10000; - gp->net_stats.collisions += 0x10000; + dev->stats.tx_aborted_errors += 0x10000; + dev->stats.collisions += 0x10000; } if (txmac_stat & MAC_TXSTAT_LCE) { - gp->net_stats.tx_aborted_errors += 0x10000; - gp->net_stats.collisions += 0x10000; + dev->stats.tx_aborted_errors += 0x10000; + dev->stats.collisions += 0x10000; } /* We do not keep track of MAC_TXSTAT_FCE and @@ -469,20 +469,20 @@ static int gem_rxmac_interrupt(struct net_device *dev, struct gem *gp, u32 gem_s u32 smac = readl(gp->regs + MAC_SMACHINE); netdev_err(dev, "RX MAC fifo overflow smac[%08x]\n", smac); - gp->net_stats.rx_over_errors++; - gp->net_stats.rx_fifo_errors++; + dev->stats.rx_over_errors++; + dev->stats.rx_fifo_errors++; ret = gem_rxmac_reset(gp); } if (rxmac_stat & MAC_RXSTAT_ACE) - gp->net_stats.rx_frame_errors += 0x10000; + dev->stats.rx_frame_errors += 0x10000; if (rxmac_stat & MAC_RXSTAT_CCE) - gp->net_stats.rx_crc_errors += 0x10000; + dev->stats.rx_crc_errors += 0x10000; if (rxmac_stat & MAC_RXSTAT_LCE) - gp->net_stats.rx_length_errors += 0x10000; + dev->stats.rx_length_errors += 0x10000; /* We do not track MAC_RXSTAT_FCE and MAC_RXSTAT_VCE * events. @@ -594,7 +594,7 @@ static int gem_abnormal_irq(struct net_device *dev, struct gem *gp, u32 gem_stat if (netif_msg_rx_err(gp)) printk(KERN_DEBUG "%s: no buffer for rx frame\n", gp->dev->name); - gp->net_stats.rx_dropped++; + dev->stats.rx_dropped++; } if (gem_status & GREG_STAT_RXTAGERR) { @@ -602,7 +602,7 @@ static int gem_abnormal_irq(struct net_device *dev, struct gem *gp, u32 gem_stat if (netif_msg_rx_err(gp)) printk(KERN_DEBUG "%s: corrupt rx tag framing\n", gp->dev->name); - gp->net_stats.rx_errors++; + dev->stats.rx_errors++; goto do_reset; } @@ -684,7 +684,7 @@ static __inline__ void gem_tx(struct net_device *dev, struct gem *gp, u32 gem_st break; } gp->tx_skbs[entry] = NULL; - gp->net_stats.tx_bytes += skb->len; + dev->stats.tx_bytes += skb->len; for (frag = 0; frag <= skb_shinfo(skb)->nr_frags; frag++) { txd = &gp->init_block->txd[entry]; @@ -696,7 +696,7 @@ static __inline__ void gem_tx(struct net_device *dev, struct gem *gp, u32 gem_st entry = NEXT_TX(entry); } - gp->net_stats.tx_packets++; + dev->stats.tx_packets++; dev_kfree_skb_irq(skb); } gp->tx_old = entry; @@ -738,6 +738,7 @@ static __inline__ void gem_post_rxds(struct gem *gp, int limit) static int gem_rx(struct gem *gp, int work_to_do) { + struct net_device *dev = gp->dev; int entry, drops, work_done = 0; u32 done; __sum16 csum; @@ -782,15 +783,15 @@ static int gem_rx(struct gem *gp, int work_to_do) len = (status & RXDCTRL_BUFSZ) >> 16; if ((len < ETH_ZLEN) || (status & RXDCTRL_BAD)) { - gp->net_stats.rx_errors++; + dev->stats.rx_errors++; if (len < ETH_ZLEN) - gp->net_stats.rx_length_errors++; + dev->stats.rx_length_errors++; if (len & RXDCTRL_BAD) - gp->net_stats.rx_crc_errors++; + dev->stats.rx_crc_errors++; /* We'll just return it to GEM. */ drop_it: - gp->net_stats.rx_dropped++; + dev->stats.rx_dropped++; goto next; } @@ -843,8 +844,8 @@ static int gem_rx(struct gem *gp, int work_to_do) netif_receive_skb(skb); - gp->net_stats.rx_packets++; - gp->net_stats.rx_bytes += len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; next: entry = NEXT_RX(entry); @@ -2472,7 +2473,6 @@ static int gem_resume(struct pci_dev *pdev) static struct net_device_stats *gem_get_stats(struct net_device *dev) { struct gem *gp = netdev_priv(dev); - struct net_device_stats *stats = &gp->net_stats; spin_lock_irq(&gp->lock); spin_lock(&gp->tx_lock); @@ -2481,17 +2481,17 @@ static struct net_device_stats *gem_get_stats(struct net_device *dev) * so we shield against this */ if (gp->running) { - stats->rx_crc_errors += readl(gp->regs + MAC_FCSERR); + dev->stats.rx_crc_errors += readl(gp->regs + MAC_FCSERR); writel(0, gp->regs + MAC_FCSERR); - stats->rx_frame_errors += readl(gp->regs + MAC_AERR); + dev->stats.rx_frame_errors += readl(gp->regs + MAC_AERR); writel(0, gp->regs + MAC_AERR); - stats->rx_length_errors += readl(gp->regs + MAC_LERR); + dev->stats.rx_length_errors += readl(gp->regs + MAC_LERR); writel(0, gp->regs + MAC_LERR); - stats->tx_aborted_errors += readl(gp->regs + MAC_ECOLL); - stats->collisions += + dev->stats.tx_aborted_errors += readl(gp->regs + MAC_ECOLL); + dev->stats.collisions += (readl(gp->regs + MAC_ECOLL) + readl(gp->regs + MAC_LCOLL)); writel(0, gp->regs + MAC_ECOLL); @@ -2501,7 +2501,7 @@ static struct net_device_stats *gem_get_stats(struct net_device *dev) spin_unlock(&gp->tx_lock); spin_unlock_irq(&gp->lock); - return &gp->net_stats; + return &dev->stats; } static int gem_set_mac_address(struct net_device *dev, void *addr) diff --git a/drivers/net/sungem.h b/drivers/net/sungem.h index 1990546..ede0178 100644 --- a/drivers/net/sungem.h +++ b/drivers/net/sungem.h @@ -994,7 +994,6 @@ struct gem { u32 status; struct napi_struct napi; - struct net_device_stats net_stats; int tx_fifo_sz; int rx_fifo_sz; diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 06c0e503..6be4185 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -4,7 +4,7 @@ * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com) * Copyright (C) 2001, 2002, 2003 Jeff Garzik (jgarzik@pobox.com) * Copyright (C) 2004 Sun Microsystems Inc. - * Copyright (C) 2005-2010 Broadcom Corporation. + * Copyright (C) 2005-2011 Broadcom Corporation. * * Firmware is: * Derived from proprietary unpublished source code, @@ -64,10 +64,10 @@ #define DRV_MODULE_NAME "tg3" #define TG3_MAJ_NUM 3 -#define TG3_MIN_NUM 116 +#define TG3_MIN_NUM 117 #define DRV_MODULE_VERSION \ __stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM) -#define DRV_MODULE_RELDATE "December 3, 2010" +#define DRV_MODULE_RELDATE "January 25, 2011" #define TG3_DEF_MAC_MODE 0 #define TG3_DEF_RX_MODE 0 @@ -1776,9 +1776,29 @@ static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) tg3_phy_cl45_read(tp, MDIO_MMD_AN, TG3_CL45_D7_EEERES_STAT, &val); - if (val == TG3_CL45_D7_EEERES_STAT_LP_1000T || - val == TG3_CL45_D7_EEERES_STAT_LP_100TX) + switch (val) { + case TG3_CL45_D7_EEERES_STAT_LP_1000T: + switch (GET_ASIC_REV(tp->pci_chip_rev_id)) { + case ASIC_REV_5717: + case ASIC_REV_5719: + case ASIC_REV_57765: + /* Enable SM_DSP clock and tx 6dB coding. */ + val = MII_TG3_AUXCTL_SHDWSEL_AUXCTL | + MII_TG3_AUXCTL_ACTL_SMDSP_ENA | + MII_TG3_AUXCTL_ACTL_TX_6DB; + tg3_writephy(tp, MII_TG3_AUX_CTRL, val); + + tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, 0x0000); + + /* Turn off SM_DSP clock. */ + val = MII_TG3_AUXCTL_SHDWSEL_AUXCTL | + MII_TG3_AUXCTL_ACTL_TX_6DB; + tg3_writephy(tp, MII_TG3_AUX_CTRL, val); + } + /* Fallthrough */ + case TG3_CL45_D7_EEERES_STAT_LP_100TX: tp->setlpicnt = 2; + } } if (!tp->setlpicnt) { @@ -2968,11 +2988,19 @@ static void tg3_phy_copper_begin(struct tg3 *tp) MII_TG3_AUXCTL_ACTL_TX_6DB; tg3_writephy(tp, MII_TG3_AUX_CTRL, val); - if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) && - !tg3_phydsp_read(tp, MII_TG3_DSP_CH34TP2, &val)) - tg3_phydsp_write(tp, MII_TG3_DSP_CH34TP2, - val | MII_TG3_DSP_CH34TP2_HIBW01); + switch (GET_ASIC_REV(tp->pci_chip_rev_id)) { + case ASIC_REV_5717: + case ASIC_REV_57765: + if (!tg3_phydsp_read(tp, MII_TG3_DSP_CH34TP2, &val)) + tg3_phydsp_write(tp, MII_TG3_DSP_CH34TP2, val | + MII_TG3_DSP_CH34TP2_HIBW01); + /* Fall through */ + case ASIC_REV_5719: + val = MII_TG3_DSP_TAP26_ALNOKO | + MII_TG3_DSP_TAP26_RMRXSTO | + MII_TG3_DSP_TAP26_OPCSINPT; + tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val); + } val = 0; if (tp->link_config.autoneg == AUTONEG_ENABLE) { @@ -7801,7 +7829,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) TG3_CPMU_DBTMR1_LNKIDLE_2047US); tw32_f(TG3_CPMU_EEE_DBTMR2, - TG3_CPMU_DBTMR1_APE_TX_2047US | + TG3_CPMU_DBTMR2_APE_TX_2047US | TG3_CPMU_DBTMR2_TXIDXEQ_2047US); } @@ -8075,8 +8103,9 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) /* Program the jumbo buffer descriptor ring control * blocks on those devices that have them. */ - if ((tp->tg3_flags & TG3_FLAG_JUMBO_CAPABLE) && - !(tp->tg3_flags2 & TG3_FLG2_5780_CLASS)) { + if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0 || + ((tp->tg3_flags & TG3_FLAG_JUMBO_CAPABLE) && + !(tp->tg3_flags2 & TG3_FLG2_5780_CLASS))) { /* Setup replenish threshold. */ tw32(RCVBDI_JUMBO_THRESH, tp->rx_jumbo_pending / 8); @@ -8194,8 +8223,12 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) (tp->tg3_flags3 & TG3_FLG3_5717_PLUS)) { val = tr32(TG3_RDMA_RSRVCTRL_REG); if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) { - val &= ~TG3_RDMA_RSRVCTRL_TXMRGN_MASK; - val |= TG3_RDMA_RSRVCTRL_TXMRGN_320B; + val &= ~(TG3_RDMA_RSRVCTRL_TXMRGN_MASK | + TG3_RDMA_RSRVCTRL_FIFO_LWM_MASK | + TG3_RDMA_RSRVCTRL_FIFO_HWM_MASK); + val |= TG3_RDMA_RSRVCTRL_TXMRGN_320B | + TG3_RDMA_RSRVCTRL_FIFO_LWM_1_5K | + TG3_RDMA_RSRVCTRL_FIFO_HWM_1_5K; } tw32(TG3_RDMA_RSRVCTRL_REG, val | TG3_RDMA_RSRVCTRL_FIFO_OFLW_FIX); @@ -8317,7 +8350,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) tw32_f(GRC_LOCAL_CTRL, tp->grc_local_ctrl); udelay(100); - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) { + if ((tp->tg3_flags2 & TG3_FLG2_USING_MSIX) && + tp->irq_cnt > 1) { val = tr32(MSGINT_MODE); val |= MSGINT_MODE_MULTIVEC_EN | MSGINT_MODE_ENABLE; tw32(MSGINT_MODE, val); @@ -9057,7 +9091,8 @@ static void tg3_ints_init(struct tg3 *tp) if (tp->tg3_flags2 & TG3_FLG2_USING_MSI_OR_MSIX) { u32 msi_mode = tr32(MSGINT_MODE); - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) + if ((tp->tg3_flags2 & TG3_FLG2_USING_MSIX) && + tp->irq_cnt > 1) msi_mode |= MSGINT_MODE_MULTIVEC_EN; tw32(MSGINT_MODE, msi_mode | MSGINT_MODE_ENABLE); } @@ -10833,13 +10868,16 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) if (loopback_mode == TG3_MAC_LOOPBACK) { /* HW errata - mac loopback fails in some cases on 5780. * Normal traffic and PHY loopback are not affected by - * errata. + * errata. Also, the MAC loopback test is deprecated for + * all newer ASIC revisions. */ - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5780) + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5780 || + (tp->tg3_flags & TG3_FLAG_CPMU_PRESENT)) return 0; - mac_mode = (tp->mac_mode & ~MAC_MODE_PORT_MODE_MASK) | - MAC_MODE_PORT_INT_LPBACK; + mac_mode = tp->mac_mode & + ~(MAC_MODE_PORT_MODE_MASK | MAC_MODE_HALF_DUPLEX); + mac_mode |= MAC_MODE_PORT_INT_LPBACK; if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) mac_mode |= MAC_MODE_LINK_POLARITY; if (tp->phy_flags & TG3_PHYFLG_10_100_ONLY) @@ -10861,7 +10899,8 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) tg3_writephy(tp, MII_BMCR, val); udelay(40); - mac_mode = tp->mac_mode & ~MAC_MODE_PORT_MODE_MASK; + mac_mode = tp->mac_mode & + ~(MAC_MODE_PORT_MODE_MASK | MAC_MODE_HALF_DUPLEX); if (tp->phy_flags & TG3_PHYFLG_IS_FET) { tg3_writephy(tp, MII_TG3_FET_PTEST, MII_TG3_FET_PTEST_FRC_TX_LINK | @@ -10889,6 +10928,13 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) MII_TG3_EXT_CTRL_LNK3_LED_MODE); } tw32(MAC_MODE, mac_mode); + + /* Wait for link */ + for (i = 0; i < 100; i++) { + if (tr32(MAC_TX_STATUS) & TX_STATUS_LINK_UP) + break; + mdelay(1); + } } else { return -EINVAL; } @@ -10995,14 +11041,19 @@ out: static int tg3_test_loopback(struct tg3 *tp) { int err = 0; - u32 cpmuctrl = 0; + u32 eee_cap, cpmuctrl = 0; if (!netif_running(tp->dev)) return TG3_LOOPBACK_FAILED; + eee_cap = tp->phy_flags & TG3_PHYFLG_EEE_CAP; + tp->phy_flags &= ~TG3_PHYFLG_EEE_CAP; + err = tg3_reset_hw(tp, 1); - if (err) - return TG3_LOOPBACK_FAILED; + if (err) { + err = TG3_LOOPBACK_FAILED; + goto done; + } /* Turn off gphy autopowerdown. */ if (tp->phy_flags & TG3_PHYFLG_ENABLE_APD) @@ -11022,8 +11073,10 @@ static int tg3_test_loopback(struct tg3 *tp) udelay(10); } - if (status != CPMU_MUTEX_GNT_DRIVER) - return TG3_LOOPBACK_FAILED; + if (status != CPMU_MUTEX_GNT_DRIVER) { + err = TG3_LOOPBACK_FAILED; + goto done; + } /* Turn off link-based power management. */ cpmuctrl = tr32(TG3_CPMU_CTRL); @@ -11052,6 +11105,9 @@ static int tg3_test_loopback(struct tg3 *tp) if (tp->phy_flags & TG3_PHYFLG_ENABLE_APD) tg3_phy_toggle_apd(tp, true); +done: + tp->phy_flags |= eee_cap; + return err; } @@ -12407,9 +12463,11 @@ static void __devinit tg3_get_eeprom_hw_cfg(struct tg3 *tp) tp->tg3_flags3 |= TG3_FLG3_RGMII_EXT_IBND_TX_EN; } done: - device_init_wakeup(&tp->pdev->dev, tp->tg3_flags & TG3_FLAG_WOL_CAP); - device_set_wakeup_enable(&tp->pdev->dev, + if (tp->tg3_flags & TG3_FLAG_WOL_CAP) + device_set_wakeup_enable(&tp->pdev->dev, tp->tg3_flags & TG3_FLAG_WOL_ENABLE); + else + device_set_wakeup_capable(&tp->pdev->dev, false); } static int __devinit tg3_issue_otp_command(struct tg3 *tp, u32 cmd) @@ -13262,7 +13320,9 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } /* Determine TSO capabilities */ - if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) + ; /* Do nothing. HW bug. */ + else if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) tp->tg3_flags2 |= TG3_FLG2_HW_TSO_3; else if ((tp->tg3_flags3 & TG3_FLG3_5755_PLUS) || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) @@ -13313,7 +13373,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tp->tg3_flags3 |= TG3_FLG3_40BIT_DMA_LIMIT_BUG; } - if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) + if ((tp->tg3_flags3 & TG3_FLG3_5717_PLUS) && + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5719) tp->tg3_flags3 |= TG3_FLG3_USE_JUMBO_BDFLAG; if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS) || @@ -13331,42 +13392,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tp->tg3_flags2 |= TG3_FLG2_PCI_EXPRESS; tp->pcie_readrq = 4096; - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) { - u16 word; - - pci_read_config_word(tp->pdev, - tp->pcie_cap + PCI_EXP_LNKSTA, - &word); - switch (word & PCI_EXP_LNKSTA_CLS) { - case PCI_EXP_LNKSTA_CLS_2_5GB: - word &= PCI_EXP_LNKSTA_NLW; - word >>= PCI_EXP_LNKSTA_NLW_SHIFT; - switch (word) { - case 2: - tp->pcie_readrq = 2048; - break; - case 4: - tp->pcie_readrq = 1024; - break; - } - break; - - case PCI_EXP_LNKSTA_CLS_5_0GB: - word &= PCI_EXP_LNKSTA_NLW; - word >>= PCI_EXP_LNKSTA_NLW_SHIFT; - switch (word) { - case 1: - tp->pcie_readrq = 2048; - break; - case 2: - tp->pcie_readrq = 1024; - break; - case 4: - tp->pcie_readrq = 512; - break; - } - } - } + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) + tp->pcie_readrq = 2048; pcie_set_readrq(tp->pdev, tp->pcie_readrq); diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index f528243..73884b6 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -4,7 +4,7 @@ * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com) * Copyright (C) 2001 Jeff Garzik (jgarzik@pobox.com) * Copyright (C) 2004 Sun Microsystems Inc. - * Copyright (C) 2007-2010 Broadcom Corporation. + * Copyright (C) 2007-2011 Broadcom Corporation. */ #ifndef _T3_H @@ -141,6 +141,7 @@ #define CHIPREV_ID_57780_A1 0x57780001 #define CHIPREV_ID_5717_A0 0x05717000 #define CHIPREV_ID_57765_A0 0x57785000 +#define CHIPREV_ID_5719_A0 0x05719000 #define GET_ASIC_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 12) #define ASIC_REV_5700 0x07 #define ASIC_REV_5701 0x00 @@ -1105,7 +1106,7 @@ #define TG3_CPMU_DBTMR1_PCIEXIT_2047US 0x07ff0000 #define TG3_CPMU_DBTMR1_LNKIDLE_2047US 0x000070ff #define TG3_CPMU_EEE_DBTMR2 0x000036b8 -#define TG3_CPMU_DBTMR1_APE_TX_2047US 0x07ff0000 +#define TG3_CPMU_DBTMR2_APE_TX_2047US 0x07ff0000 #define TG3_CPMU_DBTMR2_TXIDXEQ_2047US 0x000070ff #define TG3_CPMU_EEE_LNKIDL_CTRL 0x000036bc #define TG3_CPMU_EEE_LNKIDL_PCIE_NL0 0x01000000 @@ -1333,6 +1334,10 @@ #define TG3_RDMA_RSRVCTRL_REG 0x00004900 #define TG3_RDMA_RSRVCTRL_FIFO_OFLW_FIX 0x00000004 +#define TG3_RDMA_RSRVCTRL_FIFO_LWM_1_5K 0x00000c00 +#define TG3_RDMA_RSRVCTRL_FIFO_LWM_MASK 0x00000ff0 +#define TG3_RDMA_RSRVCTRL_FIFO_HWM_1_5K 0x000c0000 +#define TG3_RDMA_RSRVCTRL_FIFO_HWM_MASK 0x000ff000 #define TG3_RDMA_RSRVCTRL_TXMRGN_320B 0x28000000 #define TG3_RDMA_RSRVCTRL_TXMRGN_MASK 0xffe00000 /* 0x4904 --> 0x4910 unused */ @@ -2108,6 +2113,10 @@ #define MII_TG3_DSP_TAP1 0x0001 #define MII_TG3_DSP_TAP1_AGCTGT_DFLT 0x0007 +#define MII_TG3_DSP_TAP26 0x001a +#define MII_TG3_DSP_TAP26_ALNOKO 0x0001 +#define MII_TG3_DSP_TAP26_RMRXSTO 0x0002 +#define MII_TG3_DSP_TAP26_OPCSINPT 0x0004 #define MII_TG3_DSP_AADJ1CH0 0x001f #define MII_TG3_DSP_CH34TP2 0x4022 #define MII_TG3_DSP_CH34TP2_HIBW01 0x0010 diff --git a/drivers/net/tlan.c b/drivers/net/tlan.c index f8e463c..e48a808 100644 --- a/drivers/net/tlan.c +++ b/drivers/net/tlan.c @@ -63,45 +63,45 @@ * - Other minor stuff * * v1.4 Feb 10, 2000 - Updated with more changes required after Dave's - * network cleanup in 2.3.43pre7 (Tigran & myself) - * - Minor stuff. + * network cleanup in 2.3.43pre7 (Tigran & myself) + * - Minor stuff. * - * v1.5 March 22, 2000 - Fixed another timer bug that would hang the driver - * if no cable/link were present. + * v1.5 March 22, 2000 - Fixed another timer bug that would hang the + * driver if no cable/link were present. * - Cosmetic changes. * - TODO: Port completely to new PCI/DMA API - * Auto-Neg fallback. - * - * v1.6 April 04, 2000 - Fixed driver support for kernel-parameters. Haven't - * tested it though, as the kernel support is currently - * broken (2.3.99p4p3). - * - Updated tlan.txt accordingly. - * - Adjusted minimum/maximum frame length. - * - There is now a TLAN website up at - * http://hp.sourceforge.net/ - * - * v1.7 April 07, 2000 - Started to implement custom ioctls. Driver now - * reports PHY information when used with Donald - * Beckers userspace MII diagnostics utility. - * - * v1.8 April 23, 2000 - Fixed support for forced speed/duplex settings. - * - Added link information to Auto-Neg and forced - * modes. When NIC operates with auto-neg the driver - * will report Link speed & duplex modes as well as - * link partner abilities. When forced link is used, - * the driver will report status of the established - * link. - * Please read tlan.txt for additional information. - * - Removed call to check_region(), and used - * return value of request_region() instead. + * Auto-Neg fallback. + * + * v1.6 April 04, 2000 - Fixed driver support for kernel-parameters. + * Haven't tested it though, as the kernel support + * is currently broken (2.3.99p4p3). + * - Updated tlan.txt accordingly. + * - Adjusted minimum/maximum frame length. + * - There is now a TLAN website up at + * http://hp.sourceforge.net/ + * + * v1.7 April 07, 2000 - Started to implement custom ioctls. Driver now + * reports PHY information when used with Donald + * Beckers userspace MII diagnostics utility. + * + * v1.8 April 23, 2000 - Fixed support for forced speed/duplex settings. + * - Added link information to Auto-Neg and forced + * modes. When NIC operates with auto-neg the driver + * will report Link speed & duplex modes as well as + * link partner abilities. When forced link is used, + * the driver will report status of the established + * link. + * Please read tlan.txt for additional information. + * - Removed call to check_region(), and used + * return value of request_region() instead. * * v1.8a May 28, 2000 - Minor updates. * * v1.9 July 25, 2000 - Fixed a few remaining Full-Duplex issues. - * - Updated with timer fixes from Andrew Morton. - * - Fixed module race in TLan_Open. - * - Added routine to monitor PHY status. - * - Added activity led support for Proliant devices. + * - Updated with timer fixes from Andrew Morton. + * - Fixed module race in TLan_Open. + * - Added routine to monitor PHY status. + * - Added activity led support for Proliant devices. * * v1.10 Aug 30, 2000 - Added support for EISA based tlan controllers * like the Compaq NetFlex3/E. @@ -111,8 +111,8 @@ * hardware probe is done with kernel API and * TLan_EisaProbe. * - Adjusted debug information for probing. - * - Fixed bug that would cause general debug information - * to be printed after driver removal. + * - Fixed bug that would cause general debug + * information to be printed after driver removal. * - Added transmit timeout handling. * - Fixed OOM return values in tlan_probe. * - Fixed possible mem leak in tlan_exit @@ -136,8 +136,8 @@ * * v1.12 Oct 12, 2000 - Minor fixes (memleak, init, etc.) * - * v1.13 Nov 28, 2000 - Stop flooding console with auto-neg issues - * when link can't be established. + * v1.13 Nov 28, 2000 - Stop flooding console with auto-neg issues + * when link can't be established. * - Added the bbuf option as a kernel parameter. * - Fixed ioaddr probe bug. * - Fixed stupid deadlock with MII interrupts. @@ -147,28 +147,30 @@ * TLAN v1.0 silicon. This needs to be investigated * further. * - * v1.14 Dec 16, 2000 - Added support for servicing multiple frames per. - * interrupt. Thanks goes to - * Adam Keys <adam@ti.com> - * Denis Beaudoin <dbeaudoin@ti.com> - * for providing the patch. - * - Fixed auto-neg output when using multiple - * adapters. - * - Converted to use new taskq interface. + * v1.14 Dec 16, 2000 - Added support for servicing multiple frames per. + * interrupt. Thanks goes to + * Adam Keys <adam@ti.com> + * Denis Beaudoin <dbeaudoin@ti.com> + * for providing the patch. + * - Fixed auto-neg output when using multiple + * adapters. + * - Converted to use new taskq interface. * - * v1.14a Jan 6, 2001 - Minor adjustments (spinlocks, etc.) + * v1.14a Jan 6, 2001 - Minor adjustments (spinlocks, etc.) * * Samuel Chessman <chessman@tux.org> New Maintainer! * * v1.15 Apr 4, 2002 - Correct operation when aui=1 to be - * 10T half duplex no loopback - * Thanks to Gunnar Eikman + * 10T half duplex no loopback + * Thanks to Gunnar Eikman * * Sakari Ailus <sakari.ailus@iki.fi>: * * v1.15a Dec 15 2008 - Remove bbuf support, it doesn't work anyway. + * v1.16 Jan 6 2011 - Make checkpatch.pl happy. + * v1.17 Jan 6 2011 - Add suspend/resume support. * - *******************************************************************************/ + ******************************************************************************/ #include <linux/module.h> #include <linux/init.h> @@ -185,13 +187,11 @@ #include "tlan.h" -typedef u32 (TLanIntVectorFunc)( struct net_device *, u16 ); - /* For removing EISA devices */ -static struct net_device *TLan_Eisa_Devices; +static struct net_device *tlan_eisa_devices; -static int TLanDevicesInstalled; +static int tlan_devices_installed; /* Set speed, duplex and aui settings */ static int aui[MAX_TLAN_BOARDS]; @@ -202,7 +202,8 @@ module_param_array(aui, int, NULL, 0); module_param_array(duplex, int, NULL, 0); module_param_array(speed, int, NULL, 0); MODULE_PARM_DESC(aui, "ThunderLAN use AUI port(s) (0-1)"); -MODULE_PARM_DESC(duplex, "ThunderLAN duplex setting(s) (0-default, 1-half, 2-full)"); +MODULE_PARM_DESC(duplex, + "ThunderLAN duplex setting(s) (0-default, 1-half, 2-full)"); MODULE_PARM_DESC(speed, "ThunderLAN port speen setting(s) (0,10,100)"); MODULE_AUTHOR("Maintainer: Samuel Chessman <chessman@tux.org>"); @@ -218,139 +219,144 @@ static int debug; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "ThunderLAN debug mask"); -static const char TLanSignature[] = "TLAN"; -static const char tlan_banner[] = "ThunderLAN driver v1.15a\n"; +static const char tlan_signature[] = "TLAN"; +static const char tlan_banner[] = "ThunderLAN driver v1.17\n"; static int tlan_have_pci; static int tlan_have_eisa; -static const char *media[] = { - "10BaseT-HD ", "10BaseT-FD ","100baseTx-HD ", - "100baseTx-FD", "100baseT4", NULL +static const char * const media[] = { + "10BaseT-HD", "10BaseT-FD", "100baseTx-HD", + "100BaseTx-FD", "100BaseT4", NULL }; static struct board { - const char *deviceLabel; - u32 flags; - u16 addrOfs; + const char *device_label; + u32 flags; + u16 addr_ofs; } board_info[] = { { "Compaq Netelligent 10 T PCI UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, - { "Compaq Netelligent 10/100 TX PCI UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, + { "Compaq Netelligent 10/100 TX PCI UTP", + TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, { "Compaq Integrated NetFlex-3/P", TLAN_ADAPTER_NONE, 0x83 }, { "Compaq NetFlex-3/P", TLAN_ADAPTER_UNMANAGED_PHY | TLAN_ADAPTER_BIT_RATE_PHY, 0x83 }, { "Compaq NetFlex-3/P", TLAN_ADAPTER_NONE, 0x83 }, { "Compaq Netelligent Integrated 10/100 TX UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, - { "Compaq Netelligent Dual 10/100 TX PCI UTP", TLAN_ADAPTER_NONE, 0x83 }, - { "Compaq Netelligent 10/100 TX Embedded UTP", TLAN_ADAPTER_NONE, 0x83 }, + { "Compaq Netelligent Dual 10/100 TX PCI UTP", + TLAN_ADAPTER_NONE, 0x83 }, + { "Compaq Netelligent 10/100 TX Embedded UTP", + TLAN_ADAPTER_NONE, 0x83 }, { "Olicom OC-2183/2185", TLAN_ADAPTER_USE_INTERN_10, 0x83 }, - { "Olicom OC-2325", TLAN_ADAPTER_UNMANAGED_PHY, 0xF8 }, - { "Olicom OC-2326", TLAN_ADAPTER_USE_INTERN_10, 0xF8 }, + { "Olicom OC-2325", TLAN_ADAPTER_UNMANAGED_PHY, 0xf8 }, + { "Olicom OC-2326", TLAN_ADAPTER_USE_INTERN_10, 0xf8 }, { "Compaq Netelligent 10/100 TX UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, - { "Compaq Netelligent 10 T/2 PCI UTP/Coax", TLAN_ADAPTER_NONE, 0x83 }, + { "Compaq Netelligent 10 T/2 PCI UTP/coax", TLAN_ADAPTER_NONE, 0x83 }, { "Compaq NetFlex-3/E", - TLAN_ADAPTER_ACTIVITY_LED | /* EISA card */ + TLAN_ADAPTER_ACTIVITY_LED | /* EISA card */ TLAN_ADAPTER_UNMANAGED_PHY | TLAN_ADAPTER_BIT_RATE_PHY, 0x83 }, - { "Compaq NetFlex-3/E", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, /* EISA card */ + { "Compaq NetFlex-3/E", + TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, /* EISA card */ }; static DEFINE_PCI_DEVICE_TABLE(tlan_pci_tbl) = { { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL10, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETFLEX3I, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 2 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 2 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_THUNDER, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 3 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 3 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETFLEX3B, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100PI, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100D, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100I, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 7 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 7 }, { PCI_VENDOR_ID_OLICOM, PCI_DEVICE_ID_OLICOM_OC2183, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 8 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 8 }, { PCI_VENDOR_ID_OLICOM, PCI_DEVICE_ID_OLICOM_OC2325, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 9 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 9 }, { PCI_VENDOR_ID_OLICOM, PCI_DEVICE_ID_OLICOM_OC2326, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 10 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 10 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_NETELLIGENT_10_100_WS_5100, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 11 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 11 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_NETELLIGENT_10_T2, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 12 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 12 }, { 0,} }; MODULE_DEVICE_TABLE(pci, tlan_pci_tbl); -static void TLan_EisaProbe( void ); -static void TLan_Eisa_Cleanup( void ); -static int TLan_Init( struct net_device * ); -static int TLan_Open( struct net_device *dev ); -static netdev_tx_t TLan_StartTx( struct sk_buff *, struct net_device *); -static irqreturn_t TLan_HandleInterrupt( int, void *); -static int TLan_Close( struct net_device *); -static struct net_device_stats *TLan_GetStats( struct net_device *); -static void TLan_SetMulticastList( struct net_device *); -static int TLan_ioctl( struct net_device *dev, struct ifreq *rq, int cmd); -static int TLan_probe1( struct pci_dev *pdev, long ioaddr, - int irq, int rev, const struct pci_device_id *ent); -static void TLan_tx_timeout( struct net_device *dev); -static void TLan_tx_timeout_work(struct work_struct *work); -static int tlan_init_one( struct pci_dev *pdev, const struct pci_device_id *ent); - -static u32 TLan_HandleTxEOF( struct net_device *, u16 ); -static u32 TLan_HandleStatOverflow( struct net_device *, u16 ); -static u32 TLan_HandleRxEOF( struct net_device *, u16 ); -static u32 TLan_HandleDummy( struct net_device *, u16 ); -static u32 TLan_HandleTxEOC( struct net_device *, u16 ); -static u32 TLan_HandleStatusCheck( struct net_device *, u16 ); -static u32 TLan_HandleRxEOC( struct net_device *, u16 ); - -static void TLan_Timer( unsigned long ); - -static void TLan_ResetLists( struct net_device * ); -static void TLan_FreeLists( struct net_device * ); -static void TLan_PrintDio( u16 ); -static void TLan_PrintList( TLanList *, char *, int ); -static void TLan_ReadAndClearStats( struct net_device *, int ); -static void TLan_ResetAdapter( struct net_device * ); -static void TLan_FinishReset( struct net_device * ); -static void TLan_SetMac( struct net_device *, int areg, char *mac ); - -static void TLan_PhyPrint( struct net_device * ); -static void TLan_PhyDetect( struct net_device * ); -static void TLan_PhyPowerDown( struct net_device * ); -static void TLan_PhyPowerUp( struct net_device * ); -static void TLan_PhyReset( struct net_device * ); -static void TLan_PhyStartLink( struct net_device * ); -static void TLan_PhyFinishAutoNeg( struct net_device * ); +static void tlan_eisa_probe(void); +static void tlan_eisa_cleanup(void); +static int tlan_init(struct net_device *); +static int tlan_open(struct net_device *dev); +static netdev_tx_t tlan_start_tx(struct sk_buff *, struct net_device *); +static irqreturn_t tlan_handle_interrupt(int, void *); +static int tlan_close(struct net_device *); +static struct net_device_stats *tlan_get_stats(struct net_device *); +static void tlan_set_multicast_list(struct net_device *); +static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); +static int tlan_probe1(struct pci_dev *pdev, long ioaddr, + int irq, int rev, const struct pci_device_id *ent); +static void tlan_tx_timeout(struct net_device *dev); +static void tlan_tx_timeout_work(struct work_struct *work); +static int tlan_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent); + +static u32 tlan_handle_tx_eof(struct net_device *, u16); +static u32 tlan_handle_stat_overflow(struct net_device *, u16); +static u32 tlan_handle_rx_eof(struct net_device *, u16); +static u32 tlan_handle_dummy(struct net_device *, u16); +static u32 tlan_handle_tx_eoc(struct net_device *, u16); +static u32 tlan_handle_status_check(struct net_device *, u16); +static u32 tlan_handle_rx_eoc(struct net_device *, u16); + +static void tlan_timer(unsigned long); + +static void tlan_reset_lists(struct net_device *); +static void tlan_free_lists(struct net_device *); +static void tlan_print_dio(u16); +static void tlan_print_list(struct tlan_list *, char *, int); +static void tlan_read_and_clear_stats(struct net_device *, int); +static void tlan_reset_adapter(struct net_device *); +static void tlan_finish_reset(struct net_device *); +static void tlan_set_mac(struct net_device *, int areg, char *mac); + +static void tlan_phy_print(struct net_device *); +static void tlan_phy_detect(struct net_device *); +static void tlan_phy_power_down(struct net_device *); +static void tlan_phy_power_up(struct net_device *); +static void tlan_phy_reset(struct net_device *); +static void tlan_phy_start_link(struct net_device *); +static void tlan_phy_finish_auto_neg(struct net_device *); #ifdef MONITOR -static void TLan_PhyMonitor( struct net_device * ); +static void tlan_phy_monitor(struct net_device *); #endif /* -static int TLan_PhyNop( struct net_device * ); -static int TLan_PhyInternalCheck( struct net_device * ); -static int TLan_PhyInternalService( struct net_device * ); -static int TLan_PhyDp83840aCheck( struct net_device * ); + static int tlan_phy_nop(struct net_device *); + static int tlan_phy_internal_check(struct net_device *); + static int tlan_phy_internal_service(struct net_device *); + static int tlan_phy_dp83840a_check(struct net_device *); */ -static bool TLan_MiiReadReg( struct net_device *, u16, u16, u16 * ); -static void TLan_MiiSendData( u16, u32, unsigned ); -static void TLan_MiiSync( u16 ); -static void TLan_MiiWriteReg( struct net_device *, u16, u16, u16 ); +static bool tlan_mii_read_reg(struct net_device *, u16, u16, u16 *); +static void tlan_mii_send_data(u16, u32, unsigned); +static void tlan_mii_sync(u16); +static void tlan_mii_write_reg(struct net_device *, u16, u16, u16); -static void TLan_EeSendStart( u16 ); -static int TLan_EeSendByte( u16, u8, int ); -static void TLan_EeReceiveByte( u16, u8 *, int ); -static int TLan_EeReadByte( struct net_device *, u8, u8 * ); +static void tlan_ee_send_start(u16); +static int tlan_ee_send_byte(u16, u8, int); +static void tlan_ee_receive_byte(u16, u8 *, int); +static int tlan_ee_read_byte(struct net_device *, u8, u8 *); static inline void -TLan_StoreSKB( struct tlan_list_tag *tag, struct sk_buff *skb) +tlan_store_skb(struct tlan_list *tag, struct sk_buff *skb) { unsigned long addr = (unsigned long)skb; tag->buffer[9].address = addr; @@ -358,7 +364,7 @@ TLan_StoreSKB( struct tlan_list_tag *tag, struct sk_buff *skb) } static inline struct sk_buff * -TLan_GetSKB( const struct tlan_list_tag *tag) +tlan_get_skb(const struct tlan_list *tag) { unsigned long addr; @@ -367,50 +373,50 @@ TLan_GetSKB( const struct tlan_list_tag *tag) return (struct sk_buff *) addr; } - -static TLanIntVectorFunc *TLanIntVector[TLAN_INT_NUMBER_OF_INTS] = { +static u32 +(*tlan_int_vector[TLAN_INT_NUMBER_OF_INTS])(struct net_device *, u16) = { NULL, - TLan_HandleTxEOF, - TLan_HandleStatOverflow, - TLan_HandleRxEOF, - TLan_HandleDummy, - TLan_HandleTxEOC, - TLan_HandleStatusCheck, - TLan_HandleRxEOC + tlan_handle_tx_eof, + tlan_handle_stat_overflow, + tlan_handle_rx_eof, + tlan_handle_dummy, + tlan_handle_tx_eoc, + tlan_handle_status_check, + tlan_handle_rx_eoc }; static inline void -TLan_SetTimer( struct net_device *dev, u32 ticks, u32 type ) +tlan_set_timer(struct net_device *dev, u32 ticks, u32 type) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; if (!in_irq()) spin_lock_irqsave(&priv->lock, flags); - if ( priv->timer.function != NULL && - priv->timerType != TLAN_TIMER_ACTIVITY ) { + if (priv->timer.function != NULL && + priv->timer_type != TLAN_TIMER_ACTIVITY) { if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); return; } - priv->timer.function = TLan_Timer; + priv->timer.function = tlan_timer; if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); priv->timer.data = (unsigned long) dev; - priv->timerSetAt = jiffies; - priv->timerType = type; + priv->timer_set_at = jiffies; + priv->timer_type = type; mod_timer(&priv->timer, jiffies + ticks); -} /* TLan_SetTimer */ +} /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Primary Functions +ThunderLAN driver primary functions - These functions are more or less common to all Linux network drivers. +these functions are more or less common to all linux network drivers. ****************************************************************************** *****************************************************************************/ @@ -419,49 +425,117 @@ TLan_SetTimer( struct net_device *dev, u32 ticks, u32 type ) - /*************************************************************** - * tlan_remove_one - * - * Returns: - * Nothing - * Parms: - * None - * - * Goes through the TLanDevices list and frees the device - * structs and memory associated with each device (lists - * and buffers). It also ureserves the IO port regions - * associated with this device. - * - **************************************************************/ +/*************************************************************** + * tlan_remove_one + * + * Returns: + * Nothing + * Parms: + * None + * + * Goes through the TLanDevices list and frees the device + * structs and memory associated with each device (lists + * and buffers). It also ureserves the IO port regions + * associated with this device. + * + **************************************************************/ -static void __devexit tlan_remove_one( struct pci_dev *pdev) +static void __devexit tlan_remove_one(struct pci_dev *pdev) { - struct net_device *dev = pci_get_drvdata( pdev ); - TLanPrivateInfo *priv = netdev_priv(dev); + struct net_device *dev = pci_get_drvdata(pdev); + struct tlan_priv *priv = netdev_priv(dev); - unregister_netdev( dev ); + unregister_netdev(dev); - if ( priv->dmaStorage ) { - pci_free_consistent(priv->pciDev, - priv->dmaSize, priv->dmaStorage, - priv->dmaStorageDMA ); + if (priv->dma_storage) { + pci_free_consistent(priv->pci_dev, + priv->dma_size, priv->dma_storage, + priv->dma_storage_dma); } #ifdef CONFIG_PCI pci_release_regions(pdev); #endif - free_netdev( dev ); + free_netdev(dev); + + pci_set_drvdata(pdev, NULL); +} + +static void tlan_start(struct net_device *dev) +{ + tlan_reset_lists(dev); + /* NOTE: It might not be necessary to read the stats before a + reset if you don't care what the values are. + */ + tlan_read_and_clear_stats(dev, TLAN_IGNORE); + tlan_reset_adapter(dev); + netif_wake_queue(dev); +} + +static void tlan_stop(struct net_device *dev) +{ + struct tlan_priv *priv = netdev_priv(dev); + + tlan_read_and_clear_stats(dev, TLAN_RECORD); + outl(TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD); + /* Reset and power down phy */ + tlan_reset_adapter(dev); + if (priv->timer.function != NULL) { + del_timer_sync(&priv->timer); + priv->timer.function = NULL; + } +} + +#ifdef CONFIG_PM + +static int tlan_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct net_device *dev = pci_get_drvdata(pdev); + + if (netif_running(dev)) + tlan_stop(dev); + + netif_device_detach(dev); + pci_save_state(pdev); + pci_disable_device(pdev); + pci_wake_from_d3(pdev, false); + pci_set_power_state(pdev, PCI_D3hot); - pci_set_drvdata( pdev, NULL ); + return 0; } +static int tlan_resume(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + pci_enable_wake(pdev, 0, 0); + netif_device_attach(dev); + + if (netif_running(dev)) + tlan_start(dev); + + return 0; +} + +#else /* CONFIG_PM */ + +#define tlan_suspend NULL +#define tlan_resume NULL + +#endif /* CONFIG_PM */ + + static struct pci_driver tlan_driver = { .name = "tlan", .id_table = tlan_pci_tbl, .probe = tlan_init_one, .remove = __devexit_p(tlan_remove_one), + .suspend = tlan_suspend, + .resume = tlan_resume, }; static int __init tlan_probe(void) @@ -482,13 +556,13 @@ static int __init tlan_probe(void) } TLAN_DBG(TLAN_DEBUG_PROBE, "Starting EISA Probe....\n"); - TLan_EisaProbe(); + tlan_eisa_probe(); printk(KERN_INFO "TLAN: %d device%s installed, PCI: %d EISA: %d\n", - TLanDevicesInstalled, TLanDevicesInstalled == 1 ? "" : "s", - tlan_have_pci, tlan_have_eisa); + tlan_devices_installed, tlan_devices_installed == 1 ? "" : "s", + tlan_have_pci, tlan_have_eisa); - if (TLanDevicesInstalled == 0) { + if (tlan_devices_installed == 0) { rc = -ENODEV; goto err_out_pci_unreg; } @@ -501,39 +575,39 @@ err_out_pci_free: } -static int __devinit tlan_init_one( struct pci_dev *pdev, - const struct pci_device_id *ent) +static int __devinit tlan_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent) { - return TLan_probe1( pdev, -1, -1, 0, ent); + return tlan_probe1(pdev, -1, -1, 0, ent); } /* - *************************************************************** - * tlan_probe1 - * - * Returns: - * 0 on success, error code on error - * Parms: - * none - * - * The name is lower case to fit in with all the rest of - * the netcard_probe names. This function looks for - * another TLan based adapter, setting it up with the - * allocated device struct if one is found. - * tlan_probe has been ported to the new net API and - * now allocates its own device structure. This function - * is also used by modules. - * - **************************************************************/ - -static int __devinit TLan_probe1(struct pci_dev *pdev, +*************************************************************** +* tlan_probe1 +* +* Returns: +* 0 on success, error code on error +* Parms: +* none +* +* The name is lower case to fit in with all the rest of +* the netcard_probe names. This function looks for +* another TLan based adapter, setting it up with the +* allocated device struct if one is found. +* tlan_probe has been ported to the new net API and +* now allocates its own device structure. This function +* is also used by modules. +* +**************************************************************/ + +static int __devinit tlan_probe1(struct pci_dev *pdev, long ioaddr, int irq, int rev, - const struct pci_device_id *ent ) + const struct pci_device_id *ent) { struct net_device *dev; - TLanPrivateInfo *priv; + struct tlan_priv *priv; u16 device_id; int reg, rc = -ENODEV; @@ -543,7 +617,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, if (rc) return rc; - rc = pci_request_regions(pdev, TLanSignature); + rc = pci_request_regions(pdev, tlan_signature); if (rc) { printk(KERN_ERR "TLAN: Could not reserve IO regions\n"); goto err_out; @@ -551,7 +625,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, } #endif /* CONFIG_PCI */ - dev = alloc_etherdev(sizeof(TLanPrivateInfo)); + dev = alloc_etherdev(sizeof(struct tlan_priv)); if (dev == NULL) { printk(KERN_ERR "TLAN: Could not allocate memory for device.\n"); rc = -ENOMEM; @@ -561,26 +635,28 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, priv = netdev_priv(dev); - priv->pciDev = pdev; + priv->pci_dev = pdev; priv->dev = dev; /* Is this a PCI device? */ if (pdev) { - u32 pci_io_base = 0; + u32 pci_io_base = 0; priv->adapter = &board_info[ent->driver_data]; rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) { - printk(KERN_ERR "TLAN: No suitable PCI mapping available.\n"); + printk(KERN_ERR + "TLAN: No suitable PCI mapping available.\n"); goto err_out_free_dev; } - for ( reg= 0; reg <= 5; reg ++ ) { + for (reg = 0; reg <= 5; reg++) { if (pci_resource_flags(pdev, reg) & IORESOURCE_IO) { pci_io_base = pci_resource_start(pdev, reg); - TLAN_DBG( TLAN_DEBUG_GNRL, "IO mapping is available at %x.\n", - pci_io_base); + TLAN_DBG(TLAN_DEBUG_GNRL, + "IO mapping is available at %x.\n", + pci_io_base); break; } } @@ -592,7 +668,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, dev->base_addr = pci_io_base; dev->irq = pdev->irq; - priv->adapterRev = pdev->revision; + priv->adapter_rev = pdev->revision; pci_set_master(pdev); pci_set_drvdata(pdev, dev); @@ -602,11 +678,11 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, device_id = inw(ioaddr + EISA_ID2); priv->is_eisa = 1; if (device_id == 0x20F1) { - priv->adapter = &board_info[13]; /* NetFlex-3/E */ - priv->adapterRev = 23; /* TLAN 2.3 */ + priv->adapter = &board_info[13]; /* NetFlex-3/E */ + priv->adapter_rev = 23; /* TLAN 2.3 */ } else { priv->adapter = &board_info[14]; - priv->adapterRev = 10; /* TLAN 1.0 */ + priv->adapter_rev = 10; /* TLAN 1.0 */ } dev->base_addr = ioaddr; dev->irq = irq; @@ -620,11 +696,11 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, priv->speed = ((dev->mem_start & 0x18) == 0x18) ? 0 : (dev->mem_start & 0x18) >> 3; - if (priv->speed == 0x1) { + if (priv->speed == 0x1) priv->speed = TLAN_SPEED_10; - } else if (priv->speed == 0x2) { + else if (priv->speed == 0x2) priv->speed = TLAN_SPEED_100; - } + debug = priv->debug = dev->mem_end; } else { priv->aui = aui[boards_found]; @@ -635,11 +711,11 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, /* This will be used when we get an adapter error from * within our irq handler */ - INIT_WORK(&priv->tlan_tqueue, TLan_tx_timeout_work); + INIT_WORK(&priv->tlan_tqueue, tlan_tx_timeout_work); spin_lock_init(&priv->lock); - rc = TLan_Init(dev); + rc = tlan_init(dev); if (rc) { printk(KERN_ERR "TLAN: Could not set up device.\n"); goto err_out_free_dev; @@ -652,29 +728,29 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, } - TLanDevicesInstalled++; + tlan_devices_installed++; boards_found++; /* pdev is NULL if this is an EISA device */ if (pdev) tlan_have_pci++; else { - priv->nextDevice = TLan_Eisa_Devices; - TLan_Eisa_Devices = dev; + priv->next_device = tlan_eisa_devices; + tlan_eisa_devices = dev; tlan_have_eisa++; } printk(KERN_INFO "TLAN: %s irq=%2d, io=%04x, %s, Rev. %d\n", - dev->name, - (int) dev->irq, - (int) dev->base_addr, - priv->adapter->deviceLabel, - priv->adapterRev); + dev->name, + (int) dev->irq, + (int) dev->base_addr, + priv->adapter->device_label, + priv->adapter_rev); return 0; err_out_uninit: - pci_free_consistent(priv->pciDev, priv->dmaSize, priv->dmaStorage, - priv->dmaStorageDMA ); + pci_free_consistent(priv->pci_dev, priv->dma_size, priv->dma_storage, + priv->dma_storage_dma); err_out_free_dev: free_netdev(dev); err_out_regions: @@ -689,22 +765,23 @@ err_out: } -static void TLan_Eisa_Cleanup(void) +static void tlan_eisa_cleanup(void) { struct net_device *dev; - TLanPrivateInfo *priv; + struct tlan_priv *priv; - while( tlan_have_eisa ) { - dev = TLan_Eisa_Devices; + while (tlan_have_eisa) { + dev = tlan_eisa_devices; priv = netdev_priv(dev); - if (priv->dmaStorage) { - pci_free_consistent(priv->pciDev, priv->dmaSize, - priv->dmaStorage, priv->dmaStorageDMA ); + if (priv->dma_storage) { + pci_free_consistent(priv->pci_dev, priv->dma_size, + priv->dma_storage, + priv->dma_storage_dma); } - release_region( dev->base_addr, 0x10); - unregister_netdev( dev ); - TLan_Eisa_Devices = priv->nextDevice; - free_netdev( dev ); + release_region(dev->base_addr, 0x10); + unregister_netdev(dev); + tlan_eisa_devices = priv->next_device; + free_netdev(dev); tlan_have_eisa--; } } @@ -715,7 +792,7 @@ static void __exit tlan_exit(void) pci_unregister_driver(&tlan_driver); if (tlan_have_eisa) - TLan_Eisa_Cleanup(); + tlan_eisa_cleanup(); } @@ -726,24 +803,24 @@ module_exit(tlan_exit); - /************************************************************** - * TLan_EisaProbe - * - * Returns: 0 on success, 1 otherwise - * - * Parms: None - * - * - * This functions probes for EISA devices and calls - * TLan_probe1 when one is found. - * - *************************************************************/ +/************************************************************** + * tlan_eisa_probe + * + * Returns: 0 on success, 1 otherwise + * + * Parms: None + * + * + * This functions probes for EISA devices and calls + * TLan_probe1 when one is found. + * + *************************************************************/ -static void __init TLan_EisaProbe (void) +static void __init tlan_eisa_probe(void) { - long ioaddr; - int rc = -ENODEV; - int irq; + long ioaddr; + int rc = -ENODEV; + int irq; u16 device_id; if (!EISA_bus) { @@ -754,15 +831,16 @@ static void __init TLan_EisaProbe (void) /* Loop through all slots of the EISA bus */ for (ioaddr = 0x1000; ioaddr < 0x9000; ioaddr += 0x1000) { - TLAN_DBG(TLAN_DEBUG_PROBE,"EISA_ID 0x%4x: 0x%4x\n", - (int) ioaddr + 0xC80, inw(ioaddr + EISA_ID)); - TLAN_DBG(TLAN_DEBUG_PROBE,"EISA_ID 0x%4x: 0x%4x\n", - (int) ioaddr + 0xC82, inw(ioaddr + EISA_ID2)); + TLAN_DBG(TLAN_DEBUG_PROBE, "EISA_ID 0x%4x: 0x%4x\n", + (int) ioaddr + 0xc80, inw(ioaddr + EISA_ID)); + TLAN_DBG(TLAN_DEBUG_PROBE, "EISA_ID 0x%4x: 0x%4x\n", + (int) ioaddr + 0xc82, inw(ioaddr + EISA_ID2)); - TLAN_DBG(TLAN_DEBUG_PROBE, "Probing for EISA adapter at IO: 0x%4x : ", - (int) ioaddr); - if (request_region(ioaddr, 0x10, TLanSignature) == NULL) + TLAN_DBG(TLAN_DEBUG_PROBE, + "Probing for EISA adapter at IO: 0x%4x : ", + (int) ioaddr); + if (request_region(ioaddr, 0x10, tlan_signature) == NULL) goto out; if (inw(ioaddr + EISA_ID) != 0x110E) { @@ -772,326 +850,326 @@ static void __init TLan_EisaProbe (void) device_id = inw(ioaddr + EISA_ID2); if (device_id != 0x20F1 && device_id != 0x40F1) { - release_region (ioaddr, 0x10); + release_region(ioaddr, 0x10); goto out; } - if (inb(ioaddr + EISA_CR) != 0x1) { /* Check if adapter is enabled */ - release_region (ioaddr, 0x10); + /* check if adapter is enabled */ + if (inb(ioaddr + EISA_CR) != 0x1) { + release_region(ioaddr, 0x10); goto out2; } if (debug == 0x10) - printk("Found one\n"); + printk(KERN_INFO "Found one\n"); /* Get irq from board */ - switch (inb(ioaddr + 0xCC0)) { - case(0x10): - irq=5; - break; - case(0x20): - irq=9; - break; - case(0x40): - irq=10; - break; - case(0x80): - irq=11; - break; - default: - goto out; + switch (inb(ioaddr + 0xcc0)) { + case(0x10): + irq = 5; + break; + case(0x20): + irq = 9; + break; + case(0x40): + irq = 10; + break; + case(0x80): + irq = 11; + break; + default: + goto out; } /* Setup the newly found eisa adapter */ - rc = TLan_probe1( NULL, ioaddr, irq, - 12, NULL); + rc = tlan_probe1(NULL, ioaddr, irq, + 12, NULL); continue; - out: - if (debug == 0x10) - printk("None found\n"); - continue; +out: + if (debug == 0x10) + printk(KERN_INFO "None found\n"); + continue; - out2: if (debug == 0x10) - printk("Card found but it is not enabled, skipping\n"); - continue; +out2: + if (debug == 0x10) + printk(KERN_INFO "Card found but it is not enabled, skipping\n"); + continue; } -} /* TLan_EisaProbe */ +} #ifdef CONFIG_NET_POLL_CONTROLLER -static void TLan_Poll(struct net_device *dev) +static void tlan_poll(struct net_device *dev) { disable_irq(dev->irq); - TLan_HandleInterrupt(dev->irq, dev); + tlan_handle_interrupt(dev->irq, dev); enable_irq(dev->irq); } #endif -static const struct net_device_ops TLan_netdev_ops = { - .ndo_open = TLan_Open, - .ndo_stop = TLan_Close, - .ndo_start_xmit = TLan_StartTx, - .ndo_tx_timeout = TLan_tx_timeout, - .ndo_get_stats = TLan_GetStats, - .ndo_set_multicast_list = TLan_SetMulticastList, - .ndo_do_ioctl = TLan_ioctl, +static const struct net_device_ops tlan_netdev_ops = { + .ndo_open = tlan_open, + .ndo_stop = tlan_close, + .ndo_start_xmit = tlan_start_tx, + .ndo_tx_timeout = tlan_tx_timeout, + .ndo_get_stats = tlan_get_stats, + .ndo_set_multicast_list = tlan_set_multicast_list, + .ndo_do_ioctl = tlan_ioctl, .ndo_change_mtu = eth_change_mtu, - .ndo_set_mac_address = eth_mac_addr, + .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = TLan_Poll, + .ndo_poll_controller = tlan_poll, #endif }; - /*************************************************************** - * TLan_Init - * - * Returns: - * 0 on success, error code otherwise. - * Parms: - * dev The structure of the device to be - * init'ed. - * - * This function completes the initialization of the - * device structure and driver. It reserves the IO - * addresses, allocates memory for the lists and bounce - * buffers, retrieves the MAC address from the eeprom - * and assignes the device's methods. - * - **************************************************************/ - -static int TLan_Init( struct net_device *dev ) +/*************************************************************** + * tlan_init + * + * Returns: + * 0 on success, error code otherwise. + * Parms: + * dev The structure of the device to be + * init'ed. + * + * This function completes the initialization of the + * device structure and driver. It reserves the IO + * addresses, allocates memory for the lists and bounce + * buffers, retrieves the MAC address from the eeprom + * and assignes the device's methods. + * + **************************************************************/ + +static int tlan_init(struct net_device *dev) { int dma_size; - int err; + int err; int i; - TLanPrivateInfo *priv; + struct tlan_priv *priv; priv = netdev_priv(dev); - dma_size = ( TLAN_NUM_RX_LISTS + TLAN_NUM_TX_LISTS ) - * ( sizeof(TLanList) ); - priv->dmaStorage = pci_alloc_consistent(priv->pciDev, - dma_size, &priv->dmaStorageDMA); - priv->dmaSize = dma_size; - - if ( priv->dmaStorage == NULL ) { - printk(KERN_ERR "TLAN: Could not allocate lists and buffers for %s.\n", - dev->name ); + dma_size = (TLAN_NUM_RX_LISTS + TLAN_NUM_TX_LISTS) + * (sizeof(struct tlan_list)); + priv->dma_storage = pci_alloc_consistent(priv->pci_dev, + dma_size, + &priv->dma_storage_dma); + priv->dma_size = dma_size; + + if (priv->dma_storage == NULL) { + printk(KERN_ERR + "TLAN: Could not allocate lists and buffers for %s.\n", + dev->name); return -ENOMEM; } - memset( priv->dmaStorage, 0, dma_size ); - priv->rxList = (TLanList *) ALIGN((unsigned long)priv->dmaStorage, 8); - priv->rxListDMA = ALIGN(priv->dmaStorageDMA, 8); - priv->txList = priv->rxList + TLAN_NUM_RX_LISTS; - priv->txListDMA = priv->rxListDMA + sizeof(TLanList) * TLAN_NUM_RX_LISTS; + memset(priv->dma_storage, 0, dma_size); + priv->rx_list = (struct tlan_list *) + ALIGN((unsigned long)priv->dma_storage, 8); + priv->rx_list_dma = ALIGN(priv->dma_storage_dma, 8); + priv->tx_list = priv->rx_list + TLAN_NUM_RX_LISTS; + priv->tx_list_dma = + priv->rx_list_dma + sizeof(struct tlan_list)*TLAN_NUM_RX_LISTS; err = 0; - for ( i = 0; i < 6 ; i++ ) - err |= TLan_EeReadByte( dev, - (u8) priv->adapter->addrOfs + i, - (u8 *) &dev->dev_addr[i] ); - if ( err ) { + for (i = 0; i < 6 ; i++) + err |= tlan_ee_read_byte(dev, + (u8) priv->adapter->addr_ofs + i, + (u8 *) &dev->dev_addr[i]); + if (err) { printk(KERN_ERR "TLAN: %s: Error reading MAC from eeprom: %d\n", - dev->name, - err ); + dev->name, + err); } dev->addr_len = 6; netif_carrier_off(dev); /* Device methods */ - dev->netdev_ops = &TLan_netdev_ops; + dev->netdev_ops = &tlan_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; return 0; -} /* TLan_Init */ +} - /*************************************************************** - * TLan_Open - * - * Returns: - * 0 on success, error code otherwise. - * Parms: - * dev Structure of device to be opened. - * - * This routine puts the driver and TLAN adapter in a - * state where it is ready to send and receive packets. - * It allocates the IRQ, resets and brings the adapter - * out of reset, and allows interrupts. It also delays - * the startup for autonegotiation or sends a Rx GO - * command to the adapter, as appropriate. - * - **************************************************************/ +/*************************************************************** + * tlan_open + * + * Returns: + * 0 on success, error code otherwise. + * Parms: + * dev Structure of device to be opened. + * + * This routine puts the driver and TLAN adapter in a + * state where it is ready to send and receive packets. + * It allocates the IRQ, resets and brings the adapter + * out of reset, and allows interrupts. It also delays + * the startup for autonegotiation or sends a Rx GO + * command to the adapter, as appropriate. + * + **************************************************************/ -static int TLan_Open( struct net_device *dev ) +static int tlan_open(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int err; - priv->tlanRev = TLan_DioRead8( dev->base_addr, TLAN_DEF_REVISION ); - err = request_irq( dev->irq, TLan_HandleInterrupt, IRQF_SHARED, - dev->name, dev ); + priv->tlan_rev = tlan_dio_read8(dev->base_addr, TLAN_DEF_REVISION); + err = request_irq(dev->irq, tlan_handle_interrupt, IRQF_SHARED, + dev->name, dev); - if ( err ) { + if (err) { pr_err("TLAN: Cannot open %s because IRQ %d is already in use.\n", - dev->name, dev->irq ); + dev->name, dev->irq); return err; } init_timer(&priv->timer); - netif_start_queue(dev); - /* NOTE: It might not be necessary to read the stats before a - reset if you don't care what the values are. - */ - TLan_ResetLists( dev ); - TLan_ReadAndClearStats( dev, TLAN_IGNORE ); - TLan_ResetAdapter( dev ); + tlan_start(dev); - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Opened. TLAN Chip Rev: %x\n", - dev->name, priv->tlanRev ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Opened. TLAN Chip Rev: %x\n", + dev->name, priv->tlan_rev); return 0; -} /* TLan_Open */ +} - /************************************************************** - * TLan_ioctl - * - * Returns: - * 0 on success, error code otherwise - * Params: - * dev structure of device to receive ioctl. - * - * rq ifreq structure to hold userspace data. - * - * cmd ioctl command. - * - * - *************************************************************/ +/************************************************************** + * tlan_ioctl + * + * Returns: + * 0 on success, error code otherwise + * Params: + * dev structure of device to receive ioctl. + * + * rq ifreq structure to hold userspace data. + * + * cmd ioctl command. + * + * + *************************************************************/ -static int TLan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); struct mii_ioctl_data *data = if_mii(rq); - u32 phy = priv->phy[priv->phyNum]; + u32 phy = priv->phy[priv->phy_num]; - if (!priv->phyOnline) + if (!priv->phy_online) return -EAGAIN; - switch(cmd) { - case SIOCGMIIPHY: /* Get address of MII PHY in use. */ - data->phy_id = phy; + switch (cmd) { + case SIOCGMIIPHY: /* get address of MII PHY in use. */ + data->phy_id = phy; - case SIOCGMIIREG: /* Read MII PHY register. */ - TLan_MiiReadReg(dev, data->phy_id & 0x1f, - data->reg_num & 0x1f, &data->val_out); - return 0; + case SIOCGMIIREG: /* read MII PHY register. */ + tlan_mii_read_reg(dev, data->phy_id & 0x1f, + data->reg_num & 0x1f, &data->val_out); + return 0; - case SIOCSMIIREG: /* Write MII PHY register. */ - TLan_MiiWriteReg(dev, data->phy_id & 0x1f, - data->reg_num & 0x1f, data->val_in); - return 0; - default: - return -EOPNOTSUPP; + case SIOCSMIIREG: /* write MII PHY register. */ + tlan_mii_write_reg(dev, data->phy_id & 0x1f, + data->reg_num & 0x1f, data->val_in); + return 0; + default: + return -EOPNOTSUPP; } -} /* tlan_ioctl */ +} - /*************************************************************** - * TLan_tx_timeout - * - * Returns: nothing - * - * Params: - * dev structure of device which timed out - * during transmit. - * - **************************************************************/ +/*************************************************************** + * tlan_tx_timeout + * + * Returns: nothing + * + * Params: + * dev structure of device which timed out + * during transmit. + * + **************************************************************/ -static void TLan_tx_timeout(struct net_device *dev) +static void tlan_tx_timeout(struct net_device *dev) { - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Transmit timed out.\n", dev->name); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Transmit timed out.\n", dev->name); /* Ok so we timed out, lets see what we can do about it...*/ - TLan_FreeLists( dev ); - TLan_ResetLists( dev ); - TLan_ReadAndClearStats( dev, TLAN_IGNORE ); - TLan_ResetAdapter( dev ); + tlan_free_lists(dev); + tlan_reset_lists(dev); + tlan_read_and_clear_stats(dev, TLAN_IGNORE); + tlan_reset_adapter(dev); dev->trans_start = jiffies; /* prevent tx timeout */ - netif_wake_queue( dev ); + netif_wake_queue(dev); } - /*************************************************************** - * TLan_tx_timeout_work - * - * Returns: nothing - * - * Params: - * work work item of device which timed out - * - **************************************************************/ +/*************************************************************** + * tlan_tx_timeout_work + * + * Returns: nothing + * + * Params: + * work work item of device which timed out + * + **************************************************************/ -static void TLan_tx_timeout_work(struct work_struct *work) +static void tlan_tx_timeout_work(struct work_struct *work) { - TLanPrivateInfo *priv = - container_of(work, TLanPrivateInfo, tlan_tqueue); + struct tlan_priv *priv = + container_of(work, struct tlan_priv, tlan_tqueue); - TLan_tx_timeout(priv->dev); + tlan_tx_timeout(priv->dev); } - /*************************************************************** - * TLan_StartTx - * - * Returns: - * 0 on success, non-zero on failure. - * Parms: - * skb A pointer to the sk_buff containing the - * frame to be sent. - * dev The device to send the data on. - * - * This function adds a frame to the Tx list to be sent - * ASAP. First it verifies that the adapter is ready and - * there is room in the queue. Then it sets up the next - * available list, copies the frame to the corresponding - * buffer. If the adapter Tx channel is idle, it gives - * the adapter a Tx Go command on the list, otherwise it - * sets the forward address of the previous list to point - * to this one. Then it frees the sk_buff. - * - **************************************************************/ - -static netdev_tx_t TLan_StartTx( struct sk_buff *skb, struct net_device *dev ) +/*************************************************************** + * tlan_start_tx + * + * Returns: + * 0 on success, non-zero on failure. + * Parms: + * skb A pointer to the sk_buff containing the + * frame to be sent. + * dev The device to send the data on. + * + * This function adds a frame to the Tx list to be sent + * ASAP. First it verifies that the adapter is ready and + * there is room in the queue. Then it sets up the next + * available list, copies the frame to the corresponding + * buffer. If the adapter Tx channel is idle, it gives + * the adapter a Tx Go command on the list, otherwise it + * sets the forward address of the previous list to point + * to this one. Then it frees the sk_buff. + * + **************************************************************/ + +static netdev_tx_t tlan_start_tx(struct sk_buff *skb, struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); dma_addr_t tail_list_phys; - TLanList *tail_list; + struct tlan_list *tail_list; unsigned long flags; unsigned int txlen; - if ( ! priv->phyOnline ) { - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: %s PHY is not ready\n", - dev->name ); + if (!priv->phy_online) { + TLAN_DBG(TLAN_DEBUG_TX, "TRANSMIT: %s PHY is not ready\n", + dev->name); dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1100,218 +1178,214 @@ static netdev_tx_t TLan_StartTx( struct sk_buff *skb, struct net_device *dev ) return NETDEV_TX_OK; txlen = max(skb->len, (unsigned int)TLAN_MIN_FRAME_SIZE); - tail_list = priv->txList + priv->txTail; - tail_list_phys = priv->txListDMA + sizeof(TLanList) * priv->txTail; + tail_list = priv->tx_list + priv->tx_tail; + tail_list_phys = + priv->tx_list_dma + sizeof(struct tlan_list)*priv->tx_tail; - if ( tail_list->cStat != TLAN_CSTAT_UNUSED ) { - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: %s is busy (Head=%d Tail=%d)\n", - dev->name, priv->txHead, priv->txTail ); + if (tail_list->c_stat != TLAN_CSTAT_UNUSED) { + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: %s is busy (Head=%d Tail=%d)\n", + dev->name, priv->tx_head, priv->tx_tail); netif_stop_queue(dev); - priv->txBusyCount++; + priv->tx_busy_count++; return NETDEV_TX_BUSY; } tail_list->forward = 0; - tail_list->buffer[0].address = pci_map_single(priv->pciDev, + tail_list->buffer[0].address = pci_map_single(priv->pci_dev, skb->data, txlen, PCI_DMA_TODEVICE); - TLan_StoreSKB(tail_list, skb); + tlan_store_skb(tail_list, skb); - tail_list->frameSize = (u16) txlen; + tail_list->frame_size = (u16) txlen; tail_list->buffer[0].count = TLAN_LAST_BUFFER | (u32) txlen; tail_list->buffer[1].count = 0; tail_list->buffer[1].address = 0; spin_lock_irqsave(&priv->lock, flags); - tail_list->cStat = TLAN_CSTAT_READY; - if ( ! priv->txInProgress ) { - priv->txInProgress = 1; - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: Starting TX on buffer %d\n", priv->txTail ); - outl( tail_list_phys, dev->base_addr + TLAN_CH_PARM ); - outl( TLAN_HC_GO, dev->base_addr + TLAN_HOST_CMD ); + tail_list->c_stat = TLAN_CSTAT_READY; + if (!priv->tx_in_progress) { + priv->tx_in_progress = 1; + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: Starting TX on buffer %d\n", + priv->tx_tail); + outl(tail_list_phys, dev->base_addr + TLAN_CH_PARM); + outl(TLAN_HC_GO, dev->base_addr + TLAN_HOST_CMD); } else { - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: Adding buffer %d to TX channel\n", - priv->txTail ); - if ( priv->txTail == 0 ) { - ( priv->txList + ( TLAN_NUM_TX_LISTS - 1 ) )->forward + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: Adding buffer %d to TX channel\n", + priv->tx_tail); + if (priv->tx_tail == 0) { + (priv->tx_list + (TLAN_NUM_TX_LISTS - 1))->forward = tail_list_phys; } else { - ( priv->txList + ( priv->txTail - 1 ) )->forward + (priv->tx_list + (priv->tx_tail - 1))->forward = tail_list_phys; } } spin_unlock_irqrestore(&priv->lock, flags); - CIRC_INC( priv->txTail, TLAN_NUM_TX_LISTS ); + CIRC_INC(priv->tx_tail, TLAN_NUM_TX_LISTS); return NETDEV_TX_OK; -} /* TLan_StartTx */ +} - /*************************************************************** - * TLan_HandleInterrupt - * - * Returns: - * Nothing - * Parms: - * irq The line on which the interrupt - * occurred. - * dev_id A pointer to the device assigned to - * this irq line. - * - * This function handles an interrupt generated by its - * assigned TLAN adapter. The function deactivates - * interrupts on its adapter, records the type of - * interrupt, executes the appropriate subhandler, and - * acknowdges the interrupt to the adapter (thus - * re-enabling adapter interrupts. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_interrupt + * + * Returns: + * Nothing + * Parms: + * irq The line on which the interrupt + * occurred. + * dev_id A pointer to the device assigned to + * this irq line. + * + * This function handles an interrupt generated by its + * assigned TLAN adapter. The function deactivates + * interrupts on its adapter, records the type of + * interrupt, executes the appropriate subhandler, and + * acknowdges the interrupt to the adapter (thus + * re-enabling adapter interrupts. + * + **************************************************************/ -static irqreturn_t TLan_HandleInterrupt(int irq, void *dev_id) +static irqreturn_t tlan_handle_interrupt(int irq, void *dev_id) { struct net_device *dev = dev_id; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 host_int; u16 type; spin_lock(&priv->lock); - host_int = inw( dev->base_addr + TLAN_HOST_INT ); - type = ( host_int & TLAN_HI_IT_MASK ) >> 2; - if ( type ) { + host_int = inw(dev->base_addr + TLAN_HOST_INT); + type = (host_int & TLAN_HI_IT_MASK) >> 2; + if (type) { u32 ack; u32 host_cmd; - outw( host_int, dev->base_addr + TLAN_HOST_INT ); - ack = TLanIntVector[type]( dev, host_int ); + outw(host_int, dev->base_addr + TLAN_HOST_INT); + ack = tlan_int_vector[type](dev, host_int); - if ( ack ) { - host_cmd = TLAN_HC_ACK | ack | ( type << 18 ); - outl( host_cmd, dev->base_addr + TLAN_HOST_CMD ); + if (ack) { + host_cmd = TLAN_HC_ACK | ack | (type << 18); + outl(host_cmd, dev->base_addr + TLAN_HOST_CMD); } } spin_unlock(&priv->lock); return IRQ_RETVAL(type); -} /* TLan_HandleInterrupts */ +} - /*************************************************************** - * TLan_Close - * - * Returns: - * An error code. - * Parms: - * dev The device structure of the device to - * close. - * - * This function shuts down the adapter. It records any - * stats, puts the adapter into reset state, deactivates - * its time as needed, and frees the irq it is using. - * - **************************************************************/ +/*************************************************************** + * tlan_close + * + * Returns: + * An error code. + * Parms: + * dev The device structure of the device to + * close. + * + * This function shuts down the adapter. It records any + * stats, puts the adapter into reset state, deactivates + * its time as needed, and frees the irq it is using. + * + **************************************************************/ -static int TLan_Close(struct net_device *dev) +static int tlan_close(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); - netif_stop_queue(dev); priv->neg_be_verbose = 0; + tlan_stop(dev); - TLan_ReadAndClearStats( dev, TLAN_RECORD ); - outl( TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD ); - if ( priv->timer.function != NULL ) { - del_timer_sync( &priv->timer ); - priv->timer.function = NULL; - } - - free_irq( dev->irq, dev ); - TLan_FreeLists( dev ); - TLAN_DBG( TLAN_DEBUG_GNRL, "Device %s closed.\n", dev->name ); + free_irq(dev->irq, dev); + tlan_free_lists(dev); + TLAN_DBG(TLAN_DEBUG_GNRL, "Device %s closed.\n", dev->name); return 0; -} /* TLan_Close */ +} - /*************************************************************** - * TLan_GetStats - * - * Returns: - * A pointer to the device's statistics structure. - * Parms: - * dev The device structure to return the - * stats for. - * - * This function updates the devices statistics by reading - * the TLAN chip's onboard registers. Then it returns the - * address of the statistics structure. - * - **************************************************************/ +/*************************************************************** + * tlan_get_stats + * + * Returns: + * A pointer to the device's statistics structure. + * Parms: + * dev The device structure to return the + * stats for. + * + * This function updates the devices statistics by reading + * the TLAN chip's onboard registers. Then it returns the + * address of the statistics structure. + * + **************************************************************/ -static struct net_device_stats *TLan_GetStats( struct net_device *dev ) +static struct net_device_stats *tlan_get_stats(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; /* Should only read stats if open ? */ - TLan_ReadAndClearStats( dev, TLAN_RECORD ); + tlan_read_and_clear_stats(dev, TLAN_RECORD); - TLAN_DBG( TLAN_DEBUG_RX, "RECEIVE: %s EOC count = %d\n", dev->name, - priv->rxEocCount ); - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: %s Busy count = %d\n", dev->name, - priv->txBusyCount ); - if ( debug & TLAN_DEBUG_GNRL ) { - TLan_PrintDio( dev->base_addr ); - TLan_PhyPrint( dev ); + TLAN_DBG(TLAN_DEBUG_RX, "RECEIVE: %s EOC count = %d\n", dev->name, + priv->rx_eoc_count); + TLAN_DBG(TLAN_DEBUG_TX, "TRANSMIT: %s Busy count = %d\n", dev->name, + priv->tx_busy_count); + if (debug & TLAN_DEBUG_GNRL) { + tlan_print_dio(dev->base_addr); + tlan_phy_print(dev); } - if ( debug & TLAN_DEBUG_LIST ) { - for ( i = 0; i < TLAN_NUM_RX_LISTS; i++ ) - TLan_PrintList( priv->rxList + i, "RX", i ); - for ( i = 0; i < TLAN_NUM_TX_LISTS; i++ ) - TLan_PrintList( priv->txList + i, "TX", i ); + if (debug & TLAN_DEBUG_LIST) { + for (i = 0; i < TLAN_NUM_RX_LISTS; i++) + tlan_print_list(priv->rx_list + i, "RX", i); + for (i = 0; i < TLAN_NUM_TX_LISTS; i++) + tlan_print_list(priv->tx_list + i, "TX", i); } return &dev->stats; -} /* TLan_GetStats */ +} - /*************************************************************** - * TLan_SetMulticastList - * - * Returns: - * Nothing - * Parms: - * dev The device structure to set the - * multicast list for. - * - * This function sets the TLAN adaptor to various receive - * modes. If the IFF_PROMISC flag is set, promiscuous - * mode is acitviated. Otherwise, promiscuous mode is - * turned off. If the IFF_ALLMULTI flag is set, then - * the hash table is set to receive all group addresses. - * Otherwise, the first three multicast addresses are - * stored in AREG_1-3, and the rest are selected via the - * hash table, as necessary. - * - **************************************************************/ +/*************************************************************** + * tlan_set_multicast_list + * + * Returns: + * Nothing + * Parms: + * dev The device structure to set the + * multicast list for. + * + * This function sets the TLAN adaptor to various receive + * modes. If the IFF_PROMISC flag is set, promiscuous + * mode is acitviated. Otherwise, promiscuous mode is + * turned off. If the IFF_ALLMULTI flag is set, then + * the hash table is set to receive all group addresses. + * Otherwise, the first three multicast addresses are + * stored in AREG_1-3, and the rest are selected via the + * hash table, as necessary. + * + **************************************************************/ -static void TLan_SetMulticastList( struct net_device *dev ) +static void tlan_set_multicast_list(struct net_device *dev) { struct netdev_hw_addr *ha; u32 hash1 = 0; @@ -1320,53 +1394,56 @@ static void TLan_SetMulticastList( struct net_device *dev ) u32 offset; u8 tmp; - if ( dev->flags & IFF_PROMISC ) { - tmp = TLan_DioRead8( dev->base_addr, TLAN_NET_CMD ); - TLan_DioWrite8( dev->base_addr, - TLAN_NET_CMD, tmp | TLAN_NET_CMD_CAF ); + if (dev->flags & IFF_PROMISC) { + tmp = tlan_dio_read8(dev->base_addr, TLAN_NET_CMD); + tlan_dio_write8(dev->base_addr, + TLAN_NET_CMD, tmp | TLAN_NET_CMD_CAF); } else { - tmp = TLan_DioRead8( dev->base_addr, TLAN_NET_CMD ); - TLan_DioWrite8( dev->base_addr, - TLAN_NET_CMD, tmp & ~TLAN_NET_CMD_CAF ); - if ( dev->flags & IFF_ALLMULTI ) { - for ( i = 0; i < 3; i++ ) - TLan_SetMac( dev, i + 1, NULL ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_1, 0xFFFFFFFF ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_2, 0xFFFFFFFF ); + tmp = tlan_dio_read8(dev->base_addr, TLAN_NET_CMD); + tlan_dio_write8(dev->base_addr, + TLAN_NET_CMD, tmp & ~TLAN_NET_CMD_CAF); + if (dev->flags & IFF_ALLMULTI) { + for (i = 0; i < 3; i++) + tlan_set_mac(dev, i + 1, NULL); + tlan_dio_write32(dev->base_addr, TLAN_HASH_1, + 0xffffffff); + tlan_dio_write32(dev->base_addr, TLAN_HASH_2, + 0xffffffff); } else { i = 0; netdev_for_each_mc_addr(ha, dev) { - if ( i < 3 ) { - TLan_SetMac( dev, i + 1, + if (i < 3) { + tlan_set_mac(dev, i + 1, (char *) &ha->addr); } else { - offset = TLan_HashFunc((u8 *)&ha->addr); - if ( offset < 32 ) - hash1 |= ( 1 << offset ); + offset = + tlan_hash_func((u8 *)&ha->addr); + if (offset < 32) + hash1 |= (1 << offset); else - hash2 |= ( 1 << ( offset - 32 ) ); + hash2 |= (1 << (offset - 32)); } i++; } - for ( ; i < 3; i++ ) - TLan_SetMac( dev, i + 1, NULL ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_1, hash1 ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_2, hash2 ); + for ( ; i < 3; i++) + tlan_set_mac(dev, i + 1, NULL); + tlan_dio_write32(dev->base_addr, TLAN_HASH_1, hash1); + tlan_dio_write32(dev->base_addr, TLAN_HASH_2, hash2); } } -} /* TLan_SetMulticastList */ +} /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Interrupt Vectors and Table +ThunderLAN driver interrupt vectors and table - Please see Chap. 4, "Interrupt Handling" of the "ThunderLAN - Programmer's Guide" for more informations on handling interrupts - generated by TLAN based adapters. +please see chap. 4, "Interrupt Handling" of the "ThunderLAN +Programmer's Guide" for more informations on handling interrupts +generated by TLAN based adapters. ****************************************************************************** *****************************************************************************/ @@ -1374,46 +1451,48 @@ static void TLan_SetMulticastList( struct net_device *dev ) - /*************************************************************** - * TLan_HandleTxEOF - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles Tx EOF interrupts which are raised - * by the adapter when it has completed sending the - * contents of a buffer. If detemines which list/buffer - * was completed and resets it. If the buffer was the last - * in the channel (EOC), then the function checks to see if - * another buffer is ready to send, and if so, sends a Tx - * Go command. Finally, the driver activates/continues the - * activity LED. - * - **************************************************************/ - -static u32 TLan_HandleTxEOF( struct net_device *dev, u16 host_int ) +/*************************************************************** + * tlan_handle_tx_eof + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles Tx EOF interrupts which are raised + * by the adapter when it has completed sending the + * contents of a buffer. If detemines which list/buffer + * was completed and resets it. If the buffer was the last + * in the channel (EOC), then the function checks to see if + * another buffer is ready to send, and if so, sends a Tx + * Go command. Finally, the driver activates/continues the + * activity LED. + * + **************************************************************/ + +static u32 tlan_handle_tx_eof(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int eoc = 0; - TLanList *head_list; + struct tlan_list *head_list; dma_addr_t head_list_phys; u32 ack = 0; - u16 tmpCStat; + u16 tmp_c_stat; - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: Handling TX EOF (Head=%d Tail=%d)\n", - priv->txHead, priv->txTail ); - head_list = priv->txList + priv->txHead; + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: Handling TX EOF (Head=%d Tail=%d)\n", + priv->tx_head, priv->tx_tail); + head_list = priv->tx_list + priv->tx_head; - while (((tmpCStat = head_list->cStat ) & TLAN_CSTAT_FRM_CMP) && (ack < 255)) { - struct sk_buff *skb = TLan_GetSKB(head_list); + while (((tmp_c_stat = head_list->c_stat) & TLAN_CSTAT_FRM_CMP) + && (ack < 255)) { + struct sk_buff *skb = tlan_get_skb(head_list); ack++; - pci_unmap_single(priv->pciDev, head_list->buffer[0].address, + pci_unmap_single(priv->pci_dev, head_list->buffer[0].address, max(skb->len, (unsigned int)TLAN_MIN_FRAME_SIZE), PCI_DMA_TODEVICE); @@ -1421,304 +1500,313 @@ static u32 TLan_HandleTxEOF( struct net_device *dev, u16 host_int ) head_list->buffer[8].address = 0; head_list->buffer[9].address = 0; - if ( tmpCStat & TLAN_CSTAT_EOC ) + if (tmp_c_stat & TLAN_CSTAT_EOC) eoc = 1; - dev->stats.tx_bytes += head_list->frameSize; + dev->stats.tx_bytes += head_list->frame_size; - head_list->cStat = TLAN_CSTAT_UNUSED; + head_list->c_stat = TLAN_CSTAT_UNUSED; netif_start_queue(dev); - CIRC_INC( priv->txHead, TLAN_NUM_TX_LISTS ); - head_list = priv->txList + priv->txHead; + CIRC_INC(priv->tx_head, TLAN_NUM_TX_LISTS); + head_list = priv->tx_list + priv->tx_head; } if (!ack) - printk(KERN_INFO "TLAN: Received interrupt for uncompleted TX frame.\n"); - - if ( eoc ) { - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: Handling TX EOC (Head=%d Tail=%d)\n", - priv->txHead, priv->txTail ); - head_list = priv->txList + priv->txHead; - head_list_phys = priv->txListDMA + sizeof(TLanList) * priv->txHead; - if ( ( head_list->cStat & TLAN_CSTAT_READY ) == TLAN_CSTAT_READY ) { - outl(head_list_phys, dev->base_addr + TLAN_CH_PARM ); + printk(KERN_INFO + "TLAN: Received interrupt for uncompleted TX frame.\n"); + + if (eoc) { + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: handling TX EOC (Head=%d Tail=%d)\n", + priv->tx_head, priv->tx_tail); + head_list = priv->tx_list + priv->tx_head; + head_list_phys = priv->tx_list_dma + + sizeof(struct tlan_list)*priv->tx_head; + if ((head_list->c_stat & TLAN_CSTAT_READY) + == TLAN_CSTAT_READY) { + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO; } else { - priv->txInProgress = 0; + priv->tx_in_progress = 0; } } - if ( priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED ) { - TLan_DioWrite8( dev->base_addr, - TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT ); - if ( priv->timer.function == NULL ) { - priv->timer.function = TLan_Timer; - priv->timer.data = (unsigned long) dev; - priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; - priv->timerSetAt = jiffies; - priv->timerType = TLAN_TIMER_ACTIVITY; - add_timer(&priv->timer); - } else if ( priv->timerType == TLAN_TIMER_ACTIVITY ) { - priv->timerSetAt = jiffies; + if (priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED) { + tlan_dio_write8(dev->base_addr, + TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); + if (priv->timer.function == NULL) { + priv->timer.function = tlan_timer; + priv->timer.data = (unsigned long) dev; + priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; + priv->timer_set_at = jiffies; + priv->timer_type = TLAN_TIMER_ACTIVITY; + add_timer(&priv->timer); + } else if (priv->timer_type == TLAN_TIMER_ACTIVITY) { + priv->timer_set_at = jiffies; } } return ack; -} /* TLan_HandleTxEOF */ +} - /*************************************************************** - * TLan_HandleStatOverflow - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles the Statistics Overflow interrupt - * which means that one or more of the TLAN statistics - * registers has reached 1/2 capacity and needs to be read. - * - **************************************************************/ +/*************************************************************** + * TLan_HandleStatOverflow + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles the Statistics Overflow interrupt + * which means that one or more of the TLAN statistics + * registers has reached 1/2 capacity and needs to be read. + * + **************************************************************/ -static u32 TLan_HandleStatOverflow( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_stat_overflow(struct net_device *dev, u16 host_int) { - TLan_ReadAndClearStats( dev, TLAN_RECORD ); + tlan_read_and_clear_stats(dev, TLAN_RECORD); return 1; -} /* TLan_HandleStatOverflow */ - - - - - /*************************************************************** - * TLan_HandleRxEOF - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles the Rx EOF interrupt which - * indicates a frame has been received by the adapter from - * the net and the frame has been transferred to memory. - * The function determines the bounce buffer the frame has - * been loaded into, creates a new sk_buff big enough to - * hold the frame, and sends it to protocol stack. It - * then resets the used buffer and appends it to the end - * of the list. If the frame was the last in the Rx - * channel (EOC), the function restarts the receive channel - * by sending an Rx Go command to the adapter. Then it - * activates/continues the activity LED. - * - **************************************************************/ - -static u32 TLan_HandleRxEOF( struct net_device *dev, u16 host_int ) +} + + + + +/*************************************************************** + * TLan_HandleRxEOF + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles the Rx EOF interrupt which + * indicates a frame has been received by the adapter from + * the net and the frame has been transferred to memory. + * The function determines the bounce buffer the frame has + * been loaded into, creates a new sk_buff big enough to + * hold the frame, and sends it to protocol stack. It + * then resets the used buffer and appends it to the end + * of the list. If the frame was the last in the Rx + * channel (EOC), the function restarts the receive channel + * by sending an Rx Go command to the adapter. Then it + * activates/continues the activity LED. + * + **************************************************************/ + +static u32 tlan_handle_rx_eof(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u32 ack = 0; int eoc = 0; - TLanList *head_list; + struct tlan_list *head_list; struct sk_buff *skb; - TLanList *tail_list; - u16 tmpCStat; + struct tlan_list *tail_list; + u16 tmp_c_stat; dma_addr_t head_list_phys; - TLAN_DBG( TLAN_DEBUG_RX, "RECEIVE: Handling RX EOF (Head=%d Tail=%d)\n", - priv->rxHead, priv->rxTail ); - head_list = priv->rxList + priv->rxHead; - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; + TLAN_DBG(TLAN_DEBUG_RX, "RECEIVE: handling RX EOF (Head=%d Tail=%d)\n", + priv->rx_head, priv->rx_tail); + head_list = priv->rx_list + priv->rx_head; + head_list_phys = + priv->rx_list_dma + sizeof(struct tlan_list)*priv->rx_head; - while (((tmpCStat = head_list->cStat) & TLAN_CSTAT_FRM_CMP) && (ack < 255)) { - dma_addr_t frameDma = head_list->buffer[0].address; - u32 frameSize = head_list->frameSize; + while (((tmp_c_stat = head_list->c_stat) & TLAN_CSTAT_FRM_CMP) + && (ack < 255)) { + dma_addr_t frame_dma = head_list->buffer[0].address; + u32 frame_size = head_list->frame_size; struct sk_buff *new_skb; ack++; - if (tmpCStat & TLAN_CSTAT_EOC) + if (tmp_c_stat & TLAN_CSTAT_EOC) eoc = 1; new_skb = netdev_alloc_skb_ip_align(dev, TLAN_MAX_FRAME_SIZE + 5); - if ( !new_skb ) + if (!new_skb) goto drop_and_reuse; - skb = TLan_GetSKB(head_list); - pci_unmap_single(priv->pciDev, frameDma, + skb = tlan_get_skb(head_list); + pci_unmap_single(priv->pci_dev, frame_dma, TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - skb_put( skb, frameSize ); + skb_put(skb, frame_size); - dev->stats.rx_bytes += frameSize; + dev->stats.rx_bytes += frame_size; - skb->protocol = eth_type_trans( skb, dev ); - netif_rx( skb ); + skb->protocol = eth_type_trans(skb, dev); + netif_rx(skb); - head_list->buffer[0].address = pci_map_single(priv->pciDev, - new_skb->data, - TLAN_MAX_FRAME_SIZE, - PCI_DMA_FROMDEVICE); + head_list->buffer[0].address = + pci_map_single(priv->pci_dev, new_skb->data, + TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - TLan_StoreSKB(head_list, new_skb); + tlan_store_skb(head_list, new_skb); drop_and_reuse: head_list->forward = 0; - head_list->cStat = 0; - tail_list = priv->rxList + priv->rxTail; + head_list->c_stat = 0; + tail_list = priv->rx_list + priv->rx_tail; tail_list->forward = head_list_phys; - CIRC_INC( priv->rxHead, TLAN_NUM_RX_LISTS ); - CIRC_INC( priv->rxTail, TLAN_NUM_RX_LISTS ); - head_list = priv->rxList + priv->rxHead; - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; + CIRC_INC(priv->rx_head, TLAN_NUM_RX_LISTS); + CIRC_INC(priv->rx_tail, TLAN_NUM_RX_LISTS); + head_list = priv->rx_list + priv->rx_head; + head_list_phys = priv->rx_list_dma + + sizeof(struct tlan_list)*priv->rx_head; } if (!ack) - printk(KERN_INFO "TLAN: Received interrupt for uncompleted RX frame.\n"); - - - if ( eoc ) { - TLAN_DBG( TLAN_DEBUG_RX, - "RECEIVE: Handling RX EOC (Head=%d Tail=%d)\n", - priv->rxHead, priv->rxTail ); - head_list = priv->rxList + priv->rxHead; - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; - outl(head_list_phys, dev->base_addr + TLAN_CH_PARM ); + printk(KERN_INFO + "TLAN: Received interrupt for uncompleted RX frame.\n"); + + + if (eoc) { + TLAN_DBG(TLAN_DEBUG_RX, + "RECEIVE: handling RX EOC (Head=%d Tail=%d)\n", + priv->rx_head, priv->rx_tail); + head_list = priv->rx_list + priv->rx_head; + head_list_phys = priv->rx_list_dma + + sizeof(struct tlan_list)*priv->rx_head; + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO | TLAN_HC_RT; - priv->rxEocCount++; + priv->rx_eoc_count++; } - if ( priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED ) { - TLan_DioWrite8( dev->base_addr, - TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT ); - if ( priv->timer.function == NULL ) { - priv->timer.function = TLan_Timer; + if (priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED) { + tlan_dio_write8(dev->base_addr, + TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); + if (priv->timer.function == NULL) { + priv->timer.function = tlan_timer; priv->timer.data = (unsigned long) dev; priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; - priv->timerSetAt = jiffies; - priv->timerType = TLAN_TIMER_ACTIVITY; + priv->timer_set_at = jiffies; + priv->timer_type = TLAN_TIMER_ACTIVITY; add_timer(&priv->timer); - } else if ( priv->timerType == TLAN_TIMER_ACTIVITY ) { - priv->timerSetAt = jiffies; + } else if (priv->timer_type == TLAN_TIMER_ACTIVITY) { + priv->timer_set_at = jiffies; } } return ack; -} /* TLan_HandleRxEOF */ +} - /*************************************************************** - * TLan_HandleDummy - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles the Dummy interrupt, which is - * raised whenever a test interrupt is generated by setting - * the Req_Int bit of HOST_CMD to 1. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_dummy + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles the Dummy interrupt, which is + * raised whenever a test interrupt is generated by setting + * the Req_Int bit of HOST_CMD to 1. + * + **************************************************************/ -static u32 TLan_HandleDummy( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_dummy(struct net_device *dev, u16 host_int) { - printk( "TLAN: Test interrupt on %s.\n", dev->name ); + pr_info("TLAN: Test interrupt on %s.\n", dev->name); return 1; -} /* TLan_HandleDummy */ +} - /*************************************************************** - * TLan_HandleTxEOC - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This driver is structured to determine EOC occurrences by - * reading the CSTAT member of the list structure. Tx EOC - * interrupts are disabled via the DIO INTDIS register. - * However, TLAN chips before revision 3.0 didn't have this - * functionality, so process EOC events if this is the - * case. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_tx_eoc + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This driver is structured to determine EOC occurrences by + * reading the CSTAT member of the list structure. Tx EOC + * interrupts are disabled via the DIO INTDIS register. + * However, TLAN chips before revision 3.0 didn't have this + * functionality, so process EOC events if this is the + * case. + * + **************************************************************/ -static u32 TLan_HandleTxEOC( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_tx_eoc(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); - TLanList *head_list; + struct tlan_priv *priv = netdev_priv(dev); + struct tlan_list *head_list; dma_addr_t head_list_phys; u32 ack = 1; host_int = 0; - if ( priv->tlanRev < 0x30 ) { - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: Handling TX EOC (Head=%d Tail=%d) -- IRQ\n", - priv->txHead, priv->txTail ); - head_list = priv->txList + priv->txHead; - head_list_phys = priv->txListDMA + sizeof(TLanList) * priv->txHead; - if ( ( head_list->cStat & TLAN_CSTAT_READY ) == TLAN_CSTAT_READY ) { + if (priv->tlan_rev < 0x30) { + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: handling TX EOC (Head=%d Tail=%d) -- IRQ\n", + priv->tx_head, priv->tx_tail); + head_list = priv->tx_list + priv->tx_head; + head_list_phys = priv->tx_list_dma + + sizeof(struct tlan_list)*priv->tx_head; + if ((head_list->c_stat & TLAN_CSTAT_READY) + == TLAN_CSTAT_READY) { netif_stop_queue(dev); - outl( head_list_phys, dev->base_addr + TLAN_CH_PARM ); + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO; } else { - priv->txInProgress = 0; + priv->tx_in_progress = 0; } } return ack; -} /* TLan_HandleTxEOC */ +} - /*************************************************************** - * TLan_HandleStatusCheck - * - * Returns: - * 0 if Adapter check, 1 if Network Status check. - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles Adapter Check/Network Status - * interrupts generated by the adapter. It checks the - * vector in the HOST_INT register to determine if it is - * an Adapter Check interrupt. If so, it resets the - * adapter. Otherwise it clears the status registers - * and services the PHY. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_status_check + * + * Returns: + * 0 if Adapter check, 1 if Network Status check. + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles Adapter Check/Network Status + * interrupts generated by the adapter. It checks the + * vector in the HOST_INT register to determine if it is + * an Adapter Check interrupt. If so, it resets the + * adapter. Otherwise it clears the status registers + * and services the PHY. + * + **************************************************************/ -static u32 TLan_HandleStatusCheck( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_status_check(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u32 ack; u32 error; u8 net_sts; @@ -1727,92 +1815,94 @@ static u32 TLan_HandleStatusCheck( struct net_device *dev, u16 host_int ) u16 tlphy_sts; ack = 1; - if ( host_int & TLAN_HI_IV_MASK ) { - netif_stop_queue( dev ); - error = inl( dev->base_addr + TLAN_CH_PARM ); - printk( "TLAN: %s: Adaptor Error = 0x%x\n", dev->name, error ); - TLan_ReadAndClearStats( dev, TLAN_RECORD ); - outl( TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD ); + if (host_int & TLAN_HI_IV_MASK) { + netif_stop_queue(dev); + error = inl(dev->base_addr + TLAN_CH_PARM); + pr_info("TLAN: %s: Adaptor Error = 0x%x\n", dev->name, error); + tlan_read_and_clear_stats(dev, TLAN_RECORD); + outl(TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD); schedule_work(&priv->tlan_tqueue); netif_wake_queue(dev); ack = 0; } else { - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Status Check\n", dev->name ); - phy = priv->phy[priv->phyNum]; - - net_sts = TLan_DioRead8( dev->base_addr, TLAN_NET_STS ); - if ( net_sts ) { - TLan_DioWrite8( dev->base_addr, TLAN_NET_STS, net_sts ); - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Net_Sts = %x\n", - dev->name, (unsigned) net_sts ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Status Check\n", dev->name); + phy = priv->phy[priv->phy_num]; + + net_sts = tlan_dio_read8(dev->base_addr, TLAN_NET_STS); + if (net_sts) { + tlan_dio_write8(dev->base_addr, TLAN_NET_STS, net_sts); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Net_Sts = %x\n", + dev->name, (unsigned) net_sts); } - if ( ( net_sts & TLAN_NET_STS_MIRQ ) && ( priv->phyNum == 0 ) ) { - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_STS, &tlphy_sts ); - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl ); - if ( ! ( tlphy_sts & TLAN_TS_POLOK ) && - ! ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { - tlphy_ctl |= TLAN_TC_SWAPOL; - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); - } else if ( ( tlphy_sts & TLAN_TS_POLOK ) && - ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { - tlphy_ctl &= ~TLAN_TC_SWAPOL; - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); - } - - if (debug) { - TLan_PhyPrint( dev ); + if ((net_sts & TLAN_NET_STS_MIRQ) && (priv->phy_num == 0)) { + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_STS, &tlphy_sts); + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl); + if (!(tlphy_sts & TLAN_TS_POLOK) && + !(tlphy_ctl & TLAN_TC_SWAPOL)) { + tlphy_ctl |= TLAN_TC_SWAPOL; + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, + tlphy_ctl); + } else if ((tlphy_sts & TLAN_TS_POLOK) && + (tlphy_ctl & TLAN_TC_SWAPOL)) { + tlphy_ctl &= ~TLAN_TC_SWAPOL; + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, + tlphy_ctl); } + + if (debug) + tlan_phy_print(dev); } } return ack; -} /* TLan_HandleStatusCheck */ +} - /*************************************************************** - * TLan_HandleRxEOC - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This driver is structured to determine EOC occurrences by - * reading the CSTAT member of the list structure. Rx EOC - * interrupts are disabled via the DIO INTDIS register. - * However, TLAN chips before revision 3.0 didn't have this - * CSTAT member or a INTDIS register, so if this chip is - * pre-3.0, process EOC interrupts normally. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_rx_eoc + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This driver is structured to determine EOC occurrences by + * reading the CSTAT member of the list structure. Rx EOC + * interrupts are disabled via the DIO INTDIS register. + * However, TLAN chips before revision 3.0 didn't have this + * CSTAT member or a INTDIS register, so if this chip is + * pre-3.0, process EOC interrupts normally. + * + **************************************************************/ -static u32 TLan_HandleRxEOC( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_rx_eoc(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); dma_addr_t head_list_phys; u32 ack = 1; - if ( priv->tlanRev < 0x30 ) { - TLAN_DBG( TLAN_DEBUG_RX, - "RECEIVE: Handling RX EOC (Head=%d Tail=%d) -- IRQ\n", - priv->rxHead, priv->rxTail ); - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; - outl( head_list_phys, dev->base_addr + TLAN_CH_PARM ); + if (priv->tlan_rev < 0x30) { + TLAN_DBG(TLAN_DEBUG_RX, + "RECEIVE: Handling RX EOC (head=%d tail=%d) -- IRQ\n", + priv->rx_head, priv->rx_tail); + head_list_phys = priv->rx_list_dma + + sizeof(struct tlan_list)*priv->rx_head; + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO | TLAN_HC_RT; - priv->rxEocCount++; + priv->rx_eoc_count++; } return ack; -} /* TLan_HandleRxEOC */ +} @@ -1820,98 +1910,98 @@ static u32 TLan_HandleRxEOC( struct net_device *dev, u16 host_int ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Timer Function +ThunderLAN driver timer function ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_Timer - * - * Returns: - * Nothing - * Parms: - * data A value given to add timer when - * add_timer was called. - * - * This function handles timed functionality for the - * TLAN driver. The two current timer uses are for - * delaying for autonegotionation and driving the ACT LED. - * - Autonegotiation requires being allowed about - * 2 1/2 seconds before attempting to transmit a - * packet. It would be a very bad thing to hang - * the kernel this long, so the driver doesn't - * allow transmission 'til after this time, for - * certain PHYs. It would be much nicer if all - * PHYs were interrupt-capable like the internal - * PHY. - * - The ACT LED, which shows adapter activity, is - * driven by the driver, and so must be left on - * for a short period to power up the LED so it - * can be seen. This delay can be changed by - * changing the TLAN_TIMER_ACT_DELAY in tlan.h, - * if desired. 100 ms produces a slightly - * sluggish response. - * - **************************************************************/ - -static void TLan_Timer( unsigned long data ) +/*************************************************************** + * tlan_timer + * + * Returns: + * Nothing + * Parms: + * data A value given to add timer when + * add_timer was called. + * + * This function handles timed functionality for the + * TLAN driver. The two current timer uses are for + * delaying for autonegotionation and driving the ACT LED. + * - Autonegotiation requires being allowed about + * 2 1/2 seconds before attempting to transmit a + * packet. It would be a very bad thing to hang + * the kernel this long, so the driver doesn't + * allow transmission 'til after this time, for + * certain PHYs. It would be much nicer if all + * PHYs were interrupt-capable like the internal + * PHY. + * - The ACT LED, which shows adapter activity, is + * driven by the driver, and so must be left on + * for a short period to power up the LED so it + * can be seen. This delay can be changed by + * changing the TLAN_TIMER_ACT_DELAY in tlan.h, + * if desired. 100 ms produces a slightly + * sluggish response. + * + **************************************************************/ + +static void tlan_timer(unsigned long data) { struct net_device *dev = (struct net_device *) data; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u32 elapsed; unsigned long flags = 0; priv->timer.function = NULL; - switch ( priv->timerType ) { + switch (priv->timer_type) { #ifdef MONITOR - case TLAN_TIMER_LINK_BEAT: - TLan_PhyMonitor( dev ); - break; + case TLAN_TIMER_LINK_BEAT: + tlan_phy_monitor(dev); + break; #endif - case TLAN_TIMER_PHY_PDOWN: - TLan_PhyPowerDown( dev ); - break; - case TLAN_TIMER_PHY_PUP: - TLan_PhyPowerUp( dev ); - break; - case TLAN_TIMER_PHY_RESET: - TLan_PhyReset( dev ); - break; - case TLAN_TIMER_PHY_START_LINK: - TLan_PhyStartLink( dev ); - break; - case TLAN_TIMER_PHY_FINISH_AN: - TLan_PhyFinishAutoNeg( dev ); - break; - case TLAN_TIMER_FINISH_RESET: - TLan_FinishReset( dev ); - break; - case TLAN_TIMER_ACTIVITY: - spin_lock_irqsave(&priv->lock, flags); - if ( priv->timer.function == NULL ) { - elapsed = jiffies - priv->timerSetAt; - if ( elapsed >= TLAN_TIMER_ACT_DELAY ) { - TLan_DioWrite8( dev->base_addr, - TLAN_LED_REG, TLAN_LED_LINK ); - } else { - priv->timer.function = TLan_Timer; - priv->timer.expires = priv->timerSetAt - + TLAN_TIMER_ACT_DELAY; - spin_unlock_irqrestore(&priv->lock, flags); - add_timer( &priv->timer ); - break; - } + case TLAN_TIMER_PHY_PDOWN: + tlan_phy_power_down(dev); + break; + case TLAN_TIMER_PHY_PUP: + tlan_phy_power_up(dev); + break; + case TLAN_TIMER_PHY_RESET: + tlan_phy_reset(dev); + break; + case TLAN_TIMER_PHY_START_LINK: + tlan_phy_start_link(dev); + break; + case TLAN_TIMER_PHY_FINISH_AN: + tlan_phy_finish_auto_neg(dev); + break; + case TLAN_TIMER_FINISH_RESET: + tlan_finish_reset(dev); + break; + case TLAN_TIMER_ACTIVITY: + spin_lock_irqsave(&priv->lock, flags); + if (priv->timer.function == NULL) { + elapsed = jiffies - priv->timer_set_at; + if (elapsed >= TLAN_TIMER_ACT_DELAY) { + tlan_dio_write8(dev->base_addr, + TLAN_LED_REG, TLAN_LED_LINK); + } else { + priv->timer.function = tlan_timer; + priv->timer.expires = priv->timer_set_at + + TLAN_TIMER_ACT_DELAY; + spin_unlock_irqrestore(&priv->lock, flags); + add_timer(&priv->timer); + break; } - spin_unlock_irqrestore(&priv->lock, flags); - break; - default: - break; + } + spin_unlock_irqrestore(&priv->lock, flags); + break; + default: + break; } -} /* TLan_Timer */ +} @@ -1919,39 +2009,39 @@ static void TLan_Timer( unsigned long data ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Adapter Related Routines +ThunderLAN driver adapter related routines ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_ResetLists - * - * Returns: - * Nothing - * Parms: - * dev The device structure with the list - * stuctures to be reset. - * - * This routine sets the variables associated with managing - * the TLAN lists to their initial values. - * - **************************************************************/ - -static void TLan_ResetLists( struct net_device *dev ) +/*************************************************************** + * tlan_reset_lists + * + * Returns: + * Nothing + * Parms: + * dev The device structure with the list + * stuctures to be reset. + * + * This routine sets the variables associated with managing + * the TLAN lists to their initial values. + * + **************************************************************/ + +static void tlan_reset_lists(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; - TLanList *list; + struct tlan_list *list; dma_addr_t list_phys; struct sk_buff *skb; - priv->txHead = 0; - priv->txTail = 0; - for ( i = 0; i < TLAN_NUM_TX_LISTS; i++ ) { - list = priv->txList + i; - list->cStat = TLAN_CSTAT_UNUSED; + priv->tx_head = 0; + priv->tx_tail = 0; + for (i = 0; i < TLAN_NUM_TX_LISTS; i++) { + list = priv->tx_list + i; + list->c_stat = TLAN_CSTAT_UNUSED; list->buffer[0].address = 0; list->buffer[2].count = 0; list->buffer[2].address = 0; @@ -1959,169 +2049,169 @@ static void TLan_ResetLists( struct net_device *dev ) list->buffer[9].address = 0; } - priv->rxHead = 0; - priv->rxTail = TLAN_NUM_RX_LISTS - 1; - for ( i = 0; i < TLAN_NUM_RX_LISTS; i++ ) { - list = priv->rxList + i; - list_phys = priv->rxListDMA + sizeof(TLanList) * i; - list->cStat = TLAN_CSTAT_READY; - list->frameSize = TLAN_MAX_FRAME_SIZE; + priv->rx_head = 0; + priv->rx_tail = TLAN_NUM_RX_LISTS - 1; + for (i = 0; i < TLAN_NUM_RX_LISTS; i++) { + list = priv->rx_list + i; + list_phys = priv->rx_list_dma + sizeof(struct tlan_list)*i; + list->c_stat = TLAN_CSTAT_READY; + list->frame_size = TLAN_MAX_FRAME_SIZE; list->buffer[0].count = TLAN_MAX_FRAME_SIZE | TLAN_LAST_BUFFER; skb = netdev_alloc_skb_ip_align(dev, TLAN_MAX_FRAME_SIZE + 5); - if ( !skb ) { - pr_err("TLAN: out of memory for received data.\n" ); + if (!skb) { + pr_err("TLAN: out of memory for received data.\n"); break; } - list->buffer[0].address = pci_map_single(priv->pciDev, + list->buffer[0].address = pci_map_single(priv->pci_dev, skb->data, TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - TLan_StoreSKB(list, skb); + tlan_store_skb(list, skb); list->buffer[1].count = 0; list->buffer[1].address = 0; - list->forward = list_phys + sizeof(TLanList); + list->forward = list_phys + sizeof(struct tlan_list); } /* in case ran out of memory early, clear bits */ while (i < TLAN_NUM_RX_LISTS) { - TLan_StoreSKB(priv->rxList + i, NULL); + tlan_store_skb(priv->rx_list + i, NULL); ++i; } list->forward = 0; -} /* TLan_ResetLists */ +} -static void TLan_FreeLists( struct net_device *dev ) +static void tlan_free_lists(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; - TLanList *list; + struct tlan_list *list; struct sk_buff *skb; - for ( i = 0; i < TLAN_NUM_TX_LISTS; i++ ) { - list = priv->txList + i; - skb = TLan_GetSKB(list); - if ( skb ) { + for (i = 0; i < TLAN_NUM_TX_LISTS; i++) { + list = priv->tx_list + i; + skb = tlan_get_skb(list); + if (skb) { pci_unmap_single( - priv->pciDev, + priv->pci_dev, list->buffer[0].address, max(skb->len, (unsigned int)TLAN_MIN_FRAME_SIZE), PCI_DMA_TODEVICE); - dev_kfree_skb_any( skb ); + dev_kfree_skb_any(skb); list->buffer[8].address = 0; list->buffer[9].address = 0; } } - for ( i = 0; i < TLAN_NUM_RX_LISTS; i++ ) { - list = priv->rxList + i; - skb = TLan_GetSKB(list); - if ( skb ) { - pci_unmap_single(priv->pciDev, + for (i = 0; i < TLAN_NUM_RX_LISTS; i++) { + list = priv->rx_list + i; + skb = tlan_get_skb(list); + if (skb) { + pci_unmap_single(priv->pci_dev, list->buffer[0].address, TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - dev_kfree_skb_any( skb ); + dev_kfree_skb_any(skb); list->buffer[8].address = 0; list->buffer[9].address = 0; } } -} /* TLan_FreeLists */ +} - /*************************************************************** - * TLan_PrintDio - * - * Returns: - * Nothing - * Parms: - * io_base Base IO port of the device of - * which to print DIO registers. - * - * This function prints out all the internal (DIO) - * registers of a TLAN chip. - * - **************************************************************/ +/*************************************************************** + * tlan_print_dio + * + * Returns: + * Nothing + * Parms: + * io_base Base IO port of the device of + * which to print DIO registers. + * + * This function prints out all the internal (DIO) + * registers of a TLAN chip. + * + **************************************************************/ -static void TLan_PrintDio( u16 io_base ) +static void tlan_print_dio(u16 io_base) { u32 data0, data1; int i; - printk( "TLAN: Contents of internal registers for io base 0x%04hx.\n", - io_base ); - printk( "TLAN: Off. +0 +4\n" ); - for ( i = 0; i < 0x4C; i+= 8 ) { - data0 = TLan_DioRead32( io_base, i ); - data1 = TLan_DioRead32( io_base, i + 0x4 ); - printk( "TLAN: 0x%02x 0x%08x 0x%08x\n", i, data0, data1 ); + pr_info("TLAN: Contents of internal registers for io base 0x%04hx.\n", + io_base); + pr_info("TLAN: Off. +0 +4\n"); + for (i = 0; i < 0x4C; i += 8) { + data0 = tlan_dio_read32(io_base, i); + data1 = tlan_dio_read32(io_base, i + 0x4); + pr_info("TLAN: 0x%02x 0x%08x 0x%08x\n", i, data0, data1); } -} /* TLan_PrintDio */ +} - /*************************************************************** - * TLan_PrintList - * - * Returns: - * Nothing - * Parms: - * list A pointer to the TLanList structure to - * be printed. - * type A string to designate type of list, - * "Rx" or "Tx". - * num The index of the list. - * - * This function prints out the contents of the list - * pointed to by the list parameter. - * - **************************************************************/ +/*************************************************************** + * TLan_PrintList + * + * Returns: + * Nothing + * Parms: + * list A pointer to the struct tlan_list structure to + * be printed. + * type A string to designate type of list, + * "Rx" or "Tx". + * num The index of the list. + * + * This function prints out the contents of the list + * pointed to by the list parameter. + * + **************************************************************/ -static void TLan_PrintList( TLanList *list, char *type, int num) +static void tlan_print_list(struct tlan_list *list, char *type, int num) { int i; - printk( "TLAN: %s List %d at %p\n", type, num, list ); - printk( "TLAN: Forward = 0x%08x\n", list->forward ); - printk( "TLAN: CSTAT = 0x%04hx\n", list->cStat ); - printk( "TLAN: Frame Size = 0x%04hx\n", list->frameSize ); - /* for ( i = 0; i < 10; i++ ) { */ - for ( i = 0; i < 2; i++ ) { - printk( "TLAN: Buffer[%d].count, addr = 0x%08x, 0x%08x\n", - i, list->buffer[i].count, list->buffer[i].address ); + pr_info("TLAN: %s List %d at %p\n", type, num, list); + pr_info("TLAN: Forward = 0x%08x\n", list->forward); + pr_info("TLAN: CSTAT = 0x%04hx\n", list->c_stat); + pr_info("TLAN: Frame Size = 0x%04hx\n", list->frame_size); + /* for (i = 0; i < 10; i++) { */ + for (i = 0; i < 2; i++) { + pr_info("TLAN: Buffer[%d].count, addr = 0x%08x, 0x%08x\n", + i, list->buffer[i].count, list->buffer[i].address); } -} /* TLan_PrintList */ +} - /*************************************************************** - * TLan_ReadAndClearStats - * - * Returns: - * Nothing - * Parms: - * dev Pointer to device structure of adapter - * to which to read stats. - * record Flag indicating whether to add - * - * This functions reads all the internal status registers - * of the TLAN chip, which clears them as a side effect. - * It then either adds the values to the device's status - * struct, or discards them, depending on whether record - * is TLAN_RECORD (!=0) or TLAN_IGNORE (==0). - * - **************************************************************/ +/*************************************************************** + * tlan_read_and_clear_stats + * + * Returns: + * Nothing + * Parms: + * dev Pointer to device structure of adapter + * to which to read stats. + * record Flag indicating whether to add + * + * This functions reads all the internal status registers + * of the TLAN chip, which clears them as a side effect. + * It then either adds the values to the device's status + * struct, or discards them, depending on whether record + * is TLAN_RECORD (!=0) or TLAN_IGNORE (==0). + * + **************************************************************/ -static void TLan_ReadAndClearStats( struct net_device *dev, int record ) +static void tlan_read_and_clear_stats(struct net_device *dev, int record) { u32 tx_good, tx_under; u32 rx_good, rx_over; @@ -2129,41 +2219,42 @@ static void TLan_ReadAndClearStats( struct net_device *dev, int record ) u32 multi_col, single_col; u32 excess_col, late_col, loss; - outw( TLAN_GOOD_TX_FRMS, dev->base_addr + TLAN_DIO_ADR ); - tx_good = inb( dev->base_addr + TLAN_DIO_DATA ); - tx_good += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - tx_good += inb( dev->base_addr + TLAN_DIO_DATA + 2 ) << 16; - tx_under = inb( dev->base_addr + TLAN_DIO_DATA + 3 ); - - outw( TLAN_GOOD_RX_FRMS, dev->base_addr + TLAN_DIO_ADR ); - rx_good = inb( dev->base_addr + TLAN_DIO_DATA ); - rx_good += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - rx_good += inb( dev->base_addr + TLAN_DIO_DATA + 2 ) << 16; - rx_over = inb( dev->base_addr + TLAN_DIO_DATA + 3 ); - - outw( TLAN_DEFERRED_TX, dev->base_addr + TLAN_DIO_ADR ); - def_tx = inb( dev->base_addr + TLAN_DIO_DATA ); - def_tx += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - crc = inb( dev->base_addr + TLAN_DIO_DATA + 2 ); - code = inb( dev->base_addr + TLAN_DIO_DATA + 3 ); - - outw( TLAN_MULTICOL_FRMS, dev->base_addr + TLAN_DIO_ADR ); - multi_col = inb( dev->base_addr + TLAN_DIO_DATA ); - multi_col += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - single_col = inb( dev->base_addr + TLAN_DIO_DATA + 2 ); - single_col += inb( dev->base_addr + TLAN_DIO_DATA + 3 ) << 8; - - outw( TLAN_EXCESSCOL_FRMS, dev->base_addr + TLAN_DIO_ADR ); - excess_col = inb( dev->base_addr + TLAN_DIO_DATA ); - late_col = inb( dev->base_addr + TLAN_DIO_DATA + 1 ); - loss = inb( dev->base_addr + TLAN_DIO_DATA + 2 ); - - if ( record ) { + outw(TLAN_GOOD_TX_FRMS, dev->base_addr + TLAN_DIO_ADR); + tx_good = inb(dev->base_addr + TLAN_DIO_DATA); + tx_good += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + tx_good += inb(dev->base_addr + TLAN_DIO_DATA + 2) << 16; + tx_under = inb(dev->base_addr + TLAN_DIO_DATA + 3); + + outw(TLAN_GOOD_RX_FRMS, dev->base_addr + TLAN_DIO_ADR); + rx_good = inb(dev->base_addr + TLAN_DIO_DATA); + rx_good += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + rx_good += inb(dev->base_addr + TLAN_DIO_DATA + 2) << 16; + rx_over = inb(dev->base_addr + TLAN_DIO_DATA + 3); + + outw(TLAN_DEFERRED_TX, dev->base_addr + TLAN_DIO_ADR); + def_tx = inb(dev->base_addr + TLAN_DIO_DATA); + def_tx += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + crc = inb(dev->base_addr + TLAN_DIO_DATA + 2); + code = inb(dev->base_addr + TLAN_DIO_DATA + 3); + + outw(TLAN_MULTICOL_FRMS, dev->base_addr + TLAN_DIO_ADR); + multi_col = inb(dev->base_addr + TLAN_DIO_DATA); + multi_col += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + single_col = inb(dev->base_addr + TLAN_DIO_DATA + 2); + single_col += inb(dev->base_addr + TLAN_DIO_DATA + 3) << 8; + + outw(TLAN_EXCESSCOL_FRMS, dev->base_addr + TLAN_DIO_ADR); + excess_col = inb(dev->base_addr + TLAN_DIO_DATA); + late_col = inb(dev->base_addr + TLAN_DIO_DATA + 1); + loss = inb(dev->base_addr + TLAN_DIO_DATA + 2); + + if (record) { dev->stats.rx_packets += rx_good; dev->stats.rx_errors += rx_over + crc + code; dev->stats.tx_packets += tx_good; dev->stats.tx_errors += tx_under + loss; - dev->stats.collisions += multi_col + single_col + excess_col + late_col; + dev->stats.collisions += multi_col + + single_col + excess_col + late_col; dev->stats.rx_over_errors += rx_over; dev->stats.rx_crc_errors += crc; @@ -2173,39 +2264,39 @@ static void TLan_ReadAndClearStats( struct net_device *dev, int record ) dev->stats.tx_carrier_errors += loss; } -} /* TLan_ReadAndClearStats */ +} - /*************************************************************** - * TLan_Reset - * - * Returns: - * 0 - * Parms: - * dev Pointer to device structure of adapter - * to be reset. - * - * This function resets the adapter and it's physical - * device. See Chap. 3, pp. 9-10 of the "ThunderLAN - * Programmer's Guide" for details. The routine tries to - * implement what is detailed there, though adjustments - * have been made. - * - **************************************************************/ +/*************************************************************** + * TLan_Reset + * + * Returns: + * 0 + * Parms: + * dev Pointer to device structure of adapter + * to be reset. + * + * This function resets the adapter and it's physical + * device. See Chap. 3, pp. 9-10 of the "ThunderLAN + * Programmer's Guide" for details. The routine tries to + * implement what is detailed there, though adjustments + * have been made. + * + **************************************************************/ static void -TLan_ResetAdapter( struct net_device *dev ) +tlan_reset_adapter(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; u32 addr; u32 data; u8 data8; - priv->tlanFullDuplex = false; - priv->phyOnline=0; + priv->tlan_full_duplex = false; + priv->phy_online = 0; netif_carrier_off(dev); /* 1. Assert reset bit. */ @@ -2216,7 +2307,7 @@ TLan_ResetAdapter( struct net_device *dev ) udelay(1000); -/* 2. Turn off interrupts. ( Probably isn't necessary ) */ +/* 2. Turn off interrupts. (Probably isn't necessary) */ data = inl(dev->base_addr + TLAN_HOST_CMD); data |= TLAN_HC_INT_OFF; @@ -2224,207 +2315,208 @@ TLan_ResetAdapter( struct net_device *dev ) /* 3. Clear AREGs and HASHs. */ - for ( i = TLAN_AREG_0; i <= TLAN_HASH_2; i += 4 ) { - TLan_DioWrite32( dev->base_addr, (u16) i, 0 ); - } + for (i = TLAN_AREG_0; i <= TLAN_HASH_2; i += 4) + tlan_dio_write32(dev->base_addr, (u16) i, 0); /* 4. Setup NetConfig register. */ data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, (u16) data ); + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, (u16) data); /* 5. Load Ld_Tmr and Ld_Thr in HOST_CMD. */ - outl( TLAN_HC_LD_TMR | 0x3f, dev->base_addr + TLAN_HOST_CMD ); - outl( TLAN_HC_LD_THR | 0x9, dev->base_addr + TLAN_HOST_CMD ); + outl(TLAN_HC_LD_TMR | 0x3f, dev->base_addr + TLAN_HOST_CMD); + outl(TLAN_HC_LD_THR | 0x9, dev->base_addr + TLAN_HOST_CMD); /* 6. Unreset the MII by setting NMRST (in NetSio) to 1. */ - outw( TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR); addr = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_SetBit( TLAN_NET_SIO_NMRST, addr ); + tlan_set_bit(TLAN_NET_SIO_NMRST, addr); /* 7. Setup the remaining registers. */ - if ( priv->tlanRev >= 0x30 ) { + if (priv->tlan_rev >= 0x30) { data8 = TLAN_ID_TX_EOC | TLAN_ID_RX_EOC; - TLan_DioWrite8( dev->base_addr, TLAN_INT_DIS, data8 ); + tlan_dio_write8(dev->base_addr, TLAN_INT_DIS, data8); } - TLan_PhyDetect( dev ); + tlan_phy_detect(dev); data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN; - if ( priv->adapter->flags & TLAN_ADAPTER_BIT_RATE_PHY ) { + if (priv->adapter->flags & TLAN_ADAPTER_BIT_RATE_PHY) { data |= TLAN_NET_CFG_BIT; - if ( priv->aui == 1 ) { - TLan_DioWrite8( dev->base_addr, TLAN_ACOMMIT, 0x0a ); - } else if ( priv->duplex == TLAN_DUPLEX_FULL ) { - TLan_DioWrite8( dev->base_addr, TLAN_ACOMMIT, 0x00 ); - priv->tlanFullDuplex = true; + if (priv->aui == 1) { + tlan_dio_write8(dev->base_addr, TLAN_ACOMMIT, 0x0a); + } else if (priv->duplex == TLAN_DUPLEX_FULL) { + tlan_dio_write8(dev->base_addr, TLAN_ACOMMIT, 0x00); + priv->tlan_full_duplex = true; } else { - TLan_DioWrite8( dev->base_addr, TLAN_ACOMMIT, 0x08 ); + tlan_dio_write8(dev->base_addr, TLAN_ACOMMIT, 0x08); } } - if ( priv->phyNum == 0 ) { + if (priv->phy_num == 0) data |= TLAN_NET_CFG_PHY_EN; - } - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, (u16) data ); + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, (u16) data); - if ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) { - TLan_FinishReset( dev ); - } else { - TLan_PhyPowerDown( dev ); - } + if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) + tlan_finish_reset(dev); + else + tlan_phy_power_down(dev); -} /* TLan_ResetAdapter */ +} static void -TLan_FinishReset( struct net_device *dev ) +tlan_finish_reset(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u8 data; u32 phy; u8 sio; u16 status; u16 partner; u16 tlphy_ctl; - u16 tlphy_par; + u16 tlphy_par; u16 tlphy_id1, tlphy_id2; - int i; + int i; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; data = TLAN_NET_CMD_NRESET | TLAN_NET_CMD_NWRAP; - if ( priv->tlanFullDuplex ) { + if (priv->tlan_full_duplex) data |= TLAN_NET_CMD_DUPLEX; - } - TLan_DioWrite8( dev->base_addr, TLAN_NET_CMD, data ); + tlan_dio_write8(dev->base_addr, TLAN_NET_CMD, data); data = TLAN_NET_MASK_MASK4 | TLAN_NET_MASK_MASK5; - if ( priv->phyNum == 0 ) { + if (priv->phy_num == 0) data |= TLAN_NET_MASK_MASK7; - } - TLan_DioWrite8( dev->base_addr, TLAN_NET_MASK, data ); - TLan_DioWrite16( dev->base_addr, TLAN_MAX_RX, ((1536)+7)&~7 ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_HI, &tlphy_id1 ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_LO, &tlphy_id2 ); + tlan_dio_write8(dev->base_addr, TLAN_NET_MASK, data); + tlan_dio_write16(dev->base_addr, TLAN_MAX_RX, ((1536)+7)&~7); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_HI, &tlphy_id1); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_LO, &tlphy_id2); - if ( ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) || - ( priv->aui ) ) { + if ((priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) || + (priv->aui)) { status = MII_GS_LINK; - printk( "TLAN: %s: Link forced.\n", dev->name ); + pr_info("TLAN: %s: Link forced.\n", dev->name); } else { - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - udelay( 1000 ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - if ( (status & MII_GS_LINK) && - /* We only support link info on Nat.Sem. PHY's */ - (tlphy_id1 == NAT_SEM_ID1) && - (tlphy_id2 == NAT_SEM_ID2) ) { - TLan_MiiReadReg( dev, phy, MII_AN_LPA, &partner ); - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_PAR, &tlphy_par ); - - printk( "TLAN: %s: Link active with ", dev->name ); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + udelay(1000); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + if ((status & MII_GS_LINK) && + /* We only support link info on Nat.Sem. PHY's */ + (tlphy_id1 == NAT_SEM_ID1) && + (tlphy_id2 == NAT_SEM_ID2)) { + tlan_mii_read_reg(dev, phy, MII_AN_LPA, &partner); + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_PAR, &tlphy_par); + + pr_info("TLAN: %s: Link active with ", dev->name); if (!(tlphy_par & TLAN_PHY_AN_EN_STAT)) { - printk( "forced 10%sMbps %s-Duplex\n", - tlphy_par & TLAN_PHY_SPEED_100 ? "" : "0", - tlphy_par & TLAN_PHY_DUPLEX_FULL ? "Full" : "Half"); + pr_info("forced 10%sMbps %s-Duplex\n", + tlphy_par & TLAN_PHY_SPEED_100 + ? "" : "0", + tlphy_par & TLAN_PHY_DUPLEX_FULL + ? "Full" : "Half"); } else { - printk( "AutoNegotiation enabled, at 10%sMbps %s-Duplex\n", - tlphy_par & TLAN_PHY_SPEED_100 ? "" : "0", - tlphy_par & TLAN_PHY_DUPLEX_FULL ? "Full" : "Half"); - printk("TLAN: Partner capability: "); - for (i = 5; i <= 10; i++) - if (partner & (1<<i)) - printk("%s",media[i-5]); + pr_info("Autonegotiation enabled, at 10%sMbps %s-Duplex\n", + tlphy_par & TLAN_PHY_SPEED_100 + ? "" : "0", + tlphy_par & TLAN_PHY_DUPLEX_FULL + ? "Full" : "half"); + pr_info("TLAN: Partner capability: "); + for (i = 5; i <= 10; i++) + if (partner & (1<<i)) + printk("%s", media[i-5]); printk("\n"); } - TLan_DioWrite8( dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK ); + tlan_dio_write8(dev->base_addr, TLAN_LED_REG, + TLAN_LED_LINK); #ifdef MONITOR /* We have link beat..for now anyway */ - priv->link = 1; - /*Enabling link beat monitoring */ - TLan_SetTimer( dev, (10*HZ), TLAN_TIMER_LINK_BEAT ); + priv->link = 1; + /*Enabling link beat monitoring */ + tlan_set_timer(dev, (10*HZ), TLAN_TIMER_LINK_BEAT); #endif } else if (status & MII_GS_LINK) { - printk( "TLAN: %s: Link active\n", dev->name ); - TLan_DioWrite8( dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK ); + pr_info("TLAN: %s: Link active\n", dev->name); + tlan_dio_write8(dev->base_addr, TLAN_LED_REG, + TLAN_LED_LINK); } } - if ( priv->phyNum == 0 ) { - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl ); - tlphy_ctl |= TLAN_TC_INTEN; - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl ); - sio = TLan_DioRead8( dev->base_addr, TLAN_NET_SIO ); - sio |= TLAN_NET_SIO_MINTEN; - TLan_DioWrite8( dev->base_addr, TLAN_NET_SIO, sio ); - } - - if ( status & MII_GS_LINK ) { - TLan_SetMac( dev, 0, dev->dev_addr ); - priv->phyOnline = 1; - outb( ( TLAN_HC_INT_ON >> 8 ), dev->base_addr + TLAN_HOST_CMD + 1 ); - if ( debug >= 1 && debug != TLAN_DEBUG_PROBE ) { - outb( ( TLAN_HC_REQ_INT >> 8 ), dev->base_addr + TLAN_HOST_CMD + 1 ); - } - outl( priv->rxListDMA, dev->base_addr + TLAN_CH_PARM ); - outl( TLAN_HC_GO | TLAN_HC_RT, dev->base_addr + TLAN_HOST_CMD ); + if (priv->phy_num == 0) { + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl); + tlphy_ctl |= TLAN_TC_INTEN; + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); + sio = tlan_dio_read8(dev->base_addr, TLAN_NET_SIO); + sio |= TLAN_NET_SIO_MINTEN; + tlan_dio_write8(dev->base_addr, TLAN_NET_SIO, sio); + } + + if (status & MII_GS_LINK) { + tlan_set_mac(dev, 0, dev->dev_addr); + priv->phy_online = 1; + outb((TLAN_HC_INT_ON >> 8), dev->base_addr + TLAN_HOST_CMD + 1); + if (debug >= 1 && debug != TLAN_DEBUG_PROBE) + outb((TLAN_HC_REQ_INT >> 8), + dev->base_addr + TLAN_HOST_CMD + 1); + outl(priv->rx_list_dma, dev->base_addr + TLAN_CH_PARM); + outl(TLAN_HC_GO | TLAN_HC_RT, dev->base_addr + TLAN_HOST_CMD); netif_carrier_on(dev); } else { - printk( "TLAN: %s: Link inactive, will retry in 10 secs...\n", - dev->name ); - TLan_SetTimer( dev, (10*HZ), TLAN_TIMER_FINISH_RESET ); + pr_info("TLAN: %s: Link inactive, will retry in 10 secs...\n", + dev->name); + tlan_set_timer(dev, (10*HZ), TLAN_TIMER_FINISH_RESET); return; } - TLan_SetMulticastList(dev); + tlan_set_multicast_list(dev); -} /* TLan_FinishReset */ +} - /*************************************************************** - * TLan_SetMac - * - * Returns: - * Nothing - * Parms: - * dev Pointer to device structure of adapter - * on which to change the AREG. - * areg The AREG to set the address in (0 - 3). - * mac A pointer to an array of chars. Each - * element stores one byte of the address. - * IE, it isn't in ascii. - * - * This function transfers a MAC address to one of the - * TLAN AREGs (address registers). The TLAN chip locks - * the register on writing to offset 0 and unlocks the - * register after writing to offset 5. If NULL is passed - * in mac, then the AREG is filled with 0's. - * - **************************************************************/ +/*************************************************************** + * tlan_set_mac + * + * Returns: + * Nothing + * Parms: + * dev Pointer to device structure of adapter + * on which to change the AREG. + * areg The AREG to set the address in (0 - 3). + * mac A pointer to an array of chars. Each + * element stores one byte of the address. + * IE, it isn't in ascii. + * + * This function transfers a MAC address to one of the + * TLAN AREGs (address registers). The TLAN chip locks + * the register on writing to offset 0 and unlocks the + * register after writing to offset 5. If NULL is passed + * in mac, then the AREG is filled with 0's. + * + **************************************************************/ -static void TLan_SetMac( struct net_device *dev, int areg, char *mac ) +static void tlan_set_mac(struct net_device *dev, int areg, char *mac) { int i; areg *= 6; - if ( mac != NULL ) { - for ( i = 0; i < 6; i++ ) - TLan_DioWrite8( dev->base_addr, - TLAN_AREG_0 + areg + i, mac[i] ); + if (mac != NULL) { + for (i = 0; i < 6; i++) + tlan_dio_write8(dev->base_addr, + TLAN_AREG_0 + areg + i, mac[i]); } else { - for ( i = 0; i < 6; i++ ) - TLan_DioWrite8( dev->base_addr, - TLAN_AREG_0 + areg + i, 0 ); + for (i = 0; i < 6; i++) + tlan_dio_write8(dev->base_addr, + TLAN_AREG_0 + areg + i, 0); } -} /* TLan_SetMac */ +} @@ -2432,205 +2524,202 @@ static void TLan_SetMac( struct net_device *dev, int areg, char *mac ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver PHY Layer Routines +ThunderLAN driver PHY layer routines ****************************************************************************** *****************************************************************************/ - /********************************************************************* - * TLan_PhyPrint - * - * Returns: - * Nothing - * Parms: - * dev A pointer to the device structure of the - * TLAN device having the PHYs to be detailed. - * - * This function prints the registers a PHY (aka transceiver). - * - ********************************************************************/ +/********************************************************************* + * tlan_phy_print + * + * Returns: + * Nothing + * Parms: + * dev A pointer to the device structure of the + * TLAN device having the PHYs to be detailed. + * + * This function prints the registers a PHY (aka transceiver). + * + ********************************************************************/ -static void TLan_PhyPrint( struct net_device *dev ) +static void tlan_phy_print(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 i, data0, data1, data2, data3, phy; - phy = priv->phy[priv->phyNum]; - - if ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) { - printk( "TLAN: Device %s, Unmanaged PHY.\n", dev->name ); - } else if ( phy <= TLAN_PHY_MAX_ADDR ) { - printk( "TLAN: Device %s, PHY 0x%02x.\n", dev->name, phy ); - printk( "TLAN: Off. +0 +1 +2 +3\n" ); - for ( i = 0; i < 0x20; i+= 4 ) { - printk( "TLAN: 0x%02x", i ); - TLan_MiiReadReg( dev, phy, i, &data0 ); - printk( " 0x%04hx", data0 ); - TLan_MiiReadReg( dev, phy, i + 1, &data1 ); - printk( " 0x%04hx", data1 ); - TLan_MiiReadReg( dev, phy, i + 2, &data2 ); - printk( " 0x%04hx", data2 ); - TLan_MiiReadReg( dev, phy, i + 3, &data3 ); - printk( " 0x%04hx\n", data3 ); + phy = priv->phy[priv->phy_num]; + + if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) { + pr_info("TLAN: Device %s, Unmanaged PHY.\n", dev->name); + } else if (phy <= TLAN_PHY_MAX_ADDR) { + pr_info("TLAN: Device %s, PHY 0x%02x.\n", dev->name, phy); + pr_info("TLAN: Off. +0 +1 +2 +3\n"); + for (i = 0; i < 0x20; i += 4) { + pr_info("TLAN: 0x%02x", i); + tlan_mii_read_reg(dev, phy, i, &data0); + printk(" 0x%04hx", data0); + tlan_mii_read_reg(dev, phy, i + 1, &data1); + printk(" 0x%04hx", data1); + tlan_mii_read_reg(dev, phy, i + 2, &data2); + printk(" 0x%04hx", data2); + tlan_mii_read_reg(dev, phy, i + 3, &data3); + printk(" 0x%04hx\n", data3); } } else { - printk( "TLAN: Device %s, Invalid PHY.\n", dev->name ); + pr_info("TLAN: Device %s, Invalid PHY.\n", dev->name); } -} /* TLan_PhyPrint */ +} - /********************************************************************* - * TLan_PhyDetect - * - * Returns: - * Nothing - * Parms: - * dev A pointer to the device structure of the adapter - * for which the PHY needs determined. - * - * So far I've found that adapters which have external PHYs - * may also use the internal PHY for part of the functionality. - * (eg, AUI/Thinnet). This function finds out if this TLAN - * chip has an internal PHY, and then finds the first external - * PHY (starting from address 0) if it exists). - * - ********************************************************************/ +/********************************************************************* + * tlan_phy_detect + * + * Returns: + * Nothing + * Parms: + * dev A pointer to the device structure of the adapter + * for which the PHY needs determined. + * + * So far I've found that adapters which have external PHYs + * may also use the internal PHY for part of the functionality. + * (eg, AUI/Thinnet). This function finds out if this TLAN + * chip has an internal PHY, and then finds the first external + * PHY (starting from address 0) if it exists). + * + ********************************************************************/ -static void TLan_PhyDetect( struct net_device *dev ) +static void tlan_phy_detect(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 control; u16 hi; u16 lo; u32 phy; - if ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) { - priv->phyNum = 0xFFFF; + if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) { + priv->phy_num = 0xffff; return; } - TLan_MiiReadReg( dev, TLAN_PHY_MAX_ADDR, MII_GEN_ID_HI, &hi ); + tlan_mii_read_reg(dev, TLAN_PHY_MAX_ADDR, MII_GEN_ID_HI, &hi); - if ( hi != 0xFFFF ) { + if (hi != 0xffff) priv->phy[0] = TLAN_PHY_MAX_ADDR; - } else { + else priv->phy[0] = TLAN_PHY_NONE; - } priv->phy[1] = TLAN_PHY_NONE; - for ( phy = 0; phy <= TLAN_PHY_MAX_ADDR; phy++ ) { - TLan_MiiReadReg( dev, phy, MII_GEN_CTL, &control ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_HI, &hi ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_LO, &lo ); - if ( ( control != 0xFFFF ) || - ( hi != 0xFFFF ) || ( lo != 0xFFFF ) ) { - TLAN_DBG( TLAN_DEBUG_GNRL, - "PHY found at %02x %04x %04x %04x\n", - phy, control, hi, lo ); - if ( ( priv->phy[1] == TLAN_PHY_NONE ) && - ( phy != TLAN_PHY_MAX_ADDR ) ) { + for (phy = 0; phy <= TLAN_PHY_MAX_ADDR; phy++) { + tlan_mii_read_reg(dev, phy, MII_GEN_CTL, &control); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_HI, &hi); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_LO, &lo); + if ((control != 0xffff) || + (hi != 0xffff) || (lo != 0xffff)) { + TLAN_DBG(TLAN_DEBUG_GNRL, + "PHY found at %02x %04x %04x %04x\n", + phy, control, hi, lo); + if ((priv->phy[1] == TLAN_PHY_NONE) && + (phy != TLAN_PHY_MAX_ADDR)) { priv->phy[1] = phy; } } } - if ( priv->phy[1] != TLAN_PHY_NONE ) { - priv->phyNum = 1; - } else if ( priv->phy[0] != TLAN_PHY_NONE ) { - priv->phyNum = 0; - } else { - printk( "TLAN: Cannot initialize device, no PHY was found!\n" ); - } + if (priv->phy[1] != TLAN_PHY_NONE) + priv->phy_num = 1; + else if (priv->phy[0] != TLAN_PHY_NONE) + priv->phy_num = 0; + else + pr_info("TLAN: Cannot initialize device, no PHY was found!\n"); -} /* TLan_PhyDetect */ +} -static void TLan_PhyPowerDown( struct net_device *dev ) +static void tlan_phy_power_down(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 value; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Powering down PHY(s).\n", dev->name ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Powering down PHY(s).\n", dev->name); value = MII_GC_PDOWN | MII_GC_LOOPBK | MII_GC_ISOLATE; - TLan_MiiSync( dev->base_addr ); - TLan_MiiWriteReg( dev, priv->phy[priv->phyNum], MII_GEN_CTL, value ); - if ( ( priv->phyNum == 0 ) && - ( priv->phy[1] != TLAN_PHY_NONE ) && - ( ! ( priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10 ) ) ) { - TLan_MiiSync( dev->base_addr ); - TLan_MiiWriteReg( dev, priv->phy[1], MII_GEN_CTL, value ); + tlan_mii_sync(dev->base_addr); + tlan_mii_write_reg(dev, priv->phy[priv->phy_num], MII_GEN_CTL, value); + if ((priv->phy_num == 0) && + (priv->phy[1] != TLAN_PHY_NONE) && + (!(priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10))) { + tlan_mii_sync(dev->base_addr); + tlan_mii_write_reg(dev, priv->phy[1], MII_GEN_CTL, value); } /* Wait for 50 ms and powerup * This is abitrary. It is intended to make sure the * transceiver settles. */ - TLan_SetTimer( dev, (HZ/20), TLAN_TIMER_PHY_PUP ); + tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_PUP); -} /* TLan_PhyPowerDown */ +} -static void TLan_PhyPowerUp( struct net_device *dev ) +static void tlan_phy_power_up(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 value; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Powering up PHY.\n", dev->name ); - TLan_MiiSync( dev->base_addr ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Powering up PHY.\n", dev->name); + tlan_mii_sync(dev->base_addr); value = MII_GC_LOOPBK; - TLan_MiiWriteReg( dev, priv->phy[priv->phyNum], MII_GEN_CTL, value ); - TLan_MiiSync(dev->base_addr); + tlan_mii_write_reg(dev, priv->phy[priv->phy_num], MII_GEN_CTL, value); + tlan_mii_sync(dev->base_addr); /* Wait for 500 ms and reset the * transceiver. The TLAN docs say both 50 ms and * 500 ms, so do the longer, just in case. */ - TLan_SetTimer( dev, (HZ/20), TLAN_TIMER_PHY_RESET ); + tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_RESET); -} /* TLan_PhyPowerUp */ +} -static void TLan_PhyReset( struct net_device *dev ) +static void tlan_phy_reset(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 phy; u16 value; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Reseting PHY.\n", dev->name ); - TLan_MiiSync( dev->base_addr ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Reseting PHY.\n", dev->name); + tlan_mii_sync(dev->base_addr); value = MII_GC_LOOPBK | MII_GC_RESET; - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, value ); - TLan_MiiReadReg( dev, phy, MII_GEN_CTL, &value ); - while ( value & MII_GC_RESET ) { - TLan_MiiReadReg( dev, phy, MII_GEN_CTL, &value ); - } + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, value); + tlan_mii_read_reg(dev, phy, MII_GEN_CTL, &value); + while (value & MII_GC_RESET) + tlan_mii_read_reg(dev, phy, MII_GEN_CTL, &value); /* Wait for 500 ms and initialize. * I don't remember why I wait this long. * I've changed this to 50ms, as it seems long enough. */ - TLan_SetTimer( dev, (HZ/20), TLAN_TIMER_PHY_START_LINK ); + tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_START_LINK); -} /* TLan_PhyReset */ +} -static void TLan_PhyStartLink( struct net_device *dev ) +static void tlan_phy_start_link(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 ability; u16 control; u16 data; @@ -2638,86 +2727,88 @@ static void TLan_PhyStartLink( struct net_device *dev ) u16 status; u16 tctl; - phy = priv->phy[priv->phyNum]; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Trying to activate link.\n", dev->name ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &ability ); + phy = priv->phy[priv->phy_num]; + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Trying to activate link.\n", dev->name); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &ability); - if ( ( status & MII_GS_AUTONEG ) && - ( ! priv->aui ) ) { + if ((status & MII_GS_AUTONEG) && + (!priv->aui)) { ability = status >> 11; - if ( priv->speed == TLAN_SPEED_10 && - priv->duplex == TLAN_DUPLEX_HALF) { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x0000); - } else if ( priv->speed == TLAN_SPEED_10 && - priv->duplex == TLAN_DUPLEX_FULL) { - priv->tlanFullDuplex = true; - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x0100); - } else if ( priv->speed == TLAN_SPEED_100 && - priv->duplex == TLAN_DUPLEX_HALF) { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x2000); - } else if ( priv->speed == TLAN_SPEED_100 && - priv->duplex == TLAN_DUPLEX_FULL) { - priv->tlanFullDuplex = true; - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x2100); + if (priv->speed == TLAN_SPEED_10 && + priv->duplex == TLAN_DUPLEX_HALF) { + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x0000); + } else if (priv->speed == TLAN_SPEED_10 && + priv->duplex == TLAN_DUPLEX_FULL) { + priv->tlan_full_duplex = true; + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x0100); + } else if (priv->speed == TLAN_SPEED_100 && + priv->duplex == TLAN_DUPLEX_HALF) { + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x2000); + } else if (priv->speed == TLAN_SPEED_100 && + priv->duplex == TLAN_DUPLEX_FULL) { + priv->tlan_full_duplex = true; + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x2100); } else { /* Set Auto-Neg advertisement */ - TLan_MiiWriteReg( dev, phy, MII_AN_ADV, (ability << 5) | 1); + tlan_mii_write_reg(dev, phy, MII_AN_ADV, + (ability << 5) | 1); /* Enablee Auto-Neg */ - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x1000 ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x1000); /* Restart Auto-Neg */ - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x1200 ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x1200); /* Wait for 4 sec for autonegotiation - * to complete. The max spec time is less than this - * but the card need additional time to start AN. - * .5 sec should be plenty extra. - */ - printk( "TLAN: %s: Starting autonegotiation.\n", dev->name ); - TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_PHY_FINISH_AN ); + * to complete. The max spec time is less than this + * but the card need additional time to start AN. + * .5 sec should be plenty extra. + */ + pr_info("TLAN: %s: Starting autonegotiation.\n", + dev->name); + tlan_set_timer(dev, (2*HZ), TLAN_TIMER_PHY_FINISH_AN); return; } } - if ( ( priv->aui ) && ( priv->phyNum != 0 ) ) { - priv->phyNum = 0; - data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, data ); - TLan_SetTimer( dev, (40*HZ/1000), TLAN_TIMER_PHY_PDOWN ); + if ((priv->aui) && (priv->phy_num != 0)) { + priv->phy_num = 0; + data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN + | TLAN_NET_CFG_PHY_EN; + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, data); + tlan_set_timer(dev, (40*HZ/1000), TLAN_TIMER_PHY_PDOWN); return; - } else if ( priv->phyNum == 0 ) { + } else if (priv->phy_num == 0) { control = 0; - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_CTL, &tctl ); - if ( priv->aui ) { - tctl |= TLAN_TC_AUISEL; + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tctl); + if (priv->aui) { + tctl |= TLAN_TC_AUISEL; } else { - tctl &= ~TLAN_TC_AUISEL; - if ( priv->duplex == TLAN_DUPLEX_FULL ) { + tctl &= ~TLAN_TC_AUISEL; + if (priv->duplex == TLAN_DUPLEX_FULL) { control |= MII_GC_DUPLEX; - priv->tlanFullDuplex = true; + priv->tlan_full_duplex = true; } - if ( priv->speed == TLAN_SPEED_100 ) { + if (priv->speed == TLAN_SPEED_100) control |= MII_GC_SPEEDSEL; - } } - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, control ); - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tctl ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, control); + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, tctl); } /* Wait for 2 sec to give the transceiver time * to establish link. */ - TLan_SetTimer( dev, (4*HZ), TLAN_TIMER_FINISH_RESET ); + tlan_set_timer(dev, (4*HZ), TLAN_TIMER_FINISH_RESET); -} /* TLan_PhyStartLink */ +} -static void TLan_PhyFinishAutoNeg( struct net_device *dev ) +static void tlan_phy_finish_auto_neg(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 an_adv; u16 an_lpa; u16 data; @@ -2725,115 +2816,118 @@ static void TLan_PhyFinishAutoNeg( struct net_device *dev ) u16 phy; u16 status; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - udelay( 1000 ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + udelay(1000); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); - if ( ! ( status & MII_GS_AUTOCMPLT ) ) { + if (!(status & MII_GS_AUTOCMPLT)) { /* Wait for 8 sec to give the process * more time. Perhaps we should fail after a while. */ - if (!priv->neg_be_verbose++) { - pr_info("TLAN: Giving autonegotiation more time.\n"); - pr_info("TLAN: Please check that your adapter has\n"); - pr_info("TLAN: been properly connected to a HUB or Switch.\n"); - pr_info("TLAN: Trying to establish link in the background...\n"); - } - TLan_SetTimer( dev, (8*HZ), TLAN_TIMER_PHY_FINISH_AN ); + if (!priv->neg_be_verbose++) { + pr_info("TLAN: Giving autonegotiation more time.\n"); + pr_info("TLAN: Please check that your adapter has\n"); + pr_info("TLAN: been properly connected to a HUB or Switch.\n"); + pr_info("TLAN: Trying to establish link in the background...\n"); + } + tlan_set_timer(dev, (8*HZ), TLAN_TIMER_PHY_FINISH_AN); return; } - printk( "TLAN: %s: Autonegotiation complete.\n", dev->name ); - TLan_MiiReadReg( dev, phy, MII_AN_ADV, &an_adv ); - TLan_MiiReadReg( dev, phy, MII_AN_LPA, &an_lpa ); + pr_info("TLAN: %s: Autonegotiation complete.\n", dev->name); + tlan_mii_read_reg(dev, phy, MII_AN_ADV, &an_adv); + tlan_mii_read_reg(dev, phy, MII_AN_LPA, &an_lpa); mode = an_adv & an_lpa & 0x03E0; - if ( mode & 0x0100 ) { - priv->tlanFullDuplex = true; - } else if ( ! ( mode & 0x0080 ) && ( mode & 0x0040 ) ) { - priv->tlanFullDuplex = true; - } - - if ( ( ! ( mode & 0x0180 ) ) && - ( priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10 ) && - ( priv->phyNum != 0 ) ) { - priv->phyNum = 0; - data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, data ); - TLan_SetTimer( dev, (400*HZ/1000), TLAN_TIMER_PHY_PDOWN ); + if (mode & 0x0100) + priv->tlan_full_duplex = true; + else if (!(mode & 0x0080) && (mode & 0x0040)) + priv->tlan_full_duplex = true; + + if ((!(mode & 0x0180)) && + (priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10) && + (priv->phy_num != 0)) { + priv->phy_num = 0; + data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN + | TLAN_NET_CFG_PHY_EN; + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, data); + tlan_set_timer(dev, (400*HZ/1000), TLAN_TIMER_PHY_PDOWN); return; } - if ( priv->phyNum == 0 ) { - if ( ( priv->duplex == TLAN_DUPLEX_FULL ) || - ( an_adv & an_lpa & 0x0040 ) ) { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, - MII_GC_AUTOENB | MII_GC_DUPLEX ); - pr_info("TLAN: Starting internal PHY with FULL-DUPLEX\n" ); + if (priv->phy_num == 0) { + if ((priv->duplex == TLAN_DUPLEX_FULL) || + (an_adv & an_lpa & 0x0040)) { + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, + MII_GC_AUTOENB | MII_GC_DUPLEX); + pr_info("TLAN: Starting internal PHY with FULL-DUPLEX\n"); } else { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, MII_GC_AUTOENB ); - pr_info( "TLAN: Starting internal PHY with HALF-DUPLEX\n" ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, + MII_GC_AUTOENB); + pr_info("TLAN: Starting internal PHY with HALF-DUPLEX\n"); } } /* Wait for 100 ms. No reason in partiticular. */ - TLan_SetTimer( dev, (HZ/10), TLAN_TIMER_FINISH_RESET ); + tlan_set_timer(dev, (HZ/10), TLAN_TIMER_FINISH_RESET); -} /* TLan_PhyFinishAutoNeg */ +} #ifdef MONITOR - /********************************************************************* - * - * TLan_phyMonitor - * - * Returns: - * None - * - * Params: - * dev The device structure of this device. - * - * - * This function monitors PHY condition by reading the status - * register via the MII bus. This can be used to give info - * about link changes (up/down), and possible switch to alternate - * media. - * - * ******************************************************************/ - -void TLan_PhyMonitor( struct net_device *dev ) +/********************************************************************* + * + * tlan_phy_monitor + * + * Returns: + * None + * + * Params: + * dev The device structure of this device. + * + * + * This function monitors PHY condition by reading the status + * register via the MII bus. This can be used to give info + * about link changes (up/down), and possible switch to alternate + * media. + * + *******************************************************************/ + +void tlan_phy_monitor(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 phy; u16 phy_status; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; - /* Get PHY status register */ - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &phy_status ); + /* Get PHY status register */ + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &phy_status); - /* Check if link has been lost */ - if (!(phy_status & MII_GS_LINK)) { - if (priv->link) { - priv->link = 0; - printk(KERN_DEBUG "TLAN: %s has lost link\n", dev->name); - netif_carrier_off(dev); - TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_LINK_BEAT ); - return; + /* Check if link has been lost */ + if (!(phy_status & MII_GS_LINK)) { + if (priv->link) { + priv->link = 0; + printk(KERN_DEBUG "TLAN: %s has lost link\n", + dev->name); + netif_carrier_off(dev); + tlan_set_timer(dev, (2*HZ), TLAN_TIMER_LINK_BEAT); + return; } } - /* Link restablished? */ - if ((phy_status & MII_GS_LINK) && !priv->link) { - priv->link = 1; - printk(KERN_DEBUG "TLAN: %s has reestablished link\n", dev->name); + /* Link restablished? */ + if ((phy_status & MII_GS_LINK) && !priv->link) { + priv->link = 1; + printk(KERN_DEBUG "TLAN: %s has reestablished link\n", + dev->name); netif_carrier_on(dev); - } + } /* Setup a new monitor */ - TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_LINK_BEAT ); + tlan_set_timer(dev, (2*HZ), TLAN_TIMER_LINK_BEAT); } #endif /* MONITOR */ @@ -2842,47 +2936,48 @@ void TLan_PhyMonitor( struct net_device *dev ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver MII Routines +ThunderLAN driver MII routines - These routines are based on the information in Chap. 2 of the - "ThunderLAN Programmer's Guide", pp. 15-24. +these routines are based on the information in chap. 2 of the +"ThunderLAN Programmer's Guide", pp. 15-24. ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_MiiReadReg - * - * Returns: - * false if ack received ok - * true if no ack received or other error - * - * Parms: - * dev The device structure containing - * The io address and interrupt count - * for this device. - * phy The address of the PHY to be queried. - * reg The register whose contents are to be - * retrieved. - * val A pointer to a variable to store the - * retrieved value. - * - * This function uses the TLAN's MII bus to retrieve the contents - * of a given register on a PHY. It sends the appropriate info - * and then reads the 16-bit register value from the MII bus via - * the TLAN SIO register. - * - **************************************************************/ - -static bool TLan_MiiReadReg( struct net_device *dev, u16 phy, u16 reg, u16 *val ) +/*************************************************************** + * tlan_mii_read_reg + * + * Returns: + * false if ack received ok + * true if no ack received or other error + * + * Parms: + * dev The device structure containing + * The io address and interrupt count + * for this device. + * phy The address of the PHY to be queried. + * reg The register whose contents are to be + * retrieved. + * val A pointer to a variable to store the + * retrieved value. + * + * This function uses the TLAN's MII bus to retrieve the contents + * of a given register on a PHY. It sends the appropriate info + * and then reads the 16-bit register value from the MII bus via + * the TLAN SIO register. + * + **************************************************************/ + +static bool +tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val) { u8 nack; u16 sio, tmp; - u32 i; + u32 i; bool err; int minten; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; err = false; @@ -2892,48 +2987,48 @@ static bool TLan_MiiReadReg( struct net_device *dev, u16 phy, u16 reg, u16 *val if (!in_irq()) spin_lock_irqsave(&priv->lock, flags); - TLan_MiiSync(dev->base_addr); + tlan_mii_sync(dev->base_addr); - minten = TLan_GetBit( TLAN_NET_SIO_MINTEN, sio ); - if ( minten ) - TLan_ClearBit(TLAN_NET_SIO_MINTEN, sio); + minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio); + if (minten) + tlan_clear_bit(TLAN_NET_SIO_MINTEN, sio); - TLan_MiiSendData( dev->base_addr, 0x1, 2 ); /* Start ( 01b ) */ - TLan_MiiSendData( dev->base_addr, 0x2, 2 ); /* Read ( 10b ) */ - TLan_MiiSendData( dev->base_addr, phy, 5 ); /* Device # */ - TLan_MiiSendData( dev->base_addr, reg, 5 ); /* Register # */ + tlan_mii_send_data(dev->base_addr, 0x1, 2); /* start (01b) */ + tlan_mii_send_data(dev->base_addr, 0x2, 2); /* read (10b) */ + tlan_mii_send_data(dev->base_addr, phy, 5); /* device # */ + tlan_mii_send_data(dev->base_addr, reg, 5); /* register # */ - TLan_ClearBit(TLAN_NET_SIO_MTXEN, sio); /* Change direction */ + tlan_clear_bit(TLAN_NET_SIO_MTXEN, sio); /* change direction */ - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); /* Clock Idle bit */ - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); /* Wait 300ns */ + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* clock idle bit */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* wait 300ns */ - nack = TLan_GetBit(TLAN_NET_SIO_MDATA, sio); /* Check for ACK */ - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); /* Finish ACK */ - if (nack) { /* No ACK, so fake it */ + nack = tlan_get_bit(TLAN_NET_SIO_MDATA, sio); /* check for ACK */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); /* finish ACK */ + if (nack) { /* no ACK, so fake it */ for (i = 0; i < 16; i++) { - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); } tmp = 0xffff; err = true; } else { /* ACK, so read data */ for (tmp = 0, i = 0x8000; i; i >>= 1) { - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); - if (TLan_GetBit(TLAN_NET_SIO_MDATA, sio)) + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + if (tlan_get_bit(TLAN_NET_SIO_MDATA, sio)) tmp |= i; - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); } } - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); /* Idle cycle */ - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* idle cycle */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); - if ( minten ) - TLan_SetBit(TLAN_NET_SIO_MINTEN, sio); + if (minten) + tlan_set_bit(TLAN_NET_SIO_MINTEN, sio); *val = tmp; @@ -2942,116 +3037,117 @@ static bool TLan_MiiReadReg( struct net_device *dev, u16 phy, u16 reg, u16 *val return err; -} /* TLan_MiiReadReg */ +} - /*************************************************************** - * TLan_MiiSendData - * - * Returns: - * Nothing - * Parms: - * base_port The base IO port of the adapter in - * question. - * dev The address of the PHY to be queried. - * data The value to be placed on the MII bus. - * num_bits The number of bits in data that are to - * be placed on the MII bus. - * - * This function sends on sequence of bits on the MII - * configuration bus. - * - **************************************************************/ +/*************************************************************** + * tlan_mii_send_data + * + * Returns: + * Nothing + * Parms: + * base_port The base IO port of the adapter in + * question. + * dev The address of the PHY to be queried. + * data The value to be placed on the MII bus. + * num_bits The number of bits in data that are to + * be placed on the MII bus. + * + * This function sends on sequence of bits on the MII + * configuration bus. + * + **************************************************************/ -static void TLan_MiiSendData( u16 base_port, u32 data, unsigned num_bits ) +static void tlan_mii_send_data(u16 base_port, u32 data, unsigned num_bits) { u16 sio; u32 i; - if ( num_bits == 0 ) + if (num_bits == 0) return; - outw( TLAN_NET_SIO, base_port + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, base_port + TLAN_DIO_ADR); sio = base_port + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_SetBit( TLAN_NET_SIO_MTXEN, sio ); + tlan_set_bit(TLAN_NET_SIO_MTXEN, sio); - for ( i = ( 0x1 << ( num_bits - 1 ) ); i; i >>= 1 ) { - TLan_ClearBit( TLAN_NET_SIO_MCLK, sio ); - (void) TLan_GetBit( TLAN_NET_SIO_MCLK, sio ); - if ( data & i ) - TLan_SetBit( TLAN_NET_SIO_MDATA, sio ); + for (i = (0x1 << (num_bits - 1)); i; i >>= 1) { + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + (void) tlan_get_bit(TLAN_NET_SIO_MCLK, sio); + if (data & i) + tlan_set_bit(TLAN_NET_SIO_MDATA, sio); else - TLan_ClearBit( TLAN_NET_SIO_MDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_MCLK, sio ); - (void) TLan_GetBit( TLAN_NET_SIO_MCLK, sio ); + tlan_clear_bit(TLAN_NET_SIO_MDATA, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); + (void) tlan_get_bit(TLAN_NET_SIO_MCLK, sio); } -} /* TLan_MiiSendData */ +} - /*************************************************************** - * TLan_MiiSync - * - * Returns: - * Nothing - * Parms: - * base_port The base IO port of the adapter in - * question. - * - * This functions syncs all PHYs in terms of the MII configuration - * bus. - * - **************************************************************/ +/*************************************************************** + * TLan_MiiSync + * + * Returns: + * Nothing + * Parms: + * base_port The base IO port of the adapter in + * question. + * + * This functions syncs all PHYs in terms of the MII configuration + * bus. + * + **************************************************************/ -static void TLan_MiiSync( u16 base_port ) +static void tlan_mii_sync(u16 base_port) { int i; u16 sio; - outw( TLAN_NET_SIO, base_port + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, base_port + TLAN_DIO_ADR); sio = base_port + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_ClearBit( TLAN_NET_SIO_MTXEN, sio ); - for ( i = 0; i < 32; i++ ) { - TLan_ClearBit( TLAN_NET_SIO_MCLK, sio ); - TLan_SetBit( TLAN_NET_SIO_MCLK, sio ); + tlan_clear_bit(TLAN_NET_SIO_MTXEN, sio); + for (i = 0; i < 32; i++) { + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); } -} /* TLan_MiiSync */ +} - /*************************************************************** - * TLan_MiiWriteReg - * - * Returns: - * Nothing - * Parms: - * dev The device structure for the device - * to write to. - * phy The address of the PHY to be written to. - * reg The register whose contents are to be - * written. - * val The value to be written to the register. - * - * This function uses the TLAN's MII bus to write the contents of a - * given register on a PHY. It sends the appropriate info and then - * writes the 16-bit register value from the MII configuration bus - * via the TLAN SIO register. - * - **************************************************************/ +/*************************************************************** + * tlan_mii_write_reg + * + * Returns: + * Nothing + * Parms: + * dev The device structure for the device + * to write to. + * phy The address of the PHY to be written to. + * reg The register whose contents are to be + * written. + * val The value to be written to the register. + * + * This function uses the TLAN's MII bus to write the contents of a + * given register on a PHY. It sends the appropriate info and then + * writes the 16-bit register value from the MII configuration bus + * via the TLAN SIO register. + * + **************************************************************/ -static void TLan_MiiWriteReg( struct net_device *dev, u16 phy, u16 reg, u16 val ) +static void +tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val) { u16 sio; int minten; unsigned long flags = 0; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR); sio = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO; @@ -3059,30 +3155,30 @@ static void TLan_MiiWriteReg( struct net_device *dev, u16 phy, u16 reg, u16 val if (!in_irq()) spin_lock_irqsave(&priv->lock, flags); - TLan_MiiSync( dev->base_addr ); + tlan_mii_sync(dev->base_addr); - minten = TLan_GetBit( TLAN_NET_SIO_MINTEN, sio ); - if ( minten ) - TLan_ClearBit( TLAN_NET_SIO_MINTEN, sio ); + minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio); + if (minten) + tlan_clear_bit(TLAN_NET_SIO_MINTEN, sio); - TLan_MiiSendData( dev->base_addr, 0x1, 2 ); /* Start ( 01b ) */ - TLan_MiiSendData( dev->base_addr, 0x1, 2 ); /* Write ( 01b ) */ - TLan_MiiSendData( dev->base_addr, phy, 5 ); /* Device # */ - TLan_MiiSendData( dev->base_addr, reg, 5 ); /* Register # */ + tlan_mii_send_data(dev->base_addr, 0x1, 2); /* start (01b) */ + tlan_mii_send_data(dev->base_addr, 0x1, 2); /* write (01b) */ + tlan_mii_send_data(dev->base_addr, phy, 5); /* device # */ + tlan_mii_send_data(dev->base_addr, reg, 5); /* register # */ - TLan_MiiSendData( dev->base_addr, 0x2, 2 ); /* Send ACK */ - TLan_MiiSendData( dev->base_addr, val, 16 ); /* Send Data */ + tlan_mii_send_data(dev->base_addr, 0x2, 2); /* send ACK */ + tlan_mii_send_data(dev->base_addr, val, 16); /* send data */ - TLan_ClearBit( TLAN_NET_SIO_MCLK, sio ); /* Idle cycle */ - TLan_SetBit( TLAN_NET_SIO_MCLK, sio ); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* idle cycle */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); - if ( minten ) - TLan_SetBit( TLAN_NET_SIO_MINTEN, sio ); + if (minten) + tlan_set_bit(TLAN_NET_SIO_MINTEN, sio); if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); -} /* TLan_MiiWriteReg */ +} @@ -3090,229 +3186,226 @@ static void TLan_MiiWriteReg( struct net_device *dev, u16 phy, u16 reg, u16 val /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Eeprom routines +ThunderLAN driver eeprom routines - The Compaq Netelligent 10 and 10/100 cards use a Microchip 24C02A - EEPROM. These functions are based on information in Microchip's - data sheet. I don't know how well this functions will work with - other EEPROMs. +the Compaq netelligent 10 and 10/100 cards use a microchip 24C02A +EEPROM. these functions are based on information in microchip's +data sheet. I don't know how well this functions will work with +other Eeproms. ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_EeSendStart - * - * Returns: - * Nothing - * Parms: - * io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * - * This function sends a start cycle to an EEPROM attached - * to a TLAN chip. - * - **************************************************************/ - -static void TLan_EeSendStart( u16 io_base ) +/*************************************************************** + * tlan_ee_send_start + * + * Returns: + * Nothing + * Parms: + * io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * + * This function sends a start cycle to an EEPROM attached + * to a TLAN chip. + * + **************************************************************/ + +static void tlan_ee_send_start(u16 io_base) { u16 sio; - outw( TLAN_NET_SIO, io_base + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, io_base + TLAN_DIO_ADR); sio = io_base + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ETXEN, sio ); - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); - -} /* TLan_EeSendStart */ - - - - - /*************************************************************** - * TLan_EeSendByte - * - * Returns: - * If the correct ack was received, 0, otherwise 1 - * Parms: io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * data The 8 bits of information to - * send to the EEPROM. - * stop If TLAN_EEPROM_STOP is passed, a - * stop cycle is sent after the - * byte is sent after the ack is - * read. - * - * This function sends a byte on the serial EEPROM line, - * driving the clock to send each bit. The function then - * reverses transmission direction and reads an acknowledge - * bit. - * - **************************************************************/ - -static int TLan_EeSendByte( u16 io_base, u8 data, int stop ) + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ETXEN, sio); + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); + +} + + + + +/*************************************************************** + * tlan_ee_send_byte + * + * Returns: + * If the correct ack was received, 0, otherwise 1 + * Parms: io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * data The 8 bits of information to + * send to the EEPROM. + * stop If TLAN_EEPROM_STOP is passed, a + * stop cycle is sent after the + * byte is sent after the ack is + * read. + * + * This function sends a byte on the serial EEPROM line, + * driving the clock to send each bit. The function then + * reverses transmission direction and reads an acknowledge + * bit. + * + **************************************************************/ + +static int tlan_ee_send_byte(u16 io_base, u8 data, int stop) { int err; u8 place; u16 sio; - outw( TLAN_NET_SIO, io_base + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, io_base + TLAN_DIO_ADR); sio = io_base + TLAN_DIO_DATA + TLAN_NET_SIO; /* Assume clock is low, tx is enabled; */ - for ( place = 0x80; place != 0; place >>= 1 ) { - if ( place & data ) - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); + for (place = 0x80; place != 0; place >>= 1) { + if (place & data) + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); else - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); } - TLan_ClearBit( TLAN_NET_SIO_ETXEN, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - err = TLan_GetBit( TLAN_NET_SIO_EDATA, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_ETXEN, sio ); + tlan_clear_bit(TLAN_NET_SIO_ETXEN, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + err = tlan_get_bit(TLAN_NET_SIO_EDATA, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_ETXEN, sio); - if ( ( ! err ) && stop ) { + if ((!err) && stop) { /* STOP, raise data while clock is high */ - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); } return err; -} /* TLan_EeSendByte */ - - - - - /*************************************************************** - * TLan_EeReceiveByte - * - * Returns: - * Nothing - * Parms: - * io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * data An address to a char to hold the - * data sent from the EEPROM. - * stop If TLAN_EEPROM_STOP is passed, a - * stop cycle is sent after the - * byte is received, and no ack is - * sent. - * - * This function receives 8 bits of data from the EEPROM - * over the serial link. It then sends and ack bit, or no - * ack and a stop bit. This function is used to retrieve - * data after the address of a byte in the EEPROM has been - * sent. - * - **************************************************************/ - -static void TLan_EeReceiveByte( u16 io_base, u8 *data, int stop ) +} + + + + +/*************************************************************** + * tlan_ee_receive_byte + * + * Returns: + * Nothing + * Parms: + * io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * data An address to a char to hold the + * data sent from the EEPROM. + * stop If TLAN_EEPROM_STOP is passed, a + * stop cycle is sent after the + * byte is received, and no ack is + * sent. + * + * This function receives 8 bits of data from the EEPROM + * over the serial link. It then sends and ack bit, or no + * ack and a stop bit. This function is used to retrieve + * data after the address of a byte in the EEPROM has been + * sent. + * + **************************************************************/ + +static void tlan_ee_receive_byte(u16 io_base, u8 *data, int stop) { u8 place; u16 sio; - outw( TLAN_NET_SIO, io_base + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, io_base + TLAN_DIO_ADR); sio = io_base + TLAN_DIO_DATA + TLAN_NET_SIO; *data = 0; /* Assume clock is low, tx is enabled; */ - TLan_ClearBit( TLAN_NET_SIO_ETXEN, sio ); - for ( place = 0x80; place; place >>= 1 ) { - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - if ( TLan_GetBit( TLAN_NET_SIO_EDATA, sio ) ) + tlan_clear_bit(TLAN_NET_SIO_ETXEN, sio); + for (place = 0x80; place; place >>= 1) { + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + if (tlan_get_bit(TLAN_NET_SIO_EDATA, sio)) *data |= place; - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); } - TLan_SetBit( TLAN_NET_SIO_ETXEN, sio ); - if ( ! stop ) { - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); /* Ack = 0 */ - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_set_bit(TLAN_NET_SIO_ETXEN, sio); + if (!stop) { + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); /* ack = 0 */ + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); } else { - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); /* No ack = 1 (?) */ - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); /* no ack = 1 (?) */ + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); /* STOP, raise data while clock is high */ - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); - } - -} /* TLan_EeReceiveByte */ - - - - - /*************************************************************** - * TLan_EeReadByte - * - * Returns: - * No error = 0, else, the stage at which the error - * occurred. - * Parms: - * io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * ee_addr The address of the byte in the - * EEPROM whose contents are to be - * retrieved. - * data An address to a char to hold the - * data obtained from the EEPROM. - * - * This function reads a byte of information from an byte - * cell in the EEPROM. - * - **************************************************************/ - -static int TLan_EeReadByte( struct net_device *dev, u8 ee_addr, u8 *data ) + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); + } + +} + + + + +/*************************************************************** + * tlan_ee_read_byte + * + * Returns: + * No error = 0, else, the stage at which the error + * occurred. + * Parms: + * io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * ee_addr The address of the byte in the + * EEPROM whose contents are to be + * retrieved. + * data An address to a char to hold the + * data obtained from the EEPROM. + * + * This function reads a byte of information from an byte + * cell in the EEPROM. + * + **************************************************************/ + +static int tlan_ee_read_byte(struct net_device *dev, u8 ee_addr, u8 *data) { int err; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; - int ret=0; + int ret = 0; spin_lock_irqsave(&priv->lock, flags); - TLan_EeSendStart( dev->base_addr ); - err = TLan_EeSendByte( dev->base_addr, 0xA0, TLAN_EEPROM_ACK ); - if (err) - { - ret=1; + tlan_ee_send_start(dev->base_addr); + err = tlan_ee_send_byte(dev->base_addr, 0xa0, TLAN_EEPROM_ACK); + if (err) { + ret = 1; goto fail; } - err = TLan_EeSendByte( dev->base_addr, ee_addr, TLAN_EEPROM_ACK ); - if (err) - { - ret=2; + err = tlan_ee_send_byte(dev->base_addr, ee_addr, TLAN_EEPROM_ACK); + if (err) { + ret = 2; goto fail; } - TLan_EeSendStart( dev->base_addr ); - err = TLan_EeSendByte( dev->base_addr, 0xA1, TLAN_EEPROM_ACK ); - if (err) - { - ret=3; + tlan_ee_send_start(dev->base_addr); + err = tlan_ee_send_byte(dev->base_addr, 0xa1, TLAN_EEPROM_ACK); + if (err) { + ret = 3; goto fail; } - TLan_EeReceiveByte( dev->base_addr, data, TLAN_EEPROM_STOP ); + tlan_ee_receive_byte(dev->base_addr, data, TLAN_EEPROM_STOP); fail: spin_unlock_irqrestore(&priv->lock, flags); return ret; -} /* TLan_EeReadByte */ +} diff --git a/drivers/net/tlan.h b/drivers/net/tlan.h index 3315ced..5fc98a8 100644 --- a/drivers/net/tlan.h +++ b/drivers/net/tlan.h @@ -20,8 +20,8 @@ ********************************************************************/ -#include <asm/io.h> -#include <asm/types.h> +#include <linux/io.h> +#include <linux/types.h> #include <linux/netdevice.h> @@ -40,8 +40,11 @@ #define TLAN_IGNORE 0 #define TLAN_RECORD 1 -#define TLAN_DBG(lvl, format, args...) \ - do { if (debug&lvl) printk(KERN_DEBUG "TLAN: " format, ##args ); } while(0) +#define TLAN_DBG(lvl, format, args...) \ + do { \ + if (debug&lvl) \ + printk(KERN_DEBUG "TLAN: " format, ##args); \ + } while (0) #define TLAN_DEBUG_GNRL 0x0001 #define TLAN_DEBUG_TX 0x0002 @@ -50,7 +53,8 @@ #define TLAN_DEBUG_PROBE 0x0010 #define TX_TIMEOUT (10*HZ) /* We need time for auto-neg */ -#define MAX_TLAN_BOARDS 8 /* Max number of boards installed at a time */ +#define MAX_TLAN_BOARDS 8 /* Max number of boards installed + at a time */ /***************************************************************** @@ -70,13 +74,13 @@ #define PCI_DEVICE_ID_OLICOM_OC2326 0x0014 #endif -typedef struct tlan_adapter_entry { - u16 vendorId; - u16 deviceId; - char *deviceLabel; +struct tlan_adapter_entry { + u16 vendor_id; + u16 device_id; + char *device_label; u32 flags; - u16 addrOfs; -} TLanAdapterEntry; + u16 addr_ofs; +}; #define TLAN_ADAPTER_NONE 0x00000000 #define TLAN_ADAPTER_UNMANAGED_PHY 0x00000001 @@ -129,18 +133,18 @@ typedef struct tlan_adapter_entry { #define TLAN_CSTAT_DP_PR 0x0100 -typedef struct tlan_buffer_ref_tag { +struct tlan_buffer { u32 count; u32 address; -} TLanBufferRef; +}; -typedef struct tlan_list_tag { +struct tlan_list { u32 forward; - u16 cStat; - u16 frameSize; - TLanBufferRef buffer[TLAN_BUFFERS_PER_LIST]; -} TLanList; + u16 c_stat; + u16 frame_size; + struct tlan_buffer buffer[TLAN_BUFFERS_PER_LIST]; +}; typedef u8 TLanBuffer[TLAN_MAX_FRAME_SIZE]; @@ -164,49 +168,49 @@ typedef u8 TLanBuffer[TLAN_MAX_FRAME_SIZE]; * ****************************************************************/ -typedef struct tlan_private_tag { - struct net_device *nextDevice; - struct pci_dev *pciDev; +struct tlan_priv { + struct net_device *next_device; + struct pci_dev *pci_dev; struct net_device *dev; - void *dmaStorage; - dma_addr_t dmaStorageDMA; - unsigned int dmaSize; - u8 *padBuffer; - TLanList *rxList; - dma_addr_t rxListDMA; - u8 *rxBuffer; - dma_addr_t rxBufferDMA; - u32 rxHead; - u32 rxTail; - u32 rxEocCount; - TLanList *txList; - dma_addr_t txListDMA; - u8 *txBuffer; - dma_addr_t txBufferDMA; - u32 txHead; - u32 txInProgress; - u32 txTail; - u32 txBusyCount; - u32 phyOnline; - u32 timerSetAt; - u32 timerType; + void *dma_storage; + dma_addr_t dma_storage_dma; + unsigned int dma_size; + u8 *pad_buffer; + struct tlan_list *rx_list; + dma_addr_t rx_list_dma; + u8 *rx_buffer; + dma_addr_t rx_buffer_dma; + u32 rx_head; + u32 rx_tail; + u32 rx_eoc_count; + struct tlan_list *tx_list; + dma_addr_t tx_list_dma; + u8 *tx_buffer; + dma_addr_t tx_buffer_dma; + u32 tx_head; + u32 tx_in_progress; + u32 tx_tail; + u32 tx_busy_count; + u32 phy_online; + u32 timer_set_at; + u32 timer_type; struct timer_list timer; struct board *adapter; - u32 adapterRev; + u32 adapter_rev; u32 aui; u32 debug; u32 duplex; u32 phy[2]; - u32 phyNum; + u32 phy_num; u32 speed; - u8 tlanRev; - u8 tlanFullDuplex; + u8 tlan_rev; + u8 tlan_full_duplex; spinlock_t lock; u8 link; u8 is_eisa; struct work_struct tlan_tqueue; u8 neg_be_verbose; -} TLanPrivateInfo; +}; @@ -247,7 +251,7 @@ typedef struct tlan_private_tag { ****************************************************************/ #define TLAN_HOST_CMD 0x00 -#define TLAN_HC_GO 0x80000000 +#define TLAN_HC_GO 0x80000000 #define TLAN_HC_STOP 0x40000000 #define TLAN_HC_ACK 0x20000000 #define TLAN_HC_CS_MASK 0x1FE00000 @@ -283,7 +287,7 @@ typedef struct tlan_private_tag { #define TLAN_NET_CMD_TRFRAM 0x02 #define TLAN_NET_CMD_TXPACE 0x01 #define TLAN_NET_SIO 0x01 -#define TLAN_NET_SIO_MINTEN 0x80 +#define TLAN_NET_SIO_MINTEN 0x80 #define TLAN_NET_SIO_ECLOK 0x40 #define TLAN_NET_SIO_ETXEN 0x20 #define TLAN_NET_SIO_EDATA 0x10 @@ -304,7 +308,7 @@ typedef struct tlan_private_tag { #define TLAN_NET_MASK_MASK4 0x10 #define TLAN_NET_MASK_RSRVD 0x0F #define TLAN_NET_CONFIG 0x04 -#define TLAN_NET_CFG_RCLK 0x8000 +#define TLAN_NET_CFG_RCLK 0x8000 #define TLAN_NET_CFG_TCLK 0x4000 #define TLAN_NET_CFG_BIT 0x2000 #define TLAN_NET_CFG_RXCRC 0x1000 @@ -372,7 +376,7 @@ typedef struct tlan_private_tag { /* Generic MII/PHY Registers */ #define MII_GEN_CTL 0x00 -#define MII_GC_RESET 0x8000 +#define MII_GC_RESET 0x8000 #define MII_GC_LOOPBK 0x4000 #define MII_GC_SPEEDSEL 0x2000 #define MII_GC_AUTOENB 0x1000 @@ -397,9 +401,9 @@ typedef struct tlan_private_tag { #define MII_GS_EXTCAP 0x0001 #define MII_GEN_ID_HI 0x02 #define MII_GEN_ID_LO 0x03 -#define MII_GIL_OUI 0xFC00 -#define MII_GIL_MODEL 0x03F0 -#define MII_GIL_REVISION 0x000F +#define MII_GIL_OUI 0xFC00 +#define MII_GIL_MODEL 0x03F0 +#define MII_GIL_REVISION 0x000F #define MII_AN_ADV 0x04 #define MII_AN_LPA 0x05 #define MII_AN_EXP 0x06 @@ -408,7 +412,7 @@ typedef struct tlan_private_tag { #define TLAN_TLPHY_ID 0x10 #define TLAN_TLPHY_CTL 0x11 -#define TLAN_TC_IGLINK 0x8000 +#define TLAN_TC_IGLINK 0x8000 #define TLAN_TC_SWAPOL 0x4000 #define TLAN_TC_AUISEL 0x2000 #define TLAN_TC_SQEEN 0x1000 @@ -435,41 +439,41 @@ typedef struct tlan_private_tag { #define LEVEL1_ID1 0x7810 #define LEVEL1_ID2 0x0000 -#define CIRC_INC( a, b ) if ( ++a >= b ) a = 0 +#define CIRC_INC(a, b) if (++a >= b) a = 0 /* Routines to access internal registers. */ -static inline u8 TLan_DioRead8(u16 base_addr, u16 internal_addr) +static inline u8 tlan_dio_read8(u16 base_addr, u16 internal_addr) { outw(internal_addr, base_addr + TLAN_DIO_ADR); return inb((base_addr + TLAN_DIO_DATA) + (internal_addr & 0x3)); -} /* TLan_DioRead8 */ +} -static inline u16 TLan_DioRead16(u16 base_addr, u16 internal_addr) +static inline u16 tlan_dio_read16(u16 base_addr, u16 internal_addr) { outw(internal_addr, base_addr + TLAN_DIO_ADR); return inw((base_addr + TLAN_DIO_DATA) + (internal_addr & 0x2)); -} /* TLan_DioRead16 */ +} -static inline u32 TLan_DioRead32(u16 base_addr, u16 internal_addr) +static inline u32 tlan_dio_read32(u16 base_addr, u16 internal_addr) { outw(internal_addr, base_addr + TLAN_DIO_ADR); return inl(base_addr + TLAN_DIO_DATA); -} /* TLan_DioRead32 */ +} -static inline void TLan_DioWrite8(u16 base_addr, u16 internal_addr, u8 data) +static inline void tlan_dio_write8(u16 base_addr, u16 internal_addr, u8 data) { outw(internal_addr, base_addr + TLAN_DIO_ADR); outb(data, base_addr + TLAN_DIO_DATA + (internal_addr & 0x3)); @@ -479,7 +483,7 @@ static inline void TLan_DioWrite8(u16 base_addr, u16 internal_addr, u8 data) -static inline void TLan_DioWrite16(u16 base_addr, u16 internal_addr, u16 data) +static inline void tlan_dio_write16(u16 base_addr, u16 internal_addr, u16 data) { outw(internal_addr, base_addr + TLAN_DIO_ADR); outw(data, base_addr + TLAN_DIO_DATA + (internal_addr & 0x2)); @@ -489,16 +493,16 @@ static inline void TLan_DioWrite16(u16 base_addr, u16 internal_addr, u16 data) -static inline void TLan_DioWrite32(u16 base_addr, u16 internal_addr, u32 data) +static inline void tlan_dio_write32(u16 base_addr, u16 internal_addr, u32 data) { outw(internal_addr, base_addr + TLAN_DIO_ADR); outl(data, base_addr + TLAN_DIO_DATA + (internal_addr & 0x2)); } -#define TLan_ClearBit( bit, port ) outb_p(inb_p(port) & ~bit, port) -#define TLan_GetBit( bit, port ) ((int) (inb_p(port) & bit)) -#define TLan_SetBit( bit, port ) outb_p(inb_p(port) | bit, port) +#define tlan_clear_bit(bit, port) outb_p(inb_p(port) & ~bit, port) +#define tlan_get_bit(bit, port) ((int) (inb_p(port) & bit)) +#define tlan_set_bit(bit, port) outb_p(inb_p(port) | bit, port) /* * given 6 bytes, view them as 8 6-bit numbers and return the XOR of those @@ -506,37 +510,37 @@ static inline void TLan_DioWrite32(u16 base_addr, u16 internal_addr, u32 data) * * The original code was: * - * u32 xor( u32 a, u32 b ) { return ( ( a && ! b ) || ( ! a && b ) ); } + * u32 xor(u32 a, u32 b) { return ((a && !b ) || (! a && b )); } * - * #define XOR8( a, b, c, d, e, f, g, h ) \ - * xor( a, xor( b, xor( c, xor( d, xor( e, xor( f, xor( g, h ) ) ) ) ) ) ) - * #define DA( a, bit ) ( ( (u8) a[bit/8] ) & ( (u8) ( 1 << bit%8 ) ) ) + * #define XOR8(a, b, c, d, e, f, g, h) \ + * xor(a, xor(b, xor(c, xor(d, xor(e, xor(f, xor(g, h)) ) ) ) ) ) + * #define DA(a, bit) (( (u8) a[bit/8] ) & ( (u8) (1 << bit%8)) ) * - * hash = XOR8( DA(a,0), DA(a, 6), DA(a,12), DA(a,18), DA(a,24), - * DA(a,30), DA(a,36), DA(a,42) ); - * hash |= XOR8( DA(a,1), DA(a, 7), DA(a,13), DA(a,19), DA(a,25), - * DA(a,31), DA(a,37), DA(a,43) ) << 1; - * hash |= XOR8( DA(a,2), DA(a, 8), DA(a,14), DA(a,20), DA(a,26), - * DA(a,32), DA(a,38), DA(a,44) ) << 2; - * hash |= XOR8( DA(a,3), DA(a, 9), DA(a,15), DA(a,21), DA(a,27), - * DA(a,33), DA(a,39), DA(a,45) ) << 3; - * hash |= XOR8( DA(a,4), DA(a,10), DA(a,16), DA(a,22), DA(a,28), - * DA(a,34), DA(a,40), DA(a,46) ) << 4; - * hash |= XOR8( DA(a,5), DA(a,11), DA(a,17), DA(a,23), DA(a,29), - * DA(a,35), DA(a,41), DA(a,47) ) << 5; + * hash = XOR8(DA(a,0), DA(a, 6), DA(a,12), DA(a,18), DA(a,24), + * DA(a,30), DA(a,36), DA(a,42)); + * hash |= XOR8(DA(a,1), DA(a, 7), DA(a,13), DA(a,19), DA(a,25), + * DA(a,31), DA(a,37), DA(a,43)) << 1; + * hash |= XOR8(DA(a,2), DA(a, 8), DA(a,14), DA(a,20), DA(a,26), + * DA(a,32), DA(a,38), DA(a,44)) << 2; + * hash |= XOR8(DA(a,3), DA(a, 9), DA(a,15), DA(a,21), DA(a,27), + * DA(a,33), DA(a,39), DA(a,45)) << 3; + * hash |= XOR8(DA(a,4), DA(a,10), DA(a,16), DA(a,22), DA(a,28), + * DA(a,34), DA(a,40), DA(a,46)) << 4; + * hash |= XOR8(DA(a,5), DA(a,11), DA(a,17), DA(a,23), DA(a,29), + * DA(a,35), DA(a,41), DA(a,47)) << 5; * */ -static inline u32 TLan_HashFunc( const u8 *a ) +static inline u32 tlan_hash_func(const u8 *a) { - u8 hash; + u8 hash; - hash = (a[0]^a[3]); /* & 077 */ - hash ^= ((a[0]^a[3])>>6); /* & 003 */ - hash ^= ((a[1]^a[4])<<2); /* & 074 */ - hash ^= ((a[1]^a[4])>>4); /* & 017 */ - hash ^= ((a[2]^a[5])<<4); /* & 060 */ - hash ^= ((a[2]^a[5])>>2); /* & 077 */ + hash = (a[0]^a[3]); /* & 077 */ + hash ^= ((a[0]^a[3])>>6); /* & 003 */ + hash ^= ((a[1]^a[4])<<2); /* & 074 */ + hash ^= ((a[1]^a[4])>>4); /* & 017 */ + hash ^= ((a[2]^a[5])<<4); /* & 060 */ + hash ^= ((a[2]^a[5])>>2); /* & 077 */ - return hash & 077; + return hash & 077; } #endif diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b100bd5..55786a0 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1142,7 +1142,7 @@ static int tun_get_iff(struct net *net, struct tun_struct *tun, * privs required. */ static int set_offload(struct net_device *dev, unsigned long arg) { - unsigned int old_features, features; + u32 old_features, features; old_features = dev->features; /* Unset features, set them as we chew on the arg. */ diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index a3c46f6..7fa5ec2 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -123,12 +123,11 @@ static const int multicast_filter_limit = 32; #include <linux/in6.h> #include <linux/dma-mapping.h> #include <linux/firmware.h> -#include <generated/utsrelease.h> #include "typhoon.h" MODULE_AUTHOR("David Dillow <dave@thedillows.org>"); -MODULE_VERSION(UTS_RELEASE); +MODULE_VERSION("1.0"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_NAME); MODULE_DESCRIPTION("3Com Typhoon Family (3C990, 3CR990, and variants)"); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index cc83fa7..105d7f0 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -403,17 +403,6 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, if (tb[IFLA_ADDRESS] == NULL) random_ether_addr(dev->dev_addr); - if (tb[IFLA_IFNAME]) - nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); - else - snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d"); - - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto err_alloc_name; - } - err = register_netdevice(dev); if (err < 0) goto err_register_dev; @@ -433,7 +422,6 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, err_register_dev: /* nothing to do */ -err_alloc_name: err_configure_peer: unregister_netdevice(peer); return err; diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index 09cac70..0d6fec6 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -2923,6 +2923,7 @@ static u16 wol_calc_crc(int size, u8 *pattern, u8 *mask_pattern) static int velocity_set_wol(struct velocity_info *vptr) { struct mac_regs __iomem *regs = vptr->mac_regs; + enum speed_opt spd_dpx = vptr->options.spd_dpx; static u8 buf[256]; int i; @@ -2968,6 +2969,12 @@ static int velocity_set_wol(struct velocity_info *vptr) writew(0x0FFF, ®s->WOLSRClr); + if (spd_dpx == SPD_DPX_1000_FULL) + goto mac_done; + + if (spd_dpx != SPD_DPX_AUTO) + goto advertise_done; + if (vptr->mii_status & VELOCITY_AUTONEG_ENABLE) { if (PHYID_GET_PHY_ID(vptr->phy_id) == PHYID_CICADA_CS8201) MII_REG_BITS_ON(AUXCR_MDPPS, MII_NCONFIG, vptr->mac_regs); @@ -2978,6 +2985,7 @@ static int velocity_set_wol(struct velocity_info *vptr) if (vptr->mii_status & VELOCITY_SPEED_1000) MII_REG_BITS_ON(BMCR_ANRESTART, MII_BMCR, vptr->mac_regs); +advertise_done: BYTE_REG_BITS_ON(CHIPGCR_FCMODE, ®s->CHIPGCR); { @@ -2987,6 +2995,7 @@ static int velocity_set_wol(struct velocity_info *vptr) writeb(GCR, ®s->CHIPGCR); } +mac_done: BYTE_REG_BITS_OFF(ISR_PWEI, ®s->ISR); /* Turn on SWPTAG just before entering power mode */ BYTE_REG_BITS_ON(STICKHW_SWPTAG, ®s->STICKHW); diff --git a/drivers/net/via-velocity.h b/drivers/net/via-velocity.h index aa2e69b..d722753 100644 --- a/drivers/net/via-velocity.h +++ b/drivers/net/via-velocity.h @@ -361,7 +361,7 @@ enum velocity_owner { #define MAC_REG_CHIPGSR 0x9C #define MAC_REG_TESTCFG 0x9D #define MAC_REG_DEBUG 0x9E -#define MAC_REG_CHIPGCR 0x9F +#define MAC_REG_CHIPGCR 0x9F /* Chip Operation and Diagnostic Control */ #define MAC_REG_WOLCR0_SET 0xA0 #define MAC_REG_WOLCR1_SET 0xA1 #define MAC_REG_PWCFG_SET 0xA2 @@ -848,10 +848,10 @@ enum velocity_owner { * Bits in CHIPGCR register */ -#define CHIPGCR_FCGMII 0x80 /* enable GMII mode */ -#define CHIPGCR_FCFDX 0x40 +#define CHIPGCR_FCGMII 0x80 /* force GMII (else MII only) */ +#define CHIPGCR_FCFDX 0x40 /* force full duplex */ #define CHIPGCR_FCRESV 0x20 -#define CHIPGCR_FCMODE 0x10 +#define CHIPGCR_FCMODE 0x10 /* enable MAC forced mode */ #define CHIPGCR_LPSOPT 0x08 #define CHIPGCR_TM1US 0x04 #define CHIPGCR_TM0US 0x02 diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c index 228d4f7..e74e4b4 100644 --- a/drivers/net/vxge/vxge-config.c +++ b/drivers/net/vxge/vxge-config.c @@ -387,8 +387,8 @@ vxge_hw_vpath_eprom_img_ver_get(struct __vxge_hw_device *hldev, data1 = steer_ctrl = 0; status = vxge_hw_vpath_fw_api(vpath, - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, VXGE_HW_FW_API_GET_EPROM_REV, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, 0, &data0, &data1, &steer_ctrl); if (status != VXGE_HW_OK) break; @@ -2868,6 +2868,8 @@ __vxge_hw_ring_create(struct __vxge_hw_vpath_handle *vp, ring->rxd_init = attr->rxd_init; ring->rxd_term = attr->rxd_term; ring->buffer_mode = config->buffer_mode; + ring->tim_rti_cfg1_saved = vp->vpath->tim_rti_cfg1_saved; + ring->tim_rti_cfg3_saved = vp->vpath->tim_rti_cfg3_saved; ring->rxds_limit = config->rxds_limit; ring->rxd_size = vxge_hw_ring_rxd_size_get(config->buffer_mode); @@ -3511,6 +3513,8 @@ __vxge_hw_fifo_create(struct __vxge_hw_vpath_handle *vp, /* apply "interrupts per txdl" attribute */ fifo->interrupt_type = VXGE_HW_FIFO_TXD_INT_TYPE_UTILZ; + fifo->tim_tti_cfg1_saved = vpath->tim_tti_cfg1_saved; + fifo->tim_tti_cfg3_saved = vpath->tim_tti_cfg3_saved; if (fifo->config->intr) fifo->interrupt_type = VXGE_HW_FIFO_TXD_INT_TYPE_PER_LIST; @@ -4377,6 +4381,8 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); + vpath->tim_tti_cfg1_saved = val64; + val64 = readq(&vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_TX]); if (config->tti.uec_a != VXGE_HW_USE_FLASH_DEFAULT) { @@ -4433,6 +4439,7 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_TX]); + vpath->tim_tti_cfg3_saved = val64; } if (config->ring.enable == VXGE_HW_RING_ENABLE) { @@ -4481,6 +4488,8 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_RX]); + vpath->tim_rti_cfg1_saved = val64; + val64 = readq(&vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_RX]); if (config->rti.uec_a != VXGE_HW_USE_FLASH_DEFAULT) { @@ -4537,6 +4546,7 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_RX]); + vpath->tim_rti_cfg3_saved = val64; } val64 = 0; @@ -4555,26 +4565,6 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) return status; } -void vxge_hw_vpath_tti_ci_set(struct __vxge_hw_device *hldev, u32 vp_id) -{ - struct __vxge_hw_virtualpath *vpath; - struct vxge_hw_vpath_reg __iomem *vp_reg; - struct vxge_hw_vp_config *config; - u64 val64; - - vpath = &hldev->virtual_paths[vp_id]; - vp_reg = vpath->vp_reg; - config = vpath->vp_config; - - if (config->fifo.enable == VXGE_HW_FIFO_ENABLE && - config->tti.timer_ci_en != VXGE_HW_TIM_TIMER_CI_ENABLE) { - config->tti.timer_ci_en = VXGE_HW_TIM_TIMER_CI_ENABLE; - val64 = readq(&vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); - val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI; - writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); - } -} - /* * __vxge_hw_vpath_initialize * This routine is the final phase of init which initializes the diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h index e249e28..3c53aa7 100644 --- a/drivers/net/vxge/vxge-config.h +++ b/drivers/net/vxge/vxge-config.h @@ -682,6 +682,10 @@ struct __vxge_hw_virtualpath { u32 vsport_number; u32 max_kdfc_db; u32 max_nofl_db; + u64 tim_tti_cfg1_saved; + u64 tim_tti_cfg3_saved; + u64 tim_rti_cfg1_saved; + u64 tim_rti_cfg3_saved; struct __vxge_hw_ring *____cacheline_aligned ringh; struct __vxge_hw_fifo *____cacheline_aligned fifoh; @@ -921,6 +925,9 @@ struct __vxge_hw_ring { u32 doorbell_cnt; u32 total_db_cnt; u64 rxds_limit; + u32 rtimer; + u64 tim_rti_cfg1_saved; + u64 tim_rti_cfg3_saved; enum vxge_hw_status (*callback)( struct __vxge_hw_ring *ringh, @@ -1000,6 +1007,9 @@ struct __vxge_hw_fifo { u32 per_txdl_space; u32 vp_id; u32 tx_intr_num; + u32 rtimer; + u64 tim_tti_cfg1_saved; + u64 tim_tti_cfg3_saved; enum vxge_hw_status (*callback)( struct __vxge_hw_fifo *fifo_handle, diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index c81a651..e40f619 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -371,9 +371,6 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr, struct vxge_hw_ring_rxd_info ext_info; vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d", ring->ndev->name, __func__, __LINE__); - ring->pkts_processed = 0; - - vxge_hw_ring_replenish(ringh); do { prefetch((char *)dtr + L1_CACHE_BYTES); @@ -1588,6 +1585,36 @@ static int vxge_reset_vpath(struct vxgedev *vdev, int vp_id) return ret; } +/* Configure CI */ +static void vxge_config_ci_for_tti_rti(struct vxgedev *vdev) +{ + int i = 0; + + /* Enable CI for RTI */ + if (vdev->config.intr_type == MSI_X) { + for (i = 0; i < vdev->no_of_vpath; i++) { + struct __vxge_hw_ring *hw_ring; + + hw_ring = vdev->vpaths[i].ring.handle; + vxge_hw_vpath_dynamic_rti_ci_set(hw_ring); + } + } + + /* Enable CI for TTI */ + for (i = 0; i < vdev->no_of_vpath; i++) { + struct __vxge_hw_fifo *hw_fifo = vdev->vpaths[i].fifo.handle; + vxge_hw_vpath_tti_ci_set(hw_fifo); + /* + * For Inta (with or without napi), Set CI ON for only one + * vpath. (Have only one free running timer). + */ + if ((vdev->config.intr_type == INTA) && (i == 0)) + break; + } + + return; +} + static int do_vxge_reset(struct vxgedev *vdev, int event) { enum vxge_hw_status status; @@ -1753,6 +1780,9 @@ static int do_vxge_reset(struct vxgedev *vdev, int event) netif_tx_wake_all_queues(vdev->ndev); } + /* configure CI */ + vxge_config_ci_for_tti_rti(vdev); + out: vxge_debug_entryexit(VXGE_TRACE, "%s:%d Exiting...", __func__, __LINE__); @@ -1793,22 +1823,29 @@ static void vxge_reset(struct work_struct *work) */ static int vxge_poll_msix(struct napi_struct *napi, int budget) { - struct vxge_ring *ring = - container_of(napi, struct vxge_ring, napi); + struct vxge_ring *ring = container_of(napi, struct vxge_ring, napi); + int pkts_processed; int budget_org = budget; - ring->budget = budget; + ring->budget = budget; + ring->pkts_processed = 0; vxge_hw_vpath_poll_rx(ring->handle); + pkts_processed = ring->pkts_processed; if (ring->pkts_processed < budget_org) { napi_complete(napi); + /* Re enable the Rx interrupts for the vpath */ vxge_hw_channel_msix_unmask( (struct __vxge_hw_channel *)ring->handle, ring->rx_vector_no); + mmiowb(); } - return ring->pkts_processed; + /* We are copying and returning the local variable, in case if after + * clearing the msix interrupt above, if the interrupt fires right + * away which can preempt this NAPI thread */ + return pkts_processed; } static int vxge_poll_inta(struct napi_struct *napi, int budget) @@ -1824,6 +1861,7 @@ static int vxge_poll_inta(struct napi_struct *napi, int budget) for (i = 0; i < vdev->no_of_vpath; i++) { ring = &vdev->vpaths[i].ring; ring->budget = budget; + ring->pkts_processed = 0; vxge_hw_vpath_poll_rx(ring->handle); pkts_processed += ring->pkts_processed; budget -= ring->pkts_processed; @@ -2054,6 +2092,7 @@ static int vxge_open_vpaths(struct vxgedev *vdev) netdev_get_tx_queue(vdev->ndev, 0); vpath->fifo.indicate_max_pkts = vdev->config.fifo_indicate_max_pkts; + vpath->fifo.tx_vector_no = 0; vpath->ring.rx_vector_no = 0; vpath->ring.rx_csum = vdev->rx_csum; vpath->ring.rx_hwts = vdev->rx_hwts; @@ -2079,6 +2118,61 @@ static int vxge_open_vpaths(struct vxgedev *vdev) return VXGE_HW_OK; } +/** + * adaptive_coalesce_tx_interrupts - Changes the interrupt coalescing + * if the interrupts are not within a range + * @fifo: pointer to transmit fifo structure + * Description: The function changes boundary timer and restriction timer + * value depends on the traffic + * Return Value: None + */ +static void adaptive_coalesce_tx_interrupts(struct vxge_fifo *fifo) +{ + fifo->interrupt_count++; + if (jiffies > fifo->jiffies + HZ / 100) { + struct __vxge_hw_fifo *hw_fifo = fifo->handle; + + fifo->jiffies = jiffies; + if (fifo->interrupt_count > VXGE_T1A_MAX_TX_INTERRUPT_COUNT && + hw_fifo->rtimer != VXGE_TTI_RTIMER_ADAPT_VAL) { + hw_fifo->rtimer = VXGE_TTI_RTIMER_ADAPT_VAL; + vxge_hw_vpath_dynamic_tti_rtimer_set(hw_fifo); + } else if (hw_fifo->rtimer != 0) { + hw_fifo->rtimer = 0; + vxge_hw_vpath_dynamic_tti_rtimer_set(hw_fifo); + } + fifo->interrupt_count = 0; + } +} + +/** + * adaptive_coalesce_rx_interrupts - Changes the interrupt coalescing + * if the interrupts are not within a range + * @ring: pointer to receive ring structure + * Description: The function increases of decreases the packet counts within + * the ranges of traffic utilization, if the interrupts due to this ring are + * not within a fixed range. + * Return Value: Nothing + */ +static void adaptive_coalesce_rx_interrupts(struct vxge_ring *ring) +{ + ring->interrupt_count++; + if (jiffies > ring->jiffies + HZ / 100) { + struct __vxge_hw_ring *hw_ring = ring->handle; + + ring->jiffies = jiffies; + if (ring->interrupt_count > VXGE_T1A_MAX_INTERRUPT_COUNT && + hw_ring->rtimer != VXGE_RTI_RTIMER_ADAPT_VAL) { + hw_ring->rtimer = VXGE_RTI_RTIMER_ADAPT_VAL; + vxge_hw_vpath_dynamic_rti_rtimer_set(hw_ring); + } else if (hw_ring->rtimer != 0) { + hw_ring->rtimer = 0; + vxge_hw_vpath_dynamic_rti_rtimer_set(hw_ring); + } + ring->interrupt_count = 0; + } +} + /* * vxge_isr_napi * @irq: the irq of the device. @@ -2139,24 +2233,39 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id) #ifdef CONFIG_PCI_MSI -static irqreturn_t -vxge_tx_msix_handle(int irq, void *dev_id) +static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id) { struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id; + adaptive_coalesce_tx_interrupts(fifo); + + vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)fifo->handle, + fifo->tx_vector_no); + + vxge_hw_channel_msix_clear((struct __vxge_hw_channel *)fifo->handle, + fifo->tx_vector_no); + VXGE_COMPLETE_VPATH_TX(fifo); + vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle, + fifo->tx_vector_no); + + mmiowb(); + return IRQ_HANDLED; } -static irqreturn_t -vxge_rx_msix_napi_handle(int irq, void *dev_id) +static irqreturn_t vxge_rx_msix_napi_handle(int irq, void *dev_id) { struct vxge_ring *ring = (struct vxge_ring *)dev_id; - /* MSIX_IDX for Rx is 1 */ + adaptive_coalesce_rx_interrupts(ring); + vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)ring->handle, - ring->rx_vector_no); + ring->rx_vector_no); + + vxge_hw_channel_msix_clear((struct __vxge_hw_channel *)ring->handle, + ring->rx_vector_no); napi_schedule(&ring->napi); return IRQ_HANDLED; @@ -2173,14 +2282,20 @@ vxge_alarm_msix_handle(int irq, void *dev_id) VXGE_HW_VPATH_MSIX_ACTIVE) + VXGE_ALARM_MSIX_ID; for (i = 0; i < vdev->no_of_vpath; i++) { + /* Reduce the chance of loosing alarm interrupts by masking + * the vector. A pending bit will be set if an alarm is + * generated and on unmask the interrupt will be fired. + */ vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id); + vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id); + mmiowb(); status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle, vdev->exec_mode); if (status == VXGE_HW_OK) { - vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle, - msix_id); + msix_id); + mmiowb(); continue; } vxge_debug_intr(VXGE_ERR, @@ -2299,6 +2414,9 @@ static int vxge_enable_msix(struct vxgedev *vdev) vpath->ring.rx_vector_no = (vpath->device_id * VXGE_HW_VPATH_MSIX_ACTIVE) + 1; + vpath->fifo.tx_vector_no = (vpath->device_id * + VXGE_HW_VPATH_MSIX_ACTIVE); + vxge_hw_vpath_msix_set(vpath->handle, tim_msix_id, VXGE_ALARM_MSIX_ID); } @@ -2474,8 +2592,9 @@ INTA_MODE: "%s:vxge:INTA", vdev->ndev->name); vxge_hw_device_set_intr_type(vdev->devh, VXGE_HW_INTR_MODE_IRQLINE); - vxge_hw_vpath_tti_ci_set(vdev->devh, - vdev->vpaths[0].device_id); + + vxge_hw_vpath_tti_ci_set(vdev->vpaths[0].fifo.handle); + ret = request_irq((int) vdev->pdev->irq, vxge_isr_napi, IRQF_SHARED, vdev->desc[0], vdev); @@ -2745,6 +2864,10 @@ static int vxge_open(struct net_device *dev) } netif_tx_start_all_queues(vdev->ndev); + + /* configure CI */ + vxge_config_ci_for_tti_rti(vdev); + goto out0; out2: @@ -3348,7 +3471,7 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, vxge_debug_init(VXGE_ERR, "%s: vpath memory allocation failed", vdev->ndev->name); - ret = -ENODEV; + ret = -ENOMEM; goto _out1; } @@ -3369,11 +3492,11 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, if (vdev->config.gro_enable) ndev->features |= NETIF_F_GRO; - if (register_netdev(ndev)) { + ret = register_netdev(ndev); + if (ret) { vxge_debug_init(vxge_hw_device_trace_level_get(hldev), "%s: %s : device registration failed!", ndev->name, __func__); - ret = -ENODEV; goto _out2; } @@ -3444,6 +3567,11 @@ static void vxge_device_unregister(struct __vxge_hw_device *hldev) /* in 2.6 will call stop() if device is up */ unregister_netdev(dev); + kfree(vdev->vpaths); + + /* we are safe to free it now */ + free_netdev(dev); + vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered", buf); vxge_debug_entryexit(vdev->level_trace, "%s: %s:%d Exiting...", buf, @@ -3799,7 +3927,7 @@ static void __devinit vxge_device_config_init( break; case MSI_X: - device_config->intr_mode = VXGE_HW_INTR_MODE_MSIX; + device_config->intr_mode = VXGE_HW_INTR_MODE_MSIX_ONE_SHOT; break; } @@ -4335,10 +4463,10 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) goto _exit1; } - if (pci_request_region(pdev, 0, VXGE_DRIVER_NAME)) { + ret = pci_request_region(pdev, 0, VXGE_DRIVER_NAME); + if (ret) { vxge_debug_init(VXGE_ERR, "%s : request regions failed", __func__); - ret = -ENODEV; goto _exit1; } @@ -4446,7 +4574,7 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) if (!img[i].is_valid) break; vxge_debug_init(VXGE_TRACE, "%s: EPROM %d, version " - "%d.%d.%d.%d\n", VXGE_DRIVER_NAME, i, + "%d.%d.%d.%d", VXGE_DRIVER_NAME, i, VXGE_EPROM_IMG_MAJOR(img[i].version), VXGE_EPROM_IMG_MINOR(img[i].version), VXGE_EPROM_IMG_FIX(img[i].version), @@ -4643,8 +4771,9 @@ _exit6: _exit5: vxge_device_unregister(hldev); _exit4: - pci_disable_sriov(pdev); + pci_set_drvdata(pdev, NULL); vxge_hw_device_terminate(hldev); + pci_disable_sriov(pdev); _exit3: iounmap(attr.bar0); _exit2: @@ -4655,7 +4784,7 @@ _exit0: kfree(ll_config); kfree(device_config); driver_config->config_dev_cnt--; - pci_set_drvdata(pdev, NULL); + driver_config->total_dev_cnt--; return ret; } @@ -4668,45 +4797,34 @@ _exit0: static void __devexit vxge_remove(struct pci_dev *pdev) { struct __vxge_hw_device *hldev; - struct vxgedev *vdev = NULL; - struct net_device *dev; - int i = 0; + struct vxgedev *vdev; + int i; hldev = pci_get_drvdata(pdev); - if (hldev == NULL) return; - dev = hldev->ndev; - vdev = netdev_priv(dev); + vdev = netdev_priv(hldev->ndev); vxge_debug_entryexit(vdev->level_trace, "%s:%d", __func__, __LINE__); - vxge_debug_init(vdev->level_trace, "%s : removing PCI device...", __func__); - vxge_device_unregister(hldev); - for (i = 0; i < vdev->no_of_vpath; i++) { + for (i = 0; i < vdev->no_of_vpath; i++) vxge_free_mac_add_list(&vdev->vpaths[i]); - vdev->vpaths[i].mcast_addr_cnt = 0; - vdev->vpaths[i].mac_addr_cnt = 0; - } - - kfree(vdev->vpaths); + vxge_device_unregister(hldev); + pci_set_drvdata(pdev, NULL); + /* Do not call pci_disable_sriov here, as it will break child devices */ + vxge_hw_device_terminate(hldev); iounmap(vdev->bar0); - - /* we are safe to free it now */ - free_netdev(dev); + pci_release_region(pdev, 0); + pci_disable_device(pdev); + driver_config->config_dev_cnt--; + driver_config->total_dev_cnt--; vxge_debug_init(vdev->level_trace, "%s:%d Device unregistered", __func__, __LINE__); - - vxge_hw_device_terminate(hldev); - - pci_disable_device(pdev); - pci_release_region(pdev, 0); - pci_set_drvdata(pdev, NULL); vxge_debug_entryexit(vdev->level_trace, "%s:%d Exiting...", __func__, __LINE__); } diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h index 5746fed..40474f0 100644 --- a/drivers/net/vxge/vxge-main.h +++ b/drivers/net/vxge/vxge-main.h @@ -59,11 +59,13 @@ #define VXGE_TTI_LTIMER_VAL 1000 #define VXGE_T1A_TTI_LTIMER_VAL 80 #define VXGE_TTI_RTIMER_VAL 0 +#define VXGE_TTI_RTIMER_ADAPT_VAL 10 #define VXGE_T1A_TTI_RTIMER_VAL 400 #define VXGE_RTI_BTIMER_VAL 250 #define VXGE_RTI_LTIMER_VAL 100 #define VXGE_RTI_RTIMER_VAL 0 -#define VXGE_FIFO_INDICATE_MAX_PKTS VXGE_DEF_FIFO_LENGTH +#define VXGE_RTI_RTIMER_ADAPT_VAL 15 +#define VXGE_FIFO_INDICATE_MAX_PKTS VXGE_DEF_FIFO_LENGTH #define VXGE_ISR_POLLING_CNT 8 #define VXGE_MAX_CONFIG_DEV 0xFF #define VXGE_EXEC_MODE_DISABLE 0 @@ -107,6 +109,14 @@ #define RTI_T1A_RX_UFC_C 50 #define RTI_T1A_RX_UFC_D 60 +/* + * The interrupt rate is maintained at 3k per second with the moderation + * parameters for most traffic but not all. This is the maximum interrupt + * count allowed per function with INTA or per vector in the case of + * MSI-X in a 10 millisecond time period. Enabled only for Titan 1A. + */ +#define VXGE_T1A_MAX_INTERRUPT_COUNT 100 +#define VXGE_T1A_MAX_TX_INTERRUPT_COUNT 200 /* Milli secs timer period */ #define VXGE_TIMER_DELAY 10000 @@ -247,6 +257,11 @@ struct vxge_fifo { int tx_steering_type; int indicate_max_pkts; + /* Adaptive interrupt moderation parameters used in T1A */ + unsigned long interrupt_count; + unsigned long jiffies; + + u32 tx_vector_no; /* Tx stats */ struct vxge_fifo_stats stats; } ____cacheline_aligned; @@ -271,6 +286,10 @@ struct vxge_ring { */ int driver_id; + /* Adaptive interrupt moderation parameters used in T1A */ + unsigned long interrupt_count; + unsigned long jiffies; + /* copy of the flag indicating whether rx_csum is to be used */ u32 rx_csum:1, rx_hwts:1; @@ -286,7 +305,7 @@ struct vxge_ring { int vlan_tag_strip; struct vlan_group *vlgrp; - int rx_vector_no; + u32 rx_vector_no; enum vxge_hw_status last_status; /* Rx stats */ diff --git a/drivers/net/vxge/vxge-traffic.c b/drivers/net/vxge/vxge-traffic.c index 4c10d6c..8674f33 100644 --- a/drivers/net/vxge/vxge-traffic.c +++ b/drivers/net/vxge/vxge-traffic.c @@ -218,6 +218,68 @@ exit: return status; } +void vxge_hw_vpath_tti_ci_set(struct __vxge_hw_fifo *fifo) +{ + struct vxge_hw_vpath_reg __iomem *vp_reg; + struct vxge_hw_vp_config *config; + u64 val64; + + if (fifo->config->enable != VXGE_HW_FIFO_ENABLE) + return; + + vp_reg = fifo->vp_reg; + config = container_of(fifo->config, struct vxge_hw_vp_config, fifo); + + if (config->tti.timer_ci_en != VXGE_HW_TIM_TIMER_CI_ENABLE) { + config->tti.timer_ci_en = VXGE_HW_TIM_TIMER_CI_ENABLE; + val64 = readq(&vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); + val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI; + fifo->tim_tti_cfg1_saved = val64; + writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); + } +} + +void vxge_hw_vpath_dynamic_rti_ci_set(struct __vxge_hw_ring *ring) +{ + u64 val64 = ring->tim_rti_cfg1_saved; + + val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI; + ring->tim_rti_cfg1_saved = val64; + writeq(val64, &ring->vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_RX]); +} + +void vxge_hw_vpath_dynamic_tti_rtimer_set(struct __vxge_hw_fifo *fifo) +{ + u64 val64 = fifo->tim_tti_cfg3_saved; + u64 timer = (fifo->rtimer * 1000) / 272; + + val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(0x3ffffff); + if (timer) + val64 |= VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(timer) | + VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_EVENT_SF(5); + + writeq(val64, &fifo->vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_TX]); + /* tti_cfg3_saved is not updated again because it is + * initialized at one place only - init time. + */ +} + +void vxge_hw_vpath_dynamic_rti_rtimer_set(struct __vxge_hw_ring *ring) +{ + u64 val64 = ring->tim_rti_cfg3_saved; + u64 timer = (ring->rtimer * 1000) / 272; + + val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(0x3ffffff); + if (timer) + val64 |= VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(timer) | + VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_EVENT_SF(4); + + writeq(val64, &ring->vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_RX]); + /* rti_cfg3_saved is not updated again because it is + * initialized at one place only - init time. + */ +} + /** * vxge_hw_channel_msix_mask - Mask MSIX Vector. * @channeh: Channel for rx or tx handle @@ -254,6 +316,23 @@ vxge_hw_channel_msix_unmask(struct __vxge_hw_channel *channel, int msix_id) } /** + * vxge_hw_channel_msix_clear - Unmask the MSIX Vector. + * @channel: Channel for rx or tx handle + * @msix_id: MSI ID + * + * The function unmasks the msix interrupt for the given msix_id + * if configured in MSIX oneshot mode + * + * Returns: 0 + */ +void vxge_hw_channel_msix_clear(struct __vxge_hw_channel *channel, int msix_id) +{ + __vxge_hw_pio_mem_write32_upper( + (u32) vxge_bVALn(vxge_mBIT(msix_id >> 2), 0, 32), + &channel->common_reg->clr_msix_one_shot_vec[msix_id % 4]); +} + +/** * vxge_hw_device_set_intr_type - Updates the configuration * with new interrupt type. * @hldev: HW device handle. @@ -2191,19 +2270,14 @@ vxge_hw_vpath_msix_set(struct __vxge_hw_vpath_handle *vp, int *tim_msix_id, if (vpath->hldev->config.intr_mode == VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) { __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( + VXGE_HW_ONE_SHOT_VECT0_EN_ONE_SHOT_VECT0_EN, + 0, 32), &vp_reg->one_shot_vect0_en); + __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( VXGE_HW_ONE_SHOT_VECT1_EN_ONE_SHOT_VECT1_EN, 0, 32), &vp_reg->one_shot_vect1_en); - } - - if (vpath->hldev->config.intr_mode == - VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) { __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( VXGE_HW_ONE_SHOT_VECT2_EN_ONE_SHOT_VECT2_EN, 0, 32), &vp_reg->one_shot_vect2_en); - - __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( - VXGE_HW_ONE_SHOT_VECT3_EN_ONE_SHOT_VECT3_EN, - 0, 32), &vp_reg->one_shot_vect3_en); } } @@ -2229,6 +2303,32 @@ vxge_hw_vpath_msix_mask(struct __vxge_hw_vpath_handle *vp, int msix_id) } /** + * vxge_hw_vpath_msix_clear - Clear MSIX Vector. + * @vp: Virtual Path handle. + * @msix_id: MSI ID + * + * The function clears the msix interrupt for the given msix_id + * + * Returns: 0, + * Otherwise, VXGE_HW_ERR_WRONG_IRQ if the msix index is out of range + * status. + * See also: + */ +void vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vp, int msix_id) +{ + struct __vxge_hw_device *hldev = vp->vpath->hldev; + + if ((hldev->config.intr_mode == VXGE_HW_INTR_MODE_MSIX_ONE_SHOT)) + __vxge_hw_pio_mem_write32_upper( + (u32) vxge_bVALn(vxge_mBIT((msix_id >> 2)), 0, 32), + &hldev->common_reg->clr_msix_one_shot_vec[msix_id % 4]); + else + __vxge_hw_pio_mem_write32_upper( + (u32) vxge_bVALn(vxge_mBIT((msix_id >> 2)), 0, 32), + &hldev->common_reg->clear_msix_mask_vect[msix_id % 4]); +} + +/** * vxge_hw_vpath_msix_unmask - Unmask the MSIX Vector. * @vp: Virtual Path handle. * @msix_id: MSI ID diff --git a/drivers/net/vxge/vxge-traffic.h b/drivers/net/vxge/vxge-traffic.h index d48486d..9d9dfda 100644 --- a/drivers/net/vxge/vxge-traffic.h +++ b/drivers/net/vxge/vxge-traffic.h @@ -2142,6 +2142,10 @@ void vxge_hw_device_clear_tx_rx( * Virtual Paths */ +void vxge_hw_vpath_dynamic_rti_rtimer_set(struct __vxge_hw_ring *ring); + +void vxge_hw_vpath_dynamic_tti_rtimer_set(struct __vxge_hw_fifo *fifo); + u32 vxge_hw_vpath_id( struct __vxge_hw_vpath_handle *vpath_handle); @@ -2245,6 +2249,8 @@ void vxge_hw_vpath_msix_mask(struct __vxge_hw_vpath_handle *vpath_handle, int msix_id); +void vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vp, int msix_id); + void vxge_hw_device_flush_io(struct __vxge_hw_device *devh); void @@ -2270,6 +2276,9 @@ void vxge_hw_channel_msix_unmask(struct __vxge_hw_channel *channelh, int msix_id); void +vxge_hw_channel_msix_clear(struct __vxge_hw_channel *channelh, int msix_id); + +void vxge_hw_channel_dtr_try_complete(struct __vxge_hw_channel *channel, void **dtrh); @@ -2282,7 +2291,8 @@ vxge_hw_channel_dtr_free(struct __vxge_hw_channel *channel, void *dtrh); int vxge_hw_channel_dtr_count(struct __vxge_hw_channel *channel); -void -vxge_hw_vpath_tti_ci_set(struct __vxge_hw_device *hldev, u32 vp_id); +void vxge_hw_vpath_tti_ci_set(struct __vxge_hw_fifo *fifo); + +void vxge_hw_vpath_dynamic_rti_ci_set(struct __vxge_hw_ring *ring); #endif diff --git a/drivers/net/vxge/vxge-version.h b/drivers/net/vxge/vxge-version.h index ad2f99b..581e215 100644 --- a/drivers/net/vxge/vxge-version.h +++ b/drivers/net/vxge/vxge-version.h @@ -16,8 +16,8 @@ #define VXGE_VERSION_MAJOR "2" #define VXGE_VERSION_MINOR "5" -#define VXGE_VERSION_FIX "1" -#define VXGE_VERSION_BUILD "22082" +#define VXGE_VERSION_FIX "2" +#define VXGE_VERSION_BUILD "22259" #define VXGE_VERSION_FOR "k" #define VXGE_FW_VER(maj, min, bld) (((maj) << 16) + ((min) << 8) + (bld)) diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c index 32bf79e..a9111e1 100644 --- a/drivers/net/wireless/ath/ar9170/main.c +++ b/drivers/net/wireless/ath/ar9170/main.c @@ -1945,7 +1945,8 @@ static int ar9170_conf_tx(struct ieee80211_hw *hw, u16 queue, static int ar9170_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { switch (action) { case IEEE80211_AMPDU_RX_START: diff --git a/drivers/net/wireless/ath/ath.h b/drivers/net/wireless/ath/ath.h index e43210c..a6c6a46 100644 --- a/drivers/net/wireless/ath/ath.h +++ b/drivers/net/wireless/ath/ath.h @@ -108,12 +108,14 @@ enum ath_cipher { * struct ath_ops - Register read/write operations * * @read: Register read + * @multi_read: Multiple register read * @write: Register write * @enable_write_buffer: Enable multiple register writes * @write_flush: flush buffered register writes and disable buffering */ struct ath_ops { unsigned int (*read)(void *, u32 reg_offset); + void (*multi_read)(void *, u32 *addr, u32 *val, u16 count); void (*write)(void *, u32 val, u32 reg_offset); void (*enable_write_buffer)(void *); void (*write_flush) (void *); diff --git a/drivers/net/wireless/ath/ath5k/Kconfig b/drivers/net/wireless/ath/ath5k/Kconfig index e079331..e18a9aa 100644 --- a/drivers/net/wireless/ath/ath5k/Kconfig +++ b/drivers/net/wireless/ath/ath5k/Kconfig @@ -40,6 +40,17 @@ config ATH5K_DEBUG modprobe ath5k debug=0x00000400 +config ATH5K_TRACER + bool "Atheros 5xxx tracer" + depends on ATH5K + depends on EVENT_TRACING + ---help--- + Say Y here to enable tracepoints for the ath5k driver + using the kernel tracing infrastructure. Select this + option if you are interested in debugging the driver. + + If unsure, say N. + config ATH5K_AHB bool "Atheros 5xxx AHB bus support" depends on (ATHEROS_AR231X && !PCI) diff --git a/drivers/net/wireless/ath/ath5k/ahb.c b/drivers/net/wireless/ath/ath5k/ahb.c index 707cde1..ae84b86 100644 --- a/drivers/net/wireless/ath/ath5k/ahb.c +++ b/drivers/net/wireless/ath/ath5k/ahb.c @@ -31,7 +31,8 @@ static void ath5k_ahb_read_cachesize(struct ath_common *common, int *csz) *csz = L1_CACHE_BYTES >> 2; } -bool ath5k_ahb_eeprom_read(struct ath_common *common, u32 off, u16 *data) +static bool +ath5k_ahb_eeprom_read(struct ath_common *common, u32 off, u16 *data) { struct ath5k_softc *sc = common->priv; struct platform_device *pdev = to_platform_device(sc->dev); @@ -46,10 +47,10 @@ bool ath5k_ahb_eeprom_read(struct ath_common *common, u32 off, u16 *data) eeprom += off; if (eeprom > eeprom_end) - return -EINVAL; + return false; *data = *eeprom; - return 0; + return true; } int ath5k_hw_read_srev(struct ath5k_hw *ah) diff --git a/drivers/net/wireless/ath/ath5k/ath5k.h b/drivers/net/wireless/ath/ath5k/ath5k.h index 407e39c..e43175a 100644 --- a/drivers/net/wireless/ath/ath5k/ath5k.h +++ b/drivers/net/wireless/ath/ath5k/ath5k.h @@ -210,14 +210,9 @@ /* Initial values */ #define AR5K_INIT_CYCRSSI_THR1 2 -/* Tx retry limits */ -#define AR5K_INIT_SH_RETRY 10 -#define AR5K_INIT_LG_RETRY AR5K_INIT_SH_RETRY -/* For station mode */ -#define AR5K_INIT_SSH_RETRY 32 -#define AR5K_INIT_SLG_RETRY AR5K_INIT_SSH_RETRY -#define AR5K_INIT_TX_RETRY 10 - +/* Tx retry limit defaults from standard */ +#define AR5K_INIT_RETRY_SHORT 7 +#define AR5K_INIT_RETRY_LONG 4 /* Slot time */ #define AR5K_INIT_SLOT_TIME_TURBO 6 @@ -1057,7 +1052,9 @@ struct ath5k_hw { #define ah_modes ah_capabilities.cap_mode #define ah_ee_version ah_capabilities.cap_eeprom.ee_version - u32 ah_limit_tx_retries; + u8 ah_retry_long; + u8 ah_retry_short; + u8 ah_coverage_class; bool ah_ack_bitrate_high; u8 ah_bwmode; @@ -1067,7 +1064,6 @@ struct ath5k_hw { u8 ah_ant_mode; u8 ah_tx_ant; u8 ah_def_ant; - bool ah_software_retry; struct ath5k_capabilities ah_capabilities; @@ -1250,6 +1246,8 @@ int ath5k_hw_set_tx_queueprops(struct ath5k_hw *ah, int queue, int ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type, struct ath5k_txq_info *queue_info); +void ath5k_hw_set_tx_retry_limits(struct ath5k_hw *ah, + unsigned int queue); u32 ath5k_hw_num_tx_pending(struct ath5k_hw *ah, unsigned int queue); void ath5k_hw_release_tx_queue(struct ath5k_hw *ah, unsigned int queue); int ath5k_hw_reset_tx_queue(struct ath5k_hw *ah, unsigned int queue); diff --git a/drivers/net/wireless/ath/ath5k/attach.c b/drivers/net/wireless/ath/ath5k/attach.c index cdac5cf..c71fdbb 100644 --- a/drivers/net/wireless/ath/ath5k/attach.c +++ b/drivers/net/wireless/ath/ath5k/attach.c @@ -118,8 +118,8 @@ int ath5k_hw_init(struct ath5k_softc *sc) ah->ah_bwmode = AR5K_BWMODE_DEFAULT; ah->ah_txpower.txp_tpc = AR5K_TUNE_TPC_TXPOWER; ah->ah_imr = 0; - ah->ah_limit_tx_retries = AR5K_INIT_TX_RETRY; - ah->ah_software_retry = false; + ah->ah_retry_short = AR5K_INIT_RETRY_SHORT; + ah->ah_retry_long = AR5K_INIT_RETRY_LONG; ah->ah_ant_mode = AR5K_ANTMODE_DEFAULT; ah->ah_noise_floor = -95; /* until first NF calibration is run */ sc->ani_state.ani_mode = ATH5K_ANI_MODE_AUTO; diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 09ae4ef..dbc45e0 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -61,6 +61,9 @@ #include "debug.h" #include "ani.h" +#define CREATE_TRACE_POINTS +#include "trace.h" + int ath5k_modparam_nohwcrypt; module_param_named(nohwcrypt, ath5k_modparam_nohwcrypt, bool, S_IRUGO); MODULE_PARM_DESC(nohwcrypt, "Disable hardware encryption."); @@ -242,73 +245,68 @@ static int ath5k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *re \********************/ /* - * Convert IEEE channel number to MHz frequency. - */ -static inline short -ath5k_ieee2mhz(short chan) -{ - if (chan <= 14 || chan >= 27) - return ieee80211chan2mhz(chan); - else - return 2212 + chan * 20; -} - -/* * Returns true for the channel numbers used without all_channels modparam. */ -static bool ath5k_is_standard_channel(short chan) +static bool ath5k_is_standard_channel(short chan, enum ieee80211_band band) { - return ((chan <= 14) || - /* UNII 1,2 */ - ((chan & 3) == 0 && chan >= 36 && chan <= 64) || + if (band == IEEE80211_BAND_2GHZ && chan <= 14) + return true; + + return /* UNII 1,2 */ + (((chan & 3) == 0 && chan >= 36 && chan <= 64) || /* midband */ ((chan & 3) == 0 && chan >= 100 && chan <= 140) || /* UNII-3 */ - ((chan & 3) == 1 && chan >= 149 && chan <= 165)); + ((chan & 3) == 1 && chan >= 149 && chan <= 165) || + /* 802.11j 5.030-5.080 GHz (20MHz) */ + (chan == 8 || chan == 12 || chan == 16) || + /* 802.11j 4.9GHz (20MHz) */ + (chan == 184 || chan == 188 || chan == 192 || chan == 196)); } static unsigned int -ath5k_copy_channels(struct ath5k_hw *ah, - struct ieee80211_channel *channels, - unsigned int mode, - unsigned int max) +ath5k_setup_channels(struct ath5k_hw *ah, struct ieee80211_channel *channels, + unsigned int mode, unsigned int max) { - unsigned int i, count, size, chfreq, freq, ch; - - if (!test_bit(mode, ah->ah_modes)) - return 0; + unsigned int count, size, chfreq, freq, ch; + enum ieee80211_band band; switch (mode) { case AR5K_MODE_11A: /* 1..220, but 2GHz frequencies are filtered by check_channel */ - size = 220 ; + size = 220; chfreq = CHANNEL_5GHZ; + band = IEEE80211_BAND_5GHZ; break; case AR5K_MODE_11B: case AR5K_MODE_11G: size = 26; chfreq = CHANNEL_2GHZ; + band = IEEE80211_BAND_2GHZ; break; default: ATH5K_WARN(ah->ah_sc, "bad mode, not copying channels\n"); return 0; } - for (i = 0, count = 0; i < size && max > 0; i++) { - ch = i + 1 ; - freq = ath5k_ieee2mhz(ch); + count = 0; + for (ch = 1; ch <= size && count < max; ch++) { + freq = ieee80211_channel_to_frequency(ch, band); + + if (freq == 0) /* mapping failed - not a standard channel */ + continue; /* Check if channel is supported by the chipset */ if (!ath5k_channel_ok(ah, freq, chfreq)) continue; - if (!modparam_all_channels && !ath5k_is_standard_channel(ch)) + if (!modparam_all_channels && + !ath5k_is_standard_channel(ch, band)) continue; /* Write channel info and increment counter */ channels[count].center_freq = freq; - channels[count].band = (chfreq == CHANNEL_2GHZ) ? - IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + channels[count].band = band; switch (mode) { case AR5K_MODE_11A: case AR5K_MODE_11G: @@ -319,7 +317,6 @@ ath5k_copy_channels(struct ath5k_hw *ah, } count++; - max--; } return count; @@ -364,7 +361,7 @@ ath5k_setup_bands(struct ieee80211_hw *hw) sband->n_bitrates = 12; sband->channels = sc->channels; - sband->n_channels = ath5k_copy_channels(ah, sband->channels, + sband->n_channels = ath5k_setup_channels(ah, sband->channels, AR5K_MODE_11G, max_c); hw->wiphy->bands[IEEE80211_BAND_2GHZ] = sband; @@ -390,7 +387,7 @@ ath5k_setup_bands(struct ieee80211_hw *hw) } sband->channels = sc->channels; - sband->n_channels = ath5k_copy_channels(ah, sband->channels, + sband->n_channels = ath5k_setup_channels(ah, sband->channels, AR5K_MODE_11B, max_c); hw->wiphy->bands[IEEE80211_BAND_2GHZ] = sband; @@ -410,7 +407,7 @@ ath5k_setup_bands(struct ieee80211_hw *hw) sband->n_bitrates = 8; sband->channels = &sc->channels[count_c]; - sband->n_channels = ath5k_copy_channels(ah, sband->channels, + sband->n_channels = ath5k_setup_channels(ah, sband->channels, AR5K_MODE_11A, max_c); hw->wiphy->bands[IEEE80211_BAND_5GHZ] = sband; @@ -445,18 +442,6 @@ ath5k_chan_set(struct ath5k_softc *sc, struct ieee80211_channel *chan) return ath5k_reset(sc, chan, true); } -static void -ath5k_setcurmode(struct ath5k_softc *sc, unsigned int mode) -{ - sc->curmode = mode; - - if (mode == AR5K_MODE_11A) { - sc->curband = &sc->sbands[IEEE80211_BAND_5GHZ]; - } else { - sc->curband = &sc->sbands[IEEE80211_BAND_2GHZ]; - } -} - struct ath_vif_iter_data { const u8 *hw_macaddr; u8 mask[ETH_ALEN]; @@ -569,7 +554,7 @@ ath5k_hw_to_driver_rix(struct ath5k_softc *sc, int hw_rix) "hw_rix out of bounds: %x\n", hw_rix)) return 0; - rix = sc->rate_idx[sc->curband->band][hw_rix]; + rix = sc->rate_idx[sc->curchan->band][hw_rix]; if (WARN(rix < 0, "invalid hw_rix: %x\n", hw_rix)) rix = 0; @@ -1379,7 +1364,7 @@ ath5k_receive_frame(struct ath5k_softc *sc, struct sk_buff *skb, rxs->flag |= RX_FLAG_TSFT; rxs->freq = sc->curchan->center_freq; - rxs->band = sc->curband->band; + rxs->band = sc->curchan->band; rxs->signal = sc->ah->ah_noise_floor + rs->rs_rssi; @@ -1394,10 +1379,10 @@ ath5k_receive_frame(struct ath5k_softc *sc, struct sk_buff *skb, rxs->flag |= ath5k_rx_decrypted(sc, skb, rs); if (rxs->rate_idx >= 0 && rs->rs_rate == - sc->curband->bitrates[rxs->rate_idx].hw_value_short) + sc->sbands[sc->curchan->band].bitrates[rxs->rate_idx].hw_value_short) rxs->flag |= RX_FLAG_SHORTPRE; - ath5k_debug_dump_skb(sc, skb, "RX ", 0); + trace_ath5k_rx(sc, skb); ath5k_update_beacon_rssi(sc, skb, rs->rs_rssi); @@ -1542,7 +1527,7 @@ ath5k_tx_queue(struct ieee80211_hw *hw, struct sk_buff *skb, unsigned long flags; int padsize; - ath5k_debug_dump_skb(sc, skb, "TX ", 1); + trace_ath5k_tx(sc, skb, txq); /* * The hardware expects the header padded to 4 byte boundaries. @@ -1591,7 +1576,7 @@ drop_packet: static void ath5k_tx_frame_completed(struct ath5k_softc *sc, struct sk_buff *skb, - struct ath5k_tx_status *ts) + struct ath5k_txq *txq, struct ath5k_tx_status *ts) { struct ieee80211_tx_info *info; int i; @@ -1643,6 +1628,7 @@ ath5k_tx_frame_completed(struct ath5k_softc *sc, struct sk_buff *skb, else sc->stats.antenna_tx[0]++; /* invalid */ + trace_ath5k_tx_complete(sc, skb, txq, ts); ieee80211_tx_status(sc->hw, skb); } @@ -1679,7 +1665,7 @@ ath5k_tx_processq(struct ath5k_softc *sc, struct ath5k_txq *txq) dma_unmap_single(sc->dev, bf->skbaddr, skb->len, DMA_TO_DEVICE); - ath5k_tx_frame_completed(sc, skb, &ts); + ath5k_tx_frame_completed(sc, skb, txq, &ts); } /* @@ -1821,8 +1807,6 @@ ath5k_beacon_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif) goto out; } - ath5k_debug_dump_skb(sc, skb, "BC ", 1); - ath5k_txbuf_free_skb(sc, avf->bbuf); avf->bbuf->skb = skb; ret = ath5k_beacon_setup(sc, avf->bbuf); @@ -1917,6 +1901,8 @@ ath5k_beacon_send(struct ath5k_softc *sc) sc->opmode == NL80211_IFTYPE_MESH_POINT) ath5k_beacon_update(sc->hw, vif); + trace_ath5k_tx(sc, bf->skb, &sc->txqs[sc->bhalq]); + ath5k_hw_set_txdp(ah, sc->bhalq, bf->daddr); ath5k_hw_start_tx_dma(ah, sc->bhalq); ATH5K_DBG(sc, ATH5K_DEBUG_BEACON, "TXDP[%u] = %llx (%p)\n", @@ -2417,7 +2403,8 @@ ath5k_init_softc(struct ath5k_softc *sc, const struct ath_bus_ops *bus_ops) /* set up multi-rate retry capabilities */ if (sc->ah->ah_version == AR5K_AR5212) { hw->max_rates = 4; - hw->max_rate_tries = 11; + hw->max_rate_tries = max(AR5K_INIT_RETRY_SHORT, + AR5K_INIT_RETRY_LONG); } hw->vif_data_size = sizeof(struct ath5k_vif); @@ -2554,7 +2541,6 @@ ath5k_init_hw(struct ath5k_softc *sc) * and then setup of the interrupt mask. */ sc->curchan = sc->hw->conf.channel; - sc->curband = &sc->sbands[sc->curchan->band]; sc->imask = AR5K_INT_RXOK | AR5K_INT_RXERR | AR5K_INT_RXEOL | AR5K_INT_RXORN | AR5K_INT_TXDESC | AR5K_INT_TXEOL | AR5K_INT_FATAL | AR5K_INT_GLOBAL | AR5K_INT_MIB; @@ -2681,10 +2667,8 @@ ath5k_reset(struct ath5k_softc *sc, struct ieee80211_channel *chan, * so we should also free any remaining * tx buffers */ ath5k_drain_tx_buffs(sc); - if (chan) { + if (chan) sc->curchan = chan; - sc->curband = &sc->sbands[chan->band]; - } ret = ath5k_hw_reset(ah, sc->opmode, sc->curchan, chan != NULL, skip_pcu); if (ret) { @@ -2782,12 +2766,6 @@ ath5k_init(struct ieee80211_hw *hw) goto err; } - /* NB: setup here so ath5k_rate_update is happy */ - if (test_bit(AR5K_MODE_11A, ah->ah_modes)) - ath5k_setcurmode(sc, AR5K_MODE_11A); - else - ath5k_setcurmode(sc, AR5K_MODE_11B); - /* * Allocate tx+rx descriptors and populate the lists. */ diff --git a/drivers/net/wireless/ath/ath5k/base.h b/drivers/net/wireless/ath/ath5k/base.h index 6d51147..8f919dc 100644 --- a/drivers/net/wireless/ath/ath5k/base.h +++ b/drivers/net/wireless/ath/ath5k/base.h @@ -183,8 +183,6 @@ struct ath5k_softc { enum nl80211_iftype opmode; struct ath5k_hw *ah; /* Atheros HW */ - struct ieee80211_supported_band *curband; - #ifdef CONFIG_ATH5K_DEBUG struct ath5k_dbg_info debug; /* debug info */ #endif /* CONFIG_ATH5K_DEBUG */ @@ -202,7 +200,6 @@ struct ath5k_softc { #define ATH_STAT_STARTED 4 /* opened & irqs enabled */ unsigned int filter_flags; /* HW flags, AR5K_RX_FILTER_* */ - unsigned int curmode; /* current phy mode */ struct ieee80211_channel *curchan; /* current h/w channel */ u16 nvifs; diff --git a/drivers/net/wireless/ath/ath5k/caps.c b/drivers/net/wireless/ath/ath5k/caps.c index 31cad80..f77e8a7 100644 --- a/drivers/net/wireless/ath/ath5k/caps.c +++ b/drivers/net/wireless/ath/ath5k/caps.c @@ -32,23 +32,24 @@ */ int ath5k_hw_set_capabilities(struct ath5k_hw *ah) { + struct ath5k_capabilities *caps = &ah->ah_capabilities; u16 ee_header; /* Capabilities stored in the EEPROM */ - ee_header = ah->ah_capabilities.cap_eeprom.ee_header; + ee_header = caps->cap_eeprom.ee_header; if (ah->ah_version == AR5K_AR5210) { /* * Set radio capabilities * (The AR5110 only supports the middle 5GHz band) */ - ah->ah_capabilities.cap_range.range_5ghz_min = 5120; - ah->ah_capabilities.cap_range.range_5ghz_max = 5430; - ah->ah_capabilities.cap_range.range_2ghz_min = 0; - ah->ah_capabilities.cap_range.range_2ghz_max = 0; + caps->cap_range.range_5ghz_min = 5120; + caps->cap_range.range_5ghz_max = 5430; + caps->cap_range.range_2ghz_min = 0; + caps->cap_range.range_2ghz_max = 0; /* Set supported modes */ - __set_bit(AR5K_MODE_11A, ah->ah_capabilities.cap_mode); + __set_bit(AR5K_MODE_11A, caps->cap_mode); } else { /* * XXX The tranceiver supports frequencies from 4920 to 6100GHz @@ -56,9 +57,8 @@ int ath5k_hw_set_capabilities(struct ath5k_hw *ah) * XXX current ieee80211 implementation because the IEEE * XXX channel mapping does not support negative channel * XXX numbers (2312MHz is channel -19). Of course, this - * XXX doesn't matter because these channels are out of range - * XXX but some regulation domains like MKK (Japan) will - * XXX support frequencies somewhere around 4.8GHz. + * XXX doesn't matter because these channels are out of the + * XXX legal range. */ /* @@ -66,13 +66,14 @@ int ath5k_hw_set_capabilities(struct ath5k_hw *ah) */ if (AR5K_EEPROM_HDR_11A(ee_header)) { - /* 4920 */ - ah->ah_capabilities.cap_range.range_5ghz_min = 5005; - ah->ah_capabilities.cap_range.range_5ghz_max = 6100; + if (ath_is_49ghz_allowed(caps->cap_eeprom.ee_regdomain)) + caps->cap_range.range_5ghz_min = 4920; + else + caps->cap_range.range_5ghz_min = 5005; + caps->cap_range.range_5ghz_max = 6100; /* Set supported modes */ - __set_bit(AR5K_MODE_11A, - ah->ah_capabilities.cap_mode); + __set_bit(AR5K_MODE_11A, caps->cap_mode); } /* Enable 802.11b if a 2GHz capable radio (2111/5112) is @@ -81,32 +82,29 @@ int ath5k_hw_set_capabilities(struct ath5k_hw *ah) (AR5K_EEPROM_HDR_11G(ee_header) && ah->ah_version != AR5K_AR5211)) { /* 2312 */ - ah->ah_capabilities.cap_range.range_2ghz_min = 2412; - ah->ah_capabilities.cap_range.range_2ghz_max = 2732; + caps->cap_range.range_2ghz_min = 2412; + caps->cap_range.range_2ghz_max = 2732; if (AR5K_EEPROM_HDR_11B(ee_header)) - __set_bit(AR5K_MODE_11B, - ah->ah_capabilities.cap_mode); + __set_bit(AR5K_MODE_11B, caps->cap_mode); if (AR5K_EEPROM_HDR_11G(ee_header) && ah->ah_version != AR5K_AR5211) - __set_bit(AR5K_MODE_11G, - ah->ah_capabilities.cap_mode); + __set_bit(AR5K_MODE_11G, caps->cap_mode); } } /* Set number of supported TX queues */ if (ah->ah_version == AR5K_AR5210) - ah->ah_capabilities.cap_queues.q_tx_num = - AR5K_NUM_TX_QUEUES_NOQCU; + caps->cap_queues.q_tx_num = AR5K_NUM_TX_QUEUES_NOQCU; else - ah->ah_capabilities.cap_queues.q_tx_num = AR5K_NUM_TX_QUEUES; + caps->cap_queues.q_tx_num = AR5K_NUM_TX_QUEUES; /* newer hardware has PHY error counters */ if (ah->ah_mac_srev >= AR5K_SREV_AR5213A) - ah->ah_capabilities.cap_has_phyerr_counters = true; + caps->cap_has_phyerr_counters = true; else - ah->ah_capabilities.cap_has_phyerr_counters = false; + caps->cap_has_phyerr_counters = false; return 0; } diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c index d2f84d7..0230f30 100644 --- a/drivers/net/wireless/ath/ath5k/debug.c +++ b/drivers/net/wireless/ath/ath5k/debug.c @@ -308,8 +308,6 @@ static const struct { { ATH5K_DEBUG_CALIBRATE, "calib", "periodic calibration" }, { ATH5K_DEBUG_TXPOWER, "txpower", "transmit power setting" }, { ATH5K_DEBUG_LED, "led", "LED management" }, - { ATH5K_DEBUG_DUMP_RX, "dumprx", "print received skb content" }, - { ATH5K_DEBUG_DUMP_TX, "dumptx", "print transmit skb content" }, { ATH5K_DEBUG_DUMPBANDS, "dumpbands", "dump bands" }, { ATH5K_DEBUG_DMA, "dma", "dma start/stop" }, { ATH5K_DEBUG_ANI, "ani", "adaptive noise immunity" }, @@ -1036,24 +1034,6 @@ ath5k_debug_printrxbuffs(struct ath5k_softc *sc, struct ath5k_hw *ah) } void -ath5k_debug_dump_skb(struct ath5k_softc *sc, - struct sk_buff *skb, const char *prefix, int tx) -{ - char buf[16]; - - if (likely(!((tx && (sc->debug.level & ATH5K_DEBUG_DUMP_TX)) || - (!tx && (sc->debug.level & ATH5K_DEBUG_DUMP_RX))))) - return; - - snprintf(buf, sizeof(buf), "%s %s", wiphy_name(sc->hw->wiphy), prefix); - - print_hex_dump_bytes(buf, DUMP_PREFIX_NONE, skb->data, - min(200U, skb->len)); - - printk(KERN_DEBUG "\n"); -} - -void ath5k_debug_printtxbuf(struct ath5k_softc *sc, struct ath5k_buf *bf) { struct ath5k_desc *ds = bf->desc; diff --git a/drivers/net/wireless/ath/ath5k/debug.h b/drivers/net/wireless/ath/ath5k/debug.h index 3e34428..b0355ae 100644 --- a/drivers/net/wireless/ath/ath5k/debug.h +++ b/drivers/net/wireless/ath/ath5k/debug.h @@ -116,8 +116,6 @@ enum ath5k_debug_level { ATH5K_DEBUG_CALIBRATE = 0x00000020, ATH5K_DEBUG_TXPOWER = 0x00000040, ATH5K_DEBUG_LED = 0x00000080, - ATH5K_DEBUG_DUMP_RX = 0x00000100, - ATH5K_DEBUG_DUMP_TX = 0x00000200, ATH5K_DEBUG_DUMPBANDS = 0x00000400, ATH5K_DEBUG_DMA = 0x00000800, ATH5K_DEBUG_ANI = 0x00002000, @@ -152,10 +150,6 @@ void ath5k_debug_dump_bands(struct ath5k_softc *sc); void -ath5k_debug_dump_skb(struct ath5k_softc *sc, - struct sk_buff *skb, const char *prefix, int tx); - -void ath5k_debug_printtxbuf(struct ath5k_softc *sc, struct ath5k_buf *bf); #else /* no debugging */ @@ -182,10 +176,6 @@ static inline void ath5k_debug_dump_bands(struct ath5k_softc *sc) {} static inline void -ath5k_debug_dump_skb(struct ath5k_softc *sc, - struct sk_buff *skb, const char *prefix, int tx) {} - -static inline void ath5k_debug_printtxbuf(struct ath5k_softc *sc, struct ath5k_buf *bf) {} #endif /* ifdef CONFIG_ATH5K_DEBUG */ diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c index 80e6256..b6561f7 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.c +++ b/drivers/net/wireless/ath/ath5k/eeprom.c @@ -72,7 +72,6 @@ static int ath5k_eeprom_init_header(struct ath5k_hw *ah) { struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; - int ret; u16 val; u32 cksum, offset, eep_max = AR5K_EEPROM_INFO_MAX; @@ -192,7 +191,7 @@ static int ath5k_eeprom_read_ants(struct ath5k_hw *ah, u32 *offset, struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; u32 o = *offset; u16 val; - int ret, i = 0; + int i = 0; AR5K_EEPROM_READ(o++, val); ee->ee_switch_settling[mode] = (val >> 8) & 0x7f; @@ -252,7 +251,6 @@ static int ath5k_eeprom_read_modes(struct ath5k_hw *ah, u32 *offset, struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; u32 o = *offset; u16 val; - int ret; ee->ee_n_piers[mode] = 0; AR5K_EEPROM_READ(o++, val); @@ -515,7 +513,6 @@ ath5k_eeprom_read_freq_list(struct ath5k_hw *ah, int *offset, int max, int o = *offset; int i = 0; u8 freq1, freq2; - int ret; u16 val; ee->ee_n_piers[mode] = 0; @@ -551,7 +548,7 @@ ath5k_eeprom_init_11a_pcal_freq(struct ath5k_hw *ah, int offset) { struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; struct ath5k_chan_pcal_info *pcal = ee->ee_pwr_cal_a; - int i, ret; + int i; u16 val; u8 mask; @@ -970,7 +967,6 @@ ath5k_eeprom_read_pcal_info_5112(struct ath5k_hw *ah, int mode) u32 offset; u8 i, c; u16 val; - int ret; u8 pd_gains = 0; /* Count how many curves we have and @@ -1228,7 +1224,7 @@ ath5k_eeprom_read_pcal_info_2413(struct ath5k_hw *ah, int mode) struct ath5k_chan_pcal_info *chinfo; u8 *pdgain_idx = ee->ee_pdc_to_idx[mode]; u32 offset; - int idx, i, ret; + int idx, i; u16 val; u8 pd_gains = 0; @@ -1419,7 +1415,7 @@ ath5k_eeprom_read_target_rate_pwr_info(struct ath5k_hw *ah, unsigned int mode) u8 *rate_target_pwr_num; u32 offset; u16 val; - int ret, i; + int i; offset = AR5K_EEPROM_TARGET_PWRSTART(ee->ee_misc1); rate_target_pwr_num = &ee->ee_rate_target_pwr_num[mode]; @@ -1593,7 +1589,7 @@ ath5k_eeprom_read_ctl_info(struct ath5k_hw *ah) struct ath5k_edge_power *rep; unsigned int fmask, pmask; unsigned int ctl_mode; - int ret, i, j; + int i, j; u32 offset; u16 val; @@ -1733,16 +1729,12 @@ int ath5k_eeprom_read_mac(struct ath5k_hw *ah, u8 *mac) u8 mac_d[ETH_ALEN] = {}; u32 total, offset; u16 data; - int octet, ret; + int octet; - ret = ath5k_hw_nvram_read(ah, 0x20, &data); - if (ret) - return ret; + AR5K_EEPROM_READ(0x20, data); for (offset = 0x1f, octet = 0, total = 0; offset >= 0x1d; offset--) { - ret = ath5k_hw_nvram_read(ah, offset, &data); - if (ret) - return ret; + AR5K_EEPROM_READ(offset, data); total += data; mac_d[octet + 1] = data & 0xff; diff --git a/drivers/net/wireless/ath/ath5k/eeprom.h b/drivers/net/wireless/ath/ath5k/eeprom.h index 7c09e15..6511c27 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.h +++ b/drivers/net/wireless/ath/ath5k/eeprom.h @@ -241,9 +241,8 @@ enum ath5k_eeprom_freq_bands{ #define AR5K_SPUR_SYMBOL_WIDTH_TURBO_100Hz 6250 #define AR5K_EEPROM_READ(_o, _v) do { \ - ret = ath5k_hw_nvram_read(ah, (_o), &(_v)); \ - if (ret) \ - return ret; \ + if (!ath5k_hw_nvram_read(ah, (_o), &(_v))) \ + return -EIO; \ } while (0) #define AR5K_EEPROM_READ_HDR(_o, _v) \ @@ -269,29 +268,6 @@ enum ath5k_ctl_mode { AR5K_CTL_MODE_M = 15, }; -/* Default CTL ids for the 3 main reg domains. - * Atheros only uses these by default but vendors - * can have up to 32 different CTLs for different - * scenarios. Note that theese values are ORed with - * the mode id (above) so we can have up to 24 CTL - * datasets out of these 3 main regdomains. That leaves - * 8 ids that can be used by vendors and since 0x20 is - * missing from HAL sources i guess this is the set of - * custom CTLs vendors can use. */ -#define AR5K_CTL_FCC 0x10 -#define AR5K_CTL_CUSTOM 0x20 -#define AR5K_CTL_ETSI 0x30 -#define AR5K_CTL_MKK 0x40 - -/* Indicates a CTL with only mode set and - * no reg domain mapping, such CTLs are used - * for world roaming domains or simply when - * a reg domain is not set */ -#define AR5K_CTL_NO_REGDOMAIN 0xf0 - -/* Indicates an empty (invalid) CTL */ -#define AR5K_CTL_NO_CTL 0xff - /* Per channel calibration data, used for power table setup */ struct ath5k_chan_pcal_info_rf5111 { /* Power levels in half dbm units diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c index d76d68c..36a5199 100644 --- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c +++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c @@ -226,6 +226,7 @@ ath5k_config(struct ieee80211_hw *hw, u32 changed) struct ath5k_hw *ah = sc->ah; struct ieee80211_conf *conf = &hw->conf; int ret = 0; + int i; mutex_lock(&sc->lock); @@ -243,6 +244,14 @@ ath5k_config(struct ieee80211_hw *hw, u32 changed) ath5k_hw_set_txpower_limit(ah, (conf->power_level * 2)); } + if (changed & IEEE80211_CONF_CHANGE_RETRY_LIMITS) { + ah->ah_retry_long = conf->long_frame_max_tx_count; + ah->ah_retry_short = conf->short_frame_max_tx_count; + + for (i = 0; i < ah->ah_capabilities.cap_queues.q_tx_num; i++) + ath5k_hw_set_tx_retry_limits(ah, i); + } + /* TODO: * 1) Move this on config_interface and handle each case * separately eg. when we have only one STA vif, use diff --git a/drivers/net/wireless/ath/ath5k/pci.c b/drivers/net/wireless/ath/ath5k/pci.c index 7f8c5b0..66598a0 100644 --- a/drivers/net/wireless/ath/ath5k/pci.c +++ b/drivers/net/wireless/ath/ath5k/pci.c @@ -69,7 +69,8 @@ static void ath5k_pci_read_cachesize(struct ath_common *common, int *csz) /* * Read from eeprom */ -bool ath5k_pci_eeprom_read(struct ath_common *common, u32 offset, u16 *data) +static bool +ath5k_pci_eeprom_read(struct ath_common *common, u32 offset, u16 *data) { struct ath5k_hw *ah = (struct ath5k_hw *) common->ah; u32 status, timeout; @@ -90,15 +91,15 @@ bool ath5k_pci_eeprom_read(struct ath_common *common, u32 offset, u16 *data) status = ath5k_hw_reg_read(ah, AR5K_EEPROM_STATUS); if (status & AR5K_EEPROM_STAT_RDDONE) { if (status & AR5K_EEPROM_STAT_RDERR) - return -EIO; + return false; *data = (u16)(ath5k_hw_reg_read(ah, AR5K_EEPROM_DATA) & 0xffff); - return 0; + return true; } udelay(15); } - return -ETIMEDOUT; + return false; } int ath5k_hw_read_srev(struct ath5k_hw *ah) diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c index 78c26fd..d673ab2 100644 --- a/drivers/net/wireless/ath/ath5k/phy.c +++ b/drivers/net/wireless/ath/ath5k/phy.c @@ -282,6 +282,34 @@ int ath5k_hw_phy_disable(struct ath5k_hw *ah) return 0; } +/* + * Wait for synth to settle + */ +static void ath5k_hw_wait_for_synth(struct ath5k_hw *ah, + struct ieee80211_channel *channel) +{ + /* + * On 5211+ read activation -> rx delay + * and use it (100ns steps). + */ + if (ah->ah_version != AR5K_AR5210) { + u32 delay; + delay = ath5k_hw_reg_read(ah, AR5K_PHY_RX_DELAY) & + AR5K_PHY_RX_DELAY_M; + delay = (channel->hw_value & CHANNEL_CCK) ? + ((delay << 2) / 22) : (delay / 10); + if (ah->ah_bwmode == AR5K_BWMODE_10MHZ) + delay = delay << 1; + if (ah->ah_bwmode == AR5K_BWMODE_5MHZ) + delay = delay << 2; + /* XXX: /2 on turbo ? Let's be safe + * for now */ + udelay(100 + delay); + } else { + mdelay(1); + } +} + /**********************\ * RF Gain optimization * @@ -3237,6 +3265,13 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, /* Failed */ if (i >= 100) return -EIO; + + /* Set channel and wait for synth */ + ret = ath5k_hw_channel(ah, channel); + if (ret) + return ret; + + ath5k_hw_wait_for_synth(ah, channel); } /* @@ -3251,13 +3286,53 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, if (ret) return ret; + /* Write OFDM timings on 5212*/ + if (ah->ah_version == AR5K_AR5212 && + channel->hw_value & CHANNEL_OFDM) { + + ret = ath5k_hw_write_ofdm_timings(ah, channel); + if (ret) + return ret; + + /* Spur info is available only from EEPROM versions + * greater than 5.3, but the EEPROM routines will use + * static values for older versions */ + if (ah->ah_mac_srev >= AR5K_SREV_AR5424) + ath5k_hw_set_spur_mitigation_filter(ah, + channel); + } + + /* If we used fast channel switching + * we are done, release RF bus and + * fire up NF calibration. + * + * Note: Only NF calibration due to + * channel change, not AGC calibration + * since AGC is still running ! + */ + if (fast) { + /* + * Release RF Bus grant + */ + AR5K_REG_DISABLE_BITS(ah, AR5K_PHY_RFBUS_REQ, + AR5K_PHY_RFBUS_REQ_REQUEST); + + /* + * Start NF calibration + */ + AR5K_REG_ENABLE_BITS(ah, AR5K_PHY_AGCCTL, + AR5K_PHY_AGCCTL_NF); + + return ret; + } + /* * For 5210 we do all initialization using * initvals, so we don't have to modify * any settings (5210 also only supports * a/aturbo modes) */ - if ((ah->ah_version != AR5K_AR5210) && !fast) { + if (ah->ah_version != AR5K_AR5210) { /* * Write initial RF gain settings @@ -3276,22 +3351,6 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, if (ret) return ret; - /* Write OFDM timings on 5212*/ - if (ah->ah_version == AR5K_AR5212 && - channel->hw_value & CHANNEL_OFDM) { - - ret = ath5k_hw_write_ofdm_timings(ah, channel); - if (ret) - return ret; - - /* Spur info is available only from EEPROM versions - * greater than 5.3, but the EEPROM routines will use - * static values for older versions */ - if (ah->ah_mac_srev >= AR5K_SREV_AR5424) - ath5k_hw_set_spur_mitigation_filter(ah, - channel); - } - /*Enable/disable 802.11b mode on 5111 (enable 2111 frequency converter + CCK)*/ if (ah->ah_radio == AR5K_RF5111) { @@ -3322,47 +3381,20 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, */ ath5k_hw_reg_write(ah, AR5K_PHY_ACT_ENABLE, AR5K_PHY_ACT); + ath5k_hw_wait_for_synth(ah, channel); + /* - * On 5211+ read activation -> rx delay - * and use it. + * Perform ADC test to see if baseband is ready + * Set tx hold and check adc test register */ - if (ah->ah_version != AR5K_AR5210) { - u32 delay; - delay = ath5k_hw_reg_read(ah, AR5K_PHY_RX_DELAY) & - AR5K_PHY_RX_DELAY_M; - delay = (channel->hw_value & CHANNEL_CCK) ? - ((delay << 2) / 22) : (delay / 10); - if (ah->ah_bwmode == AR5K_BWMODE_10MHZ) - delay = delay << 1; - if (ah->ah_bwmode == AR5K_BWMODE_5MHZ) - delay = delay << 2; - /* XXX: /2 on turbo ? Let's be safe - * for now */ - udelay(100 + delay); - } else { - mdelay(1); - } - - if (fast) - /* - * Release RF Bus grant - */ - AR5K_REG_DISABLE_BITS(ah, AR5K_PHY_RFBUS_REQ, - AR5K_PHY_RFBUS_REQ_REQUEST); - else { - /* - * Perform ADC test to see if baseband is ready - * Set tx hold and check adc test register - */ - phy_tst1 = ath5k_hw_reg_read(ah, AR5K_PHY_TST1); - ath5k_hw_reg_write(ah, AR5K_PHY_TST1_TXHOLD, AR5K_PHY_TST1); - for (i = 0; i <= 20; i++) { - if (!(ath5k_hw_reg_read(ah, AR5K_PHY_ADC_TEST) & 0x10)) - break; - udelay(200); - } - ath5k_hw_reg_write(ah, phy_tst1, AR5K_PHY_TST1); + phy_tst1 = ath5k_hw_reg_read(ah, AR5K_PHY_TST1); + ath5k_hw_reg_write(ah, AR5K_PHY_TST1_TXHOLD, AR5K_PHY_TST1); + for (i = 0; i <= 20; i++) { + if (!(ath5k_hw_reg_read(ah, AR5K_PHY_ADC_TEST) & 0x10)) + break; + udelay(200); } + ath5k_hw_reg_write(ah, phy_tst1, AR5K_PHY_TST1); /* * Start automatic gain control calibration diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c index 2c9c9e7..3343fb9 100644 --- a/drivers/net/wireless/ath/ath5k/qcu.c +++ b/drivers/net/wireless/ath/ath5k/qcu.c @@ -228,24 +228,9 @@ int ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type, /* * Set tx retry limits on DCU */ -static void ath5k_hw_set_tx_retry_limits(struct ath5k_hw *ah, - unsigned int queue) +void ath5k_hw_set_tx_retry_limits(struct ath5k_hw *ah, + unsigned int queue) { - u32 retry_lg, retry_sh; - - /* - * Calculate and set retry limits - */ - if (ah->ah_software_retry) { - /* XXX Need to test this */ - retry_lg = ah->ah_limit_tx_retries; - retry_sh = retry_lg = retry_lg > AR5K_DCU_RETRY_LMT_SH_RETRY ? - AR5K_DCU_RETRY_LMT_SH_RETRY : retry_lg; - } else { - retry_lg = AR5K_INIT_LG_RETRY; - retry_sh = AR5K_INIT_SH_RETRY; - } - /* Single data queue on AR5210 */ if (ah->ah_version == AR5K_AR5210) { struct ath5k_txq_info *tq = &ah->ah_txq[queue]; @@ -255,25 +240,26 @@ static void ath5k_hw_set_tx_retry_limits(struct ath5k_hw *ah, ath5k_hw_reg_write(ah, (tq->tqi_cw_min << AR5K_NODCU_RETRY_LMT_CW_MIN_S) - | AR5K_REG_SM(AR5K_INIT_SLG_RETRY, - AR5K_NODCU_RETRY_LMT_SLG_RETRY) - | AR5K_REG_SM(AR5K_INIT_SSH_RETRY, - AR5K_NODCU_RETRY_LMT_SSH_RETRY) - | AR5K_REG_SM(retry_lg, AR5K_NODCU_RETRY_LMT_LG_RETRY) - | AR5K_REG_SM(retry_sh, AR5K_NODCU_RETRY_LMT_SH_RETRY), + | AR5K_REG_SM(ah->ah_retry_long, + AR5K_NODCU_RETRY_LMT_SLG_RETRY) + | AR5K_REG_SM(ah->ah_retry_short, + AR5K_NODCU_RETRY_LMT_SSH_RETRY) + | AR5K_REG_SM(ah->ah_retry_long, + AR5K_NODCU_RETRY_LMT_LG_RETRY) + | AR5K_REG_SM(ah->ah_retry_short, + AR5K_NODCU_RETRY_LMT_SH_RETRY), AR5K_NODCU_RETRY_LMT); /* DCU on AR5211+ */ } else { ath5k_hw_reg_write(ah, - AR5K_REG_SM(AR5K_INIT_SLG_RETRY, - AR5K_DCU_RETRY_LMT_SLG_RETRY) | - AR5K_REG_SM(AR5K_INIT_SSH_RETRY, - AR5K_DCU_RETRY_LMT_SSH_RETRY) | - AR5K_REG_SM(retry_lg, AR5K_DCU_RETRY_LMT_LG_RETRY) | - AR5K_REG_SM(retry_sh, AR5K_DCU_RETRY_LMT_SH_RETRY), + AR5K_REG_SM(ah->ah_retry_long, + AR5K_DCU_RETRY_LMT_RTS) + | AR5K_REG_SM(ah->ah_retry_long, + AR5K_DCU_RETRY_LMT_STA_RTS) + | AR5K_REG_SM(max(ah->ah_retry_long, ah->ah_retry_short), + AR5K_DCU_RETRY_LMT_STA_DATA), AR5K_QUEUE_DFS_RETRY_LIMIT(queue)); } - return; } /** diff --git a/drivers/net/wireless/ath/ath5k/reg.h b/drivers/net/wireless/ath/ath5k/reg.h index fd14b91..e1c9abd 100644 --- a/drivers/net/wireless/ath/ath5k/reg.h +++ b/drivers/net/wireless/ath/ath5k/reg.h @@ -686,16 +686,15 @@ /* * DCU retry limit registers + * all these fields don't allow zero values */ #define AR5K_DCU_RETRY_LMT_BASE 0x1080 /* Register Address -Queue0 DCU_RETRY_LMT */ -#define AR5K_DCU_RETRY_LMT_SH_RETRY 0x0000000f /* Short retry limit mask */ -#define AR5K_DCU_RETRY_LMT_SH_RETRY_S 0 -#define AR5K_DCU_RETRY_LMT_LG_RETRY 0x000000f0 /* Long retry limit mask */ -#define AR5K_DCU_RETRY_LMT_LG_RETRY_S 4 -#define AR5K_DCU_RETRY_LMT_SSH_RETRY 0x00003f00 /* Station short retry limit mask (?) */ -#define AR5K_DCU_RETRY_LMT_SSH_RETRY_S 8 -#define AR5K_DCU_RETRY_LMT_SLG_RETRY 0x000fc000 /* Station long retry limit mask (?) */ -#define AR5K_DCU_RETRY_LMT_SLG_RETRY_S 14 +#define AR5K_DCU_RETRY_LMT_RTS 0x0000000f /* RTS failure limit. Transmission fails if no CTS is received for this number of times */ +#define AR5K_DCU_RETRY_LMT_RTS_S 0 +#define AR5K_DCU_RETRY_LMT_STA_RTS 0x00003f00 /* STA RTS failure limit. If exceeded CW reset */ +#define AR5K_DCU_RETRY_LMT_STA_RTS_S 8 +#define AR5K_DCU_RETRY_LMT_STA_DATA 0x000fc000 /* STA data failure limit. If exceeded CW reset. */ +#define AR5K_DCU_RETRY_LMT_STA_DATA_S 14 #define AR5K_QUEUE_DFS_RETRY_LIMIT(_q) AR5K_QUEUE_REG(AR5K_DCU_RETRY_LMT_BASE, _q) /* diff --git a/drivers/net/wireless/ath/ath5k/trace.h b/drivers/net/wireless/ath/ath5k/trace.h new file mode 100644 index 0000000..2de68ad --- /dev/null +++ b/drivers/net/wireless/ath/ath5k/trace.h @@ -0,0 +1,107 @@ +#if !defined(__TRACE_ATH5K_H) || defined(TRACE_HEADER_MULTI_READ) +#define __TRACE_ATH5K_H + +#include <linux/tracepoint.h> +#include "base.h" + +#ifndef CONFIG_ATH5K_TRACER +#undef TRACE_EVENT +#define TRACE_EVENT(name, proto, ...) \ +static inline void trace_ ## name(proto) {} +#endif + +struct sk_buff; + +#define PRIV_ENTRY __field(struct ath5k_softc *, priv) +#define PRIV_ASSIGN __entry->priv = priv + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ath5k + +TRACE_EVENT(ath5k_rx, + TP_PROTO(struct ath5k_softc *priv, struct sk_buff *skb), + TP_ARGS(priv, skb), + TP_STRUCT__entry( + PRIV_ENTRY + __field(unsigned long, skbaddr) + __dynamic_array(u8, frame, skb->len) + ), + TP_fast_assign( + PRIV_ASSIGN; + __entry->skbaddr = (unsigned long) skb; + memcpy(__get_dynamic_array(frame), skb->data, skb->len); + ), + TP_printk( + "[%p] RX skb=%lx", __entry->priv, __entry->skbaddr + ) +); + +TRACE_EVENT(ath5k_tx, + TP_PROTO(struct ath5k_softc *priv, struct sk_buff *skb, + struct ath5k_txq *q), + + TP_ARGS(priv, skb, q), + + TP_STRUCT__entry( + PRIV_ENTRY + __field(unsigned long, skbaddr) + __field(u8, qnum) + __dynamic_array(u8, frame, skb->len) + ), + + TP_fast_assign( + PRIV_ASSIGN; + __entry->skbaddr = (unsigned long) skb; + __entry->qnum = (u8) q->qnum; + memcpy(__get_dynamic_array(frame), skb->data, skb->len); + ), + + TP_printk( + "[%p] TX skb=%lx q=%d", __entry->priv, __entry->skbaddr, + __entry->qnum + ) +); + +TRACE_EVENT(ath5k_tx_complete, + TP_PROTO(struct ath5k_softc *priv, struct sk_buff *skb, + struct ath5k_txq *q, struct ath5k_tx_status *ts), + + TP_ARGS(priv, skb, q, ts), + + TP_STRUCT__entry( + PRIV_ENTRY + __field(unsigned long, skbaddr) + __field(u8, qnum) + __field(u8, ts_status) + __field(s8, ts_rssi) + __field(u8, ts_antenna) + ), + + TP_fast_assign( + PRIV_ASSIGN; + __entry->skbaddr = (unsigned long) skb; + __entry->qnum = (u8) q->qnum; + __entry->ts_status = ts->ts_status; + __entry->ts_rssi = ts->ts_rssi; + __entry->ts_antenna = ts->ts_antenna; + ), + + TP_printk( + "[%p] TX end skb=%lx q=%d stat=%x rssi=%d ant=%x", + __entry->priv, __entry->skbaddr, __entry->qnum, + __entry->ts_status, __entry->ts_rssi, __entry->ts_antenna + ) +); + +#endif /* __TRACE_ATH5K_H */ + +#ifdef CONFIG_ATH5K_TRACER + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../../drivers/net/wireless/ath/ath5k +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +#include <trace/define_trace.h> + +#endif diff --git a/drivers/net/wireless/ath/ath9k/Makefile b/drivers/net/wireless/ath/ath9k/Makefile index aca0162..4d66ca8 100644 --- a/drivers/net/wireless/ath/ath9k/Makefile +++ b/drivers/net/wireless/ath/ath9k/Makefile @@ -4,7 +4,6 @@ ath9k-y += beacon.o \ main.o \ recv.o \ xmit.o \ - virtual.o \ ath9k-$(CONFIG_ATH9K_RATE_CONTROL) += rc.o ath9k-$(CONFIG_PCI) += pci.o diff --git a/drivers/net/wireless/ath/ath9k/ahb.c b/drivers/net/wireless/ath/ath9k/ahb.c index 25a6e44..9936721 100644 --- a/drivers/net/wireless/ath/ath9k/ahb.c +++ b/drivers/net/wireless/ath/ath9k/ahb.c @@ -54,7 +54,6 @@ static struct ath_bus_ops ath_ahb_bus_ops = { static int ath_ahb_probe(struct platform_device *pdev) { void __iomem *mem; - struct ath_wiphy *aphy; struct ath_softc *sc; struct ieee80211_hw *hw; struct resource *res; @@ -92,8 +91,7 @@ static int ath_ahb_probe(struct platform_device *pdev) irq = res->start; - hw = ieee80211_alloc_hw(sizeof(struct ath_wiphy) + - sizeof(struct ath_softc), &ath9k_ops); + hw = ieee80211_alloc_hw(sizeof(struct ath_softc), &ath9k_ops); if (hw == NULL) { dev_err(&pdev->dev, "no memory for ieee80211_hw\n"); ret = -ENOMEM; @@ -103,11 +101,7 @@ static int ath_ahb_probe(struct platform_device *pdev) SET_IEEE80211_DEV(hw, &pdev->dev); platform_set_drvdata(pdev, hw); - aphy = hw->priv; - sc = (struct ath_softc *) (aphy + 1); - aphy->sc = sc; - aphy->hw = hw; - sc->pri_wiphy = aphy; + sc = hw->priv; sc->hw = hw; sc->dev = &pdev->dev; sc->mem = mem; @@ -151,8 +145,7 @@ static int ath_ahb_remove(struct platform_device *pdev) struct ieee80211_hw *hw = platform_get_drvdata(pdev); if (hw) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; void __iomem *mem = sc->mem; ath9k_deinit_device(sc); diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c index 5e300bd..76388c6 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c @@ -805,7 +805,10 @@ static bool ar9002_hw_init_cal(struct ath_hw *ah, struct ath9k_channel *chan) { struct ath_common *common = ath9k_hw_common(ah); - if (AR_SREV_9271(ah) || AR_SREV_9285_12_OR_LATER(ah)) { + if (AR_SREV_9271(ah)) { + if (!ar9285_hw_cl_cal(ah, chan)) + return false; + } else if (AR_SREV_9285_12_OR_LATER(ah)) { if (!ar9285_hw_clc(ah, chan)) return false; } else { diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index 4819747..4a92718 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -3673,7 +3673,7 @@ static void ar9003_hw_internal_regulator_apply(struct ath_hw *ah) return; reg_pmu_set = (5 << 1) | (7 << 4) | (1 << 8) | - (7 << 14) | (6 << 17) | (1 << 20) | + (2 << 14) | (6 << 17) | (1 << 20) | (3 << 24) | (1 << 28); REG_WRITE(ah, AR_PHY_PMU1, reg_pmu_set); @@ -3959,19 +3959,19 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) { #define POW_SM(_r, _s) (((_r) & 0x3f) << (_s)) /* make sure forced gain is not set */ - REG_WRITE(ah, 0xa458, 0); + REG_WRITE(ah, AR_PHY_TX_FORCED_GAIN, 0); /* Write the OFDM power per rate set */ /* 6 (LSB), 9, 12, 18 (MSB) */ - REG_WRITE(ah, 0xa3c0, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(0), POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 16) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 8) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 0)); /* 24 (LSB), 36, 48, 54 (MSB) */ - REG_WRITE(ah, 0xa3c4, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(1), POW_SM(pPwrArray[ALL_TARGET_LEGACY_54], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_48], 16) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_36], 8) | @@ -3980,14 +3980,14 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) /* Write the CCK power per rate set */ /* 1L (LSB), reserved, 2L, 2S (MSB) */ - REG_WRITE(ah, 0xa3c8, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(2), POW_SM(pPwrArray[ALL_TARGET_LEGACY_1L_5L], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_1L_5L], 16) | /* POW_SM(txPowerTimes2, 8) | this is reserved for AR9003 */ POW_SM(pPwrArray[ALL_TARGET_LEGACY_1L_5L], 0)); /* 5.5L (LSB), 5.5S, 11L, 11S (MSB) */ - REG_WRITE(ah, 0xa3cc, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(3), POW_SM(pPwrArray[ALL_TARGET_LEGACY_11S], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_11L], 16) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_5S], 8) | @@ -3997,7 +3997,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) /* Write the HT20 power per rate set */ /* 0/8/16 (LSB), 1-3/9-11/17-19, 4, 5 (MSB) */ - REG_WRITE(ah, 0xa3d0, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(4), POW_SM(pPwrArray[ALL_TARGET_HT20_5], 24) | POW_SM(pPwrArray[ALL_TARGET_HT20_4], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_1_3_9_11_17_19], 8) | @@ -4005,7 +4005,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 6 (LSB), 7, 12, 13 (MSB) */ - REG_WRITE(ah, 0xa3d4, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(5), POW_SM(pPwrArray[ALL_TARGET_HT20_13], 24) | POW_SM(pPwrArray[ALL_TARGET_HT20_12], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_7], 8) | @@ -4013,7 +4013,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 14 (LSB), 15, 20, 21 */ - REG_WRITE(ah, 0xa3e4, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(9), POW_SM(pPwrArray[ALL_TARGET_HT20_21], 24) | POW_SM(pPwrArray[ALL_TARGET_HT20_20], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_15], 8) | @@ -4023,7 +4023,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) /* Mixed HT20 and HT40 rates */ /* HT20 22 (LSB), HT20 23, HT40 22, HT40 23 (MSB) */ - REG_WRITE(ah, 0xa3e8, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(10), POW_SM(pPwrArray[ALL_TARGET_HT40_23], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_22], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_23], 8) | @@ -4035,7 +4035,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) * correct PAR difference between HT40 and HT20/LEGACY * 0/8/16 (LSB), 1-3/9-11/17-19, 4, 5 (MSB) */ - REG_WRITE(ah, 0xa3d8, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(6), POW_SM(pPwrArray[ALL_TARGET_HT40_5], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_4], 16) | POW_SM(pPwrArray[ALL_TARGET_HT40_1_3_9_11_17_19], 8) | @@ -4043,7 +4043,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 6 (LSB), 7, 12, 13 (MSB) */ - REG_WRITE(ah, 0xa3dc, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(7), POW_SM(pPwrArray[ALL_TARGET_HT40_13], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_12], 16) | POW_SM(pPwrArray[ALL_TARGET_HT40_7], 8) | @@ -4051,7 +4051,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 14 (LSB), 15, 20, 21 */ - REG_WRITE(ah, 0xa3ec, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(11), POW_SM(pPwrArray[ALL_TARGET_HT40_21], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_20], 16) | POW_SM(pPwrArray[ALL_TARGET_HT40_15], 8) | diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c index 4ceddbb..038a0cb 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c @@ -615,7 +615,7 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs, */ if (rxsp->status11 & AR_CRCErr) rxs->rs_status |= ATH9K_RXERR_CRC; - if (rxsp->status11 & AR_PHYErr) { + else if (rxsp->status11 & AR_PHYErr) { phyerr = MS(rxsp->status11, AR_PHYErrCode); /* * If we reach a point here where AR_PostDelimCRCErr is @@ -638,11 +638,11 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs, rxs->rs_phyerr = phyerr; } - } - if (rxsp->status11 & AR_DecryptCRCErr) + } else if (rxsp->status11 & AR_DecryptCRCErr) rxs->rs_status |= ATH9K_RXERR_DECRYPT; - if (rxsp->status11 & AR_MichaelErr) + else if (rxsp->status11 & AR_MichaelErr) rxs->rs_status |= ATH9K_RXERR_MIC; + if (rxsp->status11 & AR_KeyMiss) rxs->rs_status |= ATH9K_RXERR_DECRYPT; } diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.h b/drivers/net/wireless/ath/ath9k/ar9003_phy.h index 59bab6b..8bdda2c 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.h +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.h @@ -486,6 +486,8 @@ #define AR_PHY_HEAVYCLIP_40 (AR_SM_BASE + 0x1ac) #define AR_PHY_ILLEGAL_TXRATE (AR_SM_BASE + 0x1b0) +#define AR_PHY_POWER_TX_RATE(_d) (AR_SM_BASE + 0x1c0 + ((_d) << 2)) + #define AR_PHY_PWRTX_MAX (AR_SM_BASE + 0x1f0) #define AR_PHY_POWER_TX_SUB (AR_SM_BASE + 0x1f4) diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index 23838e3..9272278 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -95,9 +95,9 @@ struct ath_config { * @BUF_XRETRY: To denote excessive retries of the buffer */ enum buffer_type { - BUF_AMPDU = BIT(2), - BUF_AGGR = BIT(3), - BUF_XRETRY = BIT(5), + BUF_AMPDU = BIT(0), + BUF_AGGR = BIT(1), + BUF_XRETRY = BIT(2), }; #define bf_isampdu(bf) (bf->bf_state.bf_type & BUF_AMPDU) @@ -137,7 +137,6 @@ void ath_descdma_cleanup(struct ath_softc *sc, struct ath_descdma *dd, (((_tid) == 4) || ((_tid) == 5)) ? WME_AC_VI : \ WME_AC_VO) -#define ADDBA_EXCHANGE_ATTEMPTS 10 #define ATH_AGGR_DELIM_SZ 4 #define ATH_AGGR_MINPLEN 256 /* in bytes, minimum packet length */ /* number of delimiters for encryption padding */ @@ -184,7 +183,8 @@ enum ATH_AGGR_STATUS { #define ATH_TXFIFO_DEPTH 8 struct ath_txq { - u32 axq_qnum; + int mac80211_qnum; /* mac80211 queue number, -1 means not mac80211 Q */ + u32 axq_qnum; /* ath9k hardware queue number */ u32 *axq_link; struct list_head axq_q; spinlock_t axq_lock; @@ -234,7 +234,6 @@ struct ath_buf { bool bf_stale; u16 bf_flags; struct ath_buf_state bf_state; - struct ath_wiphy *aphy; }; struct ath_atx_tid { @@ -255,7 +254,10 @@ struct ath_atx_tid { }; struct ath_node { - struct ath_common *common; +#ifdef CONFIG_ATH9K_DEBUGFS + struct list_head list; /* for sc->nodes */ + struct ieee80211_sta *sta; /* station struct we're part of */ +#endif struct ath_atx_tid tid[WME_NUM_TID]; struct ath_atx_ac ac[WME_NUM_AC]; u16 maxampdu; @@ -278,6 +280,11 @@ struct ath_tx_control { #define ATH_TX_XRETRY 0x02 #define ATH_TX_BAR 0x04 +/** + * @txq_map: Index is mac80211 queue number. This is + * not necessarily the same as the hardware queue number + * (axq_qnum). + */ struct ath_tx { u16 seq_no; u32 txqsetup; @@ -304,6 +311,8 @@ struct ath_rx { struct ath_descdma rxdma; struct ath_buf *rx_bufptr; struct ath_rx_edma rx_edma[ATH9K_RX_QUEUE_MAX]; + + struct sk_buff *frag; }; int ath_startrecv(struct ath_softc *sc); @@ -343,7 +352,6 @@ struct ath_vif { __le64 tsf_adjust; /* TSF adjustment for staggered beacons */ enum nl80211_iftype av_opmode; struct ath_buf *av_bcbuf; - struct ath_tx_control av_btxctl; u8 bssid[ETH_ALEN]; /* current BSSID from config_interface */ }; @@ -382,7 +390,6 @@ struct ath_beacon { u32 ast_be_xmit; u64 bc_tstamp; struct ieee80211_vif *bslot[ATH_BCBUF]; - struct ath_wiphy *bslot_aphy[ATH_BCBUF]; int slottime; int slotupdate; struct ath9k_tx_queue_info beacon_qi; @@ -393,7 +400,7 @@ struct ath_beacon { void ath_beacon_tasklet(unsigned long data); void ath_beacon_config(struct ath_softc *sc, struct ieee80211_vif *vif); -int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif); +int ath_beacon_alloc(struct ath_softc *sc, struct ieee80211_vif *vif); void ath_beacon_return(struct ath_softc *sc, struct ath_vif *avp); int ath_beaconq_config(struct ath_softc *sc); @@ -530,7 +537,6 @@ struct ath_ant_comb { #define ATH_CABQ_READY_TIME 80 /* % of beacon interval */ #define ATH_MAX_SW_RETRIES 10 #define ATH_CHAN_MAX 255 -#define IEEE80211_WEP_NKID 4 /* number of key ids */ #define ATH_TXPOWER_MAX 100 /* .5 dBm units */ #define ATH_RATE_DUMMY_MARKER 0 @@ -558,27 +564,28 @@ struct ath_ant_comb { #define PS_WAIT_FOR_TX_ACK BIT(3) #define PS_BEACON_SYNC BIT(4) -struct ath_wiphy; struct ath_rate_table; +struct ath9k_vif_iter_data { + const u8 *hw_macaddr; /* phy's hardware address, set + * before starting iteration for + * valid bssid mask. + */ + u8 mask[ETH_ALEN]; /* bssid mask */ + int naps; /* number of AP vifs */ + int nmeshes; /* number of mesh vifs */ + int nstations; /* number of station vifs */ + int nwds; /* number of nwd vifs */ + int nadhocs; /* number of adhoc vifs */ + int nothers; /* number of vifs not specified above. */ +}; + struct ath_softc { struct ieee80211_hw *hw; struct device *dev; - spinlock_t wiphy_lock; /* spinlock to protect ath_wiphy data */ - struct ath_wiphy *pri_wiphy; - struct ath_wiphy **sec_wiphy; /* secondary wiphys (virtual radios); may - * have NULL entries */ - int num_sec_wiphy; /* number of sec_wiphy pointers in the array */ int chan_idx; int chan_is_ht; - struct ath_wiphy *next_wiphy; - struct work_struct chan_work; - int wiphy_select_failures; - unsigned long wiphy_select_first_fail; - struct delayed_work wiphy_work; - unsigned long wiphy_scheduler_int; - int wiphy_scheduler_index; struct survey_info *cur_survey; struct survey_info survey[ATH9K_NUM_CHANNELS]; @@ -595,14 +602,16 @@ struct ath_softc { struct work_struct hw_check_work; struct completion paprd_complete; + unsigned int hw_busy_count; + u32 intrstatus; u32 sc_flags; /* SC_OP_* */ u16 ps_flags; /* PS_* */ u16 curtxpow; - u8 nbcnvifs; - u16 nvifs; bool ps_enabled; bool ps_idle; + short nbcnvifs; + short nvifs; unsigned long ps_usecount; struct ath_config config; @@ -621,13 +630,20 @@ struct ath_softc { int led_on_cnt; int led_off_cnt; + struct ath9k_hw_cal_data caldata; + int last_rssi; + int beacon_interval; #ifdef CONFIG_ATH9K_DEBUGFS struct ath9k_debug debug; + spinlock_t nodes_lock; + struct list_head nodes; /* basically, stations */ + unsigned int tx_complete_poll_work_seen; #endif struct ath_beacon_config cur_beacon_conf; struct delayed_work tx_complete_work; + struct delayed_work hw_pll_work; struct ath_btcoex btcoex; struct ath_descdma txsdma; @@ -637,23 +653,6 @@ struct ath_softc { struct pm_qos_request_list pm_qos_req; }; -struct ath_wiphy { - struct ath_softc *sc; /* shared for all virtual wiphys */ - struct ieee80211_hw *hw; - struct ath9k_hw_cal_data caldata; - enum ath_wiphy_state { - ATH_WIPHY_INACTIVE, - ATH_WIPHY_ACTIVE, - ATH_WIPHY_PAUSING, - ATH_WIPHY_PAUSED, - ATH_WIPHY_SCAN, - } state; - bool idle; - int chan_idx; - int chan_is_ht; - int last_rssi; -}; - void ath9k_tasklet(unsigned long data); int ath_reset(struct ath_softc *sc, bool retry_tx); int ath_cabq_update(struct ath_softc *); @@ -675,14 +674,13 @@ int ath9k_init_device(u16 devid, struct ath_softc *sc, u16 subsysid, const struct ath_bus_ops *bus_ops); void ath9k_deinit_device(struct ath_softc *sc); void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw); -void ath9k_update_ichannel(struct ath_softc *sc, struct ieee80211_hw *hw, - struct ath9k_channel *ichan); int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, struct ath9k_channel *hchan); void ath_radio_enable(struct ath_softc *sc, struct ieee80211_hw *hw); void ath_radio_disable(struct ath_softc *sc, struct ieee80211_hw *hw); bool ath9k_setpower(struct ath_softc *sc, enum ath9k_power_mode mode); +bool ath9k_uses_beacons(int type); #ifdef CONFIG_PCI int ath_pci_init(void); @@ -706,26 +704,12 @@ void ath9k_ps_restore(struct ath_softc *sc); u8 ath_txchainmask_reduction(struct ath_softc *sc, u8 chainmask, u32 rate); void ath9k_set_bssid_mask(struct ieee80211_hw *hw, struct ieee80211_vif *vif); -int ath9k_wiphy_add(struct ath_softc *sc); -int ath9k_wiphy_del(struct ath_wiphy *aphy); -void ath9k_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb, int ftype); -int ath9k_wiphy_pause(struct ath_wiphy *aphy); -int ath9k_wiphy_unpause(struct ath_wiphy *aphy); -int ath9k_wiphy_select(struct ath_wiphy *aphy); -void ath9k_wiphy_set_scheduler(struct ath_softc *sc, unsigned int msec_int); -void ath9k_wiphy_chan_work(struct work_struct *work); -bool ath9k_wiphy_started(struct ath_softc *sc); -void ath9k_wiphy_pause_all_forced(struct ath_softc *sc, - struct ath_wiphy *selected); -bool ath9k_wiphy_scanning(struct ath_softc *sc); -void ath9k_wiphy_work(struct work_struct *work); -bool ath9k_all_wiphys_idle(struct ath_softc *sc); -void ath9k_set_wiphy_idle(struct ath_wiphy *aphy, bool idle); - -void ath_mac80211_stop_queue(struct ath_softc *sc, u16 skb_queue); -bool ath_mac80211_start_queue(struct ath_softc *sc, u16 skb_queue); void ath_start_rfkill_poll(struct ath_softc *sc); extern void ath9k_rfkill_poll_state(struct ieee80211_hw *hw); +void ath9k_calculate_iter_data(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ath9k_vif_iter_data *iter_data); + #endif /* ATH9K_H */ diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index 385ba03..fcb36ab 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -112,8 +112,7 @@ static void ath_beacon_setup(struct ath_softc *sc, struct ath_vif *avp, static void ath_tx_cabq(struct ieee80211_hw *hw, struct sk_buff *skb) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_tx_control txctl; @@ -132,8 +131,7 @@ static void ath_tx_cabq(struct ieee80211_hw *hw, struct sk_buff *skb) static struct ath_buf *ath_beacon_generate(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_buf *bf; struct ath_vif *avp; @@ -142,9 +140,6 @@ static struct ath_buf *ath_beacon_generate(struct ieee80211_hw *hw, struct ieee80211_tx_info *info; int cabq_depth; - if (aphy->state != ATH_WIPHY_ACTIVE) - return NULL; - avp = (void *)vif->drv_priv; cabq = sc->beacon.cabq; @@ -225,9 +220,8 @@ static struct ath_buf *ath_beacon_generate(struct ieee80211_hw *hw, return bf; } -int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif) +int ath_beacon_alloc(struct ath_softc *sc, struct ieee80211_vif *vif) { - struct ath_softc *sc = aphy->sc; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_vif *avp; struct ath_buf *bf; @@ -244,9 +238,7 @@ int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif) struct ath_buf, list); list_del(&avp->av_bcbuf->list); - if (sc->sc_ah->opmode == NL80211_IFTYPE_AP || - sc->sc_ah->opmode == NL80211_IFTYPE_ADHOC || - sc->sc_ah->opmode == NL80211_IFTYPE_MESH_POINT) { + if (ath9k_uses_beacons(vif->type)) { int slot; /* * Assign the vif to a beacon xmit slot. As @@ -263,7 +255,6 @@ int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif) } BUG_ON(sc->beacon.bslot[avp->av_bslot] != NULL); sc->beacon.bslot[avp->av_bslot] = vif; - sc->beacon.bslot_aphy[avp->av_bslot] = aphy; sc->nbcnvifs++; } } @@ -281,10 +272,8 @@ int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif) /* NB: the beacon data buffer must be 32-bit aligned. */ skb = ieee80211_beacon_get(sc->hw, vif); - if (skb == NULL) { - ath_dbg(common, ATH_DBG_BEACON, "cannot get skb\n"); + if (skb == NULL) return -ENOMEM; - } tstamp = ((struct ieee80211_mgmt *)skb->data)->u.beacon.timestamp; sc->beacon.bc_tstamp = le64_to_cpu(tstamp); @@ -336,7 +325,6 @@ void ath_beacon_return(struct ath_softc *sc, struct ath_vif *avp) if (avp->av_bslot != -1) { sc->beacon.bslot[avp->av_bslot] = NULL; - sc->beacon.bslot_aphy[avp->av_bslot] = NULL; sc->nbcnvifs--; } @@ -362,7 +350,6 @@ void ath_beacon_tasklet(unsigned long data) struct ath_common *common = ath9k_hw_common(ah); struct ath_buf *bf = NULL; struct ieee80211_vif *vif; - struct ath_wiphy *aphy; int slot; u32 bfaddr, bc = 0, tsftu; u64 tsf; @@ -420,7 +407,6 @@ void ath_beacon_tasklet(unsigned long data) */ slot = ATH_BCBUF - slot - 1; vif = sc->beacon.bslot[slot]; - aphy = sc->beacon.bslot_aphy[slot]; ath_dbg(common, ATH_DBG_BEACON, "slot %d [tsf %llu tsftu %u intval %u] vif %p\n", @@ -428,7 +414,7 @@ void ath_beacon_tasklet(unsigned long data) bfaddr = 0; if (vif) { - bf = ath_beacon_generate(aphy->hw, vif); + bf = ath_beacon_generate(sc->hw, vif); if (bf != NULL) { bfaddr = bf->bf_daddr; bc = 1; @@ -720,10 +706,10 @@ void ath_beacon_config(struct ath_softc *sc, struct ieee80211_vif *vif) iftype = sc->sc_ah->opmode; } - cur_conf->listen_interval = 1; - cur_conf->dtim_count = 1; - cur_conf->bmiss_timeout = - ATH_DEFAULT_BMISS_LIMIT * cur_conf->beacon_interval; + cur_conf->listen_interval = 1; + cur_conf->dtim_count = 1; + cur_conf->bmiss_timeout = + ATH_DEFAULT_BMISS_LIMIT * cur_conf->beacon_interval; /* * It looks like mac80211 may end up using beacon interval of zero in @@ -735,8 +721,9 @@ void ath_beacon_config(struct ath_softc *sc, struct ieee80211_vif *vif) cur_conf->beacon_interval = 100; /* - * Some times we dont parse dtim period from mac80211, in that case - * use a default value + * We don't parse dtim period from mac80211 during the driver + * initialization as it breaks association with hidden-ssid + * AP and it causes latency in roaming */ if (cur_conf->dtim_period == 0) cur_conf->dtim_period = 1; diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c index b68a1ac..b4a92a4 100644 --- a/drivers/net/wireless/ath/ath9k/calib.c +++ b/drivers/net/wireless/ath/ath9k/calib.c @@ -382,9 +382,8 @@ void ath9k_init_nfcal_hist_buffer(struct ath_hw *ah, s16 default_nf; int i, j; - if (!ah->caldata) - return; - + ah->caldata->channel = chan->channel; + ah->caldata->channelFlags = chan->channelFlags & ~CHANNEL_CW_INT; h = ah->caldata->nfCalHist; default_nf = ath9k_hw_get_default_nf(ah, chan); for (i = 0; i < NUM_NF_READINGS; i++) { diff --git a/drivers/net/wireless/ath/ath9k/common.c b/drivers/net/wireless/ath/ath9k/common.c index df1998d..615e682 100644 --- a/drivers/net/wireless/ath/ath9k/common.c +++ b/drivers/net/wireless/ath/ath9k/common.c @@ -189,6 +189,17 @@ void ath9k_cmn_btcoex_bt_stomp(struct ath_common *common, } EXPORT_SYMBOL(ath9k_cmn_btcoex_bt_stomp); +void ath9k_cmn_update_txpow(struct ath_hw *ah, u16 cur_txpow, + u16 new_txpow, u16 *txpower) +{ + if (cur_txpow != new_txpow) { + ath9k_hw_set_txpowerlimit(ah, new_txpow, false); + /* read back in case value is clamped */ + *txpower = ath9k_hw_regulatory(ah)->power_limit; + } +} +EXPORT_SYMBOL(ath9k_cmn_update_txpow); + static int __init ath9k_cmn_init(void) { return 0; diff --git a/drivers/net/wireless/ath/ath9k/common.h b/drivers/net/wireless/ath/ath9k/common.h index a126bdd..b2f7b5f 100644 --- a/drivers/net/wireless/ath/ath9k/common.h +++ b/drivers/net/wireless/ath/ath9k/common.h @@ -23,8 +23,6 @@ /* Common header for Atheros 802.11n base driver cores */ -#define IEEE80211_WEP_NKID 4 - #define WME_NUM_TID 16 #define WME_BA_BMP_SIZE 64 #define WME_MAX_BA WME_BA_BMP_SIZE @@ -70,3 +68,5 @@ struct ath9k_channel *ath9k_cmn_get_curchannel(struct ieee80211_hw *hw, int ath9k_cmn_count_streams(unsigned int chainmask, int max); void ath9k_cmn_btcoex_bt_stomp(struct ath_common *common, enum ath_stomp_type stomp_type); +void ath9k_cmn_update_txpow(struct ath_hw *ah, u16 cur_txpow, + u16 new_txpow, u16 *txpower); diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 3586c43..5cfcf8c 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -381,41 +381,40 @@ static const struct file_operations fops_interrupt = { .llseek = default_llseek, }; -static const char * ath_wiphy_state_str(enum ath_wiphy_state state) +static const char *channel_type_str(enum nl80211_channel_type t) { - switch (state) { - case ATH_WIPHY_INACTIVE: - return "INACTIVE"; - case ATH_WIPHY_ACTIVE: - return "ACTIVE"; - case ATH_WIPHY_PAUSING: - return "PAUSING"; - case ATH_WIPHY_PAUSED: - return "PAUSED"; - case ATH_WIPHY_SCAN: - return "SCAN"; + switch (t) { + case NL80211_CHAN_NO_HT: + return "no ht"; + case NL80211_CHAN_HT20: + return "ht20"; + case NL80211_CHAN_HT40MINUS: + return "ht40-"; + case NL80211_CHAN_HT40PLUS: + return "ht40+"; + default: + return "???"; } - return "?"; } static ssize_t read_file_wiphy(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct ath_softc *sc = file->private_data; - struct ath_wiphy *aphy = sc->pri_wiphy; - struct ieee80211_channel *chan = aphy->hw->conf.channel; + struct ieee80211_channel *chan = sc->hw->conf.channel; + struct ieee80211_conf *conf = &(sc->hw->conf); char buf[512]; unsigned int len = 0; - int i; u8 addr[ETH_ALEN]; u32 tmp; len += snprintf(buf + len, sizeof(buf) - len, - "primary: %s (%s chan=%d ht=%d)\n", - wiphy_name(sc->pri_wiphy->hw->wiphy), - ath_wiphy_state_str(sc->pri_wiphy->state), + "%s (chan=%d center-freq: %d MHz channel-type: %d (%s))\n", + wiphy_name(sc->hw->wiphy), ieee80211_frequency_to_channel(chan->center_freq), - aphy->chan_is_ht); + chan->center_freq, + conf->channel_type, + channel_type_str(conf->channel_type)); put_unaligned_le32(REG_READ_D(sc->sc_ah, AR_STA_ID0), addr); put_unaligned_le16(REG_READ_D(sc->sc_ah, AR_STA_ID1) & 0xffff, addr + 4); @@ -457,156 +456,82 @@ static ssize_t read_file_wiphy(struct file *file, char __user *user_buf, else len += snprintf(buf + len, sizeof(buf) - len, "\n"); - /* Put variable-length stuff down here, and check for overflows. */ - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy_tmp = sc->sec_wiphy[i]; - if (aphy_tmp == NULL) - continue; - chan = aphy_tmp->hw->conf.channel; - len += snprintf(buf + len, sizeof(buf) - len, - "secondary: %s (%s chan=%d ht=%d)\n", - wiphy_name(aphy_tmp->hw->wiphy), - ath_wiphy_state_str(aphy_tmp->state), - ieee80211_frequency_to_channel(chan->center_freq), - aphy_tmp->chan_is_ht); - } if (len > sizeof(buf)) len = sizeof(buf); return simple_read_from_buffer(user_buf, count, ppos, buf, len); } -static struct ath_wiphy * get_wiphy(struct ath_softc *sc, const char *name) -{ - int i; - if (strcmp(name, wiphy_name(sc->pri_wiphy->hw->wiphy)) == 0) - return sc->pri_wiphy; - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - if (aphy && strcmp(name, wiphy_name(aphy->hw->wiphy)) == 0) - return aphy; - } - return NULL; -} - -static int del_wiphy(struct ath_softc *sc, const char *name) -{ - struct ath_wiphy *aphy = get_wiphy(sc, name); - if (!aphy) - return -ENOENT; - return ath9k_wiphy_del(aphy); -} - -static int pause_wiphy(struct ath_softc *sc, const char *name) -{ - struct ath_wiphy *aphy = get_wiphy(sc, name); - if (!aphy) - return -ENOENT; - return ath9k_wiphy_pause(aphy); -} - -static int unpause_wiphy(struct ath_softc *sc, const char *name) -{ - struct ath_wiphy *aphy = get_wiphy(sc, name); - if (!aphy) - return -ENOENT; - return ath9k_wiphy_unpause(aphy); -} - -static int select_wiphy(struct ath_softc *sc, const char *name) -{ - struct ath_wiphy *aphy = get_wiphy(sc, name); - if (!aphy) - return -ENOENT; - return ath9k_wiphy_select(aphy); -} - -static int schedule_wiphy(struct ath_softc *sc, const char *msec) -{ - ath9k_wiphy_set_scheduler(sc, simple_strtoul(msec, NULL, 0)); - return 0; -} - -static ssize_t write_file_wiphy(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ath_softc *sc = file->private_data; - char buf[50]; - size_t len; - - len = min(count, sizeof(buf) - 1); - if (copy_from_user(buf, user_buf, len)) - return -EFAULT; - buf[len] = '\0'; - if (len > 0 && buf[len - 1] == '\n') - buf[len - 1] = '\0'; - - if (strncmp(buf, "add", 3) == 0) { - int res = ath9k_wiphy_add(sc); - if (res < 0) - return res; - } else if (strncmp(buf, "del=", 4) == 0) { - int res = del_wiphy(sc, buf + 4); - if (res < 0) - return res; - } else if (strncmp(buf, "pause=", 6) == 0) { - int res = pause_wiphy(sc, buf + 6); - if (res < 0) - return res; - } else if (strncmp(buf, "unpause=", 8) == 0) { - int res = unpause_wiphy(sc, buf + 8); - if (res < 0) - return res; - } else if (strncmp(buf, "select=", 7) == 0) { - int res = select_wiphy(sc, buf + 7); - if (res < 0) - return res; - } else if (strncmp(buf, "schedule=", 9) == 0) { - int res = schedule_wiphy(sc, buf + 9); - if (res < 0) - return res; - } else - return -EOPNOTSUPP; - - return count; -} - static const struct file_operations fops_wiphy = { .read = read_file_wiphy, - .write = write_file_wiphy, .open = ath9k_debugfs_open, .owner = THIS_MODULE, .llseek = default_llseek, }; +#define PR_QNUM(_n) sc->tx.txq_map[_n]->axq_qnum #define PR(str, elem) \ do { \ len += snprintf(buf + len, size - len, \ "%s%13u%11u%10u%10u\n", str, \ - sc->debug.stats.txstats[WME_AC_BE].elem, \ - sc->debug.stats.txstats[WME_AC_BK].elem, \ - sc->debug.stats.txstats[WME_AC_VI].elem, \ - sc->debug.stats.txstats[WME_AC_VO].elem); \ + sc->debug.stats.txstats[PR_QNUM(WME_AC_BE)].elem, \ + sc->debug.stats.txstats[PR_QNUM(WME_AC_BK)].elem, \ + sc->debug.stats.txstats[PR_QNUM(WME_AC_VI)].elem, \ + sc->debug.stats.txstats[PR_QNUM(WME_AC_VO)].elem); \ + if (len >= size) \ + goto done; \ +} while(0) + +#define PRX(str, elem) \ +do { \ + len += snprintf(buf + len, size - len, \ + "%s%13u%11u%10u%10u\n", str, \ + (unsigned int)(sc->tx.txq_map[WME_AC_BE]->elem), \ + (unsigned int)(sc->tx.txq_map[WME_AC_BK]->elem), \ + (unsigned int)(sc->tx.txq_map[WME_AC_VI]->elem), \ + (unsigned int)(sc->tx.txq_map[WME_AC_VO]->elem)); \ + if (len >= size) \ + goto done; \ } while(0) +#define PRQLE(str, elem) \ +do { \ + len += snprintf(buf + len, size - len, \ + "%s%13i%11i%10i%10i\n", str, \ + list_empty(&sc->tx.txq_map[WME_AC_BE]->elem), \ + list_empty(&sc->tx.txq_map[WME_AC_BK]->elem), \ + list_empty(&sc->tx.txq_map[WME_AC_VI]->elem), \ + list_empty(&sc->tx.txq_map[WME_AC_VO]->elem)); \ + if (len >= size) \ + goto done; \ +} while (0) + static ssize_t read_file_xmit(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct ath_softc *sc = file->private_data; char *buf; - unsigned int len = 0, size = 2048; + unsigned int len = 0, size = 8000; + int i; ssize_t retval = 0; + char tmp[32]; buf = kzalloc(size, GFP_KERNEL); if (buf == NULL) return -ENOMEM; - len += sprintf(buf, "%30s %10s%10s%10s\n\n", "BE", "BK", "VI", "VO"); + len += sprintf(buf, "Num-Tx-Queues: %i tx-queues-setup: 0x%x" + " poll-work-seen: %u\n" + "%30s %10s%10s%10s\n\n", + ATH9K_NUM_TX_QUEUES, sc->tx.txqsetup, + sc->tx_complete_poll_work_seen, + "BE", "BK", "VI", "VO"); PR("MPDUs Queued: ", queued); PR("MPDUs Completed: ", completed); PR("Aggregates: ", a_aggr); - PR("AMPDUs Queued: ", a_queued); + PR("AMPDUs Queued HW:", a_queued_hw); + PR("AMPDUs Queued SW:", a_queued_sw); PR("AMPDUs Completed:", a_completed); PR("AMPDUs Retried: ", a_retries); PR("AMPDUs XRetried: ", a_xretries); @@ -618,6 +543,223 @@ static ssize_t read_file_xmit(struct file *file, char __user *user_buf, PR("DELIM Underrun: ", delim_underrun); PR("TX-Pkts-All: ", tx_pkts_all); PR("TX-Bytes-All: ", tx_bytes_all); + PR("hw-put-tx-buf: ", puttxbuf); + PR("hw-tx-start: ", txstart); + PR("hw-tx-proc-desc: ", txprocdesc); + len += snprintf(buf + len, size - len, + "%s%11p%11p%10p%10p\n", "txq-memory-address:", + &(sc->tx.txq_map[WME_AC_BE]), + &(sc->tx.txq_map[WME_AC_BK]), + &(sc->tx.txq_map[WME_AC_VI]), + &(sc->tx.txq_map[WME_AC_VO])); + if (len >= size) + goto done; + + PRX("axq-qnum: ", axq_qnum); + PRX("axq-depth: ", axq_depth); + PRX("axq-ampdu_depth: ", axq_ampdu_depth); + PRX("axq-stopped ", stopped); + PRX("tx-in-progress ", axq_tx_inprogress); + PRX("pending-frames ", pending_frames); + PRX("txq_headidx: ", txq_headidx); + PRX("txq_tailidx: ", txq_headidx); + + PRQLE("axq_q empty: ", axq_q); + PRQLE("axq_acq empty: ", axq_acq); + PRQLE("txq_fifo_pending: ", txq_fifo_pending); + for (i = 0; i < ATH_TXFIFO_DEPTH; i++) { + snprintf(tmp, sizeof(tmp) - 1, "txq_fifo[%i] empty: ", i); + PRQLE(tmp, txq_fifo[i]); + } + + /* Print out more detailed queue-info */ + for (i = 0; i <= WME_AC_BK; i++) { + struct ath_txq *txq = &(sc->tx.txq[i]); + struct ath_atx_ac *ac; + struct ath_atx_tid *tid; + if (len >= size) + goto done; + spin_lock_bh(&txq->axq_lock); + if (!list_empty(&txq->axq_acq)) { + ac = list_first_entry(&txq->axq_acq, struct ath_atx_ac, + list); + len += snprintf(buf + len, size - len, + "txq[%i] first-ac: %p sched: %i\n", + i, ac, ac->sched); + if (list_empty(&ac->tid_q) || (len >= size)) + goto done_for; + tid = list_first_entry(&ac->tid_q, struct ath_atx_tid, + list); + len += snprintf(buf + len, size - len, + " first-tid: %p sched: %i paused: %i\n", + tid, tid->sched, tid->paused); + } + done_for: + spin_unlock_bh(&txq->axq_lock); + } + +done: + if (len > size) + len = size; + + retval = simple_read_from_buffer(user_buf, count, ppos, buf, len); + kfree(buf); + + return retval; +} + +static ssize_t read_file_stations(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ath_softc *sc = file->private_data; + char *buf; + unsigned int len = 0, size = 64000; + struct ath_node *an = NULL; + ssize_t retval = 0; + int q; + + buf = kzalloc(size, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + len += snprintf(buf + len, size - len, + "Stations:\n" + " tid: addr sched paused buf_q-empty an ac\n" + " ac: addr sched tid_q-empty txq\n"); + + spin_lock(&sc->nodes_lock); + list_for_each_entry(an, &sc->nodes, list) { + len += snprintf(buf + len, size - len, + "%pM\n", an->sta->addr); + if (len >= size) + goto done; + + for (q = 0; q < WME_NUM_TID; q++) { + struct ath_atx_tid *tid = &(an->tid[q]); + len += snprintf(buf + len, size - len, + " tid: %p %s %s %i %p %p\n", + tid, tid->sched ? "sched" : "idle", + tid->paused ? "paused" : "running", + list_empty(&tid->buf_q), + tid->an, tid->ac); + if (len >= size) + goto done; + } + + for (q = 0; q < WME_NUM_AC; q++) { + struct ath_atx_ac *ac = &(an->ac[q]); + len += snprintf(buf + len, size - len, + " ac: %p %s %i %p\n", + ac, ac->sched ? "sched" : "idle", + list_empty(&ac->tid_q), ac->txq); + if (len >= size) + goto done; + } + } + +done: + spin_unlock(&sc->nodes_lock); + if (len > size) + len = size; + + retval = simple_read_from_buffer(user_buf, count, ppos, buf, len); + kfree(buf); + + return retval; +} + +static ssize_t read_file_misc(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ath_softc *sc = file->private_data; + struct ath_common *common = ath9k_hw_common(sc->sc_ah); + struct ath_hw *ah = sc->sc_ah; + struct ieee80211_hw *hw = sc->hw; + char *buf; + unsigned int len = 0, size = 8000; + ssize_t retval = 0; + const char *tmp; + unsigned int reg; + struct ath9k_vif_iter_data iter_data; + + ath9k_calculate_iter_data(hw, NULL, &iter_data); + + buf = kzalloc(size, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + switch (sc->sc_ah->opmode) { + case NL80211_IFTYPE_ADHOC: + tmp = "ADHOC"; + break; + case NL80211_IFTYPE_MESH_POINT: + tmp = "MESH"; + break; + case NL80211_IFTYPE_AP: + tmp = "AP"; + break; + case NL80211_IFTYPE_STATION: + tmp = "STATION"; + break; + default: + tmp = "???"; + break; + } + + len += snprintf(buf + len, size - len, + "curbssid: %pM\n" + "OP-Mode: %s(%i)\n" + "Beacon-Timer-Register: 0x%x\n", + common->curbssid, + tmp, (int)(sc->sc_ah->opmode), + REG_READ(ah, AR_BEACON_PERIOD)); + + reg = REG_READ(ah, AR_TIMER_MODE); + len += snprintf(buf + len, size - len, "Timer-Mode-Register: 0x%x (", + reg); + if (reg & AR_TBTT_TIMER_EN) + len += snprintf(buf + len, size - len, "TBTT "); + if (reg & AR_DBA_TIMER_EN) + len += snprintf(buf + len, size - len, "DBA "); + if (reg & AR_SWBA_TIMER_EN) + len += snprintf(buf + len, size - len, "SWBA "); + if (reg & AR_HCF_TIMER_EN) + len += snprintf(buf + len, size - len, "HCF "); + if (reg & AR_TIM_TIMER_EN) + len += snprintf(buf + len, size - len, "TIM "); + if (reg & AR_DTIM_TIMER_EN) + len += snprintf(buf + len, size - len, "DTIM "); + len += snprintf(buf + len, size - len, ")\n"); + + reg = sc->sc_ah->imask; + len += snprintf(buf + len, size - len, "imask: 0x%x (", reg); + if (reg & ATH9K_INT_SWBA) + len += snprintf(buf + len, size - len, "SWBA "); + if (reg & ATH9K_INT_BMISS) + len += snprintf(buf + len, size - len, "BMISS "); + if (reg & ATH9K_INT_CST) + len += snprintf(buf + len, size - len, "CST "); + if (reg & ATH9K_INT_RX) + len += snprintf(buf + len, size - len, "RX "); + if (reg & ATH9K_INT_RXHP) + len += snprintf(buf + len, size - len, "RXHP "); + if (reg & ATH9K_INT_RXLP) + len += snprintf(buf + len, size - len, "RXLP "); + if (reg & ATH9K_INT_BB_WATCHDOG) + len += snprintf(buf + len, size - len, "BB_WATCHDOG "); + /* there are other IRQs if one wanted to add them. */ + len += snprintf(buf + len, size - len, ")\n"); + + len += snprintf(buf + len, size - len, + "VIF Counts: AP: %i STA: %i MESH: %i WDS: %i" + " ADHOC: %i OTHER: %i nvifs: %hi beacon-vifs: %hi\n", + iter_data.naps, iter_data.nstations, iter_data.nmeshes, + iter_data.nwds, iter_data.nadhocs, iter_data.nothers, + sc->nvifs, sc->nbcnvifs); + + len += snprintf(buf + len, size - len, + "Calculated-BSSID-Mask: %pM\n", + iter_data.mask); if (len > size) len = size; @@ -629,9 +771,9 @@ static ssize_t read_file_xmit(struct file *file, char __user *user_buf, } void ath_debug_stat_tx(struct ath_softc *sc, struct ath_buf *bf, - struct ath_tx_status *ts) + struct ath_tx_status *ts, struct ath_txq *txq) { - int qnum = skb_get_queue_mapping(bf->bf_mpdu); + int qnum = txq->axq_qnum; TX_STAT_INC(qnum, tx_pkts_all); sc->debug.stats.txstats[qnum].tx_bytes_all += bf->bf_mpdu->len; @@ -666,6 +808,20 @@ static const struct file_operations fops_xmit = { .llseek = default_llseek, }; +static const struct file_operations fops_stations = { + .read = read_file_stations, + .open = ath9k_debugfs_open, + .owner = THIS_MODULE, + .llseek = default_llseek, +}; + +static const struct file_operations fops_misc = { + .read = read_file_misc, + .open = ath9k_debugfs_open, + .owner = THIS_MODULE, + .llseek = default_llseek, +}; + static ssize_t read_file_recv(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -903,6 +1059,14 @@ int ath9k_init_debug(struct ath_hw *ah) sc, &fops_xmit)) goto err; + if (!debugfs_create_file("stations", S_IRUSR, sc->debug.debugfs_phy, + sc, &fops_stations)) + goto err; + + if (!debugfs_create_file("misc", S_IRUSR, sc->debug.debugfs_phy, + sc, &fops_misc)) + goto err; + if (!debugfs_create_file("recv", S_IRUSR, sc->debug.debugfs_phy, sc, &fops_recv)) goto err; diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h index 1e5078b..59338de 100644 --- a/drivers/net/wireless/ath/ath9k/debug.h +++ b/drivers/net/wireless/ath/ath9k/debug.h @@ -89,7 +89,8 @@ struct ath_interrupt_stats { * @queued: Total MPDUs (non-aggr) queued * @completed: Total MPDUs (non-aggr) completed * @a_aggr: Total no. of aggregates queued - * @a_queued: Total AMPDUs queued + * @a_queued_hw: Total AMPDUs queued to hardware + * @a_queued_sw: Total AMPDUs queued to software queues * @a_completed: Total AMPDUs completed * @a_retries: No. of AMPDUs retried (SW) * @a_xretries: No. of AMPDUs dropped due to xretries @@ -102,6 +103,9 @@ struct ath_interrupt_stats { * @desc_cfg_err: Descriptor configuration errors * @data_urn: TX data underrun errors * @delim_urn: TX delimiter underrun errors + * @puttxbuf: Number of times hardware was given txbuf to write. + * @txstart: Number of times hardware was told to start tx. + * @txprocdesc: Number of times tx descriptor was processed */ struct ath_tx_stats { u32 tx_pkts_all; @@ -109,7 +113,8 @@ struct ath_tx_stats { u32 queued; u32 completed; u32 a_aggr; - u32 a_queued; + u32 a_queued_hw; + u32 a_queued_sw; u32 a_completed; u32 a_retries; u32 a_xretries; @@ -119,6 +124,9 @@ struct ath_tx_stats { u32 desc_cfg_err; u32 data_underrun; u32 delim_underrun; + u32 puttxbuf; + u32 txstart; + u32 txprocdesc; }; /** @@ -167,7 +175,7 @@ int ath9k_init_debug(struct ath_hw *ah); void ath_debug_stat_interrupt(struct ath_softc *sc, enum ath9k_int status); void ath_debug_stat_tx(struct ath_softc *sc, struct ath_buf *bf, - struct ath_tx_status *ts); + struct ath_tx_status *ts, struct ath_txq *txq); void ath_debug_stat_rx(struct ath_softc *sc, struct ath_rx_status *rs); #else @@ -184,7 +192,8 @@ static inline void ath_debug_stat_interrupt(struct ath_softc *sc, static inline void ath_debug_stat_tx(struct ath_softc *sc, struct ath_buf *bf, - struct ath_tx_status *ts) + struct ath_tx_status *ts, + struct ath_txq *txq) { } diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index d051631..8c18bed 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -89,6 +89,38 @@ bool ath9k_hw_get_lower_upper_index(u8 target, u8 *pList, u16 listSize, return false; } +void ath9k_hw_usb_gen_fill_eeprom(struct ath_hw *ah, u16 *eep_data, + int eep_start_loc, int size) +{ + int i = 0, j, addr; + u32 addrdata[8]; + u32 data[8]; + + for (addr = 0; addr < size; addr++) { + addrdata[i] = AR5416_EEPROM_OFFSET + + ((addr + eep_start_loc) << AR5416_EEPROM_S); + i++; + if (i == 8) { + REG_READ_MULTI(ah, addrdata, data, i); + + for (j = 0; j < i; j++) { + *eep_data = data[j]; + eep_data++; + } + i = 0; + } + } + + if (i != 0) { + REG_READ_MULTI(ah, addrdata, data, i); + + for (j = 0; j < i; j++) { + *eep_data = data[j]; + eep_data++; + } + } +} + bool ath9k_hw_nvram_read(struct ath_common *common, u32 off, u16 *data) { return common->bus_ops->eeprom_read(common, off, data); diff --git a/drivers/net/wireless/ath/ath9k/eeprom.h b/drivers/net/wireless/ath/ath9k/eeprom.h index 58e2ddc..bd82447 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.h +++ b/drivers/net/wireless/ath/ath9k/eeprom.h @@ -665,6 +665,8 @@ int16_t ath9k_hw_interpolate(u16 target, u16 srcLeft, u16 srcRight, bool ath9k_hw_get_lower_upper_index(u8 target, u8 *pList, u16 listSize, u16 *indexL, u16 *indexR); bool ath9k_hw_nvram_read(struct ath_common *common, u32 off, u16 *data); +void ath9k_hw_usb_gen_fill_eeprom(struct ath_hw *ah, u16 *eep_data, + int eep_start_loc, int size); void ath9k_hw_fill_vpd_table(u8 pwrMin, u8 pwrMax, u8 *pPwrList, u8 *pVpdList, u16 numIntercepts, u8 *pRetVpdList); diff --git a/drivers/net/wireless/ath/ath9k/eeprom_4k.c b/drivers/net/wireless/ath/ath9k/eeprom_4k.c index fbdff7e..bc77a30 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_4k.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_4k.c @@ -27,19 +27,13 @@ static int ath9k_hw_4k_get_eeprom_rev(struct ath_hw *ah) return ((ah->eeprom.map4k.baseEepHeader.version) & 0xFFF); } -static bool ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) -{ #define SIZE_EEPROM_4K (sizeof(struct ar5416_eeprom_4k) / sizeof(u16)) + +static bool __ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) +{ struct ath_common *common = ath9k_hw_common(ah); u16 *eep_data = (u16 *)&ah->eeprom.map4k; - int addr, eep_start_loc = 0; - - eep_start_loc = 64; - - if (!ath9k_hw_use_flash(ah)) { - ath_dbg(common, ATH_DBG_EEPROM, - "Reading from EEPROM, not flash\n"); - } + int addr, eep_start_loc = 64; for (addr = 0; addr < SIZE_EEPROM_4K; addr++) { if (!ath9k_hw_nvram_read(common, addr + eep_start_loc, eep_data)) { @@ -51,9 +45,34 @@ static bool ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) } return true; -#undef SIZE_EEPROM_4K } +static bool __ath9k_hw_usb_4k_fill_eeprom(struct ath_hw *ah) +{ + u16 *eep_data = (u16 *)&ah->eeprom.map4k; + + ath9k_hw_usb_gen_fill_eeprom(ah, eep_data, 64, SIZE_EEPROM_4K); + + return true; +} + +static bool ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!ath9k_hw_use_flash(ah)) { + ath_dbg(common, ATH_DBG_EEPROM, + "Reading from EEPROM, not flash\n"); + } + + if (common->bus_ops->ath_bus_type == ATH_USB) + return __ath9k_hw_usb_4k_fill_eeprom(ah); + else + return __ath9k_hw_4k_fill_eeprom(ah); +} + +#undef SIZE_EEPROM_4K + static int ath9k_hw_4k_check_eeprom(struct ath_hw *ah) { #define EEPROM_4K_SIZE (sizeof(struct ar5416_eeprom_4k) / sizeof(u16)) diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c index 9b6bc8a..8cd8333 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c @@ -17,7 +17,7 @@ #include "hw.h" #include "ar9002_phy.h" -#define NUM_EEP_WORDS (sizeof(struct ar9287_eeprom) / sizeof(u16)) +#define SIZE_EEPROM_AR9287 (sizeof(struct ar9287_eeprom) / sizeof(u16)) static int ath9k_hw_ar9287_get_eeprom_ver(struct ath_hw *ah) { @@ -29,25 +29,15 @@ static int ath9k_hw_ar9287_get_eeprom_rev(struct ath_hw *ah) return (ah->eeprom.map9287.baseEepHeader.version) & 0xFFF; } -static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) +static bool __ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) { struct ar9287_eeprom *eep = &ah->eeprom.map9287; struct ath_common *common = ath9k_hw_common(ah); u16 *eep_data; - int addr, eep_start_loc; + int addr, eep_start_loc = AR9287_EEP_START_LOC; eep_data = (u16 *)eep; - if (common->bus_ops->ath_bus_type == ATH_USB) - eep_start_loc = AR9287_HTC_EEP_START_LOC; - else - eep_start_loc = AR9287_EEP_START_LOC; - - if (!ath9k_hw_use_flash(ah)) { - ath_dbg(common, ATH_DBG_EEPROM, - "Reading from EEPROM, not flash\n"); - } - - for (addr = 0; addr < NUM_EEP_WORDS; addr++) { + for (addr = 0; addr < SIZE_EEPROM_AR9287; addr++) { if (!ath9k_hw_nvram_read(common, addr + eep_start_loc, eep_data)) { ath_dbg(common, ATH_DBG_EEPROM, @@ -60,6 +50,31 @@ static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) return true; } +static bool __ath9k_hw_usb_ar9287_fill_eeprom(struct ath_hw *ah) +{ + u16 *eep_data = (u16 *)&ah->eeprom.map9287; + + ath9k_hw_usb_gen_fill_eeprom(ah, eep_data, + AR9287_HTC_EEP_START_LOC, + SIZE_EEPROM_AR9287); + return true; +} + +static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!ath9k_hw_use_flash(ah)) { + ath_dbg(common, ATH_DBG_EEPROM, + "Reading from EEPROM, not flash\n"); + } + + if (common->bus_ops->ath_bus_type == ATH_USB) + return __ath9k_hw_usb_ar9287_fill_eeprom(ah); + else + return __ath9k_hw_ar9287_fill_eeprom(ah); +} + static int ath9k_hw_ar9287_check_eeprom(struct ath_hw *ah) { u32 sum = 0, el, integer; @@ -86,7 +101,7 @@ static int ath9k_hw_ar9287_check_eeprom(struct ath_hw *ah) need_swap = true; eepdata = (u16 *)(&ah->eeprom); - for (addr = 0; addr < NUM_EEP_WORDS; addr++) { + for (addr = 0; addr < SIZE_EEPROM_AR9287; addr++) { temp = swab16(*eepdata); *eepdata = temp; eepdata++; diff --git a/drivers/net/wireless/ath/ath9k/eeprom_def.c b/drivers/net/wireless/ath/ath9k/eeprom_def.c index 749a936..fccd87d 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_def.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_def.c @@ -86,9 +86,10 @@ static int ath9k_hw_def_get_eeprom_rev(struct ath_hw *ah) return ((ah->eeprom.def.baseEepHeader.version) & 0xFFF); } -static bool ath9k_hw_def_fill_eeprom(struct ath_hw *ah) -{ #define SIZE_EEPROM_DEF (sizeof(struct ar5416_eeprom_def) / sizeof(u16)) + +static bool __ath9k_hw_def_fill_eeprom(struct ath_hw *ah) +{ struct ath_common *common = ath9k_hw_common(ah); u16 *eep_data = (u16 *)&ah->eeprom.def; int addr, ar5416_eep_start_loc = 0x100; @@ -103,9 +104,34 @@ static bool ath9k_hw_def_fill_eeprom(struct ath_hw *ah) eep_data++; } return true; -#undef SIZE_EEPROM_DEF } +static bool __ath9k_hw_usb_def_fill_eeprom(struct ath_hw *ah) +{ + u16 *eep_data = (u16 *)&ah->eeprom.def; + + ath9k_hw_usb_gen_fill_eeprom(ah, eep_data, + 0x100, SIZE_EEPROM_DEF); + return true; +} + +static bool ath9k_hw_def_fill_eeprom(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!ath9k_hw_use_flash(ah)) { + ath_dbg(common, ATH_DBG_EEPROM, + "Reading from EEPROM, not flash\n"); + } + + if (common->bus_ops->ath_bus_type == ATH_USB) + return __ath9k_hw_usb_def_fill_eeprom(ah); + else + return __ath9k_hw_def_fill_eeprom(ah); +} + +#undef SIZE_EEPROM_DEF + static int ath9k_hw_def_check_eeprom(struct ath_hw *ah) { struct ar5416_eeprom_def *eep = @@ -221,9 +247,9 @@ static int ath9k_hw_def_check_eeprom(struct ath_hw *ah) } /* Enable fixup for AR_AN_TOP2 if necessary */ - if (AR_SREV_9280_20_OR_LATER(ah) && - (eep->baseEepHeader.version & 0xff) > 0x0a && - eep->baseEepHeader.pwdclkind == 0) + if ((ah->hw_version.devid == AR9280_DEVID_PCI) && + ((eep->baseEepHeader.version & 0xff) > 0x0a) && + (eep->baseEepHeader.pwdclkind == 0)) ah->need_an_top2_fixup = 1; if ((common->bus_ops->ath_bus_type == ATH_USB) && diff --git a/drivers/net/wireless/ath/ath9k/gpio.c b/drivers/net/wireless/ath/ath9k/gpio.c index 1337640..fb4f17a 100644 --- a/drivers/net/wireless/ath/ath9k/gpio.c +++ b/drivers/net/wireless/ath/ath9k/gpio.c @@ -201,8 +201,7 @@ static bool ath_is_rfkill_set(struct ath_softc *sc) void ath9k_rfkill_poll_state(struct ieee80211_hw *hw) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; bool blocked = !!ath_is_rfkill_set(sc); wiphy_rfkill_set_hw_state(hw->wiphy, blocked); diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 780ac5e..0cb504d 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -366,7 +366,7 @@ struct ath9k_htc_priv { u16 seq_no; u32 bmiss_cnt; - struct ath9k_hw_cal_data caldata[ATH9K_NUM_CHANNELS]; + struct ath9k_hw_cal_data caldata; spinlock_t beacon_lock; @@ -460,7 +460,6 @@ void ath9k_htc_ps_restore(struct ath9k_htc_priv *priv); void ath9k_ps_work(struct work_struct *work); bool ath9k_htc_setpower(struct ath9k_htc_priv *priv, enum ath9k_power_mode mode); -void ath_update_txpow(struct ath9k_htc_priv *priv); void ath9k_start_rfkill_poll(struct ath9k_htc_priv *priv); void ath9k_htc_rfkill_poll_state(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_gpio.c b/drivers/net/wireless/ath/ath9k/htc_drv_gpio.c index fe70f67..7e630a8 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_gpio.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_gpio.c @@ -389,7 +389,8 @@ void ath9k_htc_radio_enable(struct ieee80211_hw *hw) ret, ah->curchan->channel); } - ath_update_txpow(priv); + ath9k_cmn_update_txpow(ah, priv->curtxpow, priv->txpowlimit, + &priv->curtxpow); /* Start RX */ WMI_CMD(WMI_START_RECV_CMDID); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 0352f09..a7bc26d 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -294,6 +294,34 @@ static unsigned int ath9k_regread(void *hw_priv, u32 reg_offset) return be32_to_cpu(val); } +static void ath9k_multi_regread(void *hw_priv, u32 *addr, + u32 *val, u16 count) +{ + struct ath_hw *ah = (struct ath_hw *) hw_priv; + struct ath_common *common = ath9k_hw_common(ah); + struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv; + __be32 tmpaddr[8]; + __be32 tmpval[8]; + int i, ret; + + for (i = 0; i < count; i++) { + tmpaddr[i] = cpu_to_be32(addr[i]); + } + + ret = ath9k_wmi_cmd(priv->wmi, WMI_REG_READ_CMDID, + (u8 *)tmpaddr , sizeof(u32) * count, + (u8 *)tmpval, sizeof(u32) * count, + 100); + if (unlikely(ret)) { + ath_dbg(common, ATH_DBG_WMI, + "Multiple REGISTER READ FAILED (count: %d)\n", count); + } + + for (i = 0; i < count; i++) { + val[i] = be32_to_cpu(tmpval[i]); + } +} + static void ath9k_regwrite_single(void *hw_priv, u32 val, u32 reg_offset) { struct ath_hw *ah = (struct ath_hw *) hw_priv; @@ -404,6 +432,7 @@ static void ath9k_regwrite_flush(void *hw_priv) static const struct ath_ops ath9k_common_ops = { .read = ath9k_regread, + .multi_read = ath9k_multi_regread, .write = ath9k_regwrite, .enable_write_buffer = ath9k_enable_regwrite_buffer, .write_flush = ath9k_regwrite_flush, diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index 6bb5995..953036a 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -24,17 +24,6 @@ static struct dentry *ath9k_debugfs_root; /* Utilities */ /*************/ -void ath_update_txpow(struct ath9k_htc_priv *priv) -{ - struct ath_hw *ah = priv->ah; - - if (priv->curtxpow != priv->txpowlimit) { - ath9k_hw_set_txpowerlimit(ah, priv->txpowlimit, false); - /* read back in case value is clamped */ - priv->curtxpow = ath9k_hw_regulatory(ah)->power_limit; - } -} - /* HACK Alert: Use 11NG for 2.4, use 11NA for 5 */ static enum htc_phymode ath9k_htc_get_curmode(struct ath9k_htc_priv *priv, struct ath9k_channel *ichan) @@ -121,7 +110,7 @@ void ath9k_htc_reset(struct ath9k_htc_priv *priv) struct ath_hw *ah = priv->ah; struct ath_common *common = ath9k_hw_common(ah); struct ieee80211_channel *channel = priv->hw->conf.channel; - struct ath9k_hw_cal_data *caldata; + struct ath9k_hw_cal_data *caldata = NULL; enum htc_phymode mode; __be16 htc_mode; u8 cmd_rsp; @@ -139,7 +128,7 @@ void ath9k_htc_reset(struct ath9k_htc_priv *priv) WMI_CMD(WMI_DRAIN_TXQ_ALL_CMDID); WMI_CMD(WMI_STOP_RECV_CMDID); - caldata = &priv->caldata[channel->hw_value]; + caldata = &priv->caldata; ret = ath9k_hw_reset(ah, ah->curchan, caldata, false); if (ret) { ath_err(common, @@ -147,7 +136,8 @@ void ath9k_htc_reset(struct ath9k_htc_priv *priv) channel->center_freq, ret); } - ath_update_txpow(priv); + ath9k_cmn_update_txpow(ah, priv->curtxpow, priv->txpowlimit, + &priv->curtxpow); WMI_CMD(WMI_START_RECV_CMDID); ath9k_host_rx_init(priv); @@ -202,7 +192,8 @@ static int ath9k_htc_set_channel(struct ath9k_htc_priv *priv, channel->center_freq, conf_is_ht(conf), conf_is_ht40(conf), fastcc); - caldata = &priv->caldata[channel->hw_value]; + if (!fastcc) + caldata = &priv->caldata; ret = ath9k_hw_reset(ah, hchan, caldata, fastcc); if (ret) { ath_err(common, @@ -211,7 +202,8 @@ static int ath9k_htc_set_channel(struct ath9k_htc_priv *priv, goto err; } - ath_update_txpow(priv); + ath9k_cmn_update_txpow(ah, priv->curtxpow, priv->txpowlimit, + &priv->curtxpow); WMI_CMD(WMI_START_RECV_CMDID); if (ret) @@ -987,7 +979,8 @@ static int ath9k_htc_start(struct ieee80211_hw *hw) return ret; } - ath_update_txpow(priv); + ath9k_cmn_update_txpow(ah, priv->curtxpow, priv->txpowlimit, + &priv->curtxpow); mode = ath9k_htc_get_curmode(priv, init_channel); htc_mode = cpu_to_be16(mode); @@ -1051,6 +1044,7 @@ static void ath9k_htc_stop(struct ieee80211_hw *hw) cancel_work_sync(&priv->fatal_work); cancel_work_sync(&priv->ps_work); cancel_delayed_work_sync(&priv->ath9k_led_blink_work); + cancel_delayed_work_sync(&priv->ath9k_ani_work); ath9k_led_stop_brightness(priv); mutex_lock(&priv->mutex); @@ -1252,7 +1246,8 @@ static int ath9k_htc_config(struct ieee80211_hw *hw, u32 changed) if (changed & IEEE80211_CONF_CHANGE_POWER) { priv->txpowlimit = 2 * conf->power_level; - ath_update_txpow(priv); + ath9k_cmn_update_txpow(priv->ah, priv->curtxpow, + priv->txpowlimit, &priv->curtxpow); } if (changed & IEEE80211_CONF_CHANGE_IDLE) { @@ -1557,7 +1552,7 @@ static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn) + u16 tid, u16 *ssn, u8 buf_size) { struct ath9k_htc_priv *priv = hw->priv; struct ath9k_htc_sta *ista; diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 9f01e50..f9cf815 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -495,6 +495,17 @@ static int __ath9k_hw_init(struct ath_hw *ah) if (ah->hw_version.devid == AR5416_AR9100_DEVID) ah->hw_version.macVersion = AR_SREV_VERSION_9100; + ath9k_hw_read_revisions(ah); + + /* + * Read back AR_WA into a permanent copy and set bits 14 and 17. + * We need to do this to avoid RMW of this register. We cannot + * read the reg when chip is asleep. + */ + ah->WARegVal = REG_READ(ah, AR_WA); + ah->WARegVal |= (AR_WA_D3_L1_DISABLE | + AR_WA_ASPM_TIMER_BASED_DISABLE); + if (!ath9k_hw_set_reset_reg(ah, ATH9K_RESET_POWER_ON)) { ath_err(common, "Couldn't reset chip\n"); return -EIO; @@ -563,14 +574,6 @@ static int __ath9k_hw_init(struct ath_hw *ah) ath9k_hw_init_mode_regs(ah); - /* - * Read back AR_WA into a permanent copy and set bits 14 and 17. - * We need to do this to avoid RMW of this register. We cannot - * read the reg when chip is asleep. - */ - ah->WARegVal = REG_READ(ah, AR_WA); - ah->WARegVal |= (AR_WA_D3_L1_DISABLE | - AR_WA_ASPM_TIMER_BASED_DISABLE); if (ah->is_pciexpress) ath9k_hw_configpcipowersave(ah, 0, 0); @@ -668,14 +671,51 @@ static void ath9k_hw_init_qos(struct ath_hw *ah) REGWRITE_BUFFER_FLUSH(ah); } +unsigned long ar9003_get_pll_sqsum_dvc(struct ath_hw *ah) +{ + REG_WRITE(ah, PLL3, (REG_READ(ah, PLL3) & ~(PLL3_DO_MEAS_MASK))); + udelay(100); + REG_WRITE(ah, PLL3, (REG_READ(ah, PLL3) | PLL3_DO_MEAS_MASK)); + + while ((REG_READ(ah, PLL4) & PLL4_MEAS_DONE) == 0) + udelay(100); + + return (REG_READ(ah, PLL3) & SQSUM_DVC_MASK) >> 3; +} +EXPORT_SYMBOL(ar9003_get_pll_sqsum_dvc); + +#define DPLL2_KD_VAL 0x3D +#define DPLL2_KI_VAL 0x06 +#define DPLL3_PHASE_SHIFT_VAL 0x1 + static void ath9k_hw_init_pll(struct ath_hw *ah, struct ath9k_channel *chan) { u32 pll; - if (AR_SREV_9485(ah)) + if (AR_SREV_9485(ah)) { + REG_WRITE(ah, AR_RTC_PLL_CONTROL2, 0x886666); + REG_WRITE(ah, AR_CH0_DDR_DPLL2, 0x19e82f01); + + REG_RMW_FIELD(ah, AR_CH0_DDR_DPLL3, + AR_CH0_DPLL3_PHASE_SHIFT, DPLL3_PHASE_SHIFT_VAL); + + REG_WRITE(ah, AR_RTC_PLL_CONTROL, 0x1142c); + udelay(100); + REG_WRITE(ah, AR_RTC_PLL_CONTROL2, 0x886666); + REG_RMW_FIELD(ah, AR_CH0_BB_DPLL2, + AR_CH0_DPLL2_KD, DPLL2_KD_VAL); + REG_RMW_FIELD(ah, AR_CH0_BB_DPLL2, + AR_CH0_DPLL2_KI, DPLL2_KI_VAL); + + REG_RMW_FIELD(ah, AR_CH0_BB_DPLL3, + AR_CH0_DPLL3_PHASE_SHIFT, DPLL3_PHASE_SHIFT_VAL); + REG_WRITE(ah, AR_RTC_PLL_CONTROL, 0x142c); + udelay(110); + } + pll = ath9k_hw_compute_pll_control(ah, chan); REG_WRITE(ah, AR_RTC_PLL_CONTROL, pll); @@ -1082,8 +1122,6 @@ static bool ath9k_hw_set_reset_power_on(struct ath_hw *ah) return false; } - ath9k_hw_read_revisions(ah); - return ath9k_hw_set_reset(ah, ATH9K_RESET_WARM); } @@ -1348,8 +1386,6 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan, ath9k_hw_spur_mitigate_freq(ah, chan); ah->eep_ops->set_board_values(ah, chan); - ath9k_hw_set_operating_mode(ah, ah->opmode); - ENABLE_REGWRITE_BUFFER(ah); REG_WRITE(ah, AR_STA_ID0, get_unaligned_le32(common->macaddr)); @@ -1367,6 +1403,8 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan, REGWRITE_BUFFER_FLUSH(ah); + ath9k_hw_set_operating_mode(ah, ah->opmode); + r = ath9k_hw_rf_set_freq(ah, chan); if (r) return r; diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index ea9fde6..ef79f4c 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -70,6 +70,9 @@ #define REG_READ(_ah, _reg) \ ath9k_hw_common(_ah)->ops->read((_ah), (_reg)) +#define REG_READ_MULTI(_ah, _addr, _val, _cnt) \ + ath9k_hw_common(_ah)->ops->multi_read((_ah), (_addr), (_val), (_cnt)) + #define ENABLE_REGWRITE_BUFFER(_ah) \ do { \ if (ath9k_hw_common(_ah)->ops->enable_write_buffer) \ @@ -926,6 +929,7 @@ void ath9k_hw_settsf64(struct ath_hw *ah, u64 tsf64); void ath9k_hw_reset_tsf(struct ath_hw *ah); void ath9k_hw_set_tsfadjust(struct ath_hw *ah, u32 setting); void ath9k_hw_init_global_settings(struct ath_hw *ah); +unsigned long ar9003_get_pll_sqsum_dvc(struct ath_hw *ah); void ath9k_hw_set11nmac2040(struct ath_hw *ah); void ath9k_hw_beaconinit(struct ath_hw *ah, u32 next_beacon, u32 beacon_period); void ath9k_hw_set_sta_beacon_timers(struct ath_hw *ah, diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 087a6a9..e5c1eea 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -254,8 +254,7 @@ static int ath9k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request) { struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy); - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_regulatory *reg = ath9k_hw_regulatory(sc->sc_ah); return ath_reg_notifier_apply(wiphy, request, reg); @@ -442,9 +441,10 @@ static int ath9k_init_queues(struct ath_softc *sc) sc->config.cabqReadytime = ATH_CABQ_READY_TIME; ath_cabq_update(sc); - for (i = 0; i < WME_NUM_AC; i++) + for (i = 0; i < WME_NUM_AC; i++) { sc->tx.txq_map[i] = ath_txq_setup(sc, ATH9K_TX_QUEUE_DATA, i); - + sc->tx.txq_map[i]->mac80211_qnum = i; + } return 0; } @@ -516,10 +516,8 @@ static void ath9k_init_misc(struct ath_softc *sc) sc->beacon.slottime = ATH9K_SLOT_TIME_9; - for (i = 0; i < ARRAY_SIZE(sc->beacon.bslot); i++) { + for (i = 0; i < ARRAY_SIZE(sc->beacon.bslot); i++) sc->beacon.bslot[i] = NULL; - sc->beacon.bslot_aphy[i] = NULL; - } if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_ANT_DIV_COMB) sc->ant_comb.count = ATH_ANT_DIV_COMB_INIT_COUNT; @@ -537,6 +535,7 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, u16 subsysid, if (!ah) return -ENOMEM; + ah->hw = sc->hw; ah->hw_version.devid = devid; ah->hw_version.subsysid = subsysid; sc->sc_ah = ah; @@ -554,10 +553,13 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, u16 subsysid, common->btcoex_enabled = ath9k_btcoex_enable == 1; spin_lock_init(&common->cc_lock); - spin_lock_init(&sc->wiphy_lock); spin_lock_init(&sc->sc_serial_rw); spin_lock_init(&sc->sc_pm_lock); mutex_init(&sc->mutex); +#ifdef CONFIG_ATH9K_DEBUGFS + spin_lock_init(&sc->nodes_lock); + INIT_LIST_HEAD(&sc->nodes); +#endif tasklet_init(&sc->intr_tq, ath9k_tasklet, (unsigned long)sc); tasklet_init(&sc->bcon_tasklet, ath_beacon_tasklet, (unsigned long)sc); @@ -699,7 +701,6 @@ int ath9k_init_device(u16 devid, struct ath_softc *sc, u16 subsysid, const struct ath_bus_ops *bus_ops) { struct ieee80211_hw *hw = sc->hw; - struct ath_wiphy *aphy = hw->priv; struct ath_common *common; struct ath_hw *ah; int error = 0; @@ -754,10 +755,7 @@ int ath9k_init_device(u16 devid, struct ath_softc *sc, u16 subsysid, INIT_WORK(&sc->hw_check_work, ath_hw_check); INIT_WORK(&sc->paprd_work, ath_paprd_calibrate); - INIT_WORK(&sc->chan_work, ath9k_wiphy_chan_work); - INIT_DELAYED_WORK(&sc->wiphy_work, ath9k_wiphy_work); - sc->wiphy_scheduler_int = msecs_to_jiffies(500); - aphy->last_rssi = ATH_RSSI_DUMMY_MARKER; + sc->last_rssi = ATH_RSSI_DUMMY_MARKER; ath_init_leds(sc); ath_start_rfkill_poll(sc); @@ -812,7 +810,6 @@ static void ath9k_deinit_softc(struct ath_softc *sc) void ath9k_deinit_device(struct ath_softc *sc) { struct ieee80211_hw *hw = sc->hw; - int i = 0; ath9k_ps_wakeup(sc); @@ -821,21 +818,11 @@ void ath9k_deinit_device(struct ath_softc *sc) ath9k_ps_restore(sc); - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - if (aphy == NULL) - continue; - sc->sec_wiphy[i] = NULL; - ieee80211_unregister_hw(aphy->hw); - ieee80211_free_hw(aphy->hw); - } - ieee80211_unregister_hw(hw); pm_qos_remove_request(&sc->pm_qos_req); ath_rx_cleanup(sc); ath_tx_cleanup(sc); ath9k_deinit_softc(sc); - kfree(sc->sec_wiphy); } void ath_descdma_cleanup(struct ath_softc *sc, diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index 180170d..c75d40f 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -690,17 +690,23 @@ int ath9k_hw_rxprocdesc(struct ath_hw *ah, struct ath_desc *ds, rs->rs_flags |= ATH9K_RX_DECRYPT_BUSY; if ((ads.ds_rxstatus8 & AR_RxFrameOK) == 0) { + /* + * Treat these errors as mutually exclusive to avoid spurious + * extra error reports from the hardware. If a CRC error is + * reported, then decryption and MIC errors are irrelevant, + * the frame is going to be dropped either way + */ if (ads.ds_rxstatus8 & AR_CRCErr) rs->rs_status |= ATH9K_RXERR_CRC; - if (ads.ds_rxstatus8 & AR_PHYErr) { + else if (ads.ds_rxstatus8 & AR_PHYErr) { rs->rs_status |= ATH9K_RXERR_PHY; phyerr = MS(ads.ds_rxstatus8, AR_PHYErrCode); rs->rs_phyerr = phyerr; - } - if (ads.ds_rxstatus8 & AR_DecryptCRCErr) + } else if (ads.ds_rxstatus8 & AR_DecryptCRCErr) rs->rs_status |= ATH9K_RXERR_DECRYPT; - if (ads.ds_rxstatus8 & AR_MichaelErr) + else if (ads.ds_rxstatus8 & AR_MichaelErr) rs->rs_status |= ATH9K_RXERR_MIC; + if (ads.ds_rxstatus8 & AR_KeyMiss) rs->rs_status |= ATH9K_RXERR_DECRYPT; } diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h index 7512f97..04d58ae 100644 --- a/drivers/net/wireless/ath/ath9k/mac.h +++ b/drivers/net/wireless/ath/ath9k/mac.h @@ -639,6 +639,8 @@ enum ath9k_rx_filter { ATH9K_RX_FILTER_PHYERR = 0x00000100, ATH9K_RX_FILTER_MYBEACON = 0x00000200, ATH9K_RX_FILTER_COMP_BAR = 0x00000400, + ATH9K_RX_FILTER_COMP_BA = 0x00000800, + ATH9K_RX_FILTER_UNCOMP_BA_BAR = 0x00001000, ATH9K_RX_FILTER_PSPOLL = 0x00004000, ATH9K_RX_FILTER_PHYRADAR = 0x00002000, ATH9K_RX_FILTER_MCAST_BCAST_ALL = 0x00008000, diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index da5c645..4ed43b2 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -18,17 +18,6 @@ #include "ath9k.h" #include "btcoex.h" -static void ath_update_txpow(struct ath_softc *sc) -{ - struct ath_hw *ah = sc->sc_ah; - - if (sc->curtxpow != sc->config.txpowlimit) { - ath9k_hw_set_txpowerlimit(ah, sc->config.txpowlimit, false); - /* read back in case value is clamped */ - sc->curtxpow = ath9k_hw_regulatory(ah)->power_limit; - } -} - static u8 parse_mpdudensity(u8 mpdudensity) { /* @@ -64,19 +53,6 @@ static u8 parse_mpdudensity(u8 mpdudensity) } } -static struct ath9k_channel *ath_get_curchannel(struct ath_softc *sc, - struct ieee80211_hw *hw) -{ - struct ieee80211_channel *curchan = hw->conf.channel; - struct ath9k_channel *channel; - u8 chan_idx; - - chan_idx = curchan->hw_value; - channel = &sc->sc_ah->channels[chan_idx]; - ath9k_update_ichannel(sc, hw, channel); - return channel; -} - bool ath9k_setpower(struct ath_softc *sc, enum ath9k_power_mode mode) { unsigned long flags; @@ -177,7 +153,12 @@ static void ath_update_survey_nf(struct ath_softc *sc, int channel) } } -static void ath_update_survey_stats(struct ath_softc *sc) +/* + * Updates the survey statistics and returns the busy time since last + * update in %, if the measurement duration was long enough for the + * result to be useful, -1 otherwise. + */ +static int ath_update_survey_stats(struct ath_softc *sc) { struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); @@ -185,9 +166,10 @@ static void ath_update_survey_stats(struct ath_softc *sc) struct survey_info *survey = &sc->survey[pos]; struct ath_cycle_counters *cc = &common->cc_survey; unsigned int div = common->clockrate * 1000; + int ret = 0; if (!ah->curchan) - return; + return -1; if (ah->power_mode == ATH9K_PM_AWAKE) ath_hw_cycle_counters_update(common); @@ -202,9 +184,18 @@ static void ath_update_survey_stats(struct ath_softc *sc) survey->channel_time_rx += cc->rx_frame / div; survey->channel_time_tx += cc->tx_frame / div; } + + if (cc->cycles < div) + return -1; + + if (cc->cycles > 0) + ret = cc->rx_busy * 100 / cc->cycles; + memset(cc, 0, sizeof(*cc)); ath_update_survey_nf(sc, pos); + + return ret; } /* @@ -215,7 +206,6 @@ static void ath_update_survey_stats(struct ath_softc *sc) int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, struct ath9k_channel *hchan) { - struct ath_wiphy *aphy = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); struct ieee80211_conf *conf = &common->hw->conf; @@ -227,10 +217,13 @@ int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, if (sc->sc_flags & SC_OP_INVALID) return -EIO; + sc->hw_busy_count = 0; + del_timer_sync(&common->ani.timer); cancel_work_sync(&sc->paprd_work); cancel_work_sync(&sc->hw_check_work); cancel_delayed_work_sync(&sc->tx_complete_work); + cancel_delayed_work_sync(&sc->hw_pll_work); ath9k_ps_wakeup(sc); @@ -251,6 +244,9 @@ int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, if (!ath_stoprecv(sc)) stopped = false; + if (!ath9k_hw_check_alive(ah)) + stopped = false; + /* XXX: do not flush receive queue here. We don't want * to flush data frames already in queue because of * changing channel. */ @@ -259,7 +255,7 @@ int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, fastcc = false; if (!(sc->sc_flags & SC_OP_OFFCHANNEL)) - caldata = &aphy->caldata; + caldata = &sc->caldata; ath_dbg(common, ATH_DBG_CONFIG, "(%u MHz) -> (%u MHz), conf_is_ht40: %d fastcc: %d\n", @@ -281,17 +277,21 @@ int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, goto ps_restore; } - ath_update_txpow(sc); + ath9k_cmn_update_txpow(ah, sc->curtxpow, + sc->config.txpowlimit, &sc->curtxpow); ath9k_hw_set_interrupts(ah, ah->imask); if (!(sc->sc_flags & (SC_OP_OFFCHANNEL))) { if (sc->sc_flags & SC_OP_BEACONS) ath_beacon_config(sc, NULL); ieee80211_queue_delayed_work(sc->hw, &sc->tx_complete_work, 0); + ieee80211_queue_delayed_work(sc->hw, &sc->hw_pll_work, HZ/2); ath_start_ani(common); } ps_restore: + ieee80211_wake_queues(hw); + spin_unlock_bh(&sc->sc_pcu_lock); ath9k_ps_restore(sc); @@ -549,6 +549,12 @@ static void ath_node_attach(struct ath_softc *sc, struct ieee80211_sta *sta) struct ath_hw *ah = sc->sc_ah; an = (struct ath_node *)sta->drv_priv; +#ifdef CONFIG_ATH9K_DEBUGFS + spin_lock(&sc->nodes_lock); + list_add(&an->list, &sc->nodes); + spin_unlock(&sc->nodes_lock); + an->sta = sta; +#endif if ((ah->caps.hw_caps) & ATH9K_HW_CAP_APM) sc->sc_flags |= SC_OP_ENABLE_APM; @@ -564,6 +570,13 @@ static void ath_node_detach(struct ath_softc *sc, struct ieee80211_sta *sta) { struct ath_node *an = (struct ath_node *)sta->drv_priv; +#ifdef CONFIG_ATH9K_DEBUGFS + spin_lock(&sc->nodes_lock); + list_del(&an->list); + spin_unlock(&sc->nodes_lock); + an->sta = NULL; +#endif + if (sc->sc_flags & SC_OP_TXAGGR) ath_tx_node_cleanup(sc, an); } @@ -571,17 +584,25 @@ static void ath_node_detach(struct ath_softc *sc, struct ieee80211_sta *sta) void ath_hw_check(struct work_struct *work) { struct ath_softc *sc = container_of(work, struct ath_softc, hw_check_work); - int i; + struct ath_common *common = ath9k_hw_common(sc->sc_ah); + unsigned long flags; + int busy; ath9k_ps_wakeup(sc); + if (ath9k_hw_check_alive(sc->sc_ah)) + goto out; - for (i = 0; i < 3; i++) { - if (ath9k_hw_check_alive(sc->sc_ah)) - goto out; + spin_lock_irqsave(&common->cc_lock, flags); + busy = ath_update_survey_stats(sc); + spin_unlock_irqrestore(&common->cc_lock, flags); - msleep(1); - } - ath_reset(sc, true); + ath_dbg(common, ATH_DBG_RESET, "Possible baseband hang, " + "busy=%d (try %d)\n", busy, sc->hw_busy_count + 1); + if (busy >= 99) { + if (++sc->hw_busy_count >= 3) + ath_reset(sc, true); + } else if (busy >= 0) + sc->hw_busy_count = 0; out: ath9k_ps_restore(sc); @@ -604,7 +625,15 @@ void ath9k_tasklet(unsigned long data) ath9k_ps_wakeup(sc); spin_lock(&sc->sc_pcu_lock); - if (!ath9k_hw_check_alive(ah)) + /* + * Only run the baseband hang check if beacons stop working in AP or + * IBSS mode, because it has a high false positive rate. For station + * mode it should not be necessary, since the upper layers will detect + * this through a beacon miss automatically and the following channel + * change will trigger a hardware reset anyway + */ + if (ath9k_hw_numtxpending(ah, sc->beacon.beaconq) != 0 && + !ath9k_hw_check_alive(ah)) ieee80211_queue_work(sc->hw, &sc->hw_check_work); if (ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) @@ -783,54 +812,11 @@ chip_reset: #undef SCHED_INTR } -static u32 ath_get_extchanmode(struct ath_softc *sc, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type) -{ - u32 chanmode = 0; - - switch (chan->band) { - case IEEE80211_BAND_2GHZ: - switch(channel_type) { - case NL80211_CHAN_NO_HT: - case NL80211_CHAN_HT20: - chanmode = CHANNEL_G_HT20; - break; - case NL80211_CHAN_HT40PLUS: - chanmode = CHANNEL_G_HT40PLUS; - break; - case NL80211_CHAN_HT40MINUS: - chanmode = CHANNEL_G_HT40MINUS; - break; - } - break; - case IEEE80211_BAND_5GHZ: - switch(channel_type) { - case NL80211_CHAN_NO_HT: - case NL80211_CHAN_HT20: - chanmode = CHANNEL_A_HT20; - break; - case NL80211_CHAN_HT40PLUS: - chanmode = CHANNEL_A_HT40PLUS; - break; - case NL80211_CHAN_HT40MINUS: - chanmode = CHANNEL_A_HT40MINUS; - break; - } - break; - default: - break; - } - - return chanmode; -} - static void ath9k_bss_assoc_info(struct ath_softc *sc, struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *bss_conf) { - struct ath_wiphy *aphy = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); @@ -854,7 +840,7 @@ static void ath9k_bss_assoc_info(struct ath_softc *sc, ath_beacon_config(sc, vif); /* Reset rssi stats */ - aphy->last_rssi = ATH_RSSI_DUMMY_MARKER; + sc->last_rssi = ATH_RSSI_DUMMY_MARKER; sc->sc_ah->stats.avgbrssi = ATH_RSSI_DUMMY_MARKER; sc->sc_flags |= SC_OP_ANI_RUN; @@ -881,7 +867,7 @@ void ath_radio_enable(struct ath_softc *sc, struct ieee80211_hw *hw) ath9k_hw_configpcipowersave(ah, 0, 0); if (!ah->curchan) - ah->curchan = ath_get_curchannel(sc, sc->hw); + ah->curchan = ath9k_cmn_get_curchannel(sc->hw, ah); r = ath9k_hw_reset(ah, ah->curchan, ah->caldata, false); if (r) { @@ -890,7 +876,8 @@ void ath_radio_enable(struct ath_softc *sc, struct ieee80211_hw *hw) channel->center_freq, r); } - ath_update_txpow(sc); + ath9k_cmn_update_txpow(ah, sc->curtxpow, + sc->config.txpowlimit, &sc->curtxpow); if (ath_startrecv(sc) != 0) { ath_err(common, "Unable to restart recv logic\n"); goto out; @@ -942,7 +929,7 @@ void ath_radio_disable(struct ath_softc *sc, struct ieee80211_hw *hw) ath_flushrecv(sc); /* flush recv queue */ if (!ah->curchan) - ah->curchan = ath_get_curchannel(sc, hw); + ah->curchan = ath9k_cmn_get_curchannel(hw, ah); r = ath9k_hw_reset(ah, ah->curchan, ah->caldata, false); if (r) { @@ -966,6 +953,8 @@ int ath_reset(struct ath_softc *sc, bool retry_tx) struct ieee80211_hw *hw = sc->hw; int r; + sc->hw_busy_count = 0; + /* Stop ANI */ del_timer_sync(&common->ani.timer); @@ -993,7 +982,8 @@ int ath_reset(struct ath_softc *sc, bool retry_tx) * that changes the channel so update any state that * might change as a result. */ - ath_update_txpow(sc); + ath9k_cmn_update_txpow(ah, sc->curtxpow, + sc->config.txpowlimit, &sc->curtxpow); if ((sc->sc_flags & SC_OP_BEACONS) || !(sc->sc_flags & (SC_OP_OFFCHANNEL))) ath_beacon_config(sc, NULL); /* restart beacons */ @@ -1021,38 +1011,13 @@ int ath_reset(struct ath_softc *sc, bool retry_tx) return r; } -/* XXX: Remove me once we don't depend on ath9k_channel for all - * this redundant data */ -void ath9k_update_ichannel(struct ath_softc *sc, struct ieee80211_hw *hw, - struct ath9k_channel *ichan) -{ - struct ieee80211_channel *chan = hw->conf.channel; - struct ieee80211_conf *conf = &hw->conf; - - ichan->channel = chan->center_freq; - ichan->chan = chan; - - if (chan->band == IEEE80211_BAND_2GHZ) { - ichan->chanmode = CHANNEL_G; - ichan->channelFlags = CHANNEL_2GHZ | CHANNEL_OFDM | CHANNEL_G; - } else { - ichan->chanmode = CHANNEL_A; - ichan->channelFlags = CHANNEL_5GHZ | CHANNEL_OFDM; - } - - if (conf_is_ht(conf)) - ichan->chanmode = ath_get_extchanmode(sc, chan, - conf->channel_type); -} - /**********************/ /* mac80211 callbacks */ /**********************/ static int ath9k_start(struct ieee80211_hw *hw) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); struct ieee80211_channel *curchan = hw->conf.channel; @@ -1065,32 +1030,10 @@ static int ath9k_start(struct ieee80211_hw *hw) mutex_lock(&sc->mutex); - if (ath9k_wiphy_started(sc)) { - if (sc->chan_idx == curchan->hw_value) { - /* - * Already on the operational channel, the new wiphy - * can be marked active. - */ - aphy->state = ATH_WIPHY_ACTIVE; - ieee80211_wake_queues(hw); - } else { - /* - * Another wiphy is on another channel, start the new - * wiphy in paused state. - */ - aphy->state = ATH_WIPHY_PAUSED; - ieee80211_stop_queues(hw); - } - mutex_unlock(&sc->mutex); - return 0; - } - aphy->state = ATH_WIPHY_ACTIVE; - /* setup initial channel */ - sc->chan_idx = curchan->hw_value; - init_channel = ath_get_curchannel(sc, hw); + init_channel = ath9k_cmn_get_curchannel(hw, ah); /* Reset SERDES registers */ ath9k_hw_configpcipowersave(ah, 0, 0); @@ -1116,7 +1059,8 @@ static int ath9k_start(struct ieee80211_hw *hw) * This is needed only to setup initial state * but it's best done after a reset. */ - ath_update_txpow(sc); + ath9k_cmn_update_txpow(ah, sc->curtxpow, + sc->config.txpowlimit, &sc->curtxpow); /* * Setup the hardware after reset: @@ -1191,19 +1135,11 @@ mutex_unlock: static int ath9k_tx(struct ieee80211_hw *hw, struct sk_buff *skb) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_tx_control txctl; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - if (aphy->state != ATH_WIPHY_ACTIVE && aphy->state != ATH_WIPHY_SCAN) { - ath_dbg(common, ATH_DBG_XMIT, - "ath9k: %s: TX in unexpected wiphy state %d\n", - wiphy_name(hw->wiphy), aphy->state); - goto exit; - } - if (sc->ps_enabled) { /* * mac80211 does not set PM field for normal data frames, so we @@ -1262,44 +1198,26 @@ exit: static void ath9k_stop(struct ieee80211_hw *hw) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); - int i; mutex_lock(&sc->mutex); - aphy->state = ATH_WIPHY_INACTIVE; - if (led_blink) cancel_delayed_work_sync(&sc->ath_led_blink_work); cancel_delayed_work_sync(&sc->tx_complete_work); + cancel_delayed_work_sync(&sc->hw_pll_work); cancel_work_sync(&sc->paprd_work); cancel_work_sync(&sc->hw_check_work); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i]) - break; - } - - if (i == sc->num_sec_wiphy) { - cancel_delayed_work_sync(&sc->wiphy_work); - cancel_work_sync(&sc->chan_work); - } - if (sc->sc_flags & SC_OP_INVALID) { ath_dbg(common, ATH_DBG_ANY, "Device not present\n"); mutex_unlock(&sc->mutex); return; } - if (ath9k_wiphy_started(sc)) { - mutex_unlock(&sc->mutex); - return; /* another wiphy still in use */ - } - /* Ensure HW is awake when we try to shut it down. */ ath9k_ps_wakeup(sc); @@ -1325,6 +1243,11 @@ static void ath9k_stop(struct ieee80211_hw *hw) } else sc->rx.rxlink = NULL; + if (sc->rx.frag) { + dev_kfree_skb_any(sc->rx.frag); + sc->rx.frag = NULL; + } + /* disable HAL and put h/w to sleep */ ath9k_hw_disable(ah); ath9k_hw_configpcipowersave(ah, 1, 1); @@ -1340,7 +1263,6 @@ static void ath9k_stop(struct ieee80211_hw *hw) ath9k_ps_restore(sc); sc->ps_idle = true; - ath9k_set_wiphy_idle(aphy, true); ath_radio_disable(sc, hw); sc->sc_flags |= SC_OP_INVALID; @@ -1352,112 +1274,238 @@ static void ath9k_stop(struct ieee80211_hw *hw) ath_dbg(common, ATH_DBG_CONFIG, "Driver halt\n"); } -static int ath9k_add_interface(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) +bool ath9k_uses_beacons(int type) +{ + switch (type) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + return true; + default: + return false; + } +} + +static void ath9k_reclaim_beacon(struct ath_softc *sc, + struct ieee80211_vif *vif) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; - struct ath_hw *ah = sc->sc_ah; - struct ath_common *common = ath9k_hw_common(ah); struct ath_vif *avp = (void *)vif->drv_priv; - enum nl80211_iftype ic_opmode = NL80211_IFTYPE_UNSPECIFIED; - int ret = 0; - mutex_lock(&sc->mutex); + /* Disable SWBA interrupt */ + sc->sc_ah->imask &= ~ATH9K_INT_SWBA; + ath9k_ps_wakeup(sc); + ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); + ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); + tasklet_kill(&sc->bcon_tasklet); + ath9k_ps_restore(sc); + + ath_beacon_return(sc, avp); + sc->sc_flags &= ~SC_OP_BEACONS; + + if (sc->nbcnvifs > 0) { + /* Re-enable beaconing */ + sc->sc_ah->imask |= ATH9K_INT_SWBA; + ath9k_ps_wakeup(sc); + ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); + ath9k_ps_restore(sc); + } +} + +static void ath9k_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif) +{ + struct ath9k_vif_iter_data *iter_data = data; + int i; + + if (iter_data->hw_macaddr) + for (i = 0; i < ETH_ALEN; i++) + iter_data->mask[i] &= + ~(iter_data->hw_macaddr[i] ^ mac[i]); switch (vif->type) { - case NL80211_IFTYPE_STATION: - ic_opmode = NL80211_IFTYPE_STATION; + case NL80211_IFTYPE_AP: + iter_data->naps++; break; - case NL80211_IFTYPE_WDS: - ic_opmode = NL80211_IFTYPE_WDS; + case NL80211_IFTYPE_STATION: + iter_data->nstations++; break; case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_AP: + iter_data->nadhocs++; + break; case NL80211_IFTYPE_MESH_POINT: - if (sc->nbcnvifs >= ATH_BCBUF) { - ret = -ENOBUFS; - goto out; - } - ic_opmode = vif->type; + iter_data->nmeshes++; + break; + case NL80211_IFTYPE_WDS: + iter_data->nwds++; break; default: - ath_err(common, "Interface type %d not yet supported\n", - vif->type); - ret = -EOPNOTSUPP; - goto out; + iter_data->nothers++; + break; } +} - ath_dbg(common, ATH_DBG_CONFIG, - "Attach a VIF of type: %d\n", ic_opmode); +/* Called with sc->mutex held. */ +void ath9k_calculate_iter_data(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ath9k_vif_iter_data *iter_data) +{ + struct ath_softc *sc = hw->priv; + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); - /* Set the VIF opmode */ - avp->av_opmode = ic_opmode; - avp->av_bslot = -1; + /* + * Use the hardware MAC address as reference, the hardware uses it + * together with the BSSID mask when matching addresses. + */ + memset(iter_data, 0, sizeof(*iter_data)); + iter_data->hw_macaddr = common->macaddr; + memset(&iter_data->mask, 0xff, ETH_ALEN); - sc->nvifs++; + if (vif) + ath9k_vif_iter(iter_data, vif->addr, vif); - ath9k_set_bssid_mask(hw, vif); + /* Get list of all active MAC addresses */ + ieee80211_iterate_active_interfaces_atomic(sc->hw, ath9k_vif_iter, + iter_data); +} - if (sc->nvifs > 1) - goto out; /* skip global settings for secondary vif */ +/* Called with sc->mutex held. */ +static void ath9k_calculate_summary_state(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct ath_softc *sc = hw->priv; + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); + struct ath9k_vif_iter_data iter_data; + + ath9k_calculate_iter_data(hw, vif, &iter_data); + + ath9k_ps_wakeup(sc); + /* Set BSSID mask. */ + memcpy(common->bssidmask, iter_data.mask, ETH_ALEN); + ath_hw_setbssidmask(common); - if (ic_opmode == NL80211_IFTYPE_AP) { + /* Set op-mode & TSF */ + if (iter_data.naps > 0) { ath9k_hw_set_tsfadjust(ah, 1); sc->sc_flags |= SC_OP_TSF_RESET; - } + ah->opmode = NL80211_IFTYPE_AP; + } else { + ath9k_hw_set_tsfadjust(ah, 0); + sc->sc_flags &= ~SC_OP_TSF_RESET; - /* Set the device opmode */ - ah->opmode = ic_opmode; + if (iter_data.nwds + iter_data.nmeshes) + ah->opmode = NL80211_IFTYPE_AP; + else if (iter_data.nadhocs) + ah->opmode = NL80211_IFTYPE_ADHOC; + else + ah->opmode = NL80211_IFTYPE_STATION; + } /* * Enable MIB interrupts when there are hardware phy counters. - * Note we only do this (at the moment) for station mode. */ - if ((vif->type == NL80211_IFTYPE_STATION) || - (vif->type == NL80211_IFTYPE_ADHOC) || - (vif->type == NL80211_IFTYPE_MESH_POINT)) { + if ((iter_data.nstations + iter_data.nadhocs + iter_data.nmeshes) > 0) { if (ah->config.enable_ani) ah->imask |= ATH9K_INT_MIB; ah->imask |= ATH9K_INT_TSFOOR; + } else { + ah->imask &= ~ATH9K_INT_MIB; + ah->imask &= ~ATH9K_INT_TSFOOR; } ath9k_hw_set_interrupts(ah, ah->imask); + ath9k_ps_restore(sc); - if (vif->type == NL80211_IFTYPE_AP || - vif->type == NL80211_IFTYPE_ADHOC) { + /* Set up ANI */ + if ((iter_data.naps + iter_data.nadhocs) > 0) { sc->sc_flags |= SC_OP_ANI_RUN; ath_start_ani(common); + } else { + sc->sc_flags &= ~SC_OP_ANI_RUN; + del_timer_sync(&common->ani.timer); } +} -out: - mutex_unlock(&sc->mutex); - return ret; +/* Called with sc->mutex held, vif counts set up properly. */ +static void ath9k_do_vif_add_setup(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct ath_softc *sc = hw->priv; + + ath9k_calculate_summary_state(hw, vif); + + if (ath9k_uses_beacons(vif->type)) { + int error; + ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); + /* This may fail because upper levels do not have beacons + * properly configured yet. That's OK, we assume it + * will be properly configured and then we will be notified + * in the info_changed method and set up beacons properly + * there. + */ + error = ath_beacon_alloc(sc, vif); + if (!error) + ath_beacon_config(sc, vif); + } } -static void ath9k_reclaim_beacon(struct ath_softc *sc, - struct ieee80211_vif *vif) + +static int ath9k_add_interface(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { + struct ath_softc *sc = hw->priv; + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); struct ath_vif *avp = (void *)vif->drv_priv; + int ret = 0; - /* Disable SWBA interrupt */ - sc->sc_ah->imask &= ~ATH9K_INT_SWBA; - ath9k_ps_wakeup(sc); - ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); - ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); - tasklet_kill(&sc->bcon_tasklet); - ath9k_ps_restore(sc); + mutex_lock(&sc->mutex); - ath_beacon_return(sc, avp); - sc->sc_flags &= ~SC_OP_BEACONS; + switch (vif->type) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_MESH_POINT: + break; + default: + ath_err(common, "Interface type %d not yet supported\n", + vif->type); + ret = -EOPNOTSUPP; + goto out; + } - if (sc->nbcnvifs > 0) { - /* Re-enable beaconing */ - sc->sc_ah->imask |= ATH9K_INT_SWBA; - ath9k_ps_wakeup(sc); - ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); - ath9k_ps_restore(sc); + if (ath9k_uses_beacons(vif->type)) { + if (sc->nbcnvifs >= ATH_BCBUF) { + ath_err(common, "Not enough beacon buffers when adding" + " new interface of type: %i\n", + vif->type); + ret = -ENOBUFS; + goto out; + } + } + + if ((vif->type == NL80211_IFTYPE_ADHOC) && + sc->nvifs > 0) { + ath_err(common, "Cannot create ADHOC interface when other" + " interfaces already exist.\n"); + ret = -EINVAL; + goto out; } + + ath_dbg(common, ATH_DBG_CONFIG, + "Attach a VIF of type: %d\n", vif->type); + + /* Set the VIF opmode */ + avp->av_opmode = vif->type; + avp->av_bslot = -1; + + sc->nvifs++; + + ath9k_do_vif_add_setup(hw, vif); +out: + mutex_unlock(&sc->mutex); + return ret; } static int ath9k_change_interface(struct ieee80211_hw *hw, @@ -1465,40 +1513,40 @@ static int ath9k_change_interface(struct ieee80211_hw *hw, enum nl80211_iftype new_type, bool p2p) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); int ret = 0; ath_dbg(common, ATH_DBG_CONFIG, "Change Interface\n"); mutex_lock(&sc->mutex); - switch (new_type) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_ADHOC: + /* See if new interface type is valid. */ + if ((new_type == NL80211_IFTYPE_ADHOC) && + (sc->nvifs > 1)) { + ath_err(common, "When using ADHOC, it must be the only" + " interface.\n"); + ret = -EINVAL; + goto out; + } + + if (ath9k_uses_beacons(new_type) && + !ath9k_uses_beacons(vif->type)) { if (sc->nbcnvifs >= ATH_BCBUF) { ath_err(common, "No beacon slot available\n"); ret = -ENOBUFS; goto out; } - break; - case NL80211_IFTYPE_STATION: - /* Stop ANI */ - sc->sc_flags &= ~SC_OP_ANI_RUN; - del_timer_sync(&common->ani.timer); - if ((vif->type == NL80211_IFTYPE_AP) || - (vif->type == NL80211_IFTYPE_ADHOC)) - ath9k_reclaim_beacon(sc, vif); - break; - default: - ath_err(common, "Interface type %d not yet supported\n", - vif->type); - ret = -ENOTSUPP; - goto out; } + + /* Clean up old vif stuff */ + if (ath9k_uses_beacons(vif->type)) + ath9k_reclaim_beacon(sc, vif); + + /* Add new settings */ vif->type = new_type; vif->p2p = p2p; + ath9k_do_vif_add_setup(hw, vif); out: mutex_unlock(&sc->mutex); return ret; @@ -1507,25 +1555,20 @@ out: static void ath9k_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); ath_dbg(common, ATH_DBG_CONFIG, "Detach Interface\n"); mutex_lock(&sc->mutex); - /* Stop ANI */ - sc->sc_flags &= ~SC_OP_ANI_RUN; - del_timer_sync(&common->ani.timer); + sc->nvifs--; /* Reclaim beacon resources */ - if ((sc->sc_ah->opmode == NL80211_IFTYPE_AP) || - (sc->sc_ah->opmode == NL80211_IFTYPE_ADHOC) || - (sc->sc_ah->opmode == NL80211_IFTYPE_MESH_POINT)) + if (ath9k_uses_beacons(vif->type)) ath9k_reclaim_beacon(sc, vif); - sc->nvifs--; + ath9k_calculate_summary_state(hw, NULL); mutex_unlock(&sc->mutex); } @@ -1566,12 +1609,11 @@ static void ath9k_disable_ps(struct ath_softc *sc) static int ath9k_config(struct ieee80211_hw *hw, u32 changed) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); struct ieee80211_conf *conf = &hw->conf; - bool disable_radio; + bool disable_radio = false; mutex_lock(&sc->mutex); @@ -1582,29 +1624,13 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed) * the end. */ if (changed & IEEE80211_CONF_CHANGE_IDLE) { - bool enable_radio; - bool all_wiphys_idle; - bool idle = !!(conf->flags & IEEE80211_CONF_IDLE); - - spin_lock_bh(&sc->wiphy_lock); - all_wiphys_idle = ath9k_all_wiphys_idle(sc); - ath9k_set_wiphy_idle(aphy, idle); - - enable_radio = (!idle && all_wiphys_idle); - - /* - * After we unlock here its possible another wiphy - * can be re-renabled so to account for that we will - * only disable the radio toward the end of this routine - * if by then all wiphys are still idle. - */ - spin_unlock_bh(&sc->wiphy_lock); - - if (enable_radio) { - sc->ps_idle = false; + sc->ps_idle = !!(conf->flags & IEEE80211_CONF_IDLE); + if (!sc->ps_idle) { ath_radio_enable(sc, hw); ath_dbg(common, ATH_DBG_CONFIG, "not-idle: enabling radio\n"); + } else { + disable_radio = true; } } @@ -1645,29 +1671,16 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed) if (ah->curchan) old_pos = ah->curchan - &ah->channels[0]; - aphy->chan_idx = pos; - aphy->chan_is_ht = conf_is_ht(conf); if (hw->conf.flags & IEEE80211_CONF_OFFCHANNEL) sc->sc_flags |= SC_OP_OFFCHANNEL; else sc->sc_flags &= ~SC_OP_OFFCHANNEL; - if (aphy->state == ATH_WIPHY_SCAN || - aphy->state == ATH_WIPHY_ACTIVE) - ath9k_wiphy_pause_all_forced(sc, aphy); - else { - /* - * Do not change operational channel based on a paused - * wiphy changes. - */ - goto skip_chan_change; - } - ath_dbg(common, ATH_DBG_CONFIG, "Set channel: %d MHz\n", curchan->center_freq); - /* XXX: remove me eventualy */ - ath9k_update_ichannel(sc, hw, &sc->sc_ah->channels[pos]); + ath9k_cmn_update_ichannel(&sc->sc_ah->channels[pos], + curchan, conf->channel_type); /* update survey stats for the old channel before switching */ spin_lock_irqsave(&common->cc_lock, flags); @@ -1709,21 +1722,16 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed) ath_update_survey_nf(sc, old_pos); } -skip_chan_change: if (changed & IEEE80211_CONF_CHANGE_POWER) { sc->config.txpowlimit = 2 * conf->power_level; ath9k_ps_wakeup(sc); - ath_update_txpow(sc); + ath9k_cmn_update_txpow(ah, sc->curtxpow, + sc->config.txpowlimit, &sc->curtxpow); ath9k_ps_restore(sc); } - spin_lock_bh(&sc->wiphy_lock); - disable_radio = ath9k_all_wiphys_idle(sc); - spin_unlock_bh(&sc->wiphy_lock); - if (disable_radio) { ath_dbg(common, ATH_DBG_CONFIG, "idle: disabling radio\n"); - sc->ps_idle = true; ath_radio_disable(sc, hw); } @@ -1748,8 +1756,7 @@ static void ath9k_configure_filter(struct ieee80211_hw *hw, unsigned int *total_flags, u64 multicast) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; u32 rfilt; changed_flags &= SUPPORTED_FILTERS; @@ -1769,8 +1776,7 @@ static int ath9k_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; ath_node_attach(sc, sta); @@ -1781,8 +1787,7 @@ static int ath9k_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; ath_node_detach(sc, sta); @@ -1792,8 +1797,7 @@ static int ath9k_sta_remove(struct ieee80211_hw *hw, static int ath9k_conf_tx(struct ieee80211_hw *hw, u16 queue, const struct ieee80211_tx_queue_params *params) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_txq *txq; struct ath9k_tx_queue_info qi; @@ -1837,8 +1841,7 @@ static int ath9k_set_key(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_key_conf *key) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); int ret = 0; @@ -1882,8 +1885,7 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_bss_conf *bss_conf, u32 changed) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); struct ath_vif *avp = (void *)vif->drv_priv; @@ -1913,7 +1915,7 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw, if ((changed & BSS_CHANGED_BEACON) || ((changed & BSS_CHANGED_BEACON_ENABLED) && bss_conf->enable_beacon)) { ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); - error = ath_beacon_alloc(aphy, vif); + error = ath_beacon_alloc(sc, vif); if (!error) ath_beacon_config(sc, vif); } @@ -1950,7 +1952,7 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw, if (vif->type == NL80211_IFTYPE_AP) { sc->sc_flags |= SC_OP_TSF_RESET; ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); - error = ath_beacon_alloc(aphy, vif); + error = ath_beacon_alloc(sc, vif); if (!error) ath_beacon_config(sc, vif); } else { @@ -1988,9 +1990,8 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw, static u64 ath9k_get_tsf(struct ieee80211_hw *hw) { + struct ath_softc *sc = hw->priv; u64 tsf; - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; mutex_lock(&sc->mutex); ath9k_ps_wakeup(sc); @@ -2003,8 +2004,7 @@ static u64 ath9k_get_tsf(struct ieee80211_hw *hw) static void ath9k_set_tsf(struct ieee80211_hw *hw, u64 tsf) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; mutex_lock(&sc->mutex); ath9k_ps_wakeup(sc); @@ -2015,8 +2015,7 @@ static void ath9k_set_tsf(struct ieee80211_hw *hw, u64 tsf) static void ath9k_reset_tsf(struct ieee80211_hw *hw) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; mutex_lock(&sc->mutex); @@ -2031,10 +2030,9 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn) + u16 tid, u16 *ssn, u8 buf_size) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; int ret = 0; local_bh_disable(); @@ -2079,8 +2077,7 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw, static int ath9k_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; @@ -2114,47 +2111,9 @@ static int ath9k_get_survey(struct ieee80211_hw *hw, int idx, return 0; } -static void ath9k_sw_scan_start(struct ieee80211_hw *hw) -{ - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; - - mutex_lock(&sc->mutex); - if (ath9k_wiphy_scanning(sc)) { - /* - * There is a race here in mac80211 but fixing it requires - * we revisit how we handle the scan complete callback. - * After mac80211 fixes we will not have configured hardware - * to the home channel nor would we have configured the RX - * filter yet. - */ - mutex_unlock(&sc->mutex); - return; - } - - aphy->state = ATH_WIPHY_SCAN; - ath9k_wiphy_pause_all_forced(sc, aphy); - mutex_unlock(&sc->mutex); -} - -/* - * XXX: this requires a revisit after the driver - * scan_complete gets moved to another place/removed in mac80211. - */ -static void ath9k_sw_scan_complete(struct ieee80211_hw *hw) -{ - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; - - mutex_lock(&sc->mutex); - aphy->state = ATH_WIPHY_ACTIVE; - mutex_unlock(&sc->mutex); -} - static void ath9k_set_coverage_class(struct ieee80211_hw *hw, u8 coverage_class) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = sc->sc_ah; mutex_lock(&sc->mutex); @@ -2182,8 +2141,6 @@ struct ieee80211_ops ath9k_ops = { .reset_tsf = ath9k_reset_tsf, .ampdu_action = ath9k_ampdu_action, .get_survey = ath9k_get_survey, - .sw_scan_start = ath9k_sw_scan_start, - .sw_scan_complete = ath9k_sw_scan_complete, .rfkill_poll = ath9k_rfkill_poll_state, .set_coverage_class = ath9k_set_coverage_class, }; diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c index 78ef1f1..e83128c 100644 --- a/drivers/net/wireless/ath/ath9k/pci.c +++ b/drivers/net/wireless/ath/ath9k/pci.c @@ -126,7 +126,6 @@ static const struct ath_bus_ops ath_pci_bus_ops = { static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { void __iomem *mem; - struct ath_wiphy *aphy; struct ath_softc *sc; struct ieee80211_hw *hw; u8 csz; @@ -198,8 +197,7 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_iomap; } - hw = ieee80211_alloc_hw(sizeof(struct ath_wiphy) + - sizeof(struct ath_softc), &ath9k_ops); + hw = ieee80211_alloc_hw(sizeof(struct ath_softc), &ath9k_ops); if (!hw) { dev_err(&pdev->dev, "No memory for ieee80211_hw\n"); ret = -ENOMEM; @@ -209,11 +207,7 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) SET_IEEE80211_DEV(hw, &pdev->dev); pci_set_drvdata(pdev, hw); - aphy = hw->priv; - sc = (struct ath_softc *) (aphy + 1); - aphy->sc = sc; - aphy->hw = hw; - sc->pri_wiphy = aphy; + sc = hw->priv; sc->hw = hw; sc->dev = &pdev->dev; sc->mem = mem; @@ -260,8 +254,7 @@ err_dma: static void ath_pci_remove(struct pci_dev *pdev) { struct ieee80211_hw *hw = pci_get_drvdata(pdev); - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; void __iomem *mem = sc->mem; if (!is_ath9k_unloaded) @@ -281,8 +274,7 @@ static int ath_pci_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct ieee80211_hw *hw = pci_get_drvdata(pdev); - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; ath9k_hw_set_gpio(sc->sc_ah, sc->sc_ah->led_pin, 1); @@ -293,8 +285,7 @@ static int ath_pci_resume(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct ieee80211_hw *hw = pci_get_drvdata(pdev); - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; u32 val; /* @@ -320,7 +311,6 @@ static int ath_pci_resume(struct device *device) ath9k_ps_restore(sc); sc->ps_idle = true; - ath9k_set_wiphy_idle(aphy, true); ath_radio_disable(sc, hw); return 0; diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c index e451478..960d717 100644 --- a/drivers/net/wireless/ath/ath9k/rc.c +++ b/drivers/net/wireless/ath/ath9k/rc.c @@ -1560,8 +1560,7 @@ static void ath_rate_add_sta_debugfs(void *priv, void *priv_sta, static void *ath_rate_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) { - struct ath_wiphy *aphy = hw->priv; - return aphy->sc; + return hw->priv; } static void ath_rate_free(void *priv) diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index b2497b8..daf171d 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -34,27 +34,6 @@ static inline bool ath9k_check_auto_sleep(struct ath_softc *sc) (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_AUTOSLEEP); } -static struct ieee80211_hw * ath_get_virt_hw(struct ath_softc *sc, - struct ieee80211_hdr *hdr) -{ - struct ieee80211_hw *hw = sc->pri_wiphy->hw; - int i; - - spin_lock_bh(&sc->wiphy_lock); - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - if (aphy == NULL) - continue; - if (compare_ether_addr(hdr->addr1, aphy->hw->wiphy->perm_addr) - == 0) { - hw = aphy->hw; - break; - } - } - spin_unlock_bh(&sc->wiphy_lock); - return hw; -} - /* * Setup and link descriptors. * @@ -230,11 +209,6 @@ static int ath_rx_edma_init(struct ath_softc *sc, int nbufs) int error = 0, i; u32 size; - - common->rx_bufsize = roundup(IEEE80211_MAX_MPDU_LEN + - ah->caps.rx_status_len, - min(common->cachelsz, (u16)64)); - ath9k_hw_set_rx_bufsize(ah, common->rx_bufsize - ah->caps.rx_status_len); @@ -321,12 +295,12 @@ int ath_rx_init(struct ath_softc *sc, int nbufs) sc->sc_flags &= ~SC_OP_RXFLUSH; spin_lock_init(&sc->rx.rxbuflock); + common->rx_bufsize = IEEE80211_MAX_MPDU_LEN / 2 + + sc->sc_ah->caps.rx_status_len; + if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) { return ath_rx_edma_init(sc, nbufs); } else { - common->rx_bufsize = roundup(IEEE80211_MAX_MPDU_LEN, - min(common->cachelsz, (u16)64)); - ath_dbg(common, ATH_DBG_CONFIG, "cachelsz %u rxbufsize %u\n", common->cachelsz, common->rx_bufsize); @@ -463,8 +437,7 @@ u32 ath_calcrxfilter(struct ath_softc *sc) if (conf_is_ht(&sc->hw->conf)) rfilt |= ATH9K_RX_FILTER_COMP_BAR; - if (sc->sec_wiphy || (sc->nvifs > 1) || - (sc->rx.rxfilter & FIF_OTHER_BSS)) { + if (sc->nvifs > 1 || (sc->rx.rxfilter & FIF_OTHER_BSS)) { /* The following may also be needed for other older chips */ if (sc->sc_ah->hw_version.macVersion == AR_SREV_VERSION_9160) rfilt |= ATH9K_RX_FILTER_PROM; @@ -588,8 +561,14 @@ static void ath_rx_ps_beacon(struct ath_softc *sc, struct sk_buff *skb) return; mgmt = (struct ieee80211_mgmt *)skb->data; - if (memcmp(common->curbssid, mgmt->bssid, ETH_ALEN) != 0) + if (memcmp(common->curbssid, mgmt->bssid, ETH_ALEN) != 0) { + /* TODO: This doesn't work well if you have stations + * associated to two different APs because curbssid + * is just the last AP that any of the stations associated + * with. + */ return; /* not from our current AP */ + } sc->ps_flags &= ~PS_WAIT_FOR_BEACON; @@ -662,37 +641,6 @@ static void ath_rx_ps(struct ath_softc *sc, struct sk_buff *skb) } } -static void ath_rx_send_to_mac80211(struct ieee80211_hw *hw, - struct ath_softc *sc, struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr; - - hdr = (struct ieee80211_hdr *)skb->data; - - /* Send the frame to mac80211 */ - if (is_multicast_ether_addr(hdr->addr1)) { - int i; - /* - * Deliver broadcast/multicast frames to all suitable - * virtual wiphys. - */ - /* TODO: filter based on channel configuration */ - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - struct sk_buff *nskb; - if (aphy == NULL) - continue; - nskb = skb_copy(skb, GFP_ATOMIC); - if (!nskb) - continue; - ieee80211_rx(aphy->hw, nskb); - } - ieee80211_rx(sc->hw, skb); - } else - /* Deliver unicast frames based on receiver address */ - ieee80211_rx(hw, skb); -} - static bool ath_edma_get_buffers(struct ath_softc *sc, enum ath9k_rx_qtype qtype) { @@ -862,15 +810,9 @@ static bool ath9k_rx_accept(struct ath_common *common, if (rx_stats->rs_datalen > (common->rx_bufsize - rx_status_len)) return false; - /* - * rs_more indicates chained descriptors which can be used - * to link buffers together for a sort of scatter-gather - * operation. - * reject the frame, we don't support scatter-gather yet and - * the frame is probably corrupt anyway - */ + /* Only use error bits from the last fragment */ if (rx_stats->rs_more) - return false; + return true; /* * The rx_stats->rs_status will not be set until the end of the @@ -974,7 +916,7 @@ static void ath9k_process_rssi(struct ath_common *common, struct ieee80211_hdr *hdr, struct ath_rx_status *rx_stats) { - struct ath_wiphy *aphy = hw->priv; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = common->ah; int last_rssi; __le16 fc; @@ -984,13 +926,19 @@ static void ath9k_process_rssi(struct ath_common *common, fc = hdr->frame_control; if (!ieee80211_is_beacon(fc) || - compare_ether_addr(hdr->addr3, common->curbssid)) + compare_ether_addr(hdr->addr3, common->curbssid)) { + /* TODO: This doesn't work well if you have stations + * associated to two different APs because curbssid + * is just the last AP that any of the stations associated + * with. + */ return; + } if (rx_stats->rs_rssi != ATH9K_RSSI_BAD && !rx_stats->rs_moreaggr) - ATH_RSSI_LPF(aphy->last_rssi, rx_stats->rs_rssi); + ATH_RSSI_LPF(sc->last_rssi, rx_stats->rs_rssi); - last_rssi = aphy->last_rssi; + last_rssi = sc->last_rssi; if (likely(last_rssi != ATH_RSSI_DUMMY_MARKER)) rx_stats->rs_rssi = ATH_EP_RND(last_rssi, ATH_RSSI_EP_MULTIPLIER); @@ -1022,6 +970,10 @@ static int ath9k_rx_skb_preprocess(struct ath_common *common, if (!ath9k_rx_accept(common, hdr, rx_status, rx_stats, decrypt_error)) return -EINVAL; + /* Only use status info from the last fragment */ + if (rx_stats->rs_more) + return 0; + ath9k_process_rssi(common, hw, hdr, rx_stats); if (ath9k_process_rate(common, hw, rx_stats, rx_status)) @@ -1623,7 +1575,7 @@ div_comb_done: int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) { struct ath_buf *bf; - struct sk_buff *skb = NULL, *requeue_skb; + struct sk_buff *skb = NULL, *requeue_skb, *hdr_skb; struct ieee80211_rx_status *rxs; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); @@ -1632,7 +1584,7 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) * virtual wiphy so to account for that we iterate over the active * wiphys and find the appropriate wiphy and therefore hw. */ - struct ieee80211_hw *hw = NULL; + struct ieee80211_hw *hw = sc->hw; struct ieee80211_hdr *hdr; int retval; bool decrypt_error = false; @@ -1674,10 +1626,17 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) if (!skb) continue; - hdr = (struct ieee80211_hdr *) (skb->data + rx_status_len); - rxs = IEEE80211_SKB_RXCB(skb); + /* + * Take frame header from the first fragment and RX status from + * the last one. + */ + if (sc->rx.frag) + hdr_skb = sc->rx.frag; + else + hdr_skb = skb; - hw = ath_get_virt_hw(sc, hdr); + hdr = (struct ieee80211_hdr *) (hdr_skb->data + rx_status_len); + rxs = IEEE80211_SKB_RXCB(hdr_skb); ath_debug_stat_rx(sc, &rs); @@ -1686,12 +1645,12 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) * chain it back at the queue without processing it. */ if (flush) - goto requeue; + goto requeue_drop_frag; retval = ath9k_rx_skb_preprocess(common, hw, hdr, &rs, rxs, &decrypt_error); if (retval) - goto requeue; + goto requeue_drop_frag; rxs->mactime = (tsf & ~0xffffffffULL) | rs.rs_tstamp; if (rs.rs_tstamp > tsf_lower && @@ -1711,7 +1670,7 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) * skb and put it at the tail of the sc->rx.rxbuf list for * processing. */ if (!requeue_skb) - goto requeue; + goto requeue_drop_frag; /* Unmap the frame */ dma_unmap_single(sc->dev, bf->bf_buf_addr, @@ -1722,8 +1681,9 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) if (ah->caps.rx_status_len) skb_pull(skb, ah->caps.rx_status_len); - ath9k_rx_skb_postprocess(common, skb, &rs, - rxs, decrypt_error); + if (!rs.rs_more) + ath9k_rx_skb_postprocess(common, hdr_skb, &rs, + rxs, decrypt_error); /* We will now give hardware our shiny new allocated skb */ bf->bf_mpdu = requeue_skb; @@ -1736,10 +1696,42 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) bf->bf_mpdu = NULL; bf->bf_buf_addr = 0; ath_err(common, "dma_mapping_error() on RX\n"); - ath_rx_send_to_mac80211(hw, sc, skb); + ieee80211_rx(hw, skb); break; } + if (rs.rs_more) { + /* + * rs_more indicates chained descriptors which can be + * used to link buffers together for a sort of + * scatter-gather operation. + */ + if (sc->rx.frag) { + /* too many fragments - cannot handle frame */ + dev_kfree_skb_any(sc->rx.frag); + dev_kfree_skb_any(skb); + skb = NULL; + } + sc->rx.frag = skb; + goto requeue; + } + + if (sc->rx.frag) { + int space = skb->len - skb_tailroom(hdr_skb); + + sc->rx.frag = NULL; + + if (pskb_expand_head(hdr_skb, 0, space, GFP_ATOMIC) < 0) { + dev_kfree_skb(skb); + goto requeue_drop_frag; + } + + skb_copy_from_linear_data(skb, skb_put(hdr_skb, skb->len), + skb->len); + dev_kfree_skb_any(skb); + skb = hdr_skb; + } + /* * change the default rx antenna if rx diversity chooses the * other antenna 3 times in a row. @@ -1763,8 +1755,13 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) if (ah->caps.hw_caps & ATH9K_HW_CAP_ANT_DIV_COMB) ath_ant_comb_scan(sc, &rs); - ath_rx_send_to_mac80211(hw, sc, skb); + ieee80211_rx(hw, skb); +requeue_drop_frag: + if (sc->rx.frag) { + dev_kfree_skb_any(sc->rx.frag); + sc->rx.frag = NULL; + } requeue: if (edma) { list_add_tail(&bf->list, &sc->rx.rxbuf); diff --git a/drivers/net/wireless/ath/ath9k/reg.h b/drivers/net/wireless/ath/ath9k/reg.h index 4df5659..b262e98 100644 --- a/drivers/net/wireless/ath/ath9k/reg.h +++ b/drivers/net/wireless/ath/ath9k/reg.h @@ -1083,6 +1083,17 @@ enum { #define AR_ENT_OTP 0x40d8 #define AR_ENT_OTP_CHAIN2_DISABLE 0x00020000 #define AR_ENT_OTP_MPSD 0x00800000 +#define AR_CH0_BB_DPLL2 0x16184 +#define AR_CH0_BB_DPLL3 0x16188 +#define AR_CH0_DDR_DPLL2 0x16244 +#define AR_CH0_DDR_DPLL3 0x16248 +#define AR_CH0_DPLL2_KD 0x03F80000 +#define AR_CH0_DPLL2_KD_S 19 +#define AR_CH0_DPLL2_KI 0x3C000000 +#define AR_CH0_DPLL2_KI_S 26 +#define AR_CH0_DPLL3_PHASE_SHIFT 0x3F800000 +#define AR_CH0_DPLL3_PHASE_SHIFT_S 23 +#define AR_PHY_CCA_NOM_VAL_2GHZ -118 #define AR_RTC_9300_PLL_DIV 0x000003ff #define AR_RTC_9300_PLL_DIV_S 0 @@ -1129,6 +1140,12 @@ enum { #define AR_RTC_PLL_CLKSEL 0x00000300 #define AR_RTC_PLL_CLKSEL_S 8 +#define PLL3 0x16188 +#define PLL3_DO_MEAS_MASK 0x40000000 +#define PLL4 0x1618c +#define PLL4_MEAS_DONE 0x8 +#define SQSUM_DVC_MASK 0x007ffff8 + #define AR_RTC_RESET \ ((AR_SREV_9100(ah)) ? (AR_RTC_BASE + 0x0040) : 0x7040) #define AR_RTC_RESET_EN (0x00000001) diff --git a/drivers/net/wireless/ath/ath9k/virtual.c b/drivers/net/wireless/ath/ath9k/virtual.c deleted file mode 100644 index 2dc7095..0000000 --- a/drivers/net/wireless/ath/ath9k/virtual.c +++ /dev/null @@ -1,717 +0,0 @@ -/* - * Copyright (c) 2008-2009 Atheros Communications Inc. - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -#include <linux/slab.h> - -#include "ath9k.h" - -struct ath9k_vif_iter_data { - const u8 *hw_macaddr; - u8 mask[ETH_ALEN]; -}; - -static void ath9k_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif) -{ - struct ath9k_vif_iter_data *iter_data = data; - int i; - - for (i = 0; i < ETH_ALEN; i++) - iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]); -} - -void ath9k_set_bssid_mask(struct ieee80211_hw *hw, struct ieee80211_vif *vif) -{ - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; - struct ath_common *common = ath9k_hw_common(sc->sc_ah); - struct ath9k_vif_iter_data iter_data; - int i; - - /* - * Use the hardware MAC address as reference, the hardware uses it - * together with the BSSID mask when matching addresses. - */ - iter_data.hw_macaddr = common->macaddr; - memset(&iter_data.mask, 0xff, ETH_ALEN); - - if (vif) - ath9k_vif_iter(&iter_data, vif->addr, vif); - - /* Get list of all active MAC addresses */ - spin_lock_bh(&sc->wiphy_lock); - ieee80211_iterate_active_interfaces_atomic(sc->hw, ath9k_vif_iter, - &iter_data); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] == NULL) - continue; - ieee80211_iterate_active_interfaces_atomic( - sc->sec_wiphy[i]->hw, ath9k_vif_iter, &iter_data); - } - spin_unlock_bh(&sc->wiphy_lock); - - memcpy(common->bssidmask, iter_data.mask, ETH_ALEN); - ath_hw_setbssidmask(common); -} - -int ath9k_wiphy_add(struct ath_softc *sc) -{ - int i, error; - struct ath_wiphy *aphy; - struct ath_common *common = ath9k_hw_common(sc->sc_ah); - struct ieee80211_hw *hw; - u8 addr[ETH_ALEN]; - - hw = ieee80211_alloc_hw(sizeof(struct ath_wiphy), &ath9k_ops); - if (hw == NULL) - return -ENOMEM; - - spin_lock_bh(&sc->wiphy_lock); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] == NULL) - break; - } - - if (i == sc->num_sec_wiphy) { - /* No empty slot available; increase array length */ - struct ath_wiphy **n; - n = krealloc(sc->sec_wiphy, - (sc->num_sec_wiphy + 1) * - sizeof(struct ath_wiphy *), - GFP_ATOMIC); - if (n == NULL) { - spin_unlock_bh(&sc->wiphy_lock); - ieee80211_free_hw(hw); - return -ENOMEM; - } - n[i] = NULL; - sc->sec_wiphy = n; - sc->num_sec_wiphy++; - } - - SET_IEEE80211_DEV(hw, sc->dev); - - aphy = hw->priv; - aphy->sc = sc; - aphy->hw = hw; - sc->sec_wiphy[i] = aphy; - aphy->last_rssi = ATH_RSSI_DUMMY_MARKER; - spin_unlock_bh(&sc->wiphy_lock); - - memcpy(addr, common->macaddr, ETH_ALEN); - addr[0] |= 0x02; /* Locally managed address */ - /* - * XOR virtual wiphy index into the least significant bits to generate - * a different MAC address for each virtual wiphy. - */ - addr[5] ^= i & 0xff; - addr[4] ^= (i & 0xff00) >> 8; - addr[3] ^= (i & 0xff0000) >> 16; - - SET_IEEE80211_PERM_ADDR(hw, addr); - - ath9k_set_hw_capab(sc, hw); - - error = ieee80211_register_hw(hw); - - if (error == 0) { - /* Make sure wiphy scheduler is started (if enabled) */ - ath9k_wiphy_set_scheduler(sc, sc->wiphy_scheduler_int); - } - - return error; -} - -int ath9k_wiphy_del(struct ath_wiphy *aphy) -{ - struct ath_softc *sc = aphy->sc; - int i; - - spin_lock_bh(&sc->wiphy_lock); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (aphy == sc->sec_wiphy[i]) { - sc->sec_wiphy[i] = NULL; - spin_unlock_bh(&sc->wiphy_lock); - ieee80211_unregister_hw(aphy->hw); - ieee80211_free_hw(aphy->hw); - return 0; - } - } - spin_unlock_bh(&sc->wiphy_lock); - return -ENOENT; -} - -static int ath9k_send_nullfunc(struct ath_wiphy *aphy, - struct ieee80211_vif *vif, const u8 *bssid, - int ps) -{ - struct ath_softc *sc = aphy->sc; - struct ath_tx_control txctl; - struct sk_buff *skb; - struct ieee80211_hdr *hdr; - __le16 fc; - struct ieee80211_tx_info *info; - - skb = dev_alloc_skb(24); - if (skb == NULL) - return -ENOMEM; - hdr = (struct ieee80211_hdr *) skb_put(skb, 24); - memset(hdr, 0, 24); - fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | - IEEE80211_FCTL_TODS); - if (ps) - fc |= cpu_to_le16(IEEE80211_FCTL_PM); - hdr->frame_control = fc; - memcpy(hdr->addr1, bssid, ETH_ALEN); - memcpy(hdr->addr2, aphy->hw->wiphy->perm_addr, ETH_ALEN); - memcpy(hdr->addr3, bssid, ETH_ALEN); - - info = IEEE80211_SKB_CB(skb); - memset(info, 0, sizeof(*info)); - info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS; - info->control.vif = vif; - info->control.rates[0].idx = 0; - info->control.rates[0].count = 4; - info->control.rates[1].idx = -1; - - memset(&txctl, 0, sizeof(struct ath_tx_control)); - txctl.txq = sc->tx.txq_map[WME_AC_VO]; - txctl.frame_type = ps ? ATH9K_IFT_PAUSE : ATH9K_IFT_UNPAUSE; - - if (ath_tx_start(aphy->hw, skb, &txctl) != 0) - goto exit; - - return 0; -exit: - dev_kfree_skb_any(skb); - return -1; -} - -static bool __ath9k_wiphy_pausing(struct ath_softc *sc) -{ - int i; - if (sc->pri_wiphy->state == ATH_WIPHY_PAUSING) - return true; - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] && - sc->sec_wiphy[i]->state == ATH_WIPHY_PAUSING) - return true; - } - return false; -} - -static bool ath9k_wiphy_pausing(struct ath_softc *sc) -{ - bool ret; - spin_lock_bh(&sc->wiphy_lock); - ret = __ath9k_wiphy_pausing(sc); - spin_unlock_bh(&sc->wiphy_lock); - return ret; -} - -static bool __ath9k_wiphy_scanning(struct ath_softc *sc) -{ - int i; - if (sc->pri_wiphy->state == ATH_WIPHY_SCAN) - return true; - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] && - sc->sec_wiphy[i]->state == ATH_WIPHY_SCAN) - return true; - } - return false; -} - -bool ath9k_wiphy_scanning(struct ath_softc *sc) -{ - bool ret; - spin_lock_bh(&sc->wiphy_lock); - ret = __ath9k_wiphy_scanning(sc); - spin_unlock_bh(&sc->wiphy_lock); - return ret; -} - -static int __ath9k_wiphy_unpause(struct ath_wiphy *aphy); - -/* caller must hold wiphy_lock */ -static void __ath9k_wiphy_unpause_ch(struct ath_wiphy *aphy) -{ - if (aphy == NULL) - return; - if (aphy->chan_idx != aphy->sc->chan_idx) - return; /* wiphy not on the selected channel */ - __ath9k_wiphy_unpause(aphy); -} - -static void ath9k_wiphy_unpause_channel(struct ath_softc *sc) -{ - int i; - spin_lock_bh(&sc->wiphy_lock); - __ath9k_wiphy_unpause_ch(sc->pri_wiphy); - for (i = 0; i < sc->num_sec_wiphy; i++) - __ath9k_wiphy_unpause_ch(sc->sec_wiphy[i]); - spin_unlock_bh(&sc->wiphy_lock); -} - -void ath9k_wiphy_chan_work(struct work_struct *work) -{ - struct ath_softc *sc = container_of(work, struct ath_softc, chan_work); - struct ath_common *common = ath9k_hw_common(sc->sc_ah); - struct ath_wiphy *aphy = sc->next_wiphy; - - if (aphy == NULL) - return; - - /* - * All pending interfaces paused; ready to change - * channels. - */ - - /* Change channels */ - mutex_lock(&sc->mutex); - /* XXX: remove me eventually */ - ath9k_update_ichannel(sc, aphy->hw, - &sc->sc_ah->channels[sc->chan_idx]); - - /* sync hw configuration for hw code */ - common->hw = aphy->hw; - - if (ath_set_channel(sc, aphy->hw, - &sc->sc_ah->channels[sc->chan_idx]) < 0) { - printk(KERN_DEBUG "ath9k: Failed to set channel for new " - "virtual wiphy\n"); - mutex_unlock(&sc->mutex); - return; - } - mutex_unlock(&sc->mutex); - - ath9k_wiphy_unpause_channel(sc); -} - -/* - * ath9k version of ieee80211_tx_status() for TX frames that are generated - * internally in the driver. - */ -void ath9k_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb, int ftype) -{ - struct ath_wiphy *aphy = hw->priv; - struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); - - if (ftype == ATH9K_IFT_PAUSE && aphy->state == ATH_WIPHY_PAUSING) { - if (!(tx_info->flags & IEEE80211_TX_STAT_ACK)) { - printk(KERN_DEBUG "ath9k: %s: no ACK for pause " - "frame\n", wiphy_name(hw->wiphy)); - /* - * The AP did not reply; ignore this to allow us to - * continue. - */ - } - aphy->state = ATH_WIPHY_PAUSED; - if (!ath9k_wiphy_pausing(aphy->sc)) { - /* - * Drop from tasklet to work to allow mutex for channel - * change. - */ - ieee80211_queue_work(aphy->sc->hw, - &aphy->sc->chan_work); - } - } - - dev_kfree_skb(skb); -} - -static void ath9k_mark_paused(struct ath_wiphy *aphy) -{ - struct ath_softc *sc = aphy->sc; - aphy->state = ATH_WIPHY_PAUSED; - if (!__ath9k_wiphy_pausing(sc)) - ieee80211_queue_work(sc->hw, &sc->chan_work); -} - -static void ath9k_pause_iter(void *data, u8 *mac, struct ieee80211_vif *vif) -{ - struct ath_wiphy *aphy = data; - struct ath_vif *avp = (void *) vif->drv_priv; - - switch (vif->type) { - case NL80211_IFTYPE_STATION: - if (!vif->bss_conf.assoc) { - ath9k_mark_paused(aphy); - break; - } - /* TODO: could avoid this if already in PS mode */ - if (ath9k_send_nullfunc(aphy, vif, avp->bssid, 1)) { - printk(KERN_DEBUG "%s: failed to send PS nullfunc\n", - __func__); - ath9k_mark_paused(aphy); - } - break; - case NL80211_IFTYPE_AP: - /* Beacon transmission is paused by aphy->state change */ - ath9k_mark_paused(aphy); - break; - default: - break; - } -} - -/* caller must hold wiphy_lock */ -static int __ath9k_wiphy_pause(struct ath_wiphy *aphy) -{ - ieee80211_stop_queues(aphy->hw); - aphy->state = ATH_WIPHY_PAUSING; - /* - * TODO: handle PAUSING->PAUSED for the case where there are multiple - * active vifs (now we do it on the first vif getting ready; should be - * on the last) - */ - ieee80211_iterate_active_interfaces_atomic(aphy->hw, ath9k_pause_iter, - aphy); - return 0; -} - -int ath9k_wiphy_pause(struct ath_wiphy *aphy) -{ - int ret; - spin_lock_bh(&aphy->sc->wiphy_lock); - ret = __ath9k_wiphy_pause(aphy); - spin_unlock_bh(&aphy->sc->wiphy_lock); - return ret; -} - -static void ath9k_unpause_iter(void *data, u8 *mac, struct ieee80211_vif *vif) -{ - struct ath_wiphy *aphy = data; - struct ath_vif *avp = (void *) vif->drv_priv; - - switch (vif->type) { - case NL80211_IFTYPE_STATION: - if (!vif->bss_conf.assoc) - break; - ath9k_send_nullfunc(aphy, vif, avp->bssid, 0); - break; - case NL80211_IFTYPE_AP: - /* Beacon transmission is re-enabled by aphy->state change */ - break; - default: - break; - } -} - -/* caller must hold wiphy_lock */ -static int __ath9k_wiphy_unpause(struct ath_wiphy *aphy) -{ - ieee80211_iterate_active_interfaces_atomic(aphy->hw, - ath9k_unpause_iter, aphy); - aphy->state = ATH_WIPHY_ACTIVE; - ieee80211_wake_queues(aphy->hw); - return 0; -} - -int ath9k_wiphy_unpause(struct ath_wiphy *aphy) -{ - int ret; - spin_lock_bh(&aphy->sc->wiphy_lock); - ret = __ath9k_wiphy_unpause(aphy); - spin_unlock_bh(&aphy->sc->wiphy_lock); - return ret; -} - -static void __ath9k_wiphy_mark_all_paused(struct ath_softc *sc) -{ - int i; - if (sc->pri_wiphy->state != ATH_WIPHY_INACTIVE) - sc->pri_wiphy->state = ATH_WIPHY_PAUSED; - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] && - sc->sec_wiphy[i]->state != ATH_WIPHY_INACTIVE) - sc->sec_wiphy[i]->state = ATH_WIPHY_PAUSED; - } -} - -/* caller must hold wiphy_lock */ -static void __ath9k_wiphy_pause_all(struct ath_softc *sc) -{ - int i; - if (sc->pri_wiphy->state == ATH_WIPHY_ACTIVE) - __ath9k_wiphy_pause(sc->pri_wiphy); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] && - sc->sec_wiphy[i]->state == ATH_WIPHY_ACTIVE) - __ath9k_wiphy_pause(sc->sec_wiphy[i]); - } -} - -int ath9k_wiphy_select(struct ath_wiphy *aphy) -{ - struct ath_softc *sc = aphy->sc; - bool now; - - spin_lock_bh(&sc->wiphy_lock); - if (__ath9k_wiphy_scanning(sc)) { - /* - * For now, we are using mac80211 sw scan and it expects to - * have full control over channel changes, so avoid wiphy - * scheduling during a scan. This could be optimized if the - * scanning control were moved into the driver. - */ - spin_unlock_bh(&sc->wiphy_lock); - return -EBUSY; - } - if (__ath9k_wiphy_pausing(sc)) { - if (sc->wiphy_select_failures == 0) - sc->wiphy_select_first_fail = jiffies; - sc->wiphy_select_failures++; - if (time_after(jiffies, sc->wiphy_select_first_fail + HZ / 2)) - { - printk(KERN_DEBUG "ath9k: Previous wiphy select timed " - "out; disable/enable hw to recover\n"); - __ath9k_wiphy_mark_all_paused(sc); - /* - * TODO: this workaround to fix hardware is unlikely to - * be specific to virtual wiphy changes. It can happen - * on normal channel change, too, and as such, this - * should really be made more generic. For example, - * tricker radio disable/enable on GTT interrupt burst - * (say, 10 GTT interrupts received without any TX - * frame being completed) - */ - spin_unlock_bh(&sc->wiphy_lock); - ath_radio_disable(sc, aphy->hw); - ath_radio_enable(sc, aphy->hw); - /* Only the primary wiphy hw is used for queuing work */ - ieee80211_queue_work(aphy->sc->hw, - &aphy->sc->chan_work); - return -EBUSY; /* previous select still in progress */ - } - spin_unlock_bh(&sc->wiphy_lock); - return -EBUSY; /* previous select still in progress */ - } - sc->wiphy_select_failures = 0; - - /* Store the new channel */ - sc->chan_idx = aphy->chan_idx; - sc->chan_is_ht = aphy->chan_is_ht; - sc->next_wiphy = aphy; - - __ath9k_wiphy_pause_all(sc); - now = !__ath9k_wiphy_pausing(aphy->sc); - spin_unlock_bh(&sc->wiphy_lock); - - if (now) { - /* Ready to request channel change immediately */ - ieee80211_queue_work(aphy->sc->hw, &aphy->sc->chan_work); - } - - /* - * wiphys will be unpaused in ath9k_tx_status() once channel has been - * changed if any wiphy needs time to become paused. - */ - - return 0; -} - -bool ath9k_wiphy_started(struct ath_softc *sc) -{ - int i; - spin_lock_bh(&sc->wiphy_lock); - if (sc->pri_wiphy->state != ATH_WIPHY_INACTIVE) { - spin_unlock_bh(&sc->wiphy_lock); - return true; - } - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] && - sc->sec_wiphy[i]->state != ATH_WIPHY_INACTIVE) { - spin_unlock_bh(&sc->wiphy_lock); - return true; - } - } - spin_unlock_bh(&sc->wiphy_lock); - return false; -} - -static void ath9k_wiphy_pause_chan(struct ath_wiphy *aphy, - struct ath_wiphy *selected) -{ - if (selected->state == ATH_WIPHY_SCAN) { - if (aphy == selected) - return; - /* - * Pause all other wiphys for the duration of the scan even if - * they are on the current channel now. - */ - } else if (aphy->chan_idx == selected->chan_idx) - return; - aphy->state = ATH_WIPHY_PAUSED; - ieee80211_stop_queues(aphy->hw); -} - -void ath9k_wiphy_pause_all_forced(struct ath_softc *sc, - struct ath_wiphy *selected) -{ - int i; - spin_lock_bh(&sc->wiphy_lock); - if (sc->pri_wiphy->state == ATH_WIPHY_ACTIVE) - ath9k_wiphy_pause_chan(sc->pri_wiphy, selected); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] && - sc->sec_wiphy[i]->state == ATH_WIPHY_ACTIVE) - ath9k_wiphy_pause_chan(sc->sec_wiphy[i], selected); - } - spin_unlock_bh(&sc->wiphy_lock); -} - -void ath9k_wiphy_work(struct work_struct *work) -{ - struct ath_softc *sc = container_of(work, struct ath_softc, - wiphy_work.work); - struct ath_wiphy *aphy = NULL; - bool first = true; - - spin_lock_bh(&sc->wiphy_lock); - - if (sc->wiphy_scheduler_int == 0) { - /* wiphy scheduler is disabled */ - spin_unlock_bh(&sc->wiphy_lock); - return; - } - -try_again: - sc->wiphy_scheduler_index++; - while (sc->wiphy_scheduler_index <= sc->num_sec_wiphy) { - aphy = sc->sec_wiphy[sc->wiphy_scheduler_index - 1]; - if (aphy && aphy->state != ATH_WIPHY_INACTIVE) - break; - - sc->wiphy_scheduler_index++; - aphy = NULL; - } - if (aphy == NULL) { - sc->wiphy_scheduler_index = 0; - if (sc->pri_wiphy->state == ATH_WIPHY_INACTIVE) { - if (first) { - first = false; - goto try_again; - } - /* No wiphy is ready to be scheduled */ - } else - aphy = sc->pri_wiphy; - } - - spin_unlock_bh(&sc->wiphy_lock); - - if (aphy && - aphy->state != ATH_WIPHY_ACTIVE && aphy->state != ATH_WIPHY_SCAN && - ath9k_wiphy_select(aphy)) { - printk(KERN_DEBUG "ath9k: Failed to schedule virtual wiphy " - "change\n"); - } - - ieee80211_queue_delayed_work(sc->hw, - &sc->wiphy_work, - sc->wiphy_scheduler_int); -} - -void ath9k_wiphy_set_scheduler(struct ath_softc *sc, unsigned int msec_int) -{ - cancel_delayed_work_sync(&sc->wiphy_work); - sc->wiphy_scheduler_int = msecs_to_jiffies(msec_int); - if (sc->wiphy_scheduler_int) - ieee80211_queue_delayed_work(sc->hw, &sc->wiphy_work, - sc->wiphy_scheduler_int); -} - -/* caller must hold wiphy_lock */ -bool ath9k_all_wiphys_idle(struct ath_softc *sc) -{ - unsigned int i; - if (!sc->pri_wiphy->idle) - return false; - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - if (!aphy) - continue; - if (!aphy->idle) - return false; - } - return true; -} - -/* caller must hold wiphy_lock */ -void ath9k_set_wiphy_idle(struct ath_wiphy *aphy, bool idle) -{ - struct ath_softc *sc = aphy->sc; - - aphy->idle = idle; - ath_dbg(ath9k_hw_common(sc->sc_ah), ATH_DBG_CONFIG, - "Marking %s as %sidle\n", - wiphy_name(aphy->hw->wiphy), idle ? "" : "not-"); -} -/* Only bother starting a queue on an active virtual wiphy */ -bool ath_mac80211_start_queue(struct ath_softc *sc, u16 skb_queue) -{ - struct ieee80211_hw *hw = sc->pri_wiphy->hw; - unsigned int i; - bool txq_started = false; - - spin_lock_bh(&sc->wiphy_lock); - - /* Start the primary wiphy */ - if (sc->pri_wiphy->state == ATH_WIPHY_ACTIVE) { - ieee80211_wake_queue(hw, skb_queue); - txq_started = true; - goto unlock; - } - - /* Now start the secondary wiphy queues */ - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - if (!aphy) - continue; - if (aphy->state != ATH_WIPHY_ACTIVE) - continue; - - hw = aphy->hw; - ieee80211_wake_queue(hw, skb_queue); - txq_started = true; - break; - } - -unlock: - spin_unlock_bh(&sc->wiphy_lock); - return txq_started; -} - -/* Go ahead and propagate information to all virtual wiphys, it won't hurt */ -void ath_mac80211_stop_queue(struct ath_softc *sc, u16 skb_queue) -{ - struct ieee80211_hw *hw = sc->pri_wiphy->hw; - unsigned int i; - - spin_lock_bh(&sc->wiphy_lock); - - /* Stop the primary wiphy */ - ieee80211_stop_queue(hw, skb_queue); - - /* Now stop the secondary wiphy queues */ - for (i = 0; i < sc->num_sec_wiphy; i++) { - struct ath_wiphy *aphy = sc->sec_wiphy[i]; - if (!aphy) - continue; - hw = aphy->hw; - ieee80211_stop_queue(hw, skb_queue); - } - spin_unlock_bh(&sc->wiphy_lock); -} diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 07b7804..9f4e755 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -19,7 +19,6 @@ #define BITS_PER_BYTE 8 #define OFDM_PLCP_BITS 22 -#define HT_RC_2_MCS(_rc) ((_rc) & 0x1f) #define HT_RC_2_STREAMS(_rc) ((((_rc) & 0x78) >> 3) + 1) #define L_STF 8 #define L_LTF 8 @@ -32,7 +31,6 @@ #define NUM_SYMBOLS_PER_USEC(_usec) (_usec >> 2) #define NUM_SYMBOLS_PER_USEC_HALFGI(_usec) (((_usec*5)-4)/18) -#define OFDM_SIFS_TIME 16 static u16 bits_per_symbol[][2] = { /* 20MHz 40MHz */ @@ -57,8 +55,9 @@ static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf, static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, struct list_head *head); static void ath_buf_set_rate(struct ath_softc *sc, struct ath_buf *bf, int len); -static void ath_tx_rc_status(struct ath_buf *bf, struct ath_tx_status *ts, - int nframes, int nbad, int txok, bool update_rc); +static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, + struct ath_tx_status *ts, int nframes, int nbad, + int txok, bool update_rc); static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid, int seqno); @@ -169,7 +168,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid) ath_tx_update_baw(sc, tid, fi->seqno); ath_tx_complete_buf(sc, bf, txq, &bf_head, &ts, 0, 0); } else { - ath_tx_send_normal(sc, txq, tid, &bf_head); + ath_tx_send_normal(sc, txq, NULL, &bf_head); } spin_lock_bh(&txq->axq_lock); } @@ -297,7 +296,6 @@ static struct ath_buf* ath_clone_txbuf(struct ath_softc *sc, struct ath_buf *bf) ATH_TXBUF_RESET(tbf); - tbf->aphy = bf->aphy; tbf->bf_mpdu = bf->bf_mpdu; tbf->bf_buf_addr = bf->bf_buf_addr; memcpy(tbf->bf_desc, bf->bf_desc, sc->sc_ah->caps.tx_desc_len); @@ -345,7 +343,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, struct ath_node *an = NULL; struct sk_buff *skb; struct ieee80211_sta *sta; - struct ieee80211_hw *hw; + struct ieee80211_hw *hw = sc->hw; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *tx_info; struct ath_atx_tid *tid = NULL; @@ -364,7 +362,6 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, hdr = (struct ieee80211_hdr *)skb->data; tx_info = IEEE80211_SKB_CB(skb); - hw = bf->aphy->hw; memcpy(rates, tx_info->control.rates, sizeof(rates)); @@ -383,7 +380,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, !bf->bf_stale || bf_next != NULL) list_move_tail(&bf->list, &bf_head); - ath_tx_rc_status(bf, ts, 1, 1, 0, false); + ath_tx_rc_status(sc, bf, ts, 1, 1, 0, false); ath_tx_complete_buf(sc, bf, txq, &bf_head, ts, 0, 0); @@ -429,7 +426,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, ath_tx_count_frames(sc, bf, ts, txok, &nframes, &nbad); while (bf) { - txfail = txpending = 0; + txfail = txpending = sendbar = 0; bf_next = bf->bf_next; skb = bf->bf_mpdu; @@ -489,10 +486,10 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, if (rc_update && (acked_cnt == 1 || txfail_cnt == 1)) { memcpy(tx_info->control.rates, rates, sizeof(rates)); - ath_tx_rc_status(bf, ts, nframes, nbad, txok, true); + ath_tx_rc_status(sc, bf, ts, nframes, nbad, txok, true); rc_update = false; } else { - ath_tx_rc_status(bf, ts, nframes, nbad, txok, false); + ath_tx_rc_status(sc, bf, ts, nframes, nbad, txok, false); } ath_tx_complete_buf(sc, bf, txq, &bf_head, ts, @@ -516,7 +513,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, bf->bf_state.bf_type |= BUF_XRETRY; - ath_tx_rc_status(bf, ts, nframes, + ath_tx_rc_status(sc, bf, ts, nframes, nbad, 0, false); ath_tx_complete_buf(sc, bf, txq, &bf_head, @@ -566,8 +563,11 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, rcu_read_unlock(); - if (needreset) + if (needreset) { + spin_unlock_bh(&sc->sc_pcu_lock); ath_reset(sc, false); + spin_lock_bh(&sc->sc_pcu_lock); + } } static u32 ath_lookup_rate(struct ath_softc *sc, struct ath_buf *bf, @@ -856,7 +856,10 @@ int ath_tx_aggr_start(struct ath_softc *sc, struct ieee80211_sta *sta, txtid->state |= AGGR_ADDBA_PROGRESS; txtid->paused = true; - *ssn = txtid->seq_start; + *ssn = txtid->seq_start = txtid->seq_next; + + memset(txtid->tx_buf, 0, sizeof(txtid->tx_buf)); + txtid->baw_head = txtid->baw_tail = 0; return 0; } @@ -942,7 +945,7 @@ struct ath_txq *ath_txq_setup(struct ath_softc *sc, int qtype, int subtype) [WME_AC_VI] = ATH_TXQ_AC_VI, [WME_AC_VO] = ATH_TXQ_AC_VO, }; - int qnum, i; + int axq_qnum, i; memset(&qi, 0, sizeof(qi)); qi.tqi_subtype = subtype_txq_to_hwq[subtype]; @@ -976,24 +979,25 @@ struct ath_txq *ath_txq_setup(struct ath_softc *sc, int qtype, int subtype) qi.tqi_qflags = TXQ_FLAG_TXEOLINT_ENABLE | TXQ_FLAG_TXDESCINT_ENABLE; } - qnum = ath9k_hw_setuptxqueue(ah, qtype, &qi); - if (qnum == -1) { + axq_qnum = ath9k_hw_setuptxqueue(ah, qtype, &qi); + if (axq_qnum == -1) { /* * NB: don't print a message, this happens * normally on parts with too few tx queues */ return NULL; } - if (qnum >= ARRAY_SIZE(sc->tx.txq)) { + if (axq_qnum >= ARRAY_SIZE(sc->tx.txq)) { ath_err(common, "qnum %u out of range, max %zu!\n", - qnum, ARRAY_SIZE(sc->tx.txq)); - ath9k_hw_releasetxqueue(ah, qnum); + axq_qnum, ARRAY_SIZE(sc->tx.txq)); + ath9k_hw_releasetxqueue(ah, axq_qnum); return NULL; } - if (!ATH_TXQ_SETUP(sc, qnum)) { - struct ath_txq *txq = &sc->tx.txq[qnum]; + if (!ATH_TXQ_SETUP(sc, axq_qnum)) { + struct ath_txq *txq = &sc->tx.txq[axq_qnum]; - txq->axq_qnum = qnum; + txq->axq_qnum = axq_qnum; + txq->mac80211_qnum = -1; txq->axq_link = NULL; INIT_LIST_HEAD(&txq->axq_q); INIT_LIST_HEAD(&txq->axq_acq); @@ -1001,14 +1005,14 @@ struct ath_txq *ath_txq_setup(struct ath_softc *sc, int qtype, int subtype) txq->axq_depth = 0; txq->axq_ampdu_depth = 0; txq->axq_tx_inprogress = false; - sc->tx.txqsetup |= 1<<qnum; + sc->tx.txqsetup |= 1<<axq_qnum; txq->txq_headidx = txq->txq_tailidx = 0; for (i = 0; i < ATH_TXFIFO_DEPTH; i++) INIT_LIST_HEAD(&txq->txq_fifo[i]); INIT_LIST_HEAD(&txq->txq_fifo_pending); } - return &sc->tx.txq[qnum]; + return &sc->tx.txq[axq_qnum]; } int ath_txq_update(struct ath_softc *sc, int qnum, @@ -1205,8 +1209,17 @@ bool ath_drain_all_txq(struct ath_softc *sc, bool retry_tx) ath_err(common, "Failed to stop TX DMA!\n"); for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) { - if (ATH_TXQ_SETUP(sc, i)) - ath_draintxq(sc, &sc->tx.txq[i], retry_tx); + if (!ATH_TXQ_SETUP(sc, i)) + continue; + + /* + * The caller will resume queues with ieee80211_wake_queues. + * Mark the queue as not stopped to prevent ath_tx_complete + * from waking the queue too early. + */ + txq = &sc->tx.txq[i]; + txq->stopped = false; + ath_draintxq(sc, txq, retry_tx); } return !npend; @@ -1218,46 +1231,59 @@ void ath_tx_cleanupq(struct ath_softc *sc, struct ath_txq *txq) sc->tx.txqsetup &= ~(1<<txq->axq_qnum); } +/* For each axq_acq entry, for each tid, try to schedule packets + * for transmit until ampdu_depth has reached min Q depth. + */ void ath_txq_schedule(struct ath_softc *sc, struct ath_txq *txq) { - struct ath_atx_ac *ac; - struct ath_atx_tid *tid; + struct ath_atx_ac *ac, *ac_tmp, *last_ac; + struct ath_atx_tid *tid, *last_tid; - if (list_empty(&txq->axq_acq)) + if (list_empty(&txq->axq_acq) || + txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) return; ac = list_first_entry(&txq->axq_acq, struct ath_atx_ac, list); - list_del(&ac->list); - ac->sched = false; + last_ac = list_entry(txq->axq_acq.prev, struct ath_atx_ac, list); - do { - if (list_empty(&ac->tid_q)) - return; + list_for_each_entry_safe(ac, ac_tmp, &txq->axq_acq, list) { + last_tid = list_entry(ac->tid_q.prev, struct ath_atx_tid, list); + list_del(&ac->list); + ac->sched = false; - tid = list_first_entry(&ac->tid_q, struct ath_atx_tid, list); - list_del(&tid->list); - tid->sched = false; + while (!list_empty(&ac->tid_q)) { + tid = list_first_entry(&ac->tid_q, struct ath_atx_tid, + list); + list_del(&tid->list); + tid->sched = false; - if (tid->paused) - continue; + if (tid->paused) + continue; - ath_tx_sched_aggr(sc, txq, tid); + ath_tx_sched_aggr(sc, txq, tid); - /* - * add tid to round-robin queue if more frames - * are pending for the tid - */ - if (!list_empty(&tid->buf_q)) - ath_tx_queue_tid(txq, tid); + /* + * add tid to round-robin queue if more frames + * are pending for the tid + */ + if (!list_empty(&tid->buf_q)) + ath_tx_queue_tid(txq, tid); - break; - } while (!list_empty(&ac->tid_q)); + if (tid == last_tid || + txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) + break; + } - if (!list_empty(&ac->tid_q)) { - if (!ac->sched) { - ac->sched = true; - list_add_tail(&ac->list, &txq->axq_acq); + if (!list_empty(&ac->tid_q)) { + if (!ac->sched) { + ac->sched = true; + list_add_tail(&ac->list, &txq->axq_acq); + } } + + if (ac == last_ac || + txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) + return; } } @@ -1301,6 +1327,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, INIT_LIST_HEAD(&txq->txq_fifo[txq->txq_headidx]); list_splice_init(head, &txq->txq_fifo[txq->txq_headidx]); INCR(txq->txq_headidx, ATH_TXFIFO_DEPTH); + TX_STAT_INC(txq->axq_qnum, puttxbuf); ath9k_hw_puttxbuf(ah, txq->axq_qnum, bf->bf_daddr); ath_dbg(common, ATH_DBG_XMIT, "TXDP[%u] = %llx (%p)\n", txq->axq_qnum, ito64(bf->bf_daddr), bf->bf_desc); @@ -1308,6 +1335,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, list_splice_tail_init(head, &txq->axq_q); if (txq->axq_link == NULL) { + TX_STAT_INC(txq->axq_qnum, puttxbuf); ath9k_hw_puttxbuf(ah, txq->axq_qnum, bf->bf_daddr); ath_dbg(common, ATH_DBG_XMIT, "TXDP[%u] = %llx (%p)\n", txq->axq_qnum, ito64(bf->bf_daddr), @@ -1321,6 +1349,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, } ath9k_hw_get_desc_link(ah, bf->bf_lastbf->bf_desc, &txq->axq_link); + TX_STAT_INC(txq->axq_qnum, txstart); ath9k_hw_txstart(ah, txq->axq_qnum); } txq->axq_depth++; @@ -1335,7 +1364,6 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_atx_tid *tid, struct list_head bf_head; bf->bf_state.bf_type |= BUF_AMPDU; - TX_STAT_INC(txctl->txq->axq_qnum, a_queued); /* * Do not queue to h/w when any of the following conditions is true: @@ -1351,6 +1379,7 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_atx_tid *tid, * Add this frame to software queue for scheduling later * for aggregation. */ + TX_STAT_INC(txctl->txq->axq_qnum, a_queued_sw); list_add_tail(&bf->list, &tid->buf_q); ath_tx_queue_tid(txctl->txq, tid); return; @@ -1364,6 +1393,7 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_atx_tid *tid, ath_tx_addto_baw(sc, tid, fi->seqno); /* Queue to h/w without aggregation */ + TX_STAT_INC(txctl->txq->axq_qnum, a_queued_hw); bf->bf_lastbf = bf; ath_buf_set_rate(sc, bf, fi->framelen); ath_tx_txqaddbuf(sc, txctl->txq, &bf_head); @@ -1416,8 +1446,7 @@ static enum ath9k_pkt_type get_hw_packet_type(struct sk_buff *skb) static void setup_frame_info(struct ieee80211_hw *hw, struct sk_buff *skb, int framelen) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); struct ieee80211_sta *sta = tx_info->control.sta; struct ieee80211_key_conf *hw_key = tx_info->control.hw_key; @@ -1635,8 +1664,7 @@ static struct ath_buf *ath_tx_setup_buffer(struct ieee80211_hw *hw, struct ath_txq *txq, struct sk_buff *skb) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(sc->sc_ah); struct ath_frame_info *fi = get_frame_info(skb); @@ -1652,7 +1680,6 @@ static struct ath_buf *ath_tx_setup_buffer(struct ieee80211_hw *hw, ATH_TXBUF_RESET(bf); - bf->aphy = aphy; bf->bf_flags = setup_tx_flags(skb); bf->bf_mpdu = skb; @@ -1741,8 +1768,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_sta *sta = info->control.sta; - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; + struct ath_softc *sc = hw->priv; struct ath_txq *txq = txctl->txq; struct ath_buf *bf; int padpos, padsize; @@ -1794,7 +1820,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, spin_lock_bh(&txq->axq_lock); if (txq == sc->tx.txq_map[q] && ++txq->pending_frames > ATH_MAX_QDEPTH && !txq->stopped) { - ath_mac80211_stop_queue(sc, q); + ieee80211_stop_queue(sc->hw, q); txq->stopped = 1; } spin_unlock_bh(&txq->axq_lock); @@ -1809,8 +1835,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb, /*****************/ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb, - struct ath_wiphy *aphy, int tx_flags, int ftype, - struct ath_txq *txq) + int tx_flags, int ftype, struct ath_txq *txq) { struct ieee80211_hw *hw = sc->hw; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); @@ -1820,9 +1845,6 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb, ath_dbg(common, ATH_DBG_XMIT, "TX complete: skb: %p\n", skb); - if (aphy) - hw = aphy->hw; - if (tx_flags & ATH_TX_BAR) tx_info->flags |= IEEE80211_TX_STAT_AMPDU_NO_BACK; @@ -1852,19 +1874,20 @@ static void ath_tx_complete(struct ath_softc *sc, struct sk_buff *skb, PS_WAIT_FOR_TX_ACK)); } - if (unlikely(ftype)) - ath9k_tx_status(hw, skb, ftype); - else { - q = skb_get_queue_mapping(skb); - if (txq == sc->tx.txq_map[q]) { - spin_lock_bh(&txq->axq_lock); - if (WARN_ON(--txq->pending_frames < 0)) - txq->pending_frames = 0; - spin_unlock_bh(&txq->axq_lock); - } + q = skb_get_queue_mapping(skb); + if (txq == sc->tx.txq_map[q]) { + spin_lock_bh(&txq->axq_lock); + if (WARN_ON(--txq->pending_frames < 0)) + txq->pending_frames = 0; - ieee80211_tx_status(hw, skb); + if (txq->stopped && txq->pending_frames < ATH_MAX_QDEPTH) { + ieee80211_wake_queue(sc->hw, q); + txq->stopped = 0; + } + spin_unlock_bh(&txq->axq_lock); } + + ieee80211_tx_status(hw, skb); } static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf, @@ -1896,8 +1919,8 @@ static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf, else complete(&sc->paprd_complete); } else { - ath_debug_stat_tx(sc, bf, ts); - ath_tx_complete(sc, skb, bf->aphy, tx_flags, + ath_debug_stat_tx(sc, bf, ts, txq); + ath_tx_complete(sc, skb, tx_flags, bf->bf_state.bfs_ftype, txq); } /* At this point, skb (bf->bf_mpdu) is consumed...make sure we don't @@ -1913,14 +1936,14 @@ static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf, spin_unlock_irqrestore(&sc->tx.txbuflock, flags); } -static void ath_tx_rc_status(struct ath_buf *bf, struct ath_tx_status *ts, - int nframes, int nbad, int txok, bool update_rc) +static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, + struct ath_tx_status *ts, int nframes, int nbad, + int txok, bool update_rc) { struct sk_buff *skb = bf->bf_mpdu; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); - struct ieee80211_hw *hw = bf->aphy->hw; - struct ath_softc *sc = bf->aphy->sc; + struct ieee80211_hw *hw = sc->hw; struct ath_hw *ah = sc->sc_ah; u8 i, tx_rateindex; @@ -1971,19 +1994,6 @@ static void ath_tx_rc_status(struct ath_buf *bf, struct ath_tx_status *ts, tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; } -static void ath_wake_mac80211_queue(struct ath_softc *sc, int qnum) -{ - struct ath_txq *txq; - - txq = sc->tx.txq_map[qnum]; - spin_lock_bh(&txq->axq_lock); - if (txq->stopped && txq->pending_frames < ATH_MAX_QDEPTH) { - if (ath_mac80211_start_queue(sc, qnum)) - txq->stopped = 0; - } - spin_unlock_bh(&txq->axq_lock); -} - static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) { struct ath_hw *ah = sc->sc_ah; @@ -1994,7 +2004,6 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) struct ath_tx_status ts; int txok; int status; - int qnum; ath_dbg(common, ATH_DBG_QUEUE, "tx queue %d (%x), link %p\n", txq->axq_qnum, ath9k_hw_gettxbuf(sc->sc_ah, txq->axq_qnum), @@ -2004,6 +2013,8 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) spin_lock_bh(&txq->axq_lock); if (list_empty(&txq->axq_q)) { txq->axq_link = NULL; + if (sc->sc_flags & SC_OP_TXAGGR) + ath_txq_schedule(sc, txq); spin_unlock_bh(&txq->axq_lock); break; } @@ -2038,6 +2049,7 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) spin_unlock_bh(&txq->axq_lock); break; } + TX_STAT_INC(txq->axq_qnum, txprocdesc); /* * Remove ath_buf's of the same transmit unit from txq, @@ -2070,27 +2082,45 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) */ if (ts.ts_status & ATH9K_TXERR_XRETRY) bf->bf_state.bf_type |= BUF_XRETRY; - ath_tx_rc_status(bf, &ts, 1, txok ? 0 : 1, txok, true); + ath_tx_rc_status(sc, bf, &ts, 1, txok ? 0 : 1, txok, true); } - qnum = skb_get_queue_mapping(bf->bf_mpdu); - if (bf_isampdu(bf)) ath_tx_complete_aggr(sc, txq, bf, &bf_head, &ts, txok, true); else ath_tx_complete_buf(sc, bf, txq, &bf_head, &ts, txok, 0); - if (txq == sc->tx.txq_map[qnum]) - ath_wake_mac80211_queue(sc, qnum); - spin_lock_bh(&txq->axq_lock); + if (sc->sc_flags & SC_OP_TXAGGR) ath_txq_schedule(sc, txq); spin_unlock_bh(&txq->axq_lock); } } +static void ath_hw_pll_work(struct work_struct *work) +{ + struct ath_softc *sc = container_of(work, struct ath_softc, + hw_pll_work.work); + static int count; + + if (AR_SREV_9485(sc->sc_ah)) { + if (ar9003_get_pll_sqsum_dvc(sc->sc_ah) >= 0x40000) { + count++; + + if (count == 3) { + /* Rx is hung for more than 500ms. Reset it */ + ath_reset(sc, true); + count = 0; + } + } else + count = 0; + + ieee80211_queue_delayed_work(sc->hw, &sc->hw_pll_work, HZ/5); + } +} + static void ath_tx_complete_poll_work(struct work_struct *work) { struct ath_softc *sc = container_of(work, struct ath_softc, @@ -2098,6 +2128,9 @@ static void ath_tx_complete_poll_work(struct work_struct *work) struct ath_txq *txq; int i; bool needreset = false; +#ifdef CONFIG_ATH9K_DEBUGFS + sc->tx_complete_poll_work_seen++; +#endif for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) if (ATH_TXQ_SETUP(sc, i)) { @@ -2111,6 +2144,33 @@ static void ath_tx_complete_poll_work(struct work_struct *work) } else { txq->axq_tx_inprogress = true; } + } else { + /* If the queue has pending buffers, then it + * should be doing tx work (and have axq_depth). + * Shouldn't get to this state I think..but + * we do. + */ + if (!(sc->sc_flags & (SC_OP_OFFCHANNEL)) && + (txq->pending_frames > 0 || + !list_empty(&txq->axq_acq) || + txq->stopped)) { + ath_err(ath9k_hw_common(sc->sc_ah), + "txq: %p axq_qnum: %u," + " mac80211_qnum: %i" + " axq_link: %p" + " pending frames: %i" + " axq_acq empty: %i" + " stopped: %i" + " axq_depth: 0 Attempting to" + " restart tx logic.\n", + txq, txq->axq_qnum, + txq->mac80211_qnum, + txq->axq_link, + txq->pending_frames, + list_empty(&txq->axq_acq), + txq->stopped); + ath_txq_schedule(sc, txq); + } } spin_unlock_bh(&txq->axq_lock); } @@ -2150,7 +2210,6 @@ void ath_tx_edma_tasklet(struct ath_softc *sc) struct list_head bf_head; int status; int txok; - int qnum; for (;;) { status = ath9k_hw_txprocdesc(ah, NULL, (void *)&txs); @@ -2193,11 +2252,9 @@ void ath_tx_edma_tasklet(struct ath_softc *sc) if (!bf_isampdu(bf)) { if (txs.ts_status & ATH9K_TXERR_XRETRY) bf->bf_state.bf_type |= BUF_XRETRY; - ath_tx_rc_status(bf, &txs, 1, txok ? 0 : 1, txok, true); + ath_tx_rc_status(sc, bf, &txs, 1, txok ? 0 : 1, txok, true); } - qnum = skb_get_queue_mapping(bf->bf_mpdu); - if (bf_isampdu(bf)) ath_tx_complete_aggr(sc, txq, bf, &bf_head, &txs, txok, true); @@ -2205,10 +2262,8 @@ void ath_tx_edma_tasklet(struct ath_softc *sc) ath_tx_complete_buf(sc, bf, txq, &bf_head, &txs, txok, 0); - if (txq == sc->tx.txq_map[qnum]) - ath_wake_mac80211_queue(sc, qnum); - spin_lock_bh(&txq->axq_lock); + if (!list_empty(&txq->txq_fifo_pending)) { INIT_LIST_HEAD(&bf_head); bf = list_first_entry(&txq->txq_fifo_pending, @@ -2285,6 +2340,7 @@ int ath_tx_init(struct ath_softc *sc, int nbufs) } INIT_DELAYED_WORK(&sc->tx_complete_work, ath_tx_complete_poll_work); + INIT_DELAYED_WORK(&sc->hw_pll_work, ath_hw_pll_work); if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) { error = ath_tx_edma_init(sc); diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h index d07ff7f..420d437 100644 --- a/drivers/net/wireless/ath/carl9170/carl9170.h +++ b/drivers/net/wireless/ath/carl9170/carl9170.h @@ -283,6 +283,7 @@ struct ar9170 { unsigned int mem_blocks; unsigned int mem_block_size; unsigned int rx_size; + unsigned int tx_seq_table; } fw; /* reset / stuck frames/queue detection */ diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c index 546b4e4..9517ede 100644 --- a/drivers/net/wireless/ath/carl9170/fw.c +++ b/drivers/net/wireless/ath/carl9170/fw.c @@ -150,6 +150,7 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len) const struct carl9170fw_otus_desc *otus_desc; const struct carl9170fw_chk_desc *chk_desc; const struct carl9170fw_last_desc *last_desc; + const struct carl9170fw_txsq_desc *txsq_desc; last_desc = carl9170_fw_find_desc(ar, LAST_MAGIC, sizeof(*last_desc), CARL9170FW_LAST_DESC_CUR_VER); @@ -264,6 +265,9 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len) FIF_PROMISC_IN_BSS; } + if (SUPP(CARL9170FW_WOL)) + device_set_wakeup_enable(&ar->udev->dev, true); + ar->fw.vif_num = otus_desc->vif_num; ar->fw.cmd_bufs = otus_desc->cmd_bufs; ar->fw.address = le32_to_cpu(otus_desc->fw_address); @@ -296,6 +300,17 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len) } } + txsq_desc = carl9170_fw_find_desc(ar, TXSQ_MAGIC, + sizeof(*txsq_desc), CARL9170FW_TXSQ_DESC_CUR_VER); + + if (txsq_desc) { + ar->fw.tx_seq_table = le32_to_cpu(txsq_desc->seq_table_addr); + if (!valid_cpu_addr(ar->fw.tx_seq_table)) + return -EINVAL; + } else { + ar->fw.tx_seq_table = 0; + } + #undef SUPPORTED return 0; } diff --git a/drivers/net/wireless/ath/carl9170/fwcmd.h b/drivers/net/wireless/ath/carl9170/fwcmd.h index 3680dfc7..30449d2 100644 --- a/drivers/net/wireless/ath/carl9170/fwcmd.h +++ b/drivers/net/wireless/ath/carl9170/fwcmd.h @@ -167,6 +167,7 @@ struct carl9170_rx_filter_cmd { #define CARL9170_RX_FILTER_CTL_BACKR 0x20 #define CARL9170_RX_FILTER_MGMT 0x40 #define CARL9170_RX_FILTER_DATA 0x80 +#define CARL9170_RX_FILTER_EVERYTHING (~0) struct carl9170_bcn_ctrl_cmd { __le32 vif_id; diff --git a/drivers/net/wireless/ath/carl9170/fwdesc.h b/drivers/net/wireless/ath/carl9170/fwdesc.h index 71f3821..9210668 100644 --- a/drivers/net/wireless/ath/carl9170/fwdesc.h +++ b/drivers/net/wireless/ath/carl9170/fwdesc.h @@ -69,6 +69,9 @@ enum carl9170fw_feature_list { /* Firmware RX filter | CARL9170_CMD_RX_FILTER */ CARL9170FW_RX_FILTER, + /* Wake up on WLAN */ + CARL9170FW_WOL, + /* KEEP LAST */ __CARL9170FW_FEATURE_NUM }; @@ -78,6 +81,7 @@ enum carl9170fw_feature_list { #define FIX_MAGIC "FIX\0" #define DBG_MAGIC "DBG\0" #define CHK_MAGIC "CHK\0" +#define TXSQ_MAGIC "TXSQ" #define LAST_MAGIC "LAST" #define CARL9170FW_SET_DAY(d) (((d) - 1) % 31) @@ -88,8 +92,10 @@ enum carl9170fw_feature_list { #define CARL9170FW_GET_MONTH(m) ((((m) / 31) % 12) + 1) #define CARL9170FW_GET_YEAR(y) ((y) / 372 + 10) +#define CARL9170FW_MAGIC_SIZE 4 + struct carl9170fw_desc_head { - u8 magic[4]; + u8 magic[CARL9170FW_MAGIC_SIZE]; __le16 length; u8 min_ver; u8 cur_ver; @@ -170,6 +176,16 @@ struct carl9170fw_chk_desc { #define CARL9170FW_CHK_DESC_SIZE \ (sizeof(struct carl9170fw_chk_desc)) +#define CARL9170FW_TXSQ_DESC_MIN_VER 1 +#define CARL9170FW_TXSQ_DESC_CUR_VER 1 +struct carl9170fw_txsq_desc { + struct carl9170fw_desc_head head; + + __le32 seq_table_addr; +} __packed; +#define CARL9170FW_TXSQ_DESC_SIZE \ + (sizeof(struct carl9170fw_txsq_desc)) + #define CARL9170FW_LAST_DESC_MIN_VER 1 #define CARL9170FW_LAST_DESC_CUR_VER 2 struct carl9170fw_last_desc { @@ -189,8 +205,8 @@ struct carl9170fw_last_desc { } static inline void carl9170fw_fill_desc(struct carl9170fw_desc_head *head, - u8 magic[4], __le16 length, - u8 min_ver, u8 cur_ver) + u8 magic[CARL9170FW_MAGIC_SIZE], + __le16 length, u8 min_ver, u8 cur_ver) { head->magic[0] = magic[0]; head->magic[1] = magic[1]; @@ -204,7 +220,7 @@ static inline void carl9170fw_fill_desc(struct carl9170fw_desc_head *head, #define carl9170fw_for_each_hdr(desc, fw_desc) \ for (desc = fw_desc; \ - memcmp(desc->magic, LAST_MAGIC, 4) && \ + memcmp(desc->magic, LAST_MAGIC, CARL9170FW_MAGIC_SIZE) && \ le16_to_cpu(desc->length) >= CARL9170FW_DESC_HEAD_SIZE && \ le16_to_cpu(desc->length) < CARL9170FW_DESC_MAX_LENGTH; \ desc = (void *)((unsigned long)desc + le16_to_cpu(desc->length))) @@ -218,8 +234,8 @@ static inline bool carl9170fw_supports(__le32 list, u8 feature) } static inline bool carl9170fw_desc_cmp(const struct carl9170fw_desc_head *head, - const u8 descid[4], u16 min_len, - u8 compatible_revision) + const u8 descid[CARL9170FW_MAGIC_SIZE], + u16 min_len, u8 compatible_revision) { if (descid[0] == head->magic[0] && descid[1] == head->magic[1] && descid[2] == head->magic[2] && descid[3] == head->magic[3] && diff --git a/drivers/net/wireless/ath/carl9170/hw.h b/drivers/net/wireless/ath/carl9170/hw.h index e85df6e..4e30762 100644 --- a/drivers/net/wireless/ath/carl9170/hw.h +++ b/drivers/net/wireless/ath/carl9170/hw.h @@ -463,6 +463,8 @@ #define AR9170_PWR_REG_CHIP_REVISION (AR9170_PWR_REG_BASE + 0x010) #define AR9170_PWR_REG_PLL_ADDAC (AR9170_PWR_REG_BASE + 0x014) +#define AR9170_PWR_PLL_ADDAC_DIV_S 2 +#define AR9170_PWR_PLL_ADDAC_DIV 0xffc #define AR9170_PWR_REG_WATCH_DOG_MAGIC (AR9170_PWR_REG_BASE + 0x020) /* Faraday USB Controller */ @@ -471,6 +473,9 @@ #define AR9170_USB_REG_MAIN_CTRL (AR9170_USB_REG_BASE + 0x000) #define AR9170_USB_MAIN_CTRL_REMOTE_WAKEUP BIT(0) #define AR9170_USB_MAIN_CTRL_ENABLE_GLOBAL_INT BIT(2) +#define AR9170_USB_MAIN_CTRL_GO_TO_SUSPEND BIT(3) +#define AR9170_USB_MAIN_CTRL_RESET BIT(4) +#define AR9170_USB_MAIN_CTRL_CHIP_ENABLE BIT(5) #define AR9170_USB_MAIN_CTRL_HIGHSPEED BIT(6) #define AR9170_USB_REG_DEVICE_ADDRESS (AR9170_USB_REG_BASE + 0x001) @@ -499,6 +504,13 @@ #define AR9170_USB_REG_INTR_GROUP (AR9170_USB_REG_BASE + 0x020) #define AR9170_USB_REG_INTR_SOURCE_0 (AR9170_USB_REG_BASE + 0x021) +#define AR9170_USB_INTR_SRC0_SETUP BIT(0) +#define AR9170_USB_INTR_SRC0_IN BIT(1) +#define AR9170_USB_INTR_SRC0_OUT BIT(2) +#define AR9170_USB_INTR_SRC0_FAIL BIT(3) /* ??? */ +#define AR9170_USB_INTR_SRC0_END BIT(4) /* ??? */ +#define AR9170_USB_INTR_SRC0_ABORT BIT(7) + #define AR9170_USB_REG_INTR_SOURCE_1 (AR9170_USB_REG_BASE + 0x022) #define AR9170_USB_REG_INTR_SOURCE_2 (AR9170_USB_REG_BASE + 0x023) #define AR9170_USB_REG_INTR_SOURCE_3 (AR9170_USB_REG_BASE + 0x024) @@ -506,6 +518,15 @@ #define AR9170_USB_REG_INTR_SOURCE_5 (AR9170_USB_REG_BASE + 0x026) #define AR9170_USB_REG_INTR_SOURCE_6 (AR9170_USB_REG_BASE + 0x027) #define AR9170_USB_REG_INTR_SOURCE_7 (AR9170_USB_REG_BASE + 0x028) +#define AR9170_USB_INTR_SRC7_USB_RESET BIT(1) +#define AR9170_USB_INTR_SRC7_USB_SUSPEND BIT(2) +#define AR9170_USB_INTR_SRC7_USB_RESUME BIT(3) +#define AR9170_USB_INTR_SRC7_ISO_SEQ_ERR BIT(4) +#define AR9170_USB_INTR_SRC7_ISO_SEQ_ABORT BIT(5) +#define AR9170_USB_INTR_SRC7_TX0BYTE BIT(6) +#define AR9170_USB_INTR_SRC7_RX0BYTE BIT(7) + +#define AR9170_USB_REG_IDLE_COUNT (AR9170_USB_REG_BASE + 0x02f) #define AR9170_USB_REG_EP_MAP (AR9170_USB_REG_BASE + 0x030) #define AR9170_USB_REG_EP1_MAP (AR9170_USB_REG_BASE + 0x030) @@ -581,6 +602,10 @@ #define AR9170_USB_REG_MAX_AGG_UPLOAD (AR9170_USB_REG_BASE + 0x110) #define AR9170_USB_REG_UPLOAD_TIME_CTL (AR9170_USB_REG_BASE + 0x114) + +#define AR9170_USB_REG_WAKE_UP (AR9170_USB_REG_BASE + 0x120) +#define AR9170_USB_WAKE_UP_WAKE BIT(0) + #define AR9170_USB_REG_CBUS_CTRL (AR9170_USB_REG_BASE + 0x1f0) #define AR9170_USB_CBUS_CTRL_BUFFER_END (BIT(1)) diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c index 870df8c..ede3d7e 100644 --- a/drivers/net/wireless/ath/carl9170/main.c +++ b/drivers/net/wireless/ath/carl9170/main.c @@ -662,6 +662,13 @@ init: goto unlock; } + if (ar->fw.tx_seq_table) { + err = carl9170_write_reg(ar, ar->fw.tx_seq_table + vif_id * 4, + 0); + if (err) + goto unlock; + } + unlock: if (err && (vif_id >= 0)) { vif_priv->active = false; @@ -1279,7 +1286,7 @@ static int carl9170_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn) + u16 tid, u16 *ssn, u8 buf_size) { struct ar9170 *ar = hw->priv; struct carl9170_sta_info *sta_info = (void *) sta->drv_priv; diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c index 6cc58e0..6f41e21 100644 --- a/drivers/net/wireless/ath/carl9170/tx.c +++ b/drivers/net/wireless/ath/carl9170/tx.c @@ -862,6 +862,9 @@ static int carl9170_tx_prepare(struct ar9170 *ar, struct sk_buff *skb) if (unlikely(info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM)) txc->s.misc |= CARL9170_TX_SUPER_MISC_CAB; + if (unlikely(info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)) + txc->s.misc |= CARL9170_TX_SUPER_MISC_ASSIGN_SEQ; + if (unlikely(ieee80211_is_probe_resp(hdr->frame_control))) txc->s.misc |= CARL9170_TX_SUPER_MISC_FILL_IN_TSF; diff --git a/drivers/net/wireless/ath/carl9170/version.h b/drivers/net/wireless/ath/carl9170/version.h index ee0f84f..15095c0 100644 --- a/drivers/net/wireless/ath/carl9170/version.h +++ b/drivers/net/wireless/ath/carl9170/version.h @@ -1,7 +1,7 @@ #ifndef __CARL9170_SHARED_VERSION_H #define __CARL9170_SHARED_VERSION_H -#define CARL9170FW_VERSION_YEAR 10 -#define CARL9170FW_VERSION_MONTH 10 -#define CARL9170FW_VERSION_DAY 29 -#define CARL9170FW_VERSION_GIT "1.9.0" +#define CARL9170FW_VERSION_YEAR 11 +#define CARL9170FW_VERSION_MONTH 1 +#define CARL9170FW_VERSION_DAY 22 +#define CARL9170FW_VERSION_GIT "1.9.2" #endif /* __CARL9170_SHARED_VERSION_H */ diff --git a/drivers/net/wireless/ath/carl9170/wlan.h b/drivers/net/wireless/ath/carl9170/wlan.h index 24d63b5..9e1324b 100644 --- a/drivers/net/wireless/ath/carl9170/wlan.h +++ b/drivers/net/wireless/ath/carl9170/wlan.h @@ -251,7 +251,7 @@ struct carl9170_tx_superdesc { u8 ampdu_commit_factor:1; u8 ampdu_unused_bit:1; u8 queue:2; - u8 reserved:1; + u8 assign_seq:1; u8 vif_id:3; u8 fill_in_tsf:1; u8 cab:1; @@ -299,6 +299,7 @@ struct _ar9170_tx_hwdesc { #define CARL9170_TX_SUPER_MISC_QUEUE 0x3 #define CARL9170_TX_SUPER_MISC_QUEUE_S 0 +#define CARL9170_TX_SUPER_MISC_ASSIGN_SEQ 0x4 #define CARL9170_TX_SUPER_MISC_VIF_ID 0x38 #define CARL9170_TX_SUPER_MISC_VIF_ID_S 3 #define CARL9170_TX_SUPER_MISC_FILL_IN_TSF 0x40 @@ -413,6 +414,23 @@ enum ar9170_txq { __AR9170_NUM_TXQ, }; +/* + * This is an workaround for several undocumented bugs. + * Don't mess with the QoS/AC <-> HW Queue map, if you don't + * know what you are doing. + * + * Known problems [hardware]: + * * The MAC does not aggregate frames on anything other + * than the first HW queue. + * * when an AMPDU is placed [in the first hw queue] and + * additional frames are already queued on a different + * hw queue, the MAC will ALWAYS freeze. + * + * In a nutshell: The hardware can either do QoS or + * Aggregation but not both at the same time. As a + * result, this makes the device pretty much useless + * for any serious 802.11n setup. + */ static const u8 ar9170_qmap[__AR9170_NUM_TXQ] = { 2, 1, 0, 3 }; #define AR9170_TXQ_DEPTH 32 diff --git a/drivers/net/wireless/ath/key.c b/drivers/net/wireless/ath/key.c index 5d465e5..37b8e11 100644 --- a/drivers/net/wireless/ath/key.c +++ b/drivers/net/wireless/ath/key.c @@ -58,8 +58,11 @@ bool ath_hw_keyreset(struct ath_common *common, u16 entry) REG_WRITE(ah, AR_KEYTABLE_KEY1(micentry), 0); REG_WRITE(ah, AR_KEYTABLE_KEY2(micentry), 0); REG_WRITE(ah, AR_KEYTABLE_KEY3(micentry), 0); - if (common->crypt_caps & ATH_CRYPT_CAP_MIC_COMBINED) + if (common->crypt_caps & ATH_CRYPT_CAP_MIC_COMBINED) { REG_WRITE(ah, AR_KEYTABLE_KEY4(micentry), 0); + REG_WRITE(ah, AR_KEYTABLE_TYPE(micentry), + AR_KEYTABLE_TYPE_CLR); + } } diff --git a/drivers/net/wireless/ath/regd.c b/drivers/net/wireless/ath/regd.c index 2b14775..f828f29 100644 --- a/drivers/net/wireless/ath/regd.c +++ b/drivers/net/wireless/ath/regd.c @@ -158,6 +158,13 @@ ieee80211_regdomain *ath_world_regdomain(struct ath_regulatory *reg) } } +bool ath_is_49ghz_allowed(u16 regdomain) +{ + /* possibly more */ + return regdomain == MKK9_MKKC; +} +EXPORT_SYMBOL(ath_is_49ghz_allowed); + /* Frequency is one where radar detection is required */ static bool ath_is_radar_freq(u16 center_freq) { diff --git a/drivers/net/wireless/ath/regd.h b/drivers/net/wireless/ath/regd.h index 345dd97..172f63f 100644 --- a/drivers/net/wireless/ath/regd.h +++ b/drivers/net/wireless/ath/regd.h @@ -250,6 +250,7 @@ enum CountryCode { }; bool ath_is_world_regd(struct ath_regulatory *reg); +bool ath_is_49ghz_allowed(u16 redomain); int ath_regd_init(struct ath_regulatory *reg, struct wiphy *wiphy, int (*reg_notifier)(struct wiphy *wiphy, struct regulatory_request *request)); diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 61915f3..da60fae 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -1397,7 +1397,7 @@ static int ipw2100_power_cycle_adapter(struct ipw2100_priv *priv) } /* - * Send the CARD_DISABLE_PHY_OFF comamnd to the card to disable it + * Send the CARD_DISABLE_PHY_OFF command to the card to disable it * * After disabling, if the card was associated, a STATUS_ASSN_LOST will be sent. * diff --git a/drivers/net/wireless/iwlwifi/Kconfig b/drivers/net/wireless/iwlwifi/Kconfig index ed42457..e1e3b1c 100644 --- a/drivers/net/wireless/iwlwifi/Kconfig +++ b/drivers/net/wireless/iwlwifi/Kconfig @@ -2,6 +2,10 @@ config IWLWIFI tristate "Intel Wireless Wifi" depends on PCI && MAC80211 select FW_LOADER + select NEW_LEDS + select LEDS_CLASS + select LEDS_TRIGGERS + select MAC80211_LEDS menu "Debugging Options" depends on IWLWIFI @@ -106,9 +110,27 @@ config IWL5000 Intel WiFi Link 1000BGN Intel Wireless WiFi 5150AGN Intel Wireless WiFi 5100AGN, 5300AGN, and 5350AGN - Intel 6000 Gen 2 Series Wi-Fi Adapters (6000G2A and 6000G2B) - Intel WIreless WiFi Link 6050BGN Gen 2 Adapter + Intel 6005 Series Wi-Fi Adapters + Intel 6030 Series Wi-Fi Adapters + Intel Wireless WiFi Link 6150BGN 2 Adapter Intel 100 Series Wi-Fi Adapters (100BGN and 130BGN) + Intel 2000 Series Wi-Fi Adapters + +config IWL_P2P + bool "iwlwifi experimental P2P support" + depends on IWL5000 + help + This option enables experimental P2P support for some devices + based on microcode support. Since P2P support is still under + development, this option may even enable it for some devices + now that turn out to not support it in the future due to + microcode restrictions. + + To determine if your microcode supports the experimental P2P + offered by this option, check if the driver advertises AP + support when it is loaded. + + Say Y only if you want to experiment with P2P. config IWL3945 tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)" diff --git a/drivers/net/wireless/iwlwifi/Makefile b/drivers/net/wireless/iwlwifi/Makefile index 93380f9..25be742 100644 --- a/drivers/net/wireless/iwlwifi/Makefile +++ b/drivers/net/wireless/iwlwifi/Makefile @@ -26,6 +26,7 @@ iwlagn-$(CONFIG_IWL5000) += iwl-agn-rxon.o iwl-agn-hcmd.o iwl-agn-ict.o iwlagn-$(CONFIG_IWL5000) += iwl-5000.o iwlagn-$(CONFIG_IWL5000) += iwl-6000.o iwlagn-$(CONFIG_IWL5000) += iwl-1000.o +iwlagn-$(CONFIG_IWL5000) += iwl-2000.o # 3945 obj-$(CONFIG_IWL3945) += iwl3945.o diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c new file mode 100644 index 0000000..3c5dd36 --- /dev/null +++ b/drivers/net/wireless/iwlwifi/iwl-2000.c @@ -0,0 +1,560 @@ +/****************************************************************************** + * + * Copyright(c) 2008 - 2010 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110, USA + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + * Contact Information: + * Intel Linux Wireless <ilw@linux.intel.com> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + *****************************************************************************/ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/dma-mapping.h> +#include <linux/delay.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/wireless.h> +#include <net/mac80211.h> +#include <linux/etherdevice.h> +#include <asm/unaligned.h> + +#include "iwl-eeprom.h" +#include "iwl-dev.h" +#include "iwl-core.h" +#include "iwl-io.h" +#include "iwl-sta.h" +#include "iwl-agn.h" +#include "iwl-helpers.h" +#include "iwl-agn-hw.h" +#include "iwl-6000-hw.h" +#include "iwl-agn-led.h" +#include "iwl-agn-debugfs.h" + +/* Highest firmware API version supported */ +#define IWL2030_UCODE_API_MAX 5 +#define IWL2000_UCODE_API_MAX 5 +#define IWL200_UCODE_API_MAX 5 + +/* Lowest firmware API version supported */ +#define IWL2030_UCODE_API_MIN 5 +#define IWL2000_UCODE_API_MIN 5 +#define IWL200_UCODE_API_MIN 5 + +#define IWL2030_FW_PRE "iwlwifi-2030-" +#define _IWL2030_MODULE_FIRMWARE(api) IWL2030_FW_PRE #api ".ucode" +#define IWL2030_MODULE_FIRMWARE(api) _IWL2030_MODULE_FIRMWARE(api) + +#define IWL2000_FW_PRE "iwlwifi-2000-" +#define _IWL2000_MODULE_FIRMWARE(api) IWL2000_FW_PRE #api ".ucode" +#define IWL2000_MODULE_FIRMWARE(api) _IWL2000_MODULE_FIRMWARE(api) + +#define IWL200_FW_PRE "iwlwifi-200-" +#define _IWL200_MODULE_FIRMWARE(api) IWL200_FW_PRE #api ".ucode" +#define IWL200_MODULE_FIRMWARE(api) _IWL200_MODULE_FIRMWARE(api) + +static void iwl2000_set_ct_threshold(struct iwl_priv *priv) +{ + /* want Celsius */ + priv->hw_params.ct_kill_threshold = CT_KILL_THRESHOLD; + priv->hw_params.ct_kill_exit_threshold = CT_KILL_EXIT_THRESHOLD; +} + +/* NIC configuration for 2000 series */ +static void iwl2000_nic_config(struct iwl_priv *priv) +{ + u16 radio_cfg; + + radio_cfg = iwl_eeprom_query16(priv, EEPROM_RADIO_CONFIG); + + /* write radio config values to register */ + if (EEPROM_RF_CFG_TYPE_MSK(radio_cfg) <= EEPROM_RF_CONFIG_TYPE_MAX) + iwl_set_bit(priv, CSR_HW_IF_CONFIG_REG, + EEPROM_RF_CFG_TYPE_MSK(radio_cfg) | + EEPROM_RF_CFG_STEP_MSK(radio_cfg) | + EEPROM_RF_CFG_DASH_MSK(radio_cfg)); + + /* set CSR_HW_CONFIG_REG for uCode use */ + iwl_set_bit(priv, CSR_HW_IF_CONFIG_REG, + CSR_HW_IF_CONFIG_REG_BIT_RADIO_SI | + CSR_HW_IF_CONFIG_REG_BIT_MAC_SI); + + if (priv->cfg->iq_invert) + iwl_set_bit(priv, CSR_GP_DRIVER_REG, + CSR_GP_DRIVER_REG_BIT_RADIO_IQ_INVER); + +} + +static struct iwl_sensitivity_ranges iwl2000_sensitivity = { + .min_nrg_cck = 97, + .max_nrg_cck = 0, /* not used, set to 0 */ + .auto_corr_min_ofdm = 80, + .auto_corr_min_ofdm_mrc = 128, + .auto_corr_min_ofdm_x1 = 105, + .auto_corr_min_ofdm_mrc_x1 = 192, + + .auto_corr_max_ofdm = 145, + .auto_corr_max_ofdm_mrc = 232, + .auto_corr_max_ofdm_x1 = 110, + .auto_corr_max_ofdm_mrc_x1 = 232, + + .auto_corr_min_cck = 125, + .auto_corr_max_cck = 175, + .auto_corr_min_cck_mrc = 160, + .auto_corr_max_cck_mrc = 310, + .nrg_th_cck = 97, + .nrg_th_ofdm = 100, + + .barker_corr_th_min = 190, + .barker_corr_th_min_mrc = 390, + .nrg_th_cca = 62, +}; + +static int iwl2000_hw_set_hw_params(struct iwl_priv *priv) +{ + if (priv->cfg->mod_params->num_of_queues >= IWL_MIN_NUM_QUEUES && + priv->cfg->mod_params->num_of_queues <= IWLAGN_NUM_QUEUES) + priv->cfg->base_params->num_of_queues = + priv->cfg->mod_params->num_of_queues; + + priv->hw_params.max_txq_num = priv->cfg->base_params->num_of_queues; + priv->hw_params.dma_chnl_num = FH50_TCSR_CHNL_NUM; + priv->hw_params.scd_bc_tbls_size = + priv->cfg->base_params->num_of_queues * + sizeof(struct iwlagn_scd_bc_tbl); + priv->hw_params.tfd_size = sizeof(struct iwl_tfd); + priv->hw_params.max_stations = IWLAGN_STATION_COUNT; + priv->contexts[IWL_RXON_CTX_BSS].bcast_sta_id = IWLAGN_BROADCAST_ID; + + priv->hw_params.max_data_size = IWL60_RTC_DATA_SIZE; + priv->hw_params.max_inst_size = IWL60_RTC_INST_SIZE; + + priv->hw_params.max_bsm_size = 0; + priv->hw_params.ht40_channel = BIT(IEEE80211_BAND_2GHZ) | + BIT(IEEE80211_BAND_5GHZ); + priv->hw_params.rx_wrt_ptr_reg = FH_RSCSR_CHNL0_WPTR; + + priv->hw_params.tx_chains_num = num_of_ant(priv->cfg->valid_tx_ant); + if (priv->cfg->rx_with_siso_diversity) + priv->hw_params.rx_chains_num = 1; + else + priv->hw_params.rx_chains_num = + num_of_ant(priv->cfg->valid_rx_ant); + priv->hw_params.valid_tx_ant = priv->cfg->valid_tx_ant; + priv->hw_params.valid_rx_ant = priv->cfg->valid_rx_ant; + + iwl2000_set_ct_threshold(priv); + + /* Set initial sensitivity parameters */ + /* Set initial calibration set */ + priv->hw_params.sens = &iwl2000_sensitivity; + priv->hw_params.calib_init_cfg = + BIT(IWL_CALIB_XTAL) | + BIT(IWL_CALIB_LO) | + BIT(IWL_CALIB_TX_IQ) | + BIT(IWL_CALIB_BASE_BAND); + if (priv->cfg->need_dc_calib) + priv->hw_params.calib_rt_cfg |= BIT(IWL_CALIB_CFG_DC_IDX); + if (priv->cfg->need_temp_offset_calib) + priv->hw_params.calib_init_cfg |= BIT(IWL_CALIB_TEMP_OFFSET); + + priv->hw_params.beacon_time_tsf_bits = IWLAGN_EXT_BEACON_TIME_POS; + + return 0; +} + +static int iwl2030_hw_channel_switch(struct iwl_priv *priv, + struct ieee80211_channel_switch *ch_switch) +{ + /* + * MULTI-FIXME + * See iwl_mac_channel_switch. + */ + struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS]; + struct iwl6000_channel_switch_cmd cmd; + const struct iwl_channel_info *ch_info; + u32 switch_time_in_usec, ucode_switch_time; + u16 ch; + u32 tsf_low; + u8 switch_count; + u16 beacon_interval = le16_to_cpu(ctx->timing.beacon_interval); + struct ieee80211_vif *vif = ctx->vif; + struct iwl_host_cmd hcmd = { + .id = REPLY_CHANNEL_SWITCH, + .len = sizeof(cmd), + .flags = CMD_SYNC, + .data = &cmd, + }; + + cmd.band = priv->band == IEEE80211_BAND_2GHZ; + ch = ch_switch->channel->hw_value; + IWL_DEBUG_11H(priv, "channel switch from %u to %u\n", + ctx->active.channel, ch); + cmd.channel = cpu_to_le16(ch); + cmd.rxon_flags = ctx->staging.flags; + cmd.rxon_filter_flags = ctx->staging.filter_flags; + switch_count = ch_switch->count; + tsf_low = ch_switch->timestamp & 0x0ffffffff; + /* + * calculate the ucode channel switch time + * adding TSF as one of the factor for when to switch + */ + if ((priv->ucode_beacon_time > tsf_low) && beacon_interval) { + if (switch_count > ((priv->ucode_beacon_time - tsf_low) / + beacon_interval)) { + switch_count -= (priv->ucode_beacon_time - + tsf_low) / beacon_interval; + } else + switch_count = 0; + } + if (switch_count <= 1) + cmd.switch_time = cpu_to_le32(priv->ucode_beacon_time); + else { + switch_time_in_usec = + vif->bss_conf.beacon_int * switch_count * TIME_UNIT; + ucode_switch_time = iwl_usecs_to_beacons(priv, + switch_time_in_usec, + beacon_interval); + cmd.switch_time = iwl_add_beacon_time(priv, + priv->ucode_beacon_time, + ucode_switch_time, + beacon_interval); + } + IWL_DEBUG_11H(priv, "uCode time for the switch is 0x%x\n", + cmd.switch_time); + ch_info = iwl_get_channel_info(priv, priv->band, ch); + if (ch_info) + cmd.expect_beacon = is_channel_radar(ch_info); + else { + IWL_ERR(priv, "invalid channel switch from %u to %u\n", + ctx->active.channel, ch); + return -EFAULT; + } + priv->switch_rxon.channel = cmd.channel; + priv->switch_rxon.switch_in_progress = true; + + return iwl_send_cmd_sync(priv, &hcmd); +} + +static struct iwl_lib_ops iwl2000_lib = { + .set_hw_params = iwl2000_hw_set_hw_params, + .txq_update_byte_cnt_tbl = iwlagn_txq_update_byte_cnt_tbl, + .txq_inval_byte_cnt_tbl = iwlagn_txq_inval_byte_cnt_tbl, + .txq_set_sched = iwlagn_txq_set_sched, + .txq_agg_enable = iwlagn_txq_agg_enable, + .txq_agg_disable = iwlagn_txq_agg_disable, + .txq_attach_buf_to_tfd = iwl_hw_txq_attach_buf_to_tfd, + .txq_free_tfd = iwl_hw_txq_free_tfd, + .txq_init = iwl_hw_tx_queue_init, + .rx_handler_setup = iwlagn_rx_handler_setup, + .setup_deferred_work = iwlagn_setup_deferred_work, + .is_valid_rtc_data_addr = iwlagn_hw_valid_rtc_data_addr, + .load_ucode = iwlagn_load_ucode, + .dump_nic_event_log = iwl_dump_nic_event_log, + .dump_nic_error_log = iwl_dump_nic_error_log, + .dump_csr = iwl_dump_csr, + .dump_fh = iwl_dump_fh, + .init_alive_start = iwlagn_init_alive_start, + .alive_notify = iwlagn_alive_notify, + .send_tx_power = iwlagn_send_tx_power, + .update_chain_flags = iwl_update_chain_flags, + .set_channel_switch = iwl2030_hw_channel_switch, + .apm_ops = { + .init = iwl_apm_init, + .config = iwl2000_nic_config, + }, + .eeprom_ops = { + .regulatory_bands = { + EEPROM_REG_BAND_1_CHANNELS, + EEPROM_REG_BAND_2_CHANNELS, + EEPROM_REG_BAND_3_CHANNELS, + EEPROM_REG_BAND_4_CHANNELS, + EEPROM_REG_BAND_5_CHANNELS, + EEPROM_6000_REG_BAND_24_HT40_CHANNELS, + EEPROM_REG_BAND_52_HT40_CHANNELS + }, + .acquire_semaphore = iwlcore_eeprom_acquire_semaphore, + .release_semaphore = iwlcore_eeprom_release_semaphore, + .calib_version = iwlagn_eeprom_calib_version, + .query_addr = iwlagn_eeprom_query_addr, + .update_enhanced_txpower = iwlcore_eeprom_enhanced_txpower, + }, + .isr_ops = { + .isr = iwl_isr_ict, + .free = iwl_free_isr_ict, + .alloc = iwl_alloc_isr_ict, + .reset = iwl_reset_ict, + .disable = iwl_disable_ict, + }, + .temp_ops = { + .temperature = iwlagn_temperature, + }, + .debugfs_ops = { + .rx_stats_read = iwl_ucode_rx_stats_read, + .tx_stats_read = iwl_ucode_tx_stats_read, + .general_stats_read = iwl_ucode_general_stats_read, + .bt_stats_read = iwl_ucode_bt_stats_read, + .reply_tx_error = iwl_reply_tx_error_read, + }, + .check_plcp_health = iwl_good_plcp_health, + .check_ack_health = iwl_good_ack_health, + .txfifo_flush = iwlagn_txfifo_flush, + .dev_txfifo_flush = iwlagn_dev_txfifo_flush, + .tt_ops = { + .lower_power_detection = iwl_tt_is_low_power_state, + .tt_power_mode = iwl_tt_current_power_mode, + .ct_kill_check = iwl_check_for_ct_kill, + } +}; + +static const struct iwl_ops iwl2000_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static const struct iwl_ops iwl2030_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_bt_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static const struct iwl_ops iwl200_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static const struct iwl_ops iwl230_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_bt_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static struct iwl_base_params iwl2000_base_params = { + .eeprom_size = OTP_LOW_IMAGE_SIZE, + .num_of_queues = IWLAGN_NUM_QUEUES, + .num_of_ampdu_queues = IWLAGN_NUM_AMPDU_QUEUES, + .pll_cfg_val = 0, + .set_l0s = true, + .use_bsm = false, + .max_ll_items = OTP_MAX_LL_ITEMS_2x00, + .shadow_ram_support = true, + .led_compensation = 51, + .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, + .adv_thermal_throttle = true, + .support_ct_kill_exit = true, + .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, + .chain_noise_scale = 1000, + .wd_timeout = IWL_DEF_WD_TIMEOUT, + .max_event_log_size = 512, + .ucode_tracing = true, + .sensitivity_calib_by_driver = true, + .chain_noise_calib_by_driver = true, + .shadow_reg_enable = true, +}; + + +static struct iwl_base_params iwl2030_base_params = { + .eeprom_size = OTP_LOW_IMAGE_SIZE, + .num_of_queues = IWLAGN_NUM_QUEUES, + .num_of_ampdu_queues = IWLAGN_NUM_AMPDU_QUEUES, + .pll_cfg_val = 0, + .set_l0s = true, + .use_bsm = false, + .max_ll_items = OTP_MAX_LL_ITEMS_2x00, + .shadow_ram_support = true, + .led_compensation = 57, + .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, + .adv_thermal_throttle = true, + .support_ct_kill_exit = true, + .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, + .chain_noise_scale = 1000, + .wd_timeout = IWL_LONG_WD_TIMEOUT, + .max_event_log_size = 512, + .ucode_tracing = true, + .sensitivity_calib_by_driver = true, + .chain_noise_calib_by_driver = true, + .shadow_reg_enable = true, +}; + +static struct iwl_ht_params iwl2000_ht_params = { + .ht_greenfield_support = true, + .use_rts_for_aggregation = true, /* use rts/cts protection */ +}; + +static struct iwl_bt_params iwl2030_bt_params = { + .bt_statistics = true, + /* Due to bluetooth, we transmit 2.4 GHz probes only on antenna A */ + .advanced_bt_coexist = true, + .agg_time_limit = BT_AGG_THRESHOLD_DEF, + .bt_init_traffic_load = IWL_BT_COEX_TRAFFIC_LOAD_NONE, + .bt_prio_boost = IWLAGN_BT_PRIO_BOOST_DEFAULT, + .bt_sco_disable = true, +}; + +#define IWL_DEVICE_2000 \ + .fw_name_pre = IWL2000_FW_PRE, \ + .ucode_api_max = IWL2000_UCODE_API_MAX, \ + .ucode_api_min = IWL2000_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl2000_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2000_base_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .iq_invert = true \ + +struct iwl_cfg iwl2000_2bgn_cfg = { + .name = "2000 Series 2x2 BGN", + IWL_DEVICE_2000, + .ht_params = &iwl2000_ht_params, +}; + +struct iwl_cfg iwl2000_2bg_cfg = { + .name = "2000 Series 2x2 BG", + IWL_DEVICE_2000, +}; + +#define IWL_DEVICE_2030 \ + .fw_name_pre = IWL2030_FW_PRE, \ + .ucode_api_max = IWL2030_UCODE_API_MAX, \ + .ucode_api_min = IWL2030_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl2030_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2030_base_params, \ + .bt_params = &iwl2030_bt_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true, \ + .iq_invert = true \ + +struct iwl_cfg iwl2030_2bgn_cfg = { + .name = "2000 Series 2x2 BGN/BT", + IWL_DEVICE_2030, + .ht_params = &iwl2000_ht_params, +}; + +struct iwl_cfg iwl2030_2bg_cfg = { + .name = "2000 Series 2x2 BG/BT", + IWL_DEVICE_2030, +}; + +#define IWL_DEVICE_6035 \ + .fw_name_pre = IWL2030_FW_PRE, \ + .ucode_api_max = IWL2030_UCODE_API_MAX, \ + .ucode_api_min = IWL2030_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_6035_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6035_TX_POWER_VERSION, \ + .ops = &iwl2030_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2030_base_params, \ + .bt_params = &iwl2030_bt_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true \ + +struct iwl_cfg iwl6035_2agn_cfg = { + .name = "2000 Series 2x2 AGN/BT", + IWL_DEVICE_6035, + .ht_params = &iwl2000_ht_params, +}; + +struct iwl_cfg iwl6035_2abg_cfg = { + .name = "2000 Series 2x2 ABG/BT", + IWL_DEVICE_6035, +}; + +struct iwl_cfg iwl6035_2bg_cfg = { + .name = "2000 Series 2x2 BG/BT", + IWL_DEVICE_6035, +}; + +#define IWL_DEVICE_200 \ + .fw_name_pre = IWL200_FW_PRE, \ + .ucode_api_max = IWL200_UCODE_API_MAX, \ + .ucode_api_min = IWL200_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl200_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2000_base_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true, \ + .rx_with_siso_diversity = true \ + +struct iwl_cfg iwl200_bg_cfg = { + .name = "200 Series 1x1 BG", + IWL_DEVICE_200, +}; + +struct iwl_cfg iwl200_bgn_cfg = { + .name = "200 Series 1x1 BGN", + IWL_DEVICE_200, + .ht_params = &iwl2000_ht_params, +}; + +#define IWL_DEVICE_230 \ + .fw_name_pre = IWL200_FW_PRE, \ + .ucode_api_max = IWL200_UCODE_API_MAX, \ + .ucode_api_min = IWL200_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl230_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2030_base_params, \ + .bt_params = &iwl2030_bt_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true, \ + .rx_with_siso_diversity = true \ + +struct iwl_cfg iwl230_bg_cfg = { + .name = "200 Series 1x1 BG/BT", + IWL_DEVICE_230, +}; + +struct iwl_cfg iwl230_bgn_cfg = { + .name = "200 Series 1x1 BGN/BT", + IWL_DEVICE_230, + .ht_params = &iwl2000_ht_params, +}; + +MODULE_FIRMWARE(IWL2000_MODULE_FIRMWARE(IWL2000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL2030_MODULE_FIRMWARE(IWL2030_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL200_MODULE_FIRMWARE(IWL200_UCODE_API_MAX)); diff --git a/drivers/net/wireless/iwlwifi/iwl-3945-led.c b/drivers/net/wireless/iwlwifi/iwl-3945-led.c index abe2b73..dc7c3a4 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945-led.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945-led.c @@ -59,33 +59,6 @@ static int iwl3945_send_led_cmd(struct iwl_priv *priv, return iwl_send_cmd(priv, &cmd); } -/* Set led on command */ -static int iwl3945_led_on(struct iwl_priv *priv) -{ - struct iwl_led_cmd led_cmd = { - .id = IWL_LED_LINK, - .on = IWL_LED_SOLID, - .off = 0, - .interval = IWL_DEF_LED_INTRVL - }; - return iwl3945_send_led_cmd(priv, &led_cmd); -} - -/* Set led off command */ -static int iwl3945_led_off(struct iwl_priv *priv) -{ - struct iwl_led_cmd led_cmd = { - .id = IWL_LED_LINK, - .on = 0, - .off = 0, - .interval = IWL_DEF_LED_INTRVL - }; - IWL_DEBUG_LED(priv, "led off\n"); - return iwl3945_send_led_cmd(priv, &led_cmd); -} - const struct iwl_led_ops iwl3945_led_ops = { .cmd = iwl3945_send_led_cmd, - .on = iwl3945_led_on, - .off = iwl3945_led_off, }; diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.c b/drivers/net/wireless/iwlwifi/iwl-3945.c index 39b6f16..166e9f7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945.c @@ -528,10 +528,11 @@ static void iwl3945_rx_reply_rx(struct iwl_priv *priv, rx_status.flag = 0; rx_status.mactime = le64_to_cpu(rx_end->timestamp); - rx_status.freq = - ieee80211_channel_to_frequency(le16_to_cpu(rx_hdr->channel)); rx_status.band = (rx_hdr->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + rx_status.freq = + ieee80211_channel_to_frequency(le16_to_cpu(rx_hdr->channel), + rx_status.band); rx_status.rate_idx = iwl3945_hwrate_to_plcp_idx(rx_hdr->rate); if (rx_status.band == IEEE80211_BAND_5GHZ) @@ -695,8 +696,7 @@ void iwl3945_hw_build_tx_cmd_rate(struct iwl_priv *priv, /* We need to figure out how to get the sta->supp_rates while * in this running context */ - rate_mask = IWL_RATES_MASK; - + rate_mask = IWL_RATES_MASK_3945; /* Set retry limit on DATA packets and Probe Responses*/ if (ieee80211_is_probe_resp(fc)) @@ -1583,7 +1583,7 @@ static int iwl3945_hw_reg_comp_txpower_temp(struct iwl_priv *priv) ref_temp); /* set tx power value for all rates, OFDM and CCK */ - for (rate_index = 0; rate_index < IWL_RATE_COUNT; + for (rate_index = 0; rate_index < IWL_RATE_COUNT_3945; rate_index++) { int power_idx = ch_info->power_info[rate_index].base_power_index; @@ -1823,7 +1823,7 @@ int iwl3945_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) /* If we issue a new RXON command which required a tune then we must * send a new TXPOWER command or we won't be able to Tx any frames */ - rc = priv->cfg->ops->lib->send_tx_power(priv); + rc = iwl_set_tx_power(priv, priv->tx_power_next, true); if (rc) { IWL_ERR(priv, "Error setting Tx power (%d).\n", rc); return rc; diff --git a/drivers/net/wireless/iwlwifi/iwl-4965.c b/drivers/net/wireless/iwlwifi/iwl-4965.c index 91a9f52..8998ed1 100644 --- a/drivers/net/wireless/iwlwifi/iwl-4965.c +++ b/drivers/net/wireless/iwlwifi/iwl-4965.c @@ -251,14 +251,6 @@ static int iwl4965_set_ucode_ptrs(struct iwl_priv *priv) */ static void iwl4965_init_alive_start(struct iwl_priv *priv) { - /* Check alive response for "valid" sign from uCode */ - if (priv->card_alive_init.is_valid != UCODE_VALID_OK) { - /* We had an error bringing up the hardware, so take it - * all the way back down so we can try again */ - IWL_DEBUG_INFO(priv, "Initialize Alive failed.\n"); - goto restart; - } - /* Bootstrap uCode has loaded initialize uCode ... verify inst image. * This is a paranoid check, because we would not have gotten the * "initialize" alive if code weren't properly loaded. */ @@ -1571,7 +1563,7 @@ static int iwl4965_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *c /* If we issue a new RXON command which required a tune then we must * send a new TXPOWER command or we won't be able to Tx any frames */ - ret = iwl_set_tx_power(priv, priv->tx_power_user_lmt, true); + ret = iwl_set_tx_power(priv, priv->tx_power_next, true); if (ret) { IWL_ERR(priv, "Error sending TX power (%d)\n", ret); return ret; @@ -2274,6 +2266,29 @@ static void iwl4965_rx_reply_tx(struct iwl_priv *priv, spin_unlock_irqrestore(&priv->sta_lock, flags); } +static void iwl4965_rx_beacon_notif(struct iwl_priv *priv, + struct iwl_rx_mem_buffer *rxb) +{ + struct iwl_rx_packet *pkt = rxb_addr(rxb); + struct iwl4965_beacon_notif *beacon = (void *)pkt->u.raw; +#ifdef CONFIG_IWLWIFI_DEBUG + u8 rate = iwl_hw_get_rate(beacon->beacon_notify_hdr.rate_n_flags); + + IWL_DEBUG_RX(priv, "beacon status %#x, retries:%d ibssmgr:%d " + "tsf:0x%.8x%.8x rate:%d\n", + le32_to_cpu(beacon->beacon_notify_hdr.u.status) & TX_STATUS_MSK, + beacon->beacon_notify_hdr.failure_frame, + le32_to_cpu(beacon->ibss_mgr_status), + le32_to_cpu(beacon->high_tsf), + le32_to_cpu(beacon->low_tsf), rate); +#endif + + priv->ibss_manager = le32_to_cpu(beacon->ibss_mgr_status); + + if (!test_bit(STATUS_EXIT_PENDING, &priv->status)) + queue_work(priv->workqueue, &priv->beacon_update); +} + static int iwl4965_calc_rssi(struct iwl_priv *priv, struct iwl_rx_phy_res *rx_resp) { @@ -2316,6 +2331,12 @@ static void iwl4965_rx_handler_setup(struct iwl_priv *priv) priv->rx_handlers[REPLY_RX] = iwlagn_rx_reply_rx; /* Tx response */ priv->rx_handlers[REPLY_TX] = iwl4965_rx_reply_tx; + priv->rx_handlers[BEACON_NOTIFICATION] = iwl4965_rx_beacon_notif; + + /* set up notification wait support */ + spin_lock_init(&priv->_agn.notif_wait_lock); + INIT_LIST_HEAD(&priv->_agn.notif_waits); + init_waitqueue_head(&priv->_agn.notif_waitq); } static void iwl4965_setup_deferred_work(struct iwl_priv *priv) diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index ef36aff..f6493f7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -67,13 +67,13 @@ #define _IWL6050_MODULE_FIRMWARE(api) IWL6050_FW_PRE #api ".ucode" #define IWL6050_MODULE_FIRMWARE(api) _IWL6050_MODULE_FIRMWARE(api) -#define IWL6000G2A_FW_PRE "iwlwifi-6000g2a-" -#define _IWL6000G2A_MODULE_FIRMWARE(api) IWL6000G2A_FW_PRE #api ".ucode" -#define IWL6000G2A_MODULE_FIRMWARE(api) _IWL6000G2A_MODULE_FIRMWARE(api) +#define IWL6005_FW_PRE "iwlwifi-6000g2a-" +#define _IWL6005_MODULE_FIRMWARE(api) IWL6005_FW_PRE #api ".ucode" +#define IWL6005_MODULE_FIRMWARE(api) _IWL6005_MODULE_FIRMWARE(api) -#define IWL6000G2B_FW_PRE "iwlwifi-6000g2b-" -#define _IWL6000G2B_MODULE_FIRMWARE(api) IWL6000G2B_FW_PRE #api ".ucode" -#define IWL6000G2B_MODULE_FIRMWARE(api) _IWL6000G2B_MODULE_FIRMWARE(api) +#define IWL6030_FW_PRE "iwlwifi-6000g2b-" +#define _IWL6030_MODULE_FIRMWARE(api) IWL6030_FW_PRE #api ".ucode" +#define IWL6030_MODULE_FIRMWARE(api) _IWL6030_MODULE_FIRMWARE(api) static void iwl6000_set_ct_threshold(struct iwl_priv *priv) { @@ -90,7 +90,7 @@ static void iwl6050_additional_nic_config(struct iwl_priv *priv) CSR_GP_DRIVER_REG_BIT_CALIB_VERSION6); } -static void iwl6050g2_additional_nic_config(struct iwl_priv *priv) +static void iwl6150_additional_nic_config(struct iwl_priv *priv) { /* Indicate calibration version to uCode. */ if (priv->cfg->ops->lib->eeprom_ops.calib_version(priv) >= 6) @@ -354,7 +354,7 @@ static struct iwl_lib_ops iwl6000_lib = { } }; -static struct iwl_lib_ops iwl6000g2b_lib = { +static struct iwl_lib_ops iwl6030_lib = { .set_hw_params = iwl6000_hw_set_hw_params, .txq_update_byte_cnt_tbl = iwlagn_txq_update_byte_cnt_tbl, .txq_inval_byte_cnt_tbl = iwlagn_txq_inval_byte_cnt_tbl, @@ -430,8 +430,8 @@ static struct iwl_nic_ops iwl6050_nic_ops = { .additional_nic_config = &iwl6050_additional_nic_config, }; -static struct iwl_nic_ops iwl6050g2_nic_ops = { - .additional_nic_config = &iwl6050g2_additional_nic_config, +static struct iwl_nic_ops iwl6150_nic_ops = { + .additional_nic_config = &iwl6150_additional_nic_config, }; static const struct iwl_ops iwl6000_ops = { @@ -451,17 +451,17 @@ static const struct iwl_ops iwl6050_ops = { .ieee80211_ops = &iwlagn_hw_ops, }; -static const struct iwl_ops iwl6050g2_ops = { +static const struct iwl_ops iwl6150_ops = { .lib = &iwl6000_lib, .hcmd = &iwlagn_hcmd, .utils = &iwlagn_hcmd_utils, .led = &iwlagn_led_ops, - .nic = &iwl6050g2_nic_ops, + .nic = &iwl6150_nic_ops, .ieee80211_ops = &iwlagn_hw_ops, }; -static const struct iwl_ops iwl6000g2b_ops = { - .lib = &iwl6000g2b_lib, +static const struct iwl_ops iwl6030_ops = { + .lib = &iwl6030_lib, .hcmd = &iwlagn_bt_hcmd, .utils = &iwlagn_hcmd_utils, .led = &iwlagn_led_ops, @@ -479,7 +479,6 @@ static struct iwl_base_params iwl6000_base_params = { .shadow_ram_support = true, .led_compensation = 51, .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, - .supports_idle = true, .adv_thermal_throttle = true, .support_ct_kill_exit = true, .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, @@ -503,7 +502,6 @@ static struct iwl_base_params iwl6050_base_params = { .shadow_ram_support = true, .led_compensation = 51, .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, - .supports_idle = true, .adv_thermal_throttle = true, .support_ct_kill_exit = true, .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, @@ -526,7 +524,6 @@ static struct iwl_base_params iwl6000_g2_base_params = { .shadow_ram_support = true, .led_compensation = 57, .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, - .supports_idle = true, .adv_thermal_throttle = true, .support_ct_kill_exit = true, .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, @@ -555,11 +552,11 @@ static struct iwl_bt_params iwl6000_bt_params = { }; #define IWL_DEVICE_6005 \ - .fw_name_pre = IWL6000G2A_FW_PRE, \ + .fw_name_pre = IWL6005_FW_PRE, \ .ucode_api_max = IWL6000G2_UCODE_API_MAX, \ .ucode_api_min = IWL6000G2_UCODE_API_MIN, \ - .eeprom_ver = EEPROM_6000G2_EEPROM_VERSION, \ - .eeprom_calib_ver = EEPROM_6000G2_TX_POWER_VERSION, \ + .eeprom_ver = EEPROM_6005_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6005_TX_POWER_VERSION, \ .ops = &iwl6000_ops, \ .mod_params = &iwlagn_mod_params, \ .base_params = &iwl6000_g2_base_params, \ @@ -584,12 +581,12 @@ struct iwl_cfg iwl6005_2bg_cfg = { }; #define IWL_DEVICE_6030 \ - .fw_name_pre = IWL6000G2B_FW_PRE, \ + .fw_name_pre = IWL6030_FW_PRE, \ .ucode_api_max = IWL6000G2_UCODE_API_MAX, \ .ucode_api_min = IWL6000G2_UCODE_API_MIN, \ - .eeprom_ver = EEPROM_6000G2_EEPROM_VERSION, \ - .eeprom_calib_ver = EEPROM_6000G2_TX_POWER_VERSION, \ - .ops = &iwl6000g2b_ops, \ + .eeprom_ver = EEPROM_6030_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6030_TX_POWER_VERSION, \ + .ops = &iwl6030_ops, \ .mod_params = &iwlagn_mod_params, \ .base_params = &iwl6000_g2_base_params, \ .bt_params = &iwl6000_bt_params, \ @@ -708,9 +705,9 @@ struct iwl_cfg iwl6150_bgn_cfg = { .fw_name_pre = IWL6050_FW_PRE, .ucode_api_max = IWL6050_UCODE_API_MAX, .ucode_api_min = IWL6050_UCODE_API_MIN, - .eeprom_ver = EEPROM_6050G2_EEPROM_VERSION, - .eeprom_calib_ver = EEPROM_6050G2_TX_POWER_VERSION, - .ops = &iwl6050g2_ops, + .eeprom_ver = EEPROM_6150_EEPROM_VERSION, + .eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION, + .ops = &iwl6150_ops, .mod_params = &iwlagn_mod_params, .base_params = &iwl6050_base_params, .ht_params = &iwl6000_ht_params, @@ -736,5 +733,5 @@ struct iwl_cfg iwl6000_3agn_cfg = { MODULE_FIRMWARE(IWL6000_MODULE_FIRMWARE(IWL6000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL6050_MODULE_FIRMWARE(IWL6050_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL6000G2A_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL6000G2B_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL6005_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL6030_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-calib.c b/drivers/net/wireless/iwlwifi/iwl-agn-calib.c index d16bb5e..9006293 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-calib.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-calib.c @@ -631,8 +631,7 @@ void iwl_sensitivity_calibration(struct iwl_priv *priv, void *resp) } spin_lock_irqsave(&priv->lock, flags); - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { rx_info = &(((struct iwl_bt_notif_statistics *)resp)-> rx.general.common); ofdm = &(((struct iwl_bt_notif_statistics *)resp)->rx.ofdm); @@ -897,8 +896,7 @@ void iwl_chain_noise_calibration(struct iwl_priv *priv, void *stat_resp) } spin_lock_irqsave(&priv->lock, flags); - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { rx_info = &(((struct iwl_bt_notif_statistics *)stat_resp)-> rx.general.common); } else { @@ -913,8 +911,7 @@ void iwl_chain_noise_calibration(struct iwl_priv *priv, void *stat_resp) rxon_band24 = !!(ctx->staging.flags & RXON_FLG_BAND_24G_MSK); rxon_chnum = le16_to_cpu(ctx->staging.channel); - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { stat_band24 = !!(((struct iwl_bt_notif_statistics *) stat_resp)->flag & STATISTICS_REPLY_FLG_BAND_24G_MSK); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-agn-debugfs.c index a6dbd89..b500aaa 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-debugfs.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-debugfs.c @@ -39,8 +39,7 @@ static int iwl_statistics_flag(struct iwl_priv *priv, char *buf, int bufsz) int p = 0; u32 flag; - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) + if (iwl_bt_statistics(priv)) flag = le32_to_cpu(priv->_agn.statistics_bt.flag); else flag = le32_to_cpu(priv->_agn.statistics.flag); @@ -89,8 +88,7 @@ ssize_t iwl_ucode_rx_stats_read(struct file *file, char __user *user_buf, * the last statistics notification from uCode * might not reflect the current uCode activity */ - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { ofdm = &priv->_agn.statistics_bt.rx.ofdm; cck = &priv->_agn.statistics_bt.rx.cck; general = &priv->_agn.statistics_bt.rx.general.common; @@ -536,8 +534,7 @@ ssize_t iwl_ucode_tx_stats_read(struct file *file, * the last statistics notification from uCode * might not reflect the current uCode activity */ - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { tx = &priv->_agn.statistics_bt.tx; accum_tx = &priv->_agn.accum_statistics_bt.tx; delta_tx = &priv->_agn.delta_statistics_bt.tx; @@ -737,8 +734,7 @@ ssize_t iwl_ucode_general_stats_read(struct file *file, char __user *user_buf, * the last statistics notification from uCode * might not reflect the current uCode activity */ - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { general = &priv->_agn.statistics_bt.general.common; dbg = &priv->_agn.statistics_bt.general.common.dbg; div = &priv->_agn.statistics_bt.general.common.div; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c index 366340f..41543ad 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c @@ -305,7 +305,11 @@ static int iwlagn_set_pan_params(struct iwl_priv *priv) cmd.slots[0].type = 0; /* BSS */ cmd.slots[1].type = 1; /* PAN */ - if (ctx_bss->vif && ctx_pan->vif) { + if (priv->_agn.hw_roc_channel) { + /* both contexts must be used for this to happen */ + slot1 = priv->_agn.hw_roc_duration; + slot0 = IWL_MIN_SLOT_TIME; + } else if (ctx_bss->vif && ctx_pan->vif) { int bcnint = ctx_pan->vif->bss_conf.beacon_int; int dtim = ctx_pan->vif->bss_conf.dtim_period ?: 1; @@ -330,12 +334,12 @@ static int iwlagn_set_pan_params(struct iwl_priv *priv) if (test_bit(STATUS_SCAN_HW, &priv->status) || (!ctx_bss->vif->bss_conf.idle && !ctx_bss->vif->bss_conf.assoc)) { - slot0 = dtim * bcnint * 3 - 20; - slot1 = 20; + slot0 = dtim * bcnint * 3 - IWL_MIN_SLOT_TIME; + slot1 = IWL_MIN_SLOT_TIME; } else if (!ctx_pan->vif->bss_conf.idle && !ctx_pan->vif->bss_conf.assoc) { - slot1 = bcnint * 3 - 20; - slot0 = 20; + slot1 = bcnint * 3 - IWL_MIN_SLOT_TIME; + slot0 = IWL_MIN_SLOT_TIME; } } else if (ctx_pan->vif) { slot0 = 0; @@ -344,8 +348,8 @@ static int iwlagn_set_pan_params(struct iwl_priv *priv) slot1 = max_t(int, DEFAULT_BEACON_INTERVAL, slot1); if (test_bit(STATUS_SCAN_HW, &priv->status)) { - slot0 = slot1 * 3 - 20; - slot1 = 20; + slot0 = slot1 * 3 - IWL_MIN_SLOT_TIME; + slot1 = IWL_MIN_SLOT_TIME; } } diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-led.c b/drivers/net/wireless/iwlwifi/iwl-agn-led.c index 1a24946..c1190d9 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-led.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-led.c @@ -63,23 +63,11 @@ static int iwl_send_led_cmd(struct iwl_priv *priv, struct iwl_led_cmd *led_cmd) } /* Set led register off */ -static int iwl_led_on_reg(struct iwl_priv *priv) +void iwlagn_led_enable(struct iwl_priv *priv) { - IWL_DEBUG_LED(priv, "led on\n"); iwl_write32(priv, CSR_LED_REG, CSR_LED_REG_TRUN_ON); - return 0; -} - -/* Set led register off */ -static int iwl_led_off_reg(struct iwl_priv *priv) -{ - IWL_DEBUG_LED(priv, "LED Reg off\n"); - iwl_write32(priv, CSR_LED_REG, CSR_LED_REG_TRUN_OFF); - return 0; } const struct iwl_led_ops iwlagn_led_ops = { .cmd = iwl_send_led_cmd, - .on = iwl_led_on_reg, - .off = iwl_led_off_reg, }; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-led.h b/drivers/net/wireless/iwlwifi/iwl-agn-led.h index a594e4fd..96f323d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-led.h +++ b/drivers/net/wireless/iwlwifi/iwl-agn-led.h @@ -28,5 +28,6 @@ #define __iwl_agn_led_h__ extern const struct iwl_led_ops iwlagn_led_ops; +void iwlagn_led_enable(struct iwl_priv *priv); #endif /* __iwl_agn_led_h__ */ diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c index 3dee87e..3aa4864 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c @@ -473,6 +473,11 @@ void iwlagn_rx_handler_setup(struct iwl_priv *priv) priv->rx_handlers[CALIBRATION_COMPLETE_NOTIFICATION] = iwlagn_rx_calib_complete; priv->rx_handlers[REPLY_TX] = iwlagn_rx_reply_tx; + + /* set up notification wait support */ + spin_lock_init(&priv->_agn.notif_wait_lock); + INIT_LIST_HEAD(&priv->_agn.notif_waits); + init_waitqueue_head(&priv->_agn.notif_waitq); } void iwlagn_setup_deferred_work(struct iwl_priv *priv) @@ -1157,10 +1162,11 @@ void iwlagn_rx_reply_rx(struct iwl_priv *priv, /* rx_status carries information about the packet to mac80211 */ rx_status.mactime = le64_to_cpu(phy_res->timestamp); - rx_status.freq = - ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel)); rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + rx_status.freq = + ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel), + rx_status.band); rx_status.rate_idx = iwlagn_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band); rx_status.flag = 0; @@ -1389,15 +1395,12 @@ int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif) u32 extra; u32 suspend_time = 100; u32 scan_suspend_time = 100; - unsigned long flags; IWL_DEBUG_INFO(priv, "Scanning while associated...\n"); - spin_lock_irqsave(&priv->lock, flags); if (priv->is_internal_short_scan) interval = 0; else interval = vif->bss_conf.beacon_int; - spin_unlock_irqrestore(&priv->lock, flags); scan->suspend_time = 0; scan->max_out_time = cpu_to_le32(200 * 1024); @@ -1857,21 +1860,6 @@ void iwlagn_send_advance_bt_config(struct iwl_priv *priv) if (iwl_send_cmd_pdu(priv, REPLY_BT_CONFIG, sizeof(bt_cmd), &bt_cmd)) IWL_ERR(priv, "failed to send BT Coex Config\n"); - /* - * When we are doing a restart, need to also reconfigure BT - * SCO to the device. If not doing a restart, bt_sco_active - * will always be false, so there's no need to have an extra - * variable to check for it. - */ - if (priv->bt_sco_active) { - struct iwlagn_bt_sco_cmd sco_cmd = { .flags = 0 }; - - if (priv->bt_sco_active) - sco_cmd.flags |= IWLAGN_BT_SCO_ACTIVE; - if (iwl_send_cmd_pdu(priv, REPLY_BT_COEX_SCO, - sizeof(sco_cmd), &sco_cmd)) - IWL_ERR(priv, "failed to send BT SCO command\n"); - } } static void iwlagn_bt_traffic_change_work(struct work_struct *work) @@ -2032,7 +2020,6 @@ void iwlagn_bt_coex_profile_notif(struct iwl_priv *priv, unsigned long flags; struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_bt_coex_profile_notif *coex = &pkt->u.bt_coex_profile_notif; - struct iwlagn_bt_sco_cmd sco_cmd = { .flags = 0 }; struct iwl_bt_uart_msg *uart_msg = &coex->last_bt_uart_msg; IWL_DEBUG_NOTIF(priv, "BT Coex notification:\n"); @@ -2063,15 +2050,6 @@ void iwlagn_bt_coex_profile_notif(struct iwl_priv *priv, queue_work(priv->workqueue, &priv->bt_traffic_change_work); } - if (priv->bt_sco_active != - (uart_msg->frame3 & BT_UART_MSG_FRAME3SCOESCO_MSK)) { - priv->bt_sco_active = uart_msg->frame3 & - BT_UART_MSG_FRAME3SCOESCO_MSK; - if (priv->bt_sco_active) - sco_cmd.flags |= IWLAGN_BT_SCO_ACTIVE; - iwl_send_cmd_pdu_async(priv, REPLY_BT_COEX_SCO, - sizeof(sco_cmd), &sco_cmd, NULL); - } } iwlagn_set_kill_msk(priv, uart_msg); @@ -2389,3 +2367,44 @@ int iwl_dump_fh(struct iwl_priv *priv, char **buf, bool display) } return 0; } + +/* notification wait support */ +void iwlagn_init_notification_wait(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + void (*fn)(struct iwl_priv *priv, + struct iwl_rx_packet *pkt), + u8 cmd) +{ + wait_entry->fn = fn; + wait_entry->cmd = cmd; + wait_entry->triggered = false; + + spin_lock_bh(&priv->_agn.notif_wait_lock); + list_add(&wait_entry->list, &priv->_agn.notif_waits); + spin_unlock_bh(&priv->_agn.notif_wait_lock); +} + +signed long iwlagn_wait_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + unsigned long timeout) +{ + int ret; + + ret = wait_event_timeout(priv->_agn.notif_waitq, + &wait_entry->triggered, + timeout); + + spin_lock_bh(&priv->_agn.notif_wait_lock); + list_del(&wait_entry->list); + spin_unlock_bh(&priv->_agn.notif_wait_lock); + + return ret; +} + +void iwlagn_remove_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry) +{ + spin_lock_bh(&priv->_agn.notif_wait_lock); + list_del(&wait_entry->list); + spin_unlock_bh(&priv->_agn.notif_wait_lock); +} diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c index 75fcd30..d03b473 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c @@ -179,31 +179,31 @@ static s32 expected_tpt_legacy[IWL_RATE_COUNT] = { }; static s32 expected_tpt_siso20MHz[4][IWL_RATE_COUNT] = { - {0, 0, 0, 0, 42, 0, 76, 102, 124, 158, 183, 193, 202}, /* Norm */ - {0, 0, 0, 0, 46, 0, 82, 110, 132, 167, 192, 202, 210}, /* SGI */ - {0, 0, 0, 0, 48, 0, 93, 135, 176, 251, 319, 351, 381}, /* AGG */ - {0, 0, 0, 0, 53, 0, 102, 149, 193, 275, 348, 381, 413}, /* AGG+SGI */ + {0, 0, 0, 0, 42, 0, 76, 102, 124, 159, 183, 193, 202}, /* Norm */ + {0, 0, 0, 0, 46, 0, 82, 110, 132, 168, 192, 202, 210}, /* SGI */ + {0, 0, 0, 0, 47, 0, 91, 133, 171, 242, 305, 334, 362}, /* AGG */ + {0, 0, 0, 0, 52, 0, 101, 145, 187, 264, 330, 361, 390}, /* AGG+SGI */ }; static s32 expected_tpt_siso40MHz[4][IWL_RATE_COUNT] = { {0, 0, 0, 0, 77, 0, 127, 160, 184, 220, 242, 250, 257}, /* Norm */ {0, 0, 0, 0, 83, 0, 135, 169, 193, 229, 250, 257, 264}, /* SGI */ - {0, 0, 0, 0, 96, 0, 182, 259, 328, 451, 553, 598, 640}, /* AGG */ - {0, 0, 0, 0, 106, 0, 199, 282, 357, 487, 593, 640, 683}, /* AGG+SGI */ + {0, 0, 0, 0, 94, 0, 177, 249, 313, 423, 512, 550, 586}, /* AGG */ + {0, 0, 0, 0, 104, 0, 193, 270, 338, 454, 545, 584, 620}, /* AGG+SGI */ }; static s32 expected_tpt_mimo2_20MHz[4][IWL_RATE_COUNT] = { - {0, 0, 0, 0, 74, 0, 123, 155, 179, 213, 235, 243, 250}, /* Norm */ - {0, 0, 0, 0, 81, 0, 131, 164, 187, 221, 242, 250, 256}, /* SGI */ - {0, 0, 0, 0, 92, 0, 175, 250, 317, 436, 534, 578, 619}, /* AGG */ - {0, 0, 0, 0, 102, 0, 192, 273, 344, 470, 573, 619, 660}, /* AGG+SGI*/ + {0, 0, 0, 0, 74, 0, 123, 155, 179, 214, 236, 244, 251}, /* Norm */ + {0, 0, 0, 0, 81, 0, 131, 164, 188, 223, 243, 251, 257}, /* SGI */ + {0, 0, 0, 0, 89, 0, 167, 235, 296, 402, 488, 526, 560}, /* AGG */ + {0, 0, 0, 0, 97, 0, 182, 255, 320, 431, 520, 558, 593}, /* AGG+SGI*/ }; static s32 expected_tpt_mimo2_40MHz[4][IWL_RATE_COUNT] = { {0, 0, 0, 0, 123, 0, 182, 214, 235, 264, 279, 285, 289}, /* Norm */ {0, 0, 0, 0, 131, 0, 191, 222, 242, 270, 284, 289, 293}, /* SGI */ - {0, 0, 0, 0, 180, 0, 327, 446, 545, 708, 828, 878, 922}, /* AGG */ - {0, 0, 0, 0, 197, 0, 355, 481, 584, 752, 872, 922, 966}, /* AGG+SGI */ + {0, 0, 0, 0, 171, 0, 305, 410, 496, 634, 731, 771, 805}, /* AGG */ + {0, 0, 0, 0, 186, 0, 329, 439, 527, 667, 764, 803, 838}, /* AGG+SGI */ }; static s32 expected_tpt_mimo3_20MHz[4][IWL_RATE_COUNT] = { @@ -2890,6 +2890,8 @@ static void rs_fill_link_cmd(struct iwl_priv *priv, u8 ant_toggle_cnt = 0; u8 use_ht_possible = 1; u8 valid_tx_ant = 0; + struct iwl_station_priv *sta_priv = + container_of(lq_sta, struct iwl_station_priv, lq_sta); struct iwl_link_quality_cmd *lq_cmd = &lq_sta->lq; /* Override starting rate (index 0) if needed for debug purposes */ @@ -3008,7 +3010,8 @@ static void rs_fill_link_cmd(struct iwl_priv *priv, repeat_rate--; } - lq_cmd->agg_params.agg_frame_cnt_limit = LINK_QUAL_AGG_FRAME_LIMIT_DEF; + lq_cmd->agg_params.agg_frame_cnt_limit = + sta_priv->max_agg_bufsize ?: LINK_QUAL_AGG_FRAME_LIMIT_DEF; lq_cmd->agg_params.agg_dis_start_th = LINK_QUAL_AGG_DISABLE_START_DEF; lq_cmd->agg_params.agg_time_limit = diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.h b/drivers/net/wireless/iwlwifi/iwl-agn-rs.h index 75e50d3..184828c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.h +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.h @@ -213,6 +213,7 @@ enum { IWL_CCK_BASIC_RATES_MASK) #define IWL_RATES_MASK ((1 << IWL_RATE_COUNT) - 1) +#define IWL_RATES_MASK_3945 ((1 << IWL_RATE_COUNT_3945) - 1) #define IWL_INVALID_VALUE -1 diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rx.c b/drivers/net/wireless/iwlwifi/iwl-agn-rx.c index bbd40b7..b192ca8 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rx.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rx.c @@ -73,8 +73,7 @@ static void iwl_rx_calc_noise(struct iwl_priv *priv) int bcn_silence_a, bcn_silence_b, bcn_silence_c; int last_rx_noise; - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) + if (iwl_bt_statistics(priv)) rx_info = &(priv->_agn.statistics_bt.rx.general.common); else rx_info = &(priv->_agn.statistics.rx.general); @@ -125,8 +124,7 @@ static void iwl_accumulative_statistics(struct iwl_priv *priv, struct statistics_general_common *general, *accum_general; struct statistics_tx *tx, *accum_tx; - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { prev_stats = (__le32 *)&priv->_agn.statistics_bt; accum_stats = (u32 *)&priv->_agn.accum_statistics_bt; size = sizeof(struct iwl_bt_notif_statistics); @@ -207,8 +205,7 @@ bool iwl_good_plcp_health(struct iwl_priv *priv, struct statistics_rx_phy *ofdm; struct statistics_rx_ht_phy *ofdm_ht; - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { ofdm = &pkt->u.stats_bt.rx.ofdm; ofdm_ht = &pkt->u.stats_bt.rx.ofdm_ht; combined_plcp_delta = @@ -265,8 +262,7 @@ void iwl_rx_statistics(struct iwl_priv *priv, int change; struct iwl_rx_packet *pkt = rxb_addr(rxb); - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { IWL_DEBUG_RX(priv, "Statistics notification received (%d vs %d).\n", (int)sizeof(struct iwl_bt_notif_statistics), @@ -304,8 +300,7 @@ void iwl_rx_statistics(struct iwl_priv *priv, iwl_recover_from_statistics(priv, pkt); - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) + if (iwl_bt_statistics(priv)) memcpy(&priv->_agn.statistics_bt, &pkt->u.stats_bt, sizeof(priv->_agn.statistics_bt)); else diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c index 6d140bd..6c2adc5 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c @@ -52,10 +52,14 @@ static int iwlagn_disable_pan(struct iwl_priv *priv, struct iwl_rxon_context *ctx, struct iwl_rxon_cmd *send) { + struct iwl_notification_wait disable_wait; __le32 old_filter = send->filter_flags; u8 old_dev_type = send->dev_type; int ret; + iwlagn_init_notification_wait(priv, &disable_wait, NULL, + REPLY_WIPAN_DEACTIVATION_COMPLETE); + send->filter_flags &= ~RXON_FILTER_ASSOC_MSK; send->dev_type = RXON_DEV_TYPE_P2P; ret = iwl_send_cmd_pdu(priv, ctx->rxon_cmd, sizeof(*send), send); @@ -63,11 +67,18 @@ static int iwlagn_disable_pan(struct iwl_priv *priv, send->filter_flags = old_filter; send->dev_type = old_dev_type; - if (ret) + if (ret) { IWL_ERR(priv, "Error disabling PAN (%d)\n", ret); - - /* FIXME: WAIT FOR PAN DISABLE */ - msleep(300); + iwlagn_remove_notification(priv, &disable_wait); + } else { + signed long wait_res; + + wait_res = iwlagn_wait_notification(priv, &disable_wait, HZ); + if (wait_res == 0) { + IWL_ERR(priv, "Timed out waiting for PAN disable\n"); + ret = -EIO; + } + } return ret; } @@ -145,6 +156,23 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) /* always get timestamp with Rx frame */ ctx->staging.flags |= RXON_FLG_TSF2HOST_MSK; + if (ctx->ctxid == IWL_RXON_CTX_PAN && priv->_agn.hw_roc_channel) { + struct ieee80211_channel *chan = priv->_agn.hw_roc_channel; + + iwl_set_rxon_channel(priv, chan, ctx); + iwl_set_flags_for_band(priv, ctx, chan->band, NULL); + ctx->staging.filter_flags |= + RXON_FILTER_ASSOC_MSK | + RXON_FILTER_PROMISC_MSK | + RXON_FILTER_CTL2HOST_MSK; + ctx->staging.dev_type = RXON_DEV_TYPE_P2P; + new_assoc = true; + + if (memcmp(&ctx->staging, &ctx->active, + sizeof(ctx->staging)) == 0) + return 0; + } + if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) || !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK)) ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK; @@ -288,10 +316,9 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) * If we issue a new RXON command which required a tune then we must * send a new TXPOWER command or we won't be able to Tx any frames. * - * FIXME: which RXON requires a tune? Can we optimise this out in - * some cases? + * It's expected we set power here if channel is changing. */ - ret = iwl_set_tx_power(priv, priv->tx_power_user_lmt, true); + ret = iwl_set_tx_power(priv, priv->tx_power_next, true); if (ret) { IWL_ERR(priv, "Error sending TX power (%d)\n", ret); return ret; @@ -546,12 +573,10 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw, if (changes & BSS_CHANGED_ASSOC) { if (bss_conf->assoc) { - iwl_led_associate(priv); priv->timestamp = bss_conf->timestamp; ctx->staging.filter_flags |= RXON_FILTER_ASSOC_MSK; } else { ctx->staging.filter_flags &= ~RXON_FILTER_ASSOC_MSK; - iwl_led_disassociate(priv); } } diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c index 24a11b8..266490d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c @@ -539,7 +539,14 @@ int iwlagn_tx_skb(struct iwl_priv *priv, struct sk_buff *skb) unsigned long flags; bool is_agg = false; - if (info->control.vif) + /* + * If the frame needs to go out off-channel, then + * we'll have put the PAN context to that channel, + * so make the frame go out there. + */ + if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) + ctx = &priv->contexts[IWL_RXON_CTX_PAN]; + else if (info->control.vif) ctx = iwl_rxon_ctx_from_vif(info->control.vif); spin_lock_irqsave(&priv->lock, flags); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c b/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c index 24dabcd..d807e5e 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-ucode.c @@ -308,14 +308,6 @@ void iwlagn_init_alive_start(struct iwl_priv *priv) { int ret = 0; - /* Check alive response for "valid" sign from uCode */ - if (priv->card_alive_init.is_valid != UCODE_VALID_OK) { - /* We had an error bringing up the hardware, so take it - * all the way back down so we can try again */ - IWL_DEBUG_INFO(priv, "Initialize Alive failed.\n"); - goto restart; - } - /* initialize uCode was loaded... verify inst image. * This is a paranoid check, because we would not have gotten the * "initialize" alive if code weren't properly loaded. */ diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index c1cfd99..8ee810f 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -59,6 +59,7 @@ #include "iwl-sta.h" #include "iwl-agn-calib.h" #include "iwl-agn.h" +#include "iwl-agn-led.h" /****************************************************************************** @@ -461,8 +462,12 @@ static void iwl_rx_reply_alive(struct iwl_priv *priv, if (palive->is_valid == UCODE_VALID_OK) queue_delayed_work(priv->workqueue, pwork, msecs_to_jiffies(5)); - else - IWL_WARN(priv, "uCode did not respond OK.\n"); + else { + IWL_WARN(priv, "%s uCode did not respond OK.\n", + (palive->ver_subtype == INITIALIZE_SUBTYPE) ? + "init" : "runtime"); + queue_work(priv->workqueue, &priv->restart); + } } static void iwl_bg_beacon_update(struct work_struct *work) @@ -699,18 +704,18 @@ static void iwl_bg_ucode_trace(unsigned long data) } } -static void iwl_rx_beacon_notif(struct iwl_priv *priv, - struct iwl_rx_mem_buffer *rxb) +static void iwlagn_rx_beacon_notif(struct iwl_priv *priv, + struct iwl_rx_mem_buffer *rxb) { struct iwl_rx_packet *pkt = rxb_addr(rxb); - struct iwl4965_beacon_notif *beacon = - (struct iwl4965_beacon_notif *)pkt->u.raw; + struct iwlagn_beacon_notif *beacon = (void *)pkt->u.raw; #ifdef CONFIG_IWLWIFI_DEBUG + u16 status = le16_to_cpu(beacon->beacon_notify_hdr.status.status); u8 rate = iwl_hw_get_rate(beacon->beacon_notify_hdr.rate_n_flags); - IWL_DEBUG_RX(priv, "beacon status %x retries %d iss %d " - "tsf %d %d rate %d\n", - le32_to_cpu(beacon->beacon_notify_hdr.u.status) & TX_STATUS_MSK, + IWL_DEBUG_RX(priv, "beacon status %#x, retries:%d ibssmgr:%d " + "tsf:0x%.8x%.8x rate:%d\n", + status & TX_STATUS_MSK, beacon->beacon_notify_hdr.failure_frame, le32_to_cpu(beacon->ibss_mgr_status), le32_to_cpu(beacon->high_tsf), @@ -813,7 +818,7 @@ static void iwl_setup_rx_handlers(struct iwl_priv *priv) priv->rx_handlers[PM_SLEEP_NOTIFICATION] = iwl_rx_pm_sleep_notif; priv->rx_handlers[PM_DEBUG_STATISTIC_NOTIFIC] = iwl_rx_pm_debug_statistics_notif; - priv->rx_handlers[BEACON_NOTIFICATION] = iwl_rx_beacon_notif; + priv->rx_handlers[BEACON_NOTIFICATION] = iwlagn_rx_beacon_notif; /* * The same handler is used for both the REPLY to a discrete @@ -846,7 +851,7 @@ static void iwl_setup_rx_handlers(struct iwl_priv *priv) * the appropriate handlers, including command responses, * frame-received notifications, and other notifications. */ -void iwl_rx_handle(struct iwl_priv *priv) +static void iwl_rx_handle(struct iwl_priv *priv) { struct iwl_rx_mem_buffer *rxb; struct iwl_rx_packet *pkt; @@ -910,6 +915,27 @@ void iwl_rx_handle(struct iwl_priv *priv) (pkt->hdr.cmd != STATISTICS_NOTIFICATION) && (pkt->hdr.cmd != REPLY_TX); + /* + * Do the notification wait before RX handlers so + * even if the RX handler consumes the RXB we have + * access to it in the notification wait entry. + */ + if (!list_empty(&priv->_agn.notif_waits)) { + struct iwl_notification_wait *w; + + spin_lock(&priv->_agn.notif_wait_lock); + list_for_each_entry(w, &priv->_agn.notif_waits, list) { + if (w->cmd == pkt->hdr.cmd) { + w->triggered = true; + if (w->fn) + w->fn(priv, pkt); + } + } + spin_unlock(&priv->_agn.notif_wait_lock); + + wake_up_all(&priv->_agn.notif_waitq); + } + /* Based on type of command response or notification, * handle those that need handling via function in * rx_handlers table. See iwl_setup_rx_handlers() */ @@ -2632,13 +2658,6 @@ static void iwl_alive_start(struct iwl_priv *priv) IWL_DEBUG_INFO(priv, "Runtime Alive received.\n"); - if (priv->card_alive.is_valid != UCODE_VALID_OK) { - /* We had an error bringing up the hardware, so take it - * all the way back down so we can try again */ - IWL_DEBUG_INFO(priv, "Alive failed.\n"); - goto restart; - } - /* Initialize uCode has loaded Runtime uCode ... verify inst image. * This is a paranoid check, because we would not have gotten the * "runtime" alive if code weren't properly loaded. */ @@ -2726,8 +2745,6 @@ static void iwl_alive_start(struct iwl_priv *priv) /* At this point, the NIC is initialized and operational */ iwl_rf_kill_ct_config(priv); - iwl_leds_init(priv); - IWL_DEBUG_INFO(priv, "ALIVE processing complete.\n"); wake_up_interruptible(&priv->wait_command_queue); @@ -2769,7 +2786,6 @@ static void __iwl_down(struct iwl_priv *priv) priv->cfg->bt_params->bt_init_traffic_load; else priv->bt_traffic_load = 0; - priv->bt_sco_active = false; priv->bt_full_concurrent = false; priv->bt_ci_compliance = 0; @@ -3063,8 +3079,7 @@ static void iwl_bg_run_time_calib_work(struct work_struct *work) } if (priv->start_calib) { - if (priv->cfg->bt_params && - priv->cfg->bt_params->bt_statistics) { + if (iwl_bt_statistics(priv)) { iwl_chain_noise_calibration(priv, (void *)&priv->_agn.statistics_bt); iwl_sensitivity_calibration(priv, @@ -3089,7 +3104,7 @@ static void iwl_bg_restart(struct work_struct *data) if (test_and_clear_bit(STATUS_FW_ERROR, &priv->status)) { struct iwl_rxon_context *ctx; - bool bt_sco, bt_full_concurrent; + bool bt_full_concurrent; u8 bt_ci_compliance; u8 bt_load; u8 bt_status; @@ -3108,7 +3123,6 @@ static void iwl_bg_restart(struct work_struct *data) * re-configure the hw when we reconfigure the BT * command. */ - bt_sco = priv->bt_sco_active; bt_full_concurrent = priv->bt_full_concurrent; bt_ci_compliance = priv->bt_ci_compliance; bt_load = priv->bt_traffic_load; @@ -3116,7 +3130,6 @@ static void iwl_bg_restart(struct work_struct *data) __iwl_down(priv); - priv->bt_sco_active = bt_sco; priv->bt_full_concurrent = bt_full_concurrent; priv->bt_ci_compliance = bt_ci_compliance; priv->bt_traffic_load = bt_load; @@ -3178,6 +3191,8 @@ static int iwl_mac_setup_register(struct iwl_priv *priv, IEEE80211_HW_SPECTRUM_MGMT | IEEE80211_HW_REPORTS_TX_ACK_STATUS; + hw->max_tx_aggregation_subframes = LINK_QUAL_AGG_FRAME_LIMIT_DEF; + if (!priv->cfg->base_params->broken_powersave) hw->flags |= IEEE80211_HW_SUPPORTS_PS | IEEE80211_HW_SUPPORTS_DYNAMIC_PS; @@ -3194,8 +3209,11 @@ static int iwl_mac_setup_register(struct iwl_priv *priv, hw->wiphy->interface_modes |= ctx->exclusive_interface_modes; } + hw->wiphy->max_remain_on_channel_duration = 1000; + hw->wiphy->flags |= WIPHY_FLAG_CUSTOM_REGULATORY | - WIPHY_FLAG_DISABLE_BEACON_HINTS; + WIPHY_FLAG_DISABLE_BEACON_HINTS | + WIPHY_FLAG_IBSS_RSN; /* * For now, disable PS by default because it affects @@ -3219,6 +3237,8 @@ static int iwl_mac_setup_register(struct iwl_priv *priv, priv->hw->wiphy->bands[IEEE80211_BAND_5GHZ] = &priv->bands[IEEE80211_BAND_5GHZ]; + iwl_leds_init(priv); + ret = ieee80211_register_hw(priv->hw); if (ret) { IWL_ERR(priv, "Failed to register hw (error %d)\n", ret); @@ -3263,7 +3283,7 @@ int iwlagn_mac_start(struct ieee80211_hw *hw) } } - iwl_led_start(priv); + iwlagn_led_enable(priv); out: priv->is_open = 1; @@ -3345,6 +3365,14 @@ int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, return -EOPNOTSUPP; } + /* + * To support IBSS RSN, don't program group keys in IBSS, the + * hardware will then not attempt to decrypt the frames. + */ + if (vif->type == NL80211_IFTYPE_ADHOC && + !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) + return -EOPNOTSUPP; + sta_id = iwl_sta_id_or_broadcast(priv, vif_priv->ctx, sta); if (sta_id == IWL_INVALID_STATION) return -EINVAL; @@ -3399,10 +3427,12 @@ int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { struct iwl_priv *priv = hw->priv; int ret = -EINVAL; + struct iwl_station_priv *sta_priv = (void *) sta->drv_priv; IWL_DEBUG_HT(priv, "A-MPDU action on addr %pM tid %d\n", sta->addr, tid); @@ -3457,11 +3487,28 @@ int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, } break; case IEEE80211_AMPDU_TX_OPERATIONAL: + /* + * If the limit is 0, then it wasn't initialised yet, + * use the default. We can do that since we take the + * minimum below, and we don't want to go above our + * default due to hardware restrictions. + */ + if (sta_priv->max_agg_bufsize == 0) + sta_priv->max_agg_bufsize = + LINK_QUAL_AGG_FRAME_LIMIT_DEF; + + /* + * Even though in theory the peer could have different + * aggregation reorder buffer sizes for different sessions, + * our ucode doesn't allow for that and has a global limit + * for each station. Therefore, use the minimum of all the + * aggregation sessions and our default value. + */ + sta_priv->max_agg_bufsize = + min(sta_priv->max_agg_bufsize, buf_size); + if (priv->cfg->ht_params && priv->cfg->ht_params->use_rts_for_aggregation) { - struct iwl_station_priv *sta_priv = - (void *) sta->drv_priv; - /* * switch to RTS/CTS if it is the prefer protection * method for HT traffic @@ -3469,9 +3516,13 @@ int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, sta_priv->lq_sta.lq.general_params.flags |= LINK_QUAL_FLAGS_SET_STA_TLC_RTS_MSK; - iwl_send_lq_cmd(priv, iwl_rxon_ctx_from_vif(vif), - &sta_priv->lq_sta.lq, CMD_ASYNC, false); } + + sta_priv->lq_sta.lq.agg_params.agg_frame_cnt_limit = + sta_priv->max_agg_bufsize; + + iwl_send_lq_cmd(priv, iwl_rxon_ctx_from_vif(vif), + &sta_priv->lq_sta.lq, CMD_ASYNC, false); ret = 0; break; } @@ -3709,6 +3760,97 @@ done: IWL_DEBUG_MAC80211(priv, "leave\n"); } +static void iwlagn_disable_roc(struct iwl_priv *priv) +{ + struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_PAN]; + struct ieee80211_channel *chan = ACCESS_ONCE(priv->hw->conf.channel); + + lockdep_assert_held(&priv->mutex); + + if (!ctx->is_active) + return; + + ctx->staging.dev_type = RXON_DEV_TYPE_2STA; + ctx->staging.filter_flags &= ~RXON_FILTER_ASSOC_MSK; + iwl_set_rxon_channel(priv, chan, ctx); + iwl_set_flags_for_band(priv, ctx, chan->band, NULL); + + priv->_agn.hw_roc_channel = NULL; + + iwlcore_commit_rxon(priv, ctx); + + ctx->is_active = false; +} + +static void iwlagn_bg_roc_done(struct work_struct *work) +{ + struct iwl_priv *priv = container_of(work, struct iwl_priv, + _agn.hw_roc_work.work); + + mutex_lock(&priv->mutex); + ieee80211_remain_on_channel_expired(priv->hw); + iwlagn_disable_roc(priv); + mutex_unlock(&priv->mutex); +} + +#ifdef CONFIG_IWL5000 +static int iwl_mac_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_channel *channel, + enum nl80211_channel_type channel_type, + int duration) +{ + struct iwl_priv *priv = hw->priv; + int err = 0; + + if (!(priv->valid_contexts & BIT(IWL_RXON_CTX_PAN))) + return -EOPNOTSUPP; + + if (!(priv->contexts[IWL_RXON_CTX_PAN].interface_modes & + BIT(NL80211_IFTYPE_P2P_CLIENT))) + return -EOPNOTSUPP; + + mutex_lock(&priv->mutex); + + if (priv->contexts[IWL_RXON_CTX_PAN].is_active || + test_bit(STATUS_SCAN_HW, &priv->status)) { + err = -EBUSY; + goto out; + } + + priv->contexts[IWL_RXON_CTX_PAN].is_active = true; + priv->_agn.hw_roc_channel = channel; + priv->_agn.hw_roc_chantype = channel_type; + priv->_agn.hw_roc_duration = DIV_ROUND_UP(duration * 1000, 1024); + iwlcore_commit_rxon(priv, &priv->contexts[IWL_RXON_CTX_PAN]); + queue_delayed_work(priv->workqueue, &priv->_agn.hw_roc_work, + msecs_to_jiffies(duration + 20)); + + msleep(IWL_MIN_SLOT_TIME); /* TU is almost ms */ + ieee80211_ready_on_channel(priv->hw); + + out: + mutex_unlock(&priv->mutex); + + return err; +} + +static int iwl_mac_cancel_remain_on_channel(struct ieee80211_hw *hw) +{ + struct iwl_priv *priv = hw->priv; + + if (!(priv->valid_contexts & BIT(IWL_RXON_CTX_PAN))) + return -EOPNOTSUPP; + + cancel_delayed_work_sync(&priv->_agn.hw_roc_work); + + mutex_lock(&priv->mutex); + iwlagn_disable_roc(priv); + mutex_unlock(&priv->mutex); + + return 0; +} +#endif + /***************************************************************************** * * driver setup and teardown @@ -3730,6 +3872,7 @@ static void iwl_setup_deferred_work(struct iwl_priv *priv) INIT_WORK(&priv->bt_runtime_config, iwl_bg_bt_runtime_config); INIT_DELAYED_WORK(&priv->init_alive_start, iwl_bg_init_alive_start); INIT_DELAYED_WORK(&priv->alive_start, iwl_bg_alive_start); + INIT_DELAYED_WORK(&priv->_agn.hw_roc_work, iwlagn_bg_roc_done); iwl_setup_scan_deferred_work(priv); @@ -3898,6 +4041,8 @@ struct ieee80211_ops iwlagn_hw_ops = { .channel_switch = iwlagn_mac_channel_switch, .flush = iwlagn_mac_flush, .tx_last_beacon = iwl_mac_tx_last_beacon, + .remain_on_channel = iwl_mac_remain_on_channel, + .cancel_remain_on_channel = iwl_mac_cancel_remain_on_channel, }; #endif @@ -4025,6 +4170,10 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) priv->contexts[IWL_RXON_CTX_PAN].mcast_queue = IWL_IPAN_MCAST_QUEUE; priv->contexts[IWL_RXON_CTX_PAN].interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP); +#ifdef CONFIG_IWL_P2P + priv->contexts[IWL_RXON_CTX_PAN].interface_modes |= + BIT(NL80211_IFTYPE_P2P_CLIENT) | BIT(NL80211_IFTYPE_P2P_GO); +#endif priv->contexts[IWL_RXON_CTX_PAN].ap_devtype = RXON_DEV_TYPE_CP; priv->contexts[IWL_RXON_CTX_PAN].station_devtype = RXON_DEV_TYPE_2STA; priv->contexts[IWL_RXON_CTX_PAN].unused_devtype = RXON_DEV_TYPE_P2P; @@ -4272,6 +4421,9 @@ static void __devexit iwl_pci_remove(struct pci_dev *pdev) * we need to set STATUS_EXIT_PENDING bit. */ set_bit(STATUS_EXIT_PENDING, &priv->status); + + iwl_leds_exit(priv); + if (priv->mac80211_registered) { ieee80211_unregister_hw(priv->hw); priv->mac80211_registered = 0; @@ -4492,6 +4644,49 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x0896, 0x5025, iwl130_bgn_cfg)}, {IWL_PCI_DEVICE(0x0896, 0x5027, iwl130_bg_cfg)}, +/* 2x00 Series */ + {IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0891, 0x4222, iwl2000_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0890, 0x4422, iwl2000_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0890, 0x4026, iwl2000_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0891, 0x4226, iwl2000_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0890, 0x4426, iwl2000_2bg_cfg)}, + +/* 2x30 Series */ + {IWL_PCI_DEVICE(0x0887, 0x4062, iwl2030_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0888, 0x4262, iwl2030_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0887, 0x4462, iwl2030_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0887, 0x4066, iwl2030_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0888, 0x4266, iwl2030_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0887, 0x4466, iwl2030_2bg_cfg)}, + +/* 6x35 Series */ + {IWL_PCI_DEVICE(0x088E, 0x4060, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x4260, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4460, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4064, iwl6035_2abg_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x4264, iwl6035_2abg_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4464, iwl6035_2abg_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4066, iwl6035_2bg_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x4266, iwl6035_2bg_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4466, iwl6035_2bg_cfg)}, + +/* 200 Series */ + {IWL_PCI_DEVICE(0x0894, 0x0022, iwl200_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0895, 0x0222, iwl200_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0894, 0x0422, iwl200_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0894, 0x0026, iwl200_bg_cfg)}, + {IWL_PCI_DEVICE(0x0895, 0x0226, iwl200_bg_cfg)}, + {IWL_PCI_DEVICE(0x0894, 0x0426, iwl200_bg_cfg)}, + +/* 230 Series */ + {IWL_PCI_DEVICE(0x0892, 0x0062, iwl230_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0893, 0x0262, iwl230_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0892, 0x0462, iwl230_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0892, 0x0066, iwl230_bg_cfg)}, + {IWL_PCI_DEVICE(0x0893, 0x0266, iwl230_bg_cfg)}, + {IWL_PCI_DEVICE(0x0892, 0x0466, iwl230_bg_cfg)}, + #endif /* CONFIG_IWL5000 */ {0} diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h index da30358..d00e1ea 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.h +++ b/drivers/net/wireless/iwlwifi/iwl-agn.h @@ -96,6 +96,17 @@ extern struct iwl_cfg iwl100_bgn_cfg; extern struct iwl_cfg iwl100_bg_cfg; extern struct iwl_cfg iwl130_bgn_cfg; extern struct iwl_cfg iwl130_bg_cfg; +extern struct iwl_cfg iwl2000_2bgn_cfg; +extern struct iwl_cfg iwl2000_2bg_cfg; +extern struct iwl_cfg iwl2030_2bgn_cfg; +extern struct iwl_cfg iwl2030_2bg_cfg; +extern struct iwl_cfg iwl6035_2agn_cfg; +extern struct iwl_cfg iwl6035_2abg_cfg; +extern struct iwl_cfg iwl6035_2bg_cfg; +extern struct iwl_cfg iwl200_bg_cfg; +extern struct iwl_cfg iwl200_bgn_cfg; +extern struct iwl_cfg iwl230_bg_cfg; +extern struct iwl_cfg iwl230_bgn_cfg; extern struct iwl_mod_params iwlagn_mod_params; extern struct iwl_hcmd_ops iwlagn_hcmd; @@ -185,7 +196,6 @@ void iwlagn_rx_reply_rx(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb); void iwlagn_rx_reply_rx_phy(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb); -void iwl_rx_handle(struct iwl_priv *priv); /* tx */ void iwl_hw_txq_free_tfd(struct iwl_priv *priv, struct iwl_tx_queue *txq); @@ -330,6 +340,21 @@ void iwl_eeprom_get_mac(const struct iwl_priv *priv, u8 *mac); int iwlcore_eeprom_acquire_semaphore(struct iwl_priv *priv); void iwlcore_eeprom_release_semaphore(struct iwl_priv *priv); +/* notification wait support */ +void __acquires(wait_entry) +iwlagn_init_notification_wait(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + void (*fn)(struct iwl_priv *priv, + struct iwl_rx_packet *pkt), + u8 cmd); +signed long __releases(wait_entry) +iwlagn_wait_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + unsigned long timeout); +void __releases(wait_entry) +iwlagn_remove_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry); + /* mac80211 handlers (for 4965) */ int iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb); int iwlagn_mac_start(struct ieee80211_hw *hw); @@ -349,7 +374,8 @@ void iwlagn_mac_update_tkip_key(struct ieee80211_hw *hw, int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int iwlagn_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); diff --git a/drivers/net/wireless/iwlwifi/iwl-commands.h b/drivers/net/wireless/iwlwifi/iwl-commands.h index f893d4a..0a1d4ae 100644 --- a/drivers/net/wireless/iwlwifi/iwl-commands.h +++ b/drivers/net/wireless/iwlwifi/iwl-commands.h @@ -178,7 +178,6 @@ enum { REPLY_BT_COEX_PRIO_TABLE = 0xcc, REPLY_BT_COEX_PROT_ENV = 0xcd, REPLY_BT_COEX_PROFILE_NOTIF = 0xce, - REPLY_BT_COEX_SCO = 0xcf, /* PAN commands */ REPLY_WIPAN_PARAMS = 0xb2, @@ -189,6 +188,7 @@ enum { REPLY_WIPAN_WEPKEY = 0xb8, /* use REPLY_WEPKEY structure */ REPLY_WIPAN_P2P_CHANNEL_SWITCH = 0xb9, REPLY_WIPAN_NOA_NOTIFICATION = 0xbc, + REPLY_WIPAN_DEACTIVATION_COMPLETE = 0xbd, REPLY_MAX = 0xff }; @@ -3082,6 +3082,13 @@ struct iwl4965_beacon_notif { __le32 ibss_mgr_status; } __packed; +struct iwlagn_beacon_notif { + struct iwlagn_tx_resp beacon_notify_hdr; + __le32 low_tsf; + __le32 high_tsf; + __le32 ibss_mgr_status; +} __packed; + /* * REPLY_TX_BEACON = 0x91 (command, has simple generic response) */ @@ -4369,6 +4376,11 @@ int iwl_agn_check_rxon_cmd(struct iwl_priv *priv); * REPLY_WIPAN_PARAMS = 0xb2 (Commands and Notification) */ +/* + * Minimum slot time in TU + */ +#define IWL_MIN_SLOT_TIME 20 + /** * struct iwl_wipan_slot * @width: Time in TU diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index efbde1f..4ad8938 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -219,15 +219,12 @@ int iwlcore_init_geos(struct iwl_priv *priv) if (!is_channel_valid(ch)) continue; - if (is_channel_a_band(ch)) - sband = &priv->bands[IEEE80211_BAND_5GHZ]; - else - sband = &priv->bands[IEEE80211_BAND_2GHZ]; + sband = &priv->bands[ch->band]; geo_ch = &sband->channels[sband->n_channels++]; geo_ch->center_freq = - ieee80211_channel_to_frequency(ch->channel); + ieee80211_channel_to_frequency(ch->channel, ch->band); geo_ch->max_power = ch->max_power_avg; geo_ch->max_antenna_gain = 0xff; geo_ch->hw_value = ch->channel; @@ -1161,6 +1158,8 @@ int iwl_set_tx_power(struct iwl_priv *priv, s8 tx_power, bool force) { int ret; s8 prev_tx_power; + bool defer; + struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS]; lockdep_assert_held(&priv->mutex); @@ -1188,10 +1187,15 @@ int iwl_set_tx_power(struct iwl_priv *priv, s8 tx_power, bool force) if (!iwl_is_ready_rf(priv)) return -EIO; - /* scan complete use tx_power_next, need to be updated */ + /* scan complete and commit_rxon use tx_power_next value, + * it always need to be updated for newest request */ priv->tx_power_next = tx_power; - if (test_bit(STATUS_SCANNING, &priv->status) && !force) { - IWL_DEBUG_INFO(priv, "Deferring tx power set while scanning\n"); + + /* do not set tx power when scanning or channel changing */ + defer = test_bit(STATUS_SCANNING, &priv->status) || + memcmp(&ctx->active, &ctx->staging, sizeof(ctx->staging)); + if (defer && !force) { + IWL_DEBUG_INFO(priv, "Deferring tx power set\n"); return 0; } @@ -1403,9 +1407,10 @@ int iwl_mac_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) struct iwl_vif_priv *vif_priv = (void *)vif->drv_priv; struct iwl_rxon_context *tmp, *ctx = NULL; int err; + enum nl80211_iftype viftype = ieee80211_vif_type_p2p(vif); IWL_DEBUG_MAC80211(priv, "enter: type %d, addr %pM\n", - vif->type, vif->addr); + viftype, vif->addr); mutex_lock(&priv->mutex); @@ -1429,7 +1434,7 @@ int iwl_mac_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) continue; } - if (!(possible_modes & BIT(vif->type))) + if (!(possible_modes & BIT(viftype))) continue; /* have maybe usable context w/o interface */ @@ -1675,7 +1680,6 @@ void iwl_clear_traffic_stats(struct iwl_priv *priv) { memset(&priv->tx_stats, 0, sizeof(struct traffic_stats)); memset(&priv->rx_stats, 0, sizeof(struct traffic_stats)); - priv->led_tpt = 0; } /* @@ -1768,7 +1772,6 @@ void iwl_update_stats(struct iwl_priv *priv, bool is_tx, __le16 fc, u16 len) stats->data_cnt++; stats->data_bytes += len; } - iwl_leds_background(priv); } EXPORT_SYMBOL(iwl_update_stats); #endif diff --git a/drivers/net/wireless/iwlwifi/iwl-core.h b/drivers/net/wireless/iwlwifi/iwl-core.h index a347437..e0ec170 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.h +++ b/drivers/net/wireless/iwlwifi/iwl-core.h @@ -227,8 +227,6 @@ struct iwl_lib_ops { struct iwl_led_ops { int (*cmd)(struct iwl_priv *priv, struct iwl_led_cmd *led_cmd); - int (*on)(struct iwl_priv *priv); - int (*off)(struct iwl_priv *priv); }; /* NIC specific ops */ @@ -307,7 +305,6 @@ struct iwl_base_params { u16 led_compensation; const bool broken_powersave; int chain_noise_num_beacons; - const bool supports_idle; bool adv_thermal_throttle; bool support_ct_kill_exit; const bool support_wimax_coexist; @@ -366,6 +363,7 @@ struct iwl_ht_params { * @adv_pm: advance power management * @rx_with_siso_diversity: 1x1 device with rx antenna diversity * @internal_wimax_coex: internal wifi/wimax combo device + * @iq_invert: I/Q inversion * * We enable the driver to be backward compatible wrt API version. The * driver specifies which APIs it supports (with @ucode_api_max being the @@ -415,6 +413,7 @@ struct iwl_cfg { const bool adv_pm; const bool rx_with_siso_diversity; const bool internal_wimax_coex; + const bool iq_invert; }; /*************************** @@ -494,18 +493,6 @@ static inline void iwl_dbg_log_rx_data_frame(struct iwl_priv *priv, static inline void iwl_update_stats(struct iwl_priv *priv, bool is_tx, __le16 fc, u16 len) { - struct traffic_stats *stats; - - if (is_tx) - stats = &priv->tx_stats; - else - stats = &priv->rx_stats; - - if (ieee80211_is_data(fc)) { - /* data */ - stats->data_bytes += len; - } - iwl_leds_background(priv); } #endif /***************************************************** @@ -755,6 +742,17 @@ static inline const struct ieee80211_supported_band *iwl_get_hw_mode( return priv->hw->wiphy->bands[band]; } +static inline bool iwl_advanced_bt_coexist(struct iwl_priv *priv) +{ + return priv->cfg->bt_params && + priv->cfg->bt_params->advanced_bt_coexist; +} + +static inline bool iwl_bt_statistics(struct iwl_priv *priv) +{ + return priv->cfg->bt_params && priv->cfg->bt_params->bt_statistics; +} + extern bool bt_coex_active; extern bool bt_siso_mode; diff --git a/drivers/net/wireless/iwlwifi/iwl-csr.h b/drivers/net/wireless/iwlwifi/iwl-csr.h index b80bf7d..f52bc04 100644 --- a/drivers/net/wireless/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/iwlwifi/iwl-csr.h @@ -290,7 +290,7 @@ /* HW REV */ -#define CSR_HW_REV_TYPE_MSK (0x00000F0) +#define CSR_HW_REV_TYPE_MSK (0x00001F0) #define CSR_HW_REV_TYPE_3945 (0x00000D0) #define CSR_HW_REV_TYPE_4965 (0x0000000) #define CSR_HW_REV_TYPE_5300 (0x0000020) @@ -300,9 +300,15 @@ #define CSR_HW_REV_TYPE_1000 (0x0000060) #define CSR_HW_REV_TYPE_6x00 (0x0000070) #define CSR_HW_REV_TYPE_6x50 (0x0000080) -#define CSR_HW_REV_TYPE_6x50g2 (0x0000084) -#define CSR_HW_REV_TYPE_6x00g2 (0x00000B0) -#define CSR_HW_REV_TYPE_NONE (0x00000F0) +#define CSR_HW_REV_TYPE_6150 (0x0000084) +#define CSR_HW_REV_TYPE_6x05 (0x00000B0) +#define CSR_HW_REV_TYPE_6x30 CSR_HW_REV_TYPE_6x05 +#define CSR_HW_REV_TYPE_6x35 CSR_HW_REV_TYPE_6x05 +#define CSR_HW_REV_TYPE_2x30 (0x00000C0) +#define CSR_HW_REV_TYPE_2x00 (0x0000100) +#define CSR_HW_REV_TYPE_200 (0x0000110) +#define CSR_HW_REV_TYPE_230 (0x0000120) +#define CSR_HW_REV_TYPE_NONE (0x00001F0) /* EEPROM REG */ #define CSR_EEPROM_REG_READ_VALID_MSK (0x00000001) @@ -376,6 +382,8 @@ #define CSR_GP_DRIVER_REG_BIT_CALIB_VERSION6 (0x00000004) #define CSR_GP_DRIVER_REG_BIT_6050_1x2 (0x00000008) +#define CSR_GP_DRIVER_REG_BIT_RADIO_IQ_INVER (0x00000080) + /* GIO Chicken Bits (PCI Express bus link power management) */ #define CSR_GIO_CHICKEN_BITS_REG_BIT_L1A_NO_L0S_RX (0x00800000) #define CSR_GIO_CHICKEN_BITS_REG_BIT_DIS_L0S_EXIT_TIMER (0x20000000) diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c index 6fe80b5..bc7a965 100644 --- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c +++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c @@ -207,18 +207,19 @@ static ssize_t iwl_dbgfs_rx_statistics_read(struct file *file, return ret; } -#define BYTE1_MASK 0x000000ff; -#define BYTE2_MASK 0x0000ffff; -#define BYTE3_MASK 0x00ffffff; static ssize_t iwl_dbgfs_sram_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { - u32 val; + u32 val = 0; char *buf; ssize_t ret; - int i; + int i = 0; + bool device_format = false; + int offset = 0; + int len = 0; int pos = 0; + int sram; struct iwl_priv *priv = file->private_data; size_t bufsz; @@ -230,35 +231,62 @@ static ssize_t iwl_dbgfs_sram_read(struct file *file, else priv->dbgfs_sram_len = priv->ucode_data.len; } - bufsz = 30 + priv->dbgfs_sram_len * sizeof(char) * 10; + len = priv->dbgfs_sram_len; + + if (len == -4) { + device_format = true; + len = 4; + } + + bufsz = 50 + len * 4; buf = kmalloc(bufsz, GFP_KERNEL); if (!buf) return -ENOMEM; + pos += scnprintf(buf + pos, bufsz - pos, "sram_len: 0x%x\n", - priv->dbgfs_sram_len); + len); pos += scnprintf(buf + pos, bufsz - pos, "sram_offset: 0x%x\n", priv->dbgfs_sram_offset); - for (i = priv->dbgfs_sram_len; i > 0; i -= 4) { - val = iwl_read_targ_mem(priv, priv->dbgfs_sram_offset + \ - priv->dbgfs_sram_len - i); - if (i < 4) { - switch (i) { - case 1: - val &= BYTE1_MASK; - break; - case 2: - val &= BYTE2_MASK; - break; - case 3: - val &= BYTE3_MASK; - break; - } + + /* adjust sram address since reads are only on even u32 boundaries */ + offset = priv->dbgfs_sram_offset & 0x3; + sram = priv->dbgfs_sram_offset & ~0x3; + + /* read the first u32 from sram */ + val = iwl_read_targ_mem(priv, sram); + + for (; len; len--) { + /* put the address at the start of every line */ + if (i == 0) + pos += scnprintf(buf + pos, bufsz - pos, + "%08X: ", sram + offset); + + if (device_format) + pos += scnprintf(buf + pos, bufsz - pos, + "%02x", (val >> (8 * (3 - offset))) & 0xff); + else + pos += scnprintf(buf + pos, bufsz - pos, + "%02x ", (val >> (8 * offset)) & 0xff); + + /* if all bytes processed, read the next u32 from sram */ + if (++offset == 4) { + sram += 4; + offset = 0; + val = iwl_read_targ_mem(priv, sram); } - if (!(i % 16)) + + /* put in extra spaces and split lines for human readability */ + if (++i == 16) { + i = 0; pos += scnprintf(buf + pos, bufsz - pos, "\n"); - pos += scnprintf(buf + pos, bufsz - pos, "0x%08x ", val); + } else if (!(i & 7)) { + pos += scnprintf(buf + pos, bufsz - pos, " "); + } else if (!(i & 3)) { + pos += scnprintf(buf + pos, bufsz - pos, " "); + } } - pos += scnprintf(buf + pos, bufsz - pos, "\n"); + if (i) + pos += scnprintf(buf + pos, bufsz - pos, "\n"); ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos); kfree(buf); @@ -282,6 +310,9 @@ static ssize_t iwl_dbgfs_sram_write(struct file *file, if (sscanf(buf, "%x,%x", &offset, &len) == 2) { priv->dbgfs_sram_offset = offset; priv->dbgfs_sram_len = len; + } else if (sscanf(buf, "%x", &offset) == 1) { + priv->dbgfs_sram_offset = offset; + priv->dbgfs_sram_len = -4; } else { priv->dbgfs_sram_offset = 0; priv->dbgfs_sram_len = 0; @@ -668,29 +699,6 @@ static ssize_t iwl_dbgfs_qos_read(struct file *file, char __user *user_buf, return simple_read_from_buffer(user_buf, count, ppos, buf, pos); } -static ssize_t iwl_dbgfs_led_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct iwl_priv *priv = file->private_data; - int pos = 0; - char buf[256]; - const size_t bufsz = sizeof(buf); - - pos += scnprintf(buf + pos, bufsz - pos, - "allow blinking: %s\n", - (priv->allow_blinking) ? "True" : "False"); - if (priv->allow_blinking) { - pos += scnprintf(buf + pos, bufsz - pos, - "Led blinking rate: %u\n", - priv->last_blink_rate); - pos += scnprintf(buf + pos, bufsz - pos, - "Last blink time: %lu\n", - priv->last_blink_time); - } - - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - static ssize_t iwl_dbgfs_thermal_throttling_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -856,7 +864,6 @@ DEBUGFS_READ_FILE_OPS(channels); DEBUGFS_READ_FILE_OPS(status); DEBUGFS_READ_WRITE_FILE_OPS(interrupt); DEBUGFS_READ_FILE_OPS(qos); -DEBUGFS_READ_FILE_OPS(led); DEBUGFS_READ_FILE_OPS(thermal_throttling); DEBUGFS_READ_WRITE_FILE_OPS(disable_ht40); DEBUGFS_READ_WRITE_FILE_OPS(sleep_level_override); @@ -1580,10 +1587,9 @@ static ssize_t iwl_dbgfs_bt_traffic_read(struct file *file, "last traffic notif: %d\n", priv->bt_status ? "On" : "Off", priv->last_bt_traffic_load); pos += scnprintf(buf + pos, bufsz - pos, "ch_announcement: %d, " - "sco_active: %d, kill_ack_mask: %x, " - "kill_cts_mask: %x\n", - priv->bt_ch_announce, priv->bt_sco_active, - priv->kill_ack_mask, priv->kill_cts_mask); + "kill_ack_mask: %x, kill_cts_mask: %x\n", + priv->bt_ch_announce, priv->kill_ack_mask, + priv->kill_cts_mask); pos += scnprintf(buf + pos, bufsz - pos, "bluetooth traffic load: "); switch (priv->bt_traffic_load) { @@ -1725,7 +1731,6 @@ int iwl_dbgfs_register(struct iwl_priv *priv, const char *name) DEBUGFS_ADD_FILE(status, dir_data, S_IRUSR); DEBUGFS_ADD_FILE(interrupt, dir_data, S_IWUSR | S_IRUSR); DEBUGFS_ADD_FILE(qos, dir_data, S_IRUSR); - DEBUGFS_ADD_FILE(led, dir_data, S_IRUSR); if (!priv->cfg->base_params->broken_powersave) { DEBUGFS_ADD_FILE(sleep_level_override, dir_data, S_IWUSR | S_IRUSR); @@ -1759,13 +1764,13 @@ int iwl_dbgfs_register(struct iwl_priv *priv, const char *name) DEBUGFS_ADD_FILE(chain_noise, dir_debug, S_IRUSR); if (priv->cfg->base_params->ucode_tracing) DEBUGFS_ADD_FILE(ucode_tracing, dir_debug, S_IWUSR | S_IRUSR); - if (priv->cfg->bt_params && priv->cfg->bt_params->bt_statistics) + if (iwl_bt_statistics(priv)) DEBUGFS_ADD_FILE(ucode_bt_stats, dir_debug, S_IRUSR); DEBUGFS_ADD_FILE(reply_tx_error, dir_debug, S_IRUSR); DEBUGFS_ADD_FILE(rxon_flags, dir_debug, S_IWUSR); DEBUGFS_ADD_FILE(rxon_filter_flags, dir_debug, S_IWUSR); DEBUGFS_ADD_FILE(wd_timeout, dir_debug, S_IWUSR); - if (priv->cfg->bt_params && priv->cfg->bt_params->advanced_bt_coexist) + if (iwl_advanced_bt_coexist(priv)) DEBUGFS_ADD_FILE(bt_traffic, dir_debug, S_IRUSR); if (priv->cfg->base_params->sensitivity_calib_by_driver) DEBUGFS_ADD_BOOL(disable_sensitivity, dir_rf, diff --git a/drivers/net/wireless/iwlwifi/iwl-dev.h b/drivers/net/wireless/iwlwifi/iwl-dev.h index 8dda678..ecfbef4 100644 --- a/drivers/net/wireless/iwlwifi/iwl-dev.h +++ b/drivers/net/wireless/iwlwifi/iwl-dev.h @@ -34,6 +34,8 @@ #include <linux/pci.h> /* for struct pci_device_id */ #include <linux/kernel.h> +#include <linux/wait.h> +#include <linux/leds.h> #include <net/ieee80211_radiotap.h> #include "iwl-eeprom.h" @@ -136,7 +138,7 @@ struct iwl_queue { * space more than this */ int high_mark; /* high watermark, stop queue if free * space less than this */ -} __packed; +}; /* One for each TFD */ struct iwl_tx_info { @@ -507,6 +509,7 @@ struct iwl_station_priv { atomic_t pending_frames; bool client; bool asleep; + u8 max_agg_bufsize; }; /** @@ -995,7 +998,6 @@ struct reply_agg_tx_error_statistics { u32 unknown; }; -#ifdef CONFIG_IWLWIFI_DEBUGFS /* management statistics */ enum iwl_mgmt_stats { MANAGEMENT_ASSOC_REQ = 0, @@ -1026,16 +1028,13 @@ enum iwl_ctrl_stats { }; struct traffic_stats { +#ifdef CONFIG_IWLWIFI_DEBUGFS u32 mgmt[MANAGEMENT_MAX]; u32 ctrl[CONTROL_MAX]; u32 data_cnt; u64 data_bytes; -}; -#else -struct traffic_stats { - u64 data_bytes; -}; #endif +}; /* * iwl_switch_rxon: "channel switch" structure @@ -1139,6 +1138,33 @@ struct iwl_force_reset { */ #define IWLAGN_EXT_BEACON_TIME_POS 22 +/** + * struct iwl_notification_wait - notification wait entry + * @list: list head for global list + * @fn: function called with the notification + * @cmd: command ID + * + * This structure is not used directly, to wait for a + * notification declare it on the stack, and call + * iwlagn_init_notification_wait() with appropriate + * parameters. Then do whatever will cause the ucode + * to notify the driver, and to wait for that then + * call iwlagn_wait_notification(). + * + * Each notification is one-shot. If at some point we + * need to support multi-shot notifications (which + * can't be allocated on the stack) we need to modify + * the code for them. + */ +struct iwl_notification_wait { + struct list_head list; + + void (*fn)(struct iwl_priv *priv, struct iwl_rx_packet *pkt); + + u8 cmd; + bool triggered; +}; + enum iwl_rxon_context_id { IWL_RXON_CTX_BSS, IWL_RXON_CTX_PAN, @@ -1310,11 +1336,6 @@ struct iwl_priv { struct iwl_init_alive_resp card_alive_init; struct iwl_alive_resp card_alive; - unsigned long last_blink_time; - u8 last_blink_rate; - u8 allow_blinking; - u64 led_tpt; - u16 active_rate; u8 start_calib; @@ -1463,6 +1484,17 @@ struct iwl_priv { struct iwl_bt_notif_statistics delta_statistics_bt; struct iwl_bt_notif_statistics max_delta_bt; #endif + + /* notification wait support */ + struct list_head notif_waits; + spinlock_t notif_wait_lock; + wait_queue_head_t notif_waitq; + + /* remain-on-channel offload support */ + struct ieee80211_channel *hw_roc_channel; + struct delayed_work hw_roc_work; + enum nl80211_channel_type hw_roc_chantype; + int hw_roc_duration; } _agn; #endif }; @@ -1472,7 +1504,6 @@ struct iwl_priv { u8 bt_status; u8 bt_traffic_load, last_bt_traffic_load; bool bt_ch_announce; - bool bt_sco_active; bool bt_full_concurrent; bool bt_ant_couple_ok; __le32 kill_ack_mask; @@ -1547,6 +1578,10 @@ struct iwl_priv { bool hw_ready; struct iwl_event_log event_log; + + struct led_classdev led; + unsigned long blink_on, blink_off; + bool led_registered; }; /*iwl_priv */ static inline void iwl_txq_ctx_activate(struct iwl_priv *priv, int txq_id) diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom.h b/drivers/net/wireless/iwlwifi/iwl-eeprom.h index 9e6f313..98aa8af 100644 --- a/drivers/net/wireless/iwlwifi/iwl-eeprom.h +++ b/drivers/net/wireless/iwlwifi/iwl-eeprom.h @@ -247,13 +247,26 @@ struct iwl_eeprom_enhanced_txpwr { #define EEPROM_6050_TX_POWER_VERSION (4) #define EEPROM_6050_EEPROM_VERSION (0x532) -/* 6x50g2 Specific */ -#define EEPROM_6050G2_TX_POWER_VERSION (6) -#define EEPROM_6050G2_EEPROM_VERSION (0x553) +/* 6150 Specific */ +#define EEPROM_6150_TX_POWER_VERSION (6) +#define EEPROM_6150_EEPROM_VERSION (0x553) + +/* 6x05 Specific */ +#define EEPROM_6005_TX_POWER_VERSION (6) +#define EEPROM_6005_EEPROM_VERSION (0x709) + +/* 6x30 Specific */ +#define EEPROM_6030_TX_POWER_VERSION (6) +#define EEPROM_6030_EEPROM_VERSION (0x709) + +/* 2x00 Specific */ +#define EEPROM_2000_TX_POWER_VERSION (6) +#define EEPROM_2000_EEPROM_VERSION (0x805) + +/* 6x35 Specific */ +#define EEPROM_6035_TX_POWER_VERSION (6) +#define EEPROM_6035_EEPROM_VERSION (0x753) -/* 6x00g2 Specific */ -#define EEPROM_6000G2_TX_POWER_VERSION (6) -#define EEPROM_6000G2_EEPROM_VERSION (0x709) /* OTP */ /* lower blocks contain EEPROM image and calibration data */ @@ -264,6 +277,7 @@ struct iwl_eeprom_enhanced_txpwr { #define OTP_MAX_LL_ITEMS_1000 (3) /* OTP blocks for 1000 */ #define OTP_MAX_LL_ITEMS_6x00 (4) /* OTP blocks for 6x00 */ #define OTP_MAX_LL_ITEMS_6x50 (7) /* OTP blocks for 6x50 */ +#define OTP_MAX_LL_ITEMS_2x00 (4) /* OTP blocks for 2x00 */ /* 2.4 GHz */ extern const u8 iwl_eeprom_band_1[14]; diff --git a/drivers/net/wireless/iwlwifi/iwl-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-hcmd.c index c373b53..e4b953d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-hcmd.c +++ b/drivers/net/wireless/iwlwifi/iwl-hcmd.c @@ -108,6 +108,7 @@ const char *get_cmd_string(u8 cmd) IWL_CMD(REPLY_WIPAN_WEPKEY); IWL_CMD(REPLY_WIPAN_P2P_CHANNEL_SWITCH); IWL_CMD(REPLY_WIPAN_NOA_NOTIFICATION); + IWL_CMD(REPLY_WIPAN_DEACTIVATION_COMPLETE); default: return "UNKNOWN"; diff --git a/drivers/net/wireless/iwlwifi/iwl-led.c b/drivers/net/wireless/iwlwifi/iwl-led.c index 46ccdf4..074ad22 100644 --- a/drivers/net/wireless/iwlwifi/iwl-led.c +++ b/drivers/net/wireless/iwlwifi/iwl-led.c @@ -48,31 +48,19 @@ module_param(led_mode, int, S_IRUGO); MODULE_PARM_DESC(led_mode, "0=system default, " "1=On(RF On)/Off(RF Off), 2=blinking"); -static const struct { - u16 tpt; /* Mb/s */ - u8 on_time; - u8 off_time; -} blink_tbl[] = -{ - {300, 25, 25}, - {200, 40, 40}, - {100, 55, 55}, - {70, 65, 65}, - {50, 75, 75}, - {20, 85, 85}, - {10, 95, 95}, - {5, 110, 110}, - {1, 130, 130}, - {0, 167, 167}, - /* SOLID_ON */ - {-1, IWL_LED_SOLID, 0} +static const struct ieee80211_tpt_blink iwl_blink[] = { + { .throughput = 0 * 1024 - 1, .blink_time = 334 }, + { .throughput = 1 * 1024 - 1, .blink_time = 260 }, + { .throughput = 5 * 1024 - 1, .blink_time = 220 }, + { .throughput = 10 * 1024 - 1, .blink_time = 190 }, + { .throughput = 20 * 1024 - 1, .blink_time = 170 }, + { .throughput = 50 * 1024 - 1, .blink_time = 150 }, + { .throughput = 70 * 1024 - 1, .blink_time = 130 }, + { .throughput = 100 * 1024 - 1, .blink_time = 110 }, + { .throughput = 200 * 1024 - 1, .blink_time = 80 }, + { .throughput = 300 * 1024 - 1, .blink_time = 50 }, }; -#define IWL_1MB_RATE (128 * 1024) -#define IWL_LED_THRESHOLD (16) -#define IWL_MAX_BLINK_TBL (ARRAY_SIZE(blink_tbl) - 1) /* exclude SOLID_ON */ -#define IWL_SOLID_BLINK_IDX (ARRAY_SIZE(blink_tbl) - 1) - /* * Adjust led blink rate to compensate on a MAC Clock difference on every HW * Led blink rate analysis showed an average deviation of 0% on 3945, @@ -97,133 +85,104 @@ static inline u8 iwl_blink_compensation(struct iwl_priv *priv, } /* Set led pattern command */ -static int iwl_led_pattern(struct iwl_priv *priv, unsigned int idx) +static int iwl_led_cmd(struct iwl_priv *priv, + unsigned long on, + unsigned long off) { struct iwl_led_cmd led_cmd = { .id = IWL_LED_LINK, .interval = IWL_DEF_LED_INTRVL }; + int ret; - BUG_ON(idx > IWL_MAX_BLINK_TBL); + if (!test_bit(STATUS_READY, &priv->status)) + return -EBUSY; - IWL_DEBUG_LED(priv, "Led blink time compensation= %u\n", + if (priv->blink_on == on && priv->blink_off == off) + return 0; + + IWL_DEBUG_LED(priv, "Led blink time compensation=%u\n", priv->cfg->base_params->led_compensation); - led_cmd.on = - iwl_blink_compensation(priv, blink_tbl[idx].on_time, + led_cmd.on = iwl_blink_compensation(priv, on, priv->cfg->base_params->led_compensation); - led_cmd.off = - iwl_blink_compensation(priv, blink_tbl[idx].off_time, + led_cmd.off = iwl_blink_compensation(priv, off, priv->cfg->base_params->led_compensation); - return priv->cfg->ops->led->cmd(priv, &led_cmd); + ret = priv->cfg->ops->led->cmd(priv, &led_cmd); + if (!ret) { + priv->blink_on = on; + priv->blink_off = off; + } + return ret; } -int iwl_led_start(struct iwl_priv *priv) +static void iwl_led_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) { - return priv->cfg->ops->led->on(priv); -} -EXPORT_SYMBOL(iwl_led_start); + struct iwl_priv *priv = container_of(led_cdev, struct iwl_priv, led); + unsigned long on = 0; -int iwl_led_associate(struct iwl_priv *priv) -{ - IWL_DEBUG_LED(priv, "Associated\n"); - if (priv->cfg->led_mode == IWL_LED_BLINK) - priv->allow_blinking = 1; - priv->last_blink_time = jiffies; + if (brightness > 0) + on = IWL_LED_SOLID; - return 0; + iwl_led_cmd(priv, on, 0); } -EXPORT_SYMBOL(iwl_led_associate); -int iwl_led_disassociate(struct iwl_priv *priv) +static int iwl_led_blink_set(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) { - priv->allow_blinking = 0; + struct iwl_priv *priv = container_of(led_cdev, struct iwl_priv, led); - return 0; + return iwl_led_cmd(priv, *delay_on, *delay_off); } -EXPORT_SYMBOL(iwl_led_disassociate); -/* - * calculate blink rate according to last second Tx/Rx activities - */ -static int iwl_get_blink_rate(struct iwl_priv *priv) -{ - int i; - /* count both tx and rx traffic to be able to - * handle traffic in either direction - */ - u64 current_tpt = priv->tx_stats.data_bytes + - priv->rx_stats.data_bytes; - s64 tpt = current_tpt - priv->led_tpt; - - if (tpt < 0) /* wraparound */ - tpt = -tpt; - - IWL_DEBUG_LED(priv, "tpt %lld current_tpt %llu\n", - (long long)tpt, - (unsigned long long)current_tpt); - priv->led_tpt = current_tpt; - - if (!priv->allow_blinking) - i = IWL_MAX_BLINK_TBL; - else - for (i = 0; i < IWL_MAX_BLINK_TBL; i++) - if (tpt > (blink_tbl[i].tpt * IWL_1MB_RATE)) - break; - - IWL_DEBUG_LED(priv, "LED BLINK IDX=%d\n", i); - return i; -} - -/* - * this function called from handler. Since setting Led command can - * happen very frequent we postpone led command to be called from - * REPLY handler so we know ucode is up - */ -void iwl_leds_background(struct iwl_priv *priv) +void iwl_leds_init(struct iwl_priv *priv) { - u8 blink_idx; - - if (test_bit(STATUS_EXIT_PENDING, &priv->status)) { - priv->last_blink_time = 0; - return; - } - if (iwl_is_rfkill(priv)) { - priv->last_blink_time = 0; - return; + int mode = led_mode; + int ret; + + if (mode == IWL_LED_DEFAULT) + mode = priv->cfg->led_mode; + + priv->led.name = kasprintf(GFP_KERNEL, "%s-led", + wiphy_name(priv->hw->wiphy)); + priv->led.brightness_set = iwl_led_brightness_set; + priv->led.blink_set = iwl_led_blink_set; + priv->led.max_brightness = 1; + + switch (mode) { + case IWL_LED_DEFAULT: + WARN_ON(1); + break; + case IWL_LED_BLINK: + priv->led.default_trigger = + ieee80211_create_tpt_led_trigger(priv->hw, + IEEE80211_TPT_LEDTRIG_FL_CONNECTED, + iwl_blink, ARRAY_SIZE(iwl_blink)); + break; + case IWL_LED_RF_STATE: + priv->led.default_trigger = + ieee80211_get_radio_led_name(priv->hw); + break; } - if (!priv->allow_blinking) { - priv->last_blink_time = 0; - if (priv->last_blink_rate != IWL_SOLID_BLINK_IDX) { - priv->last_blink_rate = IWL_SOLID_BLINK_IDX; - iwl_led_pattern(priv, IWL_SOLID_BLINK_IDX); - } + ret = led_classdev_register(&priv->pci_dev->dev, &priv->led); + if (ret) { + kfree(priv->led.name); return; } - if (!priv->last_blink_time || - !time_after(jiffies, priv->last_blink_time + - msecs_to_jiffies(1000))) - return; - - blink_idx = iwl_get_blink_rate(priv); - /* call only if blink rate change */ - if (blink_idx != priv->last_blink_rate) - iwl_led_pattern(priv, blink_idx); - - priv->last_blink_time = jiffies; - priv->last_blink_rate = blink_idx; + priv->led_registered = true; } -EXPORT_SYMBOL(iwl_leds_background); +EXPORT_SYMBOL(iwl_leds_init); -void iwl_leds_init(struct iwl_priv *priv) +void iwl_leds_exit(struct iwl_priv *priv) { - priv->last_blink_rate = 0; - priv->last_blink_time = 0; - priv->allow_blinking = 0; - if (led_mode != IWL_LED_DEFAULT && - led_mode != priv->cfg->led_mode) - priv->cfg->led_mode = led_mode; + if (!priv->led_registered) + return; + + led_classdev_unregister(&priv->led); + kfree(priv->led.name); } -EXPORT_SYMBOL(iwl_leds_init); +EXPORT_SYMBOL(iwl_leds_exit); diff --git a/drivers/net/wireless/iwlwifi/iwl-led.h b/drivers/net/wireless/iwlwifi/iwl-led.h index 9079b33..101eef1 100644 --- a/drivers/net/wireless/iwlwifi/iwl-led.h +++ b/drivers/net/wireless/iwlwifi/iwl-led.h @@ -31,23 +31,14 @@ struct iwl_priv; #define IWL_LED_SOLID 11 -#define IWL_LED_NAME_LEN 31 #define IWL_DEF_LED_INTRVL cpu_to_le32(1000) #define IWL_LED_ACTIVITY (0<<1) #define IWL_LED_LINK (1<<1) -enum led_type { - IWL_LED_TRG_TX, - IWL_LED_TRG_RX, - IWL_LED_TRG_ASSOC, - IWL_LED_TRG_RADIO, - IWL_LED_TRG_MAX, -}; - /* * LED mode - * IWL_LED_DEFAULT: use system default + * IWL_LED_DEFAULT: use device default * IWL_LED_RF_STATE: turn LED on/off based on RF state * LED ON = RF ON * LED OFF = RF OFF @@ -60,9 +51,6 @@ enum iwl_led_mode { }; void iwl_leds_init(struct iwl_priv *priv); -void iwl_leds_background(struct iwl_priv *priv); -int iwl_led_start(struct iwl_priv *priv); -int iwl_led_associate(struct iwl_priv *priv); -int iwl_led_disassociate(struct iwl_priv *priv); +void iwl_leds_exit(struct iwl_priv *priv); #endif /* __iwl_leds_h__ */ diff --git a/drivers/net/wireless/iwlwifi/iwl-legacy.c b/drivers/net/wireless/iwlwifi/iwl-legacy.c index bb1a742..e1ace3c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-legacy.c +++ b/drivers/net/wireless/iwlwifi/iwl-legacy.c @@ -85,10 +85,9 @@ int iwl_legacy_mac_config(struct ieee80211_hw *hw, u32 changed) IWL_DEBUG_MAC80211(priv, "enter to channel %d changed 0x%X\n", channel->hw_value, changed); - if (unlikely(!priv->cfg->mod_params->disable_hw_scan && - test_bit(STATUS_SCANNING, &priv->status))) { + if (unlikely(test_bit(STATUS_SCANNING, &priv->status))) { scan_active = 1; - IWL_DEBUG_MAC80211(priv, "leave - scanning\n"); + IWL_DEBUG_MAC80211(priv, "scan active\n"); } if (changed & (IEEE80211_CONF_CHANGE_SMPS | @@ -332,7 +331,6 @@ static inline void iwl_set_no_assoc(struct iwl_priv *priv, { struct iwl_rxon_context *ctx = iwl_rxon_ctx_from_vif(vif); - iwl_led_disassociate(priv); /* * inform the ucode that there is no longer an * association and that no more packets should be @@ -520,8 +518,6 @@ void iwl_legacy_mac_bss_info_changed(struct ieee80211_hw *hw, if (bss_conf->assoc) { priv->timestamp = bss_conf->timestamp; - iwl_led_associate(priv); - if (!iwl_is_rfkill(priv)) priv->cfg->ops->legacy->post_associate(priv); } else @@ -545,7 +541,6 @@ void iwl_legacy_mac_bss_info_changed(struct ieee80211_hw *hw, memcpy(ctx->staging.bssid_addr, bss_conf->bssid, ETH_ALEN); memcpy(priv->bssid, bss_conf->bssid, ETH_ALEN); - iwl_led_associate(priv); priv->cfg->ops->legacy->config_ap(priv); } else iwl_set_no_assoc(priv, vif); diff --git a/drivers/net/wireless/iwlwifi/iwl-power.c b/drivers/net/wireless/iwlwifi/iwl-power.c index 1eec18d..1d1bf32 100644 --- a/drivers/net/wireless/iwlwifi/iwl-power.c +++ b/drivers/net/wireless/iwlwifi/iwl-power.c @@ -226,8 +226,7 @@ static void iwl_static_sleep_cmd(struct iwl_priv *priv, else cmd->flags &= ~IWL_POWER_SHADOW_REG_ENA; - if (priv->cfg->bt_params && - priv->cfg->bt_params->advanced_bt_coexist) { + if (iwl_advanced_bt_coexist(priv)) { if (!priv->cfg->bt_params->bt_sco_disable) cmd->flags |= IWL_POWER_BT_SCO_ENA; else @@ -313,8 +312,7 @@ static void iwl_power_fill_sleep_cmd(struct iwl_priv *priv, else cmd->flags &= ~IWL_POWER_SHADOW_REG_ENA; - if (priv->cfg->bt_params && - priv->cfg->bt_params->advanced_bt_coexist) { + if (iwl_advanced_bt_coexist(priv)) { if (!priv->cfg->bt_params->bt_sco_disable) cmd->flags |= IWL_POWER_BT_SCO_ENA; else @@ -358,8 +356,7 @@ static void iwl_power_build_cmd(struct iwl_priv *priv, if (priv->cfg->base_params->broken_powersave) iwl_power_sleep_cam_cmd(priv, cmd); - else if (priv->cfg->base_params->supports_idle && - priv->hw->conf.flags & IEEE80211_CONF_IDLE) + else if (priv->hw->conf.flags & IEEE80211_CONF_IDLE) iwl_static_sleep_cmd(priv, cmd, IWL_POWER_INDEX_5, 20); else if (priv->cfg->ops->lib->tt_ops.lower_power_detection && priv->cfg->ops->lib->tt_ops.tt_power_mode && diff --git a/drivers/net/wireless/iwlwifi/iwl-scan.c b/drivers/net/wireless/iwlwifi/iwl-scan.c index 12d9363..08f1bea 100644 --- a/drivers/net/wireless/iwlwifi/iwl-scan.c +++ b/drivers/net/wireless/iwlwifi/iwl-scan.c @@ -257,8 +257,7 @@ static void iwl_rx_scan_complete_notif(struct iwl_priv *priv, queue_work(priv->workqueue, &priv->scan_completed); if (priv->iw_mode != NL80211_IFTYPE_ADHOC && - priv->cfg->bt_params && - priv->cfg->bt_params->advanced_bt_coexist && + iwl_advanced_bt_coexist(priv) && priv->bt_status != scan_notif->bt_status) { if (scan_notif->bt_status) { /* BT on */ diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index 371abbf..adcef73 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -2517,7 +2517,7 @@ static void iwl3945_alive_start(struct iwl_priv *priv) ieee80211_wake_queues(priv->hw); - priv->active_rate = IWL_RATES_MASK; + priv->active_rate = IWL_RATES_MASK_3945; iwl_power_update_mode(priv, true); @@ -2535,15 +2535,14 @@ static void iwl3945_alive_start(struct iwl_priv *priv) /* Configure Bluetooth device coexistence support */ priv->cfg->ops->hcmd->send_bt_config(priv); + set_bit(STATUS_READY, &priv->status); + /* Configure the adapter for unassociated operation */ iwl3945_commit_rxon(priv, ctx); iwl3945_reg_txpower_periodic(priv); - iwl_leds_init(priv); - IWL_DEBUG_INFO(priv, "ALIVE processing complete.\n"); - set_bit(STATUS_READY, &priv->status); wake_up_interruptible(&priv->wait_command_queue); return; @@ -2861,16 +2860,13 @@ int iwl3945_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif) u32 extra; u32 suspend_time = 100; u32 scan_suspend_time = 100; - unsigned long flags; IWL_DEBUG_INFO(priv, "Scanning while associated...\n"); - spin_lock_irqsave(&priv->lock, flags); if (priv->is_internal_short_scan) interval = 0; else interval = vif->bss_conf.beacon_int; - spin_unlock_irqrestore(&priv->lock, flags); scan->suspend_time = 0; scan->max_out_time = cpu_to_le32(200 * 1024); @@ -3170,8 +3166,6 @@ static int iwl3945_mac_start(struct ieee80211_hw *hw) * no need to poll the killswitch state anymore */ cancel_delayed_work(&priv->_3945.rfkill_poll); - iwl_led_start(priv); - priv->is_open = 1; IWL_DEBUG_MAC80211(priv, "leave\n"); return 0; @@ -3289,6 +3283,14 @@ static int iwl3945_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, return -EOPNOTSUPP; } + /* + * To support IBSS RSN, don't program group keys in IBSS, the + * hardware will then not attempt to decrypt the frames. + */ + if (vif->type == NL80211_IFTYPE_ADHOC && + !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) + return -EOPNOTSUPP; + static_key = !iwl_is_associated(priv, IWL_RXON_CTX_BSS); if (!static_key) { @@ -3918,7 +3920,8 @@ static int iwl3945_setup_mac(struct iwl_priv *priv) priv->contexts[IWL_RXON_CTX_BSS].interface_modes; hw->wiphy->flags |= WIPHY_FLAG_CUSTOM_REGULATORY | - WIPHY_FLAG_DISABLE_BEACON_HINTS; + WIPHY_FLAG_DISABLE_BEACON_HINTS | + WIPHY_FLAG_IBSS_RSN; hw->wiphy->max_scan_ssids = PROBE_OPTION_MAX_3945; /* we create the 802.11 header and a zero-length SSID element */ @@ -3935,6 +3938,8 @@ static int iwl3945_setup_mac(struct iwl_priv *priv) priv->hw->wiphy->bands[IEEE80211_BAND_5GHZ] = &priv->bands[IEEE80211_BAND_5GHZ]; + iwl_leds_init(priv); + ret = ieee80211_register_hw(priv->hw); if (ret) { IWL_ERR(priv, "Failed to register hw (error %d)\n", ret); @@ -4194,6 +4199,8 @@ static void __devexit iwl3945_pci_remove(struct pci_dev *pdev) set_bit(STATUS_EXIT_PENDING, &priv->status); + iwl_leds_exit(priv); + if (priv->mac80211_registered) { ieee80211_unregister_hw(priv->hw); priv->mac80211_registered = 0; diff --git a/drivers/net/wireless/iwmc3200wifi/cfg80211.c b/drivers/net/wireless/iwmc3200wifi/cfg80211.c index 5a49822..ed57e44 100644 --- a/drivers/net/wireless/iwmc3200wifi/cfg80211.c +++ b/drivers/net/wireless/iwmc3200wifi/cfg80211.c @@ -287,7 +287,8 @@ int iwm_cfg80211_inform_bss(struct iwm_priv *iwm) return -EINVAL; } - freq = ieee80211_channel_to_frequency(umac_bss->channel); + freq = ieee80211_channel_to_frequency(umac_bss->channel, + band->band); channel = ieee80211_get_channel(wiphy, freq); signal = umac_bss->rssi * 100; diff --git a/drivers/net/wireless/iwmc3200wifi/rx.c b/drivers/net/wireless/iwmc3200wifi/rx.c index a944893..9a57cf6 100644 --- a/drivers/net/wireless/iwmc3200wifi/rx.c +++ b/drivers/net/wireless/iwmc3200wifi/rx.c @@ -543,7 +543,10 @@ static int iwm_mlme_assoc_complete(struct iwm_priv *iwm, u8 *buf, switch (le32_to_cpu(complete->status)) { case UMAC_ASSOC_COMPLETE_SUCCESS: chan = ieee80211_get_channel(wiphy, - ieee80211_channel_to_frequency(complete->channel)); + ieee80211_channel_to_frequency(complete->channel, + complete->band == UMAC_BAND_2GHZ ? + IEEE80211_BAND_2GHZ : + IEEE80211_BAND_5GHZ)); if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) { /* Associated to a unallowed channel, disassociate. */ __iwm_invalidate_mlme_profile(iwm); @@ -841,7 +844,7 @@ static int iwm_mlme_update_bss_table(struct iwm_priv *iwm, u8 *buf, goto err; } - freq = ieee80211_channel_to_frequency(umac_bss->channel); + freq = ieee80211_channel_to_frequency(umac_bss->channel, band->band); channel = ieee80211_get_channel(wiphy, freq); signal = umac_bss->rssi * 100; diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c index 698a1f7..30ef035 100644 --- a/drivers/net/wireless/libertas/cfg.c +++ b/drivers/net/wireless/libertas/cfg.c @@ -607,7 +607,8 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy, /* No channel, no luck */ if (chan_no != -1) { struct wiphy *wiphy = priv->wdev->wiphy; - int freq = ieee80211_channel_to_frequency(chan_no); + int freq = ieee80211_channel_to_frequency(chan_no, + IEEE80211_BAND_2GHZ); struct ieee80211_channel *channel = ieee80211_get_channel(wiphy, freq); @@ -1597,7 +1598,8 @@ static int lbs_get_survey(struct wiphy *wiphy, struct net_device *dev, lbs_deb_enter(LBS_DEB_CFG80211); survey->channel = ieee80211_get_channel(wiphy, - ieee80211_channel_to_frequency(priv->channel)); + ieee80211_channel_to_frequency(priv->channel, + IEEE80211_BAND_2GHZ)); ret = lbs_get_rssi(priv, &signal, &noise); if (ret == 0) { diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c index 78c4da1..7e8a658 100644 --- a/drivers/net/wireless/libertas/cmd.c +++ b/drivers/net/wireless/libertas/cmd.c @@ -145,9 +145,13 @@ int lbs_update_hw_spec(struct lbs_private *priv) if (priv->current_addr[0] == 0xff) memmove(priv->current_addr, cmd.permanentaddr, ETH_ALEN); - memcpy(priv->dev->dev_addr, priv->current_addr, ETH_ALEN); - if (priv->mesh_dev) - memcpy(priv->mesh_dev->dev_addr, priv->current_addr, ETH_ALEN); + if (!priv->copied_hwaddr) { + memcpy(priv->dev->dev_addr, priv->current_addr, ETH_ALEN); + if (priv->mesh_dev) + memcpy(priv->mesh_dev->dev_addr, + priv->current_addr, ETH_ALEN); + priv->copied_hwaddr = 1; + } out: lbs_deb_leave(LBS_DEB_CMD); diff --git a/drivers/net/wireless/libertas/dev.h b/drivers/net/wireless/libertas/dev.h index 18dd9a0..bc461eb 100644 --- a/drivers/net/wireless/libertas/dev.h +++ b/drivers/net/wireless/libertas/dev.h @@ -90,6 +90,7 @@ struct lbs_private { void *card; u8 fw_ready; u8 surpriseremoved; + u8 setup_fw_on_resume; int (*hw_host_to_card) (struct lbs_private *priv, u8 type, u8 *payload, u16 nb); void (*reset_card) (struct lbs_private *priv); int (*enter_deep_sleep) (struct lbs_private *priv); @@ -101,6 +102,7 @@ struct lbs_private { u32 fwcapinfo; u16 regioncode; u8 current_addr[ETH_ALEN]; + u8 copied_hwaddr; /* Command download */ u8 dnld_sent; diff --git a/drivers/net/wireless/libertas/if_spi.c b/drivers/net/wireless/libertas/if_spi.c index 0060023..f6c2cd6 100644 --- a/drivers/net/wireless/libertas/if_spi.c +++ b/drivers/net/wireless/libertas/if_spi.c @@ -20,10 +20,8 @@ #include <linux/moduleparam.h> #include <linux/firmware.h> #include <linux/jiffies.h> -#include <linux/kthread.h> #include <linux/list.h> #include <linux/netdevice.h> -#include <linux/semaphore.h> #include <linux/slab.h> #include <linux/spi/libertas_spi.h> #include <linux/spi/spi.h> @@ -34,6 +32,12 @@ #include "dev.h" #include "if_spi.h" +struct if_spi_packet { + struct list_head list; + u16 blen; + u8 buffer[0] __attribute__((aligned(4))); +}; + struct if_spi_card { struct spi_device *spi; struct lbs_private *priv; @@ -51,18 +55,36 @@ struct if_spi_card { unsigned long spu_reg_delay; /* Handles all SPI communication (except for FW load) */ - struct task_struct *spi_thread; - int run_thread; - - /* Used to wake up the spi_thread */ - struct semaphore spi_ready; - struct semaphore spi_thread_terminated; + struct workqueue_struct *workqueue; + struct work_struct packet_work; u8 cmd_buffer[IF_SPI_CMD_BUF_SIZE]; + + /* A buffer of incoming packets from libertas core. + * Since we can't sleep in hw_host_to_card, we have to buffer + * them. */ + struct list_head cmd_packet_list; + struct list_head data_packet_list; + + /* Protects cmd_packet_list and data_packet_list */ + spinlock_t buffer_lock; }; static void free_if_spi_card(struct if_spi_card *card) { + struct list_head *cursor, *next; + struct if_spi_packet *packet; + + list_for_each_safe(cursor, next, &card->cmd_packet_list) { + packet = container_of(cursor, struct if_spi_packet, list); + list_del(&packet->list); + kfree(packet); + } + list_for_each_safe(cursor, next, &card->data_packet_list) { + packet = container_of(cursor, struct if_spi_packet, list); + list_del(&packet->list); + kfree(packet); + } spi_set_drvdata(card->spi, NULL); kfree(card); } @@ -622,7 +644,7 @@ out: /* * SPI Transfer Thread * - * The SPI thread handles all SPI transfers, so there is no need for a lock. + * The SPI worker handles all SPI transfers, so there is no need for a lock. */ /* Move a command from the card to the host */ @@ -742,6 +764,40 @@ out: return err; } +/* Move data or a command from the host to the card. */ +static void if_spi_h2c(struct if_spi_card *card, + struct if_spi_packet *packet, int type) +{ + int err = 0; + u16 int_type, port_reg; + + switch (type) { + case MVMS_DAT: + int_type = IF_SPI_CIC_TX_DOWNLOAD_OVER; + port_reg = IF_SPI_DATA_RDWRPORT_REG; + break; + case MVMS_CMD: + int_type = IF_SPI_CIC_CMD_DOWNLOAD_OVER; + port_reg = IF_SPI_CMD_RDWRPORT_REG; + break; + default: + lbs_pr_err("can't transfer buffer of type %d\n", type); + err = -EINVAL; + goto out; + } + + /* Write the data to the card */ + err = spu_write(card, port_reg, packet->buffer, packet->blen); + if (err) + goto out; + +out: + kfree(packet); + + if (err) + lbs_pr_err("%s: error %d\n", __func__, err); +} + /* Inform the host about a card event */ static void if_spi_e2h(struct if_spi_card *card) { @@ -766,71 +822,88 @@ out: lbs_pr_err("%s: error %d\n", __func__, err); } -static int lbs_spi_thread(void *data) +static void if_spi_host_to_card_worker(struct work_struct *work) { int err; - struct if_spi_card *card = data; + struct if_spi_card *card; u16 hiStatus; + unsigned long flags; + struct if_spi_packet *packet; - while (1) { - /* Wait to be woken up by one of two things. First, our ISR - * could tell us that something happened on the WLAN. - * Secondly, libertas could call hw_host_to_card with more - * data, which we might be able to send. - */ - do { - err = down_interruptible(&card->spi_ready); - if (!card->run_thread) { - up(&card->spi_thread_terminated); - do_exit(0); - } - } while (err == -EINTR); + card = container_of(work, struct if_spi_card, packet_work); - /* Read the host interrupt status register to see what we - * can do. */ - err = spu_read_u16(card, IF_SPI_HOST_INT_STATUS_REG, - &hiStatus); - if (err) { - lbs_pr_err("I/O error\n"); + lbs_deb_enter(LBS_DEB_SPI); + + /* Read the host interrupt status register to see what we + * can do. */ + err = spu_read_u16(card, IF_SPI_HOST_INT_STATUS_REG, + &hiStatus); + if (err) { + lbs_pr_err("I/O error\n"); + goto err; + } + + if (hiStatus & IF_SPI_HIST_CMD_UPLOAD_RDY) { + err = if_spi_c2h_cmd(card); + if (err) goto err; - } + } + if (hiStatus & IF_SPI_HIST_RX_UPLOAD_RDY) { + err = if_spi_c2h_data(card); + if (err) + goto err; + } - if (hiStatus & IF_SPI_HIST_CMD_UPLOAD_RDY) { - err = if_spi_c2h_cmd(card); - if (err) - goto err; - } - if (hiStatus & IF_SPI_HIST_RX_UPLOAD_RDY) { - err = if_spi_c2h_data(card); - if (err) - goto err; + /* workaround: in PS mode, the card does not set the Command + * Download Ready bit, but it sets TX Download Ready. */ + if (hiStatus & IF_SPI_HIST_CMD_DOWNLOAD_RDY || + (card->priv->psstate != PS_STATE_FULL_POWER && + (hiStatus & IF_SPI_HIST_TX_DOWNLOAD_RDY))) { + /* This means two things. First of all, + * if there was a previous command sent, the card has + * successfully received it. + * Secondly, it is now ready to download another + * command. + */ + lbs_host_to_card_done(card->priv); + + /* Do we have any command packets from the host to + * send? */ + packet = NULL; + spin_lock_irqsave(&card->buffer_lock, flags); + if (!list_empty(&card->cmd_packet_list)) { + packet = (struct if_spi_packet *)(card-> + cmd_packet_list.next); + list_del(&packet->list); } + spin_unlock_irqrestore(&card->buffer_lock, flags); - /* workaround: in PS mode, the card does not set the Command - * Download Ready bit, but it sets TX Download Ready. */ - if (hiStatus & IF_SPI_HIST_CMD_DOWNLOAD_RDY || - (card->priv->psstate != PS_STATE_FULL_POWER && - (hiStatus & IF_SPI_HIST_TX_DOWNLOAD_RDY))) { - lbs_host_to_card_done(card->priv); + if (packet) + if_spi_h2c(card, packet, MVMS_CMD); + } + if (hiStatus & IF_SPI_HIST_TX_DOWNLOAD_RDY) { + /* Do we have any data packets from the host to + * send? */ + packet = NULL; + spin_lock_irqsave(&card->buffer_lock, flags); + if (!list_empty(&card->data_packet_list)) { + packet = (struct if_spi_packet *)(card-> + data_packet_list.next); + list_del(&packet->list); } + spin_unlock_irqrestore(&card->buffer_lock, flags); - if (hiStatus & IF_SPI_HIST_CARD_EVENT) - if_spi_e2h(card); + if (packet) + if_spi_h2c(card, packet, MVMS_DAT); + } + if (hiStatus & IF_SPI_HIST_CARD_EVENT) + if_spi_e2h(card); err: - if (err) - lbs_pr_err("%s: got error %d\n", __func__, err); - } -} + if (err) + lbs_pr_err("%s: got error %d\n", __func__, err); -/* Block until lbs_spi_thread thread has terminated */ -static void if_spi_terminate_spi_thread(struct if_spi_card *card) -{ - /* It would be nice to use kthread_stop here, but that function - * can't wake threads waiting for a semaphore. */ - card->run_thread = 0; - up(&card->spi_ready); - down(&card->spi_thread_terminated); + lbs_deb_leave(LBS_DEB_SPI); } /* @@ -842,18 +915,40 @@ static int if_spi_host_to_card(struct lbs_private *priv, u8 type, u8 *buf, u16 nb) { int err = 0; + unsigned long flags; struct if_spi_card *card = priv->card; + struct if_spi_packet *packet; + u16 blen; lbs_deb_enter_args(LBS_DEB_SPI, "type %d, bytes %d", type, nb); - nb = ALIGN(nb, 4); + if (nb == 0) { + lbs_pr_err("%s: invalid size requested: %d\n", __func__, nb); + err = -EINVAL; + goto out; + } + blen = ALIGN(nb, 4); + packet = kzalloc(sizeof(struct if_spi_packet) + blen, GFP_ATOMIC); + if (!packet) { + err = -ENOMEM; + goto out; + } + packet->blen = blen; + memcpy(packet->buffer, buf, nb); + memset(packet->buffer + nb, 0, blen - nb); switch (type) { case MVMS_CMD: - err = spu_write(card, IF_SPI_CMD_RDWRPORT_REG, buf, nb); + priv->dnld_sent = DNLD_CMD_SENT; + spin_lock_irqsave(&card->buffer_lock, flags); + list_add_tail(&packet->list, &card->cmd_packet_list); + spin_unlock_irqrestore(&card->buffer_lock, flags); break; case MVMS_DAT: - err = spu_write(card, IF_SPI_DATA_RDWRPORT_REG, buf, nb); + priv->dnld_sent = DNLD_DATA_SENT; + spin_lock_irqsave(&card->buffer_lock, flags); + list_add_tail(&packet->list, &card->data_packet_list); + spin_unlock_irqrestore(&card->buffer_lock, flags); break; default: lbs_pr_err("can't transfer buffer of type %d", type); @@ -861,6 +956,9 @@ static int if_spi_host_to_card(struct lbs_private *priv, break; } + /* Queue spi xfer work */ + queue_work(card->workqueue, &card->packet_work); +out: lbs_deb_leave_args(LBS_DEB_SPI, "err=%d", err); return err; } @@ -869,13 +967,14 @@ static int if_spi_host_to_card(struct lbs_private *priv, * Host Interrupts * * Service incoming interrupts from the WLAN device. We can't sleep here, so - * don't try to talk on the SPI bus, just wake up the SPI thread. + * don't try to talk on the SPI bus, just queue the SPI xfer work. */ static irqreturn_t if_spi_host_interrupt(int irq, void *dev_id) { struct if_spi_card *card = dev_id; - up(&card->spi_ready); + queue_work(card->workqueue, &card->packet_work); + return IRQ_HANDLED; } @@ -883,56 +982,26 @@ static irqreturn_t if_spi_host_interrupt(int irq, void *dev_id) * SPI callbacks */ -static int __devinit if_spi_probe(struct spi_device *spi) +static int if_spi_init_card(struct if_spi_card *card) { - struct if_spi_card *card; - struct lbs_private *priv = NULL; - struct libertas_spi_platform_data *pdata = spi->dev.platform_data; - int err = 0, i; + struct spi_device *spi = card->spi; + int err, i; u32 scratch; - struct sched_param param = { .sched_priority = 1 }; const struct firmware *helper = NULL; const struct firmware *mainfw = NULL; lbs_deb_enter(LBS_DEB_SPI); - if (!pdata) { - err = -EINVAL; - goto out; - } - - if (pdata->setup) { - err = pdata->setup(spi); - if (err) - goto out; - } - - /* Allocate card structure to represent this specific device */ - card = kzalloc(sizeof(struct if_spi_card), GFP_KERNEL); - if (!card) { - err = -ENOMEM; - goto out; - } - spi_set_drvdata(spi, card); - card->pdata = pdata; - card->spi = spi; - card->prev_xfer_time = jiffies; - - sema_init(&card->spi_ready, 0); - sema_init(&card->spi_thread_terminated, 0); - - /* Initialize the SPI Interface Unit */ - err = spu_init(card, pdata->use_dummy_writes); + err = spu_init(card, card->pdata->use_dummy_writes); if (err) - goto free_card; + goto out; err = spu_get_chip_revision(card, &card->card_id, &card->card_rev); if (err) - goto free_card; + goto out; - /* Firmware load */ err = spu_read_u32(card, IF_SPI_SCRATCH_4_REG, &scratch); if (err) - goto free_card; + goto out; if (scratch == SUCCESSFUL_FW_DOWNLOAD_MAGIC) lbs_deb_spi("Firmware is already loaded for " "Marvell WLAN 802.11 adapter\n"); @@ -946,7 +1015,7 @@ static int __devinit if_spi_probe(struct spi_device *spi) lbs_pr_err("Unsupported chip_id: 0x%02x\n", card->card_id); err = -ENODEV; - goto free_card; + goto out; } err = lbs_get_firmware(&card->spi->dev, NULL, NULL, @@ -954,7 +1023,7 @@ static int __devinit if_spi_probe(struct spi_device *spi) &mainfw); if (err) { lbs_pr_err("failed to find firmware (%d)\n", err); - goto free_card; + goto out; } lbs_deb_spi("Initializing FW for Marvell WLAN 802.11 adapter " @@ -966,15 +1035,68 @@ static int __devinit if_spi_probe(struct spi_device *spi) spi->max_speed_hz); err = if_spi_prog_helper_firmware(card, helper); if (err) - goto free_card; + goto out; err = if_spi_prog_main_firmware(card, mainfw); if (err) - goto free_card; + goto out; lbs_deb_spi("loaded FW for Marvell WLAN 802.11 adapter\n"); } err = spu_set_interrupt_mode(card, 0, 1); if (err) + goto out; + +out: + if (helper) + release_firmware(helper); + if (mainfw) + release_firmware(mainfw); + + lbs_deb_leave_args(LBS_DEB_SPI, "err %d\n", err); + + return err; +} + +static int __devinit if_spi_probe(struct spi_device *spi) +{ + struct if_spi_card *card; + struct lbs_private *priv = NULL; + struct libertas_spi_platform_data *pdata = spi->dev.platform_data; + int err = 0; + + lbs_deb_enter(LBS_DEB_SPI); + + if (!pdata) { + err = -EINVAL; + goto out; + } + + if (pdata->setup) { + err = pdata->setup(spi); + if (err) + goto out; + } + + /* Allocate card structure to represent this specific device */ + card = kzalloc(sizeof(struct if_spi_card), GFP_KERNEL); + if (!card) { + err = -ENOMEM; + goto teardown; + } + spi_set_drvdata(spi, card); + card->pdata = pdata; + card->spi = spi; + card->prev_xfer_time = jiffies; + + INIT_LIST_HEAD(&card->cmd_packet_list); + INIT_LIST_HEAD(&card->data_packet_list); + spin_lock_init(&card->buffer_lock); + + /* Initialize the SPI Interface Unit */ + + /* Firmware load */ + err = if_spi_init_card(card); + if (err) goto free_card; /* Register our card with libertas. @@ -993,27 +1115,16 @@ static int __devinit if_spi_probe(struct spi_device *spi) priv->fw_ready = 1; /* Initialize interrupt handling stuff. */ - card->run_thread = 1; - card->spi_thread = kthread_run(lbs_spi_thread, card, "lbs_spi_thread"); - if (IS_ERR(card->spi_thread)) { - card->run_thread = 0; - err = PTR_ERR(card->spi_thread); - lbs_pr_err("error creating SPI thread: err=%d\n", err); - goto remove_card; - } - if (sched_setscheduler(card->spi_thread, SCHED_FIFO, ¶m)) - lbs_pr_err("Error setting scheduler, using default.\n"); + card->workqueue = create_workqueue("libertas_spi"); + INIT_WORK(&card->packet_work, if_spi_host_to_card_worker); err = request_irq(spi->irq, if_spi_host_interrupt, IRQF_TRIGGER_FALLING, "libertas_spi", card); if (err) { lbs_pr_err("can't get host irq line-- request_irq failed\n"); - goto terminate_thread; + goto terminate_workqueue; } - /* poke the IRQ handler so that we don't miss the first interrupt */ - up(&card->spi_ready); - /* Start the card. * This will call register_netdev, and we'll start * getting interrupts... */ @@ -1028,18 +1139,16 @@ static int __devinit if_spi_probe(struct spi_device *spi) release_irq: free_irq(spi->irq, card); -terminate_thread: - if_spi_terminate_spi_thread(card); -remove_card: +terminate_workqueue: + flush_workqueue(card->workqueue); + destroy_workqueue(card->workqueue); lbs_remove_card(priv); /* will call free_netdev */ free_card: free_if_spi_card(card); +teardown: + if (pdata->teardown) + pdata->teardown(spi); out: - if (helper) - release_firmware(helper); - if (mainfw) - release_firmware(mainfw); - lbs_deb_leave_args(LBS_DEB_SPI, "err %d\n", err); return err; } @@ -1056,7 +1165,8 @@ static int __devexit libertas_spi_remove(struct spi_device *spi) lbs_remove_card(priv); /* will call free_netdev */ free_irq(spi->irq, card); - if_spi_terminate_spi_thread(card); + flush_workqueue(card->workqueue); + destroy_workqueue(card->workqueue); if (card->pdata->teardown) card->pdata->teardown(spi); free_if_spi_card(card); diff --git a/drivers/net/wireless/libertas/main.c b/drivers/net/wireless/libertas/main.c index 6836a6d..ca8149c 100644 --- a/drivers/net/wireless/libertas/main.c +++ b/drivers/net/wireless/libertas/main.c @@ -539,6 +539,43 @@ static int lbs_thread(void *data) return 0; } +/** + * @brief This function gets the HW spec from the firmware and sets + * some basic parameters. + * + * @param priv A pointer to struct lbs_private structure + * @return 0 or -1 + */ +static int lbs_setup_firmware(struct lbs_private *priv) +{ + int ret = -1; + s16 curlevel = 0, minlevel = 0, maxlevel = 0; + + lbs_deb_enter(LBS_DEB_FW); + + /* Read MAC address from firmware */ + memset(priv->current_addr, 0xff, ETH_ALEN); + ret = lbs_update_hw_spec(priv); + if (ret) + goto done; + + /* Read power levels if available */ + ret = lbs_get_tx_power(priv, &curlevel, &minlevel, &maxlevel); + if (ret == 0) { + priv->txpower_cur = curlevel; + priv->txpower_min = minlevel; + priv->txpower_max = maxlevel; + } + + /* Send cmd to FW to enable 11D function */ + ret = lbs_set_snmp_mib(priv, SNMP_MIB_OID_11D_ENABLE, 1); + + lbs_set_mac_control(priv); +done: + lbs_deb_leave_args(LBS_DEB_FW, "ret %d", ret); + return ret; +} + int lbs_suspend(struct lbs_private *priv) { int ret; @@ -584,47 +621,13 @@ int lbs_resume(struct lbs_private *priv) lbs_pr_err("deep sleep activation failed: %d\n", ret); } - lbs_deb_leave_args(LBS_DEB_FW, "ret %d", ret); - return ret; -} -EXPORT_SYMBOL_GPL(lbs_resume); - -/** - * @brief This function gets the HW spec from the firmware and sets - * some basic parameters. - * - * @param priv A pointer to struct lbs_private structure - * @return 0 or -1 - */ -static int lbs_setup_firmware(struct lbs_private *priv) -{ - int ret = -1; - s16 curlevel = 0, minlevel = 0, maxlevel = 0; - - lbs_deb_enter(LBS_DEB_FW); - - /* Read MAC address from firmware */ - memset(priv->current_addr, 0xff, ETH_ALEN); - ret = lbs_update_hw_spec(priv); - if (ret) - goto done; - - /* Read power levels if available */ - ret = lbs_get_tx_power(priv, &curlevel, &minlevel, &maxlevel); - if (ret == 0) { - priv->txpower_cur = curlevel; - priv->txpower_min = minlevel; - priv->txpower_max = maxlevel; - } + if (priv->setup_fw_on_resume) + ret = lbs_setup_firmware(priv); - /* Send cmd to FW to enable 11D function */ - ret = lbs_set_snmp_mib(priv, SNMP_MIB_OID_11D_ENABLE, 1); - - lbs_set_mac_control(priv); -done: lbs_deb_leave_args(LBS_DEB_FW, "ret %d", ret); return ret; } +EXPORT_SYMBOL_GPL(lbs_resume); /** * This function handles the timeout of command sending. diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 454f045..5d39b28 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -943,7 +943,8 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw, static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 9ecf840..af4f2c6 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -232,6 +232,9 @@ struct mwl8k_priv { struct completion firmware_loading_complete; }; +#define MAX_WEP_KEY_LEN 13 +#define NUM_WEP_KEYS 4 + /* Per interface specific private data */ struct mwl8k_vif { struct list_head list; @@ -242,8 +245,21 @@ struct mwl8k_vif { /* Non AMPDU sequence number assigned by driver. */ u16 seqno; + + /* Saved WEP keys */ + struct { + u8 enabled; + u8 key[sizeof(struct ieee80211_key_conf) + MAX_WEP_KEY_LEN]; + } wep_key_conf[NUM_WEP_KEYS]; + + /* BSSID */ + u8 bssid[ETH_ALEN]; + + /* A flag to indicate is HW crypto is enabled for this bssid */ + bool is_hw_crypto_enabled; }; #define MWL8K_VIF(_vif) ((struct mwl8k_vif *)&((_vif)->drv_priv)) +#define IEEE80211_KEY_CONF(_u8) ((struct ieee80211_key_conf *)(_u8)) struct mwl8k_sta { /* Index into station database. Returned by UPDATE_STADB. */ @@ -337,6 +353,7 @@ static const struct ieee80211_rate mwl8k_rates_50[] = { #define MWL8K_CMD_SET_RATEADAPT_MODE 0x0203 #define MWL8K_CMD_BSS_START 0x1100 /* per-vif */ #define MWL8K_CMD_SET_NEW_STN 0x1111 /* per-vif */ +#define MWL8K_CMD_UPDATE_ENCRYPTION 0x1122 /* per-vif */ #define MWL8K_CMD_UPDATE_STADB 0x1123 static const char *mwl8k_cmd_name(__le16 cmd, char *buf, int bufsize) @@ -375,6 +392,7 @@ static const char *mwl8k_cmd_name(__le16 cmd, char *buf, int bufsize) MWL8K_CMDNAME(SET_RATEADAPT_MODE); MWL8K_CMDNAME(BSS_START); MWL8K_CMDNAME(SET_NEW_STN); + MWL8K_CMDNAME(UPDATE_ENCRYPTION); MWL8K_CMDNAME(UPDATE_STADB); default: snprintf(buf, bufsize, "0x%x", cmd); @@ -715,10 +733,12 @@ static inline void mwl8k_remove_dma_header(struct sk_buff *skb, __le16 qos) skb_pull(skb, sizeof(*tr) - hdrlen); } -static inline void mwl8k_add_dma_header(struct sk_buff *skb) +static void +mwl8k_add_dma_header(struct sk_buff *skb, int tail_pad) { struct ieee80211_hdr *wh; int hdrlen; + int reqd_hdrlen; struct mwl8k_dma_data *tr; /* @@ -730,11 +750,13 @@ static inline void mwl8k_add_dma_header(struct sk_buff *skb) wh = (struct ieee80211_hdr *)skb->data; hdrlen = ieee80211_hdrlen(wh->frame_control); - if (hdrlen != sizeof(*tr)) - skb_push(skb, sizeof(*tr) - hdrlen); + reqd_hdrlen = sizeof(*tr); + + if (hdrlen != reqd_hdrlen) + skb_push(skb, reqd_hdrlen - hdrlen); if (ieee80211_is_data_qos(wh->frame_control)) - hdrlen -= 2; + hdrlen -= IEEE80211_QOS_CTL_LEN; tr = (struct mwl8k_dma_data *)skb->data; if (wh != &tr->wh) @@ -747,9 +769,52 @@ static inline void mwl8k_add_dma_header(struct sk_buff *skb) * payload". That is, everything except for the 802.11 header. * This includes all crypto material including the MIC. */ - tr->fwlen = cpu_to_le16(skb->len - sizeof(*tr)); + tr->fwlen = cpu_to_le16(skb->len - sizeof(*tr) + tail_pad); } +static void mwl8k_encapsulate_tx_frame(struct sk_buff *skb) +{ + struct ieee80211_hdr *wh; + struct ieee80211_tx_info *tx_info; + struct ieee80211_key_conf *key_conf; + int data_pad; + + wh = (struct ieee80211_hdr *)skb->data; + + tx_info = IEEE80211_SKB_CB(skb); + + key_conf = NULL; + if (ieee80211_is_data(wh->frame_control)) + key_conf = tx_info->control.hw_key; + + /* + * Make sure the packet header is in the DMA header format (4-address + * without QoS), the necessary crypto padding between the header and the + * payload has already been provided by mac80211, but it doesn't add tail + * padding when HW crypto is enabled. + * + * We have the following trailer padding requirements: + * - WEP: 4 trailer bytes (ICV) + * - TKIP: 12 trailer bytes (8 MIC + 4 ICV) + * - CCMP: 8 trailer bytes (MIC) + */ + data_pad = 0; + if (key_conf != NULL) { + switch (key_conf->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + data_pad = 4; + break; + case WLAN_CIPHER_SUITE_TKIP: + data_pad = 12; + break; + case WLAN_CIPHER_SUITE_CCMP: + data_pad = 8; + break; + } + } + mwl8k_add_dma_header(skb, data_pad); +} /* * Packet reception for 88w8366 AP firmware. @@ -778,6 +843,13 @@ struct mwl8k_rxd_8366_ap { #define MWL8K_8366_AP_RX_CTRL_OWNED_BY_HOST 0x80 +/* 8366 AP rx_status bits */ +#define MWL8K_8366_AP_RXSTAT_DECRYPT_ERR_MASK 0x80 +#define MWL8K_8366_AP_RXSTAT_GENERAL_DECRYPT_ERR 0xFF +#define MWL8K_8366_AP_RXSTAT_TKIP_DECRYPT_MIC_ERR 0x02 +#define MWL8K_8366_AP_RXSTAT_WEP_DECRYPT_ICV_ERR 0x04 +#define MWL8K_8366_AP_RXSTAT_TKIP_DECRYPT_ICV_ERR 0x08 + static void mwl8k_rxd_8366_ap_init(void *_rxd, dma_addr_t next_dma_addr) { struct mwl8k_rxd_8366_ap *rxd = _rxd; @@ -834,10 +906,16 @@ mwl8k_rxd_8366_ap_process(void *_rxd, struct ieee80211_rx_status *status, } else { status->band = IEEE80211_BAND_2GHZ; } - status->freq = ieee80211_channel_to_frequency(rxd->channel); + status->freq = ieee80211_channel_to_frequency(rxd->channel, + status->band); *qos = rxd->qos_control; + if ((rxd->rx_status != MWL8K_8366_AP_RXSTAT_GENERAL_DECRYPT_ERR) && + (rxd->rx_status & MWL8K_8366_AP_RXSTAT_DECRYPT_ERR_MASK) && + (rxd->rx_status & MWL8K_8366_AP_RXSTAT_TKIP_DECRYPT_MIC_ERR)) + status->flag |= RX_FLAG_MMIC_ERROR; + return le16_to_cpu(rxd->pkt_len); } @@ -876,6 +954,11 @@ struct mwl8k_rxd_sta { #define MWL8K_STA_RATE_INFO_MCS_FORMAT 0x0001 #define MWL8K_STA_RX_CTRL_OWNED_BY_HOST 0x02 +#define MWL8K_STA_RX_CTRL_DECRYPT_ERROR 0x04 +/* ICV=0 or MIC=1 */ +#define MWL8K_STA_RX_CTRL_DEC_ERR_TYPE 0x08 +/* Key is uploaded only in failure case */ +#define MWL8K_STA_RX_CTRL_KEY_INDEX 0x30 static void mwl8k_rxd_sta_init(void *_rxd, dma_addr_t next_dma_addr) { @@ -931,9 +1014,13 @@ mwl8k_rxd_sta_process(void *_rxd, struct ieee80211_rx_status *status, } else { status->band = IEEE80211_BAND_2GHZ; } - status->freq = ieee80211_channel_to_frequency(rxd->channel); + status->freq = ieee80211_channel_to_frequency(rxd->channel, + status->band); *qos = rxd->qos_control; + if ((rxd->rx_ctrl & MWL8K_STA_RX_CTRL_DECRYPT_ERROR) && + (rxd->rx_ctrl & MWL8K_STA_RX_CTRL_DEC_ERR_TYPE)) + status->flag |= RX_FLAG_MMIC_ERROR; return le16_to_cpu(rxd->pkt_len); } @@ -1092,9 +1179,25 @@ static inline void mwl8k_save_beacon(struct ieee80211_hw *hw, ieee80211_queue_work(hw, &priv->finalize_join_worker); } +static inline struct mwl8k_vif *mwl8k_find_vif_bss(struct list_head *vif_list, + u8 *bssid) +{ + struct mwl8k_vif *mwl8k_vif; + + list_for_each_entry(mwl8k_vif, + vif_list, list) { + if (memcmp(bssid, mwl8k_vif->bssid, + ETH_ALEN) == 0) + return mwl8k_vif; + } + + return NULL; +} + static int rxq_process(struct ieee80211_hw *hw, int index, int limit) { struct mwl8k_priv *priv = hw->priv; + struct mwl8k_vif *mwl8k_vif = NULL; struct mwl8k_rx_queue *rxq = priv->rxq + index; int processed; @@ -1104,6 +1207,7 @@ static int rxq_process(struct ieee80211_hw *hw, int index, int limit) void *rxd; int pkt_len; struct ieee80211_rx_status status; + struct ieee80211_hdr *wh; __le16 qos; skb = rxq->buf[rxq->head].skb; @@ -1130,8 +1234,7 @@ static int rxq_process(struct ieee80211_hw *hw, int index, int limit) rxq->rxd_count--; - skb_put(skb, pkt_len); - mwl8k_remove_dma_header(skb, qos); + wh = &((struct mwl8k_dma_data *)skb->data)->wh; /* * Check for a pending join operation. Save a @@ -1141,6 +1244,46 @@ static int rxq_process(struct ieee80211_hw *hw, int index, int limit) if (mwl8k_capture_bssid(priv, (void *)skb->data)) mwl8k_save_beacon(hw, skb); + if (ieee80211_has_protected(wh->frame_control)) { + + /* Check if hw crypto has been enabled for + * this bss. If yes, set the status flags + * accordingly + */ + mwl8k_vif = mwl8k_find_vif_bss(&priv->vif_list, + wh->addr1); + + if (mwl8k_vif != NULL && + mwl8k_vif->is_hw_crypto_enabled == true) { + /* + * When MMIC ERROR is encountered + * by the firmware, payload is + * dropped and only 32 bytes of + * mwl8k Firmware header is sent + * to the host. + * + * We need to add four bytes of + * key information. In it + * MAC80211 expects keyidx set to + * 0 for triggering Counter + * Measure of MMIC failure. + */ + if (status.flag & RX_FLAG_MMIC_ERROR) { + struct mwl8k_dma_data *tr; + tr = (struct mwl8k_dma_data *)skb->data; + memset((void *)&(tr->data), 0, 4); + pkt_len += 4; + } + + if (!ieee80211_is_auth(wh->frame_control)) + status.flag |= RX_FLAG_IV_STRIPPED | + RX_FLAG_DECRYPTED | + RX_FLAG_MMIC_STRIPPED; + } + } + + skb_put(skb, pkt_len); + mwl8k_remove_dma_header(skb, qos); memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status)); ieee80211_rx_irqsafe(hw, skb); @@ -1443,7 +1586,11 @@ mwl8k_txq_xmit(struct ieee80211_hw *hw, int index, struct sk_buff *skb) else qos = 0; - mwl8k_add_dma_header(skb); + if (priv->ap_fw) + mwl8k_encapsulate_tx_frame(skb); + else + mwl8k_add_dma_header(skb, 0); + wh = &((struct mwl8k_dma_data *)skb->data)->wh; tx_info = IEEE80211_SKB_CB(skb); @@ -3099,6 +3246,274 @@ static int mwl8k_cmd_set_new_stn_del(struct ieee80211_hw *hw, } /* + * CMD_UPDATE_ENCRYPTION. + */ + +#define MAX_ENCR_KEY_LENGTH 16 +#define MIC_KEY_LENGTH 8 + +struct mwl8k_cmd_update_encryption { + struct mwl8k_cmd_pkt header; + + __le32 action; + __le32 reserved; + __u8 mac_addr[6]; + __u8 encr_type; + +} __attribute__((packed)); + +struct mwl8k_cmd_set_key { + struct mwl8k_cmd_pkt header; + + __le32 action; + __le32 reserved; + __le16 length; + __le16 key_type_id; + __le32 key_info; + __le32 key_id; + __le16 key_len; + __u8 key_material[MAX_ENCR_KEY_LENGTH]; + __u8 tkip_tx_mic_key[MIC_KEY_LENGTH]; + __u8 tkip_rx_mic_key[MIC_KEY_LENGTH]; + __le16 tkip_rsc_low; + __le32 tkip_rsc_high; + __le16 tkip_tsc_low; + __le32 tkip_tsc_high; + __u8 mac_addr[6]; +} __attribute__((packed)); + +enum { + MWL8K_ENCR_ENABLE, + MWL8K_ENCR_SET_KEY, + MWL8K_ENCR_REMOVE_KEY, + MWL8K_ENCR_SET_GROUP_KEY, +}; + +#define MWL8K_UPDATE_ENCRYPTION_TYPE_WEP 0 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_DISABLE 1 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_TKIP 4 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_MIXED 7 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_AES 8 + +enum { + MWL8K_ALG_WEP, + MWL8K_ALG_TKIP, + MWL8K_ALG_CCMP, +}; + +#define MWL8K_KEY_FLAG_TXGROUPKEY 0x00000004 +#define MWL8K_KEY_FLAG_PAIRWISE 0x00000008 +#define MWL8K_KEY_FLAG_TSC_VALID 0x00000040 +#define MWL8K_KEY_FLAG_WEP_TXKEY 0x01000000 +#define MWL8K_KEY_FLAG_MICKEY_VALID 0x02000000 + +static int mwl8k_cmd_update_encryption_enable(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 *addr, + u8 encr_type) +{ + struct mwl8k_cmd_update_encryption *cmd; + int rc; + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + cmd->header.code = cpu_to_le16(MWL8K_CMD_UPDATE_ENCRYPTION); + cmd->header.length = cpu_to_le16(sizeof(*cmd)); + cmd->action = cpu_to_le32(MWL8K_ENCR_ENABLE); + memcpy(cmd->mac_addr, addr, ETH_ALEN); + cmd->encr_type = encr_type; + + rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); + kfree(cmd); + + return rc; +} + +static int mwl8k_encryption_set_cmd_info(struct mwl8k_cmd_set_key *cmd, + u8 *addr, + struct ieee80211_key_conf *key) +{ + cmd->header.code = cpu_to_le16(MWL8K_CMD_UPDATE_ENCRYPTION); + cmd->header.length = cpu_to_le16(sizeof(*cmd)); + cmd->length = cpu_to_le16(sizeof(*cmd) - + offsetof(struct mwl8k_cmd_set_key, length)); + cmd->key_id = cpu_to_le32(key->keyidx); + cmd->key_len = cpu_to_le16(key->keylen); + memcpy(cmd->mac_addr, addr, ETH_ALEN); + + switch (key->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + cmd->key_type_id = cpu_to_le16(MWL8K_ALG_WEP); + if (key->keyidx == 0) + cmd->key_info = cpu_to_le32(MWL8K_KEY_FLAG_WEP_TXKEY); + + break; + case WLAN_CIPHER_SUITE_TKIP: + cmd->key_type_id = cpu_to_le16(MWL8K_ALG_TKIP); + cmd->key_info = (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) + ? cpu_to_le32(MWL8K_KEY_FLAG_PAIRWISE) + : cpu_to_le32(MWL8K_KEY_FLAG_TXGROUPKEY); + cmd->key_info |= cpu_to_le32(MWL8K_KEY_FLAG_MICKEY_VALID + | MWL8K_KEY_FLAG_TSC_VALID); + break; + case WLAN_CIPHER_SUITE_CCMP: + cmd->key_type_id = cpu_to_le16(MWL8K_ALG_CCMP); + cmd->key_info = (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) + ? cpu_to_le32(MWL8K_KEY_FLAG_PAIRWISE) + : cpu_to_le32(MWL8K_KEY_FLAG_TXGROUPKEY); + break; + default: + return -ENOTSUPP; + } + + return 0; +} + +static int mwl8k_cmd_encryption_set_key(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 *addr, + struct ieee80211_key_conf *key) +{ + struct mwl8k_cmd_set_key *cmd; + int rc; + int keymlen; + u32 action; + u8 idx; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + rc = mwl8k_encryption_set_cmd_info(cmd, addr, key); + if (rc < 0) + goto done; + + idx = key->keyidx; + + if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) + action = MWL8K_ENCR_SET_KEY; + else + action = MWL8K_ENCR_SET_GROUP_KEY; + + switch (key->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + if (!mwl8k_vif->wep_key_conf[idx].enabled) { + memcpy(mwl8k_vif->wep_key_conf[idx].key, key, + sizeof(*key) + key->keylen); + mwl8k_vif->wep_key_conf[idx].enabled = 1; + } + + keymlen = 0; + action = MWL8K_ENCR_SET_KEY; + break; + case WLAN_CIPHER_SUITE_TKIP: + keymlen = MAX_ENCR_KEY_LENGTH + 2 * MIC_KEY_LENGTH; + break; + case WLAN_CIPHER_SUITE_CCMP: + keymlen = key->keylen; + break; + default: + rc = -ENOTSUPP; + goto done; + } + + memcpy(cmd->key_material, key->key, keymlen); + cmd->action = cpu_to_le32(action); + + rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); +done: + kfree(cmd); + + return rc; +} + +static int mwl8k_cmd_encryption_remove_key(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 *addr, + struct ieee80211_key_conf *key) +{ + struct mwl8k_cmd_set_key *cmd; + int rc; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + rc = mwl8k_encryption_set_cmd_info(cmd, addr, key); + if (rc < 0) + goto done; + + if (key->cipher == WLAN_CIPHER_SUITE_WEP40 || + WLAN_CIPHER_SUITE_WEP104) + mwl8k_vif->wep_key_conf[key->keyidx].enabled = 0; + + cmd->action = cpu_to_le32(MWL8K_ENCR_REMOVE_KEY); + + rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); +done: + kfree(cmd); + + return rc; +} + +static int mwl8k_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd_param, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) +{ + int rc = 0; + u8 encr_type; + u8 *addr; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + + if (vif->type == NL80211_IFTYPE_STATION) + return -EOPNOTSUPP; + + if (sta == NULL) + addr = hw->wiphy->perm_addr; + else + addr = sta->addr; + + if (cmd_param == SET_KEY) { + key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV; + rc = mwl8k_cmd_encryption_set_key(hw, vif, addr, key); + if (rc) + goto out; + + if ((key->cipher == WLAN_CIPHER_SUITE_WEP40) + || (key->cipher == WLAN_CIPHER_SUITE_WEP104)) + encr_type = MWL8K_UPDATE_ENCRYPTION_TYPE_WEP; + else + encr_type = MWL8K_UPDATE_ENCRYPTION_TYPE_MIXED; + + rc = mwl8k_cmd_update_encryption_enable(hw, vif, addr, + encr_type); + if (rc) + goto out; + + mwl8k_vif->is_hw_crypto_enabled = true; + + } else { + rc = mwl8k_cmd_encryption_remove_key(hw, vif, addr, key); + + if (rc) + goto out; + + mwl8k_vif->is_hw_crypto_enabled = false; + + } +out: + return rc; +} + +/* * CMD_UPDATE_STADB. */ struct ewc_ht_info { @@ -3469,6 +3884,8 @@ static int mwl8k_add_interface(struct ieee80211_hw *hw, mwl8k_vif->vif = vif; mwl8k_vif->macid = macid; mwl8k_vif->seqno = 0; + memcpy(mwl8k_vif->bssid, vif->addr, ETH_ALEN); + mwl8k_vif->is_hw_crypto_enabled = false; /* Set the mac address. */ mwl8k_cmd_set_mac_addr(hw, vif, vif->addr); @@ -3866,18 +4283,27 @@ static int mwl8k_sta_add(struct ieee80211_hw *hw, { struct mwl8k_priv *priv = hw->priv; int ret; + int i; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + struct ieee80211_key_conf *key; if (!priv->ap_fw) { ret = mwl8k_cmd_update_stadb_add(hw, vif, sta); if (ret >= 0) { MWL8K_STA(sta)->peer_id = ret; - return 0; + ret = 0; } - return ret; + } else { + ret = mwl8k_cmd_set_new_stn_add(hw, vif, sta); } - return mwl8k_cmd_set_new_stn_add(hw, vif, sta); + for (i = 0; i < NUM_WEP_KEYS; i++) { + key = IEEE80211_KEY_CONF(mwl8k_vif->wep_key_conf[i].key); + if (mwl8k_vif->wep_key_conf[i].enabled) + mwl8k_set_key(hw, SET_KEY, vif, sta, key); + } + return ret; } static int mwl8k_conf_tx(struct ieee80211_hw *hw, u16 queue, @@ -3932,7 +4358,8 @@ static int mwl8k_get_survey(struct ieee80211_hw *hw, int idx, static int mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { switch (action) { case IEEE80211_AMPDU_RX_START: @@ -3955,6 +4382,7 @@ static const struct ieee80211_ops mwl8k_ops = { .bss_info_changed = mwl8k_bss_info_changed, .prepare_multicast = mwl8k_prepare_multicast, .configure_filter = mwl8k_configure_filter, + .set_key = mwl8k_set_key, .set_rts_threshold = mwl8k_set_rts_threshold, .sta_add = mwl8k_sta_add, .sta_remove = mwl8k_sta_remove, diff --git a/drivers/net/wireless/rt2x00/rt2400pci.c b/drivers/net/wireless/rt2x00/rt2400pci.c index 54ca49a..2725f3c 100644 --- a/drivers/net/wireless/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/rt2x00/rt2400pci.c @@ -46,7 +46,7 @@ * These indirect registers work with busy bits, * and we will try maximal REGISTER_BUSY_COUNT times to access * the register while taking a REGISTER_BUSY_DELAY us delay - * between each attampt. When the busy bit is still set at that time, + * between each attempt. When the busy bit is still set at that time, * the access attempt is considered to have failed, * and we will print an error. */ @@ -305,9 +305,7 @@ static void rt2400pci_config_intf(struct rt2x00_dev *rt2x00dev, * Enable synchronisation. */ rt2x00pci_register_read(rt2x00dev, CSR14, ®); - rt2x00_set_field32(®, CSR14_TSF_COUNT, 1); rt2x00_set_field32(®, CSR14_TSF_SYNC, conf->sync); - rt2x00_set_field32(®, CSR14_TBCN, 1); rt2x00pci_register_write(rt2x00dev, CSR14, reg); } @@ -647,6 +645,11 @@ static void rt2400pci_start_queue(struct data_queue *queue) rt2x00pci_register_write(rt2x00dev, RXCSR0, reg); break; case QID_BEACON: + /* + * Allow the tbtt tasklet to be scheduled. + */ + tasklet_enable(&rt2x00dev->tbtt_tasklet); + rt2x00pci_register_read(rt2x00dev, CSR14, ®); rt2x00_set_field32(®, CSR14_TSF_COUNT, 1); rt2x00_set_field32(®, CSR14_TBCN, 1); @@ -708,6 +711,11 @@ static void rt2400pci_stop_queue(struct data_queue *queue) rt2x00_set_field32(®, CSR14_TBCN, 0); rt2x00_set_field32(®, CSR14_BEACON_GEN, 0); rt2x00pci_register_write(rt2x00dev, CSR14, reg); + + /* + * Wait for possibly running tbtt tasklets. + */ + tasklet_disable(&rt2x00dev->tbtt_tasklet); break; default: break; @@ -963,9 +971,9 @@ static int rt2400pci_init_bbp(struct rt2x00_dev *rt2x00dev) static void rt2400pci_toggle_irq(struct rt2x00_dev *rt2x00dev, enum dev_state state) { - int mask = (state == STATE_RADIO_IRQ_OFF) || - (state == STATE_RADIO_IRQ_OFF_ISR); + int mask = (state == STATE_RADIO_IRQ_OFF); u32 reg; + unsigned long flags; /* * When interrupts are being enabled, the interrupt registers @@ -974,12 +982,20 @@ static void rt2400pci_toggle_irq(struct rt2x00_dev *rt2x00dev, if (state == STATE_RADIO_IRQ_ON) { rt2x00pci_register_read(rt2x00dev, CSR7, ®); rt2x00pci_register_write(rt2x00dev, CSR7, reg); + + /* + * Enable tasklets. + */ + tasklet_enable(&rt2x00dev->txstatus_tasklet); + tasklet_enable(&rt2x00dev->rxdone_tasklet); } /* * Only toggle the interrupts bits we are going to use. * Non-checked interrupt bits are disabled by default. */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + rt2x00pci_register_read(rt2x00dev, CSR8, ®); rt2x00_set_field32(®, CSR8_TBCN_EXPIRE, mask); rt2x00_set_field32(®, CSR8_TXDONE_TXRING, mask); @@ -987,6 +1003,17 @@ static void rt2400pci_toggle_irq(struct rt2x00_dev *rt2x00dev, rt2x00_set_field32(®, CSR8_TXDONE_PRIORING, mask); rt2x00_set_field32(®, CSR8_RXDONE, mask); rt2x00pci_register_write(rt2x00dev, CSR8, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + if (state == STATE_RADIO_IRQ_OFF) { + /* + * Ensure that all tasklets are finished before + * disabling the interrupts. + */ + tasklet_disable(&rt2x00dev->txstatus_tasklet); + tasklet_disable(&rt2x00dev->rxdone_tasklet); + } } static int rt2400pci_enable_radio(struct rt2x00_dev *rt2x00dev) @@ -1059,9 +1086,7 @@ static int rt2400pci_set_device_state(struct rt2x00_dev *rt2x00dev, rt2400pci_disable_radio(rt2x00dev); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: rt2400pci_toggle_irq(rt2x00dev, state); break; case STATE_DEEP_SLEEP: @@ -1183,8 +1208,6 @@ static void rt2400pci_write_beacon(struct queue_entry *entry, /* * Enable beaconing again. */ - rt2x00_set_field32(®, CSR14_TSF_COUNT, 1); - rt2x00_set_field32(®, CSR14_TBCN, 1); rt2x00_set_field32(®, CSR14_BEACON_GEN, 1); rt2x00pci_register_write(rt2x00dev, CSR14, reg); } @@ -1289,57 +1312,71 @@ static void rt2400pci_txdone(struct rt2x00_dev *rt2x00dev, } } -static irqreturn_t rt2400pci_interrupt_thread(int irq, void *dev_instance) +static void rt2400pci_enable_interrupt(struct rt2x00_dev *rt2x00dev, + struct rt2x00_field32 irq_field) { - struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg = rt2x00dev->irqvalue[0]; + unsigned long flags; + u32 reg; /* - * Handle interrupts, walk through all bits - * and run the tasks, the bits are checked in order of - * priority. + * Enable a single interrupt. The interrupt mask register + * access needs locking. */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); - /* - * 1 - Beacon timer expired interrupt. - */ - if (rt2x00_get_field32(reg, CSR7_TBCN_EXPIRE)) - rt2x00lib_beacondone(rt2x00dev); + rt2x00pci_register_read(rt2x00dev, CSR8, ®); + rt2x00_set_field32(®, irq_field, 0); + rt2x00pci_register_write(rt2x00dev, CSR8, reg); - /* - * 2 - Rx ring done interrupt. - */ - if (rt2x00_get_field32(reg, CSR7_RXDONE)) - rt2x00pci_rxdone(rt2x00dev); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} - /* - * 3 - Atim ring transmit done interrupt. - */ - if (rt2x00_get_field32(reg, CSR7_TXDONE_ATIMRING)) - rt2400pci_txdone(rt2x00dev, QID_ATIM); +static void rt2400pci_txstatus_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + u32 reg; + unsigned long flags; /* - * 4 - Priority ring transmit done interrupt. + * Handle all tx queues. */ - if (rt2x00_get_field32(reg, CSR7_TXDONE_PRIORING)) - rt2400pci_txdone(rt2x00dev, QID_AC_VO); + rt2400pci_txdone(rt2x00dev, QID_ATIM); + rt2400pci_txdone(rt2x00dev, QID_AC_VO); + rt2400pci_txdone(rt2x00dev, QID_AC_VI); /* - * 5 - Tx ring transmit done interrupt. + * Enable all TXDONE interrupts again. */ - if (rt2x00_get_field32(reg, CSR7_TXDONE_TXRING)) - rt2400pci_txdone(rt2x00dev, QID_AC_VI); + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); - /* Enable interrupts again. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_ON_ISR); - return IRQ_HANDLED; + rt2x00pci_register_read(rt2x00dev, CSR8, ®); + rt2x00_set_field32(®, CSR8_TXDONE_TXRING, 0); + rt2x00_set_field32(®, CSR8_TXDONE_ATIMRING, 0); + rt2x00_set_field32(®, CSR8_TXDONE_PRIORING, 0); + rt2x00pci_register_write(rt2x00dev, CSR8, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} + +static void rt2400pci_tbtt_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00lib_beacondone(rt2x00dev); + rt2400pci_enable_interrupt(rt2x00dev, CSR8_TBCN_EXPIRE); +} + +static void rt2400pci_rxdone_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00pci_rxdone(rt2x00dev); + rt2400pci_enable_interrupt(rt2x00dev, CSR8_RXDONE); } static irqreturn_t rt2400pci_interrupt(int irq, void *dev_instance) { struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg; + u32 reg, mask; + unsigned long flags; /* * Get the interrupt sources & saved to local variable. @@ -1354,14 +1391,44 @@ static irqreturn_t rt2400pci_interrupt(int irq, void *dev_instance) if (!test_bit(DEVICE_STATE_ENABLED_RADIO, &rt2x00dev->flags)) return IRQ_HANDLED; - /* Store irqvalues for use in the interrupt thread. */ - rt2x00dev->irqvalue[0] = reg; + mask = reg; - /* Disable interrupts, will be enabled again in the interrupt thread. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_OFF_ISR); + /* + * Schedule tasklets for interrupt handling. + */ + if (rt2x00_get_field32(reg, CSR7_TBCN_EXPIRE)) + tasklet_hi_schedule(&rt2x00dev->tbtt_tasklet); - return IRQ_WAKE_THREAD; + if (rt2x00_get_field32(reg, CSR7_RXDONE)) + tasklet_schedule(&rt2x00dev->rxdone_tasklet); + + if (rt2x00_get_field32(reg, CSR7_TXDONE_ATIMRING) || + rt2x00_get_field32(reg, CSR7_TXDONE_PRIORING) || + rt2x00_get_field32(reg, CSR7_TXDONE_TXRING)) { + tasklet_schedule(&rt2x00dev->txstatus_tasklet); + /* + * Mask out all txdone interrupts. + */ + rt2x00_set_field32(&mask, CSR8_TXDONE_TXRING, 1); + rt2x00_set_field32(&mask, CSR8_TXDONE_ATIMRING, 1); + rt2x00_set_field32(&mask, CSR8_TXDONE_PRIORING, 1); + } + + /* + * Disable all interrupts for which a tasklet was scheduled right now, + * the tasklet will reenable the appropriate interrupts. + */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + + rt2x00pci_register_read(rt2x00dev, CSR8, ®); + reg |= mask; + rt2x00pci_register_write(rt2x00dev, CSR8, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + + + return IRQ_HANDLED; } /* @@ -1655,7 +1722,9 @@ static const struct ieee80211_ops rt2400pci_mac80211_ops = { static const struct rt2x00lib_ops rt2400pci_rt2x00_ops = { .irq_handler = rt2400pci_interrupt, - .irq_handler_thread = rt2400pci_interrupt_thread, + .txstatus_tasklet = rt2400pci_txstatus_tasklet, + .tbtt_tasklet = rt2400pci_tbtt_tasklet, + .rxdone_tasklet = rt2400pci_rxdone_tasklet, .probe_hw = rt2400pci_probe_hw, .initialize = rt2x00pci_initialize, .uninitialize = rt2x00pci_uninitialize, diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c index a9ff26a..3ef1fb4 100644 --- a/drivers/net/wireless/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/rt2x00/rt2500pci.c @@ -311,9 +311,7 @@ static void rt2500pci_config_intf(struct rt2x00_dev *rt2x00dev, * Enable synchronisation. */ rt2x00pci_register_read(rt2x00dev, CSR14, ®); - rt2x00_set_field32(®, CSR14_TSF_COUNT, 1); rt2x00_set_field32(®, CSR14_TSF_SYNC, conf->sync); - rt2x00_set_field32(®, CSR14_TBCN, 1); rt2x00pci_register_write(rt2x00dev, CSR14, reg); } @@ -737,6 +735,11 @@ static void rt2500pci_start_queue(struct data_queue *queue) rt2x00pci_register_write(rt2x00dev, RXCSR0, reg); break; case QID_BEACON: + /* + * Allow the tbtt tasklet to be scheduled. + */ + tasklet_enable(&rt2x00dev->tbtt_tasklet); + rt2x00pci_register_read(rt2x00dev, CSR14, ®); rt2x00_set_field32(®, CSR14_TSF_COUNT, 1); rt2x00_set_field32(®, CSR14_TBCN, 1); @@ -798,6 +801,11 @@ static void rt2500pci_stop_queue(struct data_queue *queue) rt2x00_set_field32(®, CSR14_TBCN, 0); rt2x00_set_field32(®, CSR14_BEACON_GEN, 0); rt2x00pci_register_write(rt2x00dev, CSR14, reg); + + /* + * Wait for possibly running tbtt tasklets. + */ + tasklet_disable(&rt2x00dev->tbtt_tasklet); break; default: break; @@ -1118,9 +1126,9 @@ static int rt2500pci_init_bbp(struct rt2x00_dev *rt2x00dev) static void rt2500pci_toggle_irq(struct rt2x00_dev *rt2x00dev, enum dev_state state) { - int mask = (state == STATE_RADIO_IRQ_OFF) || - (state == STATE_RADIO_IRQ_OFF_ISR); + int mask = (state == STATE_RADIO_IRQ_OFF); u32 reg; + unsigned long flags; /* * When interrupts are being enabled, the interrupt registers @@ -1129,12 +1137,20 @@ static void rt2500pci_toggle_irq(struct rt2x00_dev *rt2x00dev, if (state == STATE_RADIO_IRQ_ON) { rt2x00pci_register_read(rt2x00dev, CSR7, ®); rt2x00pci_register_write(rt2x00dev, CSR7, reg); + + /* + * Enable tasklets. + */ + tasklet_enable(&rt2x00dev->txstatus_tasklet); + tasklet_enable(&rt2x00dev->rxdone_tasklet); } /* * Only toggle the interrupts bits we are going to use. * Non-checked interrupt bits are disabled by default. */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + rt2x00pci_register_read(rt2x00dev, CSR8, ®); rt2x00_set_field32(®, CSR8_TBCN_EXPIRE, mask); rt2x00_set_field32(®, CSR8_TXDONE_TXRING, mask); @@ -1142,6 +1158,16 @@ static void rt2500pci_toggle_irq(struct rt2x00_dev *rt2x00dev, rt2x00_set_field32(®, CSR8_TXDONE_PRIORING, mask); rt2x00_set_field32(®, CSR8_RXDONE, mask); rt2x00pci_register_write(rt2x00dev, CSR8, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + if (state == STATE_RADIO_IRQ_OFF) { + /* + * Ensure that all tasklets are finished. + */ + tasklet_disable(&rt2x00dev->txstatus_tasklet); + tasklet_disable(&rt2x00dev->rxdone_tasklet); + } } static int rt2500pci_enable_radio(struct rt2x00_dev *rt2x00dev) @@ -1214,9 +1240,7 @@ static int rt2500pci_set_device_state(struct rt2x00_dev *rt2x00dev, rt2500pci_disable_radio(rt2x00dev); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: rt2500pci_toggle_irq(rt2x00dev, state); break; case STATE_DEEP_SLEEP: @@ -1337,8 +1361,6 @@ static void rt2500pci_write_beacon(struct queue_entry *entry, /* * Enable beaconing again. */ - rt2x00_set_field32(®, CSR14_TSF_COUNT, 1); - rt2x00_set_field32(®, CSR14_TBCN, 1); rt2x00_set_field32(®, CSR14_BEACON_GEN, 1); rt2x00pci_register_write(rt2x00dev, CSR14, reg); } @@ -1422,58 +1444,71 @@ static void rt2500pci_txdone(struct rt2x00_dev *rt2x00dev, } } -static irqreturn_t rt2500pci_interrupt_thread(int irq, void *dev_instance) +static void rt2500pci_enable_interrupt(struct rt2x00_dev *rt2x00dev, + struct rt2x00_field32 irq_field) { - struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg = rt2x00dev->irqvalue[0]; + unsigned long flags; + u32 reg; /* - * Handle interrupts, walk through all bits - * and run the tasks, the bits are checked in order of - * priority. + * Enable a single interrupt. The interrupt mask register + * access needs locking. */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); - /* - * 1 - Beacon timer expired interrupt. - */ - if (rt2x00_get_field32(reg, CSR7_TBCN_EXPIRE)) - rt2x00lib_beacondone(rt2x00dev); + rt2x00pci_register_read(rt2x00dev, CSR8, ®); + rt2x00_set_field32(®, irq_field, 0); + rt2x00pci_register_write(rt2x00dev, CSR8, reg); - /* - * 2 - Rx ring done interrupt. - */ - if (rt2x00_get_field32(reg, CSR7_RXDONE)) - rt2x00pci_rxdone(rt2x00dev); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} - /* - * 3 - Atim ring transmit done interrupt. - */ - if (rt2x00_get_field32(reg, CSR7_TXDONE_ATIMRING)) - rt2500pci_txdone(rt2x00dev, QID_ATIM); +static void rt2500pci_txstatus_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + u32 reg; + unsigned long flags; /* - * 4 - Priority ring transmit done interrupt. + * Handle all tx queues. */ - if (rt2x00_get_field32(reg, CSR7_TXDONE_PRIORING)) - rt2500pci_txdone(rt2x00dev, QID_AC_VO); + rt2500pci_txdone(rt2x00dev, QID_ATIM); + rt2500pci_txdone(rt2x00dev, QID_AC_VO); + rt2500pci_txdone(rt2x00dev, QID_AC_VI); /* - * 5 - Tx ring transmit done interrupt. + * Enable all TXDONE interrupts again. */ - if (rt2x00_get_field32(reg, CSR7_TXDONE_TXRING)) - rt2500pci_txdone(rt2x00dev, QID_AC_VI); + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + + rt2x00pci_register_read(rt2x00dev, CSR8, ®); + rt2x00_set_field32(®, CSR8_TXDONE_TXRING, 0); + rt2x00_set_field32(®, CSR8_TXDONE_ATIMRING, 0); + rt2x00_set_field32(®, CSR8_TXDONE_PRIORING, 0); + rt2x00pci_register_write(rt2x00dev, CSR8, reg); - /* Enable interrupts again. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_ON_ISR); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} - return IRQ_HANDLED; +static void rt2500pci_tbtt_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00lib_beacondone(rt2x00dev); + rt2500pci_enable_interrupt(rt2x00dev, CSR8_TBCN_EXPIRE); +} + +static void rt2500pci_rxdone_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00pci_rxdone(rt2x00dev); + rt2500pci_enable_interrupt(rt2x00dev, CSR8_RXDONE); } static irqreturn_t rt2500pci_interrupt(int irq, void *dev_instance) { struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg; + u32 reg, mask; + unsigned long flags; /* * Get the interrupt sources & saved to local variable. @@ -1488,14 +1523,42 @@ static irqreturn_t rt2500pci_interrupt(int irq, void *dev_instance) if (!test_bit(DEVICE_STATE_ENABLED_RADIO, &rt2x00dev->flags)) return IRQ_HANDLED; - /* Store irqvalues for use in the interrupt thread. */ - rt2x00dev->irqvalue[0] = reg; + mask = reg; - /* Disable interrupts, will be enabled again in the interrupt thread. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_OFF_ISR); + /* + * Schedule tasklets for interrupt handling. + */ + if (rt2x00_get_field32(reg, CSR7_TBCN_EXPIRE)) + tasklet_hi_schedule(&rt2x00dev->tbtt_tasklet); - return IRQ_WAKE_THREAD; + if (rt2x00_get_field32(reg, CSR7_RXDONE)) + tasklet_schedule(&rt2x00dev->rxdone_tasklet); + + if (rt2x00_get_field32(reg, CSR7_TXDONE_ATIMRING) || + rt2x00_get_field32(reg, CSR7_TXDONE_PRIORING) || + rt2x00_get_field32(reg, CSR7_TXDONE_TXRING)) { + tasklet_schedule(&rt2x00dev->txstatus_tasklet); + /* + * Mask out all txdone interrupts. + */ + rt2x00_set_field32(&mask, CSR8_TXDONE_TXRING, 1); + rt2x00_set_field32(&mask, CSR8_TXDONE_ATIMRING, 1); + rt2x00_set_field32(&mask, CSR8_TXDONE_PRIORING, 1); + } + + /* + * Disable all interrupts for which a tasklet was scheduled right now, + * the tasklet will reenable the appropriate interrupts. + */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + + rt2x00pci_register_read(rt2x00dev, CSR8, ®); + reg |= mask; + rt2x00pci_register_write(rt2x00dev, CSR8, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + return IRQ_HANDLED; } /* @@ -1952,7 +2015,9 @@ static const struct ieee80211_ops rt2500pci_mac80211_ops = { static const struct rt2x00lib_ops rt2500pci_rt2x00_ops = { .irq_handler = rt2500pci_interrupt, - .irq_handler_thread = rt2500pci_interrupt_thread, + .txstatus_tasklet = rt2500pci_txstatus_tasklet, + .tbtt_tasklet = rt2500pci_tbtt_tasklet, + .rxdone_tasklet = rt2500pci_rxdone_tasklet, .probe_hw = rt2500pci_probe_hw, .initialize = rt2x00pci_initialize, .uninitialize = rt2x00pci_uninitialize, diff --git a/drivers/net/wireless/rt2x00/rt2500usb.c b/drivers/net/wireless/rt2x00/rt2500usb.c index 6b3b1de4..01f385d 100644 --- a/drivers/net/wireless/rt2x00/rt2500usb.c +++ b/drivers/net/wireless/rt2x00/rt2500usb.c @@ -478,9 +478,7 @@ static void rt2500usb_config_intf(struct rt2x00_dev *rt2x00dev, rt2500usb_register_write(rt2x00dev, TXRX_CSR18, reg); rt2500usb_register_read(rt2x00dev, TXRX_CSR19, ®); - rt2x00_set_field16(®, TXRX_CSR19_TSF_COUNT, 1); rt2x00_set_field16(®, TXRX_CSR19_TSF_SYNC, conf->sync); - rt2x00_set_field16(®, TXRX_CSR19_TBCN, 1); rt2500usb_register_write(rt2x00dev, TXRX_CSR19, reg); } @@ -1056,9 +1054,7 @@ static int rt2500usb_set_device_state(struct rt2x00_dev *rt2x00dev, rt2500usb_disable_radio(rt2x00dev); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: /* No support, but no error either */ break; case STATE_DEEP_SLEEP: diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h index 4c55e85..ec8159c 100644 --- a/drivers/net/wireless/rt2x00/rt2800.h +++ b/drivers/net/wireless/rt2x00/rt2800.h @@ -372,8 +372,12 @@ /* * US_CYC_CNT + * BT_MODE_EN: Bluetooth mode enable + * CLOCK CYCLE: Clock cycle count in 1us. + * PCI:0x21, PCIE:0x7d, USB:0x1e */ #define US_CYC_CNT 0x02a4 +#define US_CYC_CNT_BT_MODE_EN FIELD32(0x00000100) #define US_CYC_CNT_CLOCK_CYCLE FIELD32(0x000000ff) /* @@ -1805,6 +1809,12 @@ struct mac_iveiv_entry { #define RFCSR30_RF_CALIBRATION FIELD8(0x80) /* + * RFCSR 31: + */ +#define RFCSR31_RX_AGC_FC FIELD8(0x1f) +#define RFCSR31_RX_H20M FIELD8(0x20) + +/* * RF registers */ diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 54917a2..c9bf074 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -818,8 +818,6 @@ void rt2800_write_beacon(struct queue_entry *entry, struct txentry_desc *txdesc) /* * Enable beaconing again. */ - rt2x00_set_field32(®, BCN_TIME_CFG_TSF_TICKING, 1); - rt2x00_set_field32(®, BCN_TIME_CFG_TBTT_ENABLE, 1); rt2x00_set_field32(®, BCN_TIME_CFG_BEACON_GEN, 1); rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg); @@ -831,8 +829,8 @@ void rt2800_write_beacon(struct queue_entry *entry, struct txentry_desc *txdesc) } EXPORT_SYMBOL_GPL(rt2800_write_beacon); -static inline void rt2800_clear_beacon(struct rt2x00_dev *rt2x00dev, - unsigned int beacon_base) +static inline void rt2800_clear_beacon_register(struct rt2x00_dev *rt2x00dev, + unsigned int beacon_base) { int i; @@ -845,6 +843,33 @@ static inline void rt2800_clear_beacon(struct rt2x00_dev *rt2x00dev, rt2800_register_write(rt2x00dev, beacon_base + i, 0); } +void rt2800_clear_beacon(struct queue_entry *entry) +{ + struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev; + u32 reg; + + /* + * Disable beaconing while we are reloading the beacon data, + * otherwise we might be sending out invalid data. + */ + rt2800_register_read(rt2x00dev, BCN_TIME_CFG, ®); + rt2x00_set_field32(®, BCN_TIME_CFG_BEACON_GEN, 0); + rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg); + + /* + * Clear beacon. + */ + rt2800_clear_beacon_register(rt2x00dev, + HW_BEACON_OFFSET(entry->entry_idx)); + + /* + * Enabled beaconing again. + */ + rt2x00_set_field32(®, BCN_TIME_CFG_BEACON_GEN, 1); + rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg); +} +EXPORT_SYMBOL_GPL(rt2800_clear_beacon); + #ifdef CONFIG_RT2X00_LIB_DEBUGFS const struct rt2x00debug rt2800_rt2x00debug = { .owner = THIS_MODULE, @@ -1005,7 +1030,7 @@ static void rt2800_config_wcid_attr(struct rt2x00_dev *rt2x00dev, memset(&wcid_entry, 0, sizeof(wcid_entry)); if (crypto->cmd == SET_KEY) - memcpy(&wcid_entry, crypto->address, ETH_ALEN); + memcpy(wcid_entry.mac, crypto->address, ETH_ALEN); rt2800_register_multiwrite(rt2x00dev, offset, &wcid_entry, sizeof(wcid_entry)); } @@ -1155,29 +1180,11 @@ void rt2800_config_intf(struct rt2x00_dev *rt2x00dev, struct rt2x00_intf *intf, if (flags & CONFIG_UPDATE_TYPE) { /* - * Clear current synchronisation setup. - */ - rt2800_clear_beacon(rt2x00dev, - HW_BEACON_OFFSET(intf->beacon->entry_idx)); - /* * Enable synchronisation. */ rt2800_register_read(rt2x00dev, BCN_TIME_CFG, ®); - rt2x00_set_field32(®, BCN_TIME_CFG_TSF_TICKING, 1); rt2x00_set_field32(®, BCN_TIME_CFG_TSF_SYNC, conf->sync); - rt2x00_set_field32(®, BCN_TIME_CFG_TBTT_ENABLE, - (conf->sync == TSF_SYNC_ADHOC || - conf->sync == TSF_SYNC_AP_NONE)); rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg); - - /* - * Enable pre tbtt interrupt for beaconing modes - */ - rt2800_register_read(rt2x00dev, INT_TIMER_EN, ®); - rt2x00_set_field32(®, INT_TIMER_EN_PRE_TBTT_TIMER, - (conf->sync == TSF_SYNC_AP_NONE)); - rt2800_register_write(rt2x00dev, INT_TIMER_EN, reg); - } if (flags & CONFIG_UPDATE_MAC) { @@ -2187,19 +2194,23 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev) /* * Clear all beacons */ - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE0); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE1); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE2); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE3); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE4); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE5); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE6); - rt2800_clear_beacon(rt2x00dev, HW_BEACON_BASE7); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE0); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE1); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE2); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE3); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE4); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE5); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE6); + rt2800_clear_beacon_register(rt2x00dev, HW_BEACON_BASE7); if (rt2x00_is_usb(rt2x00dev)) { rt2800_register_read(rt2x00dev, US_CYC_CNT, ®); rt2x00_set_field32(®, US_CYC_CNT_CLOCK_CYCLE, 30); rt2800_register_write(rt2x00dev, US_CYC_CNT, reg); + } else if (rt2x00_is_pcie(rt2x00dev)) { + rt2800_register_read(rt2x00dev, US_CYC_CNT, ®); + rt2x00_set_field32(®, US_CYC_CNT_CLOCK_CYCLE, 125); + rt2800_register_write(rt2x00dev, US_CYC_CNT, reg); } rt2800_register_read(rt2x00dev, HT_FBK_CFG0, ®); @@ -2436,6 +2447,10 @@ static u8 rt2800_init_rx_filter(struct rt2x00_dev *rt2x00dev, rt2x00_set_field8(&bbp, BBP4_BANDWIDTH, 2 * bw40); rt2800_bbp_write(rt2x00dev, 4, bbp); + rt2800_rfcsr_read(rt2x00dev, 31, &rfcsr); + rt2x00_set_field8(&rfcsr, RFCSR31_RX_H20M, bw40); + rt2800_rfcsr_write(rt2x00dev, 31, rfcsr); + rt2800_rfcsr_read(rt2x00dev, 22, &rfcsr); rt2x00_set_field8(&rfcsr, RFCSR22_BASEBAND_LOOPBACK, 1); rt2800_rfcsr_write(rt2x00dev, 22, rfcsr); @@ -2510,7 +2525,7 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_write(rt2x00dev, 4, 0x40); rt2800_rfcsr_write(rt2x00dev, 5, 0x03); rt2800_rfcsr_write(rt2x00dev, 6, 0x02); - rt2800_rfcsr_write(rt2x00dev, 7, 0x70); + rt2800_rfcsr_write(rt2x00dev, 7, 0x60); rt2800_rfcsr_write(rt2x00dev, 9, 0x0f); rt2800_rfcsr_write(rt2x00dev, 10, 0x41); rt2800_rfcsr_write(rt2x00dev, 11, 0x21); @@ -2602,12 +2617,12 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_register_write(rt2x00dev, LDO_CFG0, reg); } else if (rt2x00_rt(rt2x00dev, RT3071) || rt2x00_rt(rt2x00dev, RT3090)) { + rt2800_rfcsr_write(rt2x00dev, 31, 0x14); + rt2800_rfcsr_read(rt2x00dev, 6, &rfcsr); rt2x00_set_field8(&rfcsr, RFCSR6_R2, 1); rt2800_rfcsr_write(rt2x00dev, 6, rfcsr); - rt2800_rfcsr_write(rt2x00dev, 31, 0x14); - rt2800_register_read(rt2x00dev, LDO_CFG0, ®); rt2x00_set_field32(®, LDO_CFG0_BGSEL, 1); if (rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E) || @@ -2619,6 +2634,10 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2x00_set_field32(®, LDO_CFG0_LDO_CORE_VLEVEL, 0); } rt2800_register_write(rt2x00dev, LDO_CFG0, reg); + + rt2800_register_read(rt2x00dev, GPIO_SWITCH, ®); + rt2x00_set_field32(®, GPIO_SWITCH_5, 0); + rt2800_register_write(rt2x00dev, GPIO_SWITCH, reg); } else if (rt2x00_rt(rt2x00dev, RT3390)) { rt2800_register_read(rt2x00dev, GPIO_SWITCH, ®); rt2x00_set_field32(®, GPIO_SWITCH_5, 0); @@ -2670,10 +2689,11 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_read(rt2x00dev, 17, &rfcsr); rt2x00_set_field8(&rfcsr, RFCSR17_TX_LO1_EN, 0); - if (rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E) || + if (rt2x00_rt(rt2x00dev, RT3070) || + rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E) || rt2x00_rt_rev_lt(rt2x00dev, RT3090, REV_RT3090E) || rt2x00_rt_rev_lt(rt2x00dev, RT3390, REV_RT3390E)) { - if (test_bit(CONFIG_EXTERNAL_LNA_BG, &rt2x00dev->flags)) + if (!test_bit(CONFIG_EXTERNAL_LNA_BG, &rt2x00dev->flags)) rt2x00_set_field8(&rfcsr, RFCSR17_R, 1); } rt2x00_eeprom_read(rt2x00dev, EEPROM_TXMIXER_GAIN_BG, &eeprom); @@ -2686,6 +2706,7 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) if (rt2x00_rt(rt2x00dev, RT3090)) { rt2800_bbp_read(rt2x00dev, 138, &bbp); + /* Turn off unused DAC1 and ADC1 to reduce power consumption */ rt2x00_eeprom_read(rt2x00dev, EEPROM_NIC_CONF0, &eeprom); if (rt2x00_get_field16(eeprom, EEPROM_NIC_CONF0_RXPATH) == 1) rt2x00_set_field8(&bbp, BBP138_RX_ADC1, 0); @@ -2719,10 +2740,9 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_write(rt2x00dev, 21, rfcsr); } - if (rt2x00_rt(rt2x00dev, RT3070) || rt2x00_rt(rt2x00dev, RT3071)) { + if (rt2x00_rt(rt2x00dev, RT3070)) { rt2800_rfcsr_read(rt2x00dev, 27, &rfcsr); - if (rt2x00_rt_rev_lt(rt2x00dev, RT3070, REV_RT3070F) || - rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E)) + if (rt2x00_rt_rev_lt(rt2x00dev, RT3070, REV_RT3070F)) rt2x00_set_field8(&rfcsr, RFCSR27_R1, 3); else rt2x00_set_field8(&rfcsr, RFCSR27_R1, 0); @@ -2810,10 +2830,7 @@ void rt2800_disable_radio(struct rt2x00_dev *rt2x00dev) rt2800_register_read(rt2x00dev, WPDMA_GLO_CFG, ®); rt2x00_set_field32(®, WPDMA_GLO_CFG_ENABLE_TX_DMA, 0); - rt2x00_set_field32(®, WPDMA_GLO_CFG_TX_DMA_BUSY, 0); rt2x00_set_field32(®, WPDMA_GLO_CFG_ENABLE_RX_DMA, 0); - rt2x00_set_field32(®, WPDMA_GLO_CFG_RX_DMA_BUSY, 0); - rt2x00_set_field32(®, WPDMA_GLO_CFG_TX_WRITEBACK_DONE, 1); rt2800_register_write(rt2x00dev, WPDMA_GLO_CFG, reg); /* Wait for DMA, ignore error */ @@ -2823,9 +2840,6 @@ void rt2800_disable_radio(struct rt2x00_dev *rt2x00dev) rt2x00_set_field32(®, MAC_SYS_CTRL_ENABLE_TX, 0); rt2x00_set_field32(®, MAC_SYS_CTRL_ENABLE_RX, 0); rt2800_register_write(rt2x00dev, MAC_SYS_CTRL, reg); - - rt2800_register_write(rt2x00dev, PWR_PIN_CFG, 0); - rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0); } EXPORT_SYMBOL_GPL(rt2800_disable_radio); @@ -3530,7 +3544,8 @@ EXPORT_SYMBOL_GPL(rt2800_get_tsf); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { int ret = 0; diff --git a/drivers/net/wireless/rt2x00/rt2800lib.h b/drivers/net/wireless/rt2x00/rt2800lib.h index e3c995a..0c92d86 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/rt2x00/rt2800lib.h @@ -156,6 +156,7 @@ void rt2800_txdone(struct rt2x00_dev *rt2x00dev); void rt2800_txdone_entry(struct queue_entry *entry, u32 status); void rt2800_write_beacon(struct queue_entry *entry, struct txentry_desc *txdesc); +void rt2800_clear_beacon(struct queue_entry *entry); extern const struct rt2x00debug rt2800_rt2x00debug; @@ -198,7 +199,8 @@ int rt2800_conf_tx(struct ieee80211_hw *hw, u16 queue_idx, u64 rt2800_get_tsf(struct ieee80211_hw *hw); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int rt2800_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey); diff --git a/drivers/net/wireless/rt2x00/rt2800pci.c b/drivers/net/wireless/rt2x00/rt2800pci.c index aa97971..8f4dfc3 100644 --- a/drivers/net/wireless/rt2x00/rt2800pci.c +++ b/drivers/net/wireless/rt2x00/rt2800pci.c @@ -200,11 +200,22 @@ static void rt2800pci_start_queue(struct data_queue *queue) rt2800_register_write(rt2x00dev, MAC_SYS_CTRL, reg); break; case QID_BEACON: + /* + * Allow beacon tasklets to be scheduled for periodic + * beacon updates. + */ + tasklet_enable(&rt2x00dev->tbtt_tasklet); + tasklet_enable(&rt2x00dev->pretbtt_tasklet); + rt2800_register_read(rt2x00dev, BCN_TIME_CFG, ®); rt2x00_set_field32(®, BCN_TIME_CFG_TSF_TICKING, 1); rt2x00_set_field32(®, BCN_TIME_CFG_TBTT_ENABLE, 1); rt2x00_set_field32(®, BCN_TIME_CFG_BEACON_GEN, 1); rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg); + + rt2800_register_read(rt2x00dev, INT_TIMER_EN, ®); + rt2x00_set_field32(®, INT_TIMER_EN_PRE_TBTT_TIMER, 1); + rt2800_register_write(rt2x00dev, INT_TIMER_EN, reg); break; default: break; @@ -250,6 +261,16 @@ static void rt2800pci_stop_queue(struct data_queue *queue) rt2x00_set_field32(®, BCN_TIME_CFG_TBTT_ENABLE, 0); rt2x00_set_field32(®, BCN_TIME_CFG_BEACON_GEN, 0); rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg); + + rt2800_register_read(rt2x00dev, INT_TIMER_EN, ®); + rt2x00_set_field32(®, INT_TIMER_EN_PRE_TBTT_TIMER, 0); + rt2800_register_write(rt2x00dev, INT_TIMER_EN, reg); + + /* + * Wait for tbtt tasklets to finish. + */ + tasklet_disable(&rt2x00dev->tbtt_tasklet); + tasklet_disable(&rt2x00dev->pretbtt_tasklet); break; default: break; @@ -397,9 +418,9 @@ static int rt2800pci_init_queues(struct rt2x00_dev *rt2x00dev) static void rt2800pci_toggle_irq(struct rt2x00_dev *rt2x00dev, enum dev_state state) { - int mask = (state == STATE_RADIO_IRQ_ON) || - (state == STATE_RADIO_IRQ_ON_ISR); + int mask = (state == STATE_RADIO_IRQ_ON); u32 reg; + unsigned long flags; /* * When interrupts are being enabled, the interrupt registers @@ -408,8 +429,17 @@ static void rt2800pci_toggle_irq(struct rt2x00_dev *rt2x00dev, if (state == STATE_RADIO_IRQ_ON) { rt2800_register_read(rt2x00dev, INT_SOURCE_CSR, ®); rt2800_register_write(rt2x00dev, INT_SOURCE_CSR, reg); + + /* + * Enable tasklets. The beacon related tasklets are + * enabled when the beacon queue is started. + */ + tasklet_enable(&rt2x00dev->txstatus_tasklet); + tasklet_enable(&rt2x00dev->rxdone_tasklet); + tasklet_enable(&rt2x00dev->autowake_tasklet); } + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); rt2800_register_read(rt2x00dev, INT_MASK_CSR, ®); rt2x00_set_field32(®, INT_MASK_CSR_RXDELAYINT, 0); rt2x00_set_field32(®, INT_MASK_CSR_TXDELAYINT, 0); @@ -430,6 +460,17 @@ static void rt2800pci_toggle_irq(struct rt2x00_dev *rt2x00dev, rt2x00_set_field32(®, INT_MASK_CSR_RX_COHERENT, 0); rt2x00_set_field32(®, INT_MASK_CSR_TX_COHERENT, 0); rt2800_register_write(rt2x00dev, INT_MASK_CSR, reg); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + if (state == STATE_RADIO_IRQ_OFF) { + /* + * Ensure that all tasklets are finished before + * disabling the interrupts. + */ + tasklet_disable(&rt2x00dev->txstatus_tasklet); + tasklet_disable(&rt2x00dev->rxdone_tasklet); + tasklet_disable(&rt2x00dev->autowake_tasklet); + } } static int rt2800pci_init_registers(struct rt2x00_dev *rt2x00dev) @@ -475,39 +516,23 @@ static int rt2800pci_enable_radio(struct rt2x00_dev *rt2x00dev) static void rt2800pci_disable_radio(struct rt2x00_dev *rt2x00dev) { - u32 reg; - - rt2800_disable_radio(rt2x00dev); - - rt2800_register_write(rt2x00dev, PBF_SYS_CTRL, 0x00001280); - - rt2800_register_read(rt2x00dev, WPDMA_RST_IDX, ®); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX0, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX1, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX2, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX3, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX4, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX5, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DRX_IDX0, 1); - rt2800_register_write(rt2x00dev, WPDMA_RST_IDX, reg); - - rt2800_register_write(rt2x00dev, PBF_SYS_CTRL, 0x00000e1f); - rt2800_register_write(rt2x00dev, PBF_SYS_CTRL, 0x00000e00); + if (rt2x00_is_soc(rt2x00dev)) { + rt2800_disable_radio(rt2x00dev); + rt2800_register_write(rt2x00dev, PWR_PIN_CFG, 0); + rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0); + } } static int rt2800pci_set_state(struct rt2x00_dev *rt2x00dev, enum dev_state state) { - /* - * Always put the device to sleep (even when we intend to wakeup!) - * if the device is booting and wasn't asleep it will return - * failure when attempting to wakeup. - */ - rt2800_mcu_request(rt2x00dev, MCU_SLEEP, 0xff, 0xff, 2); - if (state == STATE_AWAKE) { - rt2800_mcu_request(rt2x00dev, MCU_WAKEUP, TOKEN_WAKUP, 0, 0); + rt2800_mcu_request(rt2x00dev, MCU_WAKEUP, TOKEN_WAKUP, 0, 0x02); rt2800pci_mcu_status(rt2x00dev, TOKEN_WAKUP); + } else if (state == STATE_SLEEP) { + rt2800_register_write(rt2x00dev, H2M_MAILBOX_STATUS, 0xffffffff); + rt2800_register_write(rt2x00dev, H2M_MAILBOX_CID, 0xffffffff); + rt2800_mcu_request(rt2x00dev, MCU_SLEEP, 0x01, 0xff, 0x01); } return 0; @@ -538,9 +563,7 @@ static int rt2800pci_set_device_state(struct rt2x00_dev *rt2x00dev, rt2800pci_set_state(rt2x00dev, STATE_SLEEP); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: rt2800pci_toggle_irq(rt2x00dev, state); break; case STATE_DEEP_SLEEP: @@ -652,6 +675,12 @@ static void rt2800pci_fill_rxdone(struct queue_entry *entry, */ rxdesc->flags |= RX_FLAG_IV_STRIPPED; + /* + * The hardware has already checked the Michael Mic and has + * stripped it from the frame. Signal this to mac80211. + */ + rxdesc->flags |= RX_FLAG_MMIC_STRIPPED; + if (rxdesc->cipher_status == RX_CRYPTO_SUCCESS) rxdesc->flags |= RX_FLAG_DECRYPTED; else if (rxdesc->cipher_status == RX_CRYPTO_FAIL_MIC) @@ -726,45 +755,60 @@ static void rt2800pci_txdone(struct rt2x00_dev *rt2x00dev) } } -static void rt2800pci_txstatus_tasklet(unsigned long data) +static void rt2800pci_enable_interrupt(struct rt2x00_dev *rt2x00dev, + struct rt2x00_field32 irq_field) { - rt2800pci_txdone((struct rt2x00_dev *)data); -} - -static irqreturn_t rt2800pci_interrupt_thread(int irq, void *dev_instance) -{ - struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg = rt2x00dev->irqvalue[0]; + unsigned long flags; + u32 reg; /* - * 1 - Pre TBTT interrupt. + * Enable a single interrupt. The interrupt mask register + * access needs locking. */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_PRE_TBTT)) - rt2x00lib_pretbtt(rt2x00dev); + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + rt2800_register_read(rt2x00dev, INT_MASK_CSR, ®); + rt2x00_set_field32(®, irq_field, 1); + rt2800_register_write(rt2x00dev, INT_MASK_CSR, reg); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} - /* - * 2 - Beacondone interrupt. - */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_TBTT)) - rt2x00lib_beacondone(rt2x00dev); +static void rt2800pci_txstatus_tasklet(unsigned long data) +{ + rt2800pci_txdone((struct rt2x00_dev *)data); /* - * 3 - Rx ring done interrupt. + * No need to enable the tx status interrupt here as we always + * leave it enabled to minimize the possibility of a tx status + * register overflow. See comment in interrupt handler. */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_RX_DONE)) - rt2x00pci_rxdone(rt2x00dev); +} - /* - * 4 - Auto wakeup interrupt. - */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_AUTO_WAKEUP)) - rt2800pci_wakeup(rt2x00dev); +static void rt2800pci_pretbtt_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00lib_pretbtt(rt2x00dev); + rt2800pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_PRE_TBTT); +} - /* Enable interrupts again. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_ON_ISR); +static void rt2800pci_tbtt_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00lib_beacondone(rt2x00dev); + rt2800pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_TBTT); +} - return IRQ_HANDLED; +static void rt2800pci_rxdone_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00pci_rxdone(rt2x00dev); + rt2800pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_RX_DONE); +} + +static void rt2800pci_autowake_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2800pci_wakeup(rt2x00dev); + rt2800pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_AUTO_WAKEUP); } static void rt2800pci_txstatus_interrupt(struct rt2x00_dev *rt2x00dev) @@ -810,8 +854,8 @@ static void rt2800pci_txstatus_interrupt(struct rt2x00_dev *rt2x00dev) static irqreturn_t rt2800pci_interrupt(int irq, void *dev_instance) { struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg; - irqreturn_t ret = IRQ_HANDLED; + u32 reg, mask; + unsigned long flags; /* Read status and ACK all interrupts */ rt2800_register_read(rt2x00dev, INT_SOURCE_CSR, ®); @@ -823,38 +867,44 @@ static irqreturn_t rt2800pci_interrupt(int irq, void *dev_instance) if (!test_bit(DEVICE_STATE_ENABLED_RADIO, &rt2x00dev->flags)) return IRQ_HANDLED; - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_TX_FIFO_STATUS)) - rt2800pci_txstatus_interrupt(rt2x00dev); + /* + * Since INT_MASK_CSR and INT_SOURCE_CSR use the same bits + * for interrupts and interrupt masks we can just use the value of + * INT_SOURCE_CSR to create the interrupt mask. + */ + mask = ~reg; - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_PRE_TBTT) || - rt2x00_get_field32(reg, INT_SOURCE_CSR_TBTT) || - rt2x00_get_field32(reg, INT_SOURCE_CSR_RX_DONE) || - rt2x00_get_field32(reg, INT_SOURCE_CSR_AUTO_WAKEUP)) { + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_TX_FIFO_STATUS)) { + rt2800pci_txstatus_interrupt(rt2x00dev); /* - * All other interrupts are handled in the interrupt thread. - * Store irqvalue for use in the interrupt thread. + * Never disable the TX_FIFO_STATUS interrupt. */ - rt2x00dev->irqvalue[0] = reg; + rt2x00_set_field32(&mask, INT_MASK_CSR_TX_FIFO_STATUS, 1); + } - /* - * Disable interrupts, will be enabled again in the - * interrupt thread. - */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_OFF_ISR); + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_PRE_TBTT)) + tasklet_hi_schedule(&rt2x00dev->pretbtt_tasklet); - /* - * Leave the TX_FIFO_STATUS interrupt enabled to not lose any - * tx status reports. - */ - rt2800_register_read(rt2x00dev, INT_MASK_CSR, ®); - rt2x00_set_field32(®, INT_MASK_CSR_TX_FIFO_STATUS, 1); - rt2800_register_write(rt2x00dev, INT_MASK_CSR, reg); + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_TBTT)) + tasklet_hi_schedule(&rt2x00dev->tbtt_tasklet); - ret = IRQ_WAKE_THREAD; - } + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_RX_DONE)) + tasklet_schedule(&rt2x00dev->rxdone_tasklet); - return ret; + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_AUTO_WAKEUP)) + tasklet_schedule(&rt2x00dev->autowake_tasklet); + + /* + * Disable all interrupts for which a tasklet was scheduled right now, + * the tasklet will reenable the appropriate interrupts. + */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + rt2800_register_read(rt2x00dev, INT_MASK_CSR, ®); + reg &= mask; + rt2800_register_write(rt2x00dev, INT_MASK_CSR, reg); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + return IRQ_HANDLED; } /* @@ -969,8 +1019,11 @@ static const struct rt2800_ops rt2800pci_rt2800_ops = { static const struct rt2x00lib_ops rt2800pci_rt2x00_ops = { .irq_handler = rt2800pci_interrupt, - .irq_handler_thread = rt2800pci_interrupt_thread, - .txstatus_tasklet = rt2800pci_txstatus_tasklet, + .txstatus_tasklet = rt2800pci_txstatus_tasklet, + .pretbtt_tasklet = rt2800pci_pretbtt_tasklet, + .tbtt_tasklet = rt2800pci_tbtt_tasklet, + .rxdone_tasklet = rt2800pci_rxdone_tasklet, + .autowake_tasklet = rt2800pci_autowake_tasklet, .probe_hw = rt2800pci_probe_hw, .get_firmware_name = rt2800pci_get_firmware_name, .check_firmware = rt2800_check_firmware, @@ -990,6 +1043,7 @@ static const struct rt2x00lib_ops rt2800pci_rt2x00_ops = { .write_tx_desc = rt2800pci_write_tx_desc, .write_tx_data = rt2800_write_tx_data, .write_beacon = rt2800_write_beacon, + .clear_beacon = rt2800_clear_beacon, .fill_rxdone = rt2800pci_fill_rxdone, .config_shared_key = rt2800_config_shared_key, .config_pairwise_key = rt2800_config_pairwise_key, diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index b97a4a5..5d91561 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -253,9 +253,7 @@ static int rt2800usb_set_device_state(struct rt2x00_dev *rt2x00dev, rt2800usb_set_state(rt2x00dev, STATE_SLEEP); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: /* No support, but no error either */ break; case STATE_DEEP_SLEEP: @@ -486,6 +484,12 @@ static void rt2800usb_fill_rxdone(struct queue_entry *entry, */ rxdesc->flags |= RX_FLAG_IV_STRIPPED; + /* + * The hardware has already checked the Michael Mic and has + * stripped it from the frame. Signal this to mac80211. + */ + rxdesc->flags |= RX_FLAG_MMIC_STRIPPED; + if (rxdesc->cipher_status == RX_CRYPTO_SUCCESS) rxdesc->flags |= RX_FLAG_DECRYPTED; else if (rxdesc->cipher_status == RX_CRYPTO_FAIL_MIC) @@ -633,6 +637,7 @@ static const struct rt2x00lib_ops rt2800usb_rt2x00_ops = { .write_tx_desc = rt2800usb_write_tx_desc, .write_tx_data = rt2800usb_write_tx_data, .write_beacon = rt2800_write_beacon, + .clear_beacon = rt2800_clear_beacon, .get_tx_data_len = rt2800usb_get_tx_data_len, .fill_rxdone = rt2800usb_fill_rxdone, .config_shared_key = rt2800_config_shared_key, diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h index 84aaf39..39bc2fa 100644 --- a/drivers/net/wireless/rt2x00/rt2x00.h +++ b/drivers/net/wireless/rt2x00/rt2x00.h @@ -368,6 +368,7 @@ struct rt2x00_intf { * dedicated beacon entry. */ struct queue_entry *beacon; + bool enable_beacon; /* * Actions that needed rescheduling. @@ -511,14 +512,13 @@ struct rt2x00lib_ops { irq_handler_t irq_handler; /* - * Threaded Interrupt handlers. - */ - irq_handler_t irq_handler_thread; - - /* * TX status tasklet handler. */ void (*txstatus_tasklet) (unsigned long data); + void (*pretbtt_tasklet) (unsigned long data); + void (*tbtt_tasklet) (unsigned long data); + void (*rxdone_tasklet) (unsigned long data); + void (*autowake_tasklet) (unsigned long data); /* * Device init handlers. @@ -573,6 +573,7 @@ struct rt2x00lib_ops { struct txentry_desc *txdesc); void (*write_beacon) (struct queue_entry *entry, struct txentry_desc *txdesc); + void (*clear_beacon) (struct queue_entry *entry); int (*get_tx_data_len) (struct queue_entry *entry); /* @@ -788,10 +789,12 @@ struct rt2x00_dev { * - Open ap interface count. * - Open sta interface count. * - Association count. + * - Beaconing enabled count. */ unsigned int intf_ap_count; unsigned int intf_sta_count; unsigned int intf_associated; + unsigned int intf_beaconing; /* * Link quality @@ -857,6 +860,13 @@ struct rt2x00_dev { */ struct ieee80211_low_level_stats low_level_stats; + /** + * Work queue for all work which should not be placed + * on the mac80211 workqueue (because of dependencies + * between various work structures). + */ + struct workqueue_struct *workqueue; + /* * Scheduled work. * NOTE: intf_work will use ieee80211_iterate_active_interfaces() @@ -887,12 +897,6 @@ struct rt2x00_dev { const struct firmware *fw; /* - * Interrupt values, stored between interrupt service routine - * and interrupt thread routine. - */ - u32 irqvalue[2]; - - /* * FIFO for storing tx status reports between isr and tasklet. */ DECLARE_KFIFO_PTR(txstatus_fifo, u32); @@ -901,6 +905,15 @@ struct rt2x00_dev { * Tasklet for processing tx status reports (rt2800pci). */ struct tasklet_struct txstatus_tasklet; + struct tasklet_struct pretbtt_tasklet; + struct tasklet_struct tbtt_tasklet; + struct tasklet_struct rxdone_tasklet; + struct tasklet_struct autowake_tasklet; + + /* + * Protect the interrupt mask register. + */ + spinlock_t irqmask_lock; }; /* diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c index 9597a03..9de9dbe 100644 --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -121,7 +121,7 @@ static void rt2x00lib_intf_scheduled_iter(void *data, u8 *mac, return; if (test_and_clear_bit(DELAYED_UPDATE_BEACON, &intf->delayed_flags)) - rt2x00queue_update_beacon(rt2x00dev, vif, true); + rt2x00queue_update_beacon(rt2x00dev, vif); } static void rt2x00lib_intf_scheduled(struct work_struct *work) @@ -174,7 +174,13 @@ static void rt2x00lib_beaconupdate_iter(void *data, u8 *mac, vif->type != NL80211_IFTYPE_WDS) return; - rt2x00queue_update_beacon(rt2x00dev, vif, true); + /* + * Update the beacon without locking. This is safe on PCI devices + * as they only update the beacon periodically here. This should + * never be called for USB devices. + */ + WARN_ON(rt2x00_is_usb(rt2x00dev)); + rt2x00queue_update_beacon_locked(rt2x00dev, vif); } void rt2x00lib_beacondone(struct rt2x00_dev *rt2x00dev) @@ -183,9 +189,9 @@ void rt2x00lib_beacondone(struct rt2x00_dev *rt2x00dev) return; /* send buffered bc/mc frames out for every bssid */ - ieee80211_iterate_active_interfaces(rt2x00dev->hw, - rt2x00lib_bc_buffer_iter, - rt2x00dev); + ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw, + rt2x00lib_bc_buffer_iter, + rt2x00dev); /* * Devices with pre tbtt interrupt don't need to update the beacon * here as they will fetch the next beacon directly prior to @@ -195,9 +201,9 @@ void rt2x00lib_beacondone(struct rt2x00_dev *rt2x00dev) return; /* fetch next beacon */ - ieee80211_iterate_active_interfaces(rt2x00dev->hw, - rt2x00lib_beaconupdate_iter, - rt2x00dev); + ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw, + rt2x00lib_beaconupdate_iter, + rt2x00dev); } EXPORT_SYMBOL_GPL(rt2x00lib_beacondone); @@ -207,9 +213,9 @@ void rt2x00lib_pretbtt(struct rt2x00_dev *rt2x00dev) return; /* fetch next beacon */ - ieee80211_iterate_active_interfaces(rt2x00dev->hw, - rt2x00lib_beaconupdate_iter, - rt2x00dev); + ieee80211_iterate_active_interfaces_atomic(rt2x00dev->hw, + rt2x00lib_beaconupdate_iter, + rt2x00dev); } EXPORT_SYMBOL_GPL(rt2x00lib_pretbtt); @@ -649,7 +655,10 @@ static void rt2x00lib_channel(struct ieee80211_channel *entry, const int channel, const int tx_power, const int value) { - entry->center_freq = ieee80211_channel_to_frequency(channel); + /* XXX: this assumption about the band is wrong for 802.11j */ + entry->band = channel <= 14 ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + entry->center_freq = ieee80211_channel_to_frequency(channel, + entry->band); entry->hw_value = value; entry->max_power = tx_power; entry->max_antenna_gain = 0xff; @@ -812,15 +821,29 @@ static int rt2x00lib_probe_hw(struct rt2x00_dev *rt2x00dev) GFP_KERNEL); if (status) return status; + } - /* tasklet for processing the tx status reports. */ - if (rt2x00dev->ops->lib->txstatus_tasklet) - tasklet_init(&rt2x00dev->txstatus_tasklet, - rt2x00dev->ops->lib->txstatus_tasklet, - (unsigned long)rt2x00dev); - + /* + * Initialize tasklets if used by the driver. Tasklets are + * disabled until the interrupts are turned on. The driver + * has to handle that. + */ +#define RT2X00_TASKLET_INIT(taskletname) \ + if (rt2x00dev->ops->lib->taskletname) { \ + tasklet_init(&rt2x00dev->taskletname, \ + rt2x00dev->ops->lib->taskletname, \ + (unsigned long)rt2x00dev); \ + tasklet_disable(&rt2x00dev->taskletname); \ } + RT2X00_TASKLET_INIT(txstatus_tasklet); + RT2X00_TASKLET_INIT(pretbtt_tasklet); + RT2X00_TASKLET_INIT(tbtt_tasklet); + RT2X00_TASKLET_INIT(rxdone_tasklet); + RT2X00_TASKLET_INIT(autowake_tasklet); + +#undef RT2X00_TASKLET_INIT + /* * Register HW. */ @@ -949,6 +972,7 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) { int retval = -ENOMEM; + spin_lock_init(&rt2x00dev->irqmask_lock); mutex_init(&rt2x00dev->csr_mutex); set_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags); @@ -973,8 +997,15 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev) BIT(NL80211_IFTYPE_WDS); /* - * Initialize configuration work. + * Initialize work. */ + rt2x00dev->workqueue = + alloc_ordered_workqueue(wiphy_name(rt2x00dev->hw->wiphy), 0); + if (!rt2x00dev->workqueue) { + retval = -ENOMEM; + goto exit; + } + INIT_WORK(&rt2x00dev->intf_work, rt2x00lib_intf_scheduled); /* @@ -1033,6 +1064,7 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev) cancel_work_sync(&rt2x00dev->intf_work); cancel_work_sync(&rt2x00dev->rxdone_work); cancel_work_sync(&rt2x00dev->txdone_work); + destroy_workqueue(rt2x00dev->workqueue); /* * Free the tx status fifo. @@ -1043,6 +1075,10 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev) * Kill the tx status tasklet. */ tasklet_kill(&rt2x00dev->txstatus_tasklet); + tasklet_kill(&rt2x00dev->pretbtt_tasklet); + tasklet_kill(&rt2x00dev->tbtt_tasklet); + tasklet_kill(&rt2x00dev->rxdone_tasklet); + tasklet_kill(&rt2x00dev->autowake_tasklet); /* * Uninitialize device. diff --git a/drivers/net/wireless/rt2x00/rt2x00lib.h b/drivers/net/wireless/rt2x00/rt2x00lib.h index a105c50..2d94cba 100644 --- a/drivers/net/wireless/rt2x00/rt2x00lib.h +++ b/drivers/net/wireless/rt2x00/rt2x00lib.h @@ -157,14 +157,30 @@ int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb, bool local); /** - * rt2x00queue_update_beacon - Send new beacon from mac80211 to hardware + * rt2x00queue_update_beacon - Send new beacon from mac80211 + * to hardware. Handles locking by itself (mutex). * @rt2x00dev: Pointer to &struct rt2x00_dev. * @vif: Interface for which the beacon should be updated. - * @enable_beacon: Enable beaconing */ int rt2x00queue_update_beacon(struct rt2x00_dev *rt2x00dev, - struct ieee80211_vif *vif, - const bool enable_beacon); + struct ieee80211_vif *vif); + +/** + * rt2x00queue_update_beacon_locked - Send new beacon from mac80211 + * to hardware. Caller needs to ensure locking. + * @rt2x00dev: Pointer to &struct rt2x00_dev. + * @vif: Interface for which the beacon should be updated. + */ +int rt2x00queue_update_beacon_locked(struct rt2x00_dev *rt2x00dev, + struct ieee80211_vif *vif); + +/** + * rt2x00queue_clear_beacon - Clear beacon in hardware + * @rt2x00dev: Pointer to &struct rt2x00_dev. + * @vif: Interface for which the beacon should be updated. + */ +int rt2x00queue_clear_beacon(struct rt2x00_dev *rt2x00dev, + struct ieee80211_vif *vif); /** * rt2x00queue_index_inc - Index incrementation function diff --git a/drivers/net/wireless/rt2x00/rt2x00link.c b/drivers/net/wireless/rt2x00/rt2x00link.c index bfda60e..c975b0a 100644 --- a/drivers/net/wireless/rt2x00/rt2x00link.c +++ b/drivers/net/wireless/rt2x00/rt2x00link.c @@ -417,7 +417,8 @@ void rt2x00link_start_watchdog(struct rt2x00_dev *rt2x00dev) !test_bit(DRIVER_SUPPORT_WATCHDOG, &rt2x00dev->flags)) return; - schedule_delayed_work(&link->watchdog_work, WATCHDOG_INTERVAL); + ieee80211_queue_delayed_work(rt2x00dev->hw, + &link->watchdog_work, WATCHDOG_INTERVAL); } void rt2x00link_stop_watchdog(struct rt2x00_dev *rt2x00dev) @@ -441,7 +442,9 @@ static void rt2x00link_watchdog(struct work_struct *work) rt2x00dev->ops->lib->watchdog(rt2x00dev); if (test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags)) - schedule_delayed_work(&link->watchdog_work, WATCHDOG_INTERVAL); + ieee80211_queue_delayed_work(rt2x00dev->hw, + &link->watchdog_work, + WATCHDOG_INTERVAL); } void rt2x00link_register(struct rt2x00_dev *rt2x00dev) diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c index f3da051..6a66021 100644 --- a/drivers/net/wireless/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/rt2x00/rt2x00mac.c @@ -617,11 +617,47 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, bss_conf->bssid); /* - * Update the beacon. + * Update the beacon. This is only required on USB devices. PCI + * devices fetch beacons periodically. */ - if (changes & (BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED)) - rt2x00queue_update_beacon(rt2x00dev, vif, - bss_conf->enable_beacon); + if (changes & BSS_CHANGED_BEACON && rt2x00_is_usb(rt2x00dev)) + rt2x00queue_update_beacon(rt2x00dev, vif); + + /* + * Start/stop beaconing. + */ + if (changes & BSS_CHANGED_BEACON_ENABLED) { + if (!bss_conf->enable_beacon && intf->enable_beacon) { + rt2x00queue_clear_beacon(rt2x00dev, vif); + rt2x00dev->intf_beaconing--; + intf->enable_beacon = false; + + if (rt2x00dev->intf_beaconing == 0) { + /* + * Last beaconing interface disabled + * -> stop beacon queue. + */ + mutex_lock(&intf->beacon_skb_mutex); + rt2x00queue_stop_queue(rt2x00dev->bcn); + mutex_unlock(&intf->beacon_skb_mutex); + } + + + } else if (bss_conf->enable_beacon && !intf->enable_beacon) { + rt2x00dev->intf_beaconing++; + intf->enable_beacon = true; + + if (rt2x00dev->intf_beaconing == 1) { + /* + * First beaconing interface enabled + * -> start beacon queue. + */ + mutex_lock(&intf->beacon_skb_mutex); + rt2x00queue_start_queue(rt2x00dev->bcn); + mutex_unlock(&intf->beacon_skb_mutex); + } + } + } /* * When the association status has changed we must reset the link diff --git a/drivers/net/wireless/rt2x00/rt2x00pci.c b/drivers/net/wireless/rt2x00/rt2x00pci.c index ace0b66..4dd82b0 100644 --- a/drivers/net/wireless/rt2x00/rt2x00pci.c +++ b/drivers/net/wireless/rt2x00/rt2x00pci.c @@ -160,10 +160,9 @@ int rt2x00pci_initialize(struct rt2x00_dev *rt2x00dev) /* * Register interrupt handler. */ - status = request_threaded_irq(rt2x00dev->irq, - rt2x00dev->ops->lib->irq_handler, - rt2x00dev->ops->lib->irq_handler_thread, - IRQF_SHARED, rt2x00dev->name, rt2x00dev); + status = request_irq(rt2x00dev->irq, + rt2x00dev->ops->lib->irq_handler, + IRQF_SHARED, rt2x00dev->name, rt2x00dev); if (status) { ERROR(rt2x00dev, "IRQ %d allocation failed (error %d).\n", rt2x00dev->irq, status); diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c index ca82b3a..fa17c83 100644 --- a/drivers/net/wireless/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/rt2x00/rt2x00queue.c @@ -566,13 +566,10 @@ int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb, return 0; } -int rt2x00queue_update_beacon(struct rt2x00_dev *rt2x00dev, - struct ieee80211_vif *vif, - const bool enable_beacon) +int rt2x00queue_clear_beacon(struct rt2x00_dev *rt2x00dev, + struct ieee80211_vif *vif) { struct rt2x00_intf *intf = vif_to_intf(vif); - struct skb_frame_desc *skbdesc; - struct txentry_desc txdesc; if (unlikely(!intf->beacon)) return -ENOBUFS; @@ -584,17 +581,36 @@ int rt2x00queue_update_beacon(struct rt2x00_dev *rt2x00dev, */ rt2x00queue_free_skb(intf->beacon); - if (!enable_beacon) { - rt2x00queue_stop_queue(intf->beacon->queue); - mutex_unlock(&intf->beacon_skb_mutex); - return 0; - } + /* + * Clear beacon (single bssid devices don't need to clear the beacon + * since the beacon queue will get stopped anyway). + */ + if (rt2x00dev->ops->lib->clear_beacon) + rt2x00dev->ops->lib->clear_beacon(intf->beacon); + + mutex_unlock(&intf->beacon_skb_mutex); + + return 0; +} + +int rt2x00queue_update_beacon_locked(struct rt2x00_dev *rt2x00dev, + struct ieee80211_vif *vif) +{ + struct rt2x00_intf *intf = vif_to_intf(vif); + struct skb_frame_desc *skbdesc; + struct txentry_desc txdesc; + + if (unlikely(!intf->beacon)) + return -ENOBUFS; + + /* + * Clean up the beacon skb. + */ + rt2x00queue_free_skb(intf->beacon); intf->beacon->skb = ieee80211_beacon_get(rt2x00dev->hw, vif); - if (!intf->beacon->skb) { - mutex_unlock(&intf->beacon_skb_mutex); + if (!intf->beacon->skb) return -ENOMEM; - } /* * Copy all TX descriptor information into txdesc, @@ -611,13 +627,25 @@ int rt2x00queue_update_beacon(struct rt2x00_dev *rt2x00dev, skbdesc->entry = intf->beacon; /* - * Send beacon to hardware and enable beacon genaration.. + * Send beacon to hardware. */ rt2x00dev->ops->lib->write_beacon(intf->beacon, &txdesc); + return 0; + +} + +int rt2x00queue_update_beacon(struct rt2x00_dev *rt2x00dev, + struct ieee80211_vif *vif) +{ + struct rt2x00_intf *intf = vif_to_intf(vif); + int ret; + + mutex_lock(&intf->beacon_skb_mutex); + ret = rt2x00queue_update_beacon_locked(rt2x00dev, vif); mutex_unlock(&intf->beacon_skb_mutex); - return 0; + return ret; } void rt2x00queue_for_each_entry(struct data_queue *queue, @@ -885,7 +913,7 @@ void rt2x00queue_flush_queue(struct data_queue *queue, bool drop) * The queue flush has failed... */ if (unlikely(!rt2x00queue_empty(queue))) - WARNING(queue->rt2x00dev, "Queue %d failed to flush", queue->qid); + WARNING(queue->rt2x00dev, "Queue %d failed to flush\n", queue->qid); /* * Restore the queue to the previous status diff --git a/drivers/net/wireless/rt2x00/rt2x00reg.h b/drivers/net/wireless/rt2x00/rt2x00reg.h index e8259ae..6f867ee 100644 --- a/drivers/net/wireless/rt2x00/rt2x00reg.h +++ b/drivers/net/wireless/rt2x00/rt2x00reg.h @@ -85,8 +85,6 @@ enum dev_state { STATE_RADIO_OFF, STATE_RADIO_IRQ_ON, STATE_RADIO_IRQ_OFF, - STATE_RADIO_IRQ_ON_ISR, - STATE_RADIO_IRQ_OFF_ISR, }; /* diff --git a/drivers/net/wireless/rt2x00/rt2x00usb.c b/drivers/net/wireless/rt2x00/rt2x00usb.c index 1a9937d..fbe735f 100644 --- a/drivers/net/wireless/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/rt2x00/rt2x00usb.c @@ -227,7 +227,7 @@ static void rt2x00usb_interrupt_txdone(struct urb *urb) * Schedule the delayed work for reading the TX status * from the device. */ - ieee80211_queue_work(rt2x00dev->hw, &rt2x00dev->txdone_work); + queue_work(rt2x00dev->workqueue, &rt2x00dev->txdone_work); } static void rt2x00usb_kick_tx_entry(struct queue_entry *entry) @@ -320,7 +320,7 @@ static void rt2x00usb_interrupt_rxdone(struct urb *urb) * Schedule the delayed work for reading the RX status * from the device. */ - ieee80211_queue_work(rt2x00dev->hw, &rt2x00dev->rxdone_work); + queue_work(rt2x00dev->workqueue, &rt2x00dev->rxdone_work); } static void rt2x00usb_kick_rx_entry(struct queue_entry *entry) @@ -429,7 +429,7 @@ void rt2x00usb_flush_queue(struct data_queue *queue) * Schedule the completion handler manually, when this * worker function runs, it should cleanup the queue. */ - ieee80211_queue_work(queue->rt2x00dev->hw, completion); + queue_work(queue->rt2x00dev->workqueue, completion); /* * Wait for a little while to give the driver @@ -453,7 +453,7 @@ static void rt2x00usb_watchdog_tx_status(struct data_queue *queue) WARNING(queue->rt2x00dev, "TX queue %d status timed out," " invoke forced tx handler\n", queue->qid); - ieee80211_queue_work(queue->rt2x00dev->hw, &queue->rt2x00dev->txdone_work); + queue_work(queue->rt2x00dev->workqueue, &queue->rt2x00dev->txdone_work); } void rt2x00usb_watchdog(struct rt2x00_dev *rt2x00dev) diff --git a/drivers/net/wireless/rt2x00/rt61pci.c b/drivers/net/wireless/rt2x00/rt61pci.c index 8de44dd..dd2164d 100644 --- a/drivers/net/wireless/rt2x00/rt61pci.c +++ b/drivers/net/wireless/rt2x00/rt61pci.c @@ -551,26 +551,14 @@ static void rt61pci_config_intf(struct rt2x00_dev *rt2x00dev, struct rt2x00intf_conf *conf, const unsigned int flags) { - unsigned int beacon_base; u32 reg; if (flags & CONFIG_UPDATE_TYPE) { /* - * Clear current synchronisation setup. - * For the Beacon base registers, we only need to clear - * the first byte since that byte contains the VALID and OWNER - * bits which (when set to 0) will invalidate the entire beacon. - */ - beacon_base = HW_BEACON_OFFSET(intf->beacon->entry_idx); - rt2x00pci_register_write(rt2x00dev, beacon_base, 0); - - /* * Enable synchronisation. */ rt2x00pci_register_read(rt2x00dev, TXRX_CSR9, ®); - rt2x00_set_field32(®, TXRX_CSR9_TSF_TICKING, 1); rt2x00_set_field32(®, TXRX_CSR9_TSF_SYNC, conf->sync); - rt2x00_set_field32(®, TXRX_CSR9_TBTT_ENABLE, 1); rt2x00pci_register_write(rt2x00dev, TXRX_CSR9, reg); } @@ -1154,6 +1142,11 @@ static void rt61pci_start_queue(struct data_queue *queue) rt2x00pci_register_write(rt2x00dev, TXRX_CSR0, reg); break; case QID_BEACON: + /* + * Allow the tbtt tasklet to be scheduled. + */ + tasklet_enable(&rt2x00dev->tbtt_tasklet); + rt2x00pci_register_read(rt2x00dev, TXRX_CSR9, ®); rt2x00_set_field32(®, TXRX_CSR9_TSF_TICKING, 1); rt2x00_set_field32(®, TXRX_CSR9_TBTT_ENABLE, 1); @@ -1233,6 +1226,11 @@ static void rt61pci_stop_queue(struct data_queue *queue) rt2x00_set_field32(®, TXRX_CSR9_TBTT_ENABLE, 0); rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 0); rt2x00pci_register_write(rt2x00dev, TXRX_CSR9, reg); + + /* + * Wait for possibly running tbtt tasklets. + */ + tasklet_disable(&rt2x00dev->tbtt_tasklet); break; default: break; @@ -1719,9 +1717,9 @@ static int rt61pci_init_bbp(struct rt2x00_dev *rt2x00dev) static void rt61pci_toggle_irq(struct rt2x00_dev *rt2x00dev, enum dev_state state) { - int mask = (state == STATE_RADIO_IRQ_OFF) || - (state == STATE_RADIO_IRQ_OFF_ISR); + int mask = (state == STATE_RADIO_IRQ_OFF); u32 reg; + unsigned long flags; /* * When interrupts are being enabled, the interrupt registers @@ -1733,12 +1731,21 @@ static void rt61pci_toggle_irq(struct rt2x00_dev *rt2x00dev, rt2x00pci_register_read(rt2x00dev, MCU_INT_SOURCE_CSR, ®); rt2x00pci_register_write(rt2x00dev, MCU_INT_SOURCE_CSR, reg); + + /* + * Enable tasklets. + */ + tasklet_enable(&rt2x00dev->txstatus_tasklet); + tasklet_enable(&rt2x00dev->rxdone_tasklet); + tasklet_enable(&rt2x00dev->autowake_tasklet); } /* * Only toggle the interrupts bits we are going to use. * Non-checked interrupt bits are disabled by default. */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + rt2x00pci_register_read(rt2x00dev, INT_MASK_CSR, ®); rt2x00_set_field32(®, INT_MASK_CSR_TXDONE, mask); rt2x00_set_field32(®, INT_MASK_CSR_RXDONE, mask); @@ -1758,6 +1765,17 @@ static void rt61pci_toggle_irq(struct rt2x00_dev *rt2x00dev, rt2x00_set_field32(®, MCU_INT_MASK_CSR_7, mask); rt2x00_set_field32(®, MCU_INT_MASK_CSR_TWAKEUP, mask); rt2x00pci_register_write(rt2x00dev, MCU_INT_MASK_CSR, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + if (state == STATE_RADIO_IRQ_OFF) { + /* + * Ensure that all tasklets are finished. + */ + tasklet_disable(&rt2x00dev->txstatus_tasklet); + tasklet_disable(&rt2x00dev->rxdone_tasklet); + tasklet_disable(&rt2x00dev->autowake_tasklet); + } } static int rt61pci_enable_radio(struct rt2x00_dev *rt2x00dev) @@ -1833,9 +1851,7 @@ static int rt61pci_set_device_state(struct rt2x00_dev *rt2x00dev, rt61pci_disable_radio(rt2x00dev); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: rt61pci_toggle_irq(rt2x00dev, state); break; case STATE_DEEP_SLEEP: @@ -2002,8 +2018,6 @@ static void rt61pci_write_beacon(struct queue_entry *entry, */ rt2x00pci_register_write(rt2x00dev, TXRX_CSR10, 0x00001008); - rt2x00_set_field32(®, TXRX_CSR9_TSF_TICKING, 1); - rt2x00_set_field32(®, TXRX_CSR9_TBTT_ENABLE, 1); rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 1); rt2x00pci_register_write(rt2x00dev, TXRX_CSR9, reg); @@ -2014,6 +2028,32 @@ static void rt61pci_write_beacon(struct queue_entry *entry, entry->skb = NULL; } +static void rt61pci_clear_beacon(struct queue_entry *entry) +{ + struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev; + u32 reg; + + /* + * Disable beaconing while we are reloading the beacon data, + * otherwise we might be sending out invalid data. + */ + rt2x00pci_register_read(rt2x00dev, TXRX_CSR9, ®); + rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 0); + rt2x00pci_register_write(rt2x00dev, TXRX_CSR9, reg); + + /* + * Clear beacon. + */ + rt2x00pci_register_write(rt2x00dev, + HW_BEACON_OFFSET(entry->entry_idx), 0); + + /* + * Enable beaconing again. + */ + rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 1); + rt2x00pci_register_write(rt2x00dev, TXRX_CSR9, reg); +} + /* * RX control handlers */ @@ -2078,9 +2118,8 @@ static void rt61pci_fill_rxdone(struct queue_entry *entry, rxdesc->flags |= RX_FLAG_IV_STRIPPED; /* - * FIXME: Legacy driver indicates that the frame does - * contain the Michael Mic. Unfortunately, in rt2x00 - * the MIC seems to be missing completely... + * The hardware has already checked the Michael Mic and has + * stripped it from the frame. Signal this to mac80211. */ rxdesc->flags |= RX_FLAG_MMIC_STRIPPED; @@ -2211,61 +2250,80 @@ static void rt61pci_wakeup(struct rt2x00_dev *rt2x00dev) rt61pci_config(rt2x00dev, &libconf, IEEE80211_CONF_CHANGE_PS); } -static irqreturn_t rt61pci_interrupt_thread(int irq, void *dev_instance) +static void rt61pci_enable_interrupt(struct rt2x00_dev *rt2x00dev, + struct rt2x00_field32 irq_field) { - struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg = rt2x00dev->irqvalue[0]; - u32 reg_mcu = rt2x00dev->irqvalue[1]; + unsigned long flags; + u32 reg; /* - * Handle interrupts, walk through all bits - * and run the tasks, the bits are checked in order of - * priority. + * Enable a single interrupt. The interrupt mask register + * access needs locking. */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); - /* - * 1 - Rx ring done interrupt. - */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_RXDONE)) - rt2x00pci_rxdone(rt2x00dev); + rt2x00pci_register_read(rt2x00dev, INT_MASK_CSR, ®); + rt2x00_set_field32(®, irq_field, 0); + rt2x00pci_register_write(rt2x00dev, INT_MASK_CSR, reg); - /* - * 2 - Tx ring done interrupt. - */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_TXDONE)) - rt61pci_txdone(rt2x00dev); + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} - /* - * 3 - Handle MCU command done. - */ - if (reg_mcu) - rt2x00pci_register_write(rt2x00dev, - M2H_CMD_DONE_CSR, 0xffffffff); +static void rt61pci_enable_mcu_interrupt(struct rt2x00_dev *rt2x00dev, + struct rt2x00_field32 irq_field) +{ + unsigned long flags; + u32 reg; /* - * 4 - MCU Autowakeup interrupt. + * Enable a single MCU interrupt. The interrupt mask register + * access needs locking. */ - if (rt2x00_get_field32(reg_mcu, MCU_INT_SOURCE_CSR_TWAKEUP)) - rt61pci_wakeup(rt2x00dev); + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); - /* - * 5 - Beacon done interrupt. - */ - if (rt2x00_get_field32(reg, INT_SOURCE_CSR_BEACON_DONE)) - rt2x00lib_beacondone(rt2x00dev); + rt2x00pci_register_read(rt2x00dev, MCU_INT_MASK_CSR, ®); + rt2x00_set_field32(®, irq_field, 0); + rt2x00pci_register_write(rt2x00dev, MCU_INT_MASK_CSR, reg); - /* Enable interrupts again. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_ON_ISR); - return IRQ_HANDLED; + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); +} + +static void rt61pci_txstatus_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt61pci_txdone(rt2x00dev); + rt61pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_TXDONE); +} + +static void rt61pci_tbtt_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00lib_beacondone(rt2x00dev); + rt61pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_BEACON_DONE); +} + +static void rt61pci_rxdone_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt2x00pci_rxdone(rt2x00dev); + rt61pci_enable_interrupt(rt2x00dev, INT_MASK_CSR_RXDONE); } +static void rt61pci_autowake_tasklet(unsigned long data) +{ + struct rt2x00_dev *rt2x00dev = (struct rt2x00_dev *)data; + rt61pci_wakeup(rt2x00dev); + rt2x00pci_register_write(rt2x00dev, + M2H_CMD_DONE_CSR, 0xffffffff); + rt61pci_enable_mcu_interrupt(rt2x00dev, MCU_INT_MASK_CSR_TWAKEUP); +} static irqreturn_t rt61pci_interrupt(int irq, void *dev_instance) { struct rt2x00_dev *rt2x00dev = dev_instance; - u32 reg_mcu; - u32 reg; + u32 reg_mcu, mask_mcu; + u32 reg, mask; + unsigned long flags; /* * Get the interrupt sources & saved to local variable. @@ -2283,14 +2341,46 @@ static irqreturn_t rt61pci_interrupt(int irq, void *dev_instance) if (!test_bit(DEVICE_STATE_ENABLED_RADIO, &rt2x00dev->flags)) return IRQ_HANDLED; - /* Store irqvalues for use in the interrupt thread. */ - rt2x00dev->irqvalue[0] = reg; - rt2x00dev->irqvalue[1] = reg_mcu; + /* + * Schedule tasklets for interrupt handling. + */ + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_RXDONE)) + tasklet_schedule(&rt2x00dev->rxdone_tasklet); + + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_TXDONE)) + tasklet_schedule(&rt2x00dev->txstatus_tasklet); - /* Disable interrupts, will be enabled again in the interrupt thread. */ - rt2x00dev->ops->lib->set_device_state(rt2x00dev, - STATE_RADIO_IRQ_OFF_ISR); - return IRQ_WAKE_THREAD; + if (rt2x00_get_field32(reg, INT_SOURCE_CSR_BEACON_DONE)) + tasklet_hi_schedule(&rt2x00dev->tbtt_tasklet); + + if (rt2x00_get_field32(reg_mcu, MCU_INT_SOURCE_CSR_TWAKEUP)) + tasklet_schedule(&rt2x00dev->autowake_tasklet); + + /* + * Since INT_MASK_CSR and INT_SOURCE_CSR use the same bits + * for interrupts and interrupt masks we can just use the value of + * INT_SOURCE_CSR to create the interrupt mask. + */ + mask = reg; + mask_mcu = reg_mcu; + + /* + * Disable all interrupts for which a tasklet was scheduled right now, + * the tasklet will reenable the appropriate interrupts. + */ + spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags); + + rt2x00pci_register_read(rt2x00dev, INT_MASK_CSR, ®); + reg |= mask; + rt2x00pci_register_write(rt2x00dev, INT_MASK_CSR, reg); + + rt2x00pci_register_read(rt2x00dev, MCU_INT_MASK_CSR, ®); + reg |= mask_mcu; + rt2x00pci_register_write(rt2x00dev, MCU_INT_MASK_CSR, reg); + + spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags); + + return IRQ_HANDLED; } /* @@ -2884,7 +2974,10 @@ static const struct ieee80211_ops rt61pci_mac80211_ops = { static const struct rt2x00lib_ops rt61pci_rt2x00_ops = { .irq_handler = rt61pci_interrupt, - .irq_handler_thread = rt61pci_interrupt_thread, + .txstatus_tasklet = rt61pci_txstatus_tasklet, + .tbtt_tasklet = rt61pci_tbtt_tasklet, + .rxdone_tasklet = rt61pci_rxdone_tasklet, + .autowake_tasklet = rt61pci_autowake_tasklet, .probe_hw = rt61pci_probe_hw, .get_firmware_name = rt61pci_get_firmware_name, .check_firmware = rt61pci_check_firmware, @@ -2903,6 +2996,7 @@ static const struct rt2x00lib_ops rt61pci_rt2x00_ops = { .stop_queue = rt61pci_stop_queue, .write_tx_desc = rt61pci_write_tx_desc, .write_beacon = rt61pci_write_beacon, + .clear_beacon = rt61pci_clear_beacon, .fill_rxdone = rt61pci_fill_rxdone, .config_shared_key = rt61pci_config_shared_key, .config_pairwise_key = rt61pci_config_pairwise_key, diff --git a/drivers/net/wireless/rt2x00/rt73usb.c b/drivers/net/wireless/rt2x00/rt73usb.c index 029be3c..5ff72de 100644 --- a/drivers/net/wireless/rt2x00/rt73usb.c +++ b/drivers/net/wireless/rt2x00/rt73usb.c @@ -502,26 +502,14 @@ static void rt73usb_config_intf(struct rt2x00_dev *rt2x00dev, struct rt2x00intf_conf *conf, const unsigned int flags) { - unsigned int beacon_base; u32 reg; if (flags & CONFIG_UPDATE_TYPE) { /* - * Clear current synchronisation setup. - * For the Beacon base registers we only need to clear - * the first byte since that byte contains the VALID and OWNER - * bits which (when set to 0) will invalidate the entire beacon. - */ - beacon_base = HW_BEACON_OFFSET(intf->beacon->entry_idx); - rt2x00usb_register_write(rt2x00dev, beacon_base, 0); - - /* * Enable synchronisation. */ rt2x00usb_register_read(rt2x00dev, TXRX_CSR9, ®); - rt2x00_set_field32(®, TXRX_CSR9_TSF_TICKING, 1); rt2x00_set_field32(®, TXRX_CSR9_TSF_SYNC, conf->sync); - rt2x00_set_field32(®, TXRX_CSR9_TBTT_ENABLE, 1); rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, reg); } @@ -1440,9 +1428,7 @@ static int rt73usb_set_device_state(struct rt2x00_dev *rt2x00dev, rt73usb_disable_radio(rt2x00dev); break; case STATE_RADIO_IRQ_ON: - case STATE_RADIO_IRQ_ON_ISR: case STATE_RADIO_IRQ_OFF: - case STATE_RADIO_IRQ_OFF_ISR: /* No support, but no error either */ break; case STATE_DEEP_SLEEP: @@ -1590,8 +1576,6 @@ static void rt73usb_write_beacon(struct queue_entry *entry, */ rt2x00usb_register_write(rt2x00dev, TXRX_CSR10, 0x00001008); - rt2x00_set_field32(®, TXRX_CSR9_TSF_TICKING, 1); - rt2x00_set_field32(®, TXRX_CSR9_TBTT_ENABLE, 1); rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 1); rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, reg); @@ -1602,6 +1586,33 @@ static void rt73usb_write_beacon(struct queue_entry *entry, entry->skb = NULL; } +static void rt73usb_clear_beacon(struct queue_entry *entry) +{ + struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev; + unsigned int beacon_base; + u32 reg; + + /* + * Disable beaconing while we are reloading the beacon data, + * otherwise we might be sending out invalid data. + */ + rt2x00usb_register_read(rt2x00dev, TXRX_CSR9, ®); + rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 0); + rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, reg); + + /* + * Clear beacon. + */ + beacon_base = HW_BEACON_OFFSET(entry->entry_idx); + rt2x00usb_register_write(rt2x00dev, beacon_base, 0); + + /* + * Enable beaconing again. + */ + rt2x00_set_field32(®, TXRX_CSR9_BEACON_GEN, 1); + rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, reg); +} + static int rt73usb_get_tx_data_len(struct queue_entry *entry) { int length; @@ -1698,9 +1709,8 @@ static void rt73usb_fill_rxdone(struct queue_entry *entry, rxdesc->flags |= RX_FLAG_IV_STRIPPED; /* - * FIXME: Legacy driver indicates that the frame does - * contain the Michael Mic. Unfortunately, in rt2x00 - * the MIC seems to be missing completely... + * The hardware has already checked the Michael Mic and has + * stripped it from the frame. Signal this to mac80211. */ rxdesc->flags |= RX_FLAG_MMIC_STRIPPED; @@ -2313,6 +2323,7 @@ static const struct rt2x00lib_ops rt73usb_rt2x00_ops = { .flush_queue = rt2x00usb_flush_queue, .write_tx_desc = rt73usb_write_tx_desc, .write_beacon = rt73usb_write_beacon, + .clear_beacon = rt73usb_clear_beacon, .get_tx_data_len = rt73usb_get_tx_data_len, .fill_rxdone = rt73usb_fill_rxdone, .config_shared_key = rt73usb_config_shared_key, diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c index d6a924a..25d2d66 100644 --- a/drivers/net/wireless/rtlwifi/core.c +++ b/drivers/net/wireless/rtlwifi/core.c @@ -748,7 +748,8 @@ static void rtl_op_sta_notify(struct ieee80211_hw *hw, static int rtl_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 * ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { struct rtl_priv *rtlpriv = rtl_priv(hw); diff --git a/drivers/net/wireless/wl1251/acx.c b/drivers/net/wireless/wl1251/acx.c index 64a0214..ef8370e 100644 --- a/drivers/net/wireless/wl1251/acx.c +++ b/drivers/net/wireless/wl1251/acx.c @@ -776,6 +776,31 @@ out: return ret; } +int wl1251_acx_low_rssi(struct wl1251 *wl, s8 threshold, u8 weight, + u8 depth, enum wl1251_acx_low_rssi_type type) +{ + struct acx_low_rssi *rssi; + int ret; + + wl1251_debug(DEBUG_ACX, "acx low rssi"); + + rssi = kzalloc(sizeof(*rssi), GFP_KERNEL); + if (!rssi) + return -ENOMEM; + + rssi->threshold = threshold; + rssi->weight = weight; + rssi->depth = depth; + rssi->type = type; + + ret = wl1251_cmd_configure(wl, ACX_LOW_RSSI, rssi, sizeof(*rssi)); + if (ret < 0) + wl1251_warning("failed to set low rssi threshold: %d", ret); + + kfree(rssi); + return ret; +} + int wl1251_acx_set_preamble(struct wl1251 *wl, enum acx_preamble_type preamble) { struct acx_preamble *acx; @@ -978,6 +1003,34 @@ out: return ret; } +int wl1251_acx_bet_enable(struct wl1251 *wl, enum wl1251_acx_bet_mode mode, + u8 max_consecutive) +{ + struct wl1251_acx_bet_enable *acx; + int ret; + + wl1251_debug(DEBUG_ACX, "acx bet enable"); + + acx = kzalloc(sizeof(*acx), GFP_KERNEL); + if (!acx) { + ret = -ENOMEM; + goto out; + } + + acx->enable = mode; + acx->max_consecutive = max_consecutive; + + ret = wl1251_cmd_configure(wl, ACX_BET_ENABLE, acx, sizeof(*acx)); + if (ret < 0) { + wl1251_warning("wl1251 acx bet enable failed: %d", ret); + goto out; + } + +out: + kfree(acx); + return ret; +} + int wl1251_acx_ac_cfg(struct wl1251 *wl, u8 ac, u8 cw_min, u16 cw_max, u8 aifs, u16 txop) { diff --git a/drivers/net/wireless/wl1251/acx.h b/drivers/net/wireless/wl1251/acx.h index efcc3aa..c2ba100 100644 --- a/drivers/net/wireless/wl1251/acx.h +++ b/drivers/net/wireless/wl1251/acx.h @@ -399,6 +399,49 @@ struct acx_rts_threshold { u8 pad[2]; } __packed; +enum wl1251_acx_low_rssi_type { + /* + * The event is a "Level" indication which keeps triggering + * as long as the average RSSI is below the threshold. + */ + WL1251_ACX_LOW_RSSI_TYPE_LEVEL = 0, + + /* + * The event is an "Edge" indication which triggers + * only when the RSSI threshold is crossed from above. + */ + WL1251_ACX_LOW_RSSI_TYPE_EDGE = 1, +}; + +struct acx_low_rssi { + struct acx_header header; + + /* + * The threshold (in dBm) below (or above after low rssi + * indication) which the firmware generates an interrupt to the + * host. This parameter is signed. + */ + s8 threshold; + + /* + * The weight of the current RSSI sample, before adding the new + * sample, that is used to calculate the average RSSI. + */ + u8 weight; + + /* + * The number of Beacons/Probe response frames that will be + * received before issuing the Low or Regained RSSI event. + */ + u8 depth; + + /* + * Configures how the Low RSSI Event is triggered. Refer to + * enum wl1251_acx_low_rssi_type for more. + */ + u8 type; +} __packed; + struct acx_beacon_filter_option { struct acx_header header; @@ -1164,6 +1207,31 @@ struct wl1251_acx_wr_tbtt_and_dtim { u8 padding; } __packed; +enum wl1251_acx_bet_mode { + WL1251_ACX_BET_DISABLE = 0, + WL1251_ACX_BET_ENABLE = 1, +}; + +struct wl1251_acx_bet_enable { + struct acx_header header; + + /* + * Specifies if beacon early termination procedure is enabled or + * disabled, see enum wl1251_acx_bet_mode. + */ + u8 enable; + + /* + * Specifies the maximum number of consecutive beacons that may be + * early terminated. After this number is reached at least one full + * beacon must be correctly received in FW before beacon ET + * resumes. Range 0 - 255. + */ + u8 max_consecutive; + + u8 padding[2]; +} __packed; + struct wl1251_acx_ac_cfg { struct acx_header header; @@ -1393,6 +1461,8 @@ int wl1251_acx_cca_threshold(struct wl1251 *wl); int wl1251_acx_bcn_dtim_options(struct wl1251 *wl); int wl1251_acx_aid(struct wl1251 *wl, u16 aid); int wl1251_acx_event_mbox_mask(struct wl1251 *wl, u32 event_mask); +int wl1251_acx_low_rssi(struct wl1251 *wl, s8 threshold, u8 weight, + u8 depth, enum wl1251_acx_low_rssi_type type); int wl1251_acx_set_preamble(struct wl1251 *wl, enum acx_preamble_type preamble); int wl1251_acx_cts_protect(struct wl1251 *wl, enum acx_ctsprotect_type ctsprotect); @@ -1401,6 +1471,8 @@ int wl1251_acx_tsf_info(struct wl1251 *wl, u64 *mactime); int wl1251_acx_rate_policies(struct wl1251 *wl); int wl1251_acx_mem_cfg(struct wl1251 *wl); int wl1251_acx_wr_tbtt_and_dtim(struct wl1251 *wl, u16 tbtt, u8 dtim); +int wl1251_acx_bet_enable(struct wl1251 *wl, enum wl1251_acx_bet_mode mode, + u8 max_consecutive); int wl1251_acx_ac_cfg(struct wl1251 *wl, u8 ac, u8 cw_min, u16 cw_max, u8 aifs, u16 txop); int wl1251_acx_tid_cfg(struct wl1251 *wl, u8 queue, diff --git a/drivers/net/wireless/wl1251/event.c b/drivers/net/wireless/wl1251/event.c index 712372e..dfc4579 100644 --- a/drivers/net/wireless/wl1251/event.c +++ b/drivers/net/wireless/wl1251/event.c @@ -90,6 +90,24 @@ static int wl1251_event_process(struct wl1251 *wl, struct event_mailbox *mbox) } } + if (wl->vif && wl->rssi_thold) { + if (vector & ROAMING_TRIGGER_LOW_RSSI_EVENT_ID) { + wl1251_debug(DEBUG_EVENT, + "ROAMING_TRIGGER_LOW_RSSI_EVENT"); + ieee80211_cqm_rssi_notify(wl->vif, + NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW, + GFP_KERNEL); + } + + if (vector & ROAMING_TRIGGER_REGAINED_RSSI_EVENT_ID) { + wl1251_debug(DEBUG_EVENT, + "ROAMING_TRIGGER_REGAINED_RSSI_EVENT"); + ieee80211_cqm_rssi_notify(wl->vif, + NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH, + GFP_KERNEL); + } + } + return 0; } diff --git a/drivers/net/wireless/wl1251/main.c b/drivers/net/wireless/wl1251/main.c index 40372ba..5a1c138 100644 --- a/drivers/net/wireless/wl1251/main.c +++ b/drivers/net/wireless/wl1251/main.c @@ -502,6 +502,7 @@ static void wl1251_op_stop(struct ieee80211_hw *hw) wl->psm = 0; wl->tx_queue_stopped = false; wl->power_level = WL1251_DEFAULT_POWER_LEVEL; + wl->rssi_thold = 0; wl->channel = WL1251_DEFAULT_CHANNEL; wl1251_debugfs_reset(wl); @@ -959,6 +960,16 @@ static void wl1251_op_bss_info_changed(struct ieee80211_hw *hw, if (ret < 0) goto out; + if (changed & BSS_CHANGED_CQM) { + ret = wl1251_acx_low_rssi(wl, bss_conf->cqm_rssi_thold, + WL1251_DEFAULT_LOW_RSSI_WEIGHT, + WL1251_DEFAULT_LOW_RSSI_DEPTH, + WL1251_ACX_LOW_RSSI_TYPE_EDGE); + if (ret < 0) + goto out; + wl->rssi_thold = bss_conf->cqm_rssi_thold; + } + if (changed & BSS_CHANGED_BSSID) { memcpy(wl->bssid, bss_conf->bssid, ETH_ALEN); @@ -1313,9 +1324,11 @@ int wl1251_init_ieee80211(struct wl1251 *wl) wl->hw->flags = IEEE80211_HW_SIGNAL_DBM | IEEE80211_HW_SUPPORTS_PS | IEEE80211_HW_BEACON_FILTER | - IEEE80211_HW_SUPPORTS_UAPSD; + IEEE80211_HW_SUPPORTS_UAPSD | + IEEE80211_HW_SUPPORTS_CQM_RSSI; - wl->hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); + wl->hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_ADHOC); wl->hw->wiphy->max_scan_ssids = 1; wl->hw->wiphy->bands[IEEE80211_BAND_2GHZ] = &wl1251_band_2ghz; @@ -1377,6 +1390,7 @@ struct ieee80211_hw *wl1251_alloc_hw(void) wl->psm_requested = false; wl->tx_queue_stopped = false; wl->power_level = WL1251_DEFAULT_POWER_LEVEL; + wl->rssi_thold = 0; wl->beacon_int = WL1251_DEFAULT_BEACON_INT; wl->dtim_period = WL1251_DEFAULT_DTIM_PERIOD; wl->vif = NULL; diff --git a/drivers/net/wireless/wl1251/ps.c b/drivers/net/wireless/wl1251/ps.c index 5ed47c8..9ba23ed 100644 --- a/drivers/net/wireless/wl1251/ps.c +++ b/drivers/net/wireless/wl1251/ps.c @@ -153,6 +153,11 @@ int wl1251_ps_set_mode(struct wl1251 *wl, enum wl1251_cmd_ps_mode mode) if (ret < 0) return ret; + ret = wl1251_acx_bet_enable(wl, WL1251_ACX_BET_ENABLE, + WL1251_DEFAULT_BET_CONSECUTIVE); + if (ret < 0) + return ret; + ret = wl1251_cmd_ps_mode(wl, STATION_POWER_SAVE_MODE); if (ret < 0) return ret; @@ -170,6 +175,12 @@ int wl1251_ps_set_mode(struct wl1251 *wl, enum wl1251_cmd_ps_mode mode) if (ret < 0) return ret; + /* disable BET */ + ret = wl1251_acx_bet_enable(wl, WL1251_ACX_BET_DISABLE, + WL1251_DEFAULT_BET_CONSECUTIVE); + if (ret < 0) + return ret; + /* disable beacon filtering */ ret = wl1251_acx_beacon_filter_opt(wl, false); if (ret < 0) diff --git a/drivers/net/wireless/wl1251/rx.c b/drivers/net/wireless/wl1251/rx.c index efa5360..b659e15 100644 --- a/drivers/net/wireless/wl1251/rx.c +++ b/drivers/net/wireless/wl1251/rx.c @@ -78,7 +78,8 @@ static void wl1251_rx_status(struct wl1251 *wl, */ wl->noise = desc->rssi - desc->snr / 2; - status->freq = ieee80211_channel_to_frequency(desc->channel); + status->freq = ieee80211_channel_to_frequency(desc->channel, + status->band); status->flag |= RX_FLAG_TSFT; @@ -95,8 +96,52 @@ static void wl1251_rx_status(struct wl1251 *wl, if (unlikely(!(desc->flags & RX_DESC_VALID_FCS))) status->flag |= RX_FLAG_FAILED_FCS_CRC; + switch (desc->rate) { + /* skip 1 and 12 Mbps because they have same value 0x0a */ + case RATE_2MBPS: + status->rate_idx = 1; + break; + case RATE_5_5MBPS: + status->rate_idx = 2; + break; + case RATE_11MBPS: + status->rate_idx = 3; + break; + case RATE_6MBPS: + status->rate_idx = 4; + break; + case RATE_9MBPS: + status->rate_idx = 5; + break; + case RATE_18MBPS: + status->rate_idx = 7; + break; + case RATE_24MBPS: + status->rate_idx = 8; + break; + case RATE_36MBPS: + status->rate_idx = 9; + break; + case RATE_48MBPS: + status->rate_idx = 10; + break; + case RATE_54MBPS: + status->rate_idx = 11; + break; + } + + /* for 1 and 12 Mbps we have to check the modulation */ + if (desc->rate == RATE_1MBPS) { + if (!(desc->mod_pre & OFDM_RATE_BIT)) + /* CCK -> RATE_1MBPS */ + status->rate_idx = 0; + else + /* OFDM -> RATE_12MBPS */ + status->rate_idx = 6; + } - /* FIXME: set status->rate_idx */ + if (desc->mod_pre & SHORT_PREAMBLE_BIT) + status->flag |= RX_FLAG_SHORTPRE; } static void wl1251_rx_body(struct wl1251 *wl, diff --git a/drivers/net/wireless/wl1251/tx.c b/drivers/net/wireless/wl1251/tx.c index 554b4f9..28121c5 100644 --- a/drivers/net/wireless/wl1251/tx.c +++ b/drivers/net/wireless/wl1251/tx.c @@ -213,16 +213,30 @@ static int wl1251_tx_send_packet(struct wl1251 *wl, struct sk_buff *skb, wl1251_debug(DEBUG_TX, "skb offset %d", offset); /* check whether the current skb can be used */ - if (!skb_cloned(skb) && (skb_tailroom(skb) >= offset)) { - unsigned char *src = skb->data; + if (skb_cloned(skb) || (skb_tailroom(skb) < offset)) { + struct sk_buff *newskb = skb_copy_expand(skb, 0, 3, + GFP_KERNEL); + + if (unlikely(newskb == NULL)) { + wl1251_error("Can't allocate skb!"); + return -EINVAL; + } - /* align the buffer on a 4-byte boundary */ + tx_hdr = (struct tx_double_buffer_desc *) newskb->data; + + dev_kfree_skb_any(skb); + wl->tx_frames[tx_hdr->id] = skb = newskb; + + offset = (4 - (long)skb->data) & 0x03; + wl1251_debug(DEBUG_TX, "new skb offset %d", offset); + } + + /* align the buffer on a 4-byte boundary */ + if (offset) { + unsigned char *src = skb->data; skb_reserve(skb, offset); memmove(skb->data, src, skb->len); tx_hdr = (struct tx_double_buffer_desc *) skb->data; - } else { - wl1251_info("No handler, fixme!"); - return -EINVAL; } } @@ -368,7 +382,7 @@ static void wl1251_tx_packet_cb(struct wl1251 *wl, { struct ieee80211_tx_info *info; struct sk_buff *skb; - int hdrlen, ret; + int hdrlen; u8 *frame; skb = wl->tx_frames[result->id]; @@ -407,40 +421,12 @@ static void wl1251_tx_packet_cb(struct wl1251 *wl, ieee80211_tx_status(wl->hw, skb); wl->tx_frames[result->id] = NULL; - - if (wl->tx_queue_stopped) { - wl1251_debug(DEBUG_TX, "cb: queue was stopped"); - - skb = skb_dequeue(&wl->tx_queue); - - /* The skb can be NULL because tx_work might have been - scheduled before the queue was stopped making the - queue empty */ - - if (skb) { - ret = wl1251_tx_frame(wl, skb); - if (ret == -EBUSY) { - /* firmware buffer is still full */ - wl1251_debug(DEBUG_TX, "cb: fw buffer " - "still full"); - skb_queue_head(&wl->tx_queue, skb); - return; - } else if (ret < 0) { - dev_kfree_skb(skb); - return; - } - } - - wl1251_debug(DEBUG_TX, "cb: waking queues"); - ieee80211_wake_queues(wl->hw); - wl->tx_queue_stopped = false; - } } /* Called upon reception of a TX complete interrupt */ void wl1251_tx_complete(struct wl1251 *wl) { - int i, result_index, num_complete = 0; + int i, result_index, num_complete = 0, queue_len; struct tx_result result[FW_TX_CMPLT_BLOCK_SIZE], *result_ptr; unsigned long flags; @@ -471,18 +457,22 @@ void wl1251_tx_complete(struct wl1251 *wl) } } - if (wl->tx_queue_stopped - && - skb_queue_len(&wl->tx_queue) <= WL1251_TX_QUEUE_LOW_WATERMARK){ + queue_len = skb_queue_len(&wl->tx_queue); - /* firmware buffer has space, restart queues */ + if ((num_complete > 0) && (queue_len > 0)) { + /* firmware buffer has space, reschedule tx_work */ + wl1251_debug(DEBUG_TX, "tx_complete: reschedule tx_work"); + ieee80211_queue_work(wl->hw, &wl->tx_work); + } + + if (wl->tx_queue_stopped && + queue_len <= WL1251_TX_QUEUE_LOW_WATERMARK) { + /* tx_queue has space, restart queues */ wl1251_debug(DEBUG_TX, "tx_complete: waking queues"); spin_lock_irqsave(&wl->wl_lock, flags); ieee80211_wake_queues(wl->hw); wl->tx_queue_stopped = false; spin_unlock_irqrestore(&wl->wl_lock, flags); - ieee80211_queue_work(wl->hw, &wl->tx_work); - } /* Every completed frame needs to be acknowledged */ diff --git a/drivers/net/wireless/wl1251/wl1251.h b/drivers/net/wireless/wl1251/wl1251.h index c0ce2c8..bb23cd5 100644 --- a/drivers/net/wireless/wl1251/wl1251.h +++ b/drivers/net/wireless/wl1251/wl1251.h @@ -370,6 +370,8 @@ struct wl1251 { /* in dBm */ int power_level; + int rssi_thold; + struct wl1251_stats stats; struct wl1251_debugfs debugfs; @@ -410,6 +412,8 @@ void wl1251_disable_interrupts(struct wl1251 *wl); #define WL1251_DEFAULT_CHANNEL 0 +#define WL1251_DEFAULT_BET_CONSECUTIVE 10 + #define CHIP_ID_1251_PG10 (0x7010101) #define CHIP_ID_1251_PG11 (0x7020101) #define CHIP_ID_1251_PG12 (0x7030101) @@ -431,4 +435,7 @@ void wl1251_disable_interrupts(struct wl1251 *wl); #define WL1251_PART_WORK_REG_START REGISTERS_BASE #define WL1251_PART_WORK_REG_SIZE REGISTERS_WORK_SIZE +#define WL1251_DEFAULT_LOW_RSSI_WEIGHT 10 +#define WL1251_DEFAULT_LOW_RSSI_DEPTH 10 + #endif diff --git a/drivers/net/wireless/wl12xx/acx.c b/drivers/net/wireless/wl12xx/acx.c index cc4068d..afdc601 100644 --- a/drivers/net/wireless/wl12xx/acx.c +++ b/drivers/net/wireless/wl12xx/acx.c @@ -751,10 +751,10 @@ int wl1271_acx_statistics(struct wl1271 *wl, struct acx_statistics *stats) return 0; } -int wl1271_acx_rate_policies(struct wl1271 *wl) +int wl1271_acx_sta_rate_policies(struct wl1271 *wl) { - struct acx_rate_policy *acx; - struct conf_tx_rate_class *c = &wl->conf.tx.rc_conf; + struct acx_sta_rate_policy *acx; + struct conf_tx_rate_class *c = &wl->conf.tx.sta_rc_conf; int idx = 0; int ret = 0; @@ -794,6 +794,38 @@ out: return ret; } +int wl1271_acx_ap_rate_policy(struct wl1271 *wl, struct conf_tx_rate_class *c, + u8 idx) +{ + struct acx_ap_rate_policy *acx; + int ret = 0; + + wl1271_debug(DEBUG_ACX, "acx ap rate policy"); + + acx = kzalloc(sizeof(*acx), GFP_KERNEL); + if (!acx) { + ret = -ENOMEM; + goto out; + } + + acx->rate_policy.enabled_rates = cpu_to_le32(c->enabled_rates); + acx->rate_policy.short_retry_limit = c->short_retry_limit; + acx->rate_policy.long_retry_limit = c->long_retry_limit; + acx->rate_policy.aflags = c->aflags; + + acx->rate_policy_idx = cpu_to_le32(idx); + + ret = wl1271_cmd_configure(wl, ACX_RATE_POLICY, acx, sizeof(*acx)); + if (ret < 0) { + wl1271_warning("Setting of ap rate policy failed: %d", ret); + goto out; + } + +out: + kfree(acx); + return ret; +} + int wl1271_acx_ac_cfg(struct wl1271 *wl, u8 ac, u8 cw_min, u16 cw_max, u8 aifsn, u16 txop) { @@ -1233,6 +1265,7 @@ int wl1271_acx_set_ht_capabilities(struct wl1271 *wl, struct wl1271_acx_ht_capabilities *acx; u8 mac_address[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; int ret = 0; + u32 ht_capabilites = 0; wl1271_debug(DEBUG_ACX, "acx ht capabilities setting"); @@ -1244,16 +1277,16 @@ int wl1271_acx_set_ht_capabilities(struct wl1271 *wl, /* Allow HT Operation ? */ if (allow_ht_operation) { - acx->ht_capabilites = + ht_capabilites = WL1271_ACX_FW_CAP_HT_OPERATION; if (ht_cap->cap & IEEE80211_HT_CAP_GRN_FLD) - acx->ht_capabilites |= + ht_capabilites |= WL1271_ACX_FW_CAP_GREENFIELD_FRAME_FORMAT; if (ht_cap->cap & IEEE80211_HT_CAP_SGI_20) - acx->ht_capabilites |= + ht_capabilites |= WL1271_ACX_FW_CAP_SHORT_GI_FOR_20MHZ_PACKETS; if (ht_cap->cap & IEEE80211_HT_CAP_LSIG_TXOP_PROT) - acx->ht_capabilites |= + ht_capabilites |= WL1271_ACX_FW_CAP_LSIG_TXOP_PROTECTION; /* get data from A-MPDU parameters field */ @@ -1261,10 +1294,10 @@ int wl1271_acx_set_ht_capabilities(struct wl1271 *wl, acx->ampdu_min_spacing = ht_cap->ampdu_density; memcpy(acx->mac_address, mac_address, ETH_ALEN); - } else { /* HT operations are not allowed */ - acx->ht_capabilites = 0; } + acx->ht_capabilites = cpu_to_le32(ht_capabilites); + ret = wl1271_cmd_configure(wl, ACX_PEER_HT_CAP, acx, sizeof(*acx)); if (ret < 0) { wl1271_warning("acx ht capabilities setting failed: %d", ret); @@ -1309,6 +1342,91 @@ out: return ret; } +/* Configure BA session initiator/receiver parameters setting in the FW. */ +int wl1271_acx_set_ba_session(struct wl1271 *wl, + enum ieee80211_back_parties direction, + u8 tid_index, u8 policy) +{ + struct wl1271_acx_ba_session_policy *acx; + int ret; + + wl1271_debug(DEBUG_ACX, "acx ba session setting"); + + acx = kzalloc(sizeof(*acx), GFP_KERNEL); + if (!acx) { + ret = -ENOMEM; + goto out; + } + + /* ANY role */ + acx->role_id = 0xff; + acx->tid = tid_index; + acx->enable = policy; + acx->ba_direction = direction; + + switch (direction) { + case WLAN_BACK_INITIATOR: + acx->win_size = wl->conf.ht.tx_ba_win_size; + acx->inactivity_timeout = wl->conf.ht.inactivity_timeout; + break; + case WLAN_BACK_RECIPIENT: + acx->win_size = RX_BA_WIN_SIZE; + acx->inactivity_timeout = 0; + break; + default: + wl1271_error("Incorrect acx command id=%x\n", direction); + ret = -EINVAL; + goto out; + } + + ret = wl1271_cmd_configure(wl, + ACX_BA_SESSION_POLICY_CFG, + acx, + sizeof(*acx)); + if (ret < 0) { + wl1271_warning("acx ba session setting failed: %d", ret); + goto out; + } + +out: + kfree(acx); + return ret; +} + +/* setup BA session receiver setting in the FW. */ +int wl1271_acx_set_ba_receiver_session(struct wl1271 *wl, u8 tid_index, u16 ssn, + bool enable) +{ + struct wl1271_acx_ba_receiver_setup *acx; + int ret; + + wl1271_debug(DEBUG_ACX, "acx ba receiver session setting"); + + acx = kzalloc(sizeof(*acx), GFP_KERNEL); + if (!acx) { + ret = -ENOMEM; + goto out; + } + + /* Single link for now */ + acx->link_id = 1; + acx->tid = tid_index; + acx->enable = enable; + acx->win_size = 0; + acx->ssn = ssn; + + ret = wl1271_cmd_configure(wl, ACX_BA_SESSION_RX_SETUP, acx, + sizeof(*acx)); + if (ret < 0) { + wl1271_warning("acx ba receiver session failed: %d", ret); + goto out; + } + +out: + kfree(acx); + return ret; +} + int wl1271_acx_tsf_info(struct wl1271 *wl, u64 *mactime) { struct wl1271_acx_fw_tsf_information *tsf_info; @@ -1334,3 +1452,27 @@ out: kfree(tsf_info); return ret; } + +int wl1271_acx_max_tx_retry(struct wl1271 *wl) +{ + struct wl1271_acx_max_tx_retry *acx = NULL; + int ret; + + wl1271_debug(DEBUG_ACX, "acx max tx retry"); + + acx = kzalloc(sizeof(*acx), GFP_KERNEL); + if (!acx) + return -ENOMEM; + + acx->max_tx_retry = cpu_to_le16(wl->conf.tx.ap_max_tx_retries); + + ret = wl1271_cmd_configure(wl, ACX_MAX_TX_FAILURE, acx, sizeof(*acx)); + if (ret < 0) { + wl1271_warning("acx max tx retry failed: %d", ret); + goto out; + } + +out: + kfree(acx); + return ret; +} diff --git a/drivers/net/wireless/wl12xx/acx.h b/drivers/net/wireless/wl12xx/acx.h index 7bd8e4d..4bbaf04 100644 --- a/drivers/net/wireless/wl12xx/acx.h +++ b/drivers/net/wireless/wl12xx/acx.h @@ -747,13 +747,23 @@ struct acx_rate_class { #define ACX_TX_BASIC_RATE 0 #define ACX_TX_AP_FULL_RATE 1 #define ACX_TX_RATE_POLICY_CNT 2 -struct acx_rate_policy { +struct acx_sta_rate_policy { struct acx_header header; __le32 rate_class_cnt; struct acx_rate_class rate_class[CONF_TX_MAX_RATE_CLASSES]; } __packed; + +#define ACX_TX_AP_MODE_MGMT_RATE 4 +#define ACX_TX_AP_MODE_BCST_RATE 5 +struct acx_ap_rate_policy { + struct acx_header header; + + __le32 rate_policy_idx; + struct acx_rate_class rate_policy; +} __packed; + struct acx_ac_cfg { struct acx_header header; u8 ac; @@ -1051,6 +1061,59 @@ struct wl1271_acx_ht_information { u8 padding[3]; } __packed; +#define RX_BA_WIN_SIZE 8 + +struct wl1271_acx_ba_session_policy { + struct acx_header header; + /* + * Specifies role Id, Range 0-7, 0xFF means ANY role. + * Future use. For now this field is irrelevant + */ + u8 role_id; + /* + * Specifies Link Id, Range 0-31, 0xFF means ANY Link Id. + * Not applicable if Role Id is set to ANY. + */ + u8 link_id; + + u8 tid; + + u8 enable; + + /* Windows size in number of packets */ + u16 win_size; + + /* + * As initiator inactivity timeout in time units(TU) of 1024us. + * As receiver reserved + */ + u16 inactivity_timeout; + + /* Initiator = 1/Receiver = 0 */ + u8 ba_direction; + + u8 padding[3]; +} __packed; + +struct wl1271_acx_ba_receiver_setup { + struct acx_header header; + + /* Specifies Link Id, Range 0-31, 0xFF means ANY Link Id */ + u8 link_id; + + u8 tid; + + u8 enable; + + u8 padding[1]; + + /* Windows size in number of packets */ + u16 win_size; + + /* BA session starting sequence number. RANGE 0-FFF */ + u16 ssn; +} __packed; + struct wl1271_acx_fw_tsf_information { struct acx_header header; @@ -1062,6 +1125,17 @@ struct wl1271_acx_fw_tsf_information { u8 padding[3]; } __packed; +struct wl1271_acx_max_tx_retry { + struct acx_header header; + + /* + * the number of frames transmission failures before + * issuing the aging event. + */ + __le16 max_tx_retry; + u8 padding_1[2]; +} __packed; + enum { ACX_WAKE_UP_CONDITIONS = 0x0002, ACX_MEM_CFG = 0x0003, @@ -1113,12 +1187,13 @@ enum { ACX_RSSI_SNR_WEIGHTS = 0x0052, ACX_KEEP_ALIVE_MODE = 0x0053, ACX_SET_KEEP_ALIVE_CONFIG = 0x0054, - ACX_BA_SESSION_RESPONDER_POLICY = 0x0055, - ACX_BA_SESSION_INITIATOR_POLICY = 0x0056, + ACX_BA_SESSION_POLICY_CFG = 0x0055, + ACX_BA_SESSION_RX_SETUP = 0x0056, ACX_PEER_HT_CAP = 0x0057, ACX_HT_BSS_OPERATION = 0x0058, ACX_COEX_ACTIVITY = 0x0059, ACX_SET_DCO_ITRIM_PARAMS = 0x0061, + ACX_MAX_TX_FAILURE = 0x0072, DOT11_RX_MSDU_LIFE_TIME = 0x1004, DOT11_CUR_TX_PWR = 0x100D, DOT11_RX_DOT11_MODE = 0x1012, @@ -1160,7 +1235,9 @@ int wl1271_acx_set_preamble(struct wl1271 *wl, enum acx_preamble_type preamble); int wl1271_acx_cts_protect(struct wl1271 *wl, enum acx_ctsprotect_type ctsprotect); int wl1271_acx_statistics(struct wl1271 *wl, struct acx_statistics *stats); -int wl1271_acx_rate_policies(struct wl1271 *wl); +int wl1271_acx_sta_rate_policies(struct wl1271 *wl); +int wl1271_acx_ap_rate_policy(struct wl1271 *wl, struct conf_tx_rate_class *c, + u8 idx); int wl1271_acx_ac_cfg(struct wl1271 *wl, u8 ac, u8 cw_min, u16 cw_max, u8 aifsn, u16 txop); int wl1271_acx_tid_cfg(struct wl1271 *wl, u8 queue_id, u8 channel_type, @@ -1185,6 +1262,12 @@ int wl1271_acx_set_ht_capabilities(struct wl1271 *wl, bool allow_ht_operation); int wl1271_acx_set_ht_information(struct wl1271 *wl, u16 ht_operation_mode); +int wl1271_acx_set_ba_session(struct wl1271 *wl, + enum ieee80211_back_parties direction, + u8 tid_index, u8 policy); +int wl1271_acx_set_ba_receiver_session(struct wl1271 *wl, u8 tid_index, u16 ssn, + bool enable); int wl1271_acx_tsf_info(struct wl1271 *wl, u64 *mactime); +int wl1271_acx_max_tx_retry(struct wl1271 *wl); #endif /* __WL1271_ACX_H__ */ diff --git a/drivers/net/wireless/wl12xx/boot.c b/drivers/net/wireless/wl12xx/boot.c index 4df04f8..1ffbad6 100644 --- a/drivers/net/wireless/wl12xx/boot.c +++ b/drivers/net/wireless/wl12xx/boot.c @@ -28,6 +28,7 @@ #include "boot.h" #include "io.h" #include "event.h" +#include "rx.h" static struct wl1271_partition_set part_table[PART_TABLE_LEN] = { [PART_DOWN] = { @@ -100,6 +101,22 @@ static void wl1271_boot_set_ecpu_ctrl(struct wl1271 *wl, u32 flag) wl1271_write32(wl, ACX_REG_ECPU_CONTROL, cpu_ctrl); } +static void wl1271_parse_fw_ver(struct wl1271 *wl) +{ + int ret; + + ret = sscanf(wl->chip.fw_ver_str + 4, "%u.%u.%u.%u.%u", + &wl->chip.fw_ver[0], &wl->chip.fw_ver[1], + &wl->chip.fw_ver[2], &wl->chip.fw_ver[3], + &wl->chip.fw_ver[4]); + + if (ret != 5) { + wl1271_warning("fw version incorrect value"); + memset(wl->chip.fw_ver, 0, sizeof(wl->chip.fw_ver)); + return; + } +} + static void wl1271_boot_fw_version(struct wl1271 *wl) { struct wl1271_static_data static_data; @@ -107,11 +124,13 @@ static void wl1271_boot_fw_version(struct wl1271 *wl) wl1271_read(wl, wl->cmd_box_addr, &static_data, sizeof(static_data), false); - strncpy(wl->chip.fw_ver, static_data.fw_version, - sizeof(wl->chip.fw_ver)); + strncpy(wl->chip.fw_ver_str, static_data.fw_version, + sizeof(wl->chip.fw_ver_str)); /* make sure the string is NULL-terminated */ - wl->chip.fw_ver[sizeof(wl->chip.fw_ver) - 1] = '\0'; + wl->chip.fw_ver_str[sizeof(wl->chip.fw_ver_str) - 1] = '\0'; + + wl1271_parse_fw_ver(wl); } static int wl1271_boot_upload_firmware_chunk(struct wl1271 *wl, void *buf, @@ -231,7 +250,9 @@ static int wl1271_boot_upload_nvs(struct wl1271 *wl) */ if (wl->nvs_len == sizeof(struct wl1271_nvs_file) || wl->nvs_len == WL1271_INI_LEGACY_NVS_FILE_SIZE) { - if (wl->nvs->general_params.dual_mode_select) + /* for now 11a is unsupported in AP mode */ + if (wl->bss_type != BSS_TYPE_AP_BSS && + wl->nvs->general_params.dual_mode_select) wl->enable_11a = true; } @@ -431,6 +452,9 @@ static int wl1271_boot_run_firmware(struct wl1271 *wl) PSPOLL_DELIVERY_FAILURE_EVENT_ID | SOFT_GEMINI_SENSE_EVENT_ID; + if (wl->bss_type == BSS_TYPE_AP_BSS) + wl->event_mask |= STA_REMOVE_COMPLETE_EVENT_ID; + ret = wl1271_event_unmask(wl); if (ret < 0) { wl1271_error("EVENT mask setting failed"); @@ -595,8 +619,7 @@ int wl1271_boot(struct wl1271 *wl) wl1271_boot_enable_interrupts(wl); /* set the wl1271 default filters */ - wl->rx_config = WL1271_DEFAULT_RX_CONFIG; - wl->rx_filter = WL1271_DEFAULT_RX_FILTER; + wl1271_set_default_filters(wl); wl1271_event_mbox_config(wl); diff --git a/drivers/net/wireless/wl12xx/cmd.c b/drivers/net/wireless/wl12xx/cmd.c index 0106628..1bb8be5 100644 --- a/drivers/net/wireless/wl12xx/cmd.c +++ b/drivers/net/wireless/wl12xx/cmd.c @@ -36,6 +36,7 @@ #include "wl12xx_80211.h" #include "cmd.h" #include "event.h" +#include "tx.h" #define WL1271_CMD_FAST_POLL_COUNT 50 @@ -221,7 +222,7 @@ int wl1271_cmd_ext_radio_parms(struct wl1271 *wl) * Poll the mailbox event field until any of the bits in the mask is set or a * timeout occurs (WL1271_EVENT_TIMEOUT in msecs) */ -static int wl1271_cmd_wait_for_event(struct wl1271 *wl, u32 mask) +static int wl1271_cmd_wait_for_event_or_timeout(struct wl1271 *wl, u32 mask) { u32 events_vector, event; unsigned long timeout; @@ -230,7 +231,8 @@ static int wl1271_cmd_wait_for_event(struct wl1271 *wl, u32 mask) do { if (time_after(jiffies, timeout)) { - ieee80211_queue_work(wl->hw, &wl->recovery_work); + wl1271_debug(DEBUG_CMD, "timeout waiting for event %d", + (int)mask); return -ETIMEDOUT; } @@ -248,6 +250,19 @@ static int wl1271_cmd_wait_for_event(struct wl1271 *wl, u32 mask) return 0; } +static int wl1271_cmd_wait_for_event(struct wl1271 *wl, u32 mask) +{ + int ret; + + ret = wl1271_cmd_wait_for_event_or_timeout(wl, mask); + if (ret != 0) { + ieee80211_queue_work(wl->hw, &wl->recovery_work); + return ret; + } + + return 0; +} + int wl1271_cmd_join(struct wl1271 *wl, u8 bss_type) { struct wl1271_cmd_join *join; @@ -490,8 +505,8 @@ int wl1271_cmd_template_set(struct wl1271 *wl, u16 template_id, cmd->len = cpu_to_le16(buf_len); cmd->template_type = template_id; cmd->enabled_rates = cpu_to_le32(rates); - cmd->short_retry_limit = wl->conf.tx.rc_conf.short_retry_limit; - cmd->long_retry_limit = wl->conf.tx.rc_conf.long_retry_limit; + cmd->short_retry_limit = wl->conf.tx.tmpl_short_retry_limit; + cmd->long_retry_limit = wl->conf.tx.tmpl_long_retry_limit; cmd->index = index; if (buf) @@ -659,15 +674,15 @@ int wl1271_cmd_build_arp_rsp(struct wl1271 *wl, __be32 ip_addr) /* llc layer */ memcpy(tmpl.llc_hdr, rfc1042_header, sizeof(rfc1042_header)); - tmpl.llc_type = htons(ETH_P_ARP); + tmpl.llc_type = cpu_to_be16(ETH_P_ARP); /* arp header */ arp_hdr = &tmpl.arp_hdr; - arp_hdr->ar_hrd = htons(ARPHRD_ETHER); - arp_hdr->ar_pro = htons(ETH_P_IP); + arp_hdr->ar_hrd = cpu_to_be16(ARPHRD_ETHER); + arp_hdr->ar_pro = cpu_to_be16(ETH_P_IP); arp_hdr->ar_hln = ETH_ALEN; arp_hdr->ar_pln = 4; - arp_hdr->ar_op = htons(ARPOP_REPLY); + arp_hdr->ar_op = cpu_to_be16(ARPOP_REPLY); /* arp payload */ memcpy(tmpl.sender_hw, wl->vif->addr, ETH_ALEN); @@ -702,9 +717,9 @@ int wl1271_build_qos_null_data(struct wl1271 *wl) wl->basic_rate); } -int wl1271_cmd_set_default_wep_key(struct wl1271 *wl, u8 id) +int wl1271_cmd_set_sta_default_wep_key(struct wl1271 *wl, u8 id) { - struct wl1271_cmd_set_keys *cmd; + struct wl1271_cmd_set_sta_keys *cmd; int ret = 0; wl1271_debug(DEBUG_CMD, "cmd set_default_wep_key %d", id); @@ -731,11 +746,42 @@ out: return ret; } -int wl1271_cmd_set_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, +int wl1271_cmd_set_ap_default_wep_key(struct wl1271 *wl, u8 id) +{ + struct wl1271_cmd_set_ap_keys *cmd; + int ret = 0; + + wl1271_debug(DEBUG_CMD, "cmd set_ap_default_wep_key %d", id); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + ret = -ENOMEM; + goto out; + } + + cmd->hlid = WL1271_AP_BROADCAST_HLID; + cmd->key_id = id; + cmd->lid_key_type = WEP_DEFAULT_LID_TYPE; + cmd->key_action = cpu_to_le16(KEY_SET_ID); + cmd->key_type = KEY_WEP; + + ret = wl1271_cmd_send(wl, CMD_SET_KEYS, cmd, sizeof(*cmd), 0); + if (ret < 0) { + wl1271_warning("cmd set_ap_default_wep_key failed: %d", ret); + goto out; + } + +out: + kfree(cmd); + + return ret; +} + +int wl1271_cmd_set_sta_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, u8 key_size, const u8 *key, const u8 *addr, u32 tx_seq_32, u16 tx_seq_16) { - struct wl1271_cmd_set_keys *cmd; + struct wl1271_cmd_set_sta_keys *cmd; int ret = 0; cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); @@ -788,6 +834,67 @@ out: return ret; } +int wl1271_cmd_set_ap_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, + u8 key_size, const u8 *key, u8 hlid, u32 tx_seq_32, + u16 tx_seq_16) +{ + struct wl1271_cmd_set_ap_keys *cmd; + int ret = 0; + u8 lid_type; + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + if (hlid == WL1271_AP_BROADCAST_HLID) { + if (key_type == KEY_WEP) + lid_type = WEP_DEFAULT_LID_TYPE; + else + lid_type = BROADCAST_LID_TYPE; + } else { + lid_type = UNICAST_LID_TYPE; + } + + wl1271_debug(DEBUG_CRYPT, "ap key action: %d id: %d lid: %d type: %d" + " hlid: %d", (int)action, (int)id, (int)lid_type, + (int)key_type, (int)hlid); + + cmd->lid_key_type = lid_type; + cmd->hlid = hlid; + cmd->key_action = cpu_to_le16(action); + cmd->key_size = key_size; + cmd->key_type = key_type; + cmd->key_id = id; + cmd->ac_seq_num16[0] = cpu_to_le16(tx_seq_16); + cmd->ac_seq_num32[0] = cpu_to_le32(tx_seq_32); + + if (key_type == KEY_TKIP) { + /* + * We get the key in the following form: + * TKIP (16 bytes) - TX MIC (8 bytes) - RX MIC (8 bytes) + * but the target is expecting: + * TKIP - RX MIC - TX MIC + */ + memcpy(cmd->key, key, 16); + memcpy(cmd->key + 16, key + 24, 8); + memcpy(cmd->key + 24, key + 16, 8); + } else { + memcpy(cmd->key, key, key_size); + } + + wl1271_dump(DEBUG_CRYPT, "TARGET AP KEY: ", cmd, sizeof(*cmd)); + + ret = wl1271_cmd_send(wl, CMD_SET_KEYS, cmd, sizeof(*cmd), 0); + if (ret < 0) { + wl1271_warning("could not set ap keys"); + goto out; + } + +out: + kfree(cmd); + return ret; +} + int wl1271_cmd_disconnect(struct wl1271 *wl) { struct wl1271_cmd_disconnect *cmd; @@ -850,3 +957,180 @@ out_free: out: return ret; } + +int wl1271_cmd_start_bss(struct wl1271 *wl) +{ + struct wl1271_cmd_bss_start *cmd; + struct ieee80211_bss_conf *bss_conf = &wl->vif->bss_conf; + int ret; + + wl1271_debug(DEBUG_CMD, "cmd start bss"); + + /* + * FIXME: We currently do not support hidden SSID. The real SSID + * should be fetched from mac80211 first. + */ + if (wl->ssid_len == 0) { + wl1271_warning("Hidden SSID currently not supported for AP"); + ret = -EINVAL; + goto out; + } + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + ret = -ENOMEM; + goto out; + } + + memcpy(cmd->bssid, bss_conf->bssid, ETH_ALEN); + + cmd->aging_period = cpu_to_le16(WL1271_AP_DEF_INACTIV_SEC); + cmd->bss_index = WL1271_AP_BSS_INDEX; + cmd->global_hlid = WL1271_AP_GLOBAL_HLID; + cmd->broadcast_hlid = WL1271_AP_BROADCAST_HLID; + cmd->basic_rate_set = cpu_to_le32(wl->basic_rate_set); + cmd->beacon_interval = cpu_to_le16(wl->beacon_int); + cmd->dtim_interval = bss_conf->dtim_period; + cmd->beacon_expiry = WL1271_AP_DEF_BEACON_EXP; + cmd->channel = wl->channel; + cmd->ssid_len = wl->ssid_len; + cmd->ssid_type = SSID_TYPE_PUBLIC; + memcpy(cmd->ssid, wl->ssid, wl->ssid_len); + + switch (wl->band) { + case IEEE80211_BAND_2GHZ: + cmd->band = RADIO_BAND_2_4GHZ; + break; + case IEEE80211_BAND_5GHZ: + cmd->band = RADIO_BAND_5GHZ; + break; + default: + wl1271_warning("bss start - unknown band: %d", (int)wl->band); + cmd->band = RADIO_BAND_2_4GHZ; + break; + } + + ret = wl1271_cmd_send(wl, CMD_BSS_START, cmd, sizeof(*cmd), 0); + if (ret < 0) { + wl1271_error("failed to initiate cmd start bss"); + goto out_free; + } + +out_free: + kfree(cmd); + +out: + return ret; +} + +int wl1271_cmd_stop_bss(struct wl1271 *wl) +{ + struct wl1271_cmd_bss_start *cmd; + int ret; + + wl1271_debug(DEBUG_CMD, "cmd stop bss"); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + ret = -ENOMEM; + goto out; + } + + cmd->bss_index = WL1271_AP_BSS_INDEX; + + ret = wl1271_cmd_send(wl, CMD_BSS_STOP, cmd, sizeof(*cmd), 0); + if (ret < 0) { + wl1271_error("failed to initiate cmd stop bss"); + goto out_free; + } + +out_free: + kfree(cmd); + +out: + return ret; +} + +int wl1271_cmd_add_sta(struct wl1271 *wl, struct ieee80211_sta *sta, u8 hlid) +{ + struct wl1271_cmd_add_sta *cmd; + int ret; + + wl1271_debug(DEBUG_CMD, "cmd add sta %d", (int)hlid); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + ret = -ENOMEM; + goto out; + } + + /* currently we don't support UAPSD */ + cmd->sp_len = 0; + + memcpy(cmd->addr, sta->addr, ETH_ALEN); + cmd->bss_index = WL1271_AP_BSS_INDEX; + cmd->aid = sta->aid; + cmd->hlid = hlid; + + /* + * FIXME: Does STA support QOS? We need to propagate this info from + * hostapd. Currently not that important since this is only used for + * sending the correct flavor of null-data packet in response to a + * trigger. + */ + cmd->wmm = 0; + + cmd->supported_rates = cpu_to_le32(wl1271_tx_enabled_rates_get(wl, + sta->supp_rates[wl->band])); + + wl1271_debug(DEBUG_CMD, "new sta rates: 0x%x", cmd->supported_rates); + + ret = wl1271_cmd_send(wl, CMD_ADD_STA, cmd, sizeof(*cmd), 0); + if (ret < 0) { + wl1271_error("failed to initiate cmd add sta"); + goto out_free; + } + +out_free: + kfree(cmd); + +out: + return ret; +} + +int wl1271_cmd_remove_sta(struct wl1271 *wl, u8 hlid) +{ + struct wl1271_cmd_remove_sta *cmd; + int ret; + + wl1271_debug(DEBUG_CMD, "cmd remove sta %d", (int)hlid); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + ret = -ENOMEM; + goto out; + } + + cmd->hlid = hlid; + /* We never send a deauth, mac80211 is in charge of this */ + cmd->reason_opcode = 0; + cmd->send_deauth_flag = 0; + + ret = wl1271_cmd_send(wl, CMD_REMOVE_STA, cmd, sizeof(*cmd), 0); + if (ret < 0) { + wl1271_error("failed to initiate cmd remove sta"); + goto out_free; + } + + /* + * We are ok with a timeout here. The event is sometimes not sent + * due to a firmware bug. + */ + wl1271_cmd_wait_for_event_or_timeout(wl, STA_REMOVE_COMPLETE_EVENT_ID); + +out_free: + kfree(cmd); + +out: + return ret; +} diff --git a/drivers/net/wireless/wl12xx/cmd.h b/drivers/net/wireless/wl12xx/cmd.h index 2a1d9db..7512814 100644 --- a/drivers/net/wireless/wl12xx/cmd.h +++ b/drivers/net/wireless/wl12xx/cmd.h @@ -54,12 +54,20 @@ struct sk_buff *wl1271_cmd_build_ap_probe_req(struct wl1271 *wl, int wl1271_cmd_build_arp_rsp(struct wl1271 *wl, __be32 ip_addr); int wl1271_build_qos_null_data(struct wl1271 *wl); int wl1271_cmd_build_klv_null_data(struct wl1271 *wl); -int wl1271_cmd_set_default_wep_key(struct wl1271 *wl, u8 id); -int wl1271_cmd_set_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, - u8 key_size, const u8 *key, const u8 *addr, - u32 tx_seq_32, u16 tx_seq_16); +int wl1271_cmd_set_sta_default_wep_key(struct wl1271 *wl, u8 id); +int wl1271_cmd_set_ap_default_wep_key(struct wl1271 *wl, u8 id); +int wl1271_cmd_set_sta_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, + u8 key_size, const u8 *key, const u8 *addr, + u32 tx_seq_32, u16 tx_seq_16); +int wl1271_cmd_set_ap_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, + u8 key_size, const u8 *key, u8 hlid, u32 tx_seq_32, + u16 tx_seq_16); int wl1271_cmd_disconnect(struct wl1271 *wl); int wl1271_cmd_set_sta_state(struct wl1271 *wl); +int wl1271_cmd_start_bss(struct wl1271 *wl); +int wl1271_cmd_stop_bss(struct wl1271 *wl); +int wl1271_cmd_add_sta(struct wl1271 *wl, struct ieee80211_sta *sta, u8 hlid); +int wl1271_cmd_remove_sta(struct wl1271 *wl, u8 hlid); enum wl1271_commands { CMD_INTERROGATE = 1, /*use this to read information elements*/ @@ -98,6 +106,12 @@ enum wl1271_commands { CMD_STOP_PERIODIC_SCAN = 51, CMD_SET_STA_STATE = 52, + /* AP mode commands */ + CMD_BSS_START = 60, + CMD_BSS_STOP = 61, + CMD_ADD_STA = 62, + CMD_REMOVE_STA = 63, + NUM_COMMANDS, MAX_COMMAND_ID = 0xFFFF, }; @@ -126,6 +140,13 @@ enum cmd_templ { * For CTS-to-self (FastCTS) mechanism * for BT/WLAN coexistence (SoftGemini). */ CMD_TEMPL_ARP_RSP, + + /* AP-mode specific */ + CMD_TEMPL_AP_BEACON = 13, + CMD_TEMPL_AP_PROBE_RESPONSE, + CMD_TEMPL_AP_ARP_RSP, + CMD_TEMPL_DEAUTH_AP, + CMD_TEMPL_MAX = 0xff }; @@ -270,7 +291,6 @@ struct wl1271_cmd_ps_params { /* HW encryption keys */ #define NUM_ACCESS_CATEGORIES_COPY 4 -#define MAX_KEY_SIZE 32 enum wl1271_cmd_key_action { KEY_ADD_OR_REPLACE = 1, @@ -289,7 +309,7 @@ enum wl1271_cmd_key_type { /* FIXME: Add description for key-types */ -struct wl1271_cmd_set_keys { +struct wl1271_cmd_set_sta_keys { struct wl1271_cmd_header header; /* Ignored for default WEP key */ @@ -318,6 +338,57 @@ struct wl1271_cmd_set_keys { __le32 ac_seq_num32[NUM_ACCESS_CATEGORIES_COPY]; } __packed; +enum wl1271_cmd_lid_key_type { + UNICAST_LID_TYPE = 0, + BROADCAST_LID_TYPE = 1, + WEP_DEFAULT_LID_TYPE = 2 +}; + +struct wl1271_cmd_set_ap_keys { + struct wl1271_cmd_header header; + + /* + * Indicates whether the HLID is a unicast key set + * or broadcast key set. A special value 0xFF is + * used to indicate that the HLID is on WEP-default + * (multi-hlids). of type wl1271_cmd_lid_key_type. + */ + u8 hlid; + + /* + * In WEP-default network (hlid == 0xFF) used to + * indicate which network STA/IBSS/AP role should be + * changed + */ + u8 lid_key_type; + + /* + * Key ID - For TKIP and AES key types, this field + * indicates the value that should be inserted into + * the KeyID field of frames transmitted using this + * key entry. For broadcast keys the index use as a + * marker for TX/RX key. + * For WEP default network (HLID=0xFF), this field + * indicates the ID of the key to add or remove. + */ + u8 key_id; + u8 reserved_1; + + /* key_action_e */ + __le16 key_action; + + /* key size in bytes */ + u8 key_size; + + /* key_type_e */ + u8 key_type; + + /* This field holds the security key data to add to the STA table */ + u8 key[MAX_KEY_SIZE]; + __le16 ac_seq_num16[NUM_ACCESS_CATEGORIES_COPY]; + __le32 ac_seq_num32[NUM_ACCESS_CATEGORIES_COPY]; +} __packed; + struct wl1271_cmd_test_header { u8 id; u8 padding[3]; @@ -412,4 +483,68 @@ struct wl1271_cmd_set_sta_state { u8 padding[3]; } __packed; +enum wl1271_ssid_type { + SSID_TYPE_PUBLIC = 0, + SSID_TYPE_HIDDEN = 1 +}; + +struct wl1271_cmd_bss_start { + struct wl1271_cmd_header header; + + /* wl1271_ssid_type */ + u8 ssid_type; + u8 ssid_len; + u8 ssid[IW_ESSID_MAX_SIZE]; + u8 padding_1[2]; + + /* Basic rate set */ + __le32 basic_rate_set; + /* Aging period in seconds*/ + __le16 aging_period; + + /* + * This field specifies the time between target beacon + * transmission times (TBTTs), in time units (TUs). + * Valid values are 1 to 1024. + */ + __le16 beacon_interval; + u8 bssid[ETH_ALEN]; + u8 bss_index; + /* Radio band */ + u8 band; + u8 channel; + /* The host link id for the AP's global queue */ + u8 global_hlid; + /* The host link id for the AP's broadcast queue */ + u8 broadcast_hlid; + /* DTIM count */ + u8 dtim_interval; + /* Beacon expiry time in ms */ + u8 beacon_expiry; + u8 padding_2[3]; +} __packed; + +struct wl1271_cmd_add_sta { + struct wl1271_cmd_header header; + + u8 addr[ETH_ALEN]; + u8 hlid; + u8 aid; + u8 psd_type[NUM_ACCESS_CATEGORIES_COPY]; + __le32 supported_rates; + u8 bss_index; + u8 sp_len; + u8 wmm; + u8 padding1; +} __packed; + +struct wl1271_cmd_remove_sta { + struct wl1271_cmd_header header; + + u8 hlid; + u8 reason_opcode; + u8 send_deauth_flag; + u8 padding1; +} __packed; + #endif /* __WL1271_CMD_H__ */ diff --git a/drivers/net/wireless/wl12xx/conf.h b/drivers/net/wireless/wl12xx/conf.h index a16b361..fd1dac9 100644 --- a/drivers/net/wireless/wl12xx/conf.h +++ b/drivers/net/wireless/wl12xx/conf.h @@ -496,6 +496,26 @@ struct conf_rx_settings { CONF_HW_BIT_RATE_2MBPS) #define CONF_TX_RATE_RETRY_LIMIT 10 +/* + * Rates supported for data packets when operating as AP. Note the absense + * of the 22Mbps rate. There is a FW limitation on 12 rates so we must drop + * one. The rate dropped is not mandatory under any operating mode. + */ +#define CONF_TX_AP_ENABLED_RATES (CONF_HW_BIT_RATE_1MBPS | \ + CONF_HW_BIT_RATE_2MBPS | CONF_HW_BIT_RATE_5_5MBPS | \ + CONF_HW_BIT_RATE_6MBPS | CONF_HW_BIT_RATE_9MBPS | \ + CONF_HW_BIT_RATE_11MBPS | CONF_HW_BIT_RATE_12MBPS | \ + CONF_HW_BIT_RATE_18MBPS | CONF_HW_BIT_RATE_24MBPS | \ + CONF_HW_BIT_RATE_36MBPS | CONF_HW_BIT_RATE_48MBPS | \ + CONF_HW_BIT_RATE_54MBPS) + +/* + * Default rates for management traffic when operating in AP mode. This + * should be configured according to the basic rate set of the AP + */ +#define CONF_TX_AP_DEFAULT_MGMT_RATES (CONF_HW_BIT_RATE_1MBPS | \ + CONF_HW_BIT_RATE_2MBPS | CONF_HW_BIT_RATE_5_5MBPS) + struct conf_tx_rate_class { /* @@ -636,9 +656,9 @@ struct conf_tx_settings { /* * Configuration for rate classes for TX (currently only one - * rate class supported.) + * rate class supported). Used in non-AP mode. */ - struct conf_tx_rate_class rc_conf; + struct conf_tx_rate_class sta_rc_conf; /* * Configuration for access categories for TX rate control. @@ -647,6 +667,28 @@ struct conf_tx_settings { struct conf_tx_ac_category ac_conf[CONF_TX_MAX_AC_COUNT]; /* + * Configuration for rate classes in AP-mode. These rate classes + * are for the AC TX queues + */ + struct conf_tx_rate_class ap_rc_conf[CONF_TX_MAX_AC_COUNT]; + + /* + * Management TX rate class for AP-mode. + */ + struct conf_tx_rate_class ap_mgmt_conf; + + /* + * Broadcast TX rate class for AP-mode. + */ + struct conf_tx_rate_class ap_bcst_conf; + + /* + * AP-mode - allow this number of TX retries to a station before an + * event is triggered from FW. + */ + u16 ap_max_tx_retries; + + /* * Configuration for TID parameters. */ u8 tid_conf_count; @@ -687,6 +729,12 @@ struct conf_tx_settings { * Range: CONF_HW_BIT_RATE_* bit mask */ u32 basic_rate_5; + + /* + * TX retry limits for templates + */ + u8 tmpl_short_retry_limit; + u8 tmpl_long_retry_limit; }; enum { @@ -1036,30 +1084,30 @@ struct conf_scan_settings { /* * The minimum time to wait on each channel for active scans * - * Range: 0 - 65536 tu + * Range: u32 tu/1000 */ - u16 min_dwell_time_active; + u32 min_dwell_time_active; /* * The maximum time to wait on each channel for active scans * - * Range: 0 - 65536 tu + * Range: u32 tu/1000 */ - u16 max_dwell_time_active; + u32 max_dwell_time_active; /* - * The maximum time to wait on each channel for passive scans + * The minimum time to wait on each channel for passive scans * - * Range: 0 - 65536 tu + * Range: u32 tu/1000 */ - u16 min_dwell_time_passive; + u32 min_dwell_time_passive; /* * The maximum time to wait on each channel for passive scans * - * Range: 0 - 65536 tu + * Range: u32 tu/1000 */ - u16 max_dwell_time_passive; + u32 max_dwell_time_passive; /* * Number of probe requests to transmit on each active scan channel @@ -1090,6 +1138,11 @@ struct conf_rf_settings { u8 tx_per_channel_power_compensation_5[CONF_TX_PWR_COMPENSATION_LEN_5]; }; +struct conf_ht_setting { + u16 tx_ba_win_size; + u16 inactivity_timeout; +}; + struct conf_drv_settings { struct conf_sg_settings sg; struct conf_rx_settings rx; @@ -1100,6 +1153,7 @@ struct conf_drv_settings { struct conf_roam_trigger_settings roam_trigger; struct conf_scan_settings scan; struct conf_rf_settings rf; + struct conf_ht_setting ht; }; #endif diff --git a/drivers/net/wireless/wl12xx/debugfs.c b/drivers/net/wireless/wl12xx/debugfs.c index ec60777..bebfa28 100644 --- a/drivers/net/wireless/wl12xx/debugfs.c +++ b/drivers/net/wireless/wl12xx/debugfs.c @@ -261,27 +261,25 @@ static ssize_t gpio_power_write(struct file *file, unsigned long value; int ret; - mutex_lock(&wl->mutex); - len = min(count, sizeof(buf) - 1); if (copy_from_user(buf, user_buf, len)) { - ret = -EFAULT; - goto out; + return -EFAULT; } buf[len] = '\0'; ret = strict_strtoul(buf, 0, &value); if (ret < 0) { wl1271_warning("illegal value in gpio_power"); - goto out; + return -EINVAL; } + mutex_lock(&wl->mutex); + if (value) wl1271_power_on(wl); else wl1271_power_off(wl); -out: mutex_unlock(&wl->mutex); return count; } @@ -293,12 +291,13 @@ static const struct file_operations gpio_power_ops = { .llseek = default_llseek, }; -static int wl1271_debugfs_add_files(struct wl1271 *wl) +static int wl1271_debugfs_add_files(struct wl1271 *wl, + struct dentry *rootdir) { int ret = 0; struct dentry *entry, *stats; - stats = debugfs_create_dir("fw-statistics", wl->rootdir); + stats = debugfs_create_dir("fw-statistics", rootdir); if (!stats || IS_ERR(stats)) { entry = stats; goto err; @@ -395,16 +394,11 @@ static int wl1271_debugfs_add_files(struct wl1271 *wl) DEBUGFS_FWSTATS_ADD(rxpipe, missed_beacon_host_int_trig_rx_data); DEBUGFS_FWSTATS_ADD(rxpipe, tx_xfr_host_int_trig_rx_data); - DEBUGFS_ADD(tx_queue_len, wl->rootdir); - DEBUGFS_ADD(retry_count, wl->rootdir); - DEBUGFS_ADD(excessive_retries, wl->rootdir); - - DEBUGFS_ADD(gpio_power, wl->rootdir); + DEBUGFS_ADD(tx_queue_len, rootdir); + DEBUGFS_ADD(retry_count, rootdir); + DEBUGFS_ADD(excessive_retries, rootdir); - entry = debugfs_create_x32("debug_level", 0600, wl->rootdir, - &wl12xx_debug_level); - if (!entry || IS_ERR(entry)) - goto err; + DEBUGFS_ADD(gpio_power, rootdir); return 0; @@ -419,7 +413,7 @@ err: void wl1271_debugfs_reset(struct wl1271 *wl) { - if (!wl->rootdir) + if (!wl->stats.fw_stats) return; memset(wl->stats.fw_stats, 0, sizeof(*wl->stats.fw_stats)); @@ -430,13 +424,13 @@ void wl1271_debugfs_reset(struct wl1271 *wl) int wl1271_debugfs_init(struct wl1271 *wl) { int ret; + struct dentry *rootdir; - wl->rootdir = debugfs_create_dir(KBUILD_MODNAME, - wl->hw->wiphy->debugfsdir); + rootdir = debugfs_create_dir(KBUILD_MODNAME, + wl->hw->wiphy->debugfsdir); - if (IS_ERR(wl->rootdir)) { - ret = PTR_ERR(wl->rootdir); - wl->rootdir = NULL; + if (IS_ERR(rootdir)) { + ret = PTR_ERR(rootdir); goto err; } @@ -450,7 +444,7 @@ int wl1271_debugfs_init(struct wl1271 *wl) wl->stats.fw_stats_update = jiffies; - ret = wl1271_debugfs_add_files(wl); + ret = wl1271_debugfs_add_files(wl, rootdir); if (ret < 0) goto err_file; @@ -462,8 +456,7 @@ err_file: wl->stats.fw_stats = NULL; err_fw: - debugfs_remove_recursive(wl->rootdir); - wl->rootdir = NULL; + debugfs_remove_recursive(rootdir); err: return ret; @@ -473,8 +466,4 @@ void wl1271_debugfs_exit(struct wl1271 *wl) { kfree(wl->stats.fw_stats); wl->stats.fw_stats = NULL; - - debugfs_remove_recursive(wl->rootdir); - wl->rootdir = NULL; - } diff --git a/drivers/net/wireless/wl12xx/event.c b/drivers/net/wireless/wl12xx/event.c index f9146f5..3376a5d 100644 --- a/drivers/net/wireless/wl12xx/event.c +++ b/drivers/net/wireless/wl12xx/event.c @@ -186,6 +186,7 @@ static int wl1271_event_process(struct wl1271 *wl, struct event_mailbox *mbox) int ret; u32 vector; bool beacon_loss = false; + bool is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); wl1271_event_mbox_dump(mbox); @@ -218,21 +219,21 @@ static int wl1271_event_process(struct wl1271 *wl, struct event_mailbox *mbox) * BSS_LOSE_EVENT, beacon loss has to be reported to the stack. * */ - if (vector & BSS_LOSE_EVENT_ID) { + if ((vector & BSS_LOSE_EVENT_ID) && !is_ap) { wl1271_info("Beacon loss detected."); /* indicate to the stack, that beacons have been lost */ beacon_loss = true; } - if (vector & PS_REPORT_EVENT_ID) { + if ((vector & PS_REPORT_EVENT_ID) && !is_ap) { wl1271_debug(DEBUG_EVENT, "PS_REPORT_EVENT"); ret = wl1271_event_ps_report(wl, mbox, &beacon_loss); if (ret < 0) return ret; } - if (vector & PSPOLL_DELIVERY_FAILURE_EVENT_ID) + if ((vector & PSPOLL_DELIVERY_FAILURE_EVENT_ID) && !is_ap) wl1271_event_pspoll_delivery_fail(wl); if (vector & RSSI_SNR_TRIGGER_0_EVENT_ID) { diff --git a/drivers/net/wireless/wl12xx/event.h b/drivers/net/wireless/wl12xx/event.h index 6cce014..1d5ef67 100644 --- a/drivers/net/wireless/wl12xx/event.h +++ b/drivers/net/wireless/wl12xx/event.h @@ -59,6 +59,7 @@ enum { BSS_LOSE_EVENT_ID = BIT(18), REGAINED_BSS_EVENT_ID = BIT(19), ROAMING_TRIGGER_MAX_TX_RETRY_EVENT_ID = BIT(20), + STA_REMOVE_COMPLETE_EVENT_ID = BIT(21), /* AP */ SOFT_GEMINI_SENSE_EVENT_ID = BIT(22), SOFT_GEMINI_PREDICTION_EVENT_ID = BIT(23), SOFT_GEMINI_AVALANCHE_EVENT_ID = BIT(24), @@ -115,7 +116,12 @@ struct event_mailbox { u8 scheduled_scan_status; u8 ps_status; - u8 reserved_5[29]; + /* AP FW only */ + u8 hlid_removed; + __le16 sta_aging_status; + __le16 sta_tx_retry_exceeded; + + u8 reserved_5[24]; } __packed; int wl1271_event_unmask(struct wl1271 *wl); diff --git a/drivers/net/wireless/wl12xx/init.c b/drivers/net/wireless/wl12xx/init.c index 785a530..70b3dc8 100644 --- a/drivers/net/wireless/wl12xx/init.c +++ b/drivers/net/wireless/wl12xx/init.c @@ -30,27 +30,9 @@ #include "acx.h" #include "cmd.h" #include "reg.h" +#include "tx.h" -static int wl1271_init_hwenc_config(struct wl1271 *wl) -{ - int ret; - - ret = wl1271_acx_feature_cfg(wl); - if (ret < 0) { - wl1271_warning("couldn't set feature config"); - return ret; - } - - ret = wl1271_cmd_set_default_wep_key(wl, wl->default_key); - if (ret < 0) { - wl1271_warning("couldn't set default key"); - return ret; - } - - return 0; -} - -int wl1271_init_templates_config(struct wl1271 *wl) +int wl1271_sta_init_templates_config(struct wl1271 *wl) { int ret, i; @@ -118,6 +100,132 @@ int wl1271_init_templates_config(struct wl1271 *wl) return 0; } +static int wl1271_ap_init_deauth_template(struct wl1271 *wl) +{ + struct wl12xx_disconn_template *tmpl; + int ret; + + tmpl = kzalloc(sizeof(*tmpl), GFP_KERNEL); + if (!tmpl) { + ret = -ENOMEM; + goto out; + } + + tmpl->header.frame_ctl = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_DEAUTH); + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_DEAUTH_AP, + tmpl, sizeof(*tmpl), 0, + wl1271_tx_min_rate_get(wl)); + +out: + kfree(tmpl); + return ret; +} + +static int wl1271_ap_init_null_template(struct wl1271 *wl) +{ + struct ieee80211_hdr_3addr *nullfunc; + int ret; + + nullfunc = kzalloc(sizeof(*nullfunc), GFP_KERNEL); + if (!nullfunc) { + ret = -ENOMEM; + goto out; + } + + nullfunc->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA | + IEEE80211_STYPE_NULLFUNC | + IEEE80211_FCTL_FROMDS); + + /* nullfunc->addr1 is filled by FW */ + + memcpy(nullfunc->addr2, wl->mac_addr, ETH_ALEN); + memcpy(nullfunc->addr3, wl->mac_addr, ETH_ALEN); + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_NULL_DATA, nullfunc, + sizeof(*nullfunc), 0, + wl1271_tx_min_rate_get(wl)); + +out: + kfree(nullfunc); + return ret; +} + +static int wl1271_ap_init_qos_null_template(struct wl1271 *wl) +{ + struct ieee80211_qos_hdr *qosnull; + int ret; + + qosnull = kzalloc(sizeof(*qosnull), GFP_KERNEL); + if (!qosnull) { + ret = -ENOMEM; + goto out; + } + + qosnull->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA | + IEEE80211_STYPE_QOS_NULLFUNC | + IEEE80211_FCTL_FROMDS); + + /* qosnull->addr1 is filled by FW */ + + memcpy(qosnull->addr2, wl->mac_addr, ETH_ALEN); + memcpy(qosnull->addr3, wl->mac_addr, ETH_ALEN); + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_QOS_NULL_DATA, qosnull, + sizeof(*qosnull), 0, + wl1271_tx_min_rate_get(wl)); + +out: + kfree(qosnull); + return ret; +} + +static int wl1271_ap_init_templates_config(struct wl1271 *wl) +{ + int ret; + + /* + * Put very large empty placeholders for all templates. These + * reserve memory for later. + */ + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_AP_PROBE_RESPONSE, NULL, + sizeof + (struct wl12xx_probe_resp_template), + 0, WL1271_RATE_AUTOMATIC); + if (ret < 0) + return ret; + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_AP_BEACON, NULL, + sizeof + (struct wl12xx_beacon_template), + 0, WL1271_RATE_AUTOMATIC); + if (ret < 0) + return ret; + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_DEAUTH_AP, NULL, + sizeof + (struct wl12xx_disconn_template), + 0, WL1271_RATE_AUTOMATIC); + if (ret < 0) + return ret; + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_NULL_DATA, NULL, + sizeof(struct wl12xx_null_data_template), + 0, WL1271_RATE_AUTOMATIC); + if (ret < 0) + return ret; + + ret = wl1271_cmd_template_set(wl, CMD_TEMPL_QOS_NULL_DATA, NULL, + sizeof + (struct wl12xx_qos_null_data_template), + 0, WL1271_RATE_AUTOMATIC); + if (ret < 0) + return ret; + + return 0; +} + static int wl1271_init_rx_config(struct wl1271 *wl, u32 config, u32 filter) { int ret; @@ -145,10 +253,6 @@ int wl1271_init_phy_config(struct wl1271 *wl) if (ret < 0) return ret; - ret = wl1271_acx_group_address_tbl(wl, true, NULL, 0); - if (ret < 0) - return ret; - ret = wl1271_acx_service_period_timeout(wl); if (ret < 0) return ret; @@ -213,11 +317,186 @@ static int wl1271_init_beacon_broadcast(struct wl1271 *wl) return 0; } +static int wl1271_sta_hw_init(struct wl1271 *wl) +{ + int ret; + + ret = wl1271_cmd_ext_radio_parms(wl); + if (ret < 0) + return ret; + + ret = wl1271_sta_init_templates_config(wl); + if (ret < 0) + return ret; + + ret = wl1271_acx_group_address_tbl(wl, true, NULL, 0); + if (ret < 0) + return ret; + + /* Initialize connection monitoring thresholds */ + ret = wl1271_acx_conn_monit_params(wl, false); + if (ret < 0) + return ret; + + /* Beacon filtering */ + ret = wl1271_init_beacon_filter(wl); + if (ret < 0) + return ret; + + /* Bluetooth WLAN coexistence */ + ret = wl1271_init_pta(wl); + if (ret < 0) + return ret; + + /* Beacons and broadcast settings */ + ret = wl1271_init_beacon_broadcast(wl); + if (ret < 0) + return ret; + + /* Configure for ELP power saving */ + ret = wl1271_acx_sleep_auth(wl, WL1271_PSM_ELP); + if (ret < 0) + return ret; + + /* Configure rssi/snr averaging weights */ + ret = wl1271_acx_rssi_snr_avg_weights(wl); + if (ret < 0) + return ret; + + ret = wl1271_acx_sta_rate_policies(wl); + if (ret < 0) + return ret; + + return 0; +} + +static int wl1271_sta_hw_init_post_mem(struct wl1271 *wl) +{ + int ret, i; + + ret = wl1271_cmd_set_sta_default_wep_key(wl, wl->default_key); + if (ret < 0) { + wl1271_warning("couldn't set default key"); + return ret; + } + + /* disable all keep-alive templates */ + for (i = 0; i < CMD_TEMPL_KLV_IDX_MAX; i++) { + ret = wl1271_acx_keep_alive_config(wl, i, + ACX_KEEP_ALIVE_TPL_INVALID); + if (ret < 0) + return ret; + } + + /* disable the keep-alive feature */ + ret = wl1271_acx_keep_alive_mode(wl, false); + if (ret < 0) + return ret; + + return 0; +} + +static int wl1271_ap_hw_init(struct wl1271 *wl) +{ + int ret, i; + + ret = wl1271_ap_init_templates_config(wl); + if (ret < 0) + return ret; + + /* Configure for power always on */ + ret = wl1271_acx_sleep_auth(wl, WL1271_PSM_CAM); + if (ret < 0) + return ret; + + /* Configure initial TX rate classes */ + for (i = 0; i < wl->conf.tx.ac_conf_count; i++) { + ret = wl1271_acx_ap_rate_policy(wl, + &wl->conf.tx.ap_rc_conf[i], i); + if (ret < 0) + return ret; + } + + ret = wl1271_acx_ap_rate_policy(wl, + &wl->conf.tx.ap_mgmt_conf, + ACX_TX_AP_MODE_MGMT_RATE); + if (ret < 0) + return ret; + + ret = wl1271_acx_ap_rate_policy(wl, + &wl->conf.tx.ap_bcst_conf, + ACX_TX_AP_MODE_BCST_RATE); + if (ret < 0) + return ret; + + ret = wl1271_acx_max_tx_retry(wl); + if (ret < 0) + return ret; + + return 0; +} + +static int wl1271_ap_hw_init_post_mem(struct wl1271 *wl) +{ + int ret; + + ret = wl1271_ap_init_deauth_template(wl); + if (ret < 0) + return ret; + + ret = wl1271_ap_init_null_template(wl); + if (ret < 0) + return ret; + + ret = wl1271_ap_init_qos_null_template(wl); + if (ret < 0) + return ret; + + return 0; +} + +static void wl1271_check_ba_support(struct wl1271 *wl) +{ + /* validate FW cose ver x.x.x.50-60.x */ + if ((wl->chip.fw_ver[3] >= WL12XX_BA_SUPPORT_FW_COST_VER2_START) && + (wl->chip.fw_ver[3] < WL12XX_BA_SUPPORT_FW_COST_VER2_END)) { + wl->ba_support = true; + return; + } + + wl->ba_support = false; +} + +static int wl1271_set_ba_policies(struct wl1271 *wl) +{ + u8 tid_index; + u8 ret = 0; + + /* Reset the BA RX indicators */ + wl->ba_rx_bitmap = 0; + + /* validate that FW support BA */ + wl1271_check_ba_support(wl); + + if (wl->ba_support) + /* 802.11n initiator BA session setting */ + for (tid_index = 0; tid_index < CONF_TX_MAX_TID_COUNT; + ++tid_index) { + ret = wl1271_acx_set_ba_session(wl, WLAN_BACK_INITIATOR, + tid_index, true); + if (ret < 0) + break; + } + + return ret; +} + int wl1271_hw_init(struct wl1271 *wl) { struct conf_tx_ac_category *conf_ac; struct conf_tx_tid *conf_tid; int ret, i; + bool is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); ret = wl1271_cmd_general_parms(wl); if (ret < 0) @@ -227,12 +506,12 @@ int wl1271_hw_init(struct wl1271 *wl) if (ret < 0) return ret; - ret = wl1271_cmd_ext_radio_parms(wl); - if (ret < 0) - return ret; + /* Mode specific init */ + if (is_ap) + ret = wl1271_ap_hw_init(wl); + else + ret = wl1271_sta_hw_init(wl); - /* Template settings */ - ret = wl1271_init_templates_config(wl); if (ret < 0) return ret; @@ -259,16 +538,6 @@ int wl1271_hw_init(struct wl1271 *wl) if (ret < 0) goto out_free_memmap; - /* Initialize connection monitoring thresholds */ - ret = wl1271_acx_conn_monit_params(wl, false); - if (ret < 0) - goto out_free_memmap; - - /* Beacon filtering */ - ret = wl1271_init_beacon_filter(wl); - if (ret < 0) - goto out_free_memmap; - /* Configure TX patch complete interrupt behavior */ ret = wl1271_acx_tx_config_options(wl); if (ret < 0) @@ -279,21 +548,11 @@ int wl1271_hw_init(struct wl1271 *wl) if (ret < 0) goto out_free_memmap; - /* Bluetooth WLAN coexistence */ - ret = wl1271_init_pta(wl); - if (ret < 0) - goto out_free_memmap; - /* Energy detection */ ret = wl1271_init_energy_detection(wl); if (ret < 0) goto out_free_memmap; - /* Beacons and boradcast settings */ - ret = wl1271_init_beacon_broadcast(wl); - if (ret < 0) - goto out_free_memmap; - /* Default fragmentation threshold */ ret = wl1271_acx_frag_threshold(wl, wl->conf.tx.frag_threshold); if (ret < 0) @@ -321,23 +580,13 @@ int wl1271_hw_init(struct wl1271 *wl) goto out_free_memmap; } - /* Configure TX rate classes */ - ret = wl1271_acx_rate_policies(wl); - if (ret < 0) - goto out_free_memmap; - /* Enable data path */ ret = wl1271_cmd_data_path(wl, 1); if (ret < 0) goto out_free_memmap; - /* Configure for ELP power saving */ - ret = wl1271_acx_sleep_auth(wl, WL1271_PSM_ELP); - if (ret < 0) - goto out_free_memmap; - /* Configure HW encryption */ - ret = wl1271_init_hwenc_config(wl); + ret = wl1271_acx_feature_cfg(wl); if (ret < 0) goto out_free_memmap; @@ -346,21 +595,17 @@ int wl1271_hw_init(struct wl1271 *wl) if (ret < 0) goto out_free_memmap; - /* disable all keep-alive templates */ - for (i = 0; i < CMD_TEMPL_KLV_IDX_MAX; i++) { - ret = wl1271_acx_keep_alive_config(wl, i, - ACX_KEEP_ALIVE_TPL_INVALID); - if (ret < 0) - goto out_free_memmap; - } + /* Mode specific init - post mem init */ + if (is_ap) + ret = wl1271_ap_hw_init_post_mem(wl); + else + ret = wl1271_sta_hw_init_post_mem(wl); - /* disable the keep-alive feature */ - ret = wl1271_acx_keep_alive_mode(wl, false); if (ret < 0) goto out_free_memmap; - /* Configure rssi/snr averaging weights */ - ret = wl1271_acx_rssi_snr_avg_weights(wl); + /* Configure initiator BA sessions policies */ + ret = wl1271_set_ba_policies(wl); if (ret < 0) goto out_free_memmap; diff --git a/drivers/net/wireless/wl12xx/init.h b/drivers/net/wireless/wl12xx/init.h index 7762421..3a8bd3f 100644 --- a/drivers/net/wireless/wl12xx/init.h +++ b/drivers/net/wireless/wl12xx/init.h @@ -27,7 +27,7 @@ #include "wl12xx.h" int wl1271_hw_init_power_auth(struct wl1271 *wl); -int wl1271_init_templates_config(struct wl1271 *wl); +int wl1271_sta_init_templates_config(struct wl1271 *wl); int wl1271_init_phy_config(struct wl1271 *wl); int wl1271_init_pta(struct wl1271 *wl); int wl1271_init_energy_detection(struct wl1271 *wl); diff --git a/drivers/net/wireless/wl12xx/main.c b/drivers/net/wireless/wl12xx/main.c index 062247e..254b7da 100644 --- a/drivers/net/wireless/wl12xx/main.c +++ b/drivers/net/wireless/wl12xx/main.c @@ -116,11 +116,11 @@ static struct conf_drv_settings default_conf = { }, .tx = { .tx_energy_detection = 0, - .rc_conf = { + .sta_rc_conf = { .enabled_rates = 0, .short_retry_limit = 10, .long_retry_limit = 10, - .aflags = 0 + .aflags = 0, }, .ac_conf_count = 4, .ac_conf = { @@ -153,6 +153,45 @@ static struct conf_drv_settings default_conf = { .tx_op_limit = 1504, }, }, + .ap_rc_conf = { + [0] = { + .enabled_rates = CONF_TX_AP_ENABLED_RATES, + .short_retry_limit = 10, + .long_retry_limit = 10, + .aflags = 0, + }, + [1] = { + .enabled_rates = CONF_TX_AP_ENABLED_RATES, + .short_retry_limit = 10, + .long_retry_limit = 10, + .aflags = 0, + }, + [2] = { + .enabled_rates = CONF_TX_AP_ENABLED_RATES, + .short_retry_limit = 10, + .long_retry_limit = 10, + .aflags = 0, + }, + [3] = { + .enabled_rates = CONF_TX_AP_ENABLED_RATES, + .short_retry_limit = 10, + .long_retry_limit = 10, + .aflags = 0, + }, + }, + .ap_mgmt_conf = { + .enabled_rates = CONF_TX_AP_DEFAULT_MGMT_RATES, + .short_retry_limit = 10, + .long_retry_limit = 10, + .aflags = 0, + }, + .ap_bcst_conf = { + .enabled_rates = CONF_HW_BIT_RATE_1MBPS, + .short_retry_limit = 10, + .long_retry_limit = 10, + .aflags = 0, + }, + .ap_max_tx_retries = 100, .tid_conf_count = 4, .tid_conf = { [CONF_TX_AC_BE] = { @@ -193,6 +232,8 @@ static struct conf_drv_settings default_conf = { .tx_compl_threshold = 4, .basic_rate = CONF_HW_BIT_RATE_1MBPS, .basic_rate_5 = CONF_HW_BIT_RATE_6MBPS, + .tmpl_short_retry_limit = 10, + .tmpl_long_retry_limit = 10, }, .conn = { .wake_up_event = CONF_WAKE_UP_EVENT_DTIM, @@ -233,13 +274,13 @@ static struct conf_drv_settings default_conf = { .avg_weight_rssi_beacon = 20, .avg_weight_rssi_data = 10, .avg_weight_snr_beacon = 20, - .avg_weight_snr_data = 10 + .avg_weight_snr_data = 10, }, .scan = { .min_dwell_time_active = 7500, .max_dwell_time_active = 30000, - .min_dwell_time_passive = 30000, - .max_dwell_time_passive = 60000, + .min_dwell_time_passive = 100000, + .max_dwell_time_passive = 100000, .num_probe_reqs = 2, }, .rf = { @@ -252,9 +293,14 @@ static struct conf_drv_settings default_conf = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, }, }, + .ht = { + .tx_ba_win_size = 64, + .inactivity_timeout = 10000, + }, }; static void __wl1271_op_remove_interface(struct wl1271 *wl); +static void wl1271_free_ap_keys(struct wl1271 *wl); static void wl1271_device_release(struct device *dev) @@ -393,7 +439,7 @@ static int wl1271_plt_init(struct wl1271 *wl) if (ret < 0) return ret; - ret = wl1271_init_templates_config(wl); + ret = wl1271_sta_init_templates_config(wl); if (ret < 0) return ret; @@ -616,9 +662,26 @@ out: static int wl1271_fetch_firmware(struct wl1271 *wl) { const struct firmware *fw; + const char *fw_name; int ret; - ret = request_firmware(&fw, WL1271_FW_NAME, wl1271_wl_to_dev(wl)); + switch (wl->bss_type) { + case BSS_TYPE_AP_BSS: + fw_name = WL1271_AP_FW_NAME; + break; + case BSS_TYPE_IBSS: + case BSS_TYPE_STA_BSS: + fw_name = WL1271_FW_NAME; + break; + default: + wl1271_error("no compatible firmware for bss_type %d", + wl->bss_type); + return -EINVAL; + } + + wl1271_debug(DEBUG_BOOT, "booting firmware %s", fw_name); + + ret = request_firmware(&fw, fw_name, wl1271_wl_to_dev(wl)); if (ret < 0) { wl1271_error("could not get firmware: %d", ret); @@ -632,6 +695,7 @@ static int wl1271_fetch_firmware(struct wl1271 *wl) goto out; } + vfree(wl->fw); wl->fw_len = fw->size; wl->fw = vmalloc(wl->fw_len); @@ -642,7 +706,7 @@ static int wl1271_fetch_firmware(struct wl1271 *wl) } memcpy(wl->fw, fw->data, wl->fw_len); - + wl->fw_bss_type = wl->bss_type; ret = 0; out: @@ -778,7 +842,8 @@ static int wl1271_chip_wakeup(struct wl1271 *wl) goto out; } - if (wl->fw == NULL) { + /* Make sure the firmware type matches the BSS type */ + if (wl->fw == NULL || wl->fw_bss_type != wl->bss_type) { ret = wl1271_fetch_firmware(wl); if (ret < 0) goto out; @@ -811,6 +876,8 @@ int wl1271_plt_start(struct wl1271 *wl) goto out; } + wl->bss_type = BSS_TYPE_STA_BSS; + while (retries) { retries--; ret = wl1271_chip_wakeup(wl); @@ -827,7 +894,7 @@ int wl1271_plt_start(struct wl1271 *wl) wl->state = WL1271_STATE_PLT; wl1271_notice("firmware booted in PLT mode (%s)", - wl->chip.fw_ver); + wl->chip.fw_ver_str); goto out; irq_disable: @@ -854,12 +921,10 @@ out: return ret; } -int wl1271_plt_stop(struct wl1271 *wl) +int __wl1271_plt_stop(struct wl1271 *wl) { int ret = 0; - mutex_lock(&wl->mutex); - wl1271_notice("power down"); if (wl->state != WL1271_STATE_PLT) { @@ -875,12 +940,21 @@ int wl1271_plt_stop(struct wl1271 *wl) wl->state = WL1271_STATE_OFF; wl->rx_counter = 0; -out: mutex_unlock(&wl->mutex); - cancel_work_sync(&wl->irq_work); cancel_work_sync(&wl->recovery_work); + mutex_lock(&wl->mutex); +out: + return ret; +} + +int wl1271_plt_stop(struct wl1271 *wl) +{ + int ret; + mutex_lock(&wl->mutex); + ret = __wl1271_plt_stop(wl); + mutex_unlock(&wl->mutex); return ret; } @@ -902,7 +976,8 @@ static int wl1271_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb) spin_lock_irqsave(&wl->wl_lock, flags); if (sta && (sta->supp_rates[conf->channel->band] != - (wl->sta_rate_set & HW_BG_RATES_MASK))) { + (wl->sta_rate_set & HW_BG_RATES_MASK)) && + wl->bss_type != BSS_TYPE_AP_BSS) { wl->sta_rate_set = sta->supp_rates[conf->channel->band]; set_bit(WL1271_FLAG_STA_RATES_CHANGED, &wl->flags); } @@ -967,6 +1042,9 @@ static int wl1271_op_start(struct ieee80211_hw *hw) * * The MAC address is first known when the corresponding interface * is added. That is where we will initialize the hardware. + * + * In addition, we currently have different firmwares for AP and managed + * operation. We will know which to boot according to interface type. */ return 0; @@ -1006,6 +1084,9 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw, wl->bss_type = BSS_TYPE_IBSS; wl->set_bss_type = BSS_TYPE_STA_BSS; break; + case NL80211_IFTYPE_AP: + wl->bss_type = BSS_TYPE_AP_BSS; + break; default: ret = -EOPNOTSUPP; goto out; @@ -1061,11 +1142,11 @@ power_off: wl->vif = vif; wl->state = WL1271_STATE_ON; - wl1271_info("firmware booted (%s)", wl->chip.fw_ver); + wl1271_info("firmware booted (%s)", wl->chip.fw_ver_str); /* update hw/fw version info in wiphy struct */ wiphy->hw_version = wl->chip.id; - strncpy(wiphy->fw_version, wl->chip.fw_ver, + strncpy(wiphy->fw_version, wl->chip.fw_ver_str, sizeof(wiphy->fw_version)); /* @@ -1151,6 +1232,8 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl) wl->flags = 0; wl->vif = NULL; wl->filters = 0; + wl1271_free_ap_keys(wl); + memset(wl->ap_hlid_map, 0, sizeof(wl->ap_hlid_map)); for (i = 0; i < NUM_TX_QUEUES; i++) wl->tx_blocks_freed[i] = 0; @@ -1186,8 +1269,7 @@ static void wl1271_op_remove_interface(struct ieee80211_hw *hw, static void wl1271_configure_filters(struct wl1271 *wl, unsigned int filters) { - wl->rx_config = WL1271_DEFAULT_RX_CONFIG; - wl->rx_filter = WL1271_DEFAULT_RX_FILTER; + wl1271_set_default_filters(wl); /* combine requested filters with current filter config */ filters = wl->filters | filters; @@ -1322,25 +1404,7 @@ static void wl1271_set_band_rate(struct wl1271 *wl) wl->basic_rate_set = wl->conf.tx.basic_rate_5; } -static u32 wl1271_min_rate_get(struct wl1271 *wl) -{ - int i; - u32 rate = 0; - - if (!wl->basic_rate_set) { - WARN_ON(1); - wl->basic_rate_set = wl->conf.tx.basic_rate; - } - - for (i = 0; !rate; i++) { - if ((wl->basic_rate_set >> i) & 0x1) - rate = 1 << i; - } - - return rate; -} - -static int wl1271_handle_idle(struct wl1271 *wl, bool idle) +static int wl1271_sta_handle_idle(struct wl1271 *wl, bool idle) { int ret; @@ -1350,9 +1414,9 @@ static int wl1271_handle_idle(struct wl1271 *wl, bool idle) if (ret < 0) goto out; } - wl->rate_set = wl1271_min_rate_get(wl); + wl->rate_set = wl1271_tx_min_rate_get(wl); wl->sta_rate_set = 0; - ret = wl1271_acx_rate_policies(wl); + ret = wl1271_acx_sta_rate_policies(wl); if (ret < 0) goto out; ret = wl1271_acx_keep_alive_config( @@ -1381,14 +1445,17 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed) struct wl1271 *wl = hw->priv; struct ieee80211_conf *conf = &hw->conf; int channel, ret = 0; + bool is_ap; channel = ieee80211_frequency_to_channel(conf->channel->center_freq); - wl1271_debug(DEBUG_MAC80211, "mac80211 config ch %d psm %s power %d %s", + wl1271_debug(DEBUG_MAC80211, "mac80211 config ch %d psm %s power %d %s" + " changed 0x%x", channel, conf->flags & IEEE80211_CONF_PS ? "on" : "off", conf->power_level, - conf->flags & IEEE80211_CONF_IDLE ? "idle" : "in use"); + conf->flags & IEEE80211_CONF_IDLE ? "idle" : "in use", + changed); /* * mac80211 will go to idle nearly immediately after transmitting some @@ -1406,6 +1473,8 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed) goto out; } + is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); + ret = wl1271_ps_elp_wakeup(wl, false); if (ret < 0) goto out; @@ -1417,31 +1486,34 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed) wl->band = conf->channel->band; wl->channel = channel; - /* - * FIXME: the mac80211 should really provide a fixed rate - * to use here. for now, just use the smallest possible rate - * for the band as a fixed rate for association frames and - * other control messages. - */ - if (!test_bit(WL1271_FLAG_STA_ASSOCIATED, &wl->flags)) - wl1271_set_band_rate(wl); - - wl->basic_rate = wl1271_min_rate_get(wl); - ret = wl1271_acx_rate_policies(wl); - if (ret < 0) - wl1271_warning("rate policy for update channel " - "failed %d", ret); + if (!is_ap) { + /* + * FIXME: the mac80211 should really provide a fixed + * rate to use here. for now, just use the smallest + * possible rate for the band as a fixed rate for + * association frames and other control messages. + */ + if (!test_bit(WL1271_FLAG_STA_ASSOCIATED, &wl->flags)) + wl1271_set_band_rate(wl); - if (test_bit(WL1271_FLAG_JOINED, &wl->flags)) { - ret = wl1271_join(wl, false); + wl->basic_rate = wl1271_tx_min_rate_get(wl); + ret = wl1271_acx_sta_rate_policies(wl); if (ret < 0) - wl1271_warning("cmd join to update channel " + wl1271_warning("rate policy for channel " "failed %d", ret); + + if (test_bit(WL1271_FLAG_JOINED, &wl->flags)) { + ret = wl1271_join(wl, false); + if (ret < 0) + wl1271_warning("cmd join on channel " + "failed %d", ret); + } } } - if (changed & IEEE80211_CONF_CHANGE_IDLE) { - ret = wl1271_handle_idle(wl, conf->flags & IEEE80211_CONF_IDLE); + if (changed & IEEE80211_CONF_CHANGE_IDLE && !is_ap) { + ret = wl1271_sta_handle_idle(wl, + conf->flags & IEEE80211_CONF_IDLE); if (ret < 0) wl1271_warning("idle mode change failed %d", ret); } @@ -1548,7 +1620,8 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw, struct wl1271 *wl = hw->priv; int ret; - wl1271_debug(DEBUG_MAC80211, "mac80211 configure filter"); + wl1271_debug(DEBUG_MAC80211, "mac80211 configure filter changed %x" + " total %x", changed, *total); mutex_lock(&wl->mutex); @@ -1562,15 +1635,16 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw, if (ret < 0) goto out; - - if (*total & FIF_ALLMULTI) - ret = wl1271_acx_group_address_tbl(wl, false, NULL, 0); - else if (fp) - ret = wl1271_acx_group_address_tbl(wl, fp->enabled, - fp->mc_list, - fp->mc_list_length); - if (ret < 0) - goto out_sleep; + if (wl->bss_type != BSS_TYPE_AP_BSS) { + if (*total & FIF_ALLMULTI) + ret = wl1271_acx_group_address_tbl(wl, false, NULL, 0); + else if (fp) + ret = wl1271_acx_group_address_tbl(wl, fp->enabled, + fp->mc_list, + fp->mc_list_length); + if (ret < 0) + goto out_sleep; + } /* determine, whether supported filter values have changed */ if (changed == 0) @@ -1593,38 +1667,192 @@ out: kfree(fp); } +static int wl1271_record_ap_key(struct wl1271 *wl, u8 id, u8 key_type, + u8 key_size, const u8 *key, u8 hlid, u32 tx_seq_32, + u16 tx_seq_16) +{ + struct wl1271_ap_key *ap_key; + int i; + + wl1271_debug(DEBUG_CRYPT, "record ap key id %d", (int)id); + + if (key_size > MAX_KEY_SIZE) + return -EINVAL; + + /* + * Find next free entry in ap_keys. Also check we are not replacing + * an existing key. + */ + for (i = 0; i < MAX_NUM_KEYS; i++) { + if (wl->recorded_ap_keys[i] == NULL) + break; + + if (wl->recorded_ap_keys[i]->id == id) { + wl1271_warning("trying to record key replacement"); + return -EINVAL; + } + } + + if (i == MAX_NUM_KEYS) + return -EBUSY; + + ap_key = kzalloc(sizeof(*ap_key), GFP_KERNEL); + if (!ap_key) + return -ENOMEM; + + ap_key->id = id; + ap_key->key_type = key_type; + ap_key->key_size = key_size; + memcpy(ap_key->key, key, key_size); + ap_key->hlid = hlid; + ap_key->tx_seq_32 = tx_seq_32; + ap_key->tx_seq_16 = tx_seq_16; + + wl->recorded_ap_keys[i] = ap_key; + return 0; +} + +static void wl1271_free_ap_keys(struct wl1271 *wl) +{ + int i; + + for (i = 0; i < MAX_NUM_KEYS; i++) { + kfree(wl->recorded_ap_keys[i]); + wl->recorded_ap_keys[i] = NULL; + } +} + +static int wl1271_ap_init_hwenc(struct wl1271 *wl) +{ + int i, ret = 0; + struct wl1271_ap_key *key; + bool wep_key_added = false; + + for (i = 0; i < MAX_NUM_KEYS; i++) { + if (wl->recorded_ap_keys[i] == NULL) + break; + + key = wl->recorded_ap_keys[i]; + ret = wl1271_cmd_set_ap_key(wl, KEY_ADD_OR_REPLACE, + key->id, key->key_type, + key->key_size, key->key, + key->hlid, key->tx_seq_32, + key->tx_seq_16); + if (ret < 0) + goto out; + + if (key->key_type == KEY_WEP) + wep_key_added = true; + } + + if (wep_key_added) { + ret = wl1271_cmd_set_ap_default_wep_key(wl, wl->default_key); + if (ret < 0) + goto out; + } + +out: + wl1271_free_ap_keys(wl); + return ret; +} + +static int wl1271_set_key(struct wl1271 *wl, u16 action, u8 id, u8 key_type, + u8 key_size, const u8 *key, u32 tx_seq_32, + u16 tx_seq_16, struct ieee80211_sta *sta) +{ + int ret; + bool is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); + + if (is_ap) { + struct wl1271_station *wl_sta; + u8 hlid; + + if (sta) { + wl_sta = (struct wl1271_station *)sta->drv_priv; + hlid = wl_sta->hlid; + } else { + hlid = WL1271_AP_BROADCAST_HLID; + } + + if (!test_bit(WL1271_FLAG_AP_STARTED, &wl->flags)) { + /* + * We do not support removing keys after AP shutdown. + * Pretend we do to make mac80211 happy. + */ + if (action != KEY_ADD_OR_REPLACE) + return 0; + + ret = wl1271_record_ap_key(wl, id, + key_type, key_size, + key, hlid, tx_seq_32, + tx_seq_16); + } else { + ret = wl1271_cmd_set_ap_key(wl, action, + id, key_type, key_size, + key, hlid, tx_seq_32, + tx_seq_16); + } + + if (ret < 0) + return ret; + } else { + const u8 *addr; + static const u8 bcast_addr[ETH_ALEN] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + }; + + addr = sta ? sta->addr : bcast_addr; + + if (is_zero_ether_addr(addr)) { + /* We dont support TX only encryption */ + return -EOPNOTSUPP; + } + + /* The wl1271 does not allow to remove unicast keys - they + will be cleared automatically on next CMD_JOIN. Ignore the + request silently, as we dont want the mac80211 to emit + an error message. */ + if (action == KEY_REMOVE && !is_broadcast_ether_addr(addr)) + return 0; + + ret = wl1271_cmd_set_sta_key(wl, action, + id, key_type, key_size, + key, addr, tx_seq_32, + tx_seq_16); + if (ret < 0) + return ret; + + /* the default WEP key needs to be configured at least once */ + if (key_type == KEY_WEP) { + ret = wl1271_cmd_set_sta_default_wep_key(wl, + wl->default_key); + if (ret < 0) + return ret; + } + } + + return 0; +} + static int wl1271_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key_conf) { struct wl1271 *wl = hw->priv; - const u8 *addr; int ret; u32 tx_seq_32 = 0; u16 tx_seq_16 = 0; u8 key_type; - static const u8 bcast_addr[ETH_ALEN] = - { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; - wl1271_debug(DEBUG_MAC80211, "mac80211 set key"); - addr = sta ? sta->addr : bcast_addr; - - wl1271_debug(DEBUG_CRYPT, "CMD: 0x%x", cmd); - wl1271_dump(DEBUG_CRYPT, "ADDR: ", addr, ETH_ALEN); + wl1271_debug(DEBUG_CRYPT, "CMD: 0x%x sta: %p", cmd, sta); wl1271_debug(DEBUG_CRYPT, "Key: algo:0x%x, id:%d, len:%d flags 0x%x", key_conf->cipher, key_conf->keyidx, key_conf->keylen, key_conf->flags); wl1271_dump(DEBUG_CRYPT, "KEY: ", key_conf->key, key_conf->keylen); - if (is_zero_ether_addr(addr)) { - /* We dont support TX only encryption */ - ret = -EOPNOTSUPP; - goto out; - } - mutex_lock(&wl->mutex); if (unlikely(wl->state == WL1271_STATE_OFF)) { @@ -1671,36 +1899,21 @@ static int wl1271_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, switch (cmd) { case SET_KEY: - ret = wl1271_cmd_set_key(wl, KEY_ADD_OR_REPLACE, - key_conf->keyidx, key_type, - key_conf->keylen, key_conf->key, - addr, tx_seq_32, tx_seq_16); + ret = wl1271_set_key(wl, KEY_ADD_OR_REPLACE, + key_conf->keyidx, key_type, + key_conf->keylen, key_conf->key, + tx_seq_32, tx_seq_16, sta); if (ret < 0) { wl1271_error("Could not add or replace key"); goto out_sleep; } - - /* the default WEP key needs to be configured at least once */ - if (key_type == KEY_WEP) { - ret = wl1271_cmd_set_default_wep_key(wl, - wl->default_key); - if (ret < 0) - goto out_sleep; - } break; case DISABLE_KEY: - /* The wl1271 does not allow to remove unicast keys - they - will be cleared automatically on next CMD_JOIN. Ignore the - request silently, as we dont want the mac80211 to emit - an error message. */ - if (!is_broadcast_ether_addr(addr)) - break; - - ret = wl1271_cmd_set_key(wl, KEY_REMOVE, - key_conf->keyidx, key_type, - key_conf->keylen, key_conf->key, - addr, 0, 0); + ret = wl1271_set_key(wl, KEY_REMOVE, + key_conf->keyidx, key_type, + key_conf->keylen, key_conf->key, + 0, 0, sta); if (ret < 0) { wl1271_error("Could not remove key"); goto out_sleep; @@ -1719,7 +1932,6 @@ out_sleep: out_unlock: mutex_unlock(&wl->mutex); -out: return ret; } @@ -1821,7 +2033,7 @@ out: return ret; } -static void wl1271_ssid_set(struct wl1271 *wl, struct sk_buff *skb, +static int wl1271_ssid_set(struct wl1271 *wl, struct sk_buff *skb, int offset) { u8 *ptr = skb->data + offset; @@ -1831,89 +2043,210 @@ static void wl1271_ssid_set(struct wl1271 *wl, struct sk_buff *skb, if (ptr[0] == WLAN_EID_SSID) { wl->ssid_len = ptr[1]; memcpy(wl->ssid, ptr+2, wl->ssid_len); - return; + return 0; } ptr += (ptr[1] + 2); } + wl1271_error("No SSID in IEs!\n"); + return -ENOENT; } -static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, +static int wl1271_bss_erp_info_changed(struct wl1271 *wl, struct ieee80211_bss_conf *bss_conf, u32 changed) { - enum wl1271_cmd_ps_mode mode; - struct wl1271 *wl = hw->priv; - struct ieee80211_sta *sta = ieee80211_find_sta(vif, bss_conf->bssid); - bool do_join = false; - bool set_assoc = false; - int ret; + int ret = 0; - wl1271_debug(DEBUG_MAC80211, "mac80211 bss info changed"); + if (changed & BSS_CHANGED_ERP_SLOT) { + if (bss_conf->use_short_slot) + ret = wl1271_acx_slot(wl, SLOT_TIME_SHORT); + else + ret = wl1271_acx_slot(wl, SLOT_TIME_LONG); + if (ret < 0) { + wl1271_warning("Set slot time failed %d", ret); + goto out; + } + } - mutex_lock(&wl->mutex); + if (changed & BSS_CHANGED_ERP_PREAMBLE) { + if (bss_conf->use_short_preamble) + wl1271_acx_set_preamble(wl, ACX_PREAMBLE_SHORT); + else + wl1271_acx_set_preamble(wl, ACX_PREAMBLE_LONG); + } - if (unlikely(wl->state == WL1271_STATE_OFF)) - goto out; + if (changed & BSS_CHANGED_ERP_CTS_PROT) { + if (bss_conf->use_cts_prot) + ret = wl1271_acx_cts_protect(wl, CTSPROTECT_ENABLE); + else + ret = wl1271_acx_cts_protect(wl, CTSPROTECT_DISABLE); + if (ret < 0) { + wl1271_warning("Set ctsprotect failed %d", ret); + goto out; + } + } - ret = wl1271_ps_elp_wakeup(wl, false); - if (ret < 0) - goto out; +out: + return ret; +} - if ((changed & BSS_CHANGED_BEACON_INT) && - (wl->bss_type == BSS_TYPE_IBSS)) { - wl1271_debug(DEBUG_ADHOC, "ad-hoc beacon interval updated: %d", +static int wl1271_bss_beacon_info_changed(struct wl1271 *wl, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *bss_conf, + u32 changed) +{ + bool is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); + int ret = 0; + + if ((changed & BSS_CHANGED_BEACON_INT)) { + wl1271_debug(DEBUG_MASTER, "beacon interval updated: %d", bss_conf->beacon_int); wl->beacon_int = bss_conf->beacon_int; - do_join = true; } - if ((changed & BSS_CHANGED_BEACON) && - (wl->bss_type == BSS_TYPE_IBSS)) { - struct sk_buff *beacon = ieee80211_beacon_get(hw, vif); + if ((changed & BSS_CHANGED_BEACON)) { + struct ieee80211_hdr *hdr; + int ieoffset = offsetof(struct ieee80211_mgmt, + u.beacon.variable); + struct sk_buff *beacon = ieee80211_beacon_get(wl->hw, vif); + u16 tmpl_id; - wl1271_debug(DEBUG_ADHOC, "ad-hoc beacon updated"); + if (!beacon) + goto out; - if (beacon) { - struct ieee80211_hdr *hdr; - int ieoffset = offsetof(struct ieee80211_mgmt, - u.beacon.variable); + wl1271_debug(DEBUG_MASTER, "beacon updated"); - wl1271_ssid_set(wl, beacon, ieoffset); + ret = wl1271_ssid_set(wl, beacon, ieoffset); + if (ret < 0) { + dev_kfree_skb(beacon); + goto out; + } + tmpl_id = is_ap ? CMD_TEMPL_AP_BEACON : + CMD_TEMPL_BEACON; + ret = wl1271_cmd_template_set(wl, tmpl_id, + beacon->data, + beacon->len, 0, + wl1271_tx_min_rate_get(wl)); + if (ret < 0) { + dev_kfree_skb(beacon); + goto out; + } - ret = wl1271_cmd_template_set(wl, CMD_TEMPL_BEACON, - beacon->data, - beacon->len, 0, - wl1271_min_rate_get(wl)); + hdr = (struct ieee80211_hdr *) beacon->data; + hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_PROBE_RESP); + + tmpl_id = is_ap ? CMD_TEMPL_AP_PROBE_RESPONSE : + CMD_TEMPL_PROBE_RESPONSE; + ret = wl1271_cmd_template_set(wl, + tmpl_id, + beacon->data, + beacon->len, 0, + wl1271_tx_min_rate_get(wl)); + dev_kfree_skb(beacon); + if (ret < 0) + goto out; + } - if (ret < 0) { - dev_kfree_skb(beacon); - goto out_sleep; - } +out: + return ret; +} - hdr = (struct ieee80211_hdr *) beacon->data; - hdr->frame_control = cpu_to_le16( - IEEE80211_FTYPE_MGMT | - IEEE80211_STYPE_PROBE_RESP); +/* AP mode changes */ +static void wl1271_bss_info_changed_ap(struct wl1271 *wl, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *bss_conf, + u32 changed) +{ + int ret = 0; - ret = wl1271_cmd_template_set(wl, - CMD_TEMPL_PROBE_RESPONSE, - beacon->data, - beacon->len, 0, - wl1271_min_rate_get(wl)); - dev_kfree_skb(beacon); - if (ret < 0) - goto out_sleep; + if ((changed & BSS_CHANGED_BASIC_RATES)) { + u32 rates = bss_conf->basic_rates; + struct conf_tx_rate_class mgmt_rc; + + wl->basic_rate_set = wl1271_tx_enabled_rates_get(wl, rates); + wl->basic_rate = wl1271_tx_min_rate_get(wl); + wl1271_debug(DEBUG_AP, "basic rates: 0x%x", + wl->basic_rate_set); + + /* update the AP management rate policy with the new rates */ + mgmt_rc.enabled_rates = wl->basic_rate_set; + mgmt_rc.long_retry_limit = 10; + mgmt_rc.short_retry_limit = 10; + mgmt_rc.aflags = 0; + ret = wl1271_acx_ap_rate_policy(wl, &mgmt_rc, + ACX_TX_AP_MODE_MGMT_RATE); + if (ret < 0) { + wl1271_error("AP mgmt policy change failed %d", ret); + goto out; + } + } - /* Need to update the SSID (for filtering etc) */ - do_join = true; + ret = wl1271_bss_beacon_info_changed(wl, vif, bss_conf, changed); + if (ret < 0) + goto out; + + if ((changed & BSS_CHANGED_BEACON_ENABLED)) { + if (bss_conf->enable_beacon) { + if (!test_bit(WL1271_FLAG_AP_STARTED, &wl->flags)) { + ret = wl1271_cmd_start_bss(wl); + if (ret < 0) + goto out; + + set_bit(WL1271_FLAG_AP_STARTED, &wl->flags); + wl1271_debug(DEBUG_AP, "started AP"); + + ret = wl1271_ap_init_hwenc(wl); + if (ret < 0) + goto out; + } + } else { + if (test_bit(WL1271_FLAG_AP_STARTED, &wl->flags)) { + ret = wl1271_cmd_stop_bss(wl); + if (ret < 0) + goto out; + + clear_bit(WL1271_FLAG_AP_STARTED, &wl->flags); + wl1271_debug(DEBUG_AP, "stopped AP"); + } } } - if ((changed & BSS_CHANGED_BEACON_ENABLED) && - (wl->bss_type == BSS_TYPE_IBSS)) { + ret = wl1271_bss_erp_info_changed(wl, bss_conf, changed); + if (ret < 0) + goto out; +out: + return; +} + +/* STA/IBSS mode changes */ +static void wl1271_bss_info_changed_sta(struct wl1271 *wl, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *bss_conf, + u32 changed) +{ + bool do_join = false, set_assoc = false; + bool is_ibss = (wl->bss_type == BSS_TYPE_IBSS); + int ret; + struct ieee80211_sta *sta; + + if (is_ibss) { + ret = wl1271_bss_beacon_info_changed(wl, vif, bss_conf, + changed); + if (ret < 0) + goto out; + } + + if ((changed & BSS_CHANGED_BEACON_INT) && is_ibss) + do_join = true; + + /* Need to update the SSID (for filtering etc) */ + if ((changed & BSS_CHANGED_BEACON) && is_ibss) + do_join = true; + + if ((changed & BSS_CHANGED_BEACON_ENABLED) && is_ibss) { wl1271_debug(DEBUG_ADHOC, "ad-hoc beaconing: %s", bss_conf->enable_beacon ? "enabled" : "disabled"); @@ -1924,7 +2257,7 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, do_join = true; } - if (changed & BSS_CHANGED_CQM) { + if ((changed & BSS_CHANGED_CQM)) { bool enable = false; if (bss_conf->cqm_rssi_thold) enable = true; @@ -1942,24 +2275,26 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, * and enable the BSSID filter */ memcmp(wl->bssid, bss_conf->bssid, ETH_ALEN)) { - memcpy(wl->bssid, bss_conf->bssid, ETH_ALEN); + memcpy(wl->bssid, bss_conf->bssid, ETH_ALEN); + if (!is_zero_ether_addr(wl->bssid)) { ret = wl1271_cmd_build_null_data(wl); if (ret < 0) - goto out_sleep; + goto out; ret = wl1271_build_qos_null_data(wl); if (ret < 0) - goto out_sleep; + goto out; /* filter out all packets not from this BSSID */ wl1271_configure_filters(wl, 0); /* Need to update the BSSID (for filtering etc) */ do_join = true; + } } - if (changed & BSS_CHANGED_ASSOC) { + if ((changed & BSS_CHANGED_ASSOC)) { if (bss_conf->assoc) { u32 rates; int ieoffset; @@ -1975,10 +2310,10 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, rates = bss_conf->basic_rates; wl->basic_rate_set = wl1271_tx_enabled_rates_get(wl, rates); - wl->basic_rate = wl1271_min_rate_get(wl); - ret = wl1271_acx_rate_policies(wl); + wl->basic_rate = wl1271_tx_min_rate_get(wl); + ret = wl1271_acx_sta_rate_policies(wl); if (ret < 0) - goto out_sleep; + goto out; /* * with wl1271, we don't need to update the @@ -1988,7 +2323,7 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, */ ret = wl1271_cmd_build_ps_poll(wl, wl->aid); if (ret < 0) - goto out_sleep; + goto out; /* * Get a template for hardware connection maintenance @@ -2002,17 +2337,19 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, /* enable the connection monitoring feature */ ret = wl1271_acx_conn_monit_params(wl, true); if (ret < 0) - goto out_sleep; + goto out; /* If we want to go in PSM but we're not there yet */ if (test_bit(WL1271_FLAG_PSM_REQUESTED, &wl->flags) && !test_bit(WL1271_FLAG_PSM, &wl->flags)) { + enum wl1271_cmd_ps_mode mode; + mode = STATION_POWER_SAVE_MODE; ret = wl1271_ps_set_mode(wl, mode, wl->basic_rate, true); if (ret < 0) - goto out_sleep; + goto out; } } else { /* use defaults when not associated */ @@ -2029,10 +2366,10 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, /* revert back to minimum rates for the current band */ wl1271_set_band_rate(wl); - wl->basic_rate = wl1271_min_rate_get(wl); - ret = wl1271_acx_rate_policies(wl); + wl->basic_rate = wl1271_tx_min_rate_get(wl); + ret = wl1271_acx_sta_rate_policies(wl); if (ret < 0) - goto out_sleep; + goto out; /* disable connection monitor features */ ret = wl1271_acx_conn_monit_params(wl, false); @@ -2040,74 +2377,54 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, /* Disable the keep-alive feature */ ret = wl1271_acx_keep_alive_mode(wl, false); if (ret < 0) - goto out_sleep; + goto out; /* restore the bssid filter and go to dummy bssid */ wl1271_unjoin(wl); wl1271_dummy_join(wl); } - - } - - if (changed & BSS_CHANGED_ERP_SLOT) { - if (bss_conf->use_short_slot) - ret = wl1271_acx_slot(wl, SLOT_TIME_SHORT); - else - ret = wl1271_acx_slot(wl, SLOT_TIME_LONG); - if (ret < 0) { - wl1271_warning("Set slot time failed %d", ret); - goto out_sleep; - } - } - - if (changed & BSS_CHANGED_ERP_PREAMBLE) { - if (bss_conf->use_short_preamble) - wl1271_acx_set_preamble(wl, ACX_PREAMBLE_SHORT); - else - wl1271_acx_set_preamble(wl, ACX_PREAMBLE_LONG); } - if (changed & BSS_CHANGED_ERP_CTS_PROT) { - if (bss_conf->use_cts_prot) - ret = wl1271_acx_cts_protect(wl, CTSPROTECT_ENABLE); - else - ret = wl1271_acx_cts_protect(wl, CTSPROTECT_DISABLE); - if (ret < 0) { - wl1271_warning("Set ctsprotect failed %d", ret); - goto out_sleep; - } - } + ret = wl1271_bss_erp_info_changed(wl, bss_conf, changed); + if (ret < 0) + goto out; - /* - * Takes care of: New association with HT enable, - * HT information change in beacon. - */ - if (sta && - (changed & BSS_CHANGED_HT) && - (bss_conf->channel_type != NL80211_CHAN_NO_HT)) { - ret = wl1271_acx_set_ht_capabilities(wl, &sta->ht_cap, true); - if (ret < 0) { - wl1271_warning("Set ht cap true failed %d", ret); - goto out_sleep; - } + rcu_read_lock(); + sta = ieee80211_find_sta(vif, bss_conf->bssid); + if (sta) { + /* handle new association with HT and HT information change */ + if ((changed & BSS_CHANGED_HT) && + (bss_conf->channel_type != NL80211_CHAN_NO_HT)) { + ret = wl1271_acx_set_ht_capabilities(wl, &sta->ht_cap, + true); + if (ret < 0) { + wl1271_warning("Set ht cap true failed %d", + ret); + rcu_read_unlock(); + goto out; + } ret = wl1271_acx_set_ht_information(wl, - bss_conf->ht_operation_mode); - if (ret < 0) { - wl1271_warning("Set ht information failed %d", ret); - goto out_sleep; + bss_conf->ht_operation_mode); + if (ret < 0) { + wl1271_warning("Set ht information failed %d", + ret); + rcu_read_unlock(); + goto out; + } } - } - /* - * Takes care of: New association without HT, - * Disassociation. - */ - else if (sta && (changed & BSS_CHANGED_ASSOC)) { - ret = wl1271_acx_set_ht_capabilities(wl, &sta->ht_cap, false); - if (ret < 0) { - wl1271_warning("Set ht cap false failed %d", ret); - goto out_sleep; + /* handle new association without HT and disassociation */ + else if (changed & BSS_CHANGED_ASSOC) { + ret = wl1271_acx_set_ht_capabilities(wl, &sta->ht_cap, + false); + if (ret < 0) { + wl1271_warning("Set ht cap false failed %d", + ret); + rcu_read_unlock(); + goto out; + } } } + rcu_read_unlock(); if (changed & BSS_CHANGED_ARP_FILTER) { __be32 addr = bss_conf->arp_addr_list[0]; @@ -2124,76 +2441,128 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, ret = wl1271_cmd_build_arp_rsp(wl, addr); if (ret < 0) { wl1271_warning("build arp rsp failed: %d", ret); - goto out_sleep; + goto out; } ret = wl1271_acx_arp_ip_filter(wl, - (ACX_ARP_FILTER_ARP_FILTERING | - ACX_ARP_FILTER_AUTO_ARP), + ACX_ARP_FILTER_ARP_FILTERING, addr); } else ret = wl1271_acx_arp_ip_filter(wl, 0, addr); if (ret < 0) - goto out_sleep; + goto out; } if (do_join) { ret = wl1271_join(wl, set_assoc); if (ret < 0) { wl1271_warning("cmd join failed %d", ret); - goto out_sleep; + goto out; } } -out_sleep: - wl1271_ps_elp_sleep(wl); - out: - mutex_unlock(&wl->mutex); + return; } -static int wl1271_op_conf_tx(struct ieee80211_hw *hw, u16 queue, - const struct ieee80211_tx_queue_params *params) +static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *bss_conf, + u32 changed) { struct wl1271 *wl = hw->priv; - u8 ps_scheme; + bool is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); int ret; - mutex_lock(&wl->mutex); + wl1271_debug(DEBUG_MAC80211, "mac80211 bss info changed 0x%x", + (int)changed); - wl1271_debug(DEBUG_MAC80211, "mac80211 conf tx %d", queue); + mutex_lock(&wl->mutex); - if (unlikely(wl->state == WL1271_STATE_OFF)) { - ret = -EAGAIN; + if (unlikely(wl->state == WL1271_STATE_OFF)) goto out; - } ret = wl1271_ps_elp_wakeup(wl, false); if (ret < 0) goto out; - /* the txop is confed in units of 32us by the mac80211, we need us */ - ret = wl1271_acx_ac_cfg(wl, wl1271_tx_get_queue(queue), - params->cw_min, params->cw_max, - params->aifs, params->txop << 5); - if (ret < 0) - goto out_sleep; + if (is_ap) + wl1271_bss_info_changed_ap(wl, vif, bss_conf, changed); + else + wl1271_bss_info_changed_sta(wl, vif, bss_conf, changed); + + wl1271_ps_elp_sleep(wl); + +out: + mutex_unlock(&wl->mutex); +} + +static int wl1271_op_conf_tx(struct ieee80211_hw *hw, u16 queue, + const struct ieee80211_tx_queue_params *params) +{ + struct wl1271 *wl = hw->priv; + u8 ps_scheme; + int ret = 0; + + mutex_lock(&wl->mutex); + + wl1271_debug(DEBUG_MAC80211, "mac80211 conf tx %d", queue); if (params->uapsd) ps_scheme = CONF_PS_SCHEME_UPSD_TRIGGER; else ps_scheme = CONF_PS_SCHEME_LEGACY; - ret = wl1271_acx_tid_cfg(wl, wl1271_tx_get_queue(queue), - CONF_CHANNEL_TYPE_EDCF, - wl1271_tx_get_queue(queue), - ps_scheme, CONF_ACK_POLICY_LEGACY, 0, 0); - if (ret < 0) - goto out_sleep; + if (wl->state == WL1271_STATE_OFF) { + /* + * If the state is off, the parameters will be recorded and + * configured on init. This happens in AP-mode. + */ + struct conf_tx_ac_category *conf_ac = + &wl->conf.tx.ac_conf[wl1271_tx_get_queue(queue)]; + struct conf_tx_tid *conf_tid = + &wl->conf.tx.tid_conf[wl1271_tx_get_queue(queue)]; + + conf_ac->ac = wl1271_tx_get_queue(queue); + conf_ac->cw_min = (u8)params->cw_min; + conf_ac->cw_max = params->cw_max; + conf_ac->aifsn = params->aifs; + conf_ac->tx_op_limit = params->txop << 5; + + conf_tid->queue_id = wl1271_tx_get_queue(queue); + conf_tid->channel_type = CONF_CHANNEL_TYPE_EDCF; + conf_tid->tsid = wl1271_tx_get_queue(queue); + conf_tid->ps_scheme = ps_scheme; + conf_tid->ack_policy = CONF_ACK_POLICY_LEGACY; + conf_tid->apsd_conf[0] = 0; + conf_tid->apsd_conf[1] = 0; + } else { + ret = wl1271_ps_elp_wakeup(wl, false); + if (ret < 0) + goto out; + + /* + * the txop is confed in units of 32us by the mac80211, + * we need us + */ + ret = wl1271_acx_ac_cfg(wl, wl1271_tx_get_queue(queue), + params->cw_min, params->cw_max, + params->aifs, params->txop << 5); + if (ret < 0) + goto out_sleep; + + ret = wl1271_acx_tid_cfg(wl, wl1271_tx_get_queue(queue), + CONF_CHANNEL_TYPE_EDCF, + wl1271_tx_get_queue(queue), + ps_scheme, CONF_ACK_POLICY_LEGACY, + 0, 0); + if (ret < 0) + goto out_sleep; out_sleep: - wl1271_ps_elp_sleep(wl); + wl1271_ps_elp_sleep(wl); + } out: mutex_unlock(&wl->mutex); @@ -2247,6 +2616,173 @@ static int wl1271_op_get_survey(struct ieee80211_hw *hw, int idx, return 0; } +static int wl1271_allocate_hlid(struct wl1271 *wl, + struct ieee80211_sta *sta, + u8 *hlid) +{ + struct wl1271_station *wl_sta; + int id; + + id = find_first_zero_bit(wl->ap_hlid_map, AP_MAX_STATIONS); + if (id >= AP_MAX_STATIONS) { + wl1271_warning("could not allocate HLID - too much stations"); + return -EBUSY; + } + + wl_sta = (struct wl1271_station *)sta->drv_priv; + + __set_bit(id, wl->ap_hlid_map); + wl_sta->hlid = WL1271_AP_STA_HLID_START + id; + *hlid = wl_sta->hlid; + return 0; +} + +static void wl1271_free_hlid(struct wl1271 *wl, u8 hlid) +{ + int id = hlid - WL1271_AP_STA_HLID_START; + + __clear_bit(id, wl->ap_hlid_map); +} + +static int wl1271_op_sta_add(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct wl1271 *wl = hw->priv; + int ret = 0; + u8 hlid; + + mutex_lock(&wl->mutex); + + if (unlikely(wl->state == WL1271_STATE_OFF)) + goto out; + + if (wl->bss_type != BSS_TYPE_AP_BSS) + goto out; + + wl1271_debug(DEBUG_MAC80211, "mac80211 add sta %d", (int)sta->aid); + + ret = wl1271_allocate_hlid(wl, sta, &hlid); + if (ret < 0) + goto out; + + ret = wl1271_ps_elp_wakeup(wl, false); + if (ret < 0) + goto out; + + ret = wl1271_cmd_add_sta(wl, sta, hlid); + if (ret < 0) + goto out_sleep; + +out_sleep: + wl1271_ps_elp_sleep(wl); + +out: + mutex_unlock(&wl->mutex); + return ret; +} + +static int wl1271_op_sta_remove(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct wl1271 *wl = hw->priv; + struct wl1271_station *wl_sta; + int ret = 0, id; + + mutex_lock(&wl->mutex); + + if (unlikely(wl->state == WL1271_STATE_OFF)) + goto out; + + if (wl->bss_type != BSS_TYPE_AP_BSS) + goto out; + + wl1271_debug(DEBUG_MAC80211, "mac80211 remove sta %d", (int)sta->aid); + + wl_sta = (struct wl1271_station *)sta->drv_priv; + id = wl_sta->hlid - WL1271_AP_STA_HLID_START; + if (WARN_ON(!test_bit(id, wl->ap_hlid_map))) + goto out; + + ret = wl1271_ps_elp_wakeup(wl, false); + if (ret < 0) + goto out; + + ret = wl1271_cmd_remove_sta(wl, wl_sta->hlid); + if (ret < 0) + goto out_sleep; + + wl1271_free_hlid(wl, wl_sta->hlid); + +out_sleep: + wl1271_ps_elp_sleep(wl); + +out: + mutex_unlock(&wl->mutex); + return ret; +} + +int wl1271_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + enum ieee80211_ampdu_mlme_action action, + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) +{ + struct wl1271 *wl = hw->priv; + int ret; + + mutex_lock(&wl->mutex); + + if (unlikely(wl->state == WL1271_STATE_OFF)) { + ret = -EAGAIN; + goto out; + } + + ret = wl1271_ps_elp_wakeup(wl, false); + if (ret < 0) + goto out; + + switch (action) { + case IEEE80211_AMPDU_RX_START: + if (wl->ba_support) { + ret = wl1271_acx_set_ba_receiver_session(wl, tid, *ssn, + true); + if (!ret) + wl->ba_rx_bitmap |= BIT(tid); + } else { + ret = -ENOTSUPP; + } + break; + + case IEEE80211_AMPDU_RX_STOP: + ret = wl1271_acx_set_ba_receiver_session(wl, tid, 0, false); + if (!ret) + wl->ba_rx_bitmap &= ~BIT(tid); + break; + + /* + * The BA initiator session management in FW independently. + * Falling break here on purpose for all TX APDU commands. + */ + case IEEE80211_AMPDU_TX_START: + case IEEE80211_AMPDU_TX_STOP: + case IEEE80211_AMPDU_TX_OPERATIONAL: + ret = -EINVAL; + break; + + default: + wl1271_error("Incorrect ampdu action id=%x\n", action); + ret = -EINVAL; + } + + wl1271_ps_elp_sleep(wl); + +out: + mutex_unlock(&wl->mutex); + + return ret; +} + /* can't be const, mac80211 writes to this */ static struct ieee80211_rate wl1271_rates[] = { { .bitrate = 10, @@ -2305,6 +2841,7 @@ static struct ieee80211_channel wl1271_channels[] = { { .hw_value = 11, .center_freq = 2462, .max_power = 25 }, { .hw_value = 12, .center_freq = 2467, .max_power = 25 }, { .hw_value = 13, .center_freq = 2472, .max_power = 25 }, + { .hw_value = 14, .center_freq = 2484, .max_power = 25 }, }; /* mapping to indexes for wl1271_rates */ @@ -2493,6 +3030,9 @@ static const struct ieee80211_ops wl1271_ops = { .conf_tx = wl1271_op_conf_tx, .get_tsf = wl1271_op_get_tsf, .get_survey = wl1271_op_get_survey, + .sta_add = wl1271_op_sta_add, + .sta_remove = wl1271_op_sta_remove, + .ampdu_action = wl1271_op_ampdu_action, CFG80211_TESTMODE_CMD(wl1271_tm_cmd) }; @@ -2607,6 +3147,18 @@ int wl1271_register_hw(struct wl1271 *wl) if (wl->mac80211_registered) return 0; + ret = wl1271_fetch_nvs(wl); + if (ret == 0) { + u8 *nvs_ptr = (u8 *)wl->nvs->nvs; + + wl->mac_addr[0] = nvs_ptr[11]; + wl->mac_addr[1] = nvs_ptr[10]; + wl->mac_addr[2] = nvs_ptr[6]; + wl->mac_addr[3] = nvs_ptr[5]; + wl->mac_addr[4] = nvs_ptr[4]; + wl->mac_addr[5] = nvs_ptr[3]; + } + SET_IEEE80211_PERM_ADDR(wl->hw, wl->mac_addr); ret = ieee80211_register_hw(wl->hw); @@ -2629,6 +3181,9 @@ EXPORT_SYMBOL_GPL(wl1271_register_hw); void wl1271_unregister_hw(struct wl1271 *wl) { + if (wl->state == WL1271_STATE_PLT) + __wl1271_plt_stop(wl); + unregister_netdevice_notifier(&wl1271_dev_notifier); ieee80211_unregister_hw(wl->hw); wl->mac80211_registered = false; @@ -2667,7 +3222,7 @@ int wl1271_init_ieee80211(struct wl1271 *wl) wl->hw->wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); wl->hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | - BIT(NL80211_IFTYPE_ADHOC); + BIT(NL80211_IFTYPE_ADHOC) | BIT(NL80211_IFTYPE_AP); wl->hw->wiphy->max_scan_ssids = 1; /* * Maximum length of elements in scanning probe request templates @@ -2676,8 +3231,20 @@ int wl1271_init_ieee80211(struct wl1271 *wl) */ wl->hw->wiphy->max_scan_ie_len = WL1271_CMD_TEMPL_MAX_SIZE - sizeof(struct ieee80211_header); - wl->hw->wiphy->bands[IEEE80211_BAND_2GHZ] = &wl1271_band_2ghz; - wl->hw->wiphy->bands[IEEE80211_BAND_5GHZ] = &wl1271_band_5ghz; + + /* + * We keep local copies of the band structs because we need to + * modify them on a per-device basis. + */ + memcpy(&wl->bands[IEEE80211_BAND_2GHZ], &wl1271_band_2ghz, + sizeof(wl1271_band_2ghz)); + memcpy(&wl->bands[IEEE80211_BAND_5GHZ], &wl1271_band_5ghz, + sizeof(wl1271_band_5ghz)); + + wl->hw->wiphy->bands[IEEE80211_BAND_2GHZ] = + &wl->bands[IEEE80211_BAND_2GHZ]; + wl->hw->wiphy->bands[IEEE80211_BAND_5GHZ] = + &wl->bands[IEEE80211_BAND_5GHZ]; wl->hw->queues = 4; wl->hw->max_rates = 1; @@ -2686,6 +3253,10 @@ int wl1271_init_ieee80211(struct wl1271 *wl) SET_IEEE80211_DEV(wl->hw, wl1271_wl_to_dev(wl)); + wl->hw->sta_data_size = sizeof(struct wl1271_station); + + wl->hw->max_rx_aggregation_subframes = 8; + return 0; } EXPORT_SYMBOL_GPL(wl1271_init_ieee80211); @@ -2735,8 +3306,8 @@ struct ieee80211_hw *wl1271_alloc_hw(void) wl->beacon_int = WL1271_DEFAULT_BEACON_INT; wl->default_key = 0; wl->rx_counter = 0; - wl->rx_config = WL1271_DEFAULT_RX_CONFIG; - wl->rx_filter = WL1271_DEFAULT_RX_FILTER; + wl->rx_config = WL1271_DEFAULT_STA_RX_CONFIG; + wl->rx_filter = WL1271_DEFAULT_STA_RX_FILTER; wl->psm_entry_retry = 0; wl->power_level = WL1271_DEFAULT_POWER_LEVEL; wl->basic_rate_set = CONF_TX_RATE_MASK_BASIC; @@ -2748,6 +3319,9 @@ struct ieee80211_hw *wl1271_alloc_hw(void) wl->flags = 0; wl->sg_enabled = true; wl->hw_pg_ver = -1; + wl->bss_type = MAX_BSS_TYPE; + wl->set_bss_type = MAX_BSS_TYPE; + wl->fw_bss_type = MAX_BSS_TYPE; memset(wl->tx_frames_map, 0, sizeof(wl->tx_frames_map)); for (i = 0; i < ACX_TX_DESCRIPTORS; i++) @@ -2837,9 +3411,9 @@ int wl1271_free_hw(struct wl1271 *wl) } EXPORT_SYMBOL_GPL(wl1271_free_hw); -u32 wl12xx_debug_level; +u32 wl12xx_debug_level = DEBUG_NONE; EXPORT_SYMBOL_GPL(wl12xx_debug_level); -module_param_named(debug_level, wl12xx_debug_level, uint, DEBUG_NONE); +module_param_named(debug_level, wl12xx_debug_level, uint, S_IRUSR | S_IWUSR); MODULE_PARM_DESC(debug_level, "wl12xx debugging level"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/wl12xx/rx.c b/drivers/net/wireless/wl12xx/rx.c index 682304c..b0c6ddc 100644 --- a/drivers/net/wireless/wl12xx/rx.c +++ b/drivers/net/wireless/wl12xx/rx.c @@ -76,7 +76,7 @@ static void wl1271_rx_status(struct wl1271 *wl, */ wl->noise = desc->rssi - (desc->snr >> 1); - status->freq = ieee80211_channel_to_frequency(desc->channel); + status->freq = ieee80211_channel_to_frequency(desc->channel, desc_band); if (desc->flags & WL1271_RX_DESC_ENCRYPT_MASK) { status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED; @@ -198,6 +198,16 @@ void wl1271_rx(struct wl1271 *wl, struct wl1271_fw_status *status) pkt_offset += pkt_length; } } - wl1271_write32(wl, RX_DRIVER_COUNTER_ADDRESS, - cpu_to_le32(wl->rx_counter)); + wl1271_write32(wl, RX_DRIVER_COUNTER_ADDRESS, wl->rx_counter); +} + +void wl1271_set_default_filters(struct wl1271 *wl) +{ + if (wl->bss_type == BSS_TYPE_AP_BSS) { + wl->rx_config = WL1271_DEFAULT_AP_RX_CONFIG; + wl->rx_filter = WL1271_DEFAULT_AP_RX_FILTER; + } else { + wl->rx_config = WL1271_DEFAULT_STA_RX_CONFIG; + wl->rx_filter = WL1271_DEFAULT_STA_RX_FILTER; + } } diff --git a/drivers/net/wireless/wl12xx/rx.h b/drivers/net/wireless/wl12xx/rx.h index 3abb26f..8d048b3 100644 --- a/drivers/net/wireless/wl12xx/rx.h +++ b/drivers/net/wireless/wl12xx/rx.h @@ -86,8 +86,9 @@ /* * RX Descriptor status * - * Bits 0-2 - status - * Bits 3-7 - reserved + * Bits 0-2 - error code + * Bits 3-5 - process_id tag (AP mode FW) + * Bits 6-7 - reserved */ #define WL1271_RX_DESC_STATUS_MASK 0x07 @@ -110,12 +111,16 @@ struct wl1271_rx_descriptor { u8 snr; __le32 timestamp; u8 packet_class; - u8 process_id; + union { + u8 process_id; /* STA FW */ + u8 hlid; /* AP FW */ + } __packed; u8 pad_len; u8 reserved; } __packed; void wl1271_rx(struct wl1271 *wl, struct wl1271_fw_status *status); u8 wl1271_rate_to_idx(int rate, enum ieee80211_band band); +void wl1271_set_default_filters(struct wl1271 *wl); #endif diff --git a/drivers/net/wireless/wl12xx/sdio.c b/drivers/net/wireless/wl12xx/sdio.c index 93cbb8d..d5e8748 100644 --- a/drivers/net/wireless/wl12xx/sdio.c +++ b/drivers/net/wireless/wl12xx/sdio.c @@ -345,3 +345,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>"); MODULE_FIRMWARE(WL1271_FW_NAME); +MODULE_FIRMWARE(WL1271_AP_FW_NAME); diff --git a/drivers/net/wireless/wl12xx/spi.c b/drivers/net/wireless/wl12xx/spi.c index 7145ea5..0132dad 100644 --- a/drivers/net/wireless/wl12xx/spi.c +++ b/drivers/net/wireless/wl12xx/spi.c @@ -110,6 +110,7 @@ static void wl1271_spi_reset(struct wl1271 *wl) spi_message_add_tail(&t, &m); spi_sync(wl_to_spi(wl), &m); + wl1271_dump(DEBUG_SPI, "spi reset -> ", cmd, WSPI_INIT_CMD_LEN); kfree(cmd); } @@ -494,4 +495,5 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>"); MODULE_FIRMWARE(WL1271_FW_NAME); +MODULE_FIRMWARE(WL1271_AP_FW_NAME); MODULE_ALIAS("spi:wl1271"); diff --git a/drivers/net/wireless/wl12xx/tx.c b/drivers/net/wireless/wl12xx/tx.c index b44c75c..3507c81 100644 --- a/drivers/net/wireless/wl12xx/tx.c +++ b/drivers/net/wireless/wl12xx/tx.c @@ -23,6 +23,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/etherdevice.h> #include "wl12xx.h" #include "io.h" @@ -30,6 +31,23 @@ #include "ps.h" #include "tx.h" +static int wl1271_set_default_wep_key(struct wl1271 *wl, u8 id) +{ + int ret; + bool is_ap = (wl->bss_type == BSS_TYPE_AP_BSS); + + if (is_ap) + ret = wl1271_cmd_set_ap_default_wep_key(wl, id); + else + ret = wl1271_cmd_set_sta_default_wep_key(wl, id); + + if (ret < 0) + return ret; + + wl1271_debug(DEBUG_CRYPT, "default wep key idx: %d", (int)id); + return 0; +} + static int wl1271_alloc_tx_id(struct wl1271 *wl, struct sk_buff *skb) { int id; @@ -99,7 +117,7 @@ static void wl1271_tx_fill_hdr(struct wl1271 *wl, struct sk_buff *skb, { struct timespec ts; struct wl1271_tx_hw_descr *desc; - int pad, ac; + int pad, ac, rate_idx; s64 hosttime; u16 tx_attr; @@ -117,7 +135,11 @@ static void wl1271_tx_fill_hdr(struct wl1271 *wl, struct sk_buff *skb, getnstimeofday(&ts); hosttime = (timespec_to_ns(&ts) >> 10); desc->start_time = cpu_to_le32(hosttime - wl->time_offset); - desc->life_time = cpu_to_le16(TX_HW_MGMT_PKT_LIFETIME_TU); + + if (wl->bss_type != BSS_TYPE_AP_BSS) + desc->life_time = cpu_to_le16(TX_HW_MGMT_PKT_LIFETIME_TU); + else + desc->life_time = cpu_to_le16(TX_HW_AP_MODE_PKT_LIFETIME_TU); /* configure the tx attributes */ tx_attr = wl->session_counter << TX_HW_ATTR_OFST_SESSION_COUNTER; @@ -125,7 +147,41 @@ static void wl1271_tx_fill_hdr(struct wl1271 *wl, struct sk_buff *skb, /* queue (we use same identifiers for tid's and ac's */ ac = wl1271_tx_get_queue(skb_get_queue_mapping(skb)); desc->tid = ac; - desc->aid = TX_HW_DEFAULT_AID; + + if (wl->bss_type != BSS_TYPE_AP_BSS) { + desc->aid = TX_HW_DEFAULT_AID; + + /* if the packets are destined for AP (have a STA entry) + send them with AP rate policies, otherwise use default + basic rates */ + if (control->control.sta) + rate_idx = ACX_TX_AP_FULL_RATE; + else + rate_idx = ACX_TX_BASIC_RATE; + } else { + if (control->control.sta) { + struct wl1271_station *wl_sta; + + wl_sta = (struct wl1271_station *) + control->control.sta->drv_priv; + desc->hlid = wl_sta->hlid; + rate_idx = ac; + } else { + struct ieee80211_hdr *hdr; + + hdr = (struct ieee80211_hdr *) + (skb->data + sizeof(*desc)); + if (ieee80211_is_mgmt(hdr->frame_control)) { + desc->hlid = WL1271_AP_GLOBAL_HLID; + rate_idx = ACX_TX_AP_MODE_MGMT_RATE; + } else { + desc->hlid = WL1271_AP_BROADCAST_HLID; + rate_idx = ACX_TX_AP_MODE_BCST_RATE; + } + } + } + + tx_attr |= rate_idx << TX_HW_ATTR_OFST_RATE_POLICY; desc->reserved = 0; /* align the length (and store in terms of words) */ @@ -136,14 +192,12 @@ static void wl1271_tx_fill_hdr(struct wl1271 *wl, struct sk_buff *skb, pad = pad - skb->len; tx_attr |= pad << TX_HW_ATTR_OFST_LAST_WORD_PAD; - /* if the packets are destined for AP (have a STA entry) send them - with AP rate policies, otherwise use default basic rates */ - if (control->control.sta) - tx_attr |= ACX_TX_AP_FULL_RATE << TX_HW_ATTR_OFST_RATE_POLICY; - desc->tx_attr = cpu_to_le16(tx_attr); - wl1271_debug(DEBUG_TX, "tx_fill_hdr: pad: %d", pad); + wl1271_debug(DEBUG_TX, "tx_fill_hdr: pad: %d hlid: %d " + "tx_attr: 0x%x len: %d life: %d mem: %d", pad, desc->hlid, + le16_to_cpu(desc->tx_attr), le16_to_cpu(desc->length), + le16_to_cpu(desc->life_time), desc->total_mem_blocks); } /* caller must hold wl->mutex */ @@ -153,7 +207,6 @@ static int wl1271_prepare_tx_frame(struct wl1271 *wl, struct sk_buff *skb, struct ieee80211_tx_info *info; u32 extra = 0; int ret = 0; - u8 idx; u32 total_len; if (!skb) @@ -166,11 +219,15 @@ static int wl1271_prepare_tx_frame(struct wl1271 *wl, struct sk_buff *skb, extra = WL1271_TKIP_IV_SPACE; if (info->control.hw_key) { - idx = info->control.hw_key->hw_key_idx; + bool is_wep; + u8 idx = info->control.hw_key->hw_key_idx; + u32 cipher = info->control.hw_key->cipher; + + is_wep = (cipher == WLAN_CIPHER_SUITE_WEP40) || + (cipher == WLAN_CIPHER_SUITE_WEP104); - /* FIXME: do we have to do this if we're not using WEP? */ - if (unlikely(wl->default_key != idx)) { - ret = wl1271_cmd_set_default_wep_key(wl, idx); + if (unlikely(is_wep && wl->default_key != idx)) { + ret = wl1271_set_default_wep_key(wl, idx); if (ret < 0) return ret; wl->default_key = idx; @@ -303,7 +360,7 @@ void wl1271_tx_work_locked(struct wl1271 *wl) woken_up = true; wl->rate_set = wl1271_tx_enabled_rates_get(wl, sta_rates); - wl1271_acx_rate_policies(wl); + wl1271_acx_sta_rate_policies(wl); } while ((skb = wl1271_skb_dequeue(wl))) { @@ -521,3 +578,21 @@ void wl1271_tx_flush(struct wl1271 *wl) wl1271_warning("Unable to flush all TX buffers, timed out."); } + +u32 wl1271_tx_min_rate_get(struct wl1271 *wl) +{ + int i; + u32 rate = 0; + + if (!wl->basic_rate_set) { + WARN_ON(1); + wl->basic_rate_set = wl->conf.tx.basic_rate; + } + + for (i = 0; !rate; i++) { + if ((wl->basic_rate_set >> i) & 0x1) + rate = 1 << i; + } + + return rate; +} diff --git a/drivers/net/wireless/wl12xx/tx.h b/drivers/net/wireless/wl12xx/tx.h index 903e5dc..05722a5 100644 --- a/drivers/net/wireless/wl12xx/tx.h +++ b/drivers/net/wireless/wl12xx/tx.h @@ -29,6 +29,7 @@ #define TX_HW_BLOCK_SIZE 252 #define TX_HW_MGMT_PKT_LIFETIME_TU 2000 +#define TX_HW_AP_MODE_PKT_LIFETIME_TU 8000 /* The chipset reference driver states, that the "aid" value 1 * is for infra-BSS, but is still always used */ #define TX_HW_DEFAULT_AID 1 @@ -77,8 +78,12 @@ struct wl1271_tx_hw_descr { u8 id; /* The packet TID value (as User-Priority) */ u8 tid; - /* Identifier of the remote STA in IBSS, 1 in infra-BSS */ - u8 aid; + union { + /* STA - Identifier of the remote STA in IBSS, 1 in infra-BSS */ + u8 aid; + /* AP - host link ID (HLID) */ + u8 hlid; + } __packed; u8 reserved; } __packed; @@ -146,5 +151,6 @@ void wl1271_tx_reset(struct wl1271 *wl); void wl1271_tx_flush(struct wl1271 *wl); u8 wl1271_rate_to_idx(int rate, enum ieee80211_band band); u32 wl1271_tx_enabled_rates_get(struct wl1271 *wl, u32 rate_set); +u32 wl1271_tx_min_rate_get(struct wl1271 *wl); #endif diff --git a/drivers/net/wireless/wl12xx/wl12xx.h b/drivers/net/wireless/wl12xx/wl12xx.h index 9050dd9..d1de13f 100644 --- a/drivers/net/wireless/wl12xx/wl12xx.h +++ b/drivers/net/wireless/wl12xx/wl12xx.h @@ -38,6 +38,13 @@ #define DRIVER_NAME "wl1271" #define DRIVER_PREFIX DRIVER_NAME ": " +/* + * FW versions support BA 11n + * versions marks x.x.x.50-60.x + */ +#define WL12XX_BA_SUPPORT_FW_COST_VER2_START 50 +#define WL12XX_BA_SUPPORT_FW_COST_VER2_END 60 + enum { DEBUG_NONE = 0, DEBUG_IRQ = BIT(0), @@ -57,6 +64,8 @@ enum { DEBUG_SDIO = BIT(14), DEBUG_FILTERS = BIT(15), DEBUG_ADHOC = BIT(16), + DEBUG_AP = BIT(17), + DEBUG_MASTER = (DEBUG_ADHOC | DEBUG_AP), DEBUG_ALL = ~0, }; @@ -103,16 +112,27 @@ extern u32 wl12xx_debug_level; true); \ } while (0) -#define WL1271_DEFAULT_RX_CONFIG (CFG_UNI_FILTER_EN | \ +#define WL1271_DEFAULT_STA_RX_CONFIG (CFG_UNI_FILTER_EN | \ CFG_BSSID_FILTER_EN | \ CFG_MC_FILTER_EN) -#define WL1271_DEFAULT_RX_FILTER (CFG_RX_RCTS_ACK | CFG_RX_PRSP_EN | \ +#define WL1271_DEFAULT_STA_RX_FILTER (CFG_RX_RCTS_ACK | CFG_RX_PRSP_EN | \ CFG_RX_MGMT_EN | CFG_RX_DATA_EN | \ CFG_RX_CTL_EN | CFG_RX_BCN_EN | \ CFG_RX_AUTH_EN | CFG_RX_ASSOC_EN) +#define WL1271_DEFAULT_AP_RX_CONFIG 0 + +#define WL1271_DEFAULT_AP_RX_FILTER (CFG_RX_RCTS_ACK | CFG_RX_PREQ_EN | \ + CFG_RX_MGMT_EN | CFG_RX_DATA_EN | \ + CFG_RX_CTL_EN | CFG_RX_AUTH_EN | \ + CFG_RX_ASSOC_EN) + + + #define WL1271_FW_NAME "wl1271-fw.bin" +#define WL1271_AP_FW_NAME "wl1271-fw-ap.bin" + #define WL1271_NVS_NAME "wl1271-nvs.bin" #define WL1271_TX_SECURITY_LO16(s) ((u16)((s) & 0xffff)) @@ -129,6 +149,14 @@ extern u32 wl12xx_debug_level; #define WL1271_DEFAULT_BEACON_INT 100 #define WL1271_DEFAULT_DTIM_PERIOD 1 +#define WL1271_AP_GLOBAL_HLID 0 +#define WL1271_AP_BROADCAST_HLID 1 +#define WL1271_AP_STA_HLID_START 2 + +#define WL1271_AP_BSS_INDEX 0 +#define WL1271_AP_DEF_INACTIV_SEC 300 +#define WL1271_AP_DEF_BEACON_EXP 20 + #define ACX_TX_DESCRIPTORS 32 #define WL1271_AGGR_BUFFER_SIZE (4 * PAGE_SIZE) @@ -161,10 +189,13 @@ struct wl1271_partition_set { struct wl1271; +#define WL12XX_NUM_FW_VER 5 + /* FIXME: I'm not sure about this structure name */ struct wl1271_chip { u32 id; - char fw_ver[21]; + char fw_ver_str[ETHTOOL_BUSINFO_LEN]; + unsigned int fw_ver[WL12XX_NUM_FW_VER]; }; struct wl1271_stats { @@ -178,6 +209,11 @@ struct wl1271_stats { #define NUM_TX_QUEUES 4 #define NUM_RX_PKT_DESC 8 +#define AP_MAX_STATIONS 5 + +/* Broadcast and Global links + links to stations */ +#define AP_MAX_LINKS (AP_MAX_STATIONS + 2) + /* FW status registers */ struct wl1271_fw_status { __le32 intr; @@ -188,7 +224,18 @@ struct wl1271_fw_status { __le32 rx_pkt_descs[NUM_RX_PKT_DESC]; __le32 tx_released_blks[NUM_TX_QUEUES]; __le32 fw_localtime; - __le32 padding[2]; + + /* Next fields valid only in AP FW */ + + /* + * A bitmap (where each bit represents a single HLID) + * to indicate if the station is in PS mode. + */ + __le32 link_ps_bitmap; + + /* Number of freed MBs per HLID */ + u8 tx_lnk_free_blks[AP_MAX_LINKS]; + u8 padding_1[1]; } __packed; struct wl1271_rx_mem_pool_addr { @@ -218,6 +265,19 @@ struct wl1271_if_operations { void (*disable_irq)(struct wl1271 *wl); }; +#define MAX_NUM_KEYS 14 +#define MAX_KEY_SIZE 32 + +struct wl1271_ap_key { + u8 id; + u8 key_type; + u8 key_size; + u8 key[MAX_KEY_SIZE]; + u8 hlid; + u32 tx_seq_32; + u16 tx_seq_16; +}; + struct wl1271 { struct platform_device *plat_dev; struct ieee80211_hw *hw; @@ -251,6 +311,7 @@ struct wl1271 { #define WL1271_FLAG_PSPOLL_FAILURE (12) #define WL1271_FLAG_STA_STATE_SENT (13) #define WL1271_FLAG_FW_TX_BUSY (14) +#define WL1271_FLAG_AP_STARTED (15) unsigned long flags; struct wl1271_partition_set part; @@ -262,6 +323,7 @@ struct wl1271 { u8 *fw; size_t fw_len; + u8 fw_bss_type; struct wl1271_nvs_file *nvs; size_t nvs_len; @@ -378,7 +440,6 @@ struct wl1271 { int last_rssi_event; struct wl1271_stats stats; - struct dentry *rootdir; __le32 buffer_32; u32 buffer_cmd; @@ -400,6 +461,23 @@ struct wl1271 { /* Most recently reported noise in dBm */ s8 noise; + + /* map for HLIDs of associated stations - when operating in AP mode */ + unsigned long ap_hlid_map[BITS_TO_LONGS(AP_MAX_STATIONS)]; + + /* recoreded keys for AP-mode - set here before AP startup */ + struct wl1271_ap_key *recorded_ap_keys[MAX_NUM_KEYS]; + + /* bands supported by this instance of wl12xx */ + struct ieee80211_supported_band bands[IEEE80211_NUM_BANDS]; + + /* RX BA constraint value */ + bool ba_support; + u8 ba_rx_bitmap; +}; + +struct wl1271_station { + u8 hlid; }; int wl1271_plt_start(struct wl1271 *wl); diff --git a/drivers/net/wireless/wl12xx/wl12xx_80211.h b/drivers/net/wireless/wl12xx/wl12xx_80211.h index be21032..67dcf8f 100644 --- a/drivers/net/wireless/wl12xx/wl12xx_80211.h +++ b/drivers/net/wireless/wl12xx/wl12xx_80211.h @@ -138,13 +138,13 @@ struct wl12xx_arp_rsp_template { struct ieee80211_hdr_3addr hdr; u8 llc_hdr[sizeof(rfc1042_header)]; - u16 llc_type; + __be16 llc_type; struct arphdr arp_hdr; u8 sender_hw[ETH_ALEN]; - u32 sender_ip; + __be32 sender_ip; u8 target_hw[ETH_ALEN]; - u32 target_ip; + __be32 target_ip; } __packed; @@ -160,4 +160,9 @@ struct wl12xx_probe_resp_template { struct wl12xx_ie_country country; } __packed; +struct wl12xx_disconn_template { + struct ieee80211_header header; + __le16 disconn_reason; +} __packed; + #endif diff --git a/drivers/net/wireless/zd1211rw/zd_chip.c b/drivers/net/wireless/zd1211rw/zd_chip.c index 6a9b660..54f68f1 100644 --- a/drivers/net/wireless/zd1211rw/zd_chip.c +++ b/drivers/net/wireless/zd1211rw/zd_chip.c @@ -108,25 +108,17 @@ int zd_ioread32v_locked(struct zd_chip *chip, u32 *values, const zd_addr_t *addr { int r; int i; - zd_addr_t *a16; - u16 *v16; + zd_addr_t a16[USB_MAX_IOREAD32_COUNT * 2]; + u16 v16[USB_MAX_IOREAD32_COUNT * 2]; unsigned int count16; if (count > USB_MAX_IOREAD32_COUNT) return -EINVAL; - /* Allocate a single memory block for values and addresses. */ - count16 = 2*count; - /* zd_addr_t is __nocast, so the kmalloc needs an explicit cast */ - a16 = (zd_addr_t *) kmalloc(count16 * (sizeof(zd_addr_t) + sizeof(u16)), - GFP_KERNEL); - if (!a16) { - dev_dbg_f(zd_chip_dev(chip), - "error ENOMEM in allocation of a16\n"); - r = -ENOMEM; - goto out; - } - v16 = (u16 *)(a16 + count16); + /* Use stack for values and addresses. */ + count16 = 2 * count; + BUG_ON(count16 * sizeof(zd_addr_t) > sizeof(a16)); + BUG_ON(count16 * sizeof(u16) > sizeof(v16)); for (i = 0; i < count; i++) { int j = 2*i; @@ -139,7 +131,7 @@ int zd_ioread32v_locked(struct zd_chip *chip, u32 *values, const zd_addr_t *addr if (r) { dev_dbg_f(zd_chip_dev(chip), "error: zd_ioread16v_locked. Error number %d\n", r); - goto out; + return r; } for (i = 0; i < count; i++) { @@ -147,18 +139,18 @@ int zd_ioread32v_locked(struct zd_chip *chip, u32 *values, const zd_addr_t *addr values[i] = (v16[j] << 16) | v16[j+1]; } -out: - kfree((void *)a16); - return r; + return 0; } int _zd_iowrite32v_locked(struct zd_chip *chip, const struct zd_ioreq32 *ioreqs, unsigned int count) { int i, j, r; - struct zd_ioreq16 *ioreqs16; + struct zd_ioreq16 ioreqs16[USB_MAX_IOWRITE32_COUNT * 2]; unsigned int count16; + /* Use stack for values and addresses. */ + ZD_ASSERT(mutex_is_locked(&chip->mutex)); if (count == 0) @@ -166,15 +158,8 @@ int _zd_iowrite32v_locked(struct zd_chip *chip, const struct zd_ioreq32 *ioreqs, if (count > USB_MAX_IOWRITE32_COUNT) return -EINVAL; - /* Allocate a single memory block for values and addresses. */ - count16 = 2*count; - ioreqs16 = kmalloc(count16 * sizeof(struct zd_ioreq16), GFP_KERNEL); - if (!ioreqs16) { - r = -ENOMEM; - dev_dbg_f(zd_chip_dev(chip), - "error %d in ioreqs16 allocation\n", r); - goto out; - } + count16 = 2 * count; + BUG_ON(count16 * sizeof(struct zd_ioreq16) > sizeof(ioreqs16)); for (i = 0; i < count; i++) { j = 2*i; @@ -192,8 +177,6 @@ int _zd_iowrite32v_locked(struct zd_chip *chip, const struct zd_ioreq32 *ioreqs, "error %d in zd_usb_write16v\n", r); } #endif /* DEBUG */ -out: - kfree(ioreqs16); return r; } @@ -370,16 +353,12 @@ error: return r; } -/* MAC address: if custom mac addresses are to be used CR_MAC_ADDR_P1 and - * CR_MAC_ADDR_P2 must be overwritten - */ -int zd_write_mac_addr(struct zd_chip *chip, const u8 *mac_addr) +static int zd_write_mac_addr_common(struct zd_chip *chip, const u8 *mac_addr, + const struct zd_ioreq32 *in_reqs, + const char *type) { int r; - struct zd_ioreq32 reqs[2] = { - [0] = { .addr = CR_MAC_ADDR_P1 }, - [1] = { .addr = CR_MAC_ADDR_P2 }, - }; + struct zd_ioreq32 reqs[2] = {in_reqs[0], in_reqs[1]}; if (mac_addr) { reqs[0].value = (mac_addr[3] << 24) @@ -388,9 +367,9 @@ int zd_write_mac_addr(struct zd_chip *chip, const u8 *mac_addr) | mac_addr[0]; reqs[1].value = (mac_addr[5] << 8) | mac_addr[4]; - dev_dbg_f(zd_chip_dev(chip), "mac addr %pM\n", mac_addr); + dev_dbg_f(zd_chip_dev(chip), "%s addr %pM\n", type, mac_addr); } else { - dev_dbg_f(zd_chip_dev(chip), "set NULL mac\n"); + dev_dbg_f(zd_chip_dev(chip), "set NULL %s\n", type); } mutex_lock(&chip->mutex); @@ -399,6 +378,29 @@ int zd_write_mac_addr(struct zd_chip *chip, const u8 *mac_addr) return r; } +/* MAC address: if custom mac addresses are to be used CR_MAC_ADDR_P1 and + * CR_MAC_ADDR_P2 must be overwritten + */ +int zd_write_mac_addr(struct zd_chip *chip, const u8 *mac_addr) +{ + static const struct zd_ioreq32 reqs[2] = { + [0] = { .addr = CR_MAC_ADDR_P1 }, + [1] = { .addr = CR_MAC_ADDR_P2 }, + }; + + return zd_write_mac_addr_common(chip, mac_addr, reqs, "mac"); +} + +int zd_write_bssid(struct zd_chip *chip, const u8 *bssid) +{ + static const struct zd_ioreq32 reqs[2] = { + [0] = { .addr = CR_BSSID_P1 }, + [1] = { .addr = CR_BSSID_P2 }, + }; + + return zd_write_mac_addr_common(chip, bssid, reqs, "bssid"); +} + int zd_read_regdomain(struct zd_chip *chip, u8 *regdomain) { int r; @@ -849,11 +851,12 @@ static int get_aw_pt_bi(struct zd_chip *chip, struct aw_pt_bi *s) static int set_aw_pt_bi(struct zd_chip *chip, struct aw_pt_bi *s) { struct zd_ioreq32 reqs[3]; + u16 b_interval = s->beacon_interval & 0xffff; - if (s->beacon_interval <= 5) - s->beacon_interval = 5; - if (s->pre_tbtt < 4 || s->pre_tbtt >= s->beacon_interval) - s->pre_tbtt = s->beacon_interval - 1; + if (b_interval <= 5) + b_interval = 5; + if (s->pre_tbtt < 4 || s->pre_tbtt >= b_interval) + s->pre_tbtt = b_interval - 1; if (s->atim_wnd_period >= s->pre_tbtt) s->atim_wnd_period = s->pre_tbtt - 1; @@ -862,31 +865,57 @@ static int set_aw_pt_bi(struct zd_chip *chip, struct aw_pt_bi *s) reqs[1].addr = CR_PRE_TBTT; reqs[1].value = s->pre_tbtt; reqs[2].addr = CR_BCN_INTERVAL; - reqs[2].value = s->beacon_interval; + reqs[2].value = (s->beacon_interval & ~0xffff) | b_interval; return zd_iowrite32a_locked(chip, reqs, ARRAY_SIZE(reqs)); } -static int set_beacon_interval(struct zd_chip *chip, u32 interval) +static int set_beacon_interval(struct zd_chip *chip, u16 interval, + u8 dtim_period, int type) { int r; struct aw_pt_bi s; + u32 b_interval, mode_flag; ZD_ASSERT(mutex_is_locked(&chip->mutex)); + + if (interval > 0) { + switch (type) { + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + mode_flag = BCN_MODE_IBSS; + break; + case NL80211_IFTYPE_AP: + mode_flag = BCN_MODE_AP; + break; + default: + mode_flag = 0; + break; + } + } else { + dtim_period = 0; + mode_flag = 0; + } + + b_interval = mode_flag | (dtim_period << 16) | interval; + + r = zd_iowrite32_locked(chip, b_interval, CR_BCN_INTERVAL); + if (r) + return r; r = get_aw_pt_bi(chip, &s); if (r) return r; - s.beacon_interval = interval; return set_aw_pt_bi(chip, &s); } -int zd_set_beacon_interval(struct zd_chip *chip, u32 interval) +int zd_set_beacon_interval(struct zd_chip *chip, u16 interval, u8 dtim_period, + int type) { int r; mutex_lock(&chip->mutex); - r = set_beacon_interval(chip, interval); + r = set_beacon_interval(chip, interval, dtim_period, type); mutex_unlock(&chip->mutex); return r; } @@ -905,7 +934,7 @@ static int hw_init(struct zd_chip *chip) if (r) return r; - return set_beacon_interval(chip, 100); + return set_beacon_interval(chip, 100, 0, NL80211_IFTYPE_UNSPECIFIED); } static zd_addr_t fw_reg_addr(struct zd_chip *chip, u16 offset) @@ -1407,6 +1436,9 @@ void zd_chip_disable_int(struct zd_chip *chip) mutex_lock(&chip->mutex); zd_usb_disable_int(&chip->usb); mutex_unlock(&chip->mutex); + + /* cancel pending interrupt work */ + cancel_work_sync(&zd_chip_to_mac(chip)->process_intr); } int zd_chip_enable_rxtx(struct zd_chip *chip) @@ -1416,6 +1448,7 @@ int zd_chip_enable_rxtx(struct zd_chip *chip) mutex_lock(&chip->mutex); zd_usb_enable_tx(&chip->usb); r = zd_usb_enable_rx(&chip->usb); + zd_tx_watchdog_enable(&chip->usb); mutex_unlock(&chip->mutex); return r; } @@ -1423,6 +1456,7 @@ int zd_chip_enable_rxtx(struct zd_chip *chip) void zd_chip_disable_rxtx(struct zd_chip *chip) { mutex_lock(&chip->mutex); + zd_tx_watchdog_disable(&chip->usb); zd_usb_disable_rx(&chip->usb); zd_usb_disable_tx(&chip->usb); mutex_unlock(&chip->mutex); diff --git a/drivers/net/wireless/zd1211rw/zd_chip.h b/drivers/net/wireless/zd1211rw/zd_chip.h index f8bbf7d..14e4402 100644 --- a/drivers/net/wireless/zd1211rw/zd_chip.h +++ b/drivers/net/wireless/zd1211rw/zd_chip.h @@ -546,6 +546,7 @@ enum { #define RX_FILTER_CTRL (RX_FILTER_RTS | RX_FILTER_CTS | \ RX_FILTER_CFEND | RX_FILTER_CFACK) +#define BCN_MODE_AP 0x1000000 #define BCN_MODE_IBSS 0x2000000 /* Monitor mode sets filter to 0xfffff */ @@ -881,6 +882,7 @@ static inline u8 _zd_chip_get_channel(struct zd_chip *chip) u8 zd_chip_get_channel(struct zd_chip *chip); int zd_read_regdomain(struct zd_chip *chip, u8 *regdomain); int zd_write_mac_addr(struct zd_chip *chip, const u8 *mac_addr); +int zd_write_bssid(struct zd_chip *chip, const u8 *bssid); int zd_chip_switch_radio_on(struct zd_chip *chip); int zd_chip_switch_radio_off(struct zd_chip *chip); int zd_chip_enable_int(struct zd_chip *chip); @@ -920,7 +922,8 @@ enum led_status { int zd_chip_control_leds(struct zd_chip *chip, enum led_status status); -int zd_set_beacon_interval(struct zd_chip *chip, u32 interval); +int zd_set_beacon_interval(struct zd_chip *chip, u16 interval, u8 dtim_period, + int type); static inline int zd_get_beacon_interval(struct zd_chip *chip, u32 *interval) { diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c index 6107304..74a269e 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zd1211rw/zd_mac.c @@ -138,6 +138,12 @@ static const struct ieee80211_channel zd_channels[] = { static void housekeeping_init(struct zd_mac *mac); static void housekeeping_enable(struct zd_mac *mac); static void housekeeping_disable(struct zd_mac *mac); +static void beacon_init(struct zd_mac *mac); +static void beacon_enable(struct zd_mac *mac); +static void beacon_disable(struct zd_mac *mac); +static void set_rts_cts(struct zd_mac *mac, unsigned int short_preamble); +static int zd_mac_config_beacon(struct ieee80211_hw *hw, + struct sk_buff *beacon); static int zd_reg2alpha2(u8 regdomain, char *alpha2) { @@ -231,6 +237,26 @@ static int set_rx_filter(struct zd_mac *mac) return zd_iowrite32(&mac->chip, CR_RX_FILTER, filter); } +static int set_mac_and_bssid(struct zd_mac *mac) +{ + int r; + + if (!mac->vif) + return -1; + + r = zd_write_mac_addr(&mac->chip, mac->vif->addr); + if (r) + return r; + + /* Vendor driver after setting MAC either sets BSSID for AP or + * filter for other modes. + */ + if (mac->type != NL80211_IFTYPE_AP) + return set_rx_filter(mac); + else + return zd_write_bssid(&mac->chip, mac->vif->addr); +} + static int set_mc_hash(struct zd_mac *mac) { struct zd_mc_hash hash; @@ -238,7 +264,7 @@ static int set_mc_hash(struct zd_mac *mac) return zd_chip_set_multicast_hash(&mac->chip, &hash); } -static int zd_op_start(struct ieee80211_hw *hw) +int zd_op_start(struct ieee80211_hw *hw) { struct zd_mac *mac = zd_hw_mac(hw); struct zd_chip *chip = &mac->chip; @@ -275,6 +301,8 @@ static int zd_op_start(struct ieee80211_hw *hw) goto disable_rxtx; housekeeping_enable(mac); + beacon_enable(mac); + set_bit(ZD_DEVICE_RUNNING, &mac->flags); return 0; disable_rxtx: zd_chip_disable_rxtx(chip); @@ -286,19 +314,22 @@ out: return r; } -static void zd_op_stop(struct ieee80211_hw *hw) +void zd_op_stop(struct ieee80211_hw *hw) { struct zd_mac *mac = zd_hw_mac(hw); struct zd_chip *chip = &mac->chip; struct sk_buff *skb; struct sk_buff_head *ack_wait_queue = &mac->ack_wait_queue; + clear_bit(ZD_DEVICE_RUNNING, &mac->flags); + /* The order here deliberately is a little different from the open() * method, since we need to make sure there is no opportunity for RX * frames to be processed by mac80211 after we have stopped it. */ zd_chip_disable_rxtx(chip); + beacon_disable(mac); housekeeping_disable(mac); flush_workqueue(zd_workqueue); @@ -311,6 +342,68 @@ static void zd_op_stop(struct ieee80211_hw *hw) dev_kfree_skb_any(skb); } +int zd_restore_settings(struct zd_mac *mac) +{ + struct sk_buff *beacon; + struct zd_mc_hash multicast_hash; + unsigned int short_preamble; + int r, beacon_interval, beacon_period; + u8 channel; + + dev_dbg_f(zd_mac_dev(mac), "\n"); + + spin_lock_irq(&mac->lock); + multicast_hash = mac->multicast_hash; + short_preamble = mac->short_preamble; + beacon_interval = mac->beacon.interval; + beacon_period = mac->beacon.period; + channel = mac->channel; + spin_unlock_irq(&mac->lock); + + r = set_mac_and_bssid(mac); + if (r < 0) { + dev_dbg_f(zd_mac_dev(mac), "set_mac_and_bssid failed, %d\n", r); + return r; + } + + r = zd_chip_set_channel(&mac->chip, channel); + if (r < 0) { + dev_dbg_f(zd_mac_dev(mac), "zd_chip_set_channel failed, %d\n", + r); + return r; + } + + set_rts_cts(mac, short_preamble); + + r = zd_chip_set_multicast_hash(&mac->chip, &multicast_hash); + if (r < 0) { + dev_dbg_f(zd_mac_dev(mac), + "zd_chip_set_multicast_hash failed, %d\n", r); + return r; + } + + if (mac->type == NL80211_IFTYPE_MESH_POINT || + mac->type == NL80211_IFTYPE_ADHOC || + mac->type == NL80211_IFTYPE_AP) { + if (mac->vif != NULL) { + beacon = ieee80211_beacon_get(mac->hw, mac->vif); + if (beacon) { + zd_mac_config_beacon(mac->hw, beacon); + kfree_skb(beacon); + } + } + + zd_set_beacon_interval(&mac->chip, beacon_interval, + beacon_period, mac->type); + + spin_lock_irq(&mac->lock); + mac->beacon.last_update = jiffies; + spin_unlock_irq(&mac->lock); + } + + return 0; +} + /** * zd_mac_tx_status - reports tx status of a packet if required * @hw - a &struct ieee80211_hw pointer @@ -574,64 +667,120 @@ static void cs_set_control(struct zd_mac *mac, struct zd_ctrlset *cs, static int zd_mac_config_beacon(struct ieee80211_hw *hw, struct sk_buff *beacon) { struct zd_mac *mac = zd_hw_mac(hw); - int r; + int r, ret, num_cmds, req_pos = 0; u32 tmp, j = 0; /* 4 more bytes for tail CRC */ u32 full_len = beacon->len + 4; + unsigned long end_jiffies, message_jiffies; + struct zd_ioreq32 *ioreqs; + + /* Alloc memory for full beacon write at once. */ + num_cmds = 1 + zd_chip_is_zd1211b(&mac->chip) + full_len; + ioreqs = kmalloc(num_cmds * sizeof(struct zd_ioreq32), GFP_KERNEL); + if (!ioreqs) + return -ENOMEM; - r = zd_iowrite32(&mac->chip, CR_BCN_FIFO_SEMAPHORE, 0); + mutex_lock(&mac->chip.mutex); + + r = zd_iowrite32_locked(&mac->chip, 0, CR_BCN_FIFO_SEMAPHORE); if (r < 0) - return r; - r = zd_ioread32(&mac->chip, CR_BCN_FIFO_SEMAPHORE, &tmp); + goto out; + r = zd_ioread32_locked(&mac->chip, &tmp, CR_BCN_FIFO_SEMAPHORE); if (r < 0) - return r; + goto release_sema; + end_jiffies = jiffies + HZ / 2; /*~500ms*/ + message_jiffies = jiffies + HZ / 10; /*~100ms*/ while (tmp & 0x2) { - r = zd_ioread32(&mac->chip, CR_BCN_FIFO_SEMAPHORE, &tmp); + r = zd_ioread32_locked(&mac->chip, &tmp, CR_BCN_FIFO_SEMAPHORE); if (r < 0) - return r; - if ((++j % 100) == 0) { - printk(KERN_ERR "CR_BCN_FIFO_SEMAPHORE not ready\n"); - if (j >= 500) { - printk(KERN_ERR "Giving up beacon config.\n"); - return -ETIMEDOUT; + goto release_sema; + if (time_is_before_eq_jiffies(message_jiffies)) { + message_jiffies = jiffies + HZ / 10; + dev_err(zd_mac_dev(mac), + "CR_BCN_FIFO_SEMAPHORE not ready\n"); + if (time_is_before_eq_jiffies(end_jiffies)) { + dev_err(zd_mac_dev(mac), + "Giving up beacon config.\n"); + r = -ETIMEDOUT; + goto reset_device; } } - msleep(1); + msleep(20); } - r = zd_iowrite32(&mac->chip, CR_BCN_FIFO, full_len - 1); - if (r < 0) - return r; + ioreqs[req_pos].addr = CR_BCN_FIFO; + ioreqs[req_pos].value = full_len - 1; + req_pos++; if (zd_chip_is_zd1211b(&mac->chip)) { - r = zd_iowrite32(&mac->chip, CR_BCN_LENGTH, full_len - 1); - if (r < 0) - return r; + ioreqs[req_pos].addr = CR_BCN_LENGTH; + ioreqs[req_pos].value = full_len - 1; + req_pos++; } for (j = 0 ; j < beacon->len; j++) { - r = zd_iowrite32(&mac->chip, CR_BCN_FIFO, - *((u8 *)(beacon->data + j))); - if (r < 0) - return r; + ioreqs[req_pos].addr = CR_BCN_FIFO; + ioreqs[req_pos].value = *((u8 *)(beacon->data + j)); + req_pos++; } for (j = 0; j < 4; j++) { - r = zd_iowrite32(&mac->chip, CR_BCN_FIFO, 0x0); - if (r < 0) - return r; + ioreqs[req_pos].addr = CR_BCN_FIFO; + ioreqs[req_pos].value = 0x0; + req_pos++; } - r = zd_iowrite32(&mac->chip, CR_BCN_FIFO_SEMAPHORE, 1); - if (r < 0) - return r; + BUG_ON(req_pos != num_cmds); + + r = zd_iowrite32a_locked(&mac->chip, ioreqs, num_cmds); + +release_sema: + /* + * Try very hard to release device beacon semaphore, as otherwise + * device/driver can be left in unusable state. + */ + end_jiffies = jiffies + HZ / 2; /*~500ms*/ + ret = zd_iowrite32_locked(&mac->chip, 1, CR_BCN_FIFO_SEMAPHORE); + while (ret < 0) { + if (time_is_before_eq_jiffies(end_jiffies)) { + ret = -ETIMEDOUT; + break; + } + + msleep(20); + ret = zd_iowrite32_locked(&mac->chip, 1, CR_BCN_FIFO_SEMAPHORE); + } + + if (ret < 0) + dev_err(zd_mac_dev(mac), "Could not release " + "CR_BCN_FIFO_SEMAPHORE!\n"); + if (r < 0 || ret < 0) { + if (r >= 0) + r = ret; + goto out; + } /* 802.11b/g 2.4G CCK 1Mb * 802.11a, not yet implemented, uses different values (see GPL vendor * driver) */ - return zd_iowrite32(&mac->chip, CR_BCN_PLCP_CFG, 0x00000400 | - (full_len << 19)); + r = zd_iowrite32_locked(&mac->chip, 0x00000400 | (full_len << 19), + CR_BCN_PLCP_CFG); +out: + mutex_unlock(&mac->chip.mutex); + kfree(ioreqs); + return r; + +reset_device: + mutex_unlock(&mac->chip.mutex); + kfree(ioreqs); + + /* semaphore stuck, reset device to avoid fw freeze later */ + dev_warn(zd_mac_dev(mac), "CR_BCN_FIFO_SEMAPHORE stuck, " + "reseting device..."); + usb_queue_reset_device(mac->chip.usb.intf); + + return r; } static int fill_ctrlset(struct zd_mac *mac, @@ -779,6 +928,13 @@ static int filter_ack(struct ieee80211_hw *hw, struct ieee80211_hdr *rx_hdr, mac->ack_pending = 1; mac->ack_signal = stats->signal; + + /* Prevent pending tx-packet on AP-mode */ + if (mac->type == NL80211_IFTYPE_AP) { + skb = __skb_dequeue(q); + zd_mac_tx_status(hw, skb, mac->ack_signal, NULL); + mac->ack_pending = 0; + } } spin_unlock_irqrestore(&q->lock, flags); @@ -882,13 +1038,16 @@ static int zd_op_add_interface(struct ieee80211_hw *hw, case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: mac->type = vif->type; break; default: return -EOPNOTSUPP; } - return zd_write_mac_addr(&mac->chip, vif->addr); + mac->vif = vif; + + return set_mac_and_bssid(mac); } static void zd_op_remove_interface(struct ieee80211_hw *hw, @@ -896,7 +1055,8 @@ static void zd_op_remove_interface(struct ieee80211_hw *hw, { struct zd_mac *mac = zd_hw_mac(hw); mac->type = NL80211_IFTYPE_UNSPECIFIED; - zd_set_beacon_interval(&mac->chip, 0); + mac->vif = NULL; + zd_set_beacon_interval(&mac->chip, 0, 0, NL80211_IFTYPE_UNSPECIFIED); zd_write_mac_addr(&mac->chip, NULL); } @@ -905,49 +1065,67 @@ static int zd_op_config(struct ieee80211_hw *hw, u32 changed) struct zd_mac *mac = zd_hw_mac(hw); struct ieee80211_conf *conf = &hw->conf; + spin_lock_irq(&mac->lock); + mac->channel = conf->channel->hw_value; + spin_unlock_irq(&mac->lock); + return zd_chip_set_channel(&mac->chip, conf->channel->hw_value); } -static void zd_process_intr(struct work_struct *work) +static void zd_beacon_done(struct zd_mac *mac) { - u16 int_status; - struct zd_mac *mac = container_of(work, struct zd_mac, process_intr); + struct sk_buff *skb, *beacon; - int_status = le16_to_cpu(*(__le16 *)(mac->intr_buffer+4)); - if (int_status & INT_CFG_NEXT_BCN) - dev_dbg_f_limit(zd_mac_dev(mac), "INT_CFG_NEXT_BCN\n"); - else - dev_dbg_f(zd_mac_dev(mac), "Unsupported interrupt\n"); - - zd_chip_enable_hwint(&mac->chip); -} + if (!test_bit(ZD_DEVICE_RUNNING, &mac->flags)) + return; + if (!mac->vif || mac->vif->type != NL80211_IFTYPE_AP) + return; + /* + * Send out buffered broad- and multicast frames. + */ + while (!ieee80211_queue_stopped(mac->hw, 0)) { + skb = ieee80211_get_buffered_bc(mac->hw, mac->vif); + if (!skb) + break; + zd_op_tx(mac->hw, skb); + } -static void set_multicast_hash_handler(struct work_struct *work) -{ - struct zd_mac *mac = - container_of(work, struct zd_mac, set_multicast_hash_work); - struct zd_mc_hash hash; + /* + * Fetch next beacon so that tim_count is updated. + */ + beacon = ieee80211_beacon_get(mac->hw, mac->vif); + if (beacon) { + zd_mac_config_beacon(mac->hw, beacon); + kfree_skb(beacon); + } spin_lock_irq(&mac->lock); - hash = mac->multicast_hash; + mac->beacon.last_update = jiffies; spin_unlock_irq(&mac->lock); - - zd_chip_set_multicast_hash(&mac->chip, &hash); } -static void set_rx_filter_handler(struct work_struct *work) +static void zd_process_intr(struct work_struct *work) { - struct zd_mac *mac = - container_of(work, struct zd_mac, set_rx_filter_work); - int r; + u16 int_status; + unsigned long flags; + struct zd_mac *mac = container_of(work, struct zd_mac, process_intr); - dev_dbg_f(zd_mac_dev(mac), "\n"); - r = set_rx_filter(mac); - if (r) - dev_err(zd_mac_dev(mac), "set_rx_filter_handler error %d\n", r); + spin_lock_irqsave(&mac->lock, flags); + int_status = le16_to_cpu(*(__le16 *)(mac->intr_buffer + 4)); + spin_unlock_irqrestore(&mac->lock, flags); + + if (int_status & INT_CFG_NEXT_BCN) { + /*dev_dbg_f_limit(zd_mac_dev(mac), "INT_CFG_NEXT_BCN\n");*/ + zd_beacon_done(mac); + } else { + dev_dbg_f(zd_mac_dev(mac), "Unsupported interrupt\n"); + } + + zd_chip_enable_hwint(&mac->chip); } + static u64 zd_op_prepare_multicast(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list) { @@ -979,6 +1157,7 @@ static void zd_op_configure_filter(struct ieee80211_hw *hw, }; struct zd_mac *mac = zd_hw_mac(hw); unsigned long flags; + int r; /* Only deal with supported flags */ changed_flags &= SUPPORTED_FIF_FLAGS; @@ -1000,11 +1179,13 @@ static void zd_op_configure_filter(struct ieee80211_hw *hw, mac->multicast_hash = hash; spin_unlock_irqrestore(&mac->lock, flags); - /* XXX: these can be called here now, can sleep now! */ - queue_work(zd_workqueue, &mac->set_multicast_hash_work); + zd_chip_set_multicast_hash(&mac->chip, &hash); - if (changed_flags & FIF_CONTROL) - queue_work(zd_workqueue, &mac->set_rx_filter_work); + if (changed_flags & FIF_CONTROL) { + r = set_rx_filter(mac); + if (r) + dev_err(zd_mac_dev(mac), "set_rx_filter error %d\n", r); + } /* no handling required for FIF_OTHER_BSS as we don't currently * do BSSID filtering */ @@ -1016,20 +1197,9 @@ static void zd_op_configure_filter(struct ieee80211_hw *hw, * time. */ } -static void set_rts_cts_work(struct work_struct *work) +static void set_rts_cts(struct zd_mac *mac, unsigned int short_preamble) { - struct zd_mac *mac = - container_of(work, struct zd_mac, set_rts_cts_work); - unsigned long flags; - unsigned int short_preamble; - mutex_lock(&mac->chip.mutex); - - spin_lock_irqsave(&mac->lock, flags); - mac->updating_rts_rate = 0; - short_preamble = mac->short_preamble; - spin_unlock_irqrestore(&mac->lock, flags); - zd_chip_set_rts_cts_rate_locked(&mac->chip, short_preamble); mutex_unlock(&mac->chip.mutex); } @@ -1040,33 +1210,42 @@ static void zd_op_bss_info_changed(struct ieee80211_hw *hw, u32 changes) { struct zd_mac *mac = zd_hw_mac(hw); - unsigned long flags; int associated; dev_dbg_f(zd_mac_dev(mac), "changes: %x\n", changes); if (mac->type == NL80211_IFTYPE_MESH_POINT || - mac->type == NL80211_IFTYPE_ADHOC) { + mac->type == NL80211_IFTYPE_ADHOC || + mac->type == NL80211_IFTYPE_AP) { associated = true; if (changes & BSS_CHANGED_BEACON) { struct sk_buff *beacon = ieee80211_beacon_get(hw, vif); if (beacon) { + zd_chip_disable_hwint(&mac->chip); zd_mac_config_beacon(hw, beacon); + zd_chip_enable_hwint(&mac->chip); kfree_skb(beacon); } } if (changes & BSS_CHANGED_BEACON_ENABLED) { - u32 interval; + u16 interval = 0; + u8 period = 0; - if (bss_conf->enable_beacon) - interval = BCN_MODE_IBSS | - bss_conf->beacon_int; - else - interval = 0; + if (bss_conf->enable_beacon) { + period = bss_conf->dtim_period; + interval = bss_conf->beacon_int; + } - zd_set_beacon_interval(&mac->chip, interval); + spin_lock_irq(&mac->lock); + mac->beacon.period = period; + mac->beacon.interval = interval; + mac->beacon.last_update = jiffies; + spin_unlock_irq(&mac->lock); + + zd_set_beacon_interval(&mac->chip, interval, period, + mac->type); } } else associated = is_valid_ether_addr(bss_conf->bssid); @@ -1078,15 +1257,11 @@ static void zd_op_bss_info_changed(struct ieee80211_hw *hw, /* TODO: do hardware bssid filtering */ if (changes & BSS_CHANGED_ERP_PREAMBLE) { - spin_lock_irqsave(&mac->lock, flags); + spin_lock_irq(&mac->lock); mac->short_preamble = bss_conf->use_short_preamble; - if (!mac->updating_rts_rate) { - mac->updating_rts_rate = 1; - /* FIXME: should disable TX here, until work has - * completed and RTS_CTS reg is updated */ - queue_work(zd_workqueue, &mac->set_rts_cts_work); - } - spin_unlock_irqrestore(&mac->lock, flags); + spin_unlock_irq(&mac->lock); + + set_rts_cts(mac, bss_conf->use_short_preamble); } } @@ -1138,12 +1313,14 @@ struct ieee80211_hw *zd_mac_alloc_hw(struct usb_interface *intf) hw->wiphy->bands[IEEE80211_BAND_2GHZ] = &mac->band; hw->flags = IEEE80211_HW_RX_INCLUDES_FCS | - IEEE80211_HW_SIGNAL_UNSPEC; + IEEE80211_HW_SIGNAL_UNSPEC | + IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING; hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_MESH_POINT) | BIT(NL80211_IFTYPE_STATION) | - BIT(NL80211_IFTYPE_ADHOC); + BIT(NL80211_IFTYPE_ADHOC) | + BIT(NL80211_IFTYPE_AP); hw->max_signal = 100; hw->queues = 1; @@ -1160,15 +1337,82 @@ struct ieee80211_hw *zd_mac_alloc_hw(struct usb_interface *intf) zd_chip_init(&mac->chip, hw, intf); housekeeping_init(mac); - INIT_WORK(&mac->set_multicast_hash_work, set_multicast_hash_handler); - INIT_WORK(&mac->set_rts_cts_work, set_rts_cts_work); - INIT_WORK(&mac->set_rx_filter_work, set_rx_filter_handler); + beacon_init(mac); INIT_WORK(&mac->process_intr, zd_process_intr); SET_IEEE80211_DEV(hw, &intf->dev); return hw; } +#define BEACON_WATCHDOG_DELAY round_jiffies_relative(HZ) + +static void beacon_watchdog_handler(struct work_struct *work) +{ + struct zd_mac *mac = + container_of(work, struct zd_mac, beacon.watchdog_work.work); + struct sk_buff *beacon; + unsigned long timeout; + int interval, period; + + if (!test_bit(ZD_DEVICE_RUNNING, &mac->flags)) + goto rearm; + if (mac->type != NL80211_IFTYPE_AP || !mac->vif) + goto rearm; + + spin_lock_irq(&mac->lock); + interval = mac->beacon.interval; + period = mac->beacon.period; + timeout = mac->beacon.last_update + msecs_to_jiffies(interval) + HZ; + spin_unlock_irq(&mac->lock); + + if (interval > 0 && time_is_before_jiffies(timeout)) { + dev_dbg_f(zd_mac_dev(mac), "beacon interrupt stalled, " + "restarting. " + "(interval: %d, dtim: %d)\n", + interval, period); + + zd_chip_disable_hwint(&mac->chip); + + beacon = ieee80211_beacon_get(mac->hw, mac->vif); + if (beacon) { + zd_mac_config_beacon(mac->hw, beacon); + kfree_skb(beacon); + } + + zd_set_beacon_interval(&mac->chip, interval, period, mac->type); + + zd_chip_enable_hwint(&mac->chip); + + spin_lock_irq(&mac->lock); + mac->beacon.last_update = jiffies; + spin_unlock_irq(&mac->lock); + } + +rearm: + queue_delayed_work(zd_workqueue, &mac->beacon.watchdog_work, + BEACON_WATCHDOG_DELAY); +} + +static void beacon_init(struct zd_mac *mac) +{ + INIT_DELAYED_WORK(&mac->beacon.watchdog_work, beacon_watchdog_handler); +} + +static void beacon_enable(struct zd_mac *mac) +{ + dev_dbg_f(zd_mac_dev(mac), "\n"); + + mac->beacon.last_update = jiffies; + queue_delayed_work(zd_workqueue, &mac->beacon.watchdog_work, + BEACON_WATCHDOG_DELAY); +} + +static void beacon_disable(struct zd_mac *mac) +{ + dev_dbg_f(zd_mac_dev(mac), "\n"); + cancel_delayed_work_sync(&mac->beacon.watchdog_work); +} + #define LINK_LED_WORK_DELAY HZ static void link_led_handler(struct work_struct *work) @@ -1179,6 +1423,9 @@ static void link_led_handler(struct work_struct *work) int is_associated; int r; + if (!test_bit(ZD_DEVICE_RUNNING, &mac->flags)) + goto requeue; + spin_lock_irq(&mac->lock); is_associated = mac->associated; spin_unlock_irq(&mac->lock); @@ -1188,6 +1435,7 @@ static void link_led_handler(struct work_struct *work) if (r) dev_dbg_f(zd_mac_dev(mac), "zd_chip_control_leds error %d\n", r); +requeue: queue_delayed_work(zd_workqueue, &mac->housekeeping.link_led_work, LINK_LED_WORK_DELAY); } diff --git a/drivers/net/wireless/zd1211rw/zd_mac.h b/drivers/net/wireless/zd1211rw/zd_mac.h index a6d86b9..f8c93c3 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.h +++ b/drivers/net/wireless/zd1211rw/zd_mac.h @@ -163,6 +163,17 @@ struct housekeeping { struct delayed_work link_led_work; }; +struct beacon { + struct delayed_work watchdog_work; + unsigned long last_update; + u16 interval; + u8 period; +}; + +enum zd_device_flags { + ZD_DEVICE_RUNNING, +}; + #define ZD_MAC_STATS_BUFFER_SIZE 16 #define ZD_MAC_MAX_ACK_WAITERS 50 @@ -172,17 +183,19 @@ struct zd_mac { spinlock_t lock; spinlock_t intr_lock; struct ieee80211_hw *hw; + struct ieee80211_vif *vif; struct housekeeping housekeeping; - struct work_struct set_multicast_hash_work; + struct beacon beacon; struct work_struct set_rts_cts_work; - struct work_struct set_rx_filter_work; struct work_struct process_intr; struct zd_mc_hash multicast_hash; u8 intr_buffer[USB_MAX_EP_INT_BUFFER]; u8 regdomain; u8 default_regdomain; + u8 channel; int type; int associated; + unsigned long flags; struct sk_buff_head ack_wait_queue; struct ieee80211_channel channels[14]; struct ieee80211_rate rates[12]; @@ -191,9 +204,6 @@ struct zd_mac { /* Short preamble (used for RTS/CTS) */ unsigned int short_preamble:1; - /* flags to indicate update in progress */ - unsigned int updating_rts_rate:1; - /* whether to pass frames with CRC errors to stack */ unsigned int pass_failed_fcs:1; @@ -304,6 +314,10 @@ int zd_mac_rx(struct ieee80211_hw *hw, const u8 *buffer, unsigned int length); void zd_mac_tx_failed(struct urb *urb); void zd_mac_tx_to_dev(struct sk_buff *skb, int error); +int zd_op_start(struct ieee80211_hw *hw); +void zd_op_stop(struct ieee80211_hw *hw); +int zd_restore_settings(struct zd_mac *mac); + #ifdef DEBUG void zd_dump_rx_status(const struct rx_status *status); #else diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c index 06041cb..f6df366 100644 --- a/drivers/net/wireless/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zd1211rw/zd_usb.c @@ -377,8 +377,10 @@ static inline void handle_regs_int(struct urb *urb) int_num = le16_to_cpu(*(__le16 *)(urb->transfer_buffer+2)); if (int_num == CR_INTERRUPT) { struct zd_mac *mac = zd_hw_mac(zd_usb_to_hw(urb->context)); + spin_lock(&mac->lock); memcpy(&mac->intr_buffer, urb->transfer_buffer, USB_MAX_EP_INT_BUFFER); + spin_unlock(&mac->lock); schedule_work(&mac->process_intr); } else if (intr->read_regs_enabled) { intr->read_regs.length = len = urb->actual_length; @@ -409,8 +411,10 @@ static void int_urb_complete(struct urb *urb) case -ENOENT: case -ECONNRESET: case -EPIPE: - goto kfree; + dev_dbg_f(urb_dev(urb), "urb %p error %d\n", urb, urb->status); + return; default: + dev_dbg_f(urb_dev(urb), "urb %p error %d\n", urb, urb->status); goto resubmit; } @@ -441,12 +445,11 @@ static void int_urb_complete(struct urb *urb) resubmit: r = usb_submit_urb(urb, GFP_ATOMIC); if (r) { - dev_dbg_f(urb_dev(urb), "resubmit urb %p\n", urb); - goto kfree; + dev_dbg_f(urb_dev(urb), "error: resubmit urb %p err code %d\n", + urb, r); + /* TODO: add worker to reset intr->urb */ } return; -kfree: - kfree(urb->transfer_buffer); } static inline int int_urb_interval(struct usb_device *udev) @@ -477,9 +480,8 @@ static inline int usb_int_enabled(struct zd_usb *usb) int zd_usb_enable_int(struct zd_usb *usb) { int r; - struct usb_device *udev; + struct usb_device *udev = zd_usb_to_usbdev(usb); struct zd_usb_interrupt *intr = &usb->intr; - void *transfer_buffer = NULL; struct urb *urb; dev_dbg_f(zd_usb_dev(usb), "\n"); @@ -500,20 +502,21 @@ int zd_usb_enable_int(struct zd_usb *usb) intr->urb = urb; spin_unlock_irq(&intr->lock); - /* TODO: make it a DMA buffer */ r = -ENOMEM; - transfer_buffer = kmalloc(USB_MAX_EP_INT_BUFFER, GFP_KERNEL); - if (!transfer_buffer) { + intr->buffer = usb_alloc_coherent(udev, USB_MAX_EP_INT_BUFFER, + GFP_KERNEL, &intr->buffer_dma); + if (!intr->buffer) { dev_dbg_f(zd_usb_dev(usb), "couldn't allocate transfer_buffer\n"); goto error_set_urb_null; } - udev = zd_usb_to_usbdev(usb); usb_fill_int_urb(urb, udev, usb_rcvintpipe(udev, EP_INT_IN), - transfer_buffer, USB_MAX_EP_INT_BUFFER, + intr->buffer, USB_MAX_EP_INT_BUFFER, int_urb_complete, usb, intr->interval); + urb->transfer_dma = intr->buffer_dma; + urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; dev_dbg_f(zd_usb_dev(usb), "submit urb %p\n", intr->urb); r = usb_submit_urb(urb, GFP_KERNEL); @@ -525,7 +528,8 @@ int zd_usb_enable_int(struct zd_usb *usb) return 0; error: - kfree(transfer_buffer); + usb_free_coherent(udev, USB_MAX_EP_INT_BUFFER, + intr->buffer, intr->buffer_dma); error_set_urb_null: spin_lock_irq(&intr->lock); intr->urb = NULL; @@ -539,8 +543,11 @@ out: void zd_usb_disable_int(struct zd_usb *usb) { unsigned long flags; + struct usb_device *udev = zd_usb_to_usbdev(usb); struct zd_usb_interrupt *intr = &usb->intr; struct urb *urb; + void *buffer; + dma_addr_t buffer_dma; spin_lock_irqsave(&intr->lock, flags); urb = intr->urb; @@ -549,11 +556,18 @@ void zd_usb_disable_int(struct zd_usb *usb) return; } intr->urb = NULL; + buffer = intr->buffer; + buffer_dma = intr->buffer_dma; + intr->buffer = NULL; spin_unlock_irqrestore(&intr->lock, flags); usb_kill_urb(urb); dev_dbg_f(zd_usb_dev(usb), "urb %p killed\n", urb); usb_free_urb(urb); + + if (buffer) + usb_free_coherent(udev, USB_MAX_EP_INT_BUFFER, + buffer, buffer_dma); } static void handle_rx_packet(struct zd_usb *usb, const u8 *buffer, @@ -601,6 +615,7 @@ static void handle_rx_packet(struct zd_usb *usb, const u8 *buffer, static void rx_urb_complete(struct urb *urb) { + int r; struct zd_usb *usb; struct zd_usb_rx *rx; const u8 *buffer; @@ -615,6 +630,7 @@ static void rx_urb_complete(struct urb *urb) case -ENOENT: case -ECONNRESET: case -EPIPE: + dev_dbg_f(urb_dev(urb), "urb %p error %d\n", urb, urb->status); return; default: dev_dbg_f(urb_dev(urb), "urb %p error %d\n", urb, urb->status); @@ -626,6 +642,8 @@ static void rx_urb_complete(struct urb *urb) usb = urb->context; rx = &usb->rx; + zd_usb_reset_rx_idle_timer(usb); + if (length%rx->usb_packet_size > rx->usb_packet_size-4) { /* If there is an old first fragment, we don't care. */ dev_dbg_f(urb_dev(urb), "*** first fragment ***\n"); @@ -654,7 +672,9 @@ static void rx_urb_complete(struct urb *urb) } resubmit: - usb_submit_urb(urb, GFP_ATOMIC); + r = usb_submit_urb(urb, GFP_ATOMIC); + if (r) + dev_dbg_f(urb_dev(urb), "urb %p resubmit error %d\n", urb, r); } static struct urb *alloc_rx_urb(struct zd_usb *usb) @@ -690,7 +710,7 @@ static void free_rx_urb(struct urb *urb) usb_free_urb(urb); } -int zd_usb_enable_rx(struct zd_usb *usb) +static int __zd_usb_enable_rx(struct zd_usb *usb) { int i, r; struct zd_usb_rx *rx = &usb->rx; @@ -742,7 +762,21 @@ error: return r; } -void zd_usb_disable_rx(struct zd_usb *usb) +int zd_usb_enable_rx(struct zd_usb *usb) +{ + int r; + struct zd_usb_rx *rx = &usb->rx; + + mutex_lock(&rx->setup_mutex); + r = __zd_usb_enable_rx(usb); + mutex_unlock(&rx->setup_mutex); + + zd_usb_reset_rx_idle_timer(usb); + + return r; +} + +static void __zd_usb_disable_rx(struct zd_usb *usb) { int i; unsigned long flags; @@ -769,6 +803,40 @@ void zd_usb_disable_rx(struct zd_usb *usb) spin_unlock_irqrestore(&rx->lock, flags); } +void zd_usb_disable_rx(struct zd_usb *usb) +{ + struct zd_usb_rx *rx = &usb->rx; + + mutex_lock(&rx->setup_mutex); + __zd_usb_disable_rx(usb); + mutex_unlock(&rx->setup_mutex); + + cancel_delayed_work_sync(&rx->idle_work); +} + +static void zd_usb_reset_rx(struct zd_usb *usb) +{ + bool do_reset; + struct zd_usb_rx *rx = &usb->rx; + unsigned long flags; + + mutex_lock(&rx->setup_mutex); + + spin_lock_irqsave(&rx->lock, flags); + do_reset = rx->urbs != NULL; + spin_unlock_irqrestore(&rx->lock, flags); + + if (do_reset) { + __zd_usb_disable_rx(usb); + __zd_usb_enable_rx(usb); + } + + mutex_unlock(&rx->setup_mutex); + + if (do_reset) + zd_usb_reset_rx_idle_timer(usb); +} + /** * zd_usb_disable_tx - disable transmission * @usb: the zd1211rw-private USB structure @@ -779,19 +847,21 @@ void zd_usb_disable_tx(struct zd_usb *usb) { struct zd_usb_tx *tx = &usb->tx; unsigned long flags; - struct list_head *pos, *n; + + atomic_set(&tx->enabled, 0); + + /* kill all submitted tx-urbs */ + usb_kill_anchored_urbs(&tx->submitted); spin_lock_irqsave(&tx->lock, flags); - list_for_each_safe(pos, n, &tx->free_urb_list) { - list_del(pos); - usb_free_urb(list_entry(pos, struct urb, urb_list)); - } - tx->enabled = 0; + WARN_ON(!skb_queue_empty(&tx->submitted_skbs)); + WARN_ON(tx->submitted_urbs != 0); tx->submitted_urbs = 0; + spin_unlock_irqrestore(&tx->lock, flags); + /* The stopped state is ignored, relying on ieee80211_wake_queues() * in a potentionally following zd_usb_enable_tx(). */ - spin_unlock_irqrestore(&tx->lock, flags); } /** @@ -807,63 +877,13 @@ void zd_usb_enable_tx(struct zd_usb *usb) struct zd_usb_tx *tx = &usb->tx; spin_lock_irqsave(&tx->lock, flags); - tx->enabled = 1; + atomic_set(&tx->enabled, 1); tx->submitted_urbs = 0; ieee80211_wake_queues(zd_usb_to_hw(usb)); tx->stopped = 0; spin_unlock_irqrestore(&tx->lock, flags); } -/** - * alloc_tx_urb - provides an tx URB - * @usb: a &struct zd_usb pointer - * - * Allocates a new URB. If possible takes the urb from the free list in - * usb->tx. - */ -static struct urb *alloc_tx_urb(struct zd_usb *usb) -{ - struct zd_usb_tx *tx = &usb->tx; - unsigned long flags; - struct list_head *entry; - struct urb *urb; - - spin_lock_irqsave(&tx->lock, flags); - if (list_empty(&tx->free_urb_list)) { - urb = usb_alloc_urb(0, GFP_ATOMIC); - goto out; - } - entry = tx->free_urb_list.next; - list_del(entry); - urb = list_entry(entry, struct urb, urb_list); -out: - spin_unlock_irqrestore(&tx->lock, flags); - return urb; -} - -/** - * free_tx_urb - frees a used tx URB - * @usb: a &struct zd_usb pointer - * @urb: URB to be freed - * - * Frees the transmission URB, which means to put it on the free URB - * list. - */ -static void free_tx_urb(struct zd_usb *usb, struct urb *urb) -{ - struct zd_usb_tx *tx = &usb->tx; - unsigned long flags; - - spin_lock_irqsave(&tx->lock, flags); - if (!tx->enabled) { - usb_free_urb(urb); - goto out; - } - list_add(&urb->urb_list, &tx->free_urb_list); -out: - spin_unlock_irqrestore(&tx->lock, flags); -} - static void tx_dec_submitted_urbs(struct zd_usb *usb) { struct zd_usb_tx *tx = &usb->tx; @@ -905,6 +925,16 @@ static void tx_urb_complete(struct urb *urb) struct sk_buff *skb; struct ieee80211_tx_info *info; struct zd_usb *usb; + struct zd_usb_tx *tx; + + skb = (struct sk_buff *)urb->context; + info = IEEE80211_SKB_CB(skb); + /* + * grab 'usb' pointer before handing off the skb (since + * it might be freed by zd_mac_tx_to_dev or mac80211) + */ + usb = &zd_hw_mac(info->rate_driver_data[0])->chip.usb; + tx = &usb->tx; switch (urb->status) { case 0: @@ -922,20 +952,16 @@ static void tx_urb_complete(struct urb *urb) goto resubmit; } free_urb: - skb = (struct sk_buff *)urb->context; - /* - * grab 'usb' pointer before handing off the skb (since - * it might be freed by zd_mac_tx_to_dev or mac80211) - */ - info = IEEE80211_SKB_CB(skb); - usb = &zd_hw_mac(info->rate_driver_data[0])->chip.usb; + skb_unlink(skb, &usb->tx.submitted_skbs); zd_mac_tx_to_dev(skb, urb->status); - free_tx_urb(usb, urb); + usb_free_urb(urb); tx_dec_submitted_urbs(usb); return; resubmit: + usb_anchor_urb(urb, &tx->submitted); r = usb_submit_urb(urb, GFP_ATOMIC); if (r) { + usb_unanchor_urb(urb); dev_dbg_f(urb_dev(urb), "error resubmit urb %p %d\n", urb, r); goto free_urb; } @@ -956,10 +982,17 @@ resubmit: int zd_usb_tx(struct zd_usb *usb, struct sk_buff *skb) { int r; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct usb_device *udev = zd_usb_to_usbdev(usb); struct urb *urb; + struct zd_usb_tx *tx = &usb->tx; - urb = alloc_tx_urb(usb); + if (!atomic_read(&tx->enabled)) { + r = -ENOENT; + goto out; + } + + urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) { r = -ENOMEM; goto out; @@ -968,17 +1001,118 @@ int zd_usb_tx(struct zd_usb *usb, struct sk_buff *skb) usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_DATA_OUT), skb->data, skb->len, tx_urb_complete, skb); + info->rate_driver_data[1] = (void *)jiffies; + skb_queue_tail(&tx->submitted_skbs, skb); + usb_anchor_urb(urb, &tx->submitted); + r = usb_submit_urb(urb, GFP_ATOMIC); - if (r) + if (r) { + dev_dbg_f(zd_usb_dev(usb), "error submit urb %p %d\n", urb, r); + usb_unanchor_urb(urb); + skb_unlink(skb, &tx->submitted_skbs); goto error; + } tx_inc_submitted_urbs(usb); return 0; error: - free_tx_urb(usb, urb); + usb_free_urb(urb); out: return r; } +static bool zd_tx_timeout(struct zd_usb *usb) +{ + struct zd_usb_tx *tx = &usb->tx; + struct sk_buff_head *q = &tx->submitted_skbs; + struct sk_buff *skb, *skbnext; + struct ieee80211_tx_info *info; + unsigned long flags, trans_start; + bool have_timedout = false; + + spin_lock_irqsave(&q->lock, flags); + skb_queue_walk_safe(q, skb, skbnext) { + info = IEEE80211_SKB_CB(skb); + trans_start = (unsigned long)info->rate_driver_data[1]; + + if (time_is_before_jiffies(trans_start + ZD_TX_TIMEOUT)) { + have_timedout = true; + break; + } + } + spin_unlock_irqrestore(&q->lock, flags); + + return have_timedout; +} + +static void zd_tx_watchdog_handler(struct work_struct *work) +{ + struct zd_usb *usb = + container_of(work, struct zd_usb, tx.watchdog_work.work); + struct zd_usb_tx *tx = &usb->tx; + + if (!atomic_read(&tx->enabled) || !tx->watchdog_enabled) + goto out; + if (!zd_tx_timeout(usb)) + goto out; + + /* TX halted, try reset */ + dev_warn(zd_usb_dev(usb), "TX-stall detected, reseting device..."); + + usb_queue_reset_device(usb->intf); + + /* reset will stop this worker, don't rearm */ + return; +out: + queue_delayed_work(zd_workqueue, &tx->watchdog_work, + ZD_TX_WATCHDOG_INTERVAL); +} + +void zd_tx_watchdog_enable(struct zd_usb *usb) +{ + struct zd_usb_tx *tx = &usb->tx; + + if (!tx->watchdog_enabled) { + dev_dbg_f(zd_usb_dev(usb), "\n"); + queue_delayed_work(zd_workqueue, &tx->watchdog_work, + ZD_TX_WATCHDOG_INTERVAL); + tx->watchdog_enabled = 1; + } +} + +void zd_tx_watchdog_disable(struct zd_usb *usb) +{ + struct zd_usb_tx *tx = &usb->tx; + + if (tx->watchdog_enabled) { + dev_dbg_f(zd_usb_dev(usb), "\n"); + tx->watchdog_enabled = 0; + cancel_delayed_work_sync(&tx->watchdog_work); + } +} + +static void zd_rx_idle_timer_handler(struct work_struct *work) +{ + struct zd_usb *usb = + container_of(work, struct zd_usb, rx.idle_work.work); + struct zd_mac *mac = zd_usb_to_mac(usb); + + if (!test_bit(ZD_DEVICE_RUNNING, &mac->flags)) + return; + + dev_dbg_f(zd_usb_dev(usb), "\n"); + + /* 30 seconds since last rx, reset rx */ + zd_usb_reset_rx(usb); +} + +void zd_usb_reset_rx_idle_timer(struct zd_usb *usb) +{ + struct zd_usb_rx *rx = &usb->rx; + + cancel_delayed_work(&rx->idle_work); + queue_delayed_work(zd_workqueue, &rx->idle_work, ZD_RX_IDLE_INTERVAL); +} + static inline void init_usb_interrupt(struct zd_usb *usb) { struct zd_usb_interrupt *intr = &usb->intr; @@ -993,22 +1127,27 @@ static inline void init_usb_rx(struct zd_usb *usb) { struct zd_usb_rx *rx = &usb->rx; spin_lock_init(&rx->lock); + mutex_init(&rx->setup_mutex); if (interface_to_usbdev(usb->intf)->speed == USB_SPEED_HIGH) { rx->usb_packet_size = 512; } else { rx->usb_packet_size = 64; } ZD_ASSERT(rx->fragment_length == 0); + INIT_DELAYED_WORK(&rx->idle_work, zd_rx_idle_timer_handler); } static inline void init_usb_tx(struct zd_usb *usb) { struct zd_usb_tx *tx = &usb->tx; spin_lock_init(&tx->lock); - tx->enabled = 0; + atomic_set(&tx->enabled, 0); tx->stopped = 0; - INIT_LIST_HEAD(&tx->free_urb_list); + skb_queue_head_init(&tx->submitted_skbs); + init_usb_anchor(&tx->submitted); tx->submitted_urbs = 0; + tx->watchdog_enabled = 0; + INIT_DELAYED_WORK(&tx->watchdog_work, zd_tx_watchdog_handler); } void zd_usb_init(struct zd_usb *usb, struct ieee80211_hw *hw, @@ -1240,6 +1379,7 @@ static void disconnect(struct usb_interface *intf) ieee80211_unregister_hw(hw); /* Just in case something has gone wrong! */ + zd_usb_disable_tx(usb); zd_usb_disable_rx(usb); zd_usb_disable_int(usb); @@ -1255,11 +1395,92 @@ static void disconnect(struct usb_interface *intf) dev_dbg(&intf->dev, "disconnected\n"); } +static void zd_usb_resume(struct zd_usb *usb) +{ + struct zd_mac *mac = zd_usb_to_mac(usb); + int r; + + dev_dbg_f(zd_usb_dev(usb), "\n"); + + r = zd_op_start(zd_usb_to_hw(usb)); + if (r < 0) { + dev_warn(zd_usb_dev(usb), "Device resume failed " + "with error code %d. Retrying...\n", r); + if (usb->was_running) + set_bit(ZD_DEVICE_RUNNING, &mac->flags); + usb_queue_reset_device(usb->intf); + return; + } + + if (mac->type != NL80211_IFTYPE_UNSPECIFIED) { + r = zd_restore_settings(mac); + if (r < 0) { + dev_dbg(zd_usb_dev(usb), + "failed to restore settings, %d\n", r); + return; + } + } +} + +static void zd_usb_stop(struct zd_usb *usb) +{ + dev_dbg_f(zd_usb_dev(usb), "\n"); + + zd_op_stop(zd_usb_to_hw(usb)); + + zd_usb_disable_tx(usb); + zd_usb_disable_rx(usb); + zd_usb_disable_int(usb); + + usb->initialized = 0; +} + +static int pre_reset(struct usb_interface *intf) +{ + struct ieee80211_hw *hw = usb_get_intfdata(intf); + struct zd_mac *mac; + struct zd_usb *usb; + + if (!hw || intf->condition != USB_INTERFACE_BOUND) + return 0; + + mac = zd_hw_mac(hw); + usb = &mac->chip.usb; + + usb->was_running = test_bit(ZD_DEVICE_RUNNING, &mac->flags); + + zd_usb_stop(usb); + + mutex_lock(&mac->chip.mutex); + return 0; +} + +static int post_reset(struct usb_interface *intf) +{ + struct ieee80211_hw *hw = usb_get_intfdata(intf); + struct zd_mac *mac; + struct zd_usb *usb; + + if (!hw || intf->condition != USB_INTERFACE_BOUND) + return 0; + + mac = zd_hw_mac(hw); + usb = &mac->chip.usb; + + mutex_unlock(&mac->chip.mutex); + + if (usb->was_running) + zd_usb_resume(usb); + return 0; +} + static struct usb_driver driver = { .name = KBUILD_MODNAME, .id_table = usb_ids, .probe = probe, .disconnect = disconnect, + .pre_reset = pre_reset, + .post_reset = post_reset, }; struct workqueue_struct *zd_workqueue; @@ -1393,15 +1614,20 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values, return -EWOULDBLOCK; } if (!usb_int_enabled(usb)) { - dev_dbg_f(zd_usb_dev(usb), + dev_dbg_f(zd_usb_dev(usb), "error: usb interrupt not enabled\n"); return -EWOULDBLOCK; } + ZD_ASSERT(mutex_is_locked(&zd_usb_to_chip(usb)->mutex)); + BUILD_BUG_ON(sizeof(struct usb_req_read_regs) + USB_MAX_IOREAD16_COUNT * + sizeof(__le16) > sizeof(usb->req_buf)); + BUG_ON(sizeof(struct usb_req_read_regs) + count * sizeof(__le16) > + sizeof(usb->req_buf)); + req_len = sizeof(struct usb_req_read_regs) + count * sizeof(__le16); - req = kmalloc(req_len, GFP_KERNEL); - if (!req) - return -ENOMEM; + req = (void *)usb->req_buf; + req->id = cpu_to_le16(USB_REQ_READ_REGS); for (i = 0; i < count; i++) req->addr[i] = cpu_to_le16((u16)addresses[i]); @@ -1409,7 +1635,7 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values, udev = zd_usb_to_usbdev(usb); prepare_read_regs_int(usb); r = usb_bulk_msg(udev, usb_sndbulkpipe(udev, EP_REGS_OUT), - req, req_len, &actual_req_len, 1000 /* ms */); + req, req_len, &actual_req_len, 50 /* ms */); if (r) { dev_dbg_f(zd_usb_dev(usb), "error in usb_bulk_msg(). Error number %d\n", r); @@ -1424,7 +1650,7 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values, } timeout = wait_for_completion_timeout(&usb->intr.read_regs.completion, - msecs_to_jiffies(1000)); + msecs_to_jiffies(50)); if (!timeout) { disable_read_regs_int(usb); dev_dbg_f(zd_usb_dev(usb), "read timed out\n"); @@ -1434,7 +1660,6 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values, r = get_results(usb, values, req, count); error: - kfree(req); return r; } @@ -1460,11 +1685,17 @@ int zd_usb_iowrite16v(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs, return -EWOULDBLOCK; } + ZD_ASSERT(mutex_is_locked(&zd_usb_to_chip(usb)->mutex)); + BUILD_BUG_ON(sizeof(struct usb_req_write_regs) + + USB_MAX_IOWRITE16_COUNT * sizeof(struct reg_data) > + sizeof(usb->req_buf)); + BUG_ON(sizeof(struct usb_req_write_regs) + + count * sizeof(struct reg_data) > + sizeof(usb->req_buf)); + req_len = sizeof(struct usb_req_write_regs) + count * sizeof(struct reg_data); - req = kmalloc(req_len, GFP_KERNEL); - if (!req) - return -ENOMEM; + req = (void *)usb->req_buf; req->id = cpu_to_le16(USB_REQ_WRITE_REGS); for (i = 0; i < count; i++) { @@ -1475,7 +1706,7 @@ int zd_usb_iowrite16v(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs, udev = zd_usb_to_usbdev(usb); r = usb_bulk_msg(udev, usb_sndbulkpipe(udev, EP_REGS_OUT), - req, req_len, &actual_req_len, 1000 /* ms */); + req, req_len, &actual_req_len, 50 /* ms */); if (r) { dev_dbg_f(zd_usb_dev(usb), "error in usb_bulk_msg(). Error number %d\n", r); @@ -1492,7 +1723,6 @@ int zd_usb_iowrite16v(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs, /* FALL-THROUGH with r == 0 */ error: - kfree(req); return r; } @@ -1537,14 +1767,19 @@ int zd_usb_rfwrite(struct zd_usb *usb, u32 value, u8 bits) if (r) { dev_dbg_f(zd_usb_dev(usb), "error %d: Couldn't read CR203\n", r); - goto out; + return r; } bit_value_template &= ~(RF_IF_LE|RF_CLK|RF_DATA); + ZD_ASSERT(mutex_is_locked(&zd_usb_to_chip(usb)->mutex)); + BUILD_BUG_ON(sizeof(struct usb_req_rfwrite) + + USB_MAX_RFWRITE_BIT_COUNT * sizeof(__le16) > + sizeof(usb->req_buf)); + BUG_ON(sizeof(struct usb_req_rfwrite) + bits * sizeof(__le16) > + sizeof(usb->req_buf)); + req_len = sizeof(struct usb_req_rfwrite) + bits * sizeof(__le16); - req = kmalloc(req_len, GFP_KERNEL); - if (!req) - return -ENOMEM; + req = (void *)usb->req_buf; req->id = cpu_to_le16(USB_REQ_WRITE_RF); /* 1: 3683a, but not used in ZYDAS driver */ @@ -1560,7 +1795,7 @@ int zd_usb_rfwrite(struct zd_usb *usb, u32 value, u8 bits) udev = zd_usb_to_usbdev(usb); r = usb_bulk_msg(udev, usb_sndbulkpipe(udev, EP_REGS_OUT), - req, req_len, &actual_req_len, 1000 /* ms */); + req, req_len, &actual_req_len, 50 /* ms */); if (r) { dev_dbg_f(zd_usb_dev(usb), "error in usb_bulk_msg(). Error number %d\n", r); @@ -1576,6 +1811,5 @@ int zd_usb_rfwrite(struct zd_usb *usb, u32 value, u8 bits) /* FALL-THROUGH with r == 0 */ out: - kfree(req); return r; } diff --git a/drivers/net/wireless/zd1211rw/zd_usb.h b/drivers/net/wireless/zd1211rw/zd_usb.h index 1b1655c..2d688f4 100644 --- a/drivers/net/wireless/zd1211rw/zd_usb.h +++ b/drivers/net/wireless/zd1211rw/zd_usb.h @@ -32,6 +32,10 @@ #define ZD_USB_TX_HIGH 5 #define ZD_USB_TX_LOW 2 +#define ZD_TX_TIMEOUT (HZ * 5) +#define ZD_TX_WATCHDOG_INTERVAL round_jiffies_relative(HZ) +#define ZD_RX_IDLE_INTERVAL round_jiffies_relative(30 * HZ) + enum devicetype { DEVICE_ZD1211 = 0, DEVICE_ZD1211B = 1, @@ -162,6 +166,8 @@ struct zd_usb_interrupt { struct read_regs_int read_regs; spinlock_t lock; struct urb *urb; + void *buffer; + dma_addr_t buffer_dma; int interval; u8 read_regs_enabled:1; }; @@ -175,7 +181,9 @@ static inline struct usb_int_regs *get_read_regs(struct zd_usb_interrupt *intr) struct zd_usb_rx { spinlock_t lock; - u8 fragment[2*USB_MAX_RX_SIZE]; + struct mutex setup_mutex; + struct delayed_work idle_work; + u8 fragment[2 * USB_MAX_RX_SIZE]; unsigned int fragment_length; unsigned int usb_packet_size; struct urb **urbs; @@ -184,19 +192,21 @@ struct zd_usb_rx { /** * struct zd_usb_tx - structure used for transmitting frames + * @enabled: atomic enabled flag, indicates whether tx is enabled * @lock: lock for transmission - * @free_urb_list: list of free URBs, contains all the URBs, which can be used + * @submitted: anchor for URBs sent to device * @submitted_urbs: atomic integer that counts the URBs having sent to the * device, which haven't been completed - * @enabled: enabled flag, indicates whether tx is enabled * @stopped: indicates whether higher level tx queues are stopped */ struct zd_usb_tx { + atomic_t enabled; spinlock_t lock; - struct list_head free_urb_list; + struct delayed_work watchdog_work; + struct sk_buff_head submitted_skbs; + struct usb_anchor submitted; int submitted_urbs; - int enabled; - int stopped; + u8 stopped:1, watchdog_enabled:1; }; /* Contains the usb parts. The structure doesn't require a lock because intf @@ -207,7 +217,8 @@ struct zd_usb { struct zd_usb_rx rx; struct zd_usb_tx tx; struct usb_interface *intf; - u8 is_zd1211b:1, initialized:1; + u8 req_buf[64]; /* zd_usb_iowrite16v needs 62 bytes */ + u8 is_zd1211b:1, initialized:1, was_running:1; }; #define zd_usb_dev(usb) (&usb->intf->dev) @@ -234,12 +245,17 @@ void zd_usb_clear(struct zd_usb *usb); int zd_usb_scnprint_id(struct zd_usb *usb, char *buffer, size_t size); +void zd_tx_watchdog_enable(struct zd_usb *usb); +void zd_tx_watchdog_disable(struct zd_usb *usb); + int zd_usb_enable_int(struct zd_usb *usb); void zd_usb_disable_int(struct zd_usb *usb); int zd_usb_enable_rx(struct zd_usb *usb); void zd_usb_disable_rx(struct zd_usb *usb); +void zd_usb_reset_rx_idle_timer(struct zd_usb *usb); + void zd_usb_enable_tx(struct zd_usb *usb); void zd_usb_disable_tx(struct zd_usb *usb); diff --git a/include/linux/audit.h b/include/linux/audit.h index 359df04..9d339eb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -103,6 +103,8 @@ #define AUDIT_BPRM_FCAPS 1321 /* Information about fcaps increasing perms */ #define AUDIT_CAPSET 1322 /* Record showing argument to sys_capset */ #define AUDIT_MMAP 1323 /* Record showing descriptor and flags in mmap */ +#define AUDIT_NETFILTER_PKT 1324 /* Packets traversing netfilter chains */ +#define AUDIT_NETFILTER_CFG 1325 /* Netfilter chain modifications */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h new file mode 100644 index 0000000..473771a --- /dev/null +++ b/include/linux/cpu_rmap.h @@ -0,0 +1,73 @@ +/* + * cpu_rmap.c: CPU affinity reverse-map support + * Copyright 2011 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include <linux/cpumask.h> +#include <linux/gfp.h> +#include <linux/slab.h> + +/** + * struct cpu_rmap - CPU affinity reverse-map + * @size: Number of objects to be reverse-mapped + * @used: Number of objects added + * @obj: Pointer to array of object pointers + * @near: For each CPU, the index and distance to the nearest object, + * based on affinity masks + */ +struct cpu_rmap { + u16 size, used; + void **obj; + struct { + u16 index; + u16 dist; + } near[0]; +}; +#define CPU_RMAP_DIST_INF 0xffff + +extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags); + +/** + * free_cpu_rmap - free CPU affinity reverse-map + * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL + */ +static inline void free_cpu_rmap(struct cpu_rmap *rmap) +{ + kfree(rmap); +} + +extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj); +extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index, + const struct cpumask *affinity); + +static inline u16 cpu_rmap_lookup_index(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->near[cpu].index; +} + +static inline void *cpu_rmap_lookup_obj(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->obj[rmap->near[cpu].index]; +} + +#ifdef CONFIG_GENERIC_HARDIRQS + +/** + * alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs + * @size: Number of objects to be mapped + * + * Must be called in process context. + */ +static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size) +{ + return alloc_cpu_rmap(size, GFP_KERNEL); +} +extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); + +extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); + +#endif diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 66900e3..4c5b26e 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -25,6 +25,11 @@ /* IEEE 802.1Qaz std supported values */ #define IEEE_8021QAZ_MAX_TCS 8 +#define IEEE_8021QAZ_TSA_STRICT 0 +#define IEEE_8021QAZ_TSA_CB_SHABER 1 +#define IEEE_8021QAZ_TSA_ETS 2 +#define IEEE_8021QAZ_TSA_VENDOR 255 + /* This structure contains the IEEE 802.1Qaz ETS managed object * * @willing: willing bit in ETS configuratin TLV diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 010e2d8..d638e85 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -279,8 +279,6 @@ enum dccp_state { DCCP_MAX_STATES }; -#define DCCP_STATE_MASK 0x1f - enum { DCCPF_OPEN = TCPF_ESTABLISHED, DCCPF_REQUESTING = TCPF_SYN_SENT, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 1908929..54d776c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -251,6 +251,7 @@ enum ethtool_stringset { ETH_SS_STATS, ETH_SS_PRIV_FLAGS, ETH_SS_NTUPLE_FILTERS, + ETH_SS_FEATURES, }; /* for passing string sets for data tagging */ @@ -523,6 +524,87 @@ struct ethtool_flash { char data[ETHTOOL_FLASH_MAX_FILENAME]; }; +/* for returning and changing feature sets */ + +/** + * struct ethtool_get_features_block - block with state of 32 features + * @available: mask of changeable features + * @requested: mask of features requested to be enabled if possible + * @active: mask of currently enabled features + * @never_changed: mask of features not changeable for any device + */ +struct ethtool_get_features_block { + __u32 available; + __u32 requested; + __u32 active; + __u32 never_changed; +}; + +/** + * struct ethtool_gfeatures - command to get state of device's features + * @cmd: command number = %ETHTOOL_GFEATURES + * @size: in: number of elements in the features[] array; + * out: number of elements in features[] needed to hold all features + * @features: state of features + */ +struct ethtool_gfeatures { + __u32 cmd; + __u32 size; + struct ethtool_get_features_block features[0]; +}; + +/** + * struct ethtool_set_features_block - block with request for 32 features + * @valid: mask of features to be changed + * @requested: values of features to be changed + */ +struct ethtool_set_features_block { + __u32 valid; + __u32 requested; +}; + +/** + * struct ethtool_sfeatures - command to request change in device's features + * @cmd: command number = %ETHTOOL_SFEATURES + * @size: array size of the features[] array + * @features: feature change masks + */ +struct ethtool_sfeatures { + __u32 cmd; + __u32 size; + struct ethtool_set_features_block features[0]; +}; + +/* + * %ETHTOOL_SFEATURES changes features present in features[].valid to the + * values of corresponding bits in features[].requested. Bits in .requested + * not set in .valid or not changeable are ignored. + * + * Returns %EINVAL when .valid contains undefined or never-changable bits + * or size is not equal to required number of features words (32-bit blocks). + * Returns >= 0 if request was completed; bits set in the value mean: + * %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not + * changeable (not present in %ETHTOOL_GFEATURES' features[].available) + * those bits were ignored. + * %ETHTOOL_F_WISH - some or all changes requested were recorded but the + * resulting state of bits masked by .valid is not equal to .requested. + * Probably there are other device-specific constraints on some features + * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered + * here as though ignored bits were cleared. + * + * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of + * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands + * for ETH_SS_FEATURES string set. First entry in the table corresponds to least + * significant bit in features[0] fields. Empty strings mark undefined features. + */ +enum ethtool_sfeatures_retval_bits { + ETHTOOL_F_UNSUPPORTED__BIT, + ETHTOOL_F_WISH__BIT, +}; + +#define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT) +#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT) + #ifdef __KERNEL__ #include <linux/rculist.h> @@ -543,7 +625,6 @@ struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ u32 ethtool_op_get_link(struct net_device *dev); -u32 ethtool_op_get_rx_csum(struct net_device *dev); u32 ethtool_op_get_tx_csum(struct net_device *dev); int ethtool_op_set_tx_csum(struct net_device *dev, u32 data); int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data); @@ -744,6 +825,9 @@ struct ethtool_ops { #define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */ #define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */ +#define ETHTOOL_GFEATURES 0x0000003a /* Get device offload settings */ +#define ETHTOOL_SFEATURES 0x0000003b /* Change device offload settings */ + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 6485d2a..f4a2e6b 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -135,6 +135,7 @@ enum { IFLA_VF_PORTS, IFLA_PORT_SELF, IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ __IFLA_MAX }; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ae8fdc5..5f81466 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -144,6 +144,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) struct in_ifaddr { + struct hlist_node hash; struct in_ifaddr *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 55e0d42..63c5ad7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -14,6 +14,8 @@ #include <linux/smp.h> #include <linux/percpu.h> #include <linux/hrtimer.h> +#include <linux/kref.h> +#include <linux/workqueue.h> #include <asm/atomic.h> #include <asm/ptrace.h> @@ -240,6 +242,35 @@ extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); + +/** + * struct irq_affinity_notify - context for notification of IRQ affinity changes + * @irq: Interrupt to which notification applies + * @kref: Reference count, for internal use + * @work: Work item, for internal use + * @notify: Function to be called on change. This will be + * called in process context. + * @release: Function to be called on release. This will be + * called in process context. Once registered, the + * structure must only be freed when this function is + * called or later. + */ +struct irq_affinity_notify { + unsigned int irq; + struct kref kref; + struct work_struct work; + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); +}; + +extern int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); + +static inline void irq_run_affinity_notifiers(void) +{ + flush_scheduled_work(); +} + #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) @@ -255,7 +286,7 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } static inline int irq_set_affinity_hint(unsigned int irq, - const struct cpumask *m) + const struct cpumask *m) { return -EINVAL; } diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 5f43a3b..4deb383 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -89,6 +89,14 @@ #define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */ #define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */ +#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \ + IP_VS_CONN_F_NOOUTPUT | \ + IP_VS_CONN_F_INACTIVE | \ + IP_VS_CONN_F_SEQ_MASK | \ + IP_VS_CONN_F_NO_CPORT | \ + IP_VS_CONN_F_TEMPLATE \ + ) + /* Flags that are not sent to backup server start from bit 16 */ #define IP_VS_CONN_F_NFCT (1 << 16) /* use netfilter conntrack */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c1a95b7..bfef56d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -8,6 +8,7 @@ * For now it's included from <linux/irq.h> */ +struct irq_affinity_notify; struct proc_dir_entry; struct timer_rand_state; /** @@ -24,6 +25,7 @@ struct timer_rand_state; * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @lock: locking for SMP + * @affinity_notify: context for notification of affinity changes * @pending_mask: pending rebalanced interrupts * @threads_active: number of irqaction threads currently running * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers @@ -70,6 +72,7 @@ struct irq_desc { raw_spinlock_t lock; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; + struct irq_affinity_notify *affinity_notify; #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_var_t pending_mask; #endif diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h new file mode 100644 index 0000000..dd8da34 --- /dev/null +++ b/include/linux/micrel_phy.h @@ -0,0 +1,16 @@ +#ifndef _MICREL_PHY_H +#define _MICREL_PHY_H + +#define MICREL_PHY_ID_MASK 0x00fffff0 + +#define PHY_ID_KSZ9021 0x00221611 +#define PHY_ID_KS8737 0x00221720 +#define PHY_ID_KS8041 0x00221510 +#define PHY_ID_KS8051 0x00221550 +/* both for ks8001 Rev. A/B, and for ks8721 Rev 3. */ +#define PHY_ID_KS8001 0x0022161A + +/* struct phy_device dev_flags definitions */ +#define MICREL_PHY_50MHZ_CLK 0x00000001 + +#endif /* _MICREL_PHY_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d971346..ffe56c1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -75,6 +75,9 @@ struct wireless_dev; #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +/* Initial net device group. All devices belong to group 0 by default. */ +#define INIT_NETDEV_GROUP 0 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -551,14 +554,16 @@ struct rps_map { #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) /* - * The rps_dev_flow structure contains the mapping of a flow to a CPU and the - * tail pointer for that CPU's input queue at the time of last enqueue. + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. */ struct rps_dev_flow { u16 cpu; - u16 fill; + u16 filter; unsigned int last_qtail; }; +#define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. @@ -608,6 +613,11 @@ static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; +#ifdef CONFIG_RFS_ACCEL +extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id); +#endif + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map __rcu *rps_map; @@ -643,6 +653,14 @@ struct xps_dev_maps { (nr_cpu_ids * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ +#define TC_MAX_QUEUE 16 +#define TC_BITMASK 15 +/* HW offloaded queuing disciplines txq count and offset maps */ +struct netdev_tc_txq { + u16 count; + u16 offset; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -753,6 +771,38 @@ struct xps_dev_maps { * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) + * Called to setup 'tc' number of traffic classes in the net device. This + * is always called from the stack with the rtnl lock held and netif tx + * queues stopped. This allows the netdevice to perform queue management + * safely. + * + * RFS acceleration. + * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, + * u16 rxq_index, u32 flow_id); + * Set hardware filter for RFS. rxq_index is the target queue index; + * flow_id is a flow ID to be passed to rps_may_expire_flow() later. + * Return the filter ID on success, or a negative error code. + * + * Slave management functions (for bridge, bonding, etc). User should + * call netdev_set_master() to set dev->master properly. + * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); + * Called to make another netdev an underling. + * + * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); + * Called to release previously enslaved netdev. + * + * Feature/offload setting functions. + * u32 (*ndo_fix_features)(struct net_device *dev, u32 features); + * Adjusts the requested feature flags according to device-specific + * constraints, and returns the resulting flags. Must not modify + * the device state. + * + * int (*ndo_set_features)(struct net_device *dev, u32 features); + * Called to update device configuration to new features. Passed + * feature set might be less than what was returned by ndo_fix_features()). + * Must return >0 or -errno if it changed dev->features itself. + * */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -811,6 +861,7 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_setup_tc)(struct net_device *dev, u8 tc); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -825,6 +876,20 @@ struct net_device_ops { int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif +#ifdef CONFIG_RFS_ACCEL + int (*ndo_rx_flow_steer)(struct net_device *dev, + const struct sk_buff *skb, + u16 rxq_index, + u32 flow_id); +#endif + int (*ndo_add_slave)(struct net_device *dev, + struct net_device *slave_dev); + int (*ndo_del_slave)(struct net_device *dev, + struct net_device *slave_dev); + u32 (*ndo_fix_features)(struct net_device *dev, + u32 features); + int (*ndo_set_features)(struct net_device *dev, + u32 features); }; /* @@ -876,8 +941,18 @@ struct net_device { struct list_head napi_list; struct list_head unreg_list; - /* Net device features */ - unsigned long features; + /* currently active device features */ + u32 features; + /* user-changeable features */ + u32 hw_features; + /* user-requested features */ + u32 wanted_features; + /* VLAN feature mask */ + u32 vlan_features; + + /* Net device feature bits; if you change something, + * also update netdev_features_strings[] in ethtool.c */ + #define NETIF_F_SG 1 /* Scatter/gather IO. */ #define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */ #define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */ @@ -902,6 +977,7 @@ struct net_device { #define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/ #define NETIF_F_NTUPLE (1 << 27) /* N-tuple filters supported */ #define NETIF_F_RXHASH (1 << 28) /* Receive hashing offload */ +#define NETIF_F_RXCSUM (1 << 29) /* Receive checksumming offload */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 @@ -913,6 +989,12 @@ struct net_device { #define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT) #define NETIF_F_FSO (SKB_GSO_FCOE << NETIF_F_GSO_SHIFT) + /* Features valid for ethtool to change */ + /* = all defined minus driver/device-class-related */ +#define NETIF_F_NEVER_CHANGE (NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \ + NETIF_F_LLTX | NETIF_F_NETNS_LOCAL) +#define NETIF_F_ETHTOOL_BITS (0x3f3fffff & ~NETIF_F_NEVER_CHANGE) + /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \ NETIF_F_TSO6 | NETIF_F_UFO) @@ -923,6 +1005,12 @@ struct net_device { #define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM) #define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) +#define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) + +#define NETIF_F_ALL_TX_OFFLOADS (NETIF_F_ALL_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_SCTP_CSUM | NETIF_F_FCOE_CRC) + /* * If one device supports one of these features, then enable them * for all in netdev_increment_features. @@ -931,6 +1019,9 @@ struct net_device { NETIF_F_SG | NETIF_F_HIGHDMA | \ NETIF_F_FRAGLIST) + /* changeable features with no special hardware requirements */ +#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) + /* Interface index. Unique device identifier */ int ifindex; int iflink; @@ -1039,6 +1130,13 @@ struct net_device { /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; + +#ifdef CONFIG_RFS_ACCEL + /* CPU reverse-mapping for RX completion interrupts, indexed + * by RX queue number. Assigned by driver. This must only be + * set if the ndo_rx_flow_steer operation is defined. */ + struct cpu_rmap *rx_cpu_rmap; +#endif #endif rx_handler_func_t __rcu *rx_handler; @@ -1132,9 +1230,6 @@ struct net_device { /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; - /* VLAN feature mask */ - unsigned long vlan_features; - /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; @@ -1143,6 +1238,9 @@ struct net_device { /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif + u8 num_tc; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; + u8 prio_tc_map[TC_BITMASK + 1]; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* max exchange id for FCoE LRO by ddp */ @@ -1153,12 +1251,66 @@ struct net_device { /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; + + /* group the device belongs to */ + int group; }; #define to_net_dev(d) container_of(d, struct net_device, dev) #define NETDEV_ALIGN 32 static inline +int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) +{ + return dev->prio_tc_map[prio & TC_BITMASK]; +} + +static inline +int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; + return 0; +} + +static inline +void netdev_reset_tc(struct net_device *dev) +{ + dev->num_tc = 0; + memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); + memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); +} + +static inline +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->tc_to_txq[tc].count = count; + dev->tc_to_txq[tc].offset = offset; + return 0; +} + +static inline +int netdev_set_num_tc(struct net_device *dev, u8 num_tc) +{ + if (num_tc > TC_MAX_QUEUE) + return -EINVAL; + + dev->num_tc = num_tc; + return 0; +} + +static inline +int netdev_get_num_tc(struct net_device *dev) +{ + return dev->num_tc; +} + +static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { @@ -1300,7 +1452,7 @@ struct packet_type { struct packet_type *, struct net_device *); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); @@ -1345,7 +1497,7 @@ static inline struct net_device *next_net_device_rcu(struct net_device *dev) struct net *net; net = dev_net(dev); - lh = rcu_dereference(dev->dev_list.next); + lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } @@ -1355,6 +1507,13 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } +static inline struct net_device *first_net_device_rcu(struct net *net) +{ + struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); + + return lh == &net->dev_base_head ? NULL : net_device_entry(lh); +} + extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, @@ -1844,6 +2003,7 @@ extern int dev_set_alias(struct net_device *, const char *, size_t); extern int dev_change_net_namespace(struct net_device *, struct net *, const char *); extern int dev_set_mtu(struct net_device *, int); +extern void dev_set_group(struct net_device *, int); extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_hard_start_xmit(struct sk_buff *skb, @@ -2267,8 +2427,10 @@ extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); +extern int netdev_set_bond_master(struct net_device *dev, + struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb); -extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else @@ -2295,22 +2457,26 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l extern void linkwatch_run_queue(void); -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask); -unsigned long netdev_fix_features(unsigned long features, const char *name); +static inline u32 netdev_get_wanted_features(struct net_device *dev) +{ + return (dev->features & ~dev->hw_features) | dev->wanted_features; +} +u32 netdev_increment_features(u32 all, u32 one, u32 mask); +u32 netdev_fix_features(struct net_device *dev, u32 features); +void netdev_update_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -int netif_skb_features(struct sk_buff *skb); +u32 netif_skb_features(struct sk_buff *skb); -static inline int net_gso_ok(int features, int gso_type) +static inline int net_gso_ok(u32 features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; return (features & feature) == feature; } -static inline int skb_gso_ok(struct sk_buff *skb, int features) +static inline int skb_gso_ok(struct sk_buff *skb, u32 features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); @@ -2328,15 +2494,9 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } -extern int __skb_bond_should_drop(struct sk_buff *skb, - struct net_device *master); - -static inline int skb_bond_should_drop(struct sk_buff *skb, - struct net_device *master) +static inline int netif_is_bond_slave(struct net_device *dev) { - if (master) - return __skb_bond_should_drop(skb, master); - return 0; + return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } extern struct pernet_operations __net_initdata loopback_net_ops; @@ -2351,6 +2511,8 @@ static inline int dev_ethtool_get_settings(struct net_device *dev, static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev) { + if (dev->hw_features & NETIF_F_RXCSUM) + return !!(dev->features & NETIF_F_RXCSUM); if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum) return 0; return dev->ethtool_ops->get_rx_csum(dev); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1893837..eeec00a 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,16 +24,20 @@ #define NF_MAX_VERDICT NF_STOP /* we overload the higher bits for encoding auxiliary data such as the queue - * number. Not nice, but better than additional function arguments. */ -#define NF_VERDICT_MASK 0x0000ffff -#define NF_VERDICT_BITS 16 + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 +/* queue number (NF_QUEUE) or errno (NF_DROP) */ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) -#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) /* only for userspace compatibility */ #ifndef __KERNEL__ @@ -41,6 +45,9 @@ <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 #endif enum nf_inet_hooks { @@ -72,6 +79,10 @@ union nf_inet_addr { #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER +static inline int NF_DROP_GETERR(int verdict) +{ + return -(verdict >> NF_VERDICT_QBITS); +} static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) @@ -267,7 +278,7 @@ struct nf_afinfo { int route_key_size; }; -extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO]; +extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO]; static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) { return rcu_dereference(nf_afinfo[family]); @@ -357,9 +368,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *); +extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 9d40eff..15e83bf 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -1,3 +1,5 @@ +header-y += ipset/ + header-y += nf_conntrack_common.h header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h @@ -9,6 +11,7 @@ header-y += nfnetlink_conntrack.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h header-y += x_tables.h +header-y += xt_AUDIT.h header-y += xt_CHECKSUM.h header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h @@ -34,6 +37,7 @@ header-y += xt_connmark.h header-y += xt_conntrack.h header-y += xt_cpu.h header-y += xt_dccp.h +header-y += xt_devgroup.h header-y += xt_dscp.h header-y += xt_esp.h header-y += xt_hashlimit.h @@ -54,7 +58,9 @@ header-y += xt_quota.h header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_recent.h +header-y += xt_set.h header-y += xt_sctp.h +header-y += xt_socket.h header-y += xt_state.h header-y += xt_statistic.h header-y += xt_string.h diff --git a/include/linux/netfilter/ipset/Kbuild b/include/linux/netfilter/ipset/Kbuild new file mode 100644 index 0000000..601fe71 --- /dev/null +++ b/include/linux/netfilter/ipset/Kbuild @@ -0,0 +1,4 @@ +header-y += ip_set.h +header-y += ip_set_bitmap.h +header-y += ip_set_hash.h +header-y += ip_set_list.h diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h new file mode 100644 index 0000000..ec333d8 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set.h @@ -0,0 +1,452 @@ +#ifndef _IP_SET_H +#define _IP_SET_H + +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Martin Josefsson <gandalf@wlug.westbo.se> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* The protocol version */ +#define IPSET_PROTOCOL 6 + +/* The max length of strings including NUL: set and type identifiers */ +#define IPSET_MAXNAMELEN 32 + +/* Message types and commands */ +enum ipset_cmd { + IPSET_CMD_NONE, + IPSET_CMD_PROTOCOL, /* 1: Return protocol version */ + IPSET_CMD_CREATE, /* 2: Create a new (empty) set */ + IPSET_CMD_DESTROY, /* 3: Destroy a (empty) set */ + IPSET_CMD_FLUSH, /* 4: Remove all elements from a set */ + IPSET_CMD_RENAME, /* 5: Rename a set */ + IPSET_CMD_SWAP, /* 6: Swap two sets */ + IPSET_CMD_LIST, /* 7: List sets */ + IPSET_CMD_SAVE, /* 8: Save sets */ + IPSET_CMD_ADD, /* 9: Add an element to a set */ + IPSET_CMD_DEL, /* 10: Delete an element from a set */ + IPSET_CMD_TEST, /* 11: Test an element in a set */ + IPSET_CMD_HEADER, /* 12: Get set header data only */ + IPSET_CMD_TYPE, /* 13: Get set type */ + IPSET_MSG_MAX, /* Netlink message commands */ + + /* Commands in userspace: */ + IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 14: Enter restore mode */ + IPSET_CMD_HELP, /* 15: Get help */ + IPSET_CMD_VERSION, /* 16: Get program version */ + IPSET_CMD_QUIT, /* 17: Quit from interactive mode */ + + IPSET_CMD_MAX, + + IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 18: Commit buffered commands */ +}; + +/* Attributes at command level */ +enum { + IPSET_ATTR_UNSPEC, + IPSET_ATTR_PROTOCOL, /* 1: Protocol version */ + IPSET_ATTR_SETNAME, /* 2: Name of the set */ + IPSET_ATTR_TYPENAME, /* 3: Typename */ + IPSET_ATTR_SETNAME2 = IPSET_ATTR_TYPENAME, /* Setname at rename/swap */ + IPSET_ATTR_REVISION, /* 4: Settype revision */ + IPSET_ATTR_FAMILY, /* 5: Settype family */ + IPSET_ATTR_FLAGS, /* 6: Flags at command level */ + IPSET_ATTR_DATA, /* 7: Nested attributes */ + IPSET_ATTR_ADT, /* 8: Multiple data containers */ + IPSET_ATTR_LINENO, /* 9: Restore lineno */ + IPSET_ATTR_PROTOCOL_MIN, /* 10: Minimal supported version number */ + IPSET_ATTR_REVISION_MIN = IPSET_ATTR_PROTOCOL_MIN, /* type rev min */ + __IPSET_ATTR_CMD_MAX, +}; +#define IPSET_ATTR_CMD_MAX (__IPSET_ATTR_CMD_MAX - 1) + +/* CADT specific attributes */ +enum { + IPSET_ATTR_IP = IPSET_ATTR_UNSPEC + 1, + IPSET_ATTR_IP_FROM = IPSET_ATTR_IP, + IPSET_ATTR_IP_TO, /* 2 */ + IPSET_ATTR_CIDR, /* 3 */ + IPSET_ATTR_PORT, /* 4 */ + IPSET_ATTR_PORT_FROM = IPSET_ATTR_PORT, + IPSET_ATTR_PORT_TO, /* 5 */ + IPSET_ATTR_TIMEOUT, /* 6 */ + IPSET_ATTR_PROTO, /* 7 */ + IPSET_ATTR_CADT_FLAGS, /* 8 */ + IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */ + /* Reserve empty slots */ + IPSET_ATTR_CADT_MAX = 16, + /* Create-only specific attributes */ + IPSET_ATTR_GC, + IPSET_ATTR_HASHSIZE, + IPSET_ATTR_MAXELEM, + IPSET_ATTR_NETMASK, + IPSET_ATTR_PROBES, + IPSET_ATTR_RESIZE, + IPSET_ATTR_SIZE, + /* Kernel-only */ + IPSET_ATTR_ELEMENTS, + IPSET_ATTR_REFERENCES, + IPSET_ATTR_MEMSIZE, + + __IPSET_ATTR_CREATE_MAX, +}; +#define IPSET_ATTR_CREATE_MAX (__IPSET_ATTR_CREATE_MAX - 1) + +/* ADT specific attributes */ +enum { + IPSET_ATTR_ETHER = IPSET_ATTR_CADT_MAX + 1, + IPSET_ATTR_NAME, + IPSET_ATTR_NAMEREF, + IPSET_ATTR_IP2, + IPSET_ATTR_CIDR2, + __IPSET_ATTR_ADT_MAX, +}; +#define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1) + +/* IP specific attributes */ +enum { + IPSET_ATTR_IPADDR_IPV4 = IPSET_ATTR_UNSPEC + 1, + IPSET_ATTR_IPADDR_IPV6, + __IPSET_ATTR_IPADDR_MAX, +}; +#define IPSET_ATTR_IPADDR_MAX (__IPSET_ATTR_IPADDR_MAX - 1) + +/* Error codes */ +enum ipset_errno { + IPSET_ERR_PRIVATE = 4096, + IPSET_ERR_PROTOCOL, + IPSET_ERR_FIND_TYPE, + IPSET_ERR_MAX_SETS, + IPSET_ERR_BUSY, + IPSET_ERR_EXIST_SETNAME2, + IPSET_ERR_TYPE_MISMATCH, + IPSET_ERR_EXIST, + IPSET_ERR_INVALID_CIDR, + IPSET_ERR_INVALID_NETMASK, + IPSET_ERR_INVALID_FAMILY, + IPSET_ERR_TIMEOUT, + IPSET_ERR_REFERENCED, + IPSET_ERR_IPADDR_IPV4, + IPSET_ERR_IPADDR_IPV6, + + /* Type specific error codes */ + IPSET_ERR_TYPE_SPECIFIC = 4352, +}; + +/* Flags at command level */ +enum ipset_cmd_flags { + IPSET_FLAG_BIT_EXIST = 0, + IPSET_FLAG_EXIST = (1 << IPSET_FLAG_BIT_EXIST), +}; + +/* Flags at CADT attribute level */ +enum ipset_cadt_flags { + IPSET_FLAG_BIT_BEFORE = 0, + IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE), +}; + +/* Commands with settype-specific attributes */ +enum ipset_adt { + IPSET_ADD, + IPSET_DEL, + IPSET_TEST, + IPSET_ADT_MAX, + IPSET_CREATE = IPSET_ADT_MAX, + IPSET_CADT_MAX, +}; + +#ifdef __KERNEL__ +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/vmalloc.h> +#include <net/netlink.h> + +/* Sets are identified by an index in kernel space. Tweak with ip_set_id_t + * and IPSET_INVALID_ID if you want to increase the max number of sets. + */ +typedef u16 ip_set_id_t; + +#define IPSET_INVALID_ID 65535 + +enum ip_set_dim { + IPSET_DIM_ZERO = 0, + IPSET_DIM_ONE, + IPSET_DIM_TWO, + IPSET_DIM_THREE, + /* Max dimension in elements. + * If changed, new revision of iptables match/target is required. + */ + IPSET_DIM_MAX = 6, +}; + +/* Option flags for kernel operations */ +enum ip_set_kopt { + IPSET_INV_MATCH = (1 << IPSET_DIM_ZERO), + IPSET_DIM_ONE_SRC = (1 << IPSET_DIM_ONE), + IPSET_DIM_TWO_SRC = (1 << IPSET_DIM_TWO), + IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE), +}; + +/* Set features */ +enum ip_set_feature { + IPSET_TYPE_IP_FLAG = 0, + IPSET_TYPE_IP = (1 << IPSET_TYPE_IP_FLAG), + IPSET_TYPE_PORT_FLAG = 1, + IPSET_TYPE_PORT = (1 << IPSET_TYPE_PORT_FLAG), + IPSET_TYPE_MAC_FLAG = 2, + IPSET_TYPE_MAC = (1 << IPSET_TYPE_MAC_FLAG), + IPSET_TYPE_IP2_FLAG = 3, + IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG), + IPSET_TYPE_NAME_FLAG = 4, + IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), + /* Strictly speaking not a feature, but a flag for dumping: + * this settype must be dumped last */ + IPSET_DUMP_LAST_FLAG = 7, + IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), +}; + +struct ip_set; + +typedef int (*ipset_adtfn)(struct ip_set *set, void *value, u32 timeout); + +/* Set type, variant-specific part */ +struct ip_set_type_variant { + /* Kernelspace: test/add/del entries + * returns negative error code, + * zero for no match/success to add/delete + * positive for matching element */ + int (*kadt)(struct ip_set *set, const struct sk_buff * skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags); + + /* Userspace: test/add/del entries + * returns negative error code, + * zero for no match/success to add/delete + * positive for matching element */ + int (*uadt)(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags); + + /* Low level add/del/test functions */ + ipset_adtfn adt[IPSET_ADT_MAX]; + + /* When adding entries and set is full, try to resize the set */ + int (*resize)(struct ip_set *set, bool retried); + /* Destroy the set */ + void (*destroy)(struct ip_set *set); + /* Flush the elements */ + void (*flush)(struct ip_set *set); + /* Expire entries before listing */ + void (*expire)(struct ip_set *set); + /* List set header data */ + int (*head)(struct ip_set *set, struct sk_buff *skb); + /* List elements */ + int (*list)(const struct ip_set *set, struct sk_buff *skb, + struct netlink_callback *cb); + + /* Return true if "b" set is the same as "a" + * according to the create set parameters */ + bool (*same_set)(const struct ip_set *a, const struct ip_set *b); +}; + +/* The core set type structure */ +struct ip_set_type { + struct list_head list; + + /* Typename */ + char name[IPSET_MAXNAMELEN]; + /* Protocol version */ + u8 protocol; + /* Set features to control swapping */ + u8 features; + /* Set type dimension */ + u8 dimension; + /* Supported family: may be AF_UNSPEC for both AF_INET/AF_INET6 */ + u8 family; + /* Type revision */ + u8 revision; + + /* Create set */ + int (*create)(struct ip_set *set, struct nlattr *tb[], u32 flags); + + /* Attribute policies */ + const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1]; + const struct nla_policy adt_policy[IPSET_ATTR_ADT_MAX + 1]; + + /* Set this to THIS_MODULE if you are a module, otherwise NULL */ + struct module *me; +}; + +/* register and unregister set type */ +extern int ip_set_type_register(struct ip_set_type *set_type); +extern void ip_set_type_unregister(struct ip_set_type *set_type); + +/* A generic IP set */ +struct ip_set { + /* The name of the set */ + char name[IPSET_MAXNAMELEN]; + /* Lock protecting the set data */ + rwlock_t lock; + /* References to the set */ + atomic_t ref; + /* The core set type */ + struct ip_set_type *type; + /* The type variant doing the real job */ + const struct ip_set_type_variant *variant; + /* The actual INET family of the set */ + u8 family; + /* The type specific data */ + void *data; +}; + +/* register and unregister set references */ +extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set); +extern void ip_set_put_byindex(ip_set_id_t index); +extern const char * ip_set_name_byindex(ip_set_id_t index); +extern ip_set_id_t ip_set_nfnl_get(const char *name); +extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index); +extern void ip_set_nfnl_put(ip_set_id_t index); + +/* API for iptables set match, and SET target */ +extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); +extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); +extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); + +/* Utility functions */ +extern void * ip_set_alloc(size_t size); +extern void ip_set_free(void *members); +extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); +extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); + +static inline int +ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) +{ + __be32 ip; + int ret = ip_set_get_ipaddr4(nla, &ip); + + if (ret) + return ret; + *ipaddr = ntohl(ip); + return 0; +} + +/* Ignore IPSET_ERR_EXIST errors if asked to do so? */ +static inline bool +ip_set_eexist(int ret, u32 flags) +{ + return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST); +} + +/* Check the NLA_F_NET_BYTEORDER flag */ +static inline bool +ip_set_attr_netorder(struct nlattr *tb[], int type) +{ + return tb[type] && (tb[type]->nla_type & NLA_F_NET_BYTEORDER); +} + +static inline bool +ip_set_optattr_netorder(struct nlattr *tb[], int type) +{ + return !tb[type] || (tb[type]->nla_type & NLA_F_NET_BYTEORDER); +} + +/* Useful converters */ +static inline u32 +ip_set_get_h32(const struct nlattr *attr) +{ + return ntohl(nla_get_be32(attr)); +} + +static inline u16 +ip_set_get_h16(const struct nlattr *attr) +{ + return ntohs(nla_get_be16(attr)); +} + +#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED) +#define ipset_nest_end(skb, start) nla_nest_end(skb, start) + +#define NLA_PUT_IPADDR4(skb, type, ipaddr) \ +do { \ + struct nlattr *__nested = ipset_nest_start(skb, type); \ + \ + if (!__nested) \ + goto nla_put_failure; \ + NLA_PUT_NET32(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); \ + ipset_nest_end(skb, __nested); \ +} while (0) + +#define NLA_PUT_IPADDR6(skb, type, ipaddrptr) \ +do { \ + struct nlattr *__nested = ipset_nest_start(skb, type); \ + \ + if (!__nested) \ + goto nla_put_failure; \ + NLA_PUT(skb, IPSET_ATTR_IPADDR_IPV6, \ + sizeof(struct in6_addr), ipaddrptr); \ + ipset_nest_end(skb, __nested); \ +} while (0) + +/* Get address from skbuff */ +static inline __be32 +ip4addr(const struct sk_buff *skb, bool src) +{ + return src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; +} + +static inline void +ip4addrptr(const struct sk_buff *skb, bool src, __be32 *addr) +{ + *addr = src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; +} + +static inline void +ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) +{ + memcpy(addr, src ? &ipv6_hdr(skb)->saddr : &ipv6_hdr(skb)->daddr, + sizeof(*addr)); +} + +/* Calculate the bytes required to store the inclusive range of a-b */ +static inline int +bitmap_bytes(u32 a, u32 b) +{ + return 4 * ((((b - a + 8) / 8) + 3) / 4); +} + +/* Interface to iptables/ip6tables */ + +#define SO_IP_SET 83 + +union ip_set_name_index { + char name[IPSET_MAXNAMELEN]; + ip_set_id_t index; +}; + +#define IP_SET_OP_GET_BYNAME 0x00000006 /* Get set index by name */ +struct ip_set_req_get_set { + unsigned op; + unsigned version; + union ip_set_name_index set; +}; + +#define IP_SET_OP_GET_BYINDEX 0x00000007 /* Get set name by index */ +/* Uses ip_set_req_get_set */ + +#define IP_SET_OP_VERSION 0x00000100 /* Ask kernel version */ +struct ip_set_req_version { + unsigned op; + unsigned version; +}; + +#endif /* __KERNEL__ */ + +#endif /*_IP_SET_H */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h new file mode 100644 index 0000000..ec9d9be --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -0,0 +1,1074 @@ +#ifndef _IP_SET_AHASH_H +#define _IP_SET_AHASH_H + +#include <linux/rcupdate.h> +#include <linux/jhash.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> + +/* Hashing which uses arrays to resolve clashing. The hash table is resized + * (doubled) when searching becomes too long. + * Internally jhash is used with the assumption that the size of the + * stored data is a multiple of sizeof(u32). If storage supports timeout, + * the timeout field must be the last one in the data structure - that field + * is ignored when computing the hash key. + * + * Readers and resizing + * + * Resizing can be triggered by userspace command only, and those + * are serialized by the nfnl mutex. During resizing the set is + * read-locked, so the only possible concurrent operations are + * the kernel side readers. Those must be protected by proper RCU locking. + */ + +/* Number of elements to store in an initial array block */ +#define AHASH_INIT_SIZE 4 +/* Max number of elements to store in an array block */ +#define AHASH_MAX_SIZE (3*4) + +/* A hash bucket */ +struct hbucket { + void *value; /* the array of the values */ + u8 size; /* size of the array */ + u8 pos; /* position of the first free entry */ +}; + +/* The hash table: the table size stored here in order to make resizing easy */ +struct htable { + u8 htable_bits; /* size of hash table == 2^htable_bits */ + struct hbucket bucket[0]; /* hashtable buckets */ +}; + +#define hbucket(h, i) &((h)->bucket[i]) + +/* Book-keeping of the prefixes added to the set */ +struct ip_set_hash_nets { + u8 cidr; /* the different cidr values in the set */ + u32 nets; /* number of elements per cidr */ +}; + +/* The generic ip_set hash structure */ +struct ip_set_hash { + struct htable *table; /* the hash table */ + u32 maxelem; /* max elements in the hash */ + u32 elements; /* current element (vs timeout) */ + u32 initval; /* random jhash init value */ + u32 timeout; /* timeout value, if enabled */ + struct timer_list gc; /* garbage collection when timeout enabled */ +#ifdef IP_SET_HASH_WITH_NETMASK + u8 netmask; /* netmask value for subnets to store */ +#endif +#ifdef IP_SET_HASH_WITH_NETS + struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */ +#endif +}; + +/* Compute htable_bits from the user input parameter hashsize */ +static u8 +htable_bits(u32 hashsize) +{ + /* Assume that hashsize == 2^htable_bits */ + u8 bits = fls(hashsize - 1); + if (jhash_size(bits) != hashsize) + /* Round up to the first 2^n value */ + bits = fls(hashsize); + + return bits; +} + +#ifdef IP_SET_HASH_WITH_NETS + +#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) + +/* Network cidr size book keeping when the hash stores different + * sized networks */ +static void +add_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +{ + u8 i; + + ++h->nets[cidr-1].nets; + + pr_debug("add_cidr added %u: %u\n", cidr, h->nets[cidr-1].nets); + + if (h->nets[cidr-1].nets > 1) + return; + + /* New cidr size */ + for (i = 0; i < host_mask && h->nets[i].cidr; i++) { + /* Add in increasing prefix order, so larger cidr first */ + if (h->nets[i].cidr < cidr) + swap(h->nets[i].cidr, cidr); + } + if (i < host_mask) + h->nets[i].cidr = cidr; +} + +static void +del_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +{ + u8 i; + + --h->nets[cidr-1].nets; + + pr_debug("del_cidr deleted %u: %u\n", cidr, h->nets[cidr-1].nets); + + if (h->nets[cidr-1].nets != 0) + return; + + /* All entries with this cidr size deleted, so cleanup h->cidr[] */ + for (i = 0; i < host_mask - 1 && h->nets[i].cidr; i++) { + if (h->nets[i].cidr == cidr) + h->nets[i].cidr = cidr = h->nets[i+1].cidr; + } + h->nets[i - 1].cidr = 0; +} +#endif + +/* Destroy the hashtable part of the set */ +static void +ahash_destroy(struct htable *t) +{ + struct hbucket *n; + u32 i; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + if (n->size) + /* FIXME: use slab cache */ + kfree(n->value); + } + + ip_set_free(t); +} + +/* Calculate the actual memory size of the set data */ +static size_t +ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 host_mask) +{ + u32 i; + struct htable *t = h->table; + size_t memsize = sizeof(*h) + + sizeof(*t) +#ifdef IP_SET_HASH_WITH_NETS + + sizeof(struct ip_set_hash_nets) * host_mask +#endif + + jhash_size(t->htable_bits) * sizeof(struct hbucket); + + for (i = 0; i < jhash_size(t->htable_bits); i++) + memsize += t->bucket[i].size * dsize; + + return memsize; +} + +/* Flush a hash type of set: destroy all elements */ +static void +ip_set_hash_flush(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct hbucket *n; + u32 i; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + if (n->size) { + n->size = n->pos = 0; + /* FIXME: use slab cache */ + kfree(n->value); + } + } +#ifdef IP_SET_HASH_WITH_NETS + memset(h->nets, 0, sizeof(struct ip_set_hash_nets) + * SET_HOST_MASK(set->family)); +#endif + h->elements = 0; +} + +/* Destroy a hash type of set */ +static void +ip_set_hash_destroy(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + + if (with_timeout(h->timeout)) + del_timer_sync(&h->gc); + + ahash_destroy(h->table); + kfree(h); + + set->data = NULL; +} + +#define HKEY(data, initval, htable_bits) \ +(jhash2((u32 *)(data), sizeof(struct type_pf_elem)/sizeof(u32), initval) \ + & jhash_mask(htable_bits)) + +#endif /* _IP_SET_AHASH_H */ + +#define CONCAT(a, b, c) a##b##c +#define TOKEN(a, b, c) CONCAT(a, b, c) + +/* Type/family dependent function prototypes */ + +#define type_pf_data_equal TOKEN(TYPE, PF, _data_equal) +#define type_pf_data_isnull TOKEN(TYPE, PF, _data_isnull) +#define type_pf_data_copy TOKEN(TYPE, PF, _data_copy) +#define type_pf_data_zero_out TOKEN(TYPE, PF, _data_zero_out) +#define type_pf_data_netmask TOKEN(TYPE, PF, _data_netmask) +#define type_pf_data_list TOKEN(TYPE, PF, _data_list) +#define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) + +#define type_pf_elem TOKEN(TYPE, PF, _elem) +#define type_pf_telem TOKEN(TYPE, PF, _telem) +#define type_pf_data_timeout TOKEN(TYPE, PF, _data_timeout) +#define type_pf_data_expired TOKEN(TYPE, PF, _data_expired) +#define type_pf_data_timeout_set TOKEN(TYPE, PF, _data_timeout_set) + +#define type_pf_elem_add TOKEN(TYPE, PF, _elem_add) +#define type_pf_add TOKEN(TYPE, PF, _add) +#define type_pf_del TOKEN(TYPE, PF, _del) +#define type_pf_test_cidrs TOKEN(TYPE, PF, _test_cidrs) +#define type_pf_test TOKEN(TYPE, PF, _test) + +#define type_pf_elem_tadd TOKEN(TYPE, PF, _elem_tadd) +#define type_pf_del_telem TOKEN(TYPE, PF, _ahash_del_telem) +#define type_pf_expire TOKEN(TYPE, PF, _expire) +#define type_pf_tadd TOKEN(TYPE, PF, _tadd) +#define type_pf_tdel TOKEN(TYPE, PF, _tdel) +#define type_pf_ttest_cidrs TOKEN(TYPE, PF, _ahash_ttest_cidrs) +#define type_pf_ttest TOKEN(TYPE, PF, _ahash_ttest) + +#define type_pf_resize TOKEN(TYPE, PF, _resize) +#define type_pf_tresize TOKEN(TYPE, PF, _tresize) +#define type_pf_flush ip_set_hash_flush +#define type_pf_destroy ip_set_hash_destroy +#define type_pf_head TOKEN(TYPE, PF, _head) +#define type_pf_list TOKEN(TYPE, PF, _list) +#define type_pf_tlist TOKEN(TYPE, PF, _tlist) +#define type_pf_same_set TOKEN(TYPE, PF, _same_set) +#define type_pf_kadt TOKEN(TYPE, PF, _kadt) +#define type_pf_uadt TOKEN(TYPE, PF, _uadt) +#define type_pf_gc TOKEN(TYPE, PF, _gc) +#define type_pf_gc_init TOKEN(TYPE, PF, _gc_init) +#define type_pf_variant TOKEN(TYPE, PF, _variant) +#define type_pf_tvariant TOKEN(TYPE, PF, _tvariant) + +/* Flavour without timeout */ + +/* Get the ith element from the array block n */ +#define ahash_data(n, i) \ + ((struct type_pf_elem *)((n)->value) + (i)) + +/* Add an element to the hash table when resizing the set: + * we spare the maintenance of the internal counters. */ +static int +type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value) +{ + if (n->pos >= n->size) { + void *tmp; + + if (n->size >= AHASH_MAX_SIZE) + /* Trigger rehashing */ + return -EAGAIN; + + tmp = kzalloc((n->size + AHASH_INIT_SIZE) + * sizeof(struct type_pf_elem), + GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (n->size) { + memcpy(tmp, n->value, + sizeof(struct type_pf_elem) * n->size); + kfree(n->value); + } + n->value = tmp; + n->size += AHASH_INIT_SIZE; + } + type_pf_data_copy(ahash_data(n, n->pos++), value); + return 0; +} + +/* Resize a hash: create a new hash table with doubling the hashsize + * and inserting the elements to it. Repeat until we succeed or + * fail due to memory pressures. */ +static int +type_pf_resize(struct ip_set *set, bool retried) +{ + struct ip_set_hash *h = set->data; + struct htable *t, *orig = h->table; + u8 htable_bits = orig->htable_bits; + const struct type_pf_elem *data; + struct hbucket *n, *m; + u32 i, j; + int ret; + +retry: + ret = 0; + htable_bits++; + pr_debug("attempt to resize set %s from %u to %u, t %p\n", + set->name, orig->htable_bits, htable_bits, orig); + if (!htable_bits) + /* In case we have plenty of memory :-) */ + return -IPSET_ERR_HASH_FULL; + t = ip_set_alloc(sizeof(*t) + + jhash_size(htable_bits) * sizeof(struct hbucket)); + if (!t) + return -ENOMEM; + t->htable_bits = htable_bits; + + read_lock_bh(&set->lock); + for (i = 0; i < jhash_size(orig->htable_bits); i++) { + n = hbucket(orig, i); + for (j = 0; j < n->pos; j++) { + data = ahash_data(n, j); + m = hbucket(t, HKEY(data, h->initval, htable_bits)); + ret = type_pf_elem_add(m, data); + if (ret < 0) { + read_unlock_bh(&set->lock); + ahash_destroy(t); + if (ret == -EAGAIN) + goto retry; + return ret; + } + } + } + + rcu_assign_pointer(h->table, t); + read_unlock_bh(&set->lock); + + /* Give time to other readers of the set */ + synchronize_rcu_bh(); + + pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, + orig->htable_bits, orig, t->htable_bits, t); + ahash_destroy(orig); + + return 0; +} + +/* Add an element to a hash and update the internal counters when succeeded, + * otherwise report the proper error code. */ +static int +type_pf_add(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i, ret = 0; + u32 key; + + if (h->elements >= h->maxelem) + return -IPSET_ERR_HASH_FULL; + + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) + if (type_pf_data_equal(ahash_data(n, i), d)) { + ret = -IPSET_ERR_EXIST; + goto out; + } + + ret = type_pf_elem_add(n, value); + if (ret != 0) + goto out; + +#ifdef IP_SET_HASH_WITH_NETS + add_cidr(h, d->cidr, HOST_MASK); +#endif + h->elements++; +out: + rcu_read_unlock_bh(); + return ret; +} + +/* Delete an element from the hash: swap it with the last element + * and free up space if possible. + */ +static int +type_pf_del(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i; + struct type_pf_elem *data; + u32 key; + + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (!type_pf_data_equal(data, d)) + continue; + if (i != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, ahash_data(n, n->pos - 1)); + + n->pos--; + h->elements--; +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, d->cidr, HOST_MASK); +#endif + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_elem), + GFP_ATOMIC); + if (!tmp) + return 0; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_elem)); + kfree(n->value); + n->value = tmp; + } + return 0; + } + + return -IPSET_ERR_EXIST; +} + +#ifdef IP_SET_HASH_WITH_NETS + +/* Special test function which takes into account the different network + * sizes added to the set */ +static int +type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct hbucket *n; + const struct type_pf_elem *data; + int i, j = 0; + u32 key; + u8 host_mask = SET_HOST_MASK(set->family); + + pr_debug("test by nets\n"); + for (; j < host_mask && h->nets[j].cidr; j++) { + type_pf_data_netmask(d, h->nets[j].cidr); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (type_pf_data_equal(data, d)) + return 1; + } + } + return 0; +} +#endif + +/* Test whether the element is added to the set */ +static int +type_pf_test(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *d = value; + struct hbucket *n; + const struct type_pf_elem *data; + int i; + u32 key; + +#ifdef IP_SET_HASH_WITH_NETS + /* If we test an IP address and not a network address, + * try all possible network sizes */ + if (d->cidr == SET_HOST_MASK(set->family)) + return type_pf_test_cidrs(set, d, timeout); +#endif + + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (type_pf_data_equal(data, d)) + return 1; + } + return 0; +} + +/* Reply a HEADER request: fill out the header part of the set */ +static int +type_pf_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct ip_set_hash *h = set->data; + struct nlattr *nested; + size_t memsize; + + read_lock_bh(&set->lock); + memsize = ahash_memsize(h, with_timeout(h->timeout) + ? sizeof(struct type_pf_telem) + : sizeof(struct type_pf_elem), + set->family == AF_INET ? 32 : 128); + read_unlock_bh(&set->lock); + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_NET32(skb, IPSET_ATTR_HASHSIZE, + htonl(jhash_size(h->table->htable_bits))); + NLA_PUT_NET32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem)); +#ifdef IP_SET_HASH_WITH_NETMASK + if (h->netmask != HOST_MASK) + NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask); +#endif + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)); + if (with_timeout(h->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +/* Reply a LIST/SAVE request: dump the elements of the specified set */ +static int +type_pf_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct ip_set_hash *h = set->data; + const struct htable *t = h->table; + struct nlattr *atd, *nested; + const struct hbucket *n; + const struct type_pf_elem *data; + u32 first = cb->args[2]; + /* We assume that one hash bucket fills into one page */ + void *incomplete; + int i; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + pr_debug("list hash set %s\n", set->name); + for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { + incomplete = skb_tail_pointer(skb); + n = hbucket(t, cb->args[2]); + pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + pr_debug("list hash %lu hbucket %p i %u, data %p\n", + cb->args[2], n, i, data); + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (cb->args[2] == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + if (type_pf_data_list(skb, data)) + goto nla_put_failure; + ipset_nest_end(skb, nested); + } + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nlmsg_trim(skb, incomplete); + ipset_nest_end(skb, atd); + if (unlikely(first == cb->args[2])) { + pr_warning("Can't list set %s: one bucket does not fit into " + "a message. Please report it!\n", set->name); + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static int +type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags); +static int +type_pf_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags); + +static const struct ip_set_type_variant type_pf_variant = { + .kadt = type_pf_kadt, + .uadt = type_pf_uadt, + .adt = { + [IPSET_ADD] = type_pf_add, + [IPSET_DEL] = type_pf_del, + [IPSET_TEST] = type_pf_test, + }, + .destroy = type_pf_destroy, + .flush = type_pf_flush, + .head = type_pf_head, + .list = type_pf_list, + .resize = type_pf_resize, + .same_set = type_pf_same_set, +}; + +/* Flavour with timeout support */ + +#define ahash_tdata(n, i) \ + (struct type_pf_elem *)((struct type_pf_telem *)((n)->value) + (i)) + +static inline u32 +type_pf_data_timeout(const struct type_pf_elem *data) +{ + const struct type_pf_telem *tdata = + (const struct type_pf_telem *) data; + + return tdata->timeout; +} + +static inline bool +type_pf_data_expired(const struct type_pf_elem *data) +{ + const struct type_pf_telem *tdata = + (const struct type_pf_telem *) data; + + return ip_set_timeout_expired(tdata->timeout); +} + +static inline void +type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) +{ + struct type_pf_telem *tdata = (struct type_pf_telem *) data; + + tdata->timeout = ip_set_timeout_set(timeout); +} + +static int +type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, + u32 timeout) +{ + struct type_pf_elem *data; + + if (n->pos >= n->size) { + void *tmp; + + if (n->size >= AHASH_MAX_SIZE) + /* Trigger rehashing */ + return -EAGAIN; + + tmp = kzalloc((n->size + AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (n->size) { + memcpy(tmp, n->value, + sizeof(struct type_pf_telem) * n->size); + kfree(n->value); + } + n->value = tmp; + n->size += AHASH_INIT_SIZE; + } + data = ahash_tdata(n, n->pos++); + type_pf_data_copy(data, value); + type_pf_data_timeout_set(data, timeout); + return 0; +} + +/* Delete expired elements from the hashtable */ +static void +type_pf_expire(struct ip_set_hash *h) +{ + struct htable *t = h->table; + struct hbucket *n; + struct type_pf_elem *data; + u32 i; + int j; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + for (j = 0; j < n->pos; j++) { + data = ahash_tdata(n, j); + if (type_pf_data_expired(data)) { + pr_debug("expired %u/%u\n", i, j); +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, data->cidr, HOST_MASK); +#endif + if (j != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, + ahash_tdata(n, n->pos - 1)); + n->pos--; + h->elements--; + } + } + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + /* Still try to delete expired elements */ + continue; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_telem)); + kfree(n->value); + n->value = tmp; + } + } +} + +static int +type_pf_tresize(struct ip_set *set, bool retried) +{ + struct ip_set_hash *h = set->data; + struct htable *t, *orig = h->table; + u8 htable_bits = orig->htable_bits; + const struct type_pf_elem *data; + struct hbucket *n, *m; + u32 i, j; + int ret; + + /* Try to cleanup once */ + if (!retried) { + i = h->elements; + write_lock_bh(&set->lock); + type_pf_expire(set->data); + write_unlock_bh(&set->lock); + if (h->elements < i) + return 0; + } + +retry: + ret = 0; + htable_bits++; + if (!htable_bits) + /* In case we have plenty of memory :-) */ + return -IPSET_ERR_HASH_FULL; + t = ip_set_alloc(sizeof(*t) + + jhash_size(htable_bits) * sizeof(struct hbucket)); + if (!t) + return -ENOMEM; + t->htable_bits = htable_bits; + + read_lock_bh(&set->lock); + for (i = 0; i < jhash_size(orig->htable_bits); i++) { + n = hbucket(orig, i); + for (j = 0; j < n->pos; j++) { + data = ahash_tdata(n, j); + m = hbucket(t, HKEY(data, h->initval, htable_bits)); + ret = type_pf_elem_tadd(m, data, + type_pf_data_timeout(data)); + if (ret < 0) { + read_unlock_bh(&set->lock); + ahash_destroy(t); + if (ret == -EAGAIN) + goto retry; + return ret; + } + } + } + + rcu_assign_pointer(h->table, t); + read_unlock_bh(&set->lock); + + /* Give time to other readers of the set */ + synchronize_rcu_bh(); + + ahash_destroy(orig); + + return 0; +} + +static int +type_pf_tadd(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + struct type_pf_elem *data; + int ret = 0, i, j = AHASH_MAX_SIZE + 1; + u32 key; + + if (h->elements >= h->maxelem) + /* FIXME: when set is full, we slow down here */ + type_pf_expire(h); + if (h->elements >= h->maxelem) + return -IPSET_ERR_HASH_FULL; + + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) { + if (type_pf_data_expired(data)) + j = i; + else { + ret = -IPSET_ERR_EXIST; + goto out; + } + } else if (j == AHASH_MAX_SIZE + 1 && + type_pf_data_expired(data)) + j = i; + } + if (j != AHASH_MAX_SIZE + 1) { + data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, data->cidr, HOST_MASK); + add_cidr(h, d->cidr, HOST_MASK); +#endif + type_pf_data_copy(data, d); + type_pf_data_timeout_set(data, timeout); + goto out; + } + ret = type_pf_elem_tadd(n, d, timeout); + if (ret != 0) + goto out; + +#ifdef IP_SET_HASH_WITH_NETS + add_cidr(h, d->cidr, HOST_MASK); +#endif + h->elements++; +out: + rcu_read_unlock_bh(); + return ret; +} + +static int +type_pf_tdel(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i, ret = 0; + struct type_pf_elem *data; + u32 key; + + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (!type_pf_data_equal(data, d)) + continue; + if (type_pf_data_expired(data)) + ret = -IPSET_ERR_EXIST; + if (i != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, ahash_tdata(n, n->pos - 1)); + + n->pos--; + h->elements--; +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, d->cidr, HOST_MASK); +#endif + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + return 0; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_telem)); + kfree(n->value); + n->value = tmp; + } + return 0; + } + + return -IPSET_ERR_EXIST; +} + +#ifdef IP_SET_HASH_WITH_NETS +static int +type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *data; + struct hbucket *n; + int i, j = 0; + u32 key; + u8 host_mask = SET_HOST_MASK(set->family); + + for (; j < host_mask && h->nets[j].cidr; j++) { + type_pf_data_netmask(d, h->nets[j].cidr); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) + return !type_pf_data_expired(data); + } + } + return 0; +} +#endif + +static int +type_pf_ttest(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *data, *d = value; + struct hbucket *n; + int i; + u32 key; + +#ifdef IP_SET_HASH_WITH_NETS + if (d->cidr == SET_HOST_MASK(set->family)) + return type_pf_ttest_cidrs(set, d, timeout); +#endif + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) + return !type_pf_data_expired(data); + } + return 0; +} + +static int +type_pf_tlist(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct ip_set_hash *h = set->data; + const struct htable *t = h->table; + struct nlattr *atd, *nested; + const struct hbucket *n; + const struct type_pf_elem *data; + u32 first = cb->args[2]; + /* We assume that one hash bucket fills into one page */ + void *incomplete; + int i; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { + incomplete = skb_tail_pointer(skb); + n = hbucket(t, cb->args[2]); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + pr_debug("list %p %u\n", n, i); + if (type_pf_data_expired(data)) + continue; + pr_debug("do list %p %u\n", n, i); + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (cb->args[2] == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + if (type_pf_data_tlist(skb, data)) + goto nla_put_failure; + ipset_nest_end(skb, nested); + } + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nlmsg_trim(skb, incomplete); + ipset_nest_end(skb, atd); + if (unlikely(first == cb->args[2])) { + pr_warning("Can't list set %s: one bucket does not fit into " + "a message. Please report it!\n", set->name); + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static const struct ip_set_type_variant type_pf_tvariant = { + .kadt = type_pf_kadt, + .uadt = type_pf_uadt, + .adt = { + [IPSET_ADD] = type_pf_tadd, + [IPSET_DEL] = type_pf_tdel, + [IPSET_TEST] = type_pf_ttest, + }, + .destroy = type_pf_destroy, + .flush = type_pf_flush, + .head = type_pf_head, + .list = type_pf_tlist, + .resize = type_pf_tresize, + .same_set = type_pf_same_set, +}; + +static void +type_pf_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct ip_set_hash *h = set->data; + + pr_debug("called\n"); + write_lock_bh(&set->lock); + type_pf_expire(h); + write_unlock_bh(&set->lock); + + h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; + add_timer(&h->gc); +} + +static void +type_pf_gc_init(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + + init_timer(&h->gc); + h->gc.data = (unsigned long) set; + h->gc.function = type_pf_gc; + h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; + add_timer(&h->gc); + pr_debug("gc initialized, run in every %u\n", + IPSET_GC_PERIOD(h->timeout)); +} + +#undef type_pf_data_equal +#undef type_pf_data_isnull +#undef type_pf_data_copy +#undef type_pf_data_zero_out +#undef type_pf_data_list +#undef type_pf_data_tlist + +#undef type_pf_elem +#undef type_pf_telem +#undef type_pf_data_timeout +#undef type_pf_data_expired +#undef type_pf_data_netmask +#undef type_pf_data_timeout_set + +#undef type_pf_elem_add +#undef type_pf_add +#undef type_pf_del +#undef type_pf_test_cidrs +#undef type_pf_test + +#undef type_pf_elem_tadd +#undef type_pf_expire +#undef type_pf_tadd +#undef type_pf_tdel +#undef type_pf_ttest_cidrs +#undef type_pf_ttest + +#undef type_pf_resize +#undef type_pf_tresize +#undef type_pf_flush +#undef type_pf_destroy +#undef type_pf_head +#undef type_pf_list +#undef type_pf_tlist +#undef type_pf_same_set +#undef type_pf_kadt +#undef type_pf_uadt +#undef type_pf_gc +#undef type_pf_gc_init +#undef type_pf_variant +#undef type_pf_tvariant diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h new file mode 100644 index 0000000..61a9e87 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -0,0 +1,31 @@ +#ifndef __IP_SET_BITMAP_H +#define __IP_SET_BITMAP_H + +/* Bitmap type specific error codes */ +enum { + /* The element is out of the range of the set */ + IPSET_ERR_BITMAP_RANGE = IPSET_ERR_TYPE_SPECIFIC, + /* The range exceeds the size limit of the set type */ + IPSET_ERR_BITMAP_RANGE_SIZE, +}; + +#ifdef __KERNEL__ +#define IPSET_BITMAP_MAX_RANGE 0x0000FFFF + +/* Common functions */ + +static inline u32 +range_to_mask(u32 from, u32 to, u8 *bits) +{ + u32 mask = 0xFFFFFFFE; + + *bits = 32; + while (--(*bits) > 0 && mask && (to & mask) != from) + mask <<= 1; + + return mask; +} + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_BITMAP_H */ diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h new file mode 100644 index 0000000..3882a81 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -0,0 +1,21 @@ +#ifndef _IP_SET_GETPORT_H +#define _IP_SET_GETPORT_H + +extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto); + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +extern bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto); +#else +static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto) +{ + return false; +} +#endif + +extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, + __be16 *port); + +#endif /*_IP_SET_GETPORT_H*/ diff --git a/include/linux/netfilter/ipset/ip_set_hash.h b/include/linux/netfilter/ipset/ip_set_hash.h new file mode 100644 index 0000000..b86f15c --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_hash.h @@ -0,0 +1,26 @@ +#ifndef __IP_SET_HASH_H +#define __IP_SET_HASH_H + +/* Hash type specific error codes */ +enum { + /* Hash is full */ + IPSET_ERR_HASH_FULL = IPSET_ERR_TYPE_SPECIFIC, + /* Null-valued element */ + IPSET_ERR_HASH_ELEM, + /* Invalid protocol */ + IPSET_ERR_INVALID_PROTO, + /* Protocol missing but must be specified */ + IPSET_ERR_MISSING_PROTO, +}; + +#ifdef __KERNEL__ + +#define IPSET_DEFAULT_HASHSIZE 1024 +#define IPSET_MIMINAL_HASHSIZE 64 +#define IPSET_DEFAULT_MAXELEM 65536 +#define IPSET_DEFAULT_PROBES 4 +#define IPSET_DEFAULT_RESIZE 100 + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_HASH_H */ diff --git a/include/linux/netfilter/ipset/ip_set_list.h b/include/linux/netfilter/ipset/ip_set_list.h new file mode 100644 index 0000000..40a63f3 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_list.h @@ -0,0 +1,27 @@ +#ifndef __IP_SET_LIST_H +#define __IP_SET_LIST_H + +/* List type specific error codes */ +enum { + /* Set name to be added/deleted/tested does not exist. */ + IPSET_ERR_NAME = IPSET_ERR_TYPE_SPECIFIC, + /* list:set type is not permitted to add */ + IPSET_ERR_LOOP, + /* Missing reference set */ + IPSET_ERR_BEFORE, + /* Reference set does not exist */ + IPSET_ERR_NAMEREF, + /* Set is full */ + IPSET_ERR_LIST_FULL, + /* Reference set is not added to the set */ + IPSET_ERR_REF_EXIST, +}; + +#ifdef __KERNEL__ + +#define IP_SET_LIST_DEFAULT_SIZE 8 +#define IP_SET_LIST_MIN_SIZE 4 + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_LIST_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h new file mode 100644 index 0000000..9f30c5f --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -0,0 +1,127 @@ +#ifndef _IP_SET_TIMEOUT_H +#define _IP_SET_TIMEOUT_H + +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifdef __KERNEL__ + +/* How often should the gc be run by default */ +#define IPSET_GC_TIME (3 * 60) + +/* Timeout period depending on the timeout value of the given set */ +#define IPSET_GC_PERIOD(timeout) \ + ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) + +/* Set is defined without timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX + +#define with_timeout(timeout) ((timeout) != IPSET_NO_TIMEOUT) + +static inline unsigned int +ip_set_timeout_uget(struct nlattr *tb) +{ + unsigned int timeout = ip_set_get_h32(tb); + + /* Userspace supplied TIMEOUT parameter: adjust crazy size */ + return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout; +} + +#ifdef IP_SET_BITMAP_TIMEOUT + +/* Bitmap specific timeout constants and macros for the entries */ + +/* Bitmap entry is unset */ +#define IPSET_ELEM_UNSET 0 +/* Bitmap entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT (UINT_MAX/2) + +static inline bool +ip_set_timeout_test(unsigned long timeout) +{ + return timeout != IPSET_ELEM_UNSET && + (timeout == IPSET_ELEM_PERMANENT || + time_after(timeout, jiffies)); +} + +static inline bool +ip_set_timeout_expired(unsigned long timeout) +{ + return timeout != IPSET_ELEM_UNSET && + timeout != IPSET_ELEM_PERMANENT && + time_before(timeout, jiffies); +} + +static inline unsigned long +ip_set_timeout_set(u32 timeout) +{ + unsigned long t; + + if (!timeout) + return IPSET_ELEM_PERMANENT; + + t = timeout * HZ + jiffies; + if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT) + /* Bingo! */ + t++; + + return t; +} + +static inline u32 +ip_set_timeout_get(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ; +} + +#else + +/* Hash specific timeout constants and macros for the entries */ + +/* Hash entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 + +static inline bool +ip_set_timeout_test(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT || + time_after(timeout, jiffies); +} + +static inline bool +ip_set_timeout_expired(unsigned long timeout) +{ + return timeout != IPSET_ELEM_PERMANENT && + time_before(timeout, jiffies); +} + +static inline unsigned long +ip_set_timeout_set(u32 timeout) +{ + unsigned long t; + + if (!timeout) + return IPSET_ELEM_PERMANENT; + + t = timeout * HZ + jiffies; + if (t == IPSET_ELEM_PERMANENT) + /* Bingo! :-) */ + t++; + + return t; +} + +static inline u32 +ip_set_timeout_get(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ; +} +#endif /* ! IP_SET_BITMAP_TIMEOUT */ + +#endif /* __KERNEL__ */ + +#endif /* _IP_SET_TIMEOUT_H */ diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h new file mode 100644 index 0000000..0e1fb50 --- /dev/null +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -0,0 +1,35 @@ +#ifndef _PFXLEN_H +#define _PFXLEN_H + +#include <asm/byteorder.h> +#include <linux/netfilter.h> + +/* Prefixlen maps, by Jan Engelhardt */ +extern const union nf_inet_addr ip_set_netmask_map[]; +extern const union nf_inet_addr ip_set_hostmask_map[]; + +static inline __be32 +ip_set_netmask(u8 pfxlen) +{ + return ip_set_netmask_map[pfxlen].ip; +} + +static inline const __be32 * +ip_set_netmask6(u8 pfxlen) +{ + return &ip_set_netmask_map[pfxlen].ip6[0]; +} + +static inline u32 +ip_set_hostmask(u8 pfxlen) +{ + return (__force u32) ip_set_hostmask_map[pfxlen].ip; +} + +static inline const __be32 * +ip_set_hostmask6(u8 pfxlen) +{ + return &ip_set_hostmask_map[pfxlen].ip6[0]; +} + +#endif /*_PFXLEN_H */ diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h new file mode 100644 index 0000000..064bc63 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -0,0 +1,9 @@ +#ifndef _NF_CONNTRACK_SNMP_H +#define _NF_CONNTRACK_SNMP_H + +extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo); + +#endif /* _NF_CONNTRACK_SNMP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 361d6b5..2b11fc1 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -47,7 +47,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_QUEUE 3 #define NFNL_SUBSYS_ULOG 4 #define NFNL_SUBSYS_OSF 5 -#define NFNL_SUBSYS_COUNT 6 +#define NFNL_SUBSYS_IPSET 6 +#define NFNL_SUBSYS_COUNT 7 #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 19711e3..debf1ae 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -42,6 +42,7 @@ enum ctattr_type { CTA_SECMARK, /* obsolete */ CTA_ZONE, CTA_SECCTX, + CTA_TIMESTAMP, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -127,6 +128,14 @@ enum ctattr_counters { }; #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) +enum ctattr_tstamp { + CTA_TIMESTAMP_UNSPEC, + CTA_TIMESTAMP_START, + CTA_TIMESTAMP_STOP, + __CTA_TIMESTAMP_MAX +}; +#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1) + enum ctattr_nat { CTA_NAT_UNSPEC, CTA_NAT_MINIP, diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 6712e71..3721952 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -611,8 +611,9 @@ struct _compat_xt_align { extern void xt_compat_lock(u_int8_t af); extern void xt_compat_unlock(u_int8_t af); -extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta); +extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); extern void xt_compat_flush_offsets(u_int8_t af); +extern void xt_compat_init_offsets(u_int8_t af, unsigned int number); extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset); extern int xt_compat_match_offset(const struct xt_match *match); diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h new file mode 100644 index 0000000..38751d2 --- /dev/null +++ b/include/linux/netfilter/xt_AUDIT.h @@ -0,0 +1,30 @@ +/* + * Header file for iptables xt_AUDIT target + * + * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> + * (C) 2010-2011 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _XT_AUDIT_TARGET_H +#define _XT_AUDIT_TARGET_H + +#include <linux/types.h> + +enum { + XT_AUDIT_TYPE_ACCEPT = 0, + XT_AUDIT_TYPE_DROP, + XT_AUDIT_TYPE_REJECT, + __XT_AUDIT_TYPE_MAX, +}; + +#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1) + +struct xt_audit_info { + __u8 type; /* XT_AUDIT_TYPE_* */ +}; + +#endif /* _XT_AUDIT_TARGET_H */ diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h index 1b56410..b56e768 100644 --- a/include/linux/netfilter/xt_CT.h +++ b/include/linux/netfilter/xt_CT.h @@ -1,14 +1,16 @@ #ifndef _XT_CT_H #define _XT_CT_H +#include <linux/types.h> + #define XT_CT_NOTRACK 0x1 struct xt_ct_target_info { - u_int16_t flags; - u_int16_t zone; - u_int32_t ct_events; - u_int32_t exp_events; - char helper[16]; + __u16 flags; + __u16 zone; + __u32 ct_events; + __u32 exp_events; + char helper[16]; /* Used internally by the kernel */ struct nf_conn *ct __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h index 2584f4a..9eafdbb 100644 --- a/include/linux/netfilter/xt_NFQUEUE.h +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 { __u16 queues_total; }; +struct xt_NFQ_info_v2 { + __u16 queuenum; + __u16 queues_total; + __u16 bypass; +}; + #endif /* _XT_NFQ_TARGET_H */ diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h index 2db5432..7157318 100644 --- a/include/linux/netfilter/xt_TCPOPTSTRIP.h +++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h @@ -1,13 +1,15 @@ #ifndef _XT_TCPOPTSTRIP_H #define _XT_TCPOPTSTRIP_H +#include <linux/types.h> + #define tcpoptstrip_set_bit(bmap, idx) \ (bmap[(idx) >> 5] |= 1U << (idx & 31)) #define tcpoptstrip_test_bit(bmap, idx) \ (((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0) struct xt_tcpoptstrip_target_info { - u_int32_t strip_bmap[8]; + __u32 strip_bmap[8]; }; #endif /* _XT_TCPOPTSTRIP_H */ diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h index 3f3d693..902043c 100644 --- a/include/linux/netfilter/xt_TPROXY.h +++ b/include/linux/netfilter/xt_TPROXY.h @@ -1,19 +1,21 @@ #ifndef _XT_TPROXY_H #define _XT_TPROXY_H +#include <linux/types.h> + /* TPROXY target is capable of marking the packet to perform * redirection. We can get rid of that whenever we get support for * mutliple targets in the same rule. */ struct xt_tproxy_target_info { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; __be32 laddr; __be16 lport; }; struct xt_tproxy_target_info_v1 { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; union nf_inet_addr laddr; __be16 lport; }; diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h index 8866826..9b883c8 100644 --- a/include/linux/netfilter/xt_cluster.h +++ b/include/linux/netfilter/xt_cluster.h @@ -1,15 +1,17 @@ #ifndef _XT_CLUSTER_MATCH_H #define _XT_CLUSTER_MATCH_H +#include <linux/types.h> + enum xt_cluster_flags { XT_CLUSTER_F_INV = (1 << 0) }; struct xt_cluster_match_info { - u_int32_t total_nodes; - u_int32_t node_mask; - u_int32_t hash_seed; - u_int32_t flags; + __u32 total_nodes; + __u32 node_mask; + __u32 hash_seed; + __u32 flags; }; #define XT_CLUSTER_NODES_MAX 32 diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h index eacfedc..0ea5e79 100644 --- a/include/linux/netfilter/xt_comment.h +++ b/include/linux/netfilter/xt_comment.h @@ -4,7 +4,7 @@ #define XT_MAX_COMMENT_LEN 256 struct xt_comment_info { - unsigned char comment[XT_MAX_COMMENT_LEN]; + char comment[XT_MAX_COMMENT_LEN]; }; #endif /* XT_COMMENT_H */ diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index 7e3284b..0ca66e9 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -1,8 +1,15 @@ #ifndef _XT_CONNLIMIT_H #define _XT_CONNLIMIT_H +#include <linux/types.h> + struct xt_connlimit_data; +enum { + XT_CONNLIMIT_INVERT = 1 << 0, + XT_CONNLIMIT_DADDR = 1 << 1, +}; + struct xt_connlimit_info { union { union nf_inet_addr mask; @@ -13,7 +20,14 @@ struct xt_connlimit_info { }; #endif }; - unsigned int limit, inverse; + unsigned int limit; + union { + /* revision 0 */ + unsigned int inverse; + + /* revision 1 */ + __u32 flags; + }; /* Used internally by the kernel */ struct xt_connlimit_data *data __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 54f47a2..74b904d 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 { __u16 state_mask, status_mask; }; +struct xt_conntrack_mtinfo3 { + union nf_inet_addr origsrc_addr, origsrc_mask; + union nf_inet_addr origdst_addr, origdst_mask; + union nf_inet_addr replsrc_addr, replsrc_mask; + union nf_inet_addr repldst_addr, repldst_mask; + __u32 expires_min, expires_max; + __u16 l4proto; + __u16 origsrc_port, origdst_port; + __u16 replsrc_port, repldst_port; + __u16 match_flags, invert_flags; + __u16 state_mask, status_mask; + __u16 origsrc_port_high, origdst_port_high; + __u16 replsrc_port_high, repldst_port_high; +}; + #endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_devgroup.h b/include/linux/netfilter/xt_devgroup.h new file mode 100644 index 0000000..1babde0 --- /dev/null +++ b/include/linux/netfilter/xt_devgroup.h @@ -0,0 +1,21 @@ +#ifndef _XT_DEVGROUP_H +#define _XT_DEVGROUP_H + +#include <linux/types.h> + +enum xt_devgroup_flags { + XT_DEVGROUP_MATCH_SRC = 0x1, + XT_DEVGROUP_INVERT_SRC = 0x2, + XT_DEVGROUP_MATCH_DST = 0x4, + XT_DEVGROUP_INVERT_DST = 0x8, +}; + +struct xt_devgroup_info { + __u32 flags; + __u32 src_group; + __u32 src_mask; + __u32 dst_group; + __u32 dst_mask; +}; + +#endif /* _XT_DEVGROUP_H */ diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h index b0d28c6..ca6e03e 100644 --- a/include/linux/netfilter/xt_quota.h +++ b/include/linux/netfilter/xt_quota.h @@ -1,6 +1,8 @@ #ifndef _XT_QUOTA_H #define _XT_QUOTA_H +#include <linux/types.h> + enum xt_quota_flags { XT_QUOTA_INVERT = 0x1, }; @@ -9,9 +11,9 @@ enum xt_quota_flags { struct xt_quota_priv; struct xt_quota_info { - u_int32_t flags; - u_int32_t pad; - aligned_u64 quota; + __u32 flags; + __u32 pad; + aligned_u64 quota; /* Used internally by the kernel */ struct xt_quota_priv *master; diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h new file mode 100644 index 0000000..081f1de --- /dev/null +++ b/include/linux/netfilter/xt_set.h @@ -0,0 +1,56 @@ +#ifndef _XT_SET_H +#define _XT_SET_H + +#include <linux/types.h> +#include <linux/netfilter/ipset/ip_set.h> + +/* Revision 0 interface: backward compatible with netfilter/iptables */ + +/* + * Option flags for kernel operations (xt_set_info_v0) + */ +#define IPSET_SRC 0x01 /* Source match/add */ +#define IPSET_DST 0x02 /* Destination match/add */ +#define IPSET_MATCH_INV 0x04 /* Inverse matching */ + +struct xt_set_info_v0 { + ip_set_id_t index; + union { + __u32 flags[IPSET_DIM_MAX + 1]; + struct { + __u32 __flags[IPSET_DIM_MAX]; + __u8 dim; + __u8 flags; + } compat; + } u; +}; + +/* match and target infos */ +struct xt_set_info_match_v0 { + struct xt_set_info_v0 match_set; +}; + +struct xt_set_info_target_v0 { + struct xt_set_info_v0 add_set; + struct xt_set_info_v0 del_set; +}; + +/* Revision 1: current interface to netfilter/iptables */ + +struct xt_set_info { + ip_set_id_t index; + __u8 dim; + __u8 flags; +}; + +/* match and target infos */ +struct xt_set_info_match { + struct xt_set_info match_set; +}; + +struct xt_set_info_target { + struct xt_set_info add_set; + struct xt_set_info del_set; +}; + +#endif /*_XT_SET_H*/ diff --git a/include/linux/netfilter/xt_socket.h b/include/linux/netfilter/xt_socket.h index 6f475b8..26d7217 100644 --- a/include/linux/netfilter/xt_socket.h +++ b/include/linux/netfilter/xt_socket.h @@ -1,6 +1,8 @@ #ifndef _XT_SOCKET_H #define _XT_SOCKET_H +#include <linux/types.h> + enum { XT_SOCKET_TRANSPARENT = 1 << 0, }; diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h index 14b6df4..7c37fac 100644 --- a/include/linux/netfilter/xt_time.h +++ b/include/linux/netfilter/xt_time.h @@ -1,14 +1,16 @@ #ifndef _XT_TIME_H #define _XT_TIME_H 1 +#include <linux/types.h> + struct xt_time_info { - u_int32_t date_start; - u_int32_t date_stop; - u_int32_t daytime_start; - u_int32_t daytime_stop; - u_int32_t monthdays_match; - u_int8_t weekdays_match; - u_int8_t flags; + __u32 date_start; + __u32 date_stop; + __u32 daytime_start; + __u32 daytime_stop; + __u32 monthdays_match; + __u8 weekdays_match; + __u8 flags; }; enum { diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h index 9947f56..04d1bfe 100644 --- a/include/linux/netfilter/xt_u32.h +++ b/include/linux/netfilter/xt_u32.h @@ -1,6 +1,8 @@ #ifndef _XT_U32_H #define _XT_U32_H 1 +#include <linux/types.h> + enum xt_u32_ops { XT_U32_AND, XT_U32_LEFTSH, @@ -9,13 +11,13 @@ enum xt_u32_ops { }; struct xt_u32_location_element { - u_int32_t number; - u_int8_t nextop; + __u32 number; + __u8 nextop; }; struct xt_u32_value_element { - u_int32_t min; - u_int32_t max; + __u32 min; + __u32 max; }; /* @@ -27,14 +29,14 @@ struct xt_u32_value_element { struct xt_u32_test { struct xt_u32_location_element location[XT_U32_MAXSIZE+1]; struct xt_u32_value_element value[XT_U32_MAXSIZE+1]; - u_int8_t nnums; - u_int8_t nvalues; + __u8 nnums; + __u8 nvalues; }; struct xt_u32 { struct xt_u32_test tests[XT_U32_MAXSIZE+1]; - u_int8_t ntests; - u_int8_t invert; + __u8 ntests; + __u8 invert; }; #endif /* _XT_U32_H */ diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h index c73ef0b..be5be15 100644 --- a/include/linux/netfilter_bridge/ebt_802_3.h +++ b/include/linux/netfilter_bridge/ebt_802_3.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_802_3_H #define __LINUX_BRIDGE_EBT_802_3_H +#include <linux/types.h> + #define EBT_802_3_SAP 0x01 #define EBT_802_3_TYPE 0x02 @@ -24,24 +26,24 @@ /* ui has one byte ctrl, ni has two */ struct hdr_ui { - uint8_t dsap; - uint8_t ssap; - uint8_t ctrl; - uint8_t orig[3]; + __u8 dsap; + __u8 ssap; + __u8 ctrl; + __u8 orig[3]; __be16 type; }; struct hdr_ni { - uint8_t dsap; - uint8_t ssap; + __u8 dsap; + __u8 ssap; __be16 ctrl; - uint8_t orig[3]; + __u8 orig[3]; __be16 type; }; struct ebt_802_3_hdr { - uint8_t daddr[6]; - uint8_t saddr[6]; + __u8 daddr[6]; + __u8 saddr[6]; __be16 len; union { struct hdr_ui ui; @@ -59,10 +61,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) #endif struct ebt_802_3_info { - uint8_t sap; + __u8 sap; __be16 type; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h index 0009558..bd4e3ad 100644 --- a/include/linux/netfilter_bridge/ebt_among.h +++ b/include/linux/netfilter_bridge/ebt_among.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_AMONG_H #define __LINUX_BRIDGE_EBT_AMONG_H +#include <linux/types.h> + #define EBT_AMONG_DST 0x01 #define EBT_AMONG_SRC 0x02 @@ -30,7 +32,7 @@ */ struct ebt_mac_wormhash_tuple { - uint32_t cmp[2]; + __u32 cmp[2]; __be32 ip; }; diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h index cbf4843..522f3e4 100644 --- a/include/linux/netfilter_bridge/ebt_arp.h +++ b/include/linux/netfilter_bridge/ebt_arp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_ARP_H #define __LINUX_BRIDGE_EBT_ARP_H +#include <linux/types.h> + #define EBT_ARP_OPCODE 0x01 #define EBT_ARP_HTYPE 0x02 #define EBT_ARP_PTYPE 0x04 @@ -27,8 +29,8 @@ struct ebt_arp_info unsigned char smmsk[ETH_ALEN]; unsigned char dmaddr[ETH_ALEN]; unsigned char dmmsk[ETH_ALEN]; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h index 6a708fb..c4bbc41 100644 --- a/include/linux/netfilter_bridge/ebt_ip.h +++ b/include/linux/netfilter_bridge/ebt_ip.h @@ -15,6 +15,8 @@ #ifndef __LINUX_BRIDGE_EBT_IP_H #define __LINUX_BRIDGE_EBT_IP_H +#include <linux/types.h> + #define EBT_IP_SOURCE 0x01 #define EBT_IP_DEST 0x02 #define EBT_IP_TOS 0x04 @@ -31,12 +33,12 @@ struct ebt_ip_info { __be32 daddr; __be32 smsk; __be32 dmsk; - uint8_t tos; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tos; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + __u16 sport[2]; + __u16 dport[2]; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h index e5de987..42b8896 100644 --- a/include/linux/netfilter_bridge/ebt_ip6.h +++ b/include/linux/netfilter_bridge/ebt_ip6.h @@ -12,14 +12,19 @@ #ifndef __LINUX_BRIDGE_EBT_IP6_H #define __LINUX_BRIDGE_EBT_IP6_H +#include <linux/types.h> + #define EBT_IP6_SOURCE 0x01 #define EBT_IP6_DEST 0x02 #define EBT_IP6_TCLASS 0x04 #define EBT_IP6_PROTO 0x08 #define EBT_IP6_SPORT 0x10 #define EBT_IP6_DPORT 0x20 +#define EBT_IP6_ICMP6 0x40 + #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\ - EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT) + EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \ + EBT_IP6_ICMP6) #define EBT_IP6_MATCH "ip6" /* the same values are used for the invflags */ @@ -28,12 +33,18 @@ struct ebt_ip6_info { struct in6_addr daddr; struct in6_addr smsk; struct in6_addr dmsk; - uint8_t tclass; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tclass; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + union { + __u16 sport[2]; + __u8 icmpv6_type[2]; + }; + union { + __u16 dport[2]; + __u8 icmpv6_code[2]; + }; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h index 4bf76b7..66d80b3 100644 --- a/include/linux/netfilter_bridge/ebt_limit.h +++ b/include/linux/netfilter_bridge/ebt_limit.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LIMIT_H #define __LINUX_BRIDGE_EBT_LIMIT_H +#include <linux/types.h> + #define EBT_LIMIT_MATCH "limit" /* timings are in milliseconds. */ @@ -10,13 +12,13 @@ seconds, or one every 59 hours. */ struct ebt_limit_info { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* Used internally by the kernel */ unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; + __u32 credit; + __u32 credit_cap, cost; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h index cc2cdfb..7e7f1d1 100644 --- a/include/linux/netfilter_bridge/ebt_log.h +++ b/include/linux/netfilter_bridge/ebt_log.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LOG_H #define __LINUX_BRIDGE_EBT_LOG_H +#include <linux/types.h> + #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */ #define EBT_LOG_ARP 0x02 #define EBT_LOG_NFLOG 0x04 @@ -10,9 +12,9 @@ #define EBT_LOG_WATCHER "log" struct ebt_log_info { - uint8_t loglevel; - uint8_t prefix[EBT_LOG_PREFIX_SIZE]; - uint32_t bitmask; + __u8 loglevel; + __u8 prefix[EBT_LOG_PREFIX_SIZE]; + __u32 bitmask; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h index 9ceb10e..410f9e5 100644 --- a/include/linux/netfilter_bridge/ebt_mark_m.h +++ b/include/linux/netfilter_bridge/ebt_mark_m.h @@ -1,13 +1,15 @@ #ifndef __LINUX_BRIDGE_EBT_MARK_M_H #define __LINUX_BRIDGE_EBT_MARK_M_H +#include <linux/types.h> + #define EBT_MARK_AND 0x01 #define EBT_MARK_OR 0x02 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR) struct ebt_mark_m_info { unsigned long mark, mask; - uint8_t invert; - uint8_t bitmask; + __u8 invert; + __u8 bitmask; }; #define EBT_MARK_MATCH "mark_m" diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h index 0528178..df829fc 100644 --- a/include/linux/netfilter_bridge/ebt_nflog.h +++ b/include/linux/netfilter_bridge/ebt_nflog.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_NFLOG_H #define __LINUX_BRIDGE_EBT_NFLOG_H +#include <linux/types.h> + #define EBT_NFLOG_MASK 0x0 #define EBT_NFLOG_PREFIX_SIZE 64 @@ -10,11 +12,11 @@ #define EBT_NFLOG_DEFAULT_THRESHOLD 1 struct ebt_nflog_info { - u_int32_t len; - u_int16_t group; - u_int16_t threshold; - u_int16_t flags; - u_int16_t pad; + __u32 len; + __u16 group; + __u16 threshold; + __u16 flags; + __u16 pad; char prefix[EBT_NFLOG_PREFIX_SIZE]; }; diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h index 51a7998..c241bad 100644 --- a/include/linux/netfilter_bridge/ebt_pkttype.h +++ b/include/linux/netfilter_bridge/ebt_pkttype.h @@ -1,9 +1,11 @@ #ifndef __LINUX_BRIDGE_EBT_PKTTYPE_H #define __LINUX_BRIDGE_EBT_PKTTYPE_H +#include <linux/types.h> + struct ebt_pkttype_info { - uint8_t pkt_type; - uint8_t invert; + __u8 pkt_type; + __u8 invert; }; #define EBT_PKTTYPE_MATCH "pkttype" diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h index e503a0a..1025b9f 100644 --- a/include/linux/netfilter_bridge/ebt_stp.h +++ b/include/linux/netfilter_bridge/ebt_stp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_STP_H #define __LINUX_BRIDGE_EBT_STP_H +#include <linux/types.h> + #define EBT_STP_TYPE 0x0001 #define EBT_STP_FLAGS 0x0002 @@ -21,24 +23,24 @@ #define EBT_STP_MATCH "stp" struct ebt_stp_config_info { - uint8_t flags; - uint16_t root_priol, root_priou; + __u8 flags; + __u16 root_priol, root_priou; char root_addr[6], root_addrmsk[6]; - uint32_t root_costl, root_costu; - uint16_t sender_priol, sender_priou; + __u32 root_costl, root_costu; + __u16 sender_priol, sender_priou; char sender_addr[6], sender_addrmsk[6]; - uint16_t portl, portu; - uint16_t msg_agel, msg_ageu; - uint16_t max_agel, max_ageu; - uint16_t hello_timel, hello_timeu; - uint16_t forward_delayl, forward_delayu; + __u16 portl, portu; + __u16 msg_agel, msg_ageu; + __u16 max_agel, max_ageu; + __u16 hello_timel, hello_timeu; + __u16 forward_delayl, forward_delayu; }; struct ebt_stp_info { - uint8_t type; + __u8 type; struct ebt_stp_config_info config; - uint16_t bitmask; - uint16_t invflags; + __u16 bitmask; + __u16 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h index b677e26..89a6bec 100644 --- a/include/linux/netfilter_bridge/ebt_ulog.h +++ b/include/linux/netfilter_bridge/ebt_ulog.h @@ -1,6 +1,8 @@ #ifndef _EBT_ULOG_H #define _EBT_ULOG_H +#include <linux/types.h> + #define EBT_ULOG_DEFAULT_NLGROUP 0 #define EBT_ULOG_DEFAULT_QTHRESHOLD 1 #define EBT_ULOG_MAXNLGROUPS 32 /* hardcoded netlink max */ @@ -10,7 +12,7 @@ #define EBT_ULOG_VERSION 1 struct ebt_ulog_info { - uint32_t nlgroup; + __u32 nlgroup; unsigned int cprange; unsigned int qthreshold; char prefix[EBT_ULOG_PREFIX_LEN]; diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h index 1d98be4..967d1d5 100644 --- a/include/linux/netfilter_bridge/ebt_vlan.h +++ b/include/linux/netfilter_bridge/ebt_vlan.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_VLAN_H #define __LINUX_BRIDGE_EBT_VLAN_H +#include <linux/types.h> + #define EBT_VLAN_ID 0x01 #define EBT_VLAN_PRIO 0x02 #define EBT_VLAN_ENCAP 0x04 @@ -8,12 +10,12 @@ #define EBT_VLAN_MATCH "vlan" struct ebt_vlan_info { - uint16_t id; /* VLAN ID {1-4095} */ - uint8_t prio; /* VLAN User Priority {0-7} */ + __u16 id; /* VLAN ID {1-4095} */ + __u8 prio; /* VLAN User Priority {0-7} */ __be16 encap; /* VLAN Encapsulated frame code {0-65535} */ - uint8_t bitmask; /* Args bitmask bit 1=1 - ID arg, + __u8 bitmask; /* Args bitmask bit 1=1 - ID arg, bit 2=1 User-Priority arg, bit 3=1 encap*/ - uint8_t invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, + __u8 invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, bit 2=1 - inversed Pirority arg */ }; diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h index e5a3687..c6a204c 100644 --- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -1,6 +1,8 @@ #ifndef _IPT_CLUSTERIP_H_target #define _IPT_CLUSTERIP_H_target +#include <linux/types.h> + enum clusterip_hashmode { CLUSTERIP_HASHMODE_SIP = 0, CLUSTERIP_HASHMODE_SIP_SPT, @@ -17,15 +19,15 @@ struct clusterip_config; struct ipt_clusterip_tgt_info { - u_int32_t flags; + __u32 flags; /* only relevant for new ones */ - u_int8_t clustermac[6]; - u_int16_t num_total_nodes; - u_int16_t num_local_nodes; - u_int16_t local_nodes[CLUSTERIP_MAX_NODES]; - u_int32_t hash_mode; - u_int32_t hash_initval; + __u8 clustermac[6]; + __u16 num_total_nodes; + __u16 num_local_nodes; + __u16 local_nodes[CLUSTERIP_MAX_NODES]; + __u32 hash_mode; + __u32 hash_initval; /* Used internally by the kernel */ struct clusterip_config *config; diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h index 7ca4591..bb88d53 100644 --- a/include/linux/netfilter_ipv4/ipt_ECN.h +++ b/include/linux/netfilter_ipv4/ipt_ECN.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_TARGET_H #define _IPT_ECN_TARGET_H + +#include <linux/types.h> #include <linux/netfilter/xt_DSCP.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -19,11 +21,11 @@ #define IPT_ECN_OP_MASK 0xce struct ipt_ECN_info { - u_int8_t operation; /* bitset of operations */ - u_int8_t ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ + __u8 operation; /* bitset of operations */ + __u8 ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ union { struct { - u_int8_t ece:1, cwr:1; /* TCP ECT bits */ + __u8 ece:1, cwr:1; /* TCP ECT bits */ } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h index 2529660..5bca782 100644 --- a/include/linux/netfilter_ipv4/ipt_SAME.h +++ b/include/linux/netfilter_ipv4/ipt_SAME.h @@ -1,15 +1,17 @@ #ifndef _IPT_SAME_H #define _IPT_SAME_H +#include <linux/types.h> + #define IPT_SAME_MAX_RANGE 10 #define IPT_SAME_NODST 0x01 struct ipt_same_info { unsigned char info; - u_int32_t rangesize; - u_int32_t ipnum; - u_int32_t *iparray; + __u32 rangesize; + __u32 ipnum; + __u32 *iparray; /* hangs off end. */ struct nf_nat_range range[IPT_SAME_MAX_RANGE]; diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h index ee6611e..f6ac169 100644 --- a/include/linux/netfilter_ipv4/ipt_TTL.h +++ b/include/linux/netfilter_ipv4/ipt_TTL.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_SET = 0, IPT_TTL_INC, @@ -13,8 +15,8 @@ enum { #define IPT_TTL_MAXMODE IPT_TTL_DEC struct ipt_TTL_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h index 446de6a..0da4223 100644 --- a/include/linux/netfilter_ipv4/ipt_addrtype.h +++ b/include/linux/netfilter_ipv4/ipt_addrtype.h @@ -1,6 +1,8 @@ #ifndef _IPT_ADDRTYPE_H #define _IPT_ADDRTYPE_H +#include <linux/types.h> + enum { IPT_ADDRTYPE_INVERT_SOURCE = 0x0001, IPT_ADDRTYPE_INVERT_DEST = 0x0002, @@ -9,17 +11,17 @@ enum { }; struct ipt_addrtype_info_v1 { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t flags; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 flags; }; /* revision 0 */ struct ipt_addrtype_info { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t invert_source; - u_int32_t invert_dest; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 invert_source; + __u32 invert_dest; }; #endif diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h index 2e555b4..4e02bb0 100644 --- a/include/linux/netfilter_ipv4/ipt_ah.h +++ b/include/linux/netfilter_ipv4/ipt_ah.h @@ -1,9 +1,11 @@ #ifndef _IPT_AH_H #define _IPT_AH_H +#include <linux/types.h> + struct ipt_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u8 invflags; /* Inverse flags */ }; diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h index 9945baa..eabf95f 100644 --- a/include/linux/netfilter_ipv4/ipt_ecn.h +++ b/include/linux/netfilter_ipv4/ipt_ecn.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_H #define _IPT_ECN_H + +#include <linux/types.h> #include <linux/netfilter/xt_dscp.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -20,12 +22,12 @@ /* match info */ struct ipt_ecn_info { - u_int8_t operation; - u_int8_t invert; - u_int8_t ip_ect; + __u8 operation; + __u8 invert; + __u8 ip_ect; union { struct { - u_int8_t ect; + __u8 ect; } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h index ee24fd8..37bee44 100644 --- a/include/linux/netfilter_ipv4/ipt_ttl.h +++ b/include/linux/netfilter_ipv4/ipt_ttl.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_EQ = 0, /* equals */ IPT_TTL_NE, /* not equals */ @@ -13,8 +15,8 @@ enum { struct ipt_ttl_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h index afb7813..ebd8ead 100644 --- a/include/linux/netfilter_ipv6/ip6t_HL.h +++ b/include/linux/netfilter_ipv6/ip6t_HL.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_SET = 0, IP6T_HL_INC, @@ -14,8 +16,8 @@ enum { #define IP6T_HL_MAXMODE IP6T_HL_DEC struct ip6t_HL_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h index 6be6504..205ed62 100644 --- a/include/linux/netfilter_ipv6/ip6t_REJECT.h +++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h @@ -1,6 +1,8 @@ #ifndef _IP6T_REJECT_H #define _IP6T_REJECT_H +#include <linux/types.h> + enum ip6t_reject_with { IP6T_ICMP6_NO_ROUTE, IP6T_ICMP6_ADM_PROHIBITED, @@ -12,7 +14,7 @@ enum ip6t_reject_with { }; struct ip6t_reject_info { - u_int32_t with; /* reject type */ + __u32 with; /* reject type */ }; #endif /*_IP6T_REJECT_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h index 17a745c..5da2b65 100644 --- a/include/linux/netfilter_ipv6/ip6t_ah.h +++ b/include/linux/netfilter_ipv6/ip6t_ah.h @@ -1,11 +1,13 @@ #ifndef _IP6T_AH_H #define _IP6T_AH_H +#include <linux/types.h> + struct ip6t_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t hdrres; /* Test of the Reserved Filed */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 hdrres; /* Test of the Reserved Filed */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_AH_SPI 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h index 3724d08..b47f61b 100644 --- a/include/linux/netfilter_ipv6/ip6t_frag.h +++ b/include/linux/netfilter_ipv6/ip6t_frag.h @@ -1,11 +1,13 @@ #ifndef _IP6T_FRAG_H #define _IP6T_FRAG_H +#include <linux/types.h> + struct ip6t_frag { - u_int32_t ids[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 ids[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_FRAG_IDS 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h index 5ef91b8..6e76dbc 100644 --- a/include/linux/netfilter_ipv6/ip6t_hl.h +++ b/include/linux/netfilter_ipv6/ip6t_hl.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_EQ = 0, /* equals */ IP6T_HL_NE, /* not equals */ @@ -14,8 +16,8 @@ enum { struct ip6t_hl_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h index 01dfd44..efae3a2 100644 --- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h +++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h @@ -8,10 +8,12 @@ on whether they contain certain headers */ #ifndef __IPV6HEADER_H #define __IPV6HEADER_H +#include <linux/types.h> + struct ip6t_ipv6header_info { - u_int8_t matchflags; - u_int8_t invflags; - u_int8_t modeflag; + __u8 matchflags; + __u8 invflags; + __u8 modeflag; }; #define MASK_HOPOPTS 128 diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h index 18549bc..a7729a5 100644 --- a/include/linux/netfilter_ipv6/ip6t_mh.h +++ b/include/linux/netfilter_ipv6/ip6t_mh.h @@ -1,10 +1,12 @@ #ifndef _IP6T_MH_H #define _IP6T_MH_H +#include <linux/types.h> + /* MH matching stuff */ struct ip6t_mh { - u_int8_t types[2]; /* MH type range */ - u_int8_t invflags; /* Inverse flags */ + __u8 types[2]; /* MH type range */ + __u8 invflags; /* Inverse flags */ }; /* Values for "invflags" field in struct ip6t_mh. */ diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h index 62d89bc..17d419a 100644 --- a/include/linux/netfilter_ipv6/ip6t_opts.h +++ b/include/linux/netfilter_ipv6/ip6t_opts.h @@ -1,14 +1,16 @@ #ifndef _IP6T_OPTS_H #define _IP6T_OPTS_H +#include <linux/types.h> + #define IP6T_OPTS_OPTSNR 16 struct ip6t_opts { - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ - u_int16_t opts[IP6T_OPTS_OPTSNR]; /* opts */ - u_int8_t optsnr; /* Nr of OPts */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ + __u16 opts[IP6T_OPTS_OPTSNR]; /* opts */ + __u8 optsnr; /* Nr of OPts */ }; #define IP6T_OPTS_LEN 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h index ab91bfd..7605a5f 100644 --- a/include/linux/netfilter_ipv6/ip6t_rt.h +++ b/include/linux/netfilter_ipv6/ip6t_rt.h @@ -1,18 +1,19 @@ #ifndef _IP6T_RT_H #define _IP6T_RT_H +#include <linux/types.h> /*#include <linux/in6.h>*/ #define IP6T_RT_HOPS 16 struct ip6t_rt { - u_int32_t rt_type; /* Routing Type */ - u_int32_t segsleft[2]; /* Segments Left */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 rt_type; /* Routing Type */ + __u32 segsleft[2]; /* Segments Left */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ struct in6_addr addrs[IP6T_RT_HOPS]; /* Hops */ - u_int8_t addrnr; /* Nr of Addresses */ + __u8 addrnr; /* Nr of Addresses */ }; #define IP6T_RT_TYP 0x01 diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index 2cfa4bc..d4bb6f5 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -247,6 +247,35 @@ struct tc_gred_sopt { __u16 pad1; }; +/* CHOKe section */ + +enum { + TCA_CHOKE_UNSPEC, + TCA_CHOKE_PARMS, + TCA_CHOKE_STAB, + __TCA_CHOKE_MAX, +}; + +#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1) + +struct tc_choke_qopt { + __u32 limit; /* Hard queue length (packets) */ + __u32 qth_min; /* Min average threshold (packets) */ + __u32 qth_max; /* Max average threshold (packets) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; /* see RED flags */ +}; + +struct tc_choke_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ + __u32 matched; /* Drops due to flow match */ +}; + /* HTB section */ #define TC_HTB_NUMPRIO 8 #define TC_HTB_MAXDEPTH 8 @@ -481,4 +510,16 @@ struct tc_drr_stats { __u32 deficit; }; +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf221d6..31f02d0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1801,6 +1801,15 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \ skb = skb->prev) +#define skb_queue_reverse_walk_safe(queue, skb, tmp) \ + for (skb = (queue)->prev, tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) + +#define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ + for (tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { @@ -1868,7 +1877,7 @@ extern void skb_split(struct sk_buff *skb, extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); -extern struct sk_buff *skb_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 930fdd2..b93d6f5 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -350,6 +350,7 @@ struct xfrm_usersa_info { #define XFRM_STATE_WILDRECV 8 #define XFRM_STATE_ICMP 16 #define XFRM_STATE_AF_UNSPEC 32 +#define XFRM_STATE_ALIGN4 64 }; struct xfrm_usersa_id { diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1322695..679a049 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1790,8 +1790,9 @@ static inline void *wdev_priv(struct wireless_dev *wdev) /** * ieee80211_channel_to_frequency - convert channel number to frequency * @chan: channel number + * @band: band, necessary due to channel number overlap */ -extern int ieee80211_channel_to_frequency(int chan); +extern int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); /** * ieee80211_frequency_to_channel - convert frequency to channel number diff --git a/include/net/dst.h b/include/net/dst.h index 93b0310..23b564d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -40,24 +40,10 @@ struct dst_entry { struct rcu_head rcu_head; struct dst_entry *child; struct net_device *dev; - short error; - short obsolete; - int flags; -#define DST_HOST 0x0001 -#define DST_NOXFRM 0x0002 -#define DST_NOPOLICY 0x0004 -#define DST_NOHASH 0x0008 -#define DST_NOCACHE 0x0010 + struct dst_ops *ops; + unsigned long _metrics; unsigned long expires; - - unsigned short header_len; /* more space at head required */ - unsigned short trailer_len; /* space to reserve at tail */ - - unsigned int rate_tokens; - unsigned long rate_last; /* rate limiting for ICMP */ - struct dst_entry *path; - struct neighbour *neighbour; struct hh_cache *hh; #ifdef CONFIG_XFRM @@ -68,17 +54,16 @@ struct dst_entry { int (*input)(struct sk_buff*); int (*output)(struct sk_buff*); - struct dst_ops *ops; - - u32 _metrics[RTAX_MAX]; - -#ifdef CONFIG_NET_CLS_ROUTE + short error; + short obsolete; + unsigned short header_len; /* more space at head required */ + unsigned short trailer_len; /* space to reserve at tail */ +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 tclassid; #else __u32 __pad2; #endif - /* * Align __refcnt to a 64 bytes alignment * (L1_CACHE_SIZE would be too much) @@ -93,6 +78,12 @@ struct dst_entry { atomic_t __refcnt; /* client references */ int __use; unsigned long lastuse; + int flags; +#define DST_HOST 0x0001 +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOHASH 0x0008 +#define DST_NOCACHE 0x0010 union { struct dst_entry *next; struct rtable __rcu *rt_next; @@ -103,10 +94,70 @@ struct dst_entry { #ifdef __KERNEL__ +extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); +extern const u32 dst_default_metrics[RTAX_MAX]; + +#define DST_METRICS_READ_ONLY 0x1UL +#define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_READ_ONLY)) +#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) + +static inline bool dst_metrics_read_only(const struct dst_entry *dst) +{ + return dst->_metrics & DST_METRICS_READ_ONLY; +} + +extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); + +static inline void dst_destroy_metrics_generic(struct dst_entry *dst) +{ + unsigned long val = dst->_metrics; + if (!(val & DST_METRICS_READ_ONLY)) + __dst_destroy_metrics_generic(dst, val); +} + +static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) +{ + unsigned long p = dst->_metrics; + + if (p & DST_METRICS_READ_ONLY) + return dst->ops->cow_metrics(dst, p); + return __DST_METRICS_PTR(p); +} + +/* This may only be invoked before the entry has reached global + * visibility. + */ +static inline void dst_init_metrics(struct dst_entry *dst, + const u32 *src_metrics, + bool read_only) +{ + dst->_metrics = ((unsigned long) src_metrics) | + (read_only ? DST_METRICS_READ_ONLY : 0); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + u32 *dst_metrics = dst_metrics_write_ptr(dest); + + if (dst_metrics) { + u32 *src_metrics = DST_METRICS_PTR(src); + + memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); + } +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return DST_METRICS_PTR(dst); +} + static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { - return dst->_metrics[metric-1]; + u32 *p = DST_METRICS_PTR(dst); + + return p[metric-1]; } static inline u32 @@ -131,22 +182,10 @@ dst_metric_advmss(const struct dst_entry *dst) static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { - dst->_metrics[metric-1] = val; -} + u32 *p = dst_metrics_write_ptr(dst); -static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) -{ - memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); -} - -static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) -{ - dst_import_metrics(dest, src->_metrics); -} - -static inline u32 *dst_metrics_ptr(struct dst_entry *dst) -{ - return dst->_metrics; + if (p) + p[metric-1] = val; } static inline u32 @@ -181,8 +220,6 @@ static inline u32 dst_allfrag(const struct dst_entry *dst) { int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); - /* Yes, _exactly_. This is paranoia. */ - barrier(); return ret; } @@ -315,7 +352,7 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb) } extern int dst_discard(struct sk_buff *skb); -extern void * dst_alloc(struct dst_ops * ops); +extern void *dst_alloc(struct dst_ops * ops, int initial_ref); extern void __dst_free(struct dst_entry * dst); extern struct dst_entry *dst_destroy(struct dst_entry * dst); diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 21a320b..dc07463 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -18,6 +18,7 @@ struct dst_ops { struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*default_mtu)(const struct dst_entry *); + u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); diff --git a/include/net/flow.h b/include/net/flow.h index 240b7f3..1ae901f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -48,7 +48,8 @@ struct flowi { __u8 proto; __u8 flags; -#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_PRECOW_METRICS 0x02 union { struct { __be16 sport; diff --git a/include/net/icmp.h b/include/net/icmp.h index 6e991e0..f0698b9 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -45,7 +45,4 @@ extern int icmp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int icmp_init(void); extern void icmp_out_count(struct net *net, unsigned char type); -/* Move into dst.h ? */ -extern int xrlim_allow(struct dst_entry *dst, int timeout); - #endif /* _ICMP_H */ diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index af49f8a..b0be5fb 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -178,6 +178,11 @@ struct ieee80211_radiotap_header { * * Number of unicast retries a transmitted frame used. * + * IEEE80211_RADIOTAP_MCS u8, u8, u8 unitless + * + * Contains a bitmap of known fields/flags, the flags, and + * the MCS index. + * */ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_TSFT = 0, @@ -199,6 +204,8 @@ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_RTS_RETRIES = 16, IEEE80211_RADIOTAP_DATA_RETRIES = 17, + IEEE80211_RADIOTAP_MCS = 19, + /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, IEEE80211_RADIOTAP_VENDOR_NAMESPACE = 30, @@ -245,6 +252,24 @@ enum ieee80211_radiotap_type { #define IEEE80211_RADIOTAP_F_TX_CTS 0x0002 /* used cts 'protection' */ #define IEEE80211_RADIOTAP_F_TX_RTS 0x0004 /* used rts/cts handshake */ + +/* For IEEE80211_RADIOTAP_MCS */ +#define IEEE80211_RADIOTAP_MCS_HAVE_BW 0x01 +#define IEEE80211_RADIOTAP_MCS_HAVE_MCS 0x02 +#define IEEE80211_RADIOTAP_MCS_HAVE_GI 0x04 +#define IEEE80211_RADIOTAP_MCS_HAVE_FMT 0x08 +#define IEEE80211_RADIOTAP_MCS_HAVE_FEC 0x10 + +#define IEEE80211_RADIOTAP_MCS_BW_MASK 0x03 +#define IEEE80211_RADIOTAP_MCS_BW_20 0 +#define IEEE80211_RADIOTAP_MCS_BW_40 1 +#define IEEE80211_RADIOTAP_MCS_BW_20L 2 +#define IEEE80211_RADIOTAP_MCS_BW_20U 3 +#define IEEE80211_RADIOTAP_MCS_SGI 0x04 +#define IEEE80211_RADIOTAP_MCS_FMT_GF 0x08 +#define IEEE80211_RADIOTAP_MCS_FEC_LDPC 0x10 + + /* Ugly macro to convert literal channel numbers into their mhz equivalents * There are certianly some conditions that will break this (like feeding it '30') * but they shouldn't arise since nothing talks on channel 30. */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8181498..6e6dfd7 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -219,7 +219,13 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { - return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; + __u8 flags = 0; + + if (inet_sk(sk)->transparent) + flags |= FLOWI_FLAG_ANYSRC; + if (sk->sk_protocol == IPPROTO_TCP) + flags |= FLOWI_FLAG_PRECOW_METRICS; + return flags; } #endif /* _INET_SOCK_H */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 599d96e..e6dd8da6 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -11,15 +11,20 @@ #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> +#include <linux/rtnetlink.h> #include <net/ipv6.h> #include <asm/atomic.h> -struct inetpeer_addr { +struct inetpeer_addr_base { union { - __be32 a4; - __be32 a6[4]; + __be32 a4; + __be32 a6[4]; }; - __u16 family; +}; + +struct inetpeer_addr { + struct inetpeer_addr_base addr; + __u16 family; }; struct inet_peer { @@ -33,15 +38,22 @@ struct inet_peer { atomic_t refcnt; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp - * We can share memory with rcu_head to keep inet_peer small + * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp, metrics + * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { - atomic_t rid; /* Frag reception counter */ - atomic_t ip_id_count; /* IP ID for the next packet */ - __u32 tcp_ts; - __u32 tcp_ts_stamp; + atomic_t rid; /* Frag reception counter */ + atomic_t ip_id_count; /* IP ID for the next packet */ + __u32 tcp_ts; + __u32 tcp_ts_stamp; + u32 metrics[RTAX_MAX]; + u32 rate_tokens; /* rate limiting for ICMP */ + unsigned long rate_last; + unsigned long pmtu_expires; + u32 pmtu_orig; + u32 pmtu_learned; + struct inetpeer_addr_base redirect_learned; }; struct rcu_head rcu; }; @@ -49,6 +61,13 @@ struct inet_peer { void inet_initpeers(void) __init; +#define INETPEER_METRICS_NEW (~(u32) 0) + +static inline bool inet_metrics_new(const struct inet_peer *p) +{ + return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW; +} + /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create); @@ -56,7 +75,7 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) { struct inetpeer_addr daddr; - daddr.a4 = v4daddr; + daddr.addr.a4 = v4daddr; daddr.family = AF_INET; return inet_getpeer(&daddr, create); } @@ -65,13 +84,14 @@ static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int cr { struct inetpeer_addr daddr; - ipv6_addr_copy((struct in6_addr *)daddr.a6, v6daddr); + ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr); daddr.family = AF_INET6; return inet_getpeer(&daddr, create); } /* can be called from BH context or outside */ extern void inet_putpeer(struct inet_peer *p); +extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); /* * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 708ff7c..46a6e8a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -108,6 +108,7 @@ struct rt6_info { u32 rt6i_flags; struct rt6key rt6i_src; u32 rt6i_metric; + u32 rt6i_peer_genid; struct inet6_dev *rt6i_idev; struct inet_peer *rt6i_peer; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 07bdb5e..523a170 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -55,7 +55,7 @@ struct fib_nh { int nh_weight; int nh_power; #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif int nh_oif; @@ -77,7 +77,7 @@ struct fib_info { int fib_protocol; __be32 fib_prefsrc; u32 fib_priority; - u32 fib_metrics[RTAX_MAX]; + u32 *fib_metrics; #define fib_mtu fib_metrics[RTAX_MTU-1] #define fib_window fib_metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics[RTAX_RTT-1] @@ -96,12 +96,15 @@ struct fib_info { struct fib_rule; #endif +struct fib_table; struct fib_result { unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; struct fib_info *fi; + struct fib_table *table; + struct list_head *fa_head; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule *r; #endif @@ -155,9 +158,6 @@ extern int fib_table_delete(struct fib_table *, struct fib_config *); extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); extern int fib_table_flush(struct fib_table *table); -extern void fib_table_select_default(struct fib_table *table, - const struct flowi *flp, - struct fib_result *res); extern void fib_free_table(struct fib_table *tb); @@ -201,8 +201,8 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp, extern int __net_init fib4_rules_init(struct net *net); extern void __net_exit fib4_rules_exit(struct net *net); -#ifdef CONFIG_NET_CLS_ROUTE -extern u32 fib_rules_tclass(struct fib_result *res); +#ifdef CONFIG_IP_ROUTE_CLASSID +extern u32 fib_rules_tclass(const struct fib_result *res); #endif extern int fib_lookup(struct net *n, struct flowi *flp, struct fib_result *res); @@ -218,8 +218,7 @@ extern void ip_fib_init(void); extern int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, __be32 *spec_dst, u32 *itag, u32 mark); -extern void fib_select_default(struct net *net, const struct flowi *flp, - struct fib_result *res); +extern void fib_select_default(struct fib_result *res); /* Exported by fib_semantics.c */ extern int ip_fib_check_default(__be32 gw, struct net_device *dev); @@ -229,13 +228,13 @@ extern int fib_sync_up(struct net_device *dev); extern __be32 __fib_res_prefsrc(struct fib_result *res); extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res); -/* Exported by fib_{hash|trie}.c */ -extern void fib_hash_init(void); -extern struct fib_table *fib_hash_table(u32 id); +/* Exported by fib_trie.c */ +extern void fib_trie_init(void); +extern struct fib_table *fib_trie_table(u32 id); -static inline void fib_combine_itag(u32 *itag, struct fib_result *res) +static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b7bbd6c..5d75fea 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -28,6 +28,80 @@ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #endif +#include <net/net_namespace.h> /* Netw namespace */ + +/* + * Generic access of ipvs struct + */ +static inline struct netns_ipvs *net_ipvs(struct net* net) +{ + return net->ipvs; +} +/* + * Get net ptr from skb in traffic cases + * use skb_sknet when call is from userland (ioctl or netlink) + */ +static inline struct net *skb_net(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* + * This is used for debug only. + * Start with the most likely hit + * End with BUG + */ + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + if (skb_dst(skb)->dev) + return dev_net(skb_dst(skb)->dev); + WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", + __func__, __LINE__); + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return dev_net(skb->dev ? : skb_dst(skb)->dev); +#endif +#else + return &init_net; +#endif +} + +static inline struct net *skb_sknet(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* Start with the most likely hit */ + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", + __func__, __LINE__); + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return sock_net(skb->sk); +#endif +#else + return &init_net; +#endif +} +/* + * This one needed for single_open_net since net is stored directly in + * private not as a struct i.e. seq_file_net cant be used. + */ +static inline struct net *seq_file_single_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + return (struct net *)seq->private; +#else + return &init_net; +#endif +} /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; @@ -258,6 +332,23 @@ struct ip_vs_seq { before last resized pkt */ }; +/* + * counters per cpu + */ +struct ip_vs_counters { + __u32 conns; /* connections scheduled */ + __u32 inpkts; /* incoming packets */ + __u32 outpkts; /* outgoing packets */ + __u64 inbytes; /* incoming bytes */ + __u64 outbytes; /* outgoing bytes */ +}; +/* + * Stats per cpu + */ +struct ip_vs_cpu_stats { + struct ip_vs_counters ustats; + struct u64_stats_sync syncp; +}; /* * IPVS statistics objects @@ -279,17 +370,34 @@ struct ip_vs_estimator { }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ - - spinlock_t lock; /* spin lock */ + struct ip_vs_cpu_stats *cpustats; /* per cpu counters */ + spinlock_t lock; /* spin lock */ }; +/* + * Helper Macros for per cpu + * ipvs->tot_stats->ustats.count + */ +#define IPVS_STAT_INC(ipvs, count) \ + __this_cpu_inc((ipvs)->ustats->count) + +#define IPVS_STAT_ADD(ipvs, count, value) \ + do {\ + write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + __this_cpu_add((ipvs)->ustats->count, value); \ + write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + } while (0) + struct dst_entry; struct iphdr; struct ip_vs_conn; struct ip_vs_app; struct sk_buff; +struct ip_vs_proto_data; struct ip_vs_protocol { struct ip_vs_protocol *next; @@ -297,21 +405,22 @@ struct ip_vs_protocol { u16 protocol; u16 num_states; int dont_defrag; - atomic_t appcnt; /* counter of proto app incs */ - int *timeout_table; /* protocol timeout table */ void (*init)(struct ip_vs_protocol *pp); void (*exit)(struct ip_vs_protocol *pp); + void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + + void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*conn_schedule)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp); struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -319,7 +428,6 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -337,11 +445,11 @@ struct ip_vs_protocol { int (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); - int (*register_app)(struct ip_vs_app *inc); + int (*register_app)(struct net *net, struct ip_vs_app *inc); - void (*unregister_app)(struct ip_vs_app *inc); + void (*unregister_app)(struct net *net, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); @@ -350,14 +458,26 @@ struct ip_vs_protocol { int offset, const char *msg); - void (*timeout_change)(struct ip_vs_protocol *pp, int flags); + void (*timeout_change)(struct ip_vs_proto_data *pd, int flags); +}; - int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to); +/* + * protocol data per netns + */ +struct ip_vs_proto_data { + struct ip_vs_proto_data *next; + struct ip_vs_protocol *pp; + int *timeout_table; /* protocol timeout table */ + atomic_t appcnt; /* counter of proto app incs. */ + struct tcp_states_t *tcp_state_table; }; -extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, + unsigned short proto); struct ip_vs_conn_param { + struct net *net; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -375,16 +495,19 @@ struct ip_vs_conn_param { */ struct ip_vs_conn { struct list_head c_list; /* hashed list heads */ - +#ifdef CONFIG_NET_NS + struct net *net; /* Name space */ +#endif /* Protocol, addresses and port numbers */ - u16 af; /* address family */ - union nf_inet_addr caddr; /* client address */ - union nf_inet_addr vaddr; /* virtual address */ - union nf_inet_addr daddr; /* destination address */ - volatile __u32 flags; /* status flags */ - __be16 cport; - __be16 vport; - __be16 dport; + u16 af; /* address family */ + __be16 cport; + __be16 vport; + __be16 dport; + __u32 fwmark; /* Fire wall mark from skb */ + union nf_inet_addr caddr; /* client address */ + union nf_inet_addr vaddr; /* virtual address */ + union nf_inet_addr daddr; /* destination address */ + volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ /* counter and timer */ @@ -422,10 +545,38 @@ struct ip_vs_conn { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ + const struct ip_vs_pe *pe; char *pe_data; __u8 pe_data_len; }; +/* + * To save some memory in conn table when name space is disabled. + */ +static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) +{ +#ifdef CONFIG_NET_NS + return cp->net; +#else + return &init_net; +#endif +} +static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) +{ +#ifdef CONFIG_NET_NS + cp->net = net; +#endif +} + +static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, + struct net *net) +{ +#ifdef CONFIG_NET_NS + return cp->net == net; +#else + return 1; +#endif +} /* * Extended internal versions of struct ip_vs_service_user and @@ -485,6 +636,7 @@ struct ip_vs_service { unsigned flags; /* service status flags */ unsigned timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity */ + struct net *net; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ @@ -510,8 +662,8 @@ struct ip_vs_dest { struct list_head d_list; /* for table with all the dests */ u16 af; /* address family */ - union nf_inet_addr addr; /* IP address of the server */ __be16 port; /* port number of the server */ + union nf_inet_addr addr; /* IP address of the server */ volatile unsigned flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ @@ -538,8 +690,8 @@ struct ip_vs_dest { /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ __u16 protocol; /* which protocol (TCP/UDP) */ - union nf_inet_addr vaddr; /* virtual IP address */ __be16 vport; /* virtual port number */ + union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ }; @@ -674,13 +826,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(int af, int protocol, +static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { + p->net = net; p->af = af; p->protocol = protocol; p->caddr = caddr; @@ -695,7 +848,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -703,7 +855,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -719,14 +870,14 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest); + struct ip_vs_dest *dest, __u32 fwmark); extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp); extern const char * ip_vs_state_name(__u16 proto, int state); -extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); +extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); extern int ip_vs_check_template(struct ip_vs_conn *ct); -extern void ip_vs_random_dropentry(void); +extern void ip_vs_random_dropentry(struct net *net); extern int ip_vs_conn_init(void); extern void ip_vs_conn_cleanup(void); @@ -796,12 +947,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -extern int register_ip_vs_app(struct ip_vs_app *app); -extern void unregister_ip_vs_app(struct ip_vs_app *app); +extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app); +extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern void ip_vs_unbind_app(struct ip_vs_conn *cp); -extern int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port); +extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, + __u16 proto, __u16 port); extern int ip_vs_app_inc_get(struct ip_vs_app *inc); extern void ip_vs_app_inc_put(struct ip_vs_app *inc); @@ -814,15 +965,27 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); void ip_vs_unbind_pe(struct ip_vs_service *svc); int register_ip_vs_pe(struct ip_vs_pe *pe); int unregister_ip_vs_pe(struct ip_vs_pe *pe); -extern struct ip_vs_pe *ip_vs_pe_get(const char *name); -extern void ip_vs_pe_put(struct ip_vs_pe *pe); +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name); +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name); + +static inline void ip_vs_pe_get(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + __module_get(pe->module); +} + +static inline void ip_vs_pe_put(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + module_put(pe->module); +} /* * IPVS protocol functions (from ip_vs_proto.c) */ extern int ip_vs_protocol_init(void); extern void ip_vs_protocol_cleanup(void); -extern void ip_vs_protocol_timeout_change(int flags); +extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags); extern int *ip_vs_create_timeout_table(int *table, int size); extern int ip_vs_set_state_timeout(int *table, int num, const char *const *names, @@ -852,26 +1015,21 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored); + struct ip_vs_proto_data *pd, int *ignored); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); /* * IPVS control data and functions (from ip_vs_ctl.c) */ -extern int sysctl_ip_vs_cache_bypass; -extern int sysctl_ip_vs_expire_nodest_conn; -extern int sysctl_ip_vs_expire_quiescent_template; -extern int sysctl_ip_vs_sync_threshold[2]; -extern int sysctl_ip_vs_nat_icmp_send; -extern int sysctl_ip_vs_conntrack; -extern int sysctl_ip_vs_snat_reroute; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; +extern int sysctl_ip_vs_sync_ver; +extern void ip_vs_sync_switch_mode(struct net *net, int mode); extern struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); static inline void ip_vs_service_put(struct ip_vs_service *svc) @@ -880,7 +1038,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc) } extern struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); extern int ip_vs_use_count_inc(void); @@ -888,8 +1046,9 @@ extern void ip_vs_use_count_dec(void); extern int ip_vs_control_init(void); extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * -ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport, - const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol); +ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, + __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, + __u16 protocol, __u32 fwmark); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); @@ -897,14 +1056,12 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); * IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -extern volatile int ip_vs_sync_state; -extern volatile int ip_vs_master_syncid; -extern volatile int ip_vs_backup_syncid; -extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid); -extern int stop_sync_thread(int state); -extern void ip_vs_sync_conn(struct ip_vs_conn *cp); +extern int start_sync_thread(struct net *net, int state, char *mcast_ifn, + __u8 syncid); +extern int stop_sync_thread(struct net *net, int state); +extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp); +extern int ip_vs_sync_init(void); +extern void ip_vs_sync_cleanup(void); /* @@ -912,8 +1069,8 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp); */ extern int ip_vs_estimator_init(void); extern void ip_vs_estimator_cleanup(void); -extern void ip_vs_new_estimator(struct ip_vs_stats *stats); -extern void ip_vs_kill_estimator(struct ip_vs_stats *stats); +extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats); +extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats); extern void ip_vs_zero_estimator(struct ip_vs_stats *stats); /* @@ -952,14 +1109,14 @@ extern int ip_vs_icmp_xmit_v6 * we are loaded. Just set ip_vs_drop_rate to 'n' and * we start to drop 1/rate of the packets */ -extern int ip_vs_drop_rate; -extern int ip_vs_drop_counter; -static __inline__ int ip_vs_todrop(void) +static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { - if (!ip_vs_drop_rate) return 0; - if (--ip_vs_drop_counter > 0) return 0; - ip_vs_drop_counter = ip_vs_drop_rate; + if (!ipvs->drop_rate) + return 0; + if (--ipvs->drop_counter > 0) + return 0; + ipvs->drop_counter = ipvs->drop_rate; return 1; } @@ -1047,9 +1204,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb) * Netfilter connection tracking * (from ip_vs_nfct.c) */ -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { - return sysctl_ip_vs_conntrack; + return ipvs->sysctl_conntrack; } extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, @@ -1062,7 +1219,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp); #else -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { return 0; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 62c0ce2..8fcd169 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -341,6 +341,9 @@ struct ieee80211_bss_conf { * the off-channel channel when a remain-on-channel offload is done * in hardware -- normal packets still flow and are expected to be * handled properly by the device. + * @IEEE80211_TX_INTFL_TKIP_MIC_FAILURE: Marks this packet to be used for TKIP + * testing. It will be sent out with incorrect Michael MIC key to allow + * TKIP countermeasures to be tested. * * Note: If you have to add new flags to the enumeration, then don't * forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary. @@ -370,6 +373,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_LDPC = BIT(22), IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), IEEE80211_TX_CTL_TX_OFFCHAN = BIT(25), + IEEE80211_TX_INTFL_TKIP_MIC_FAILURE = BIT(26), }; #define IEEE80211_TX_CTL_STBC_SHIFT 23 @@ -1069,6 +1073,13 @@ enum ieee80211_tkip_key_type { * to decrypt group addressed frames, then IBSS RSN support is still * possible but software crypto will be used. Advertise the wiphy flag * only in that case. + * + * @IEEE80211_HW_AP_LINK_PS: When operating in AP mode the device + * autonomously manages the PS status of connected stations. When + * this flag is set mac80211 will not trigger PS mode for connected + * stations based on the PM bit of incoming frames. + * Use ieee80211_start_ps()/ieee8021_end_ps() to manually configure + * the PS mode of connected stations. */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -1093,6 +1104,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_CONNECTION_MONITOR = 1<<19, IEEE80211_HW_SUPPORTS_CQM_RSSI = 1<<20, IEEE80211_HW_SUPPORTS_PER_STA_GTK = 1<<21, + IEEE80211_HW_AP_LINK_PS = 1<<22, }; /** @@ -1147,6 +1159,17 @@ enum ieee80211_hw_flags { * @napi_weight: weight used for NAPI polling. You must specify an * appropriate value here if a napi_poll operation is provided * by your driver. + + * @max_rx_aggregation_subframes: maximum buffer size (number of + * sub-frames) to be used for A-MPDU block ack receiver + * aggregation. + * This is only relevant if the device has restrictions on the + * number of subframes, if it relies on mac80211 to do reordering + * it shouldn't be set. + * + * @max_tx_aggregation_subframes: maximum number of subframes in an + * aggregate an HT driver will transmit, used by the peer as a + * hint to size its reorder buffer. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -1165,6 +1188,8 @@ struct ieee80211_hw { u8 max_rates; u8 max_report_rates; u8 max_rate_tries; + u8 max_rx_aggregation_subframes; + u8 max_tx_aggregation_subframes; }; /** @@ -1688,7 +1713,9 @@ enum ieee80211_ampdu_mlme_action { * station, AP, IBSS/WDS/mesh peer etc. This callback can sleep. * * @sta_notify: Notifies low level driver about power state transition of an - * associated station, AP, IBSS/WDS/mesh peer etc. Must be atomic. + * associated station, AP, IBSS/WDS/mesh peer etc. For a VIF operating + * in AP mode, this callback will not be called when the flag + * %IEEE80211_HW_AP_LINK_PS is set. Must be atomic. * * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max), * bursting) for a hardware TX queue. @@ -1723,6 +1750,10 @@ enum ieee80211_ampdu_mlme_action { * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. + * The @buf_size parameter is only valid when the action is set to + * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder + * buffer size (number of subframes) for this session -- aggregates + * containing more subframes than this may not be transmitted to the peer. * Returns a negative error code on failure. * The callback can sleep. * @@ -1825,7 +1856,8 @@ struct ieee80211_ops { int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); @@ -2113,6 +2145,48 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, local_bh_enable(); } +/** + * ieee80211_sta_ps_transition - PS transition for connected sta + * + * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS + * flag set, use this function to inform mac80211 about a connected station + * entering/leaving PS mode. + * + * This function may not be called in IRQ context or with softirqs enabled. + * + * Calls to this function for a single hardware must be synchronized against + * each other. + * + * The function returns -EINVAL when the requested PS mode is already set. + * + * @sta: currently connected sta + * @start: start or stop PS + */ +int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start); + +/** + * ieee80211_sta_ps_transition_ni - PS transition for connected sta + * (in process context) + * + * Like ieee80211_sta_ps_transition() but can be called in process context + * (internally disables bottom halves). Concurrent call restriction still + * applies. + * + * @sta: currently connected sta + * @start: start or stop PS + */ +static inline int ieee80211_sta_ps_transition_ni(struct ieee80211_sta *sta, + bool start) +{ + int ret; + + local_bh_disable(); + ret = ieee80211_sta_ps_transition(sta, start); + local_bh_enable(); + + return ret; +} + /* * The TX headroom reserved by mac80211 for its own tx_status functions. * This is enough for the radiotap header. diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1bf812b..b3b4a34 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -20,6 +20,7 @@ #include <net/netns/conntrack.h> #endif #include <net/netns/xfrm.h> +#include <net/netns/ip_vs.h> struct proc_dir_entry; struct net_device; @@ -94,6 +95,7 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif + struct netns_ipvs *ipvs; }; diff --git a/include/net/netevent.h b/include/net/netevent.h index e82b7ba..22b239c 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -21,7 +21,6 @@ struct netevent_redirect { enum netevent_notif_type { NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */ - NETEVENT_PMTU_UPDATE, /* arg is struct dst_entry ptr */ NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */ }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d85cff1..d0d1337 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -50,11 +50,24 @@ union nf_conntrack_expect_proto { /* per conntrack: application helper private data */ union nf_conntrack_help { /* insert conntrack helper private data (master) here */ +#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE) struct nf_ct_ftp_master ct_ftp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_PPTP) || \ + defined(CONFIG_NF_CONNTRACK_PPTP_MODULE) struct nf_ct_pptp_master ct_pptp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_H323) || \ + defined(CONFIG_NF_CONNTRACK_H323_MODULE) struct nf_ct_h323_master ct_h323_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SANE) || \ + defined(CONFIG_NF_CONNTRACK_SANE_MODULE) struct nf_ct_sane_master ct_sane_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE) struct nf_ct_sip_master ct_sip_info; +#endif }; #include <linux/types.h> @@ -116,14 +129,14 @@ struct nf_conn { u_int32_t secmark; #endif - /* Storage reserved for other modules: */ - union nf_conntrack_proto proto; - /* Extensions */ struct nf_ct_ext *ext; #ifdef CONFIG_NET_NS struct net *ct_net; #endif + + /* Storage reserved for other modules, must be the last member */ + union nf_conntrack_proto proto; }; static inline struct nf_conn * @@ -189,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto); * Allocate a hashtable of hlist_head (if nulls == 0), * or hlist_nulls_head (if nulls == 1) */ -extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls); +extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); +extern void nf_ct_free_hashtable(void *hash, unsigned int size); extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 349cefe..4283508 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -23,12 +23,17 @@ struct nf_conntrack_ecache { static inline struct nf_conntrack_ecache * nf_ct_ecache_find(const struct nf_conn *ct) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE); +#else + return NULL; +#endif } static inline struct nf_conntrack_ecache * nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; @@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) e->expmask = expmask; } return e; +#else + return NULL; +#endif }; #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -59,7 +67,7 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier *nf_conntrack_event_cb; +extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); @@ -156,7 +164,7 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier *nf_expect_event_cb; +extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 0772d29..2dcf317 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -7,10 +7,19 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, +#endif NF_CT_EXT_ACCT, +#ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES NF_CT_EXT_ZONE, +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + NF_CT_EXT_TSTAMP, +#endif NF_CT_EXT_NUM, }; @@ -19,6 +28,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone +#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 32c305d..f1c1311 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) extern int nf_conntrack_helper_init(void); extern void nf_conntrack_helper_fini(void); +extern int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout); + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index a754761..e8010f4 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -73,7 +73,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; /* Protocol registration. */ extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h new file mode 100644 index 0000000..fc9c82b --- /dev/null +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -0,0 +1,65 @@ +#ifndef _NF_CONNTRACK_TSTAMP_H +#define _NF_CONNTRACK_TSTAMP_H + +#include <net/net_namespace.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> + +struct nf_conn_tstamp { + u_int64_t start; + u_int64_t stop; +}; + +static inline +struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP); +#else + return NULL; +#endif +} + +static inline +struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + struct net *net = nf_ct_net(ct); + + if (!net->ct.sysctl_tstamp) + return NULL; + + return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp); +#else + return NULL; +#endif +}; + +static inline bool nf_ct_tstamp_enabled(struct net *net) +{ + return net->ct.sysctl_tstamp != 0; +} + +static inline void nf_ct_set_tstamp(struct net *net, bool enable) +{ + net->ct.sysctl_tstamp = enable; +} + +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +extern int nf_conntrack_tstamp_init(struct net *net); +extern void nf_conntrack_tstamp_fini(struct net *net); +#else +static inline int nf_conntrack_tstamp_init(struct net *net) +{ + return 0; +} + +static inline void nf_conntrack_tstamp_fini(struct net *net) +{ + return; +} +#endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ + +#endif /* _NF_CONNTRACK_TSTAMP_H */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index f5f09f0..aff80b1 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat { /* per conntrack: nat application helper private data */ union nf_conntrack_nat_help { /* insert nat helper private data here */ +#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE) struct nf_nat_pptp nat_pptp_info; +#endif }; struct nf_conn; @@ -84,7 +86,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) return nf_ct_ext_find(ct, NF_CT_EXT_NAT); +#else + return NULL; +#endif } #else /* !__KERNEL__: iptables wants this to compile. */ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index 33602ab..3dc7b98 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) { if (manip == IP_NAT_MANIP_SRC) - return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_SRC_NAT_DONE; else - return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_DST_NAT_DONE; } struct nlattr; diff --git a/include/net/netlink.h b/include/net/netlink.h index 373f1a9..8a3906a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -856,18 +856,27 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, #define NLA_PUT_BE16(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be16, attrtype, value) +#define NLA_PUT_NET16(skb, attrtype, value) \ + NLA_PUT_BE16(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u32, attrtype, value) #define NLA_PUT_BE32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be32, attrtype, value) +#define NLA_PUT_NET32(skb, attrtype, value) \ + NLA_PUT_BE32(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u64, attrtype, value) #define NLA_PUT_BE64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be64, attrtype, value) +#define NLA_PUT_NET64(skb, attrtype, value) \ + NLA_PUT_BE64(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_STRING(skb, attrtype, value) \ NLA_PUT(skb, attrtype, strlen(value) + 1, value) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index d4958d4..341eb08 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -21,15 +21,15 @@ struct netns_ct { int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; + int sysctl_tstamp; int sysctl_checksum; unsigned int sysctl_log_invalid; /* Log invalid packets */ #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; struct ctl_table_header *acct_sysctl_header; + struct ctl_table_header *tstamp_sysctl_header; struct ctl_table_header *event_sysctl_header; #endif - int hash_vmalloc; - int expect_vmalloc; char *slabname; }; #endif diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h new file mode 100644 index 0000000..259ebac --- /dev/null +++ b/include/net/netns/ip_vs.h @@ -0,0 +1,143 @@ +/* + * IP Virtual Server + * Data structure for network namspace + * + */ + +#ifndef IP_VS_H_ +#define IP_VS_H_ + +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/list_nulls.h> +#include <linux/ip_vs.h> +#include <asm/atomic.h> +#include <linux/in.h> + +struct ip_vs_stats; +struct ip_vs_sync_buff; +struct ctl_table_header; + +struct netns_ipvs { + int gen; /* Generation */ + /* + * Hash table: for real service lookups + */ + #define IP_VS_RTAB_BITS 4 + #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) + #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) + + struct list_head rs_table[IP_VS_RTAB_SIZE]; + /* ip_vs_app */ + struct list_head app_list; + struct mutex app_mutex; + struct lock_class_key app_key; /* mutex debuging */ + + /* ip_vs_proto */ + #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ + struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE]; + /* ip_vs_proto_tcp */ +#ifdef CONFIG_IP_VS_PROTO_TCP + #define TCP_APP_TAB_BITS 4 + #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) + #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) + struct list_head tcp_apps[TCP_APP_TAB_SIZE]; + spinlock_t tcp_app_lock; +#endif + /* ip_vs_proto_udp */ +#ifdef CONFIG_IP_VS_PROTO_UDP + #define UDP_APP_TAB_BITS 4 + #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) + #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) + struct list_head udp_apps[UDP_APP_TAB_SIZE]; + spinlock_t udp_app_lock; +#endif + /* ip_vs_proto_sctp */ +#ifdef CONFIG_IP_VS_PROTO_SCTP + #define SCTP_APP_TAB_BITS 4 + #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) + #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) + /* Hash table for SCTP application incarnations */ + struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; + spinlock_t sctp_app_lock; +#endif + /* ip_vs_conn */ + atomic_t conn_count; /* connection counter */ + + /* ip_vs_ctl */ + struct ip_vs_stats *tot_stats; /* Statistics & est. */ + struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */ + seqcount_t *ustats_seq; /* u64 read retry */ + + int num_services; /* no of virtual services */ + /* 1/rate drop and drop-entry variables */ + struct delayed_work defense_work; /* Work handler */ + int drop_rate; + int drop_counter; + atomic_t dropentry; + /* locks in ctl.c */ + spinlock_t dropentry_lock; /* drop entry handling */ + spinlock_t droppacket_lock; /* drop packet handling */ + spinlock_t securetcp_lock; /* state and timeout tables */ + rwlock_t rs_lock; /* real services table */ + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ + struct lock_class_key ctl_key; /* ctl_mutex debuging */ + /* Trash for destinations */ + struct list_head dest_trash; + /* Service counters */ + atomic_t ftpsvc_counter; + atomic_t nullsvc_counter; + + /* sys-ctl struct */ + struct ctl_table_header *sysctl_hdr; + struct ctl_table *sysctl_tbl; + /* sysctl variables */ + int sysctl_amemthresh; + int sysctl_am_droprate; + int sysctl_drop_entry; + int sysctl_drop_packet; + int sysctl_secure_tcp; +#ifdef CONFIG_IP_VS_NFCT + int sysctl_conntrack; +#endif + int sysctl_snat_reroute; + int sysctl_sync_ver; + int sysctl_cache_bypass; + int sysctl_expire_nodest_conn; + int sysctl_expire_quiescent_template; + int sysctl_sync_threshold[2]; + int sysctl_nat_icmp_send; + + /* ip_vs_lblc */ + int sysctl_lblc_expiration; + struct ctl_table_header *lblc_ctl_header; + struct ctl_table *lblc_ctl_table; + /* ip_vs_lblcr */ + int sysctl_lblcr_expiration; + struct ctl_table_header *lblcr_ctl_header; + struct ctl_table *lblcr_ctl_table; + /* ip_vs_est */ + struct list_head est_list; /* estimator list */ + spinlock_t est_lock; + struct timer_list est_timer; /* Estimation timer */ + /* ip_vs_sync */ + struct list_head sync_queue; + spinlock_t sync_lock; + struct ip_vs_sync_buff *sync_buff; + spinlock_t sync_buff_lock; + struct sockaddr_in sync_mcast_addr; + struct task_struct *master_thread; + struct task_struct *backup_thread; + int send_mesg_maxlen; + int recv_mesg_maxlen; + volatile int sync_state; + volatile int master_syncid; + volatile int backup_syncid; + /* multicast interface name */ + char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + /* net name space ptr */ + struct net *net; /* Needed by timer routines */ +}; + +#endif /* IP_VS_H_ */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d68c3f1..e2e2ef5 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,7 +43,6 @@ struct netns_ipv4 { struct xt_table *nat_table; struct hlist_head *nat_bysource; unsigned int nat_htable_size; - int nat_vmalloced; #endif int sysctl_icmp_echo_ignore_all; diff --git a/include/net/protocol.h b/include/net/protocol.h index dc07495..6f7eb80 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -38,7 +38,7 @@ struct net_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -57,7 +57,7 @@ struct inet6_protocol { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); diff --git a/include/net/route.h b/include/net/route.h index 93e10c4..bf790c1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -49,6 +49,7 @@ struct fib_nh; struct inet_peer; +struct fib_info; struct rtable { struct dst_entry dst; @@ -68,7 +69,9 @@ struct rtable { /* Miscellaneous cached information */ __be32 rt_spec_dst; /* RFC1122 specific destination */ + u32 rt_peer_genid; struct inet_peer *peer; /* long-living peer info */ + struct fib_info *fi; /* for client ref to shared metrics */ }; static inline bool rt_is_input_route(struct rtable *rt) @@ -180,6 +183,8 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; if (!dst || !src) { err = __ip_route_output_key(net, rp, &fl); @@ -207,6 +212,8 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol, fl.proto = protocol; if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; ip_rt_put(*rp); *rp = NULL; security_sk_classify_flow(sk, &fl); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 160a407..16626a0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -31,10 +31,12 @@ enum qdisc_state_t { * following bits are only changed while qdisc lock is held */ enum qdisc___state_t { - __QDISC___STATE_RUNNING, + __QDISC___STATE_RUNNING = 1, + __QDISC___STATE_THROTTLED = 2, }; struct qdisc_size_table { + struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; @@ -46,14 +48,13 @@ struct Qdisc { struct sk_buff * (*dequeue)(struct Qdisc *dev); unsigned flags; #define TCQ_F_BUILTIN 1 -#define TCQ_F_THROTTLED 2 -#define TCQ_F_INGRESS 4 -#define TCQ_F_CAN_BYPASS 8 -#define TCQ_F_MQROOT 16 +#define TCQ_F_INGRESS 2 +#define TCQ_F_CAN_BYPASS 4 +#define TCQ_F_MQROOT 8 #define TCQ_F_WARN_NONWC (1 << 16) int padded; struct Qdisc_ops *ops; - struct qdisc_size_table *stab; + struct qdisc_size_table __rcu *stab; struct list_head list; u32 handle; u32 parent; @@ -78,25 +79,43 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned long __state; + unsigned int __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; spinlock_t busylock; }; -static inline bool qdisc_is_running(struct Qdisc *qdisc) +static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { - return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + if (qdisc_is_running(qdisc)) + return false; + qdisc->__state |= __QDISC___STATE_RUNNING; + return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - __clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + qdisc->__state &= ~__QDISC___STATE_RUNNING; +} + +static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) +{ + return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false; +} + +static inline void qdisc_throttled(struct Qdisc *qdisc) +{ + qdisc->__state |= __QDISC___STATE_THROTTLED; +} + +static inline void qdisc_unthrottled(struct Qdisc *qdisc) +{ + qdisc->__state &= ~__QDISC___STATE_THROTTLED; } struct Qdisc_class_ops { @@ -331,8 +350,8 @@ extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops); extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc_ops *ops, u32 parentid); -extern void qdisc_calculate_pkt_len(struct sk_buff *skb, - struct qdisc_size_table *stab); +extern void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab); extern void tcf_destroy(struct tcf_proto *tp); extern void tcf_destroy_chain(struct tcf_proto **fl); @@ -411,12 +430,20 @@ enum net_xmit_qdisc_t { #define net_xmit_drop_count(e) (1) #endif -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED - if (sch->stab) - qdisc_calculate_pkt_len(skb, sch->stab); + struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); + + if (stab) + __qdisc_calculate_pkt_len(skb, stab); #endif +} + +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch); } diff --git a/include/net/sock.h b/include/net/sock.h index bc1cf7d8..e3893a2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1191,7 +1191,7 @@ extern void sk_filter_release_rcu(struct rcu_head *rcu); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - call_rcu_bh(&fp->rcu, sk_filter_release_rcu); + call_rcu(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) diff --git a/include/net/tcp.h b/include/net/tcp.h index 38509f0..adfe6db 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ +/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ +#define TCP_INIT_CWND 10 + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -799,15 +802,6 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) -/* - * Convert RFC 3390 larger initial window into an equivalent number of packets. - * This is based on the numbers specified in RFC 5681, 3.1. - */ -static inline u32 rfc3390_bytes_to_packets(const u32 smss) -{ - return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); -} - extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst); @@ -1404,7 +1398,7 @@ extern struct request_sock_ops tcp6_request_sock_ops; extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features); extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, diff --git a/include/net/udp.h b/include/net/udp.h index bb967dd..e82f3a8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -245,5 +245,5 @@ extern void udp4_proc_exit(void); extern void udp_init(void); extern int udp4_ufo_send_check(struct sk_buff *skb); -extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features); +extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features); #endif /* _UDP_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b9f385d..1f6e8a0 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -36,6 +36,7 @@ #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS +#define XFRM_ALIGN4(len) (((len) + 3) & ~3) #define XFRM_ALIGN8(len) (((len) + 7) & ~7) #define MODULE_ALIAS_XFRM_MODE(family, encap) \ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) diff --git a/kernel/audit.c b/kernel/audit.c index e495624..162e88e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -74,6 +74,8 @@ static int audit_initialized; int audit_enabled; int audit_ever_enabled; +EXPORT_SYMBOL_GPL(audit_enabled); + /* Default state when kernel boots without any parameters. */ static int audit_default; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0caa59f..0587c5c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -134,6 +134,10 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) irq_set_thread_affinity(desc); } #endif + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); + schedule_work(&desc->affinity_notify->work); + } desc->status |= IRQ_AFFINITY_SET; raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; @@ -155,6 +159,79 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; + + if (!desc) + goto out; + + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + goto out; + + raw_spin_lock_irqsave(&desc->lock, flags); +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (desc->status & IRQ_MOVE_PENDING) + cpumask_copy(cpumask, desc->pending_mask); + else +#endif + cpumask_copy(cpumask, desc->affinity); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + notify->notify(notify, cpumask); + + free_cpumask_var(cpumask); +out: + kref_put(¬ify->kref, notify->release); +} + +/** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification + * @notify: Context for notification, or %NULL to disable + * notification. Function pointers must be initialised; + * the other fields will be initialised by this function. + * + * Must be called in process context. Notification may only be enabled + * after the IRQ is allocated and must be disabled before the IRQ is + * freed using free_irq(). + */ +int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irq_affinity_notify *old_notify; + unsigned long flags; + + /* The release function is promised process context */ + might_sleep(); + + if (!desc) + return -EINVAL; + + /* Complete initialisation of *notify */ + if (notify) { + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); + } + + raw_spin_lock_irqsave(&desc->lock, flags); + old_notify = desc->affinity_notify; + desc->affinity_notify = notify; + raw_spin_unlock_irqrestore(&desc->lock, flags); + + if (old_notify) + kref_put(&old_notify->kref, old_notify->release); + + return 0; +} +EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); + #ifndef CONFIG_AUTO_IRQ_AFFINITY /* * Generic version of the affinity autoselector. @@ -1004,6 +1081,11 @@ void free_irq(unsigned int irq, void *dev_id) if (!desc) return; +#ifdef CONFIG_SMP + if (WARN_ON(desc->affinity_notify)) + desc->affinity_notify = NULL; +#endif + chip_bus_lock(desc); kfree(__free_irq(irq, dev_id)); chip_bus_sync_unlock(desc); diff --git a/lib/Kconfig b/lib/Kconfig index 0ee67e0..8334342 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -201,6 +201,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS depends on EXPERIMENTAL && BROKEN +config CPU_RMAP + bool + depends on SMP + # # Netlink attribute parsing support is select'ed if needed # diff --git a/lib/Makefile b/lib/Makefile index cbb774f..b73ba01 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -110,6 +110,8 @@ obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o obj-$(CONFIG_AVERAGE) += average.o +obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c new file mode 100644 index 0000000..987acfa --- /dev/null +++ b/lib/cpu_rmap.c @@ -0,0 +1,269 @@ +/* + * cpu_rmap.c: CPU affinity reverse-map support + * Copyright 2011 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include <linux/cpu_rmap.h> +#ifdef CONFIG_GENERIC_HARDIRQS +#include <linux/interrupt.h> +#endif +#include <linux/module.h> + +/* + * These functions maintain a mapping from CPUs to some ordered set of + * objects with CPU affinities. This can be seen as a reverse-map of + * CPU affinity. However, we do not assume that the object affinities + * cover all CPUs in the system. For those CPUs not directly covered + * by object affinities, we attempt to find a nearest object based on + * CPU topology. + */ + +/** + * alloc_cpu_rmap - allocate CPU affinity reverse-map + * @size: Number of objects to be mapped + * @flags: Allocation flags e.g. %GFP_KERNEL + */ +struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags) +{ + struct cpu_rmap *rmap; + unsigned int cpu; + size_t obj_offset; + + /* This is a silly number of objects, and we use u16 indices. */ + if (size > 0xffff) + return NULL; + + /* Offset of object pointer array from base structure */ + obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]), + sizeof(void *)); + + rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags); + if (!rmap) + return NULL; + + rmap->obj = (void **)((char *)rmap + obj_offset); + + /* Initially assign CPUs to objects on a rota, since we have + * no idea where the objects are. Use infinite distance, so + * any object with known distance is preferable. Include the + * CPUs that are not present/online, since we definitely want + * any newly-hotplugged CPUs to have some object assigned. + */ + for_each_possible_cpu(cpu) { + rmap->near[cpu].index = cpu % size; + rmap->near[cpu].dist = CPU_RMAP_DIST_INF; + } + + rmap->size = size; + return rmap; +} +EXPORT_SYMBOL(alloc_cpu_rmap); + +/* Reevaluate nearest object for given CPU, comparing with the given + * neighbours at the given distance. + */ +static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu, + const struct cpumask *mask, u16 dist) +{ + int neigh; + + for_each_cpu(neigh, mask) { + if (rmap->near[cpu].dist > dist && + rmap->near[neigh].dist <= dist) { + rmap->near[cpu].index = rmap->near[neigh].index; + rmap->near[cpu].dist = dist; + return true; + } + } + return false; +} + +#ifdef DEBUG +static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix) +{ + unsigned index; + unsigned int cpu; + + pr_info("cpu_rmap %p, %s:\n", rmap, prefix); + + for_each_possible_cpu(cpu) { + index = rmap->near[cpu].index; + pr_info("cpu %d -> obj %u (distance %u)\n", + cpu, index, rmap->near[cpu].dist); + } +} +#else +static inline void +debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix) +{ +} +#endif + +/** + * cpu_rmap_add - add object to a rmap + * @rmap: CPU rmap allocated with alloc_cpu_rmap() + * @obj: Object to add to rmap + * + * Return index of object. + */ +int cpu_rmap_add(struct cpu_rmap *rmap, void *obj) +{ + u16 index; + + BUG_ON(rmap->used >= rmap->size); + index = rmap->used++; + rmap->obj[index] = obj; + return index; +} +EXPORT_SYMBOL(cpu_rmap_add); + +/** + * cpu_rmap_update - update CPU rmap following a change of object affinity + * @rmap: CPU rmap to update + * @index: Index of object whose affinity changed + * @affinity: New CPU affinity of object + */ +int cpu_rmap_update(struct cpu_rmap *rmap, u16 index, + const struct cpumask *affinity) +{ + cpumask_var_t update_mask; + unsigned int cpu; + + if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL))) + return -ENOMEM; + + /* Invalidate distance for all CPUs for which this used to be + * the nearest object. Mark those CPUs for update. + */ + for_each_online_cpu(cpu) { + if (rmap->near[cpu].index == index) { + rmap->near[cpu].dist = CPU_RMAP_DIST_INF; + cpumask_set_cpu(cpu, update_mask); + } + } + + debug_print_rmap(rmap, "after invalidating old distances"); + + /* Set distance to 0 for all CPUs in the new affinity mask. + * Mark all CPUs within their NUMA nodes for update. + */ + for_each_cpu(cpu, affinity) { + rmap->near[cpu].index = index; + rmap->near[cpu].dist = 0; + cpumask_or(update_mask, update_mask, + cpumask_of_node(cpu_to_node(cpu))); + } + + debug_print_rmap(rmap, "after updating neighbours"); + + /* Update distances based on topology */ + for_each_cpu(cpu, update_mask) { + if (cpu_rmap_copy_neigh(rmap, cpu, + topology_thread_cpumask(cpu), 1)) + continue; + if (cpu_rmap_copy_neigh(rmap, cpu, + topology_core_cpumask(cpu), 2)) + continue; + if (cpu_rmap_copy_neigh(rmap, cpu, + cpumask_of_node(cpu_to_node(cpu)), 3)) + continue; + /* We could continue into NUMA node distances, but for now + * we give up. + */ + } + + debug_print_rmap(rmap, "after copying neighbours"); + + free_cpumask_var(update_mask); + return 0; +} +EXPORT_SYMBOL(cpu_rmap_update); + +#ifdef CONFIG_GENERIC_HARDIRQS + +/* Glue between IRQ affinity notifiers and CPU rmaps */ + +struct irq_glue { + struct irq_affinity_notify notify; + struct cpu_rmap *rmap; + u16 index; +}; + +/** + * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs + * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL + * + * Must be called in process context, before freeing the IRQs, and + * without holding any locks required by global workqueue items. + */ +void free_irq_cpu_rmap(struct cpu_rmap *rmap) +{ + struct irq_glue *glue; + u16 index; + + if (!rmap) + return; + + for (index = 0; index < rmap->used; index++) { + glue = rmap->obj[index]; + irq_set_affinity_notifier(glue->notify.irq, NULL); + } + irq_run_affinity_notifiers(); + + kfree(rmap); +} +EXPORT_SYMBOL(free_irq_cpu_rmap); + +static void +irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask) +{ + struct irq_glue *glue = + container_of(notify, struct irq_glue, notify); + int rc; + + rc = cpu_rmap_update(glue->rmap, glue->index, mask); + if (rc) + pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc); +} + +static void irq_cpu_rmap_release(struct kref *ref) +{ + struct irq_glue *glue = + container_of(ref, struct irq_glue, notify.kref); + kfree(glue); +} + +/** + * irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map + * @rmap: The reverse-map + * @irq: The IRQ number + * + * This adds an IRQ affinity notifier that will update the reverse-map + * automatically. + * + * Must be called in process context, after the IRQ is allocated but + * before it is bound with request_irq(). + */ +int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq) +{ + struct irq_glue *glue = kzalloc(sizeof(*glue), GFP_KERNEL); + int rc; + + if (!glue) + return -ENOMEM; + glue->notify.notify = irq_cpu_rmap_notify; + glue->notify.release = irq_cpu_rmap_release; + glue->rmap = rmap; + glue->index = cpu_rmap_add(rmap, glue); + rc = irq_set_affinity_notifier(irq, &glue->notify); + if (rc) + kfree(glue); + return rc; +} +EXPORT_SYMBOL(irq_cpu_rmap_add); + +#endif /* CONFIG_GENERIC_HARDIRQS */ diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 6e64f7c..7850412 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -327,7 +327,7 @@ static void vlan_sync_address(struct net_device *dev, static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { - unsigned long old_features = vlandev->features; + u32 old_features = vlandev->features; vlandev->features &= ~dev->vlan_features; vlandev->features |= dev->features & dev->vlan_features; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 17c5ba7..29a54cc 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -59,7 +59,6 @@ * safely advertise a maxsize * of 64k */ -#define P9_RDMA_MAX_SGE (P9_RDMA_MAXSIZE >> PAGE_SHIFT) /** * struct p9_trans_rdma - RDMA transport instance * diff --git a/net/Kconfig b/net/Kconfig index 7284062..79cabf1 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -221,6 +221,12 @@ config RPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config RFS_ACCEL + boolean + depends on RPS && GENERIC_HARDIRQS + select CPU_RMAP + default y + config XPS boolean depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index d936aec..2de93d0 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/aggregation.c b/net/batman-adv/aggregation.c index 3850a3e..1997725 100644 --- a/net/batman-adv/aggregation.c +++ b/net/batman-adv/aggregation.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/aggregation.h b/net/batman-adv/aggregation.h index 71a91b3..6ce305b 100644 --- a/net/batman-adv/aggregation.h +++ b/net/batman-adv/aggregation.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_debugfs.c b/net/batman-adv/bat_debugfs.c index 0ae81d0..0e9d435 100644 --- a/net/batman-adv/bat_debugfs.c +++ b/net/batman-adv/bat_debugfs.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -52,7 +52,6 @@ static void emit_log_char(struct debug_log *debug_log, char c) static int fdebug_log(struct debug_log *debug_log, char *fmt, ...) { - int printed_len; va_list args; static char debug_log_buf[256]; char *p; @@ -62,8 +61,7 @@ static int fdebug_log(struct debug_log *debug_log, char *fmt, ...) spin_lock_bh(&debug_log->lock); va_start(args, fmt); - printed_len = vscnprintf(debug_log_buf, sizeof(debug_log_buf), - fmt, args); + vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args); va_end(args); for (p = debug_log_buf; *p != 0; p++) diff --git a/net/batman-adv/bat_debugfs.h b/net/batman-adv/bat_debugfs.h index 72df532..bc9cda3 100644 --- a/net/batman-adv/bat_debugfs.h +++ b/net/batman-adv/bat_debugfs.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index cd7bb51..f7b93a0 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_sysfs.h b/net/batman-adv/bat_sysfs.h index 7f186c0..02f1fa7 100644 --- a/net/batman-adv/bat_sysfs.h +++ b/net/batman-adv/bat_sysfs.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index bbcd8f7..ad2ca92 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index ac54017..769c246 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 0065ffb..429a013 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 4585e65..2aa4391 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index b962982..50d3a59 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 5e728d0..55e527a 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 4f95777..f2131f4 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -34,6 +34,12 @@ /* protect update critical side of if_list - but not the content */ static DEFINE_SPINLOCK(if_list_lock); + +static int batman_skb_recv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *ptype, + struct net_device *orig_dev); + static void hardif_free_rcu(struct rcu_head *rcu) { struct batman_if *batman_if; @@ -549,8 +555,9 @@ out: /* receive a packet with the batman ethertype coming on a hard * interface */ -int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *ptype, struct net_device *orig_dev) +static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *ptype, + struct net_device *orig_dev) { struct bat_priv *bat_priv; struct batman_packet *batman_packet; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 30ec3b8..ad19543 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -35,10 +35,6 @@ struct batman_if *get_batman_if_by_netdev(struct net_device *net_dev); int hardif_enable_interface(struct batman_if *batman_if, char *iface_name); void hardif_disable_interface(struct batman_if *batman_if); void hardif_remove_interfaces(void); -int batman_skb_recv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *ptype, - struct net_device *orig_dev); int hardif_min_mtu(struct net_device *soft_iface); void update_min_mtu(struct net_device *soft_iface); diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 26e623e..fa26939 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 09216ad..eae2440 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -49,11 +49,6 @@ struct hashtable_t { /* allocates and clears the hash */ struct hashtable_t *hash_new(int size); -/* remove element if you already found the element you want to delete and don't - * need the overhead to find it again with hash_remove(). But usually, you - * don't want to use this function, as it fiddles with hash-internals. */ -void *hash_remove_element(struct hashtable_t *hash, struct element_t *elem); - /* free only the hashtable and the hash itself. */ void hash_destroy(struct hashtable_t *hash); diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index ecf6d7f..319a7cc 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -24,7 +24,6 @@ #include <linux/slab.h> #include "icmp_socket.h" #include "send.h" -#include "types.h" #include "hash.h" #include "originator.h" #include "hard-interface.h" diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index bf9b348..462b190 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_ #define _NET_BATMAN_ADV_ICMP_SOCKET_H_ -#include "types.h" - #define ICMP_SOCKET "socket" void bat_socket_init(void); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index b827f6a..06d956c 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -30,7 +30,6 @@ #include "translation-table.h" #include "hard-interface.h" #include "gateway_client.h" -#include "types.h" #include "vis.h" #include "hash.h" diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 65106fb..e235d7b 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -22,9 +22,6 @@ #ifndef _NET_BATMAN_ADV_MAIN_H_ #define _NET_BATMAN_ADV_MAIN_H_ -/* Kernel Programming */ -#define LINUX - #define DRIVER_AUTHOR "Marek Lindner <lindner_marek@yahoo.de>, " \ "Simon Wunderlich <siwu@hrz.tu-chemnitz.de>" #define DRIVER_DESC "B.A.T.M.A.N. advanced" @@ -54,7 +51,6 @@ #define NUM_WORDS (TQ_LOCAL_WINDOW_SIZE / WORD_BIT_SIZE) -#define PACKBUFF_SIZE 2000 #define LOG_BUF_LEN 8192 /* has to be a power of 2 */ #define VIS_INTERVAL 5000 /* 5 seconds */ @@ -96,15 +92,11 @@ #define DBG_ROUTES 2 /* route or hna added / changed / deleted */ #define DBG_ALL 3 -#define LOG_BUF_LEN 8192 /* has to be a power of 2 */ - /* * Vis */ -/* #define VIS_SUBCLUSTERS_DISABLED */ - /* * Kernel headers */ @@ -158,13 +150,6 @@ static inline void bat_dbg(char type __always_unused, } #endif -#define bat_warning(net_dev, fmt, arg...) \ - do { \ - struct net_device *_netdev = (net_dev); \ - struct bat_priv *_batpriv = netdev_priv(_netdev); \ - bat_dbg(DBG_ALL, _batpriv, fmt, ## arg); \ - pr_warning("%s: " fmt, _netdev->name, ## arg); \ - } while (0) #define bat_info(net_dev, fmt, arg...) \ do { \ struct net_device *_netdev = (net_dev); \ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 6b7fb6b..54863c9 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -247,7 +247,7 @@ static bool purge_orig_node(struct bat_priv *bat_priv, orig_node->hna_buff_len); /* update bonding candidates, we could have lost * some candidates. */ - update_bonding_candidates(bat_priv, orig_node); + update_bonding_candidates(orig_node); } } diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index d474ceb..8019fbd 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 2284e81..e757187 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -50,6 +50,7 @@ /* fragmentation defines */ #define UNI_FRAG_HEAD 0x01 +#define UNI_FRAG_LARGETAIL 0x02 struct batman_packet { uint8_t packet_type; diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c index defd37c..5bb6a61 100644 --- a/net/batman-adv/ring_buffer.c +++ b/net/batman-adv/ring_buffer.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h index 6b0cb9a..0395b27 100644 --- a/net/batman-adv/ring_buffer.h +++ b/net/batman-adv/ring_buffer.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 8828edd..8274140 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -28,7 +28,6 @@ #include "icmp_socket.h" #include "translation-table.h" #include "originator.h" -#include "types.h" #include "ring_buffer.h" #include "vis.h" #include "aggregation.h" @@ -433,8 +432,7 @@ static char count_real_packets(struct ethhdr *ethhdr, } /* copy primary address for bonding */ -static void mark_bonding_address(struct bat_priv *bat_priv, - struct orig_node *orig_node, +static void mark_bonding_address(struct orig_node *orig_node, struct orig_node *orig_neigh_node, struct batman_packet *batman_packet) @@ -447,8 +445,7 @@ static void mark_bonding_address(struct bat_priv *bat_priv, } /* mark possible bond.candidates in the neighbor list */ -void update_bonding_candidates(struct bat_priv *bat_priv, - struct orig_node *orig_node) +void update_bonding_candidates(struct orig_node *orig_node) { int candidates; int interference_candidate; @@ -730,9 +727,8 @@ void receive_bat_packet(struct ethhdr *ethhdr, update_orig(bat_priv, orig_node, ethhdr, batman_packet, if_incoming, hna_buff, hna_buff_len, is_duplicate); - mark_bonding_address(bat_priv, orig_node, - orig_neigh_node, batman_packet); - update_bonding_candidates(bat_priv, orig_node); + mark_bonding_address(orig_node, orig_neigh_node, batman_packet); + update_bonding_candidates(orig_node); /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { @@ -810,13 +806,11 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, { struct orig_node *orig_node; struct icmp_packet_rr *icmp_packet; - struct ethhdr *ethhdr; struct batman_if *batman_if; int ret; uint8_t dstaddr[ETH_ALEN]; icmp_packet = (struct icmp_packet_rr *)skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); /* add data to device queue */ if (icmp_packet->msg_type != ECHO_REQUEST) { @@ -848,7 +842,6 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, return NET_RX_DROP; icmp_packet = (struct icmp_packet_rr *)skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); memcpy(icmp_packet->orig, @@ -866,17 +859,15 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, } static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, - struct sk_buff *skb, size_t icmp_len) + struct sk_buff *skb) { struct orig_node *orig_node; struct icmp_packet *icmp_packet; - struct ethhdr *ethhdr; struct batman_if *batman_if; int ret; uint8_t dstaddr[ETH_ALEN]; icmp_packet = (struct icmp_packet *)skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); /* send TTL exceeded if packet is an echo request (traceroute) */ if (icmp_packet->msg_type != ECHO_REQUEST) { @@ -909,7 +900,6 @@ static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, return NET_RX_DROP; icmp_packet = (struct icmp_packet *) skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); memcpy(icmp_packet->orig, @@ -978,7 +968,7 @@ int recv_icmp_packet(struct sk_buff *skb, struct batman_if *recv_if) /* TTL exceeded */ if (icmp_packet->ttl < 2) - return recv_icmp_ttl_exceeded(bat_priv, skb, hdr_size); + return recv_icmp_ttl_exceeded(bat_priv, skb); ret = NET_RX_DROP; @@ -1001,7 +991,6 @@ int recv_icmp_packet(struct sk_buff *skb, struct batman_if *recv_if) return NET_RX_DROP; icmp_packet = (struct icmp_packet_rr *)skb->data; - ethhdr = (struct ethhdr *)skb_mac_header(skb); /* decrement ttl */ icmp_packet->ttl--; @@ -1193,7 +1182,7 @@ int route_unicast_packet(struct sk_buff *skb, struct batman_if *recv_if, dstaddr); if (unicast_packet->packet_type == BAT_UNICAST_FRAG && - 2 * skb->len - hdr_size <= batman_if->net_dev->mtu) { + frag_can_reassemble(skb, batman_if->net_dev->mtu)) { ret = frag_reassemble_skb(skb, bat_priv, &new_skb); diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index f108f23..a09d16f 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_ROUTING_H_ #define _NET_BATMAN_ADV_ROUTING_H_ -#include "types.h" - void slide_own_bcast_window(struct batman_if *batman_if); void receive_bat_packet(struct ethhdr *ethhdr, struct batman_packet *batman_packet, @@ -42,7 +40,6 @@ int recv_vis_packet(struct sk_buff *skb, struct batman_if *recv_if); int recv_bat_packet(struct sk_buff *skb, struct batman_if *recv_if); struct neigh_node *find_router(struct bat_priv *bat_priv, struct orig_node *orig_node, struct batman_if *recv_if); -void update_bonding_candidates(struct bat_priv *bat_priv, - struct orig_node *orig_node); +void update_bonding_candidates(struct orig_node *orig_node); #endif /* _NET_BATMAN_ADV_ROUTING_H_ */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index b89b9f7..8314276 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -25,7 +25,6 @@ #include "translation-table.h" #include "soft-interface.h" #include "hard-interface.h" -#include "types.h" #include "vis.h" #include "aggregation.h" #include "gateway_common.h" @@ -49,7 +48,7 @@ static unsigned long own_send_time(struct bat_priv *bat_priv) } /* when do we schedule a forwarded packet to be sent */ -static unsigned long forward_send_time(struct bat_priv *bat_priv) +static unsigned long forward_send_time(void) { return jiffies + msecs_to_jiffies(random32() % (JITTER/2)); } @@ -356,7 +355,7 @@ void schedule_forward_packet(struct orig_node *orig_node, else batman_packet->flags &= ~DIRECTLINK; - send_time = forward_send_time(bat_priv); + send_time = forward_send_time(); add_bat_packet_to_list(bat_priv, (unsigned char *)batman_packet, sizeof(struct batman_packet) + hna_buff_len, diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index c4cefa8..b68c272 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_SEND_H_ #define _NET_BATMAN_ADV_SEND_H_ -#include "types.h" - int send_skb_packet(struct sk_buff *skb, struct batman_if *batman_if, uint8_t *dst_addr); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index e89ede1..bd088f8 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -26,7 +26,6 @@ #include "send.h" #include "bat_debugfs.h" #include "translation-table.h" -#include "types.h" #include "hash.h" #include "gateway_common.h" #include "gateway_client.h" diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 02b7733..e7b0e1a 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index a633b5a4..7fb6726 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -22,7 +22,6 @@ #include "main.h" #include "translation-table.h" #include "soft-interface.h" -#include "types.h" #include "hash.h" #include "originator.h" diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 10c4c5c..f19931c 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ #define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ -#include "types.h" - int hna_local_init(struct bat_priv *bat_priv); void hna_local_add(struct net_device *soft_iface, uint8_t *addr); void hna_local_remove(struct bat_priv *bat_priv, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index bf3f6f5..7270405 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index d1a6113..121b11d 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -39,8 +39,8 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, (struct unicast_frag_packet *)skb->data; struct sk_buff *tmp_skb; struct unicast_packet *unicast_packet; - int hdr_len = sizeof(struct unicast_packet), - uni_diff = sizeof(struct unicast_frag_packet) - hdr_len; + int hdr_len = sizeof(struct unicast_packet); + int uni_diff = sizeof(struct unicast_frag_packet) - hdr_len; /* set skb to the first part and tmp_skb to the second part */ if (up->flags & UNI_FRAG_HEAD) { @@ -229,7 +229,9 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, struct unicast_frag_packet *frag1, *frag2; int uc_hdr_len = sizeof(struct unicast_packet); int ucf_hdr_len = sizeof(struct unicast_frag_packet); - int data_len = skb->len; + int data_len = skb->len - uc_hdr_len; + int large_tail = 0; + uint16_t seqno; if (!bat_priv->primary_if) goto dropped; @@ -237,10 +239,11 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, frag_skb = dev_alloc_skb(data_len - (data_len / 2) + ucf_hdr_len); if (!frag_skb) goto dropped; + skb_reserve(frag_skb, ucf_hdr_len); unicast_packet = (struct unicast_packet *) skb->data; memcpy(&tmp_uc, unicast_packet, uc_hdr_len); - skb_split(skb, frag_skb, data_len / 2); + skb_split(skb, frag_skb, data_len / 2 + uc_hdr_len); if (my_skb_head_push(skb, ucf_hdr_len - uc_hdr_len) < 0 || my_skb_head_push(frag_skb, ucf_hdr_len) < 0) @@ -258,13 +261,15 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, memcpy(frag1->orig, bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(frag2, frag1, sizeof(struct unicast_frag_packet)); - frag1->flags |= UNI_FRAG_HEAD; - frag2->flags &= ~UNI_FRAG_HEAD; + if (data_len & 1) + large_tail = UNI_FRAG_LARGETAIL; + + frag1->flags = UNI_FRAG_HEAD | large_tail; + frag2->flags = large_tail; - frag1->seqno = htons((uint16_t)atomic_inc_return( - &batman_if->frag_seqno)); - frag2->seqno = htons((uint16_t)atomic_inc_return( - &batman_if->frag_seqno)); + seqno = atomic_add_return(2, &batman_if->frag_seqno); + frag1->seqno = htons(seqno - 1); + frag2->seqno = htons(seqno); send_skb_packet(skb, batman_if, dstaddr); send_skb_packet(frag_skb, batman_if, dstaddr); @@ -281,7 +286,7 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct unicast_packet *unicast_packet; - struct orig_node *orig_node; + struct orig_node *orig_node = NULL; struct batman_if *batman_if; struct neigh_node *router; int data_len = skb->len; @@ -292,11 +297,6 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) orig_node = (struct orig_node *)gw_get_selected(bat_priv); - else - orig_node = ((struct orig_node *)hash_find(bat_priv->orig_hash, - compare_orig, - choose_orig, - ethhdr->h_dest)); /* check for hna host */ if (!orig_node) diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index e32b786..8897308 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -22,6 +22,8 @@ #ifndef _NET_BATMAN_ADV_UNICAST_H_ #define _NET_BATMAN_ADV_UNICAST_H_ +#include "packet.h" + #define FRAG_TIMEOUT 10000 /* purge frag list entrys after time in ms */ #define FRAG_BUFFER_SIZE 6 /* number of list elements in buffer */ @@ -32,4 +34,25 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv); int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, struct batman_if *batman_if, uint8_t dstaddr[]); +static inline int frag_can_reassemble(struct sk_buff *skb, int mtu) +{ + struct unicast_frag_packet *unicast_packet; + int uneven_correction = 0; + unsigned int merged_size; + + unicast_packet = (struct unicast_frag_packet *)skb->data; + + if (unicast_packet->flags & UNI_FRAG_LARGETAIL) { + if (unicast_packet->flags & UNI_FRAG_HEAD) + uneven_correction = 1; + else + uneven_correction = -1; + } + + merged_size = (skb->len - sizeof(struct unicast_frag_packet)) * 2; + merged_size += sizeof(struct unicast_packet) + uneven_correction; + + return merged_size <= mtu; +} + #endif /* _NET_BATMAN_ADV_UNICAST_H_ */ diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index de1022c..7db9ad8 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2008-2011 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/vis.h b/net/batman-adv/vis.h index 2c3b330..31b820d 100644 --- a/net/batman-adv/vis.h +++ b/net/batman-adv/vis.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008-2010 B.A.T.M.A.N. contributors: + * Copyright (C) 2008-2011 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 5564435..1461b19 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -297,6 +297,21 @@ void br_netpoll_disable(struct net_bridge_port *p) #endif +static int br_add_slave(struct net_device *dev, struct net_device *slave_dev) + +{ + struct net_bridge *br = netdev_priv(dev); + + return br_add_if(br, slave_dev); +} + +static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) +{ + struct net_bridge *br = netdev_priv(dev); + + return br_del_if(br, slave_dev); +} + static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, @@ -326,6 +341,8 @@ static const struct net_device_ops br_netdev_ops = { .ndo_netpoll_cleanup = br_netpoll_cleanup, .ndo_poll_controller = br_poll_controller, #endif + .ndo_add_slave = br_add_slave, + .ndo_del_slave = br_del_slave, }; static void br_dev_free(struct net_device *dev) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index d9d1e2b..dce8f00 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -148,6 +148,8 @@ static void del_nbp(struct net_bridge_port *p) netdev_rx_handler_unregister(dev); + netdev_set_master(dev, NULL); + br_multicast_del_port(p); kobject_uevent(&p->kobj, KOBJ_REMOVE); @@ -365,7 +367,7 @@ int br_min_mtu(const struct net_bridge *br) void br_features_recompute(struct net_bridge *br) { struct net_bridge_port *p; - unsigned long features, mask; + u32 features, mask; features = mask = br->feature_mask; if (list_empty(&br->port_list)) @@ -379,7 +381,7 @@ void br_features_recompute(struct net_bridge *br) } done: - br->dev->features = netdev_fix_features(features, NULL); + br->dev->features = netdev_fix_features(br->dev, features); } /* called with RTNL */ @@ -429,10 +431,14 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (br_netpoll_info(br) && ((err = br_netpoll_enable(p)))) goto err3; - err = netdev_rx_handler_register(dev, br_handle_frame, p); + err = netdev_set_master(dev, br->dev); if (err) goto err3; + err = netdev_rx_handler_register(dev, br_handle_frame, p); + if (err) + goto err4; + dev->priv_flags |= IFF_BRIDGE_PORT; dev_disable_lro(dev); @@ -455,6 +461,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) kobject_uevent(&p->kobj, KOBJ_ADD); return 0; + +err4: + netdev_set_master(dev, NULL); err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 4e1b620..f7afc36 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -182,7 +182,7 @@ struct net_bridge struct br_cpu_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; - unsigned long feature_mask; + u32 feature_mask; #ifdef CONFIG_BRIDGE_NETFILTER struct rtable fake_rtable; bool nf_call_iptables; diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c index 50a46af..2ed0056 100644 --- a/net/bridge/netfilter/ebt_ip6.c +++ b/net/bridge/netfilter/ebt_ip6.c @@ -22,9 +22,15 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_ip6.h> -struct tcpudphdr { - __be16 src; - __be16 dst; +union pkthdr { + struct { + __be16 src; + __be16 dst; + } tcpudphdr; + struct { + u8 type; + u8 code; + } icmphdr; }; static bool @@ -33,8 +39,8 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct ebt_ip6_info *info = par->matchinfo; const struct ipv6hdr *ih6; struct ipv6hdr _ip6h; - const struct tcpudphdr *pptr; - struct tcpudphdr _ports; + const union pkthdr *pptr; + union pkthdr _pkthdr; ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h); if (ih6 == NULL) @@ -56,26 +62,34 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO)) return false; - if (!(info->bitmask & EBT_IP6_DPORT) && - !(info->bitmask & EBT_IP6_SPORT)) + if (!(info->bitmask & ( EBT_IP6_DPORT | + EBT_IP6_SPORT | EBT_IP6_ICMP6))) return true; - pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports), - &_ports); + + /* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */ + pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr), + &_pkthdr); if (pptr == NULL) return false; if (info->bitmask & EBT_IP6_DPORT) { - u32 dst = ntohs(pptr->dst); + u16 dst = ntohs(pptr->tcpudphdr.dst); if (FWINV(dst < info->dport[0] || dst > info->dport[1], EBT_IP6_DPORT)) return false; } if (info->bitmask & EBT_IP6_SPORT) { - u32 src = ntohs(pptr->src); + u16 src = ntohs(pptr->tcpudphdr.src); if (FWINV(src < info->sport[0] || src > info->sport[1], EBT_IP6_SPORT)) return false; } - return true; + if ((info->bitmask & EBT_IP6_ICMP6) && + FWINV(pptr->icmphdr.type < info->icmpv6_type[0] || + pptr->icmphdr.type > info->icmpv6_type[1] || + pptr->icmphdr.code < info->icmpv6_code[0] || + pptr->icmphdr.code > info->icmpv6_code[1], + EBT_IP6_ICMP6)) + return false; } return true; } @@ -103,6 +117,14 @@ static int ebt_ip6_mt_check(const struct xt_mtchk_param *par) return -EINVAL; if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1]) return -EINVAL; + if (info->bitmask & EBT_IP6_ICMP6) { + if ((info->invflags & EBT_IP6_PROTO) || + info->protocol != IPPROTO_ICMPV6) + return -EINVAL; + if (info->icmpv6_type[0] > info->icmpv6_type[1] || + info->icmpv6_code[0] > info->icmpv6_code[1]) + return -EINVAL; + } return 0; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 16df053..5f1825d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1764,6 +1764,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; + xt_compat_init_offsets(AF_INET, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index c665de7..f1f98d9 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -23,10 +23,8 @@ #include <asm/atomic.h> #define MAX_PHY_LAYERS 7 -#define PHY_NAME_LEN 20 #define container_obj(layr) container_of(layr, struct cfcnfg, layer) -#define RFM_FRAGMENT_SIZE 4030 /* Information about CAIF physical interfaces held by Config Module in order * to manage physical interfaces diff --git a/net/caif/cfdgml.c b/net/caif/cfdgml.c index d3ed264..27dab26 100644 --- a/net/caif/cfdgml.c +++ b/net/caif/cfdgml.c @@ -18,7 +18,6 @@ #define DGM_CMD_BIT 0x80 #define DGM_FLOW_OFF 0x81 #define DGM_FLOW_ON 0x80 -#define DGM_CTRL_PKT_SIZE 1 #define DGM_MTU 1500 static int cfdgml_receive(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c index 9297f7d..8303fe3 100644 --- a/net/caif/cfserl.c +++ b/net/caif/cfserl.c @@ -25,7 +25,6 @@ struct cfserl { spinlock_t sync; bool usestx; }; -#define STXLEN(layr) (layr->usestx ? 1 : 0) static int cfserl_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/caif/cfutill.c b/net/caif/cfutill.c index efad410..315c0d6 100644 --- a/net/caif/cfutill.c +++ b/net/caif/cfutill.c @@ -20,7 +20,7 @@ #define UTIL_REMOTE_SHUTDOWN 0x82 #define UTIL_FLOW_OFF 0x81 #define UTIL_FLOW_ON 0x80 -#define UTIL_CTRL_PKT_SIZE 1 + static int cfutill_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfutill_transmit(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/caif/cfveil.c b/net/caif/cfveil.c index 3b425b1..c3b1dec 100644 --- a/net/caif/cfveil.c +++ b/net/caif/cfveil.c @@ -17,7 +17,7 @@ #define VEI_FLOW_OFF 0x81 #define VEI_FLOW_ON 0x80 #define VEI_SET_PIN 0x82 -#define VEI_CTRL_PKT_SIZE 1 + #define container_obj(layr) container_of(layr, struct cfsrvl, layer) static int cfvei_receive(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/core/dev.c b/net/core/dev.c index 8ae6631..9d8bfd9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -132,6 +132,7 @@ #include <trace/events/skb.h> #include <linux/pci.h> #include <linux/inetdevice.h> +#include <linux/cpu_rmap.h> #include "net-sysfs.h" @@ -1289,7 +1290,7 @@ static int __dev_close(struct net_device *dev) return retval; } -int dev_close_many(struct list_head *head) +static int dev_close_many(struct list_head *head) { struct net_device *dev, *tmp; LIST_HEAD(tmp_list); @@ -1597,6 +1598,48 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); } +/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change + * @dev: Network device + * @txq: number of queues available + * + * If real_num_tx_queues is changed the tc mappings may no longer be + * valid. To resolve this verify the tc mapping remains valid and if + * not NULL the mapping. With no priorities mapping to this + * offset/count pair it will no longer be used. In the worst case TC0 + * is invalid nothing can be done so disable priority mappings. If is + * expected that drivers will fix this mapping if they can before + * calling netif_set_real_num_tx_queues. + */ +static void netif_setup_tc(struct net_device *dev, unsigned int txq) +{ + int i; + struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; + + /* If TC0 is invalidated disable TC mapping */ + if (tc->offset + tc->count > txq) { + pr_warning("Number of in use tx queues changed " + "invalidating tc mappings. Priority " + "traffic classification disabled!\n"); + dev->num_tc = 0; + return; + } + + /* Invalidated prio to tc mappings set to TC0 */ + for (i = 1; i < TC_BITMASK + 1; i++) { + int q = netdev_get_prio_tc_map(dev, i); + + tc = &dev->tc_to_txq[q]; + if (tc->offset + tc->count > txq) { + pr_warning("Number of in use tx queues " + "changed. Priority %i to tc " + "mapping %i is no longer valid " + "setting map to 0\n", + i, q); + netdev_set_prio_tc_map(dev, i, 0); + } + } +} + /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -1608,7 +1651,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; - if (dev->reg_state == NETREG_REGISTERED) { + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, @@ -1616,6 +1660,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (rc) return rc; + if (dev->num_tc) + netif_setup_tc(dev, txq); + if (txq < dev->real_num_tx_queues) qdisc_reset_all_tx_gt(dev, txq); } @@ -1815,7 +1862,7 @@ EXPORT_SYMBOL(skb_checksum_help); * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) +struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; @@ -2003,7 +2050,7 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) protocol == htons(ETH_P_FCOE))); } -static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features) +static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features) { if (!can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; @@ -2015,10 +2062,10 @@ static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features return features; } -int netif_skb_features(struct sk_buff *skb) +u32 netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - int features = skb->dev->features; + u32 features = skb->dev->features; if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; @@ -2063,7 +2110,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int rc = NETDEV_TX_OK; if (likely(!skb->next)) { - int features; + u32 features; /* * If device doesnt need skb->dst, release it right now while @@ -2165,6 +2212,8 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, unsigned int num_tx_queues) { u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); @@ -2173,13 +2222,19 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, return hash; } + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else hash = (__force u16) skb->protocol ^ skb->rxhash; hash = jhash_1word(hash, hashrnd); - return (u16) (((u64) hash * num_tx_queues) >> 32); + return (u16) (((u64) hash * qcount) >> 32) + qoffset; } EXPORT_SYMBOL(__skb_tx_hash); @@ -2276,15 +2331,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); - bool contended = qdisc_is_running(q); + bool contended; int rc; + qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits __QDISC_STATE_RUNNING owner to get the lock more often * and dequeue packets faster. */ + contended = qdisc_is_running(q); if (unlikely(contended)) spin_lock(&q->busylock); @@ -2302,7 +2360,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); - qdisc_skb_cb(skb)->pkt_len = skb->len; qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { @@ -2317,7 +2374,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, rc = NET_XMIT_SUCCESS; } else { skb_dst_force(skb); - rc = qdisc_enqueue_root(skb, q); + rc = q->enqueue(skb, q) & NET_XMIT_MASK; if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -2536,6 +2593,53 @@ EXPORT_SYMBOL(__skb_get_rxhash); struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; EXPORT_SYMBOL(rps_sock_flow_table); +static struct rps_dev_flow * +set_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow *rflow, u16 next_cpu) +{ + u16 tcpu; + + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) { +#ifdef CONFIG_RFS_ACCEL + struct netdev_rx_queue *rxqueue; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *old_rflow; + u32 flow_id; + u16 rxq_index; + int rc; + + /* Should we steer this flow to a different hardware queue? */ + if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap) + goto out; + rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); + if (rxq_index == skb_get_rx_queue(skb)) + goto out; + + rxqueue = dev->_rx + rxq_index; + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (!flow_table) + goto out; + flow_id = skb->rxhash & flow_table->mask; + rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, + rxq_index, flow_id); + if (rc < 0) + goto out; + old_rflow = rflow; + rflow = &flow_table->flows[flow_id]; + rflow->cpu = next_cpu; + rflow->filter = rc; + if (old_rflow->filter == rflow->filter) + old_rflow->filter = RPS_NO_FILTER; + out: +#endif + rflow->last_qtail = + per_cpu(softnet_data, tcpu).input_queue_head; + } + + return rflow; +} + /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. @@ -2607,12 +2711,9 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (unlikely(tcpu != next_cpu) && (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - - rflow->last_qtail)) >= 0)) { - tcpu = rflow->cpu = next_cpu; - if (tcpu != RPS_NO_CPU) - rflow->last_qtail = per_cpu(softnet_data, - tcpu).input_queue_head; - } + rflow->last_qtail)) >= 0)) + rflow = set_rps_cpu(dev, skb, rflow, next_cpu); + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; @@ -2633,6 +2734,46 @@ done: return cpu; } +#ifdef CONFIG_RFS_ACCEL + +/** + * rps_may_expire_flow - check whether an RFS hardware filter may be removed + * @dev: Device on which the filter was set + * @rxq_index: RX queue index + * @flow_id: Flow ID passed to ndo_rx_flow_steer() + * @filter_id: Filter ID returned by ndo_rx_flow_steer() + * + * Drivers that implement ndo_rx_flow_steer() should periodically call + * this function for each installed filter and remove the filters for + * which it returns %true. + */ +bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id) +{ + struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *rflow; + bool expire = true; + int cpu; + + rcu_read_lock(); + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (flow_table && flow_id <= flow_table->mask) { + rflow = &flow_table->flows[flow_id]; + cpu = ACCESS_ONCE(rflow->cpu); + if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + ((int)(per_cpu(softnet_data, cpu).input_queue_head - + rflow->last_qtail) < + (int)(10 * flow_table->mask))) + expire = false; + } + rcu_read_unlock(); + return expire; +} +EXPORT_SYMBOL(rps_may_expire_flow); + +#endif /* CONFIG_RFS_ACCEL */ + /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { @@ -2968,7 +3109,8 @@ static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and * ARP on active-backup slaves with arp_validate enabled. */ -int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) +static int __skb_bond_should_drop(struct sk_buff *skb, + struct net_device *master) { struct net_device *dev = skb->dev; @@ -3002,14 +3144,12 @@ int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) } return 0; } -EXPORT_SYMBOL(__skb_bond_should_drop); static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct net_device *orig_dev; - struct net_device *master; struct net_device *null_or_orig; struct net_device *orig_or_bond; int ret = NET_RX_DROP; @@ -3036,15 +3176,19 @@ static int __netif_receive_skb(struct sk_buff *skb) */ null_or_orig = NULL; orig_dev = skb->dev; - master = ACCESS_ONCE(orig_dev->master); if (skb->deliver_no_wcard) null_or_orig = orig_dev; - else if (master) { - if (skb_bond_should_drop(skb, master)) { - skb->deliver_no_wcard = 1; - null_or_orig = orig_dev; /* deliver only exact match */ - } else - skb->dev = master; + else if (netif_is_bond_slave(orig_dev)) { + struct net_device *bond_master = ACCESS_ONCE(orig_dev->master); + + if (likely(bond_master)) { + if (__skb_bond_should_drop(skb, bond_master)) { + skb->deliver_no_wcard = 1; + /* deliver only exact match */ + null_or_orig = orig_dev; + } else + skb->dev = bond_master; + } } __this_cpu_inc(softnet_data.processed); @@ -3917,12 +4061,15 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos) void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net_device *dev = (v == SEQ_START_TOKEN) ? - first_net_device(seq_file_net(seq)) : - next_net_device((struct net_device *)v); + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + dev = first_net_device_rcu(seq_file_net(seq)); + else + dev = next_net_device_rcu(dev); ++*pos; - return rcu_dereference(dev); + return dev; } void dev_seq_stop(struct seq_file *seq, void *v) @@ -4206,15 +4353,14 @@ static int __init dev_proc_init(void) /** - * netdev_set_master - set up master/slave pair + * netdev_set_master - set up master pointer * @slave: slave device * @master: new master device * * Changes the master device of the slave. Pass %NULL to break the * bonding. The caller must hold the RTNL semaphore. On a failure * a negative errno code is returned. On success the reference counts - * are adjusted, %RTM_NEWLINK is sent to the routing socket and the - * function returns zero. + * are adjusted and the function returns zero. */ int netdev_set_master(struct net_device *slave, struct net_device *master) { @@ -4234,6 +4380,29 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) synchronize_net(); dev_put(old); } + return 0; +} +EXPORT_SYMBOL(netdev_set_master); + +/** + * netdev_set_bond_master - set up bonding master/slave pair + * @slave: slave device + * @master: new master device + * + * Changes the master device of the slave. Pass %NULL to break the + * bonding. The caller must hold the RTNL semaphore. On a failure + * a negative errno code is returned. On success %RTM_NEWLINK is sent + * to the routing socket and the function returns zero. + */ +int netdev_set_bond_master(struct net_device *slave, struct net_device *master) +{ + int err; + + ASSERT_RTNL(); + + err = netdev_set_master(slave, master); + if (err) + return err; if (master) slave->flags |= IFF_SLAVE; else @@ -4242,7 +4411,7 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); return 0; } -EXPORT_SYMBOL(netdev_set_master); +EXPORT_SYMBOL(netdev_set_bond_master); static void dev_change_rx_flags(struct net_device *dev, int flags) { @@ -4579,6 +4748,17 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) EXPORT_SYMBOL(dev_set_mtu); /** + * dev_set_group - Change group this device belongs to + * @dev: device + * @new_group: group this device should belong to + */ +void dev_set_group(struct net_device *dev, int new_group) +{ + dev->group = new_group; +} +EXPORT_SYMBOL(dev_set_group); + +/** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address @@ -5069,41 +5249,55 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } -unsigned long netdev_fix_features(unsigned long features, const char *name) +u32 netdev_fix_features(struct net_device *dev, u32 features) { + /* Fix illegal checksum combinations */ + if ((features & NETIF_F_HW_CSUM) && + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_info(dev, "mixed HW and IP checksum settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); + } + + if ((features & NETIF_F_NO_CSUM) && + (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_info(dev, "mixed no checksumming and other settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); + } + /* Fix illegal SG+CSUM combinations. */ if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no " - "checksum feature.\n", name); + netdev_info(dev, + "Dropping NETIF_F_SG since no checksum feature.\n"); features &= ~NETIF_F_SG; } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no " - "SG feature.\n", name); + netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n"); features &= ~NETIF_F_TSO; } + /* Software GSO depends on SG. */ + if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { + netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); + features &= ~NETIF_F_GSO; + } + + /* UFO needs SG and checksumming */ if (features & NETIF_F_UFO) { /* maybe split UFO into V4 and V6? */ if (!((features & NETIF_F_GEN_CSUM) || (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no checksum offload features.\n", - name); + netdev_info(dev, + "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; } if (!(features & NETIF_F_SG)) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_SG feature.\n", name); + netdev_info(dev, + "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); features &= ~NETIF_F_UFO; } } @@ -5112,6 +5306,37 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } EXPORT_SYMBOL(netdev_fix_features); +void netdev_update_features(struct net_device *dev) +{ + u32 features; + int err = 0; + + features = netdev_get_wanted_features(dev); + + if (dev->netdev_ops->ndo_fix_features) + features = dev->netdev_ops->ndo_fix_features(dev, features); + + /* driver might be less strict about feature dependencies */ + features = netdev_fix_features(dev, features); + + if (dev->features == features) + return; + + netdev_info(dev, "Features changed: 0x%08x -> 0x%08x\n", + dev->features, features); + + if (dev->netdev_ops->ndo_set_features) + err = dev->netdev_ops->ndo_set_features(dev, features); + + if (!err) + dev->features = features; + else if (err < 0) + netdev_err(dev, + "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n", + err, features, dev->features); +} +EXPORT_SYMBOL(netdev_update_features); + /** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from @@ -5246,26 +5471,18 @@ int register_netdevice(struct net_device *dev) if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Fix illegal checksum combinations */ - if ((dev->features & NETIF_F_HW_CSUM) && - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); - } - - if ((dev->features & NETIF_F_NO_CSUM) && - (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); - } + /* Transfer changeable features to wanted_features and enable + * software offloads (GSO and GRO). + */ + dev->hw_features |= NETIF_F_SOFT_FEATURES; + dev->wanted_features = (dev->features & dev->hw_features) + | NETIF_F_SOFT_FEATURES; - dev->features = netdev_fix_features(dev->features, dev->name); + /* Avoid warning from netdev_fix_features() for GSO without SG */ + if (!(dev->wanted_features & NETIF_F_SG)) + dev->wanted_features &= ~NETIF_F_GSO; - /* Enable software GSO if SG is supported. */ - if (dev->features & NETIF_F_SG) - dev->features |= NETIF_F_GSO; + netdev_update_features(dev); /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, * vlan_dev_init() will do the dev->features check, so these features @@ -5687,6 +5904,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #endif strcpy(dev->name, name); + dev->group = INIT_NETDEV_GROUP; return dev; free_all: @@ -6001,8 +6219,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask) +u32 netdev_increment_features(u32 all, u32 one, u32 mask) { /* If device needs checksumming, downgrade to it. */ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) diff --git a/net/core/dst.c b/net/core/dst.c index b99c7c7..91104d3 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -164,7 +164,9 @@ int dst_discard(struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard); -void *dst_alloc(struct dst_ops *ops) +const u32 dst_default_metrics[RTAX_MAX]; + +void *dst_alloc(struct dst_ops *ops, int initial_ref) { struct dst_entry *dst; @@ -175,11 +177,12 @@ void *dst_alloc(struct dst_ops *ops) dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; - atomic_set(&dst->__refcnt, 0); + atomic_set(&dst->__refcnt, initial_ref); dst->ops = ops; dst->lastuse = jiffies; dst->path = dst; dst->input = dst->output = dst_discard; + dst_init_metrics(dst, dst_default_metrics, true); #if RT_CACHE_DEBUG >= 2 atomic_inc(&dst_total); #endif @@ -282,6 +285,42 @@ void dst_release(struct dst_entry *dst) } EXPORT_SYMBOL(dst_release); +u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + + if (p) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + kfree(p); + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} +EXPORT_SYMBOL(dst_cow_metrics_generic); + +/* Caller asserts that dst_metrics_read_only(dst) is false. */ +void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + unsigned long prev, new; + + new = (unsigned long) dst_default_metrics; + prev = cmpxchg(&dst->_metrics, old, new); + if (prev == old) + kfree(__DST_METRICS_PTR(old)); +} +EXPORT_SYMBOL(__dst_destroy_metrics_generic); + /** * skb_dst_set_noref - sets skb dst, without a reference * @skb: buffer diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ff23029..66cdc76 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -34,12 +34,6 @@ u32 ethtool_op_get_link(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_link); -u32 ethtool_op_get_rx_csum(struct net_device *dev) -{ - return (dev->features & NETIF_F_ALL_CSUM) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_rx_csum); - u32 ethtool_op_get_tx_csum(struct net_device *dev) { return (dev->features & NETIF_F_ALL_CSUM) != 0; @@ -55,6 +49,7 @@ int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) return 0; } +EXPORT_SYMBOL(ethtool_op_set_tx_csum); int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) { @@ -171,6 +166,306 @@ EXPORT_SYMBOL(ethtool_ntuple_flush); /* Handlers for each ethtool command */ +#define ETHTOOL_DEV_FEATURE_WORDS 1 + +static int ethtool_get_features(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_gfeatures cmd = { + .cmd = ETHTOOL_GFEATURES, + .size = ETHTOOL_DEV_FEATURE_WORDS, + }; + struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = { + { + .available = dev->hw_features, + .requested = dev->wanted_features, + .active = dev->features, + .never_changed = NETIF_F_NEVER_CHANGE, + }, + }; + u32 __user *sizeaddr; + u32 copy_size; + + sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); + if (get_user(copy_size, sizeaddr)) + return -EFAULT; + + if (copy_size > ETHTOOL_DEV_FEATURE_WORDS) + copy_size = ETHTOOL_DEV_FEATURE_WORDS; + + if (copy_to_user(useraddr, &cmd, sizeof(cmd))) + return -EFAULT; + useraddr += sizeof(cmd); + if (copy_to_user(useraddr, features, copy_size * sizeof(*features))) + return -EFAULT; + + return 0; +} + +static int ethtool_set_features(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_sfeatures cmd; + struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; + int ret = 0; + + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + useraddr += sizeof(cmd); + + if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS) + return -EINVAL; + + if (copy_from_user(features, useraddr, sizeof(features))) + return -EFAULT; + + if (features[0].valid & ~NETIF_F_ETHTOOL_BITS) + return -EINVAL; + + if (features[0].valid & ~dev->hw_features) { + features[0].valid &= dev->hw_features; + ret |= ETHTOOL_F_UNSUPPORTED; + } + + dev->wanted_features &= ~features[0].valid; + dev->wanted_features |= features[0].valid & features[0].requested; + netdev_update_features(dev); + + if ((dev->wanted_features ^ dev->features) & features[0].valid) + ret |= ETHTOOL_F_WISH; + + return ret; +} + +static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = { + /* NETIF_F_SG */ "tx-scatter-gather", + /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4", + /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded", + /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic", + /* NETIF_F_IPV6_CSUM */ "tx_checksum-ipv6", + /* NETIF_F_HIGHDMA */ "highdma", + /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist", + /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert", + + /* NETIF_F_HW_VLAN_RX */ "rx-vlan-hw-parse", + /* NETIF_F_HW_VLAN_FILTER */ "rx-vlan-filter", + /* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged", + /* NETIF_F_GSO */ "tx-generic-segmentation", + /* NETIF_F_LLTX */ "tx-lockless", + /* NETIF_F_NETNS_LOCAL */ "netns-local", + /* NETIF_F_GRO */ "rx-gro", + /* NETIF_F_LRO */ "rx-lro", + + /* NETIF_F_TSO */ "tx-tcp-segmentation", + /* NETIF_F_UFO */ "tx-udp-fragmentation", + /* NETIF_F_GSO_ROBUST */ "tx-gso-robust", + /* NETIF_F_TSO_ECN */ "tx-tcp-ecn-segmentation", + /* NETIF_F_TSO6 */ "tx-tcp6-segmentation", + /* NETIF_F_FSO */ "tx-fcoe-segmentation", + "", + "", + + /* NETIF_F_FCOE_CRC */ "tx-checksum-fcoe-crc", + /* NETIF_F_SCTP_CSUM */ "tx-checksum-sctp", + /* NETIF_F_FCOE_MTU */ "fcoe-mtu", + /* NETIF_F_NTUPLE */ "rx-ntuple-filter", + /* NETIF_F_RXHASH */ "rx-hashing", + /* NETIF_F_RXCSUM */ "rx-checksum", + "", + "", +}; + +static int __ethtool_get_sset_count(struct net_device *dev, int sset) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (sset == ETH_SS_FEATURES) + return ARRAY_SIZE(netdev_features_strings); + + if (ops && ops->get_sset_count && ops->get_strings) + return ops->get_sset_count(dev, sset); + else + return -EOPNOTSUPP; +} + +static void __ethtool_get_strings(struct net_device *dev, + u32 stringset, u8 *data) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (stringset == ETH_SS_FEATURES) + memcpy(data, netdev_features_strings, + sizeof(netdev_features_strings)); + else + /* ops->get_strings is valid because checked earlier */ + ops->get_strings(dev, stringset, data); +} + +static u32 ethtool_get_feature_mask(u32 eth_cmd) +{ + /* feature masks of legacy discrete ethtool ops */ + + switch (eth_cmd) { + case ETHTOOL_GTXCSUM: + case ETHTOOL_STXCSUM: + return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM; + case ETHTOOL_GRXCSUM: + case ETHTOOL_SRXCSUM: + return NETIF_F_RXCSUM; + case ETHTOOL_GSG: + case ETHTOOL_SSG: + return NETIF_F_SG; + case ETHTOOL_GTSO: + case ETHTOOL_STSO: + return NETIF_F_ALL_TSO; + case ETHTOOL_GUFO: + case ETHTOOL_SUFO: + return NETIF_F_UFO; + case ETHTOOL_GGSO: + case ETHTOOL_SGSO: + return NETIF_F_GSO; + case ETHTOOL_GGRO: + case ETHTOOL_SGRO: + return NETIF_F_GRO; + default: + BUG(); + } +} + +static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops) + return NULL; + + switch (ethcmd) { + case ETHTOOL_GTXCSUM: + return ops->get_tx_csum; + case ETHTOOL_GRXCSUM: + return ops->get_rx_csum; + case ETHTOOL_SSG: + return ops->get_sg; + case ETHTOOL_STSO: + return ops->get_tso; + case ETHTOOL_SUFO: + return ops->get_ufo; + default: + return NULL; + } +} + +static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev) +{ + return !!(dev->features & NETIF_F_ALL_CSUM); +} + +static int ethtool_get_one_feature(struct net_device *dev, + char __user *useraddr, u32 ethcmd) +{ + u32 mask = ethtool_get_feature_mask(ethcmd); + struct ethtool_value edata = { + .cmd = ethcmd, + .data = !!(dev->features & mask), + }; + + /* compatibility with discrete get_ ops */ + if (!(dev->hw_features & mask)) { + u32 (*actor)(struct net_device *); + + actor = __ethtool_get_one_feature_actor(dev, ethcmd); + + /* bug compatibility with old get_rx_csum */ + if (ethcmd == ETHTOOL_GRXCSUM && !actor) + actor = __ethtool_get_rx_csum_oldbug; + + if (actor) + edata.data = actor(dev); + } + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} + +static int __ethtool_set_tx_csum(struct net_device *dev, u32 data); +static int __ethtool_set_rx_csum(struct net_device *dev, u32 data); +static int __ethtool_set_sg(struct net_device *dev, u32 data); +static int __ethtool_set_tso(struct net_device *dev, u32 data); +static int __ethtool_set_ufo(struct net_device *dev, u32 data); + +static int ethtool_set_one_feature(struct net_device *dev, + void __user *useraddr, u32 ethcmd) +{ + struct ethtool_value edata; + u32 mask; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + mask = ethtool_get_feature_mask(ethcmd); + mask &= dev->hw_features; + if (mask) { + if (edata.data) + dev->wanted_features |= mask; + else + dev->wanted_features &= ~mask; + + netdev_update_features(dev); + return 0; + } + + /* Driver is not converted to ndo_fix_features or does not + * support changing this offload. In the latter case it won't + * have corresponding ethtool_ops field set. + * + * Following part is to be removed after all drivers advertise + * their changeable features in netdev->hw_features and stop + * using discrete offload setting ops. + */ + + switch (ethcmd) { + case ETHTOOL_STXCSUM: + return __ethtool_set_tx_csum(dev, edata.data); + case ETHTOOL_SRXCSUM: + return __ethtool_set_rx_csum(dev, edata.data); + case ETHTOOL_SSG: + return __ethtool_set_sg(dev, edata.data); + case ETHTOOL_STSO: + return __ethtool_set_tso(dev, edata.data); + case ETHTOOL_SUFO: + return __ethtool_set_ufo(dev, edata.data); + default: + return -EOPNOTSUPP; + } +} + +static int __ethtool_set_flags(struct net_device *dev, u32 data) +{ + u32 changed; + + if (data & ~flags_dup_features) + return -EINVAL; + + /* legacy set_flags() op */ + if (dev->ethtool_ops->set_flags) { + if (unlikely(dev->hw_features & flags_dup_features)) + netdev_warn(dev, + "driver BUG: mixed hw_features and set_flags()\n"); + return dev->ethtool_ops->set_flags(dev, data); + } + + /* allow changing only bits set in hw_features */ + changed = (data ^ dev->wanted_features) & flags_dup_features; + if (changed & ~dev->hw_features) + return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; + + dev->wanted_features = + (dev->wanted_features & ~changed) | data; + + netdev_update_features(dev); + + return 0; +} + static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; @@ -251,14 +546,10 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, void __user *useraddr) { struct ethtool_sset_info info; - const struct ethtool_ops *ops = dev->ethtool_ops; u64 sset_mask; int i, idx = 0, n_bits = 0, ret, rc; u32 *info_buf = NULL; - if (!ops->get_sset_count) - return -EOPNOTSUPP; - if (copy_from_user(&info, useraddr, sizeof(info))) return -EFAULT; @@ -285,7 +576,7 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, if (!(sset_mask & (1ULL << i))) continue; - rc = ops->get_sset_count(dev, i); + rc = __ethtool_get_sset_count(dev, i); if (rc >= 0) { info.sset_mask |= (1ULL << i); info_buf[idx++] = rc; @@ -1091,6 +1382,9 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data) { int err; + if (data && !(dev->features & NETIF_F_ALL_CSUM)) + return -EINVAL; + if (!data && dev->ethtool_ops->set_tso) { err = dev->ethtool_ops->set_tso(dev, 0); if (err) @@ -1105,145 +1399,55 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data) return dev->ethtool_ops->set_sg(dev, data); } -static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr) +static int __ethtool_set_tx_csum(struct net_device *dev, u32 data) { - struct ethtool_value edata; int err; if (!dev->ethtool_ops->set_tx_csum) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (!edata.data && dev->ethtool_ops->set_sg) { + if (!data && dev->ethtool_ops->set_sg) { err = __ethtool_set_sg(dev, 0); if (err) return err; } - return dev->ethtool_ops->set_tx_csum(dev, edata.data); + return dev->ethtool_ops->set_tx_csum(dev, data); } -EXPORT_SYMBOL(ethtool_op_set_tx_csum); -static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr) +static int __ethtool_set_rx_csum(struct net_device *dev, u32 data) { - struct ethtool_value edata; - if (!dev->ethtool_ops->set_rx_csum) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (!edata.data && dev->ethtool_ops->set_sg) + if (!data) dev->features &= ~NETIF_F_GRO; - return dev->ethtool_ops->set_rx_csum(dev, edata.data); + return dev->ethtool_ops->set_rx_csum(dev, data); } -static int ethtool_set_sg(struct net_device *dev, char __user *useraddr) +static int __ethtool_set_tso(struct net_device *dev, u32 data) { - struct ethtool_value edata; - - if (!dev->ethtool_ops->set_sg) - return -EOPNOTSUPP; - - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (edata.data && - !(dev->features & NETIF_F_ALL_CSUM)) - return -EINVAL; - - return __ethtool_set_sg(dev, edata.data); -} - -static int ethtool_set_tso(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; - if (!dev->ethtool_ops->set_tso) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (edata.data && !(dev->features & NETIF_F_SG)) + if (data && !(dev->features & NETIF_F_SG)) return -EINVAL; - return dev->ethtool_ops->set_tso(dev, edata.data); + return dev->ethtool_ops->set_tso(dev, data); } -static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) +static int __ethtool_set_ufo(struct net_device *dev, u32 data) { - struct ethtool_value edata; - if (!dev->ethtool_ops->set_ufo) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - if (edata.data && !(dev->features & NETIF_F_SG)) + if (data && !(dev->features & NETIF_F_SG)) return -EINVAL; - if (edata.data && !((dev->features & NETIF_F_GEN_CSUM) || + if (data && !((dev->features & NETIF_F_GEN_CSUM) || (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) return -EINVAL; - return dev->ethtool_ops->set_ufo(dev, edata.data); -} - -static int ethtool_get_gso(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata = { ETHTOOL_GGSO }; - - edata.data = dev->features & NETIF_F_GSO; - if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; - return 0; -} - -static int ethtool_set_gso(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; - - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - if (edata.data) - dev->features |= NETIF_F_GSO; - else - dev->features &= ~NETIF_F_GSO; - return 0; -} - -static int ethtool_get_gro(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata = { ETHTOOL_GGRO }; - - edata.data = dev->features & NETIF_F_GRO; - if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; - return 0; -} - -static int ethtool_set_gro(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; - - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (edata.data) { - u32 rxcsum = dev->ethtool_ops->get_rx_csum ? - dev->ethtool_ops->get_rx_csum(dev) : - ethtool_op_get_rx_csum(dev); - - if (!rxcsum) - return -EINVAL; - dev->features |= NETIF_F_GRO; - } else - dev->features &= ~NETIF_F_GRO; - - return 0; + return dev->ethtool_ops->set_ufo(dev, data); } static int ethtool_self_test(struct net_device *dev, char __user *useraddr) @@ -1287,17 +1491,13 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) { struct ethtool_gstrings gstrings; - const struct ethtool_ops *ops = dev->ethtool_ops; u8 *data; int ret; - if (!ops->get_strings || !ops->get_sset_count) - return -EOPNOTSUPP; - if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) return -EFAULT; - ret = ops->get_sset_count(dev, gstrings.string_set); + ret = __ethtool_get_sset_count(dev, gstrings.string_set); if (ret < 0) return ret; @@ -1307,7 +1507,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) if (!data) return -ENOMEM; - ops->get_strings(dev, gstrings.string_set, data); + __ethtool_get_strings(dev, gstrings.string_set, data); ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) @@ -1317,7 +1517,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) goto out; ret = 0; - out: +out: kfree(data); return ret; } @@ -1458,7 +1658,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) void __user *useraddr = ifr->ifr_data; u32 ethcmd; int rc; - unsigned long old_features; + u32 old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; @@ -1500,6 +1700,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: + case ETHTOOL_GFEATURES: break; default: if (!capable(CAP_NET_ADMIN)) @@ -1570,42 +1771,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SPAUSEPARAM: rc = ethtool_set_pauseparam(dev, useraddr); break; - case ETHTOOL_GRXCSUM: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_rx_csum ? - dev->ethtool_ops->get_rx_csum : - ethtool_op_get_rx_csum)); - break; - case ETHTOOL_SRXCSUM: - rc = ethtool_set_rx_csum(dev, useraddr); - break; - case ETHTOOL_GTXCSUM: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_tx_csum ? - dev->ethtool_ops->get_tx_csum : - ethtool_op_get_tx_csum)); - break; - case ETHTOOL_STXCSUM: - rc = ethtool_set_tx_csum(dev, useraddr); - break; - case ETHTOOL_GSG: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_sg ? - dev->ethtool_ops->get_sg : - ethtool_op_get_sg)); - break; - case ETHTOOL_SSG: - rc = ethtool_set_sg(dev, useraddr); - break; - case ETHTOOL_GTSO: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_tso ? - dev->ethtool_ops->get_tso : - ethtool_op_get_tso)); - break; - case ETHTOOL_STSO: - rc = ethtool_set_tso(dev, useraddr); - break; case ETHTOOL_TEST: rc = ethtool_self_test(dev, useraddr); break; @@ -1621,21 +1786,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPERMADDR: rc = ethtool_get_perm_addr(dev, useraddr); break; - case ETHTOOL_GUFO: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_ufo ? - dev->ethtool_ops->get_ufo : - ethtool_op_get_ufo)); - break; - case ETHTOOL_SUFO: - rc = ethtool_set_ufo(dev, useraddr); - break; - case ETHTOOL_GGSO: - rc = ethtool_get_gso(dev, useraddr); - break; - case ETHTOOL_SGSO: - rc = ethtool_set_gso(dev, useraddr); - break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, (dev->ethtool_ops->get_flags ? @@ -1643,8 +1793,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) ethtool_op_get_flags)); break; case ETHTOOL_SFLAGS: - rc = ethtool_set_value(dev, useraddr, - dev->ethtool_ops->set_flags); + rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags); break; case ETHTOOL_GPFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, @@ -1666,12 +1815,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXCLSRLINS: rc = ethtool_set_rxnfc(dev, ethcmd, useraddr); break; - case ETHTOOL_GGRO: - rc = ethtool_get_gro(dev, useraddr); - break; - case ETHTOOL_SGRO: - rc = ethtool_set_gro(dev, useraddr); - break; case ETHTOOL_FLASHDEV: rc = ethtool_flash_device(dev, useraddr); break; @@ -1693,6 +1836,30 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXFHINDIR: rc = ethtool_set_rxfh_indir(dev, useraddr); break; + case ETHTOOL_GFEATURES: + rc = ethtool_get_features(dev, useraddr); + break; + case ETHTOOL_SFEATURES: + rc = ethtool_set_features(dev, useraddr); + break; + case ETHTOOL_GTXCSUM: + case ETHTOOL_GRXCSUM: + case ETHTOOL_GSG: + case ETHTOOL_GTSO: + case ETHTOOL_GUFO: + case ETHTOOL_GGSO: + case ETHTOOL_GGRO: + rc = ethtool_get_one_feature(dev, useraddr, ethcmd); + break; + case ETHTOOL_STXCSUM: + case ETHTOOL_SRXCSUM: + case ETHTOOL_SSG: + case ETHTOOL_STSO: + case ETHTOOL_SUFO: + case ETHTOOL_SGSO: + case ETHTOOL_SGRO: + rc = ethtool_set_one_feature(dev, useraddr, ethcmd); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/filter.c b/net/core/filter.c index afc5837..232b187 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -142,14 +142,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) if (err) return err; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = sk_run_filter(skb, filter->insns); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } - rcu_read_unlock_bh(); + rcu_read_unlock(); return err; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 60a9029..799f06e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -316,7 +316,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) { size_t size = entries * sizeof(struct neighbour *); struct neigh_hash_table *ret; - struct neighbour **buckets; + struct neighbour __rcu **buckets; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) @@ -324,14 +324,14 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) if (size <= PAGE_SIZE) buckets = kzalloc(size, GFP_ATOMIC); else - buckets = (struct neighbour **) + buckets = (struct neighbour __rcu **) __get_free_pages(GFP_ATOMIC | __GFP_ZERO, get_order(size)); if (!buckets) { kfree(ret); return NULL; } - rcu_assign_pointer(ret->hash_buckets, buckets); + ret->hash_buckets = buckets; ret->hash_mask = entries - 1; get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); return ret; @@ -343,7 +343,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table, rcu); size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *); - struct neighbour **buckets = nht->hash_buckets; + struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) kfree(buckets); @@ -1540,7 +1540,7 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot create neighbour proc dir entry"); #endif - tbl->nht = neigh_hash_alloc(8); + RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(8)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); @@ -1602,7 +1602,8 @@ int neigh_table_clear(struct neigh_table *tbl) } write_unlock(&neigh_tbl_lock); - call_rcu(&tbl->nht->rcu, neigh_hash_free_rcu); + call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, + neigh_hash_free_rcu); tbl->nht = NULL; kfree(tbl->phash_buckets); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e23c01b..5ceb257 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -99,7 +99,7 @@ NETDEVICE_SHOW(addr_assign_type, fmt_dec); NETDEVICE_SHOW(addr_len, fmt_dec); NETDEVICE_SHOW(iflink, fmt_dec); NETDEVICE_SHOW(ifindex, fmt_dec); -NETDEVICE_SHOW(features, fmt_long_hex); +NETDEVICE_SHOW(features, fmt_hex); NETDEVICE_SHOW(type, fmt_dec); NETDEVICE_SHOW(link_mode, fmt_dec); @@ -295,6 +295,20 @@ static ssize_t show_ifalias(struct device *dev, return ret; } +NETDEVICE_SHOW(group, fmt_dec); + +static int change_group(struct net_device *net, unsigned long new_group) +{ + dev_set_group(net, (int) new_group); + return 0; +} + +static ssize_t store_group(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_group); +} + static struct device_attribute net_class_attributes[] = { __ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL), __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), @@ -316,6 +330,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags), __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, store_tx_queue_len), + __ATTR(netdev_group, S_IRUGO | S_IWUSR, show_group, store_group), {} }; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a9e7fc4..d73b77a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -251,6 +251,7 @@ struct pktgen_dev { int max_pkt_size; /* = ETH_ZLEN; */ int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ int nfrags; + struct page *page; u64 delay; /* nano-seconds */ __u64 count; /* Default No packets to send */ @@ -1134,6 +1135,10 @@ static ssize_t pktgen_if_write(struct file *file, if (node_possible(value)) { pkt_dev->node = value; sprintf(pg_result, "OK: node=%d", pkt_dev->node); + if (pkt_dev->page) { + put_page(pkt_dev->page); + pkt_dev->page = NULL; + } } else sprintf(pg_result, "ERROR: node not possible"); @@ -2605,6 +2610,90 @@ static inline __be16 build_tci(unsigned int id, unsigned int cfi, return htons(id | (cfi << 12) | (prio << 13)); } +static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, + int datalen) +{ + struct timeval timestamp; + struct pktgen_hdr *pgh; + + pgh = (struct pktgen_hdr *)skb_put(skb, sizeof(*pgh)); + datalen -= sizeof(*pgh); + + if (pkt_dev->nfrags <= 0) { + pgh = (struct pktgen_hdr *)skb_put(skb, datalen); + memset(pgh + 1, 0, datalen); + } else { + int frags = pkt_dev->nfrags; + int i, len; + + + if (frags > MAX_SKB_FRAGS) + frags = MAX_SKB_FRAGS; + len = datalen - frags * PAGE_SIZE; + if (len > 0) { + memset(skb_put(skb, len), 0, len); + datalen = frags * PAGE_SIZE; + } + + i = 0; + while (datalen > 0) { + if (unlikely(!pkt_dev->page)) { + int node = numa_node_id(); + + if (pkt_dev->node >= 0 && (pkt_dev->flags & F_NODE)) + node = pkt_dev->node; + pkt_dev->page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!pkt_dev->page) + break; + } + skb_shinfo(skb)->frags[i].page = pkt_dev->page; + get_page(pkt_dev->page); + skb_shinfo(skb)->frags[i].page_offset = 0; + skb_shinfo(skb)->frags[i].size = + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + datalen -= skb_shinfo(skb)->frags[i].size; + skb->len += skb_shinfo(skb)->frags[i].size; + skb->data_len += skb_shinfo(skb)->frags[i].size; + i++; + skb_shinfo(skb)->nr_frags = i; + } + + while (i < frags) { + int rem; + + if (i == 0) + break; + + rem = skb_shinfo(skb)->frags[i - 1].size / 2; + if (rem == 0) + break; + + skb_shinfo(skb)->frags[i - 1].size -= rem; + + skb_shinfo(skb)->frags[i] = + skb_shinfo(skb)->frags[i - 1]; + get_page(skb_shinfo(skb)->frags[i].page); + skb_shinfo(skb)->frags[i].page = + skb_shinfo(skb)->frags[i - 1].page; + skb_shinfo(skb)->frags[i].page_offset += + skb_shinfo(skb)->frags[i - 1].size; + skb_shinfo(skb)->frags[i].size = rem; + i++; + skb_shinfo(skb)->nr_frags = i; + } + } + + /* Stamp the time, and sequence number, + * convert them to network byte order + */ + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); + + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); +} + static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct pktgen_dev *pkt_dev) { @@ -2613,7 +2702,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct udphdr *udph; int datalen, iplen; struct iphdr *iph; - struct pktgen_hdr *pgh = NULL; __be16 protocol = htons(ETH_P_IP); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ @@ -2729,76 +2817,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, pkt_dev->pkt_overhead); skb->dev = odev; skb->pkt_type = PACKET_HOST; - - if (pkt_dev->nfrags <= 0) { - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr)); - } else { - int frags = pkt_dev->nfrags; - int i, len; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - len = datalen - frags * PAGE_SIZE; - memset(skb_put(skb, len), 0, len); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; - - skb_shinfo(skb)->frags[i - 1].size -= rem; - - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } - } - - /* Stamp the time, and sequence number, - * convert them to network byte order - */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } + pktgen_finalize_skb(pkt_dev, skb, datalen); #ifdef CONFIG_XFRM if (!process_ipsec(pkt_dev, skb, protocol)) @@ -2980,7 +2999,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct udphdr *udph; int datalen; struct ipv6hdr *iph; - struct pktgen_hdr *pgh = NULL; __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ @@ -3083,75 +3101,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { - int frags = pkt_dev->nfrags; - int i; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - skb_put(skb, datalen - frags * PAGE_SIZE); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; - - skb_shinfo(skb)->frags[i - 1].size -= rem; - - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } - } - - /* Stamp the time, and sequence number, - * convert them to network byte order - * should we update cloned packets too ? - */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - /* pkt_dev->seq_num++; FF: you really mean this? */ + pktgen_finalize_skb(pkt_dev, skb, datalen); return skb; } @@ -3884,6 +3834,8 @@ static int pktgen_remove_device(struct pktgen_thread *t, free_SAs(pkt_dev); #endif vfree(pkt_dev->flows); + if (pkt_dev->page) + put_page(pkt_dev->page); kfree(pkt_dev); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2d65c6b..49f7ea5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -868,6 +868,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, netif_running(dev) ? dev->operstate : IF_OPER_DOWN); NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); + NLA_PUT_U32(skb, IFLA_GROUP, dev->group); if (dev->ifindex != dev->iflink) NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); @@ -1035,6 +1036,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_LINK] = { .type = NLA_U32 }, + [IFLA_MASTER] = { .type = NLA_U32 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, @@ -1177,6 +1179,41 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) return err; } +static int do_set_master(struct net_device *dev, int ifindex) +{ + struct net_device *master_dev; + const struct net_device_ops *ops; + int err; + + if (dev->master) { + if (dev->master->ifindex == ifindex) + return 0; + ops = dev->master->netdev_ops; + if (ops->ndo_del_slave) { + err = ops->ndo_del_slave(dev->master, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + + if (ifindex) { + master_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!master_dev) + return -EINVAL; + ops = master_dev->netdev_ops; + if (ops->ndo_add_slave) { + err = ops->ndo_add_slave(master_dev, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + return 0; +} + static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { @@ -1264,6 +1301,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, modified = 1; } + if (tb[IFLA_GROUP]) { + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + modified = 1; + } + /* * Interface selected by interface index but interface * name provided implies that a name change has been @@ -1295,6 +1337,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + if (err) + goto errout; + modified = 1; + } + if (tb[IFLA_TXQLEN]) dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); @@ -1541,6 +1590,8 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); if (tb[IFLA_LINKMODE]) dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); + if (tb[IFLA_GROUP]) + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); return dev; @@ -1551,6 +1602,24 @@ err: } EXPORT_SYMBOL(rtnl_create_link); +static int rtnl_group_changelink(struct net *net, int group, + struct ifinfomsg *ifm, + struct nlattr **tb) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + if (dev->group == group) { + err = do_setlink(dev, ifm, tb, NULL, 0); + if (err < 0) + return err; + } + } + + return 0; +} + static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); @@ -1578,10 +1647,12 @@ replay: ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); - else if (ifname[0]) - dev = __dev_get_by_name(net, ifname); - else - dev = NULL; + else { + if (ifname[0]) + dev = __dev_get_by_name(net, ifname); + else + dev = NULL; + } err = validate_linkmsg(dev, tb); if (err < 0) @@ -1645,8 +1716,13 @@ replay: return do_setlink(dev, ifm, tb, ifname, modified); } - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) + return rtnl_group_changelink(net, + nla_get_u32(tb[IFLA_GROUP]), + ifm, tb); return -ENODEV; + } if (ifm->ifi_index) return -EOPNOTSUPP; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d883dcc..14cf560 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2498,7 +2498,7 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, int features) +struct sk_buff *skb_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; @@ -2508,7 +2508,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) unsigned int offset = doffset; unsigned int headroom; unsigned int len; - int sg = features & NETIF_F_SG; + int sg = !!(features & NETIF_F_SG); int nfrags = skb_shinfo(skb)->nr_frags; int err = -ENOMEM; int i = 0; diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e96d5e8..fadecd2 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -583,6 +583,15 @@ done: dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } +/* + * Convert RFC 3390 larger initial window into an equivalent number of packets. + * This is based on the numbers specified in RFC 5681, 3.1. + */ +static inline u32 rfc3390_bytes_to_packets(const u32 smss) +{ + return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); +} + static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) { struct ccid2_hc_tx_sock *hc = ccid_priv(ccid); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 5e63636..06c054d 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -112,6 +112,7 @@ static int dn_dst_gc(struct dst_ops *ops); static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); static unsigned int dn_dst_default_mtu(const struct dst_entry *dst); +static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu); @@ -133,11 +134,18 @@ static struct dst_ops dn_dst_ops = { .check = dn_dst_check, .default_advmss = dn_dst_default_advmss, .default_mtu = dn_dst_default_mtu, + .cow_metrics = dst_cow_metrics_generic, + .destroy = dn_dst_destroy, .negative_advice = dn_dst_negative_advice, .link_failure = dn_dst_link_failure, .update_pmtu = dn_dst_update_pmtu, }; +static void dn_dst_destroy(struct dst_entry *dst) +{ + dst_destroy_metrics_generic(dst); +} + static __inline__ unsigned dn_hash(__le16 src, __le16 dst) { __u16 tmp = (__u16 __force)(src ^ dst); @@ -814,14 +822,14 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) { struct dn_fib_info *fi = res->fi; struct net_device *dev = rt->dst.dev; + unsigned int mss_metric; struct neighbour *n; - unsigned int metric; if (fi) { if (DN_FIB_RES_GW(*res) && DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = DN_FIB_RES_GW(*res); - dst_import_metrics(&rt->dst, fi->fib_metrics); + dst_init_metrics(&rt->dst, fi->fib_metrics, true); } rt->rt_type = res->type; @@ -834,10 +842,10 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu); - metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS); - if (metric) { + mss_metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS); + if (mss_metric) { unsigned int mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst)); - if (metric > mss) + if (mss_metric > mss) dst_metric_set(&rt->dst, RTAX_ADVMSS, mss); } return 0; @@ -1114,7 +1122,7 @@ make_route: if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - rt = dst_alloc(&dn_dst_ops); + rt = dst_alloc(&dn_dst_ops, 0); if (rt == NULL) goto e_nobufs; @@ -1375,7 +1383,7 @@ static int dn_route_input_slow(struct sk_buff *skb) } make_route: - rt = dst_alloc(&dn_dst_ops); + rt = dst_alloc(&dn_dst_ops, 0); if (rt == NULL) goto e_nobufs; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index f2abd37..b66600b 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -59,7 +59,6 @@ struct dn_hash }; #define dz_key_0(key) ((key).datum = 0) -#define dz_prefix(key,dz) ((key).datum) #define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\ for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index a5a1050..cbb505b 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -55,45 +55,9 @@ config IP_ADVANCED_ROUTER If unsure, say N here. -choice - prompt "Choose IP: FIB lookup algorithm (choose FIB_HASH if unsure)" - depends on IP_ADVANCED_ROUTER - default ASK_IP_FIB_HASH - -config ASK_IP_FIB_HASH - bool "FIB_HASH" - ---help--- - Current FIB is very proven and good enough for most users. - -config IP_FIB_TRIE - bool "FIB_TRIE" - ---help--- - Use new experimental LC-trie as FIB lookup algorithm. - This improves lookup performance if you have a large - number of routes. - - LC-trie is a longest matching prefix lookup algorithm which - performs better than FIB_HASH for large routing tables. - But, it consumes more memory and is more complex. - - LC-trie is described in: - - IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson - IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, - June 1999 - - An experimental study of compression methods for dynamic tries - Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. - <http://www.csc.kth.se/~snilsson/software/dyntrie2/> - -endchoice - -config IP_FIB_HASH - def_bool ASK_IP_FIB_HASH || !IP_ADVANCED_ROUTER - config IP_FIB_TRIE_STATS bool "FIB TRIE statistics" - depends on IP_FIB_TRIE + depends on IP_ADVANCED_ROUTER ---help--- Keep track of statistics on structure of FIB TRIE table. Useful for testing and measuring TRIE performance. @@ -140,6 +104,9 @@ config IP_ROUTE_VERBOSE handled by the klogd daemon which is responsible for kernel messages ("man klogd"). +config IP_ROUTE_CLASSID + bool + config IP_PNP bool "IP: kernel level autoconfiguration" help @@ -657,4 +624,3 @@ config TCP_MD5SIG on the Internet. If unsure, say N. - diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 4978d22..0dc772d 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -10,12 +10,10 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_minisocks.o tcp_cong.o \ datagram.o raw.o udp.o udplite.o \ arp.o icmp.o devinet.o af_inet.o igmp.o \ - fib_frontend.o fib_semantics.o \ + fib_frontend.o fib_semantics.o fib_trie.o \ inet_fragment.o obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o -obj-$(CONFIG_IP_FIB_HASH) += fib_hash.o -obj-$(CONFIG_IP_FIB_TRIE) += fib_trie.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o obj-$(CONFIG_IP_MROUTE) += ipmr.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 45b89d7..7ceb804 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1231,7 +1231,7 @@ out: return err; } -static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features) +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct iphdr *iph; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 86961be..325053d 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -201,7 +201,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ttl = 0; top_iph->check = 0; - ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; + if (x->props.flags & XFRM_STATE_ALIGN4) + ah->hdrlen = (XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; + else + ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; ah->reserved = 0; ah->spi = x->id.spi; @@ -299,9 +302,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; - if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) && - ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len)) - goto out; + if (x->props.flags & XFRM_STATE_ALIGN4) { + if (ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_full_len) && + ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len)) + goto out; + } else { + if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) && + ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len)) + goto out; + } if (!pskb_may_pull(skb, ah_hlen)) goto out; @@ -450,8 +459,12 @@ static int ah_init_state(struct xfrm_state *x) BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); - x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + - ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ALIGN4) + x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) + + ahp->icv_trunc_len); + else + x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + + ahp->icv_trunc_len); if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct iphdr); x->data = ahp; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index df4616f..9038928 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -51,6 +51,7 @@ #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/slab.h> +#include <linux/hash.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif @@ -92,6 +93,71 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; +/* inet_addr_hash's shifting is dependent upon this IN4_ADDR_HSIZE + * value. So if you change this define, make appropriate changes to + * inet_addr_hash as well. + */ +#define IN4_ADDR_HSIZE 256 +static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; +static DEFINE_SPINLOCK(inet_addr_hash_lock); + +static inline unsigned int inet_addr_hash(struct net *net, __be32 addr) +{ + u32 val = (__force u32) addr ^ hash_ptr(net, 8); + + return ((val ^ (val >> 8) ^ (val >> 16) ^ (val >> 24)) & + (IN4_ADDR_HSIZE - 1)); +} + +static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) +{ + unsigned int hash = inet_addr_hash(net, ifa->ifa_address); + + spin_lock(&inet_addr_hash_lock); + hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]); + spin_unlock(&inet_addr_hash_lock); +} + +static void inet_hash_remove(struct in_ifaddr *ifa) +{ + spin_lock(&inet_addr_hash_lock); + hlist_del_init_rcu(&ifa->hash); + spin_unlock(&inet_addr_hash_lock); +} + +/** + * __ip_dev_find - find the first device with a given source address. + * @net: the net namespace + * @addr: the source address + * @devref: if true, take a reference on the found device + * + * If a caller uses devref=false, it should be protected by RCU, or RTNL + */ +struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) +{ + unsigned int hash = inet_addr_hash(net, addr); + struct net_device *result = NULL; + struct in_ifaddr *ifa; + struct hlist_node *node; + + rcu_read_lock(); + hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) { + struct net_device *dev = ifa->ifa_dev->dev; + + if (!net_eq(dev_net(dev), net)) + continue; + if (ifa->ifa_address == addr) { + result = dev; + break; + } + } + if (result && devref) + dev_hold(result); + rcu_read_unlock(); + return result; +} +EXPORT_SYMBOL(__ip_dev_find); + static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); @@ -265,6 +331,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, } if (!do_promote) { + inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid); @@ -281,6 +348,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, /* 2. Unlink it */ *ifap = ifa1->ifa_next; + inet_hash_remove(ifa1); /* 3. Announce address deletion */ @@ -368,6 +436,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, ifa->ifa_next = *ifap; *ifap = ifa; + inet_hash_insert(dev_net(in_dev->dev), ifa); + /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ @@ -521,6 +591,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) if (tb[IFA_ADDRESS] == NULL) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; + INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = ifm->ifa_flags; @@ -728,6 +799,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) { ret = -ENOBUFS; ifa = inet_alloc_ifa(); + INIT_HLIST_NODE(&ifa->hash); if (!ifa) break; if (colon) @@ -1084,6 +1156,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, struct in_ifaddr *ifa = inet_alloc_ifa(); if (ifa) { + INIT_HLIST_NODE(&ifa->hash); ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; @@ -1720,6 +1793,11 @@ static struct rtnl_af_ops inet_af_ops = { void __init devinet_init(void) { + int i; + + for (i = 0; i < IN4_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet_addr_lst[i]); + register_pernet_subsys(&devinet_ops); register_gifconf(PF_INET, inet_gifconf); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 1d2cdd4..ad0778a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -51,11 +51,11 @@ static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; - local_table = fib_hash_table(RT_TABLE_LOCAL); + local_table = fib_trie_table(RT_TABLE_LOCAL); if (local_table == NULL) return -ENOMEM; - main_table = fib_hash_table(RT_TABLE_MAIN); + main_table = fib_trie_table(RT_TABLE_MAIN); if (main_table == NULL) goto fail; @@ -82,7 +82,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id) if (tb) return tb; - tb = fib_hash_table(id); + tb = fib_trie_table(id); if (!tb) return NULL; h = id & (FIB_TABLE_HASHSZ - 1); @@ -114,21 +114,6 @@ struct fib_table *fib_get_table(struct net *net, u32 id) } #endif /* CONFIG_IP_MULTIPLE_TABLES */ -void fib_select_default(struct net *net, - const struct flowi *flp, struct fib_result *res) -{ - struct fib_table *tb; - int table = RT_TABLE_MAIN; -#ifdef CONFIG_IP_MULTIPLE_TABLES - if (res->r == NULL || res->r->action != FR_ACT_TO_TBL) - return; - table = res->r->table; -#endif - tb = fib_get_table(net, table); - if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - fib_table_select_default(tb, flp, res); -} - static void fib_flush(struct net *net) { int flushed = 0; @@ -147,46 +132,6 @@ static void fib_flush(struct net *net) rt_cache_flush(net, -1); } -/** - * __ip_dev_find - find the first device with a given source address. - * @net: the net namespace - * @addr: the source address - * @devref: if true, take a reference on the found device - * - * If a caller uses devref=false, it should be protected by RCU, or RTNL - */ -struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) -{ - struct flowi fl = { - .fl4_dst = addr, - }; - struct fib_result res = { 0 }; - struct net_device *dev = NULL; - struct fib_table *local_table; - -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif - - rcu_read_lock(); - local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (!local_table || - fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) { - rcu_read_unlock(); - return NULL; - } - if (res.type != RTN_LOCAL) - goto out; - dev = FIB_RES_DEV(res); - - if (dev && devref) - dev_hold(dev); -out: - rcu_read_unlock(); - return dev; -} -EXPORT_SYMBOL(__ip_dev_find); - /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. @@ -1101,5 +1046,5 @@ void __init ip_fib_init(void) register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); - fib_hash_init(); + fib_trie_init(); } diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c deleted file mode 100644 index b3acb04..0000000 --- a/net/ipv4/fib_hash.c +++ /dev/null @@ -1,1133 +0,0 @@ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. INET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * IPv4 FIB: lookup engine and maintenance routines. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/errno.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/inetdevice.h> -#include <linux/netdevice.h> -#include <linux/if_arp.h> -#include <linux/proc_fs.h> -#include <linux/skbuff.h> -#include <linux/netlink.h> -#include <linux/init.h> -#include <linux/slab.h> - -#include <net/net_namespace.h> -#include <net/ip.h> -#include <net/protocol.h> -#include <net/route.h> -#include <net/tcp.h> -#include <net/sock.h> -#include <net/ip_fib.h> - -#include "fib_lookup.h" - -static struct kmem_cache *fn_hash_kmem __read_mostly; -static struct kmem_cache *fn_alias_kmem __read_mostly; - -struct fib_node { - struct hlist_node fn_hash; - struct list_head fn_alias; - __be32 fn_key; - struct fib_alias fn_embedded_alias; -}; - -#define EMBEDDED_HASH_SIZE (L1_CACHE_BYTES / sizeof(struct hlist_head)) - -struct fn_zone { - struct fn_zone __rcu *fz_next; /* Next not empty zone */ - struct hlist_head __rcu *fz_hash; /* Hash table pointer */ - seqlock_t fz_lock; - u32 fz_hashmask; /* (fz_divisor - 1) */ - - u8 fz_order; /* Zone order (0..32) */ - u8 fz_revorder; /* 32 - fz_order */ - __be32 fz_mask; /* inet_make_mask(order) */ -#define FZ_MASK(fz) ((fz)->fz_mask) - - struct hlist_head fz_embedded_hash[EMBEDDED_HASH_SIZE]; - - int fz_nent; /* Number of entries */ - int fz_divisor; /* Hash size (mask+1) */ -}; - -struct fn_hash { - struct fn_zone *fn_zones[33]; - struct fn_zone __rcu *fn_zone_list; -}; - -static inline u32 fn_hash(__be32 key, struct fn_zone *fz) -{ - u32 h = ntohl(key) >> fz->fz_revorder; - h ^= (h>>20); - h ^= (h>>10); - h ^= (h>>5); - h &= fz->fz_hashmask; - return h; -} - -static inline __be32 fz_key(__be32 dst, struct fn_zone *fz) -{ - return dst & FZ_MASK(fz); -} - -static unsigned int fib_hash_genid; - -#define FZ_MAX_DIVISOR ((PAGE_SIZE<<MAX_ORDER) / sizeof(struct hlist_head)) - -static struct hlist_head *fz_hash_alloc(int divisor) -{ - unsigned long size = divisor * sizeof(struct hlist_head); - - if (size <= PAGE_SIZE) - return kzalloc(size, GFP_KERNEL); - - return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(size)); -} - -/* The fib hash lock must be held when this is called. */ -static inline void fn_rebuild_zone(struct fn_zone *fz, - struct hlist_head *old_ht, - int old_divisor) -{ - int i; - - for (i = 0; i < old_divisor; i++) { - struct hlist_node *node, *n; - struct fib_node *f; - - hlist_for_each_entry_safe(f, node, n, &old_ht[i], fn_hash) { - struct hlist_head *new_head; - - hlist_del_rcu(&f->fn_hash); - - new_head = rcu_dereference_protected(fz->fz_hash, 1) + - fn_hash(f->fn_key, fz); - hlist_add_head_rcu(&f->fn_hash, new_head); - } - } -} - -static void fz_hash_free(struct hlist_head *hash, int divisor) -{ - unsigned long size = divisor * sizeof(struct hlist_head); - - if (size <= PAGE_SIZE) - kfree(hash); - else - free_pages((unsigned long)hash, get_order(size)); -} - -static void fn_rehash_zone(struct fn_zone *fz) -{ - struct hlist_head *ht, *old_ht; - int old_divisor, new_divisor; - u32 new_hashmask; - - new_divisor = old_divisor = fz->fz_divisor; - - switch (old_divisor) { - case EMBEDDED_HASH_SIZE: - new_divisor *= EMBEDDED_HASH_SIZE; - break; - case EMBEDDED_HASH_SIZE*EMBEDDED_HASH_SIZE: - new_divisor *= (EMBEDDED_HASH_SIZE/2); - break; - default: - if ((old_divisor << 1) > FZ_MAX_DIVISOR) { - printk(KERN_CRIT "route.c: bad divisor %d!\n", old_divisor); - return; - } - new_divisor = (old_divisor << 1); - break; - } - - new_hashmask = (new_divisor - 1); - -#if RT_CACHE_DEBUG >= 2 - printk(KERN_DEBUG "fn_rehash_zone: hash for zone %d grows from %d\n", - fz->fz_order, old_divisor); -#endif - - ht = fz_hash_alloc(new_divisor); - - if (ht) { - struct fn_zone nfz; - - memcpy(&nfz, fz, sizeof(nfz)); - - write_seqlock_bh(&fz->fz_lock); - old_ht = rcu_dereference_protected(fz->fz_hash, 1); - RCU_INIT_POINTER(nfz.fz_hash, ht); - nfz.fz_hashmask = new_hashmask; - nfz.fz_divisor = new_divisor; - fn_rebuild_zone(&nfz, old_ht, old_divisor); - fib_hash_genid++; - rcu_assign_pointer(fz->fz_hash, ht); - fz->fz_hashmask = new_hashmask; - fz->fz_divisor = new_divisor; - write_sequnlock_bh(&fz->fz_lock); - - if (old_ht != fz->fz_embedded_hash) { - synchronize_rcu(); - fz_hash_free(old_ht, old_divisor); - } - } -} - -static void fn_free_node_rcu(struct rcu_head *head) -{ - struct fib_node *f = container_of(head, struct fib_node, fn_embedded_alias.rcu); - - kmem_cache_free(fn_hash_kmem, f); -} - -static inline void fn_free_node(struct fib_node *f) -{ - call_rcu(&f->fn_embedded_alias.rcu, fn_free_node_rcu); -} - -static void fn_free_alias_rcu(struct rcu_head *head) -{ - struct fib_alias *fa = container_of(head, struct fib_alias, rcu); - - kmem_cache_free(fn_alias_kmem, fa); -} - -static inline void fn_free_alias(struct fib_alias *fa, struct fib_node *f) -{ - fib_release_info(fa->fa_info); - if (fa == &f->fn_embedded_alias) - fa->fa_info = NULL; - else - call_rcu(&fa->rcu, fn_free_alias_rcu); -} - -static struct fn_zone * -fn_new_zone(struct fn_hash *table, int z) -{ - int i; - struct fn_zone *fz = kzalloc(sizeof(struct fn_zone), GFP_KERNEL); - if (!fz) - return NULL; - - seqlock_init(&fz->fz_lock); - fz->fz_divisor = z ? EMBEDDED_HASH_SIZE : 1; - fz->fz_hashmask = fz->fz_divisor - 1; - RCU_INIT_POINTER(fz->fz_hash, fz->fz_embedded_hash); - fz->fz_order = z; - fz->fz_revorder = 32 - z; - fz->fz_mask = inet_make_mask(z); - - /* Find the first not empty zone with more specific mask */ - for (i = z + 1; i <= 32; i++) - if (table->fn_zones[i]) - break; - if (i > 32) { - /* No more specific masks, we are the first. */ - rcu_assign_pointer(fz->fz_next, - rtnl_dereference(table->fn_zone_list)); - rcu_assign_pointer(table->fn_zone_list, fz); - } else { - rcu_assign_pointer(fz->fz_next, - rtnl_dereference(table->fn_zones[i]->fz_next)); - rcu_assign_pointer(table->fn_zones[i]->fz_next, fz); - } - table->fn_zones[z] = fz; - fib_hash_genid++; - return fz; -} - -int fib_table_lookup(struct fib_table *tb, - const struct flowi *flp, struct fib_result *res, - int fib_flags) -{ - int err; - struct fn_zone *fz; - struct fn_hash *t = (struct fn_hash *)tb->tb_data; - - rcu_read_lock(); - for (fz = rcu_dereference(t->fn_zone_list); - fz != NULL; - fz = rcu_dereference(fz->fz_next)) { - struct hlist_head *head; - struct hlist_node *node; - struct fib_node *f; - __be32 k; - unsigned int seq; - - do { - seq = read_seqbegin(&fz->fz_lock); - k = fz_key(flp->fl4_dst, fz); - - head = rcu_dereference(fz->fz_hash) + fn_hash(k, fz); - hlist_for_each_entry_rcu(f, node, head, fn_hash) { - if (f->fn_key != k) - continue; - - err = fib_semantic_match(&f->fn_alias, - flp, res, - fz->fz_order, fib_flags); - if (err <= 0) - goto out; - } - } while (read_seqretry(&fz->fz_lock, seq)); - } - err = 1; -out: - rcu_read_unlock(); - return err; -} - -void fib_table_select_default(struct fib_table *tb, - const struct flowi *flp, struct fib_result *res) -{ - int order, last_idx; - struct hlist_node *node; - struct fib_node *f; - struct fib_info *fi = NULL; - struct fib_info *last_resort; - struct fn_hash *t = (struct fn_hash *)tb->tb_data; - struct fn_zone *fz = t->fn_zones[0]; - struct hlist_head *head; - - if (fz == NULL) - return; - - last_idx = -1; - last_resort = NULL; - order = -1; - - rcu_read_lock(); - head = rcu_dereference(fz->fz_hash); - hlist_for_each_entry_rcu(f, node, head, fn_hash) { - struct fib_alias *fa; - - list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) { - struct fib_info *next_fi = fa->fa_info; - - if (fa->fa_scope != res->scope || - fa->fa_type != RTN_UNICAST) - continue; - - if (next_fi->fib_priority > res->fi->fib_priority) - break; - if (!next_fi->fib_nh[0].nh_gw || - next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) - continue; - - fib_alias_accessed(fa); - - if (fi == NULL) { - if (next_fi != res->fi) - break; - } else if (!fib_detect_death(fi, order, &last_resort, - &last_idx, tb->tb_default)) { - fib_result_assign(res, fi); - tb->tb_default = order; - goto out; - } - fi = next_fi; - order++; - } - } - - if (order <= 0 || fi == NULL) { - tb->tb_default = -1; - goto out; - } - - if (!fib_detect_death(fi, order, &last_resort, &last_idx, - tb->tb_default)) { - fib_result_assign(res, fi); - tb->tb_default = order; - goto out; - } - - if (last_idx >= 0) - fib_result_assign(res, last_resort); - tb->tb_default = last_idx; -out: - rcu_read_unlock(); -} - -/* Insert node F to FZ. */ -static inline void fib_insert_node(struct fn_zone *fz, struct fib_node *f) -{ - struct hlist_head *head = rtnl_dereference(fz->fz_hash) + fn_hash(f->fn_key, fz); - - hlist_add_head_rcu(&f->fn_hash, head); -} - -/* Return the node in FZ matching KEY. */ -static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) -{ - struct hlist_head *head = rtnl_dereference(fz->fz_hash) + fn_hash(key, fz); - struct hlist_node *node; - struct fib_node *f; - - hlist_for_each_entry_rcu(f, node, head, fn_hash) { - if (f->fn_key == key) - return f; - } - - return NULL; -} - - -static struct fib_alias *fib_fast_alloc(struct fib_node *f) -{ - struct fib_alias *fa = &f->fn_embedded_alias; - - if (fa->fa_info != NULL) - fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - return fa; -} - -/* Caller must hold RTNL. */ -int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) -{ - struct fn_hash *table = (struct fn_hash *) tb->tb_data; - struct fib_node *new_f = NULL; - struct fib_node *f; - struct fib_alias *fa, *new_fa; - struct fn_zone *fz; - struct fib_info *fi; - u8 tos = cfg->fc_tos; - __be32 key; - int err; - - if (cfg->fc_dst_len > 32) - return -EINVAL; - - fz = table->fn_zones[cfg->fc_dst_len]; - if (!fz && !(fz = fn_new_zone(table, cfg->fc_dst_len))) - return -ENOBUFS; - - key = 0; - if (cfg->fc_dst) { - if (cfg->fc_dst & ~FZ_MASK(fz)) - return -EINVAL; - key = fz_key(cfg->fc_dst, fz); - } - - fi = fib_create_info(cfg); - if (IS_ERR(fi)) - return PTR_ERR(fi); - - if (fz->fz_nent > (fz->fz_divisor<<1) && - fz->fz_divisor < FZ_MAX_DIVISOR && - (cfg->fc_dst_len == 32 || - (1 << cfg->fc_dst_len) > fz->fz_divisor)) - fn_rehash_zone(fz); - - f = fib_find_node(fz, key); - - if (!f) - fa = NULL; - else - fa = fib_find_alias(&f->fn_alias, tos, fi->fib_priority); - - /* Now fa, if non-NULL, points to the first fib alias - * with the same keys [prefix,tos,priority], if such key already - * exists or to the node before which we will insert new one. - * - * If fa is NULL, we will need to allocate a new one and - * insert to the head of f. - * - * If f is NULL, no fib node matched the destination key - * and we need to allocate a new one of those as well. - */ - - if (fa && fa->fa_tos == tos && - fa->fa_info->fib_priority == fi->fib_priority) { - struct fib_alias *fa_first, *fa_match; - - err = -EEXIST; - if (cfg->fc_nlflags & NLM_F_EXCL) - goto out; - - /* We have 2 goals: - * 1. Find exact match for type, scope, fib_info to avoid - * duplicate routes - * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it - */ - fa_match = NULL; - fa_first = fa; - fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list); - list_for_each_entry_continue(fa, &f->fn_alias, fa_list) { - if (fa->fa_tos != tos) - break; - if (fa->fa_info->fib_priority != fi->fib_priority) - break; - if (fa->fa_type == cfg->fc_type && - fa->fa_scope == cfg->fc_scope && - fa->fa_info == fi) { - fa_match = fa; - break; - } - } - - if (cfg->fc_nlflags & NLM_F_REPLACE) { - u8 state; - - fa = fa_first; - if (fa_match) { - if (fa == fa_match) - err = 0; - goto out; - } - err = -ENOBUFS; - new_fa = fib_fast_alloc(f); - if (new_fa == NULL) - goto out; - - new_fa->fa_tos = fa->fa_tos; - new_fa->fa_info = fi; - new_fa->fa_type = cfg->fc_type; - new_fa->fa_scope = cfg->fc_scope; - state = fa->fa_state; - new_fa->fa_state = state & ~FA_S_ACCESSED; - fib_hash_genid++; - list_replace_rcu(&fa->fa_list, &new_fa->fa_list); - - fn_free_alias(fa, f); - if (state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); - rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, - tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); - return 0; - } - - /* Error if we find a perfect match which - * uses the same scope, type, and nexthop - * information. - */ - if (fa_match) - goto out; - - if (!(cfg->fc_nlflags & NLM_F_APPEND)) - fa = fa_first; - } - - err = -ENOENT; - if (!(cfg->fc_nlflags & NLM_F_CREATE)) - goto out; - - err = -ENOBUFS; - - if (!f) { - new_f = kmem_cache_zalloc(fn_hash_kmem, GFP_KERNEL); - if (new_f == NULL) - goto out; - - INIT_HLIST_NODE(&new_f->fn_hash); - INIT_LIST_HEAD(&new_f->fn_alias); - new_f->fn_key = key; - f = new_f; - } - - new_fa = fib_fast_alloc(f); - if (new_fa == NULL) - goto out; - - new_fa->fa_info = fi; - new_fa->fa_tos = tos; - new_fa->fa_type = cfg->fc_type; - new_fa->fa_scope = cfg->fc_scope; - new_fa->fa_state = 0; - - /* - * Insert new entry to the list. - */ - - if (new_f) - fib_insert_node(fz, new_f); - list_add_tail_rcu(&new_fa->fa_list, - (fa ? &fa->fa_list : &f->fn_alias)); - fib_hash_genid++; - - if (new_f) - fz->fz_nent++; - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); - - rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id, - &cfg->fc_nlinfo, 0); - return 0; - -out: - if (new_f) - kmem_cache_free(fn_hash_kmem, new_f); - fib_release_info(fi); - return err; -} - -int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) -{ - struct fn_hash *table = (struct fn_hash *)tb->tb_data; - struct fib_node *f; - struct fib_alias *fa, *fa_to_delete; - struct fn_zone *fz; - __be32 key; - - if (cfg->fc_dst_len > 32) - return -EINVAL; - - if ((fz = table->fn_zones[cfg->fc_dst_len]) == NULL) - return -ESRCH; - - key = 0; - if (cfg->fc_dst) { - if (cfg->fc_dst & ~FZ_MASK(fz)) - return -EINVAL; - key = fz_key(cfg->fc_dst, fz); - } - - f = fib_find_node(fz, key); - - if (!f) - fa = NULL; - else - fa = fib_find_alias(&f->fn_alias, cfg->fc_tos, 0); - if (!fa) - return -ESRCH; - - fa_to_delete = NULL; - fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list); - list_for_each_entry_continue(fa, &f->fn_alias, fa_list) { - struct fib_info *fi = fa->fa_info; - - if (fa->fa_tos != cfg->fc_tos) - break; - - if ((!cfg->fc_type || - fa->fa_type == cfg->fc_type) && - (cfg->fc_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == cfg->fc_scope) && - (!cfg->fc_protocol || - fi->fib_protocol == cfg->fc_protocol) && - fib_nh_match(cfg, fi) == 0) { - fa_to_delete = fa; - break; - } - } - - if (fa_to_delete) { - int kill_fn; - - fa = fa_to_delete; - rtmsg_fib(RTM_DELROUTE, key, fa, cfg->fc_dst_len, - tb->tb_id, &cfg->fc_nlinfo, 0); - - kill_fn = 0; - list_del_rcu(&fa->fa_list); - if (list_empty(&f->fn_alias)) { - hlist_del_rcu(&f->fn_hash); - kill_fn = 1; - } - fib_hash_genid++; - - if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); - fn_free_alias(fa, f); - if (kill_fn) { - fn_free_node(f); - fz->fz_nent--; - } - - return 0; - } - return -ESRCH; -} - -static int fn_flush_list(struct fn_zone *fz, int idx) -{ - struct hlist_head *head = rtnl_dereference(fz->fz_hash) + idx; - struct hlist_node *node, *n; - struct fib_node *f; - int found = 0; - - hlist_for_each_entry_safe(f, node, n, head, fn_hash) { - struct fib_alias *fa, *fa_node; - int kill_f; - - kill_f = 0; - list_for_each_entry_safe(fa, fa_node, &f->fn_alias, fa_list) { - struct fib_info *fi = fa->fa_info; - - if (fi && (fi->fib_flags&RTNH_F_DEAD)) { - list_del_rcu(&fa->fa_list); - if (list_empty(&f->fn_alias)) { - hlist_del_rcu(&f->fn_hash); - kill_f = 1; - } - fib_hash_genid++; - - fn_free_alias(fa, f); - found++; - } - } - if (kill_f) { - fn_free_node(f); - fz->fz_nent--; - } - } - return found; -} - -/* caller must hold RTNL. */ -int fib_table_flush(struct fib_table *tb) -{ - struct fn_hash *table = (struct fn_hash *) tb->tb_data; - struct fn_zone *fz; - int found = 0; - - for (fz = rtnl_dereference(table->fn_zone_list); - fz != NULL; - fz = rtnl_dereference(fz->fz_next)) { - int i; - - for (i = fz->fz_divisor - 1; i >= 0; i--) - found += fn_flush_list(fz, i); - } - return found; -} - -void fib_free_table(struct fib_table *tb) -{ - struct fn_hash *table = (struct fn_hash *) tb->tb_data; - struct fn_zone *fz, *next; - - next = table->fn_zone_list; - while (next != NULL) { - fz = next; - next = fz->fz_next; - - if (fz->fz_hash != fz->fz_embedded_hash) - fz_hash_free(fz->fz_hash, fz->fz_divisor); - - kfree(fz); - } - - kfree(tb); -} - -static inline int -fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, - struct fib_table *tb, - struct fn_zone *fz, - struct hlist_head *head) -{ - struct hlist_node *node; - struct fib_node *f; - int i, s_i; - - s_i = cb->args[4]; - i = 0; - hlist_for_each_entry_rcu(f, node, head, fn_hash) { - struct fib_alias *fa; - - list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) { - if (i < s_i) - goto next; - - if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, - fa->fa_type, - fa->fa_scope, - f->fn_key, - fz->fz_order, - fa->fa_tos, - fa->fa_info, - NLM_F_MULTI) < 0) { - cb->args[4] = i; - return -1; - } -next: - i++; - } - } - cb->args[4] = i; - return skb->len; -} - -static inline int -fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, - struct fib_table *tb, - struct fn_zone *fz) -{ - int h, s_h; - struct hlist_head *head = rcu_dereference(fz->fz_hash); - - if (head == NULL) - return skb->len; - s_h = cb->args[3]; - for (h = s_h; h < fz->fz_divisor; h++) { - if (hlist_empty(head + h)) - continue; - if (fn_hash_dump_bucket(skb, cb, tb, fz, head + h) < 0) { - cb->args[3] = h; - return -1; - } - memset(&cb->args[4], 0, - sizeof(cb->args) - 4*sizeof(cb->args[0])); - } - cb->args[3] = h; - return skb->len; -} - -int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, - struct netlink_callback *cb) -{ - int m = 0, s_m; - struct fn_zone *fz; - struct fn_hash *table = (struct fn_hash *)tb->tb_data; - - s_m = cb->args[2]; - rcu_read_lock(); - for (fz = rcu_dereference(table->fn_zone_list); - fz != NULL; - fz = rcu_dereference(fz->fz_next), m++) { - if (m < s_m) - continue; - if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) { - cb->args[2] = m; - rcu_read_unlock(); - return -1; - } - memset(&cb->args[3], 0, - sizeof(cb->args) - 3*sizeof(cb->args[0])); - } - rcu_read_unlock(); - cb->args[2] = m; - return skb->len; -} - -void __init fib_hash_init(void) -{ - fn_hash_kmem = kmem_cache_create("ip_fib_hash", sizeof(struct fib_node), - 0, SLAB_PANIC, NULL); - - fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), - 0, SLAB_PANIC, NULL); - -} - -struct fib_table *fib_hash_table(u32 id) -{ - struct fib_table *tb; - - tb = kmalloc(sizeof(struct fib_table) + sizeof(struct fn_hash), - GFP_KERNEL); - if (tb == NULL) - return NULL; - - tb->tb_id = id; - tb->tb_default = -1; - - memset(tb->tb_data, 0, sizeof(struct fn_hash)); - return tb; -} - -/* ------------------------------------------------------------------------ */ -#ifdef CONFIG_PROC_FS - -struct fib_iter_state { - struct seq_net_private p; - struct fn_zone *zone; - int bucket; - struct hlist_head *hash_head; - struct fib_node *fn; - struct fib_alias *fa; - loff_t pos; - unsigned int genid; - int valid; -}; - -static struct fib_alias *fib_get_first(struct seq_file *seq) -{ - struct fib_iter_state *iter = seq->private; - struct fib_table *main_table; - struct fn_hash *table; - - main_table = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); - table = (struct fn_hash *)main_table->tb_data; - - iter->bucket = 0; - iter->hash_head = NULL; - iter->fn = NULL; - iter->fa = NULL; - iter->pos = 0; - iter->genid = fib_hash_genid; - iter->valid = 1; - - for (iter->zone = rcu_dereference(table->fn_zone_list); - iter->zone != NULL; - iter->zone = rcu_dereference(iter->zone->fz_next)) { - int maxslot; - - if (!iter->zone->fz_nent) - continue; - - iter->hash_head = rcu_dereference(iter->zone->fz_hash); - maxslot = iter->zone->fz_divisor; - - for (iter->bucket = 0; iter->bucket < maxslot; - ++iter->bucket, ++iter->hash_head) { - struct hlist_node *node; - struct fib_node *fn; - - hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) { - struct fib_alias *fa; - - list_for_each_entry(fa, &fn->fn_alias, fa_list) { - iter->fn = fn; - iter->fa = fa; - goto out; - } - } - } - } -out: - return iter->fa; -} - -static struct fib_alias *fib_get_next(struct seq_file *seq) -{ - struct fib_iter_state *iter = seq->private; - struct fib_node *fn; - struct fib_alias *fa; - - /* Advance FA, if any. */ - fn = iter->fn; - fa = iter->fa; - if (fa) { - BUG_ON(!fn); - list_for_each_entry_continue(fa, &fn->fn_alias, fa_list) { - iter->fa = fa; - goto out; - } - } - - fa = iter->fa = NULL; - - /* Advance FN. */ - if (fn) { - struct hlist_node *node = &fn->fn_hash; - hlist_for_each_entry_continue(fn, node, fn_hash) { - iter->fn = fn; - - list_for_each_entry(fa, &fn->fn_alias, fa_list) { - iter->fa = fa; - goto out; - } - } - } - - fn = iter->fn = NULL; - - /* Advance hash chain. */ - if (!iter->zone) - goto out; - - for (;;) { - struct hlist_node *node; - int maxslot; - - maxslot = iter->zone->fz_divisor; - - while (++iter->bucket < maxslot) { - iter->hash_head++; - - hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) { - list_for_each_entry(fa, &fn->fn_alias, fa_list) { - iter->fn = fn; - iter->fa = fa; - goto out; - } - } - } - - iter->zone = rcu_dereference(iter->zone->fz_next); - - if (!iter->zone) - goto out; - - iter->bucket = 0; - iter->hash_head = rcu_dereference(iter->zone->fz_hash); - - hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) { - list_for_each_entry(fa, &fn->fn_alias, fa_list) { - iter->fn = fn; - iter->fa = fa; - goto out; - } - } - } -out: - iter->pos++; - return fa; -} - -static struct fib_alias *fib_get_idx(struct seq_file *seq, loff_t pos) -{ - struct fib_iter_state *iter = seq->private; - struct fib_alias *fa; - - if (iter->valid && pos >= iter->pos && iter->genid == fib_hash_genid) { - fa = iter->fa; - pos -= iter->pos; - } else - fa = fib_get_first(seq); - - if (fa) - while (pos && (fa = fib_get_next(seq))) - --pos; - return pos ? NULL : fa; -} - -static void *fib_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) -{ - void *v = NULL; - - rcu_read_lock(); - if (fib_get_table(seq_file_net(seq), RT_TABLE_MAIN)) - v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; - return v; -} - -static void *fib_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - ++*pos; - return v == SEQ_START_TOKEN ? fib_get_first(seq) : fib_get_next(seq); -} - -static void fib_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) -{ - rcu_read_unlock(); -} - -static unsigned fib_flag_trans(int type, __be32 mask, struct fib_info *fi) -{ - static const unsigned type2flags[RTN_MAX + 1] = { - [7] = RTF_REJECT, - [8] = RTF_REJECT, - }; - unsigned flags = type2flags[type]; - - if (fi && fi->fib_nh->nh_gw) - flags |= RTF_GATEWAY; - if (mask == htonl(0xFFFFFFFF)) - flags |= RTF_HOST; - flags |= RTF_UP; - return flags; -} - -/* - * This outputs /proc/net/route. - * - * It always works in backward compatibility mode. - * The format of the file is not supposed to be changed. - */ -static int fib_seq_show(struct seq_file *seq, void *v) -{ - struct fib_iter_state *iter; - int len; - __be32 prefix, mask; - unsigned flags; - struct fib_node *f; - struct fib_alias *fa; - struct fib_info *fi; - - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " - "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU" - "\tWindow\tIRTT"); - goto out; - } - - iter = seq->private; - f = iter->fn; - fa = iter->fa; - fi = fa->fa_info; - prefix = f->fn_key; - mask = FZ_MASK(iter->zone); - flags = fib_flag_trans(fa->fa_type, mask, fi); - if (fi) - seq_printf(seq, - "%s\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u%n", - fi->fib_dev ? fi->fib_dev->name : "*", prefix, - fi->fib_nh->nh_gw, flags, 0, 0, fi->fib_priority, - mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), - fi->fib_window, - fi->fib_rtt >> 3, &len); - else - seq_printf(seq, - "*\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u%n", - prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0, &len); - - seq_printf(seq, "%*s\n", 127 - len, ""); -out: - return 0; -} - -static const struct seq_operations fib_seq_ops = { - .start = fib_seq_start, - .next = fib_seq_next, - .stop = fib_seq_stop, - .show = fib_seq_show, -}; - -static int fib_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &fib_seq_ops, - sizeof(struct fib_iter_state)); -} - -static const struct file_operations fib_seq_fops = { - .owner = THIS_MODULE, - .open = fib_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -int __net_init fib_proc_init(struct net *net) -{ - if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_seq_fops)) - return -ENOMEM; - return 0; -} - -void __net_exit fib_proc_exit(struct net *net) -{ - proc_net_remove(net, "route"); -} -#endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index c079cc0..d5c40d8 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -25,7 +25,7 @@ static inline void fib_alias_accessed(struct fib_alias *fa) } /* Exported by fib_semantics.c */ -extern int fib_semantic_match(struct list_head *head, +extern int fib_semantic_match(struct fib_table *tb, struct list_head *head, const struct flowi *flp, struct fib_result *res, int prefixlen, int fib_flags); extern void fib_release_info(struct fib_info *); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 7981a24..3018efb 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -41,13 +41,13 @@ struct fib4_rule { __be32 srcmask; __be32 dst; __be32 dstmask; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID u32 tclassid; #endif }; -#ifdef CONFIG_NET_CLS_ROUTE -u32 fib_rules_tclass(struct fib_result *res) +#ifdef CONFIG_IP_ROUTE_CLASSID +u32 fib_rules_tclass(const struct fib_result *res) { return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0; } @@ -165,7 +165,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (frh->dst_len) rule4->dst = nla_get_be32(tb[FRA_DST]); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW]) rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); #endif @@ -195,7 +195,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->tos && (rule4->tos != frh->tos)) return 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) return 0; #endif @@ -224,7 +224,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, if (rule4->src_len) NLA_PUT_BE32(skb, FRA_SRC, rule4->src); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (rule4->tclassid) NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid); #endif diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 12d3dc3..562f34c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -49,7 +49,7 @@ static DEFINE_SPINLOCK(fib_info_lock); static struct hlist_head *fib_info_hash; static struct hlist_head *fib_info_laddrhash; -static unsigned int fib_hash_size; +static unsigned int fib_info_hash_size; static unsigned int fib_info_cnt; #define DEVINDEX_HASHBITS 8 @@ -152,6 +152,8 @@ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + if (fi->fib_metrics != (u32 *) dst_default_metrics) + kfree(fi->fib_metrics); kfree(fi); } @@ -200,7 +202,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->nh_weight != onh->nh_weight || #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD)) @@ -221,7 +223,7 @@ static inline unsigned int fib_devindex_hashfn(unsigned int val) static inline unsigned int fib_info_hashfn(const struct fib_info *fi) { - unsigned int mask = (fib_hash_size - 1); + unsigned int mask = (fib_info_hash_size - 1); unsigned int val = fi->fib_nhs; val ^= fi->fib_protocol; @@ -422,7 +424,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, nla = nla_find(attrs, attrlen, RTA_GATEWAY); nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; #endif @@ -476,7 +478,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla && nla_get_be32(nla) != nh->nh_gw) return 1; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); if (nla && nla_get_u32(nla) != nh->nh_tclassid) return 1; @@ -613,14 +615,14 @@ out: static inline unsigned int fib_laddr_hashfn(__be32 val) { - unsigned int mask = (fib_hash_size - 1); + unsigned int mask = (fib_info_hash_size - 1); return ((__force u32)val ^ ((__force u32)val >> 7) ^ ((__force u32)val >> 14)) & mask; } -static struct hlist_head *fib_hash_alloc(int bytes) +static struct hlist_head *fib_info_hash_alloc(int bytes) { if (bytes <= PAGE_SIZE) return kzalloc(bytes, GFP_KERNEL); @@ -630,7 +632,7 @@ static struct hlist_head *fib_hash_alloc(int bytes) get_order(bytes)); } -static void fib_hash_free(struct hlist_head *hash, int bytes) +static void fib_info_hash_free(struct hlist_head *hash, int bytes) { if (!hash) return; @@ -641,18 +643,18 @@ static void fib_hash_free(struct hlist_head *hash, int bytes) free_pages((unsigned long) hash, get_order(bytes)); } -static void fib_hash_move(struct hlist_head *new_info_hash, - struct hlist_head *new_laddrhash, - unsigned int new_size) +static void fib_info_hash_move(struct hlist_head *new_info_hash, + struct hlist_head *new_laddrhash, + unsigned int new_size) { struct hlist_head *old_info_hash, *old_laddrhash; - unsigned int old_size = fib_hash_size; + unsigned int old_size = fib_info_hash_size; unsigned int i, bytes; spin_lock_bh(&fib_info_lock); old_info_hash = fib_info_hash; old_laddrhash = fib_info_laddrhash; - fib_hash_size = new_size; + fib_info_hash_size = new_size; for (i = 0; i < old_size; i++) { struct hlist_head *head = &fib_info_hash[i]; @@ -693,8 +695,8 @@ static void fib_hash_move(struct hlist_head *new_info_hash, spin_unlock_bh(&fib_info_lock); bytes = old_size * sizeof(struct hlist_head *); - fib_hash_free(old_info_hash, bytes); - fib_hash_free(old_laddrhash, bytes); + fib_info_hash_free(old_info_hash, bytes); + fib_info_hash_free(old_laddrhash, bytes); } struct fib_info *fib_create_info(struct fib_config *cfg) @@ -718,8 +720,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) #endif err = -ENOBUFS; - if (fib_info_cnt >= fib_hash_size) { - unsigned int new_size = fib_hash_size << 1; + if (fib_info_cnt >= fib_info_hash_size) { + unsigned int new_size = fib_info_hash_size << 1; struct hlist_head *new_info_hash; struct hlist_head *new_laddrhash; unsigned int bytes; @@ -727,21 +729,27 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (!new_size) new_size = 1; bytes = new_size * sizeof(struct hlist_head *); - new_info_hash = fib_hash_alloc(bytes); - new_laddrhash = fib_hash_alloc(bytes); + new_info_hash = fib_info_hash_alloc(bytes); + new_laddrhash = fib_info_hash_alloc(bytes); if (!new_info_hash || !new_laddrhash) { - fib_hash_free(new_info_hash, bytes); - fib_hash_free(new_laddrhash, bytes); + fib_info_hash_free(new_info_hash, bytes); + fib_info_hash_free(new_laddrhash, bytes); } else - fib_hash_move(new_info_hash, new_laddrhash, new_size); + fib_info_hash_move(new_info_hash, new_laddrhash, new_size); - if (!fib_hash_size) + if (!fib_info_hash_size) goto failure; } fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (fi == NULL) goto failure; + if (cfg->fc_mx) { + fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + if (!fi->fib_metrics) + goto failure; + } else + fi->fib_metrics = (u32 *) dst_default_metrics; fib_info_cnt++; fi->fib_net = hold_net(net); @@ -779,7 +787,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto err_inval; if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) goto err_inval; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) goto err_inval; #endif @@ -792,7 +800,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) nh->nh_oif = cfg->fc_oif; nh->nh_gw = cfg->fc_gw; nh->nh_flags = cfg->fc_flags; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid = cfg->fc_flow; #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -881,8 +889,9 @@ failure: } /* Note! fib_semantic_match intentionally uses RCU list functions. */ -int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, int prefixlen, int fib_flags) +int fib_semantic_match(struct fib_table *tb, struct list_head *head, + const struct flowi *flp, struct fib_result *res, + int prefixlen, int fib_flags) { struct fib_alias *fa; int nh_sel = 0; @@ -946,6 +955,8 @@ out_fill_res: res->type = fa->fa_type; res->scope = fa->fa_scope; res->fi = fa->fa_info; + res->table = tb; + res->fa_head = head; if (!(fib_flags & FIB_LOOKUP_NOREF)) atomic_inc(&res->fi->fib_clntref); return 0; @@ -1002,7 +1013,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (fi->fib_nh->nh_oif) NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (fi->fib_nh[0].nh_tclassid) NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid); #endif @@ -1027,7 +1038,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (nh->nh_gw) NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (nh->nh_tclassid) NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); #endif @@ -1125,6 +1136,62 @@ int fib_sync_down_dev(struct net_device *dev, int force) return ret; } +/* Must be invoked inside of an RCU protected region. */ +void fib_select_default(struct fib_result *res) +{ + struct fib_info *fi = NULL, *last_resort = NULL; + struct list_head *fa_head = res->fa_head; + struct fib_table *tb = res->table; + int order = -1, last_idx = -1; + struct fib_alias *fa; + + list_for_each_entry_rcu(fa, fa_head, fa_list) { + struct fib_info *next_fi = fa->fa_info; + + if (fa->fa_scope != res->scope || + fa->fa_type != RTN_UNICAST) + continue; + + if (next_fi->fib_priority > res->fi->fib_priority) + break; + if (!next_fi->fib_nh[0].nh_gw || + next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) + continue; + + fib_alias_accessed(fa); + + if (fi == NULL) { + if (next_fi != res->fi) + break; + } else if (!fib_detect_death(fi, order, &last_resort, + &last_idx, tb->tb_default)) { + fib_result_assign(res, fi); + tb->tb_default = order; + goto out; + } + fi = next_fi; + order++; + } + + if (order <= 0 || fi == NULL) { + tb->tb_default = -1; + goto out; + } + + if (!fib_detect_death(fi, order, &last_resort, &last_idx, + tb->tb_default)) { + fib_result_assign(res, fi); + tb->tb_default = order; + goto out; + } + + if (last_idx >= 0) + fib_result_assign(res, last_resort); + tb->tb_default = last_idx; +out: + return; +} + #ifdef CONFIG_IP_ROUTE_MULTIPATH /* diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 0f28034..edf3b09 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -95,7 +95,7 @@ typedef unsigned int t_key; #define IS_TNODE(n) (!(n->parent & T_LEAF)) #define IS_LEAF(n) (n->parent & T_LEAF) -struct node { +struct rt_trie_node { unsigned long parent; t_key key; }; @@ -126,7 +126,7 @@ struct tnode { struct work_struct work; struct tnode *tnode_free; }; - struct node *child[0]; + struct rt_trie_node *child[0]; }; #ifdef CONFIG_IP_FIB_TRIE_STATS @@ -151,16 +151,16 @@ struct trie_stat { }; struct trie { - struct node *trie; + struct rt_trie_node *trie; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats stats; #endif }; -static void put_child(struct trie *t, struct tnode *tn, int i, struct node *n); -static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, +static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n); +static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull); -static struct node *resize(struct trie *t, struct tnode *tn); +static struct rt_trie_node *resize(struct trie *t, struct tnode *tn); static struct tnode *inflate(struct trie *t, struct tnode *tn); static struct tnode *halve(struct trie *t, struct tnode *tn); /* tnodes to free after resize(); protected by RTNL */ @@ -177,12 +177,12 @@ static const int sync_pages = 128; static struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; -static inline struct tnode *node_parent(struct node *node) +static inline struct tnode *node_parent(struct rt_trie_node *node) { return (struct tnode *)(node->parent & ~NODE_TYPE_MASK); } -static inline struct tnode *node_parent_rcu(struct node *node) +static inline struct tnode *node_parent_rcu(struct rt_trie_node *node) { struct tnode *ret = node_parent(node); @@ -192,22 +192,22 @@ static inline struct tnode *node_parent_rcu(struct node *node) /* Same as rcu_assign_pointer * but that macro() assumes that value is a pointer. */ -static inline void node_set_parent(struct node *node, struct tnode *ptr) +static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr) { smp_wmb(); node->parent = (unsigned long)ptr | NODE_TYPE(node); } -static inline struct node *tnode_get_child(struct tnode *tn, unsigned int i) +static inline struct rt_trie_node *tnode_get_child(struct tnode *tn, unsigned int i) { BUG_ON(i >= 1U << tn->bits); return tn->child[i]; } -static inline struct node *tnode_get_child_rcu(struct tnode *tn, unsigned int i) +static inline struct rt_trie_node *tnode_get_child_rcu(struct tnode *tn, unsigned int i) { - struct node *ret = tnode_get_child(tn, i); + struct rt_trie_node *ret = tnode_get_child(tn, i); return rcu_dereference_rtnl(ret); } @@ -217,12 +217,12 @@ static inline int tnode_child_length(const struct tnode *tn) return 1 << tn->bits; } -static inline t_key mask_pfx(t_key k, unsigned short l) +static inline t_key mask_pfx(t_key k, unsigned int l) { return (l == 0) ? 0 : k >> (KEYLENGTH-l) << (KEYLENGTH-l); } -static inline t_key tkey_extract_bits(t_key a, int offset, int bits) +static inline t_key tkey_extract_bits(t_key a, unsigned int offset, unsigned int bits) { if (offset < KEYLENGTH) return ((t_key)(a << offset)) >> (KEYLENGTH - bits); @@ -378,7 +378,7 @@ static void __tnode_free_rcu(struct rcu_head *head) { struct tnode *tn = container_of(head, struct tnode, rcu); size_t size = sizeof(struct tnode) + - (sizeof(struct node *) << tn->bits); + (sizeof(struct rt_trie_node *) << tn->bits); if (size <= PAGE_SIZE) kfree(tn); @@ -402,7 +402,7 @@ static void tnode_free_safe(struct tnode *tn) tn->tnode_free = tnode_free_head; tnode_free_head = tn; tnode_free_size += sizeof(struct tnode) + - (sizeof(struct node *) << tn->bits); + (sizeof(struct rt_trie_node *) << tn->bits); } static void tnode_free_flush(void) @@ -443,7 +443,7 @@ static struct leaf_info *leaf_info_new(int plen) static struct tnode *tnode_new(t_key key, int pos, int bits) { - size_t sz = sizeof(struct tnode) + (sizeof(struct node *) << bits); + size_t sz = sizeof(struct tnode) + (sizeof(struct rt_trie_node *) << bits); struct tnode *tn = tnode_alloc(sz); if (tn) { @@ -456,7 +456,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) } pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), - sizeof(struct node) << bits); + sizeof(struct rt_trie_node) << bits); return tn; } @@ -465,7 +465,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) * and no bits are skipped. See discussion in dyntree paper p. 6 */ -static inline int tnode_full(const struct tnode *tn, const struct node *n) +static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node *n) { if (n == NULL || IS_LEAF(n)) return 0; @@ -474,7 +474,7 @@ static inline int tnode_full(const struct tnode *tn, const struct node *n) } static inline void put_child(struct trie *t, struct tnode *tn, int i, - struct node *n) + struct rt_trie_node *n) { tnode_put_child_reorg(tn, i, n, -1); } @@ -484,10 +484,10 @@ static inline void put_child(struct trie *t, struct tnode *tn, int i, * Update the value of full_children and empty_children. */ -static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, +static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull) { - struct node *chi = tn->child[i]; + struct rt_trie_node *chi = tn->child[i]; int isfull; BUG_ON(i >= 1<<tn->bits); @@ -515,7 +515,7 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, } #define MAX_WORK 10 -static struct node *resize(struct trie *t, struct tnode *tn) +static struct rt_trie_node *resize(struct trie *t, struct tnode *tn) { int i; struct tnode *old_tn; @@ -605,7 +605,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Keep root node larger */ - if (!node_parent((struct node *)tn)) { + if (!node_parent((struct rt_trie_node *)tn)) { inflate_threshold_use = inflate_threshold_root; halve_threshold_use = halve_threshold_root; } else { @@ -635,7 +635,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Return if at least one inflate is run */ if (max_work != MAX_WORK) - return (struct node *) tn; + return (struct rt_trie_node *) tn; /* * Halve as long as the number of empty children in this @@ -663,7 +663,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) if (tn->empty_children == tnode_child_length(tn) - 1) { one_child: for (i = 0; i < tnode_child_length(tn); i++) { - struct node *n; + struct rt_trie_node *n; n = tn->child[i]; if (!n) @@ -676,7 +676,7 @@ one_child: return n; } } - return (struct node *) tn; + return (struct rt_trie_node *) tn; } static struct tnode *inflate(struct trie *t, struct tnode *tn) @@ -723,14 +723,14 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) goto nomem; } - put_child(t, tn, 2*i, (struct node *) left); - put_child(t, tn, 2*i+1, (struct node *) right); + put_child(t, tn, 2*i, (struct rt_trie_node *) left); + put_child(t, tn, 2*i+1, (struct rt_trie_node *) right); } } for (i = 0; i < olen; i++) { struct tnode *inode; - struct node *node = tnode_get_child(oldtnode, i); + struct rt_trie_node *node = tnode_get_child(oldtnode, i); struct tnode *left, *right; int size, j; @@ -825,7 +825,7 @@ nomem: static struct tnode *halve(struct trie *t, struct tnode *tn) { struct tnode *oldtnode = tn; - struct node *left, *right; + struct rt_trie_node *left, *right; int i; int olen = tnode_child_length(tn); @@ -856,7 +856,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (!newn) goto nomem; - put_child(t, tn, i/2, (struct node *)newn); + put_child(t, tn, i/2, (struct rt_trie_node *)newn); } } @@ -958,7 +958,7 @@ fib_find_node(struct trie *t, u32 key) { int pos; struct tnode *tn; - struct node *n; + struct rt_trie_node *n; pos = 0; n = rcu_dereference_rtnl(t->trie); @@ -993,17 +993,17 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) key = tn->key; - while (tn != NULL && (tp = node_parent((struct node *)tn)) != NULL) { + while (tn != NULL && (tp = node_parent((struct rt_trie_node *)tn)) != NULL) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); wasfull = tnode_full(tp, tnode_get_child(tp, cindex)); tn = (struct tnode *) resize(t, (struct tnode *)tn); tnode_put_child_reorg((struct tnode *)tp, cindex, - (struct node *)tn, wasfull); + (struct rt_trie_node *)tn, wasfull); - tp = node_parent((struct node *) tn); + tp = node_parent((struct rt_trie_node *) tn); if (!tp) - rcu_assign_pointer(t->trie, (struct node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); if (!tp) @@ -1015,7 +1015,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) if (IS_TNODE(tn)) tn = (struct tnode *)resize(t, (struct tnode *)tn); - rcu_assign_pointer(t->trie, (struct node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); } @@ -1025,7 +1025,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) { int pos, newpos; struct tnode *tp = NULL, *tn = NULL; - struct node *n; + struct rt_trie_node *n; struct leaf *l; int missbit; struct list_head *fa_head = NULL; @@ -1111,10 +1111,10 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) if (t->trie && n == NULL) { /* Case 2: n is NULL, and will just insert a new leaf */ - node_set_parent((struct node *)l, tp); + node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, (struct node *)l); + put_child(t, (struct tnode *)tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1141,18 +1141,18 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) return NULL; } - node_set_parent((struct node *)tn, tp); + node_set_parent((struct rt_trie_node *)tn, tp); missbit = tkey_extract_bits(key, newpos, 1); - put_child(t, tn, missbit, (struct node *)l); + put_child(t, tn, missbit, (struct rt_trie_node *)l); put_child(t, tn, 1-missbit, n); if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); put_child(t, (struct tnode *)tp, cindex, - (struct node *)tn); + (struct rt_trie_node *)tn); } else { - rcu_assign_pointer(t->trie, (struct node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; } } @@ -1340,7 +1340,7 @@ err: } /* should be called with rcu_read_lock */ -static int check_leaf(struct trie *t, struct leaf *l, +static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, t_key key, const struct flowi *flp, struct fib_result *res, int fib_flags) { @@ -1356,7 +1356,7 @@ static int check_leaf(struct trie *t, struct leaf *l, if (l->key != (key & ntohl(mask))) continue; - err = fib_semantic_match(&li->falh, flp, res, plen, fib_flags); + err = fib_semantic_match(tb, &li->falh, flp, res, plen, fib_flags); #ifdef CONFIG_IP_FIB_TRIE_STATS if (err <= 0) @@ -1376,13 +1376,13 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, { struct trie *t = (struct trie *) tb->tb_data; int ret; - struct node *n; + struct rt_trie_node *n; struct tnode *pn; - int pos, bits; + unsigned int pos, bits; t_key key = ntohl(flp->fl4_dst); - int chopped_off; + unsigned int chopped_off; t_key cindex = 0; - int current_prefix_length = KEYLENGTH; + unsigned int current_prefix_length = KEYLENGTH; struct tnode *cn; t_key pref_mismatch; @@ -1398,7 +1398,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, /* Just a leaf? */ if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); + ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags); goto found; } @@ -1423,7 +1423,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, } if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); + ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags); if (ret > 0) goto backtrace; goto found; @@ -1541,7 +1541,7 @@ backtrace: if (chopped_off <= pn->bits) { cindex &= ~(1 << (chopped_off-1)); } else { - struct tnode *parent = node_parent_rcu((struct node *) pn); + struct tnode *parent = node_parent_rcu((struct rt_trie_node *) pn); if (!parent) goto failed; @@ -1568,7 +1568,7 @@ found: */ static void trie_leaf_remove(struct trie *t, struct leaf *l) { - struct tnode *tp = node_parent((struct node *) l); + struct tnode *tp = node_parent((struct rt_trie_node *) l); pr_debug("entering trie_leaf_remove(%p)\n", l); @@ -1706,7 +1706,7 @@ static int trie_flush_leaf(struct leaf *l) * Scan for the next right leaf starting at node p->child[idx] * Since we have back pointer, no recursion necessary. */ -static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) +static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) { do { t_key idx; @@ -1732,7 +1732,7 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) } /* Node empty, walk back up to parent */ - c = (struct node *) p; + c = (struct rt_trie_node *) p; } while ((p = node_parent_rcu(c)) != NULL); return NULL; /* Root of trie */ @@ -1753,7 +1753,7 @@ static struct leaf *trie_firstleaf(struct trie *t) static struct leaf *trie_nextleaf(struct leaf *l) { - struct node *c = (struct node *) l; + struct rt_trie_node *c = (struct rt_trie_node *) l; struct tnode *p = node_parent_rcu(c); if (!p) @@ -1802,80 +1802,6 @@ void fib_free_table(struct fib_table *tb) kfree(tb); } -void fib_table_select_default(struct fib_table *tb, - const struct flowi *flp, - struct fib_result *res) -{ - struct trie *t = (struct trie *) tb->tb_data; - int order, last_idx; - struct fib_info *fi = NULL; - struct fib_info *last_resort; - struct fib_alias *fa = NULL; - struct list_head *fa_head; - struct leaf *l; - - last_idx = -1; - last_resort = NULL; - order = -1; - - rcu_read_lock(); - - l = fib_find_node(t, 0); - if (!l) - goto out; - - fa_head = get_fa_head(l, 0); - if (!fa_head) - goto out; - - if (list_empty(fa_head)) - goto out; - - list_for_each_entry_rcu(fa, fa_head, fa_list) { - struct fib_info *next_fi = fa->fa_info; - - if (fa->fa_scope != res->scope || - fa->fa_type != RTN_UNICAST) - continue; - - if (next_fi->fib_priority > res->fi->fib_priority) - break; - if (!next_fi->fib_nh[0].nh_gw || - next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) - continue; - - fib_alias_accessed(fa); - - if (fi == NULL) { - if (next_fi != res->fi) - break; - } else if (!fib_detect_death(fi, order, &last_resort, - &last_idx, tb->tb_default)) { - fib_result_assign(res, fi); - tb->tb_default = order; - goto out; - } - fi = next_fi; - order++; - } - if (order <= 0 || fi == NULL) { - tb->tb_default = -1; - goto out; - } - - if (!fib_detect_death(fi, order, &last_resort, &last_idx, - tb->tb_default)) { - fib_result_assign(res, fi); - tb->tb_default = order; - goto out; - } - if (last_idx >= 0) - fib_result_assign(res, last_resort); - tb->tb_default = last_idx; -out: - rcu_read_unlock(); -} - static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) @@ -1990,7 +1916,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, return skb->len; } -void __init fib_hash_init(void) +void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), @@ -2003,8 +1929,7 @@ void __init fib_hash_init(void) } -/* Fix more generic FIB names for init later */ -struct fib_table *fib_hash_table(u32 id) +struct fib_table *fib_trie_table(u32 id) { struct fib_table *tb; struct trie *t; @@ -2036,7 +1961,7 @@ struct fib_trie_iter { unsigned int depth; }; -static struct node *fib_trie_get_next(struct fib_trie_iter *iter) +static struct rt_trie_node *fib_trie_get_next(struct fib_trie_iter *iter) { struct tnode *tn = iter->tnode; unsigned int cindex = iter->index; @@ -2050,7 +1975,7 @@ static struct node *fib_trie_get_next(struct fib_trie_iter *iter) iter->tnode, iter->index, iter->depth); rescan: while (cindex < (1<<tn->bits)) { - struct node *n = tnode_get_child_rcu(tn, cindex); + struct rt_trie_node *n = tnode_get_child_rcu(tn, cindex); if (n) { if (IS_LEAF(n)) { @@ -2069,7 +1994,7 @@ rescan: } /* Current node exhausted, pop back up */ - p = node_parent_rcu((struct node *)tn); + p = node_parent_rcu((struct rt_trie_node *)tn); if (p) { cindex = tkey_extract_bits(tn->key, p->pos, p->bits)+1; tn = p; @@ -2081,10 +2006,10 @@ rescan: return NULL; } -static struct node *fib_trie_get_first(struct fib_trie_iter *iter, +static struct rt_trie_node *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { - struct node *n; + struct rt_trie_node *n; if (!t) return NULL; @@ -2108,7 +2033,7 @@ static struct node *fib_trie_get_first(struct fib_trie_iter *iter, static void trie_collect_stats(struct trie *t, struct trie_stat *s) { - struct node *n; + struct rt_trie_node *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); @@ -2181,7 +2106,7 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); - bytes += sizeof(struct node *) * pointers; + bytes += sizeof(struct rt_trie_node *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } @@ -2262,7 +2187,7 @@ static const struct file_operations fib_triestat_fops = { .release = single_release_net, }; -static struct node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) +static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); @@ -2275,7 +2200,7 @@ static struct node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) struct fib_table *tb; hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { - struct node *n; + struct rt_trie_node *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); @@ -2304,7 +2229,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; - struct node *n; + struct rt_trie_node *n; ++*pos; /* next node in same table */ @@ -2390,7 +2315,7 @@ static inline const char *rtn_type(char *buf, size_t len, unsigned int t) static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; - struct node *n = v; + struct rt_trie_node *n = v; if (!node_parent_rcu(n)) fib_table_print(seq, iter->tb); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4aa1b7f..ad2bcf1 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -233,48 +233,11 @@ static inline void icmp_xmit_unlock(struct sock *sk) * Send an ICMP frame. */ -/* - * Check transmit rate limitation for given message. - * The rate information is held in the destination cache now. - * This function is generic and could be used for other purposes - * too. It uses a Token bucket filter as suggested by Alexey Kuznetsov. - * - * Note that the same dst_entry fields are modified by functions in - * route.c too, but these work for packet destinations while xrlim_allow - * works for icmp destinations. This means the rate limiting information - * for one "ip object" is shared - and these ICMPs are twice limited: - * by source and by destination. - * - * RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate - * SHOULD allow setting of rate limits - * - * Shared between ICMPv4 and ICMPv6. - */ -#define XRLIM_BURST_FACTOR 6 -int xrlim_allow(struct dst_entry *dst, int timeout) -{ - unsigned long now, token = dst->rate_tokens; - int rc = 0; - - now = jiffies; - token += now - dst->rate_last; - dst->rate_last = now; - if (token > XRLIM_BURST_FACTOR * timeout) - token = XRLIM_BURST_FACTOR * timeout; - if (token >= timeout) { - token -= timeout; - rc = 1; - } - dst->rate_tokens = token; - return rc; -} -EXPORT_SYMBOL(xrlim_allow); - -static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt, +static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, int type, int code) { struct dst_entry *dst = &rt->dst; - int rc = 1; + bool rc = true; if (type > NR_ICMP_TYPES) goto out; @@ -288,8 +251,12 @@ static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt, goto out; /* Limit if icmp type is enabled in ratemask. */ - if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) - rc = xrlim_allow(dst, net->ipv4.sysctl_icmp_ratelimit); + if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) { + if (!rt->peer) + rt_bind_peer(rt, 1); + rc = inet_peer_xrlim_allow(rt->peer, + net->ipv4.sysctl_icmp_ratelimit); + } out: return rc; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index a96e656..48f8d45 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -167,9 +167,9 @@ static int addr_compare(const struct inetpeer_addr *a, int i, n = (a->family == AF_INET ? 1 : 4); for (i = 0; i < n; i++) { - if (a->a6[i] == b->a6[i]) + if (a->addr.a6[i] == b->addr.a6[i]) continue; - if (a->a6[i] < b->a6[i]) + if (a->addr.a6[i] < b->addr.a6[i]) return -1; return 1; } @@ -510,8 +510,13 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4)); + atomic_set(&p->ip_id_count, secure_ip_id(daddr->addr.a4)); p->tcp_ts_stamp = 0; + p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; + p->rate_tokens = 0; + p->rate_last = 0; + p->pmtu_expires = 0; + memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); INIT_LIST_HEAD(&p->unused); @@ -579,3 +584,44 @@ void inet_putpeer(struct inet_peer *p) local_bh_enable(); } EXPORT_SYMBOL_GPL(inet_putpeer); + +/* + * Check transmit rate limitation for given message. + * The rate information is held in the inet_peer entries now. + * This function is generic and could be used for other purposes + * too. It uses a Token bucket filter as suggested by Alexey Kuznetsov. + * + * Note that the same inet_peer fields are modified by functions in + * route.c too, but these work for packet destinations while xrlim_allow + * works for icmp destinations. This means the rate limiting information + * for one "ip object" is shared - and these ICMPs are twice limited: + * by source and by destination. + * + * RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate + * SHOULD allow setting of rate limits + * + * Shared between ICMPv4 and ICMPv6. + */ +#define XRLIM_BURST_FACTOR 6 +bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) +{ + unsigned long now, token; + bool rc = false; + + if (!peer) + return true; + + token = peer->rate_tokens; + now = jiffies; + token += now - peer->rate_last; + peer->rate_last = now; + if (token > XRLIM_BURST_FACTOR * timeout) + token = XRLIM_BURST_FACTOR * timeout; + if (token >= timeout) { + token -= timeout; + rc = true; + } + peer->rate_tokens = token; + return rc; +} +EXPORT_SYMBOL(inet_peer_xrlim_allow); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d859bcc..d7b2b09 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -340,7 +340,7 @@ static int ip_rcv_finish(struct sk_buff *skb) } } -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (unlikely(skb_dst(skb)->tclassid)) { struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct); u32 idx = skb_dst(skb)->tclassid; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index babd1a2..f926a31 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -206,8 +206,9 @@ config IP_NF_TARGET_REDIRECT config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" - depends on NF_NAT + depends on NF_CONNTRACK_SNMP && NF_NAT depends on NETFILTER_ADVANCED + default NF_NAT && NF_CONNTRACK_SNMP ---help--- This module implements an Application Layer Gateway (ALG) for diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e855fff..e95054c 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -866,6 +866,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(NFPROTO_ARP, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1333,6 +1334,7 @@ static int translate_compat_table(const char *name, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(NFPROTO_ARP); + xt_compat_init_offsets(NFPROTO_ARP, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 652efea..ef7d7b9 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1063,6 +1063,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1664,6 +1665,7 @@ translate_compat_table(struct net *net, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET); + xt_compat_init_offsets(AF_INET, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 1e26a48..403ca57 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -300,13 +300,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) * that the ->target() function isn't called after ->destroy() */ ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) { - pr_info("no conntrack!\n"); - /* FIXME: need to drop invalid ones, since replies - * to outgoing connections of other nodes will be - * marked as INVALID */ + if (ct == NULL) return NF_DROP; - } /* special case: ICMP error handling. conntrack distinguishes between * error messages (RELATED) and information requests (see below) */ diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 72ffc8f..d76d6c9 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -442,8 +442,7 @@ ipt_log_packet(u_int8_t pf, } #endif - /* MAC logging for input path only. */ - if (in && !out) + if (in != NULL) dump_mac_header(m, loginfo, skb); dump_packet(m, loginfo, skb, 0); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 294a2a3..aef5d1f 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -60,7 +60,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, dev_net(out)->ipv4.iptable_mangle); /* Reroute for ANY change. */ - if (ret != NF_DROP && ret != NF_STOLEN && ret != NF_QUEUE) { + if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 63f60fc..5585980 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -20,6 +20,7 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_acct.h> +#include <linux/rculist_nulls.h> struct ct_iter_state { struct seq_net_private p; @@ -35,7 +36,8 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) for (st->bucket = 0; st->bucket < net->ct.htable_size; st->bucket++) { - n = rcu_dereference(net->ct.hash[st->bucket].first); + n = rcu_dereference( + hlist_nulls_first_rcu(&net->ct.hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -48,13 +50,14 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { if (++st->bucket >= net->ct.htable_size) return NULL; } - head = rcu_dereference(net->ct.hash[st->bucket].first); + head = rcu_dereference( + hlist_nulls_first_rcu(&net->ct.hash[st->bucket])); } return head; } @@ -217,7 +220,8 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq) struct hlist_node *n; for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) { - n = rcu_dereference(net->ct.expect_hash[st->bucket].first); + n = rcu_dereference( + hlist_first_rcu(&net->ct.expect_hash[st->bucket])); if (n) return n; } @@ -230,11 +234,12 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_expect_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_next_rcu(head)); while (head == NULL) { if (++st->bucket >= nf_ct_expect_hsize) return NULL; - head = rcu_dereference(net->ct.expect_hash[st->bucket].first); + head = rcu_dereference( + hlist_first_rcu(&net->ct.expect_hash[st->bucket])); } return head; } diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 0f23b3f..703f366f 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -44,13 +44,13 @@ static unsigned int help(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { - int ret; + int res; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); - if (ret == 0) + res = nf_ct_expect_related(exp); + if (res == 0) break; - else if (ret != -EBUSY) { + else if (res != -EBUSY) { port = 0; break; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index c04787c..21bcf47 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -221,7 +221,14 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, manips not an issue. */ if (maniptype == IP_NAT_MANIP_SRC && !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { - if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) { + /* try the original tuple first */ + if (in_range(orig_tuple, range)) { + if (!nf_nat_used_tuple(orig_tuple, ct)) { + *tuple = *orig_tuple; + return; + } + } else if (find_appropriate_src(net, zone, orig_tuple, tuple, + range)) { pr_debug("get_unique_tuple: Found current src map\n"); if (!nf_nat_used_tuple(tuple, ct)) return; @@ -266,7 +273,6 @@ nf_nat_setup_info(struct nf_conn *ct, struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple curr_tuple, new_tuple; struct nf_conn_nat *nat; - int have_to_hash = !(ct->status & IPS_NAT_DONE_MASK); /* nat helper or nfctnetlink also setup binding */ nat = nfct_nat(ct); @@ -306,8 +312,7 @@ nf_nat_setup_info(struct nf_conn *ct, ct->status |= IPS_DST_NAT; } - /* Place in source hash if this is the first time. */ - if (have_to_hash) { + if (maniptype == IP_NAT_MANIP_SRC) { unsigned int srchash; srchash = hash_by_src(net, nf_ct_zone(ct), @@ -323,9 +328,9 @@ nf_nat_setup_info(struct nf_conn *ct, /* It's done. */ if (maniptype == IP_NAT_MANIP_DST) - set_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + ct->status |= IPS_DST_NAT_DONE; else - set_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + ct->status |= IPS_SRC_NAT_DONE; return NF_ACCEPT; } @@ -502,7 +507,10 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto) int ret = 0; spin_lock_bh(&nf_nat_lock); - if (nf_nat_protos[proto->protonum] != &nf_nat_unknown_protocol) { + if (rcu_dereference_protected( + nf_nat_protos[proto->protonum], + lockdep_is_held(&nf_nat_lock) + ) != &nf_nat_unknown_protocol) { ret = -EBUSY; goto out; } @@ -532,7 +540,7 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (nat == NULL || nat->ct == NULL) return; - NF_CT_ASSERT(nat->ct->status & IPS_NAT_DONE_MASK); + NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); spin_lock_bh(&nf_nat_lock); hlist_del_rcu(&nat->bysource); @@ -545,11 +553,10 @@ static void nf_nat_move_storage(void *new, void *old) struct nf_conn_nat *old_nat = old; struct nf_conn *ct = old_nat->ct; - if (!ct || !(ct->status & IPS_NAT_DONE_MASK)) + if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) return; spin_lock_bh(&nf_nat_lock); - new_nat->ct = ct; hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); spin_unlock_bh(&nf_nat_lock); } @@ -679,8 +686,7 @@ static int __net_init nf_nat_net_init(struct net *net) { /* Leave them the same for the moment. */ net->ipv4.nat_htable_size = net->ct.htable_size; - net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, - &net->ipv4.nat_vmalloced, 0); + net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0); if (!net->ipv4.nat_bysource) return -ENOMEM; return 0; @@ -702,8 +708,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { nf_ct_iterate_cleanup(net, &clean_nat, NULL); synchronize_rcu(); - nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced, - net->ipv4.nat_htable_size); + nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size); } static struct pernet_operations nf_nat_net_ops = { diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index ee5f419..8812a02 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -54,6 +54,7 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_nat_helper.h> +#include <linux/netfilter/nf_conntrack_snmp.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); @@ -1310,9 +1311,9 @@ static int __init nf_nat_snmp_basic_init(void) { int ret = 0; - ret = nf_conntrack_helper_register(&snmp_helper); - if (ret < 0) - return ret; + BUG_ON(nf_nat_snmp_hook != NULL); + rcu_assign_pointer(nf_nat_snmp_hook, help); + ret = nf_conntrack_helper_register(&snmp_trap_helper); if (ret < 0) { nf_conntrack_helper_unregister(&snmp_helper); @@ -1323,7 +1324,7 @@ static int __init nf_nat_snmp_basic_init(void) static void __exit nf_nat_snmp_basic_fini(void) { - nf_conntrack_helper_unregister(&snmp_helper); + rcu_assign_pointer(nf_nat_snmp_hook, NULL); nf_conntrack_helper_unregister(&snmp_trap_helper); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6ed6603..52b077d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -131,9 +131,6 @@ static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; -static struct delayed_work expires_work; -static unsigned long expires_ljiffies; - /* * Interface to generic destination cache. */ @@ -152,6 +149,41 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { } +static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + struct rtable *rt = (struct rtable *) dst; + struct inet_peer *peer; + u32 *p = NULL; + + if (!rt->peer) + rt_bind_peer(rt, 1); + + peer = rt->peer; + if (peer) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + p = peer->metrics; + if (inet_metrics_new(peer)) + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } else { + if (rt->fi) { + fib_info_put(rt->fi); + rt->fi = NULL; + } + } + } + return p; +} + static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), @@ -159,6 +191,7 @@ static struct dst_ops ipv4_dst_ops = { .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .default_mtu = ipv4_default_mtu, + .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, @@ -514,7 +547,7 @@ static const struct file_operations rt_cpu_seq_fops = { .release = seq_release, }; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; @@ -567,14 +600,14 @@ static int __net_init ip_rt_do_proc_init(struct net *net) if (!pde) goto err2; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops); if (!pde) goto err3; #endif return 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif @@ -588,7 +621,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } @@ -632,7 +665,7 @@ static inline int rt_fast_clean(struct rtable *rth) static inline int rt_valuable(struct rtable *rth) { return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) || - rth->dst.expires; + (rth->peer && rth->peer->pmtu_expires); } static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2) @@ -643,13 +676,7 @@ static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long t if (atomic_read(&rth->dst.__refcnt)) goto out; - ret = 1; - if (rth->dst.expires && - time_after_eq(jiffies, rth->dst.expires)) - goto out; - age = jiffies - rth->dst.lastuse; - ret = 0; if ((age <= tmo1 && !rt_fast_clean(rth)) || (age <= tmo2 && rt_valuable(rth))) goto out; @@ -793,97 +820,6 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } -static void rt_check_expire(void) -{ - static unsigned int rover; - unsigned int i = rover, goal; - struct rtable *rth; - struct rtable __rcu **rthp; - unsigned long samples = 0; - unsigned long sum = 0, sum2 = 0; - unsigned long delta; - u64 mult; - - delta = jiffies - expires_ljiffies; - expires_ljiffies = jiffies; - mult = ((u64)delta) << rt_hash_log; - if (ip_rt_gc_timeout > 1) - do_div(mult, ip_rt_gc_timeout); - goal = (unsigned int)mult; - if (goal > rt_hash_mask) - goal = rt_hash_mask + 1; - for (; goal > 0; goal--) { - unsigned long tmo = ip_rt_gc_timeout; - unsigned long length; - - i = (i + 1) & rt_hash_mask; - rthp = &rt_hash_table[i].chain; - - if (need_resched()) - cond_resched(); - - samples++; - - if (rcu_dereference_raw(*rthp) == NULL) - continue; - length = 0; - spin_lock_bh(rt_hash_lock_addr(i)); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { - prefetch(rth->dst.rt_next); - if (rt_is_expired(rth)) { - *rthp = rth->dst.rt_next; - rt_free(rth); - continue; - } - if (rth->dst.expires) { - /* Entry is expired even if it is in use */ - if (time_before_eq(jiffies, rth->dst.expires)) { -nofree: - tmo >>= 1; - rthp = &rth->dst.rt_next; - /* - * We only count entries on - * a chain with equal hash inputs once - * so that entries for different QOS - * levels, and other non-hash input - * attributes don't unfairly skew - * the length computation - */ - length += has_noalias(rt_hash_table[i].chain, rth); - continue; - } - } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) - goto nofree; - - /* Cleanup aged off entries. */ - *rthp = rth->dst.rt_next; - rt_free(rth); - } - spin_unlock_bh(rt_hash_lock_addr(i)); - sum += length; - sum2 += length*length; - } - if (samples) { - unsigned long avg = sum / samples; - unsigned long sd = int_sqrt(sum2 / samples - avg*avg); - rt_chain_length_max = max_t(unsigned long, - ip_rt_gc_elasticity, - (avg + 4*sd) >> FRACT_BITS); - } - rover = i; -} - -/* - * rt_worker_func() is run in process context. - * we call rt_check_expire() to scan part of the hash table - */ -static void rt_worker_func(struct work_struct *work) -{ - rt_check_expire(); - schedule_delayed_work(&expires_work, ip_rt_gc_interval); -} - /* * Pertubation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -1272,6 +1208,13 @@ skip_hashing: return 0; } +static atomic_t __rt_peer_genid = ATOMIC_INIT(0); + +static u32 rt_peer_genid(void) +{ + return atomic_read(&__rt_peer_genid); +} + void rt_bind_peer(struct rtable *rt, int create) { struct inet_peer *peer; @@ -1280,6 +1223,8 @@ void rt_bind_peer(struct rtable *rt, int create) if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) inet_putpeer(peer); + else + rt->rt_peer_genid = rt_peer_genid(); } /* @@ -1349,13 +1294,8 @@ static void rt_del(unsigned hash, struct rtable *rt) void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { - int i, k; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rth; - struct rtable __rcu **rthp; - __be32 skeys[2] = { saddr, 0 }; - int ikeys[2] = { dev->ifindex, 0 }; - struct netevent_redirect netevent; + struct inet_peer *peer; struct net *net; if (!in_dev) @@ -1367,9 +1307,6 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, ipv4_is_zeronet(new_gw)) goto reject_redirect; - if (!rt_caching(net)) - goto reject_redirect; - if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; @@ -1380,91 +1317,13 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - for (i = 0; i < 2; i++) { - for (k = 0; k < 2; k++) { - unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], - rt_genid(net)); - - rthp = &rt_hash_table[hash].chain; - - while ((rth = rcu_dereference(*rthp)) != NULL) { - struct rtable *rt; - - if (rth->fl.fl4_dst != daddr || - rth->fl.fl4_src != skeys[i] || - rth->fl.oif != ikeys[k] || - rt_is_input_route(rth) || - rt_is_expired(rth) || - !net_eq(dev_net(rth->dst.dev), net)) { - rthp = &rth->dst.rt_next; - continue; - } - - if (rth->rt_dst != daddr || - rth->rt_src != saddr || - rth->dst.error || - rth->rt_gateway != old_gw || - rth->dst.dev != dev) - break; - - dst_hold(&rth->dst); - - rt = dst_alloc(&ipv4_dst_ops); - if (rt == NULL) { - ip_rt_put(rth); - return; - } - - /* Copy all the information. */ - *rt = *rth; - rt->dst.__use = 1; - atomic_set(&rt->dst.__refcnt, 1); - rt->dst.child = NULL; - if (rt->dst.dev) - dev_hold(rt->dst.dev); - rt->dst.obsolete = -1; - rt->dst.lastuse = jiffies; - rt->dst.path = &rt->dst; - rt->dst.neighbour = NULL; - rt->dst.hh = NULL; -#ifdef CONFIG_XFRM - rt->dst.xfrm = NULL; -#endif - rt->rt_genid = rt_genid(net); - rt->rt_flags |= RTCF_REDIRECTED; - - /* Gateway is different ... */ - rt->rt_gateway = new_gw; - - /* Redirect received -> path was valid */ - dst_confirm(&rth->dst); - - if (rt->peer) - atomic_inc(&rt->peer->refcnt); - - if (arp_bind_neighbour(&rt->dst) || - !(rt->dst.neighbour->nud_state & - NUD_VALID)) { - if (rt->dst.neighbour) - neigh_event_send(rt->dst.neighbour, NULL); - ip_rt_put(rth); - rt_drop(rt); - goto do_next; - } + peer = inet_getpeer_v4(daddr, 1); + if (peer) { + peer->redirect_learned.a4 = new_gw; - netevent.old = &rth->dst; - netevent.new = &rt->dst; - call_netevent_notifiers(NETEVENT_REDIRECT, - &netevent); + inet_putpeer(peer); - rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif)) - ip_rt_put(rt); - goto do_next; - } - do_next: - ; - } + atomic_inc(&__rt_peer_genid); } return; @@ -1488,9 +1347,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - (rt->dst.expires && - time_after_eq(jiffies, rt->dst.expires))) { + } else if (rt->rt_flags & RTCF_REDIRECTED) { unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, rt->fl.oif, rt_genid(dev_net(dst->dev))); @@ -1500,6 +1357,14 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) #endif rt_del(hash, rt); ret = NULL; + } else if (rt->peer && + rt->peer->pmtu_expires && + time_after_eq(jiffies, rt->peer->pmtu_expires)) { + unsigned long orig = rt->peer->pmtu_expires; + + if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) + dst_metric_set(dst, RTAX_MTU, + rt->peer->pmtu_orig); } } return ret; @@ -1525,6 +1390,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; + struct inet_peer *peer; int log_martians; rcu_read_lock(); @@ -1536,33 +1402,41 @@ void ip_rt_send_redirect(struct sk_buff *skb) log_martians = IN_DEV_LOG_MARTIANS(in_dev); rcu_read_unlock(); + if (!rt->peer) + rt_bind_peer(rt, 1); + peer = rt->peer; + if (!peer) { + icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); + return; + } + /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, rt->dst.rate_last + ip_rt_redirect_silence)) - rt->dst.rate_tokens = 0; + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + peer->rate_tokens = 0; /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (rt->dst.rate_tokens >= ip_rt_redirect_number) { - rt->dst.rate_last = jiffies; + if (peer->rate_tokens >= ip_rt_redirect_number) { + peer->rate_last = jiffies; return; } /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (rt->dst.rate_tokens == 0 || + if (peer->rate_tokens == 0 || time_after(jiffies, - (rt->dst.rate_last + - (ip_rt_redirect_load << rt->dst.rate_tokens)))) { + (peer->rate_last + + (ip_rt_redirect_load << peer->rate_tokens)))) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); - rt->dst.rate_last = jiffies; - ++rt->dst.rate_tokens; + peer->rate_last = jiffies; + ++peer->rate_tokens; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - rt->dst.rate_tokens == ip_rt_redirect_number && + peer->rate_tokens == ip_rt_redirect_number && net_ratelimit()) printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n", &rt->rt_src, rt->rt_iif, @@ -1574,7 +1448,9 @@ void ip_rt_send_redirect(struct sk_buff *skb) static int ip_error(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); + struct inet_peer *peer; unsigned long now; + bool send; int code; switch (rt->dst.error) { @@ -1594,15 +1470,24 @@ static int ip_error(struct sk_buff *skb) break; } - now = jiffies; - rt->dst.rate_tokens += now - rt->dst.rate_last; - if (rt->dst.rate_tokens > ip_rt_error_burst) - rt->dst.rate_tokens = ip_rt_error_burst; - rt->dst.rate_last = now; - if (rt->dst.rate_tokens >= ip_rt_error_cost) { - rt->dst.rate_tokens -= ip_rt_error_cost; - icmp_send(skb, ICMP_DEST_UNREACH, code, 0); + if (!rt->peer) + rt_bind_peer(rt, 1); + peer = rt->peer; + + send = true; + if (peer) { + now = jiffies; + peer->rate_tokens += now - peer->rate_last; + if (peer->rate_tokens > ip_rt_error_burst) + peer->rate_tokens = ip_rt_error_burst; + peer->rate_last = now; + if (peer->rate_tokens >= ip_rt_error_cost) + peer->rate_tokens -= ip_rt_error_cost; + else + send = false; } + if (send) + icmp_send(skb, ICMP_DEST_UNREACH, code, 0); out: kfree_skb(skb); return 0; @@ -1630,88 +1515,130 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev) { - int i, k; unsigned short old_mtu = ntohs(iph->tot_len); - struct rtable *rth; - int ikeys[2] = { dev->ifindex, 0 }; - __be32 skeys[2] = { iph->saddr, 0, }; - __be32 daddr = iph->daddr; unsigned short est_mtu = 0; + struct inet_peer *peer; - for (k = 0; k < 2; k++) { - for (i = 0; i < 2; i++) { - unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], - rt_genid(net)); - - rcu_read_lock(); - for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; - rth = rcu_dereference(rth->dst.rt_next)) { - unsigned short mtu = new_mtu; - - if (rth->fl.fl4_dst != daddr || - rth->fl.fl4_src != skeys[i] || - rth->rt_dst != daddr || - rth->rt_src != iph->saddr || - rth->fl.oif != ikeys[k] || - rt_is_input_route(rth) || - dst_metric_locked(&rth->dst, RTAX_MTU) || - !net_eq(dev_net(rth->dst.dev), net) || - rt_is_expired(rth)) - continue; - - if (new_mtu < 68 || new_mtu >= old_mtu) { + peer = inet_getpeer_v4(iph->daddr, 1); + if (peer) { + unsigned short mtu = new_mtu; - /* BSD 4.2 compatibility hack :-( */ - if (mtu == 0 && - old_mtu >= dst_mtu(&rth->dst) && - old_mtu >= 68 + (iph->ihl << 2)) - old_mtu -= iph->ihl << 2; + if (new_mtu < 68 || new_mtu >= old_mtu) { + /* BSD 4.2 derived systems incorrectly adjust + * tot_len by the IP header length, and report + * a zero MTU in the ICMP message. + */ + if (mtu == 0 && + old_mtu >= 68 + (iph->ihl << 2)) + old_mtu -= iph->ihl << 2; + mtu = guess_mtu(old_mtu); + } - mtu = guess_mtu(old_mtu); - } - if (mtu <= dst_mtu(&rth->dst)) { - if (mtu < dst_mtu(&rth->dst)) { - dst_confirm(&rth->dst); - if (mtu < ip_rt_min_pmtu) { - u32 lock = dst_metric(&rth->dst, - RTAX_LOCK); - mtu = ip_rt_min_pmtu; - lock |= (1 << RTAX_MTU); - dst_metric_set(&rth->dst, RTAX_LOCK, - lock); - } - dst_metric_set(&rth->dst, RTAX_MTU, mtu); - dst_set_expires(&rth->dst, - ip_rt_mtu_expires); - } - est_mtu = mtu; - } - } - rcu_read_unlock(); + if (mtu < ip_rt_min_pmtu) + mtu = ip_rt_min_pmtu; + if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { + est_mtu = mtu; + peer->pmtu_learned = mtu; + peer->pmtu_expires = jiffies + ip_rt_mtu_expires; } + + inet_putpeer(peer); + + atomic_inc(&__rt_peer_genid); } return est_mtu ? : new_mtu; } +static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) +{ + unsigned long expires = peer->pmtu_expires; + + if (time_before(expires, jiffies)) { + u32 orig_dst_mtu = dst_mtu(dst); + if (peer->pmtu_learned < orig_dst_mtu) { + if (!peer->pmtu_orig) + peer->pmtu_orig = dst_metric_raw(dst, RTAX_MTU); + dst_metric_set(dst, RTAX_MTU, peer->pmtu_learned); + } + } else if (cmpxchg(&peer->pmtu_expires, expires, 0) == expires) + dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig); +} + static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) { - if (dst_mtu(dst) > mtu && mtu >= 68 && - !(dst_metric_locked(dst, RTAX_MTU))) { - if (mtu < ip_rt_min_pmtu) { - u32 lock = dst_metric(dst, RTAX_LOCK); + struct rtable *rt = (struct rtable *) dst; + struct inet_peer *peer; + + dst_confirm(dst); + + if (!rt->peer) + rt_bind_peer(rt, 1); + peer = rt->peer; + if (peer) { + if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; - dst_metric_set(dst, RTAX_LOCK, lock | (1 << RTAX_MTU)); + if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { + peer->pmtu_learned = mtu; + peer->pmtu_expires = jiffies + ip_rt_mtu_expires; + + atomic_inc(&__rt_peer_genid); + rt->rt_peer_genid = rt_peer_genid(); + + check_peer_pmtu(dst, peer); } - dst_metric_set(dst, RTAX_MTU, mtu); - dst_set_expires(dst, ip_rt_mtu_expires); - call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); + inet_putpeer(peer); + } +} + +static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +{ + struct rtable *rt = (struct rtable *) dst; + __be32 orig_gw = rt->rt_gateway; + + dst_confirm(&rt->dst); + + neigh_release(rt->dst.neighbour); + rt->dst.neighbour = NULL; + + rt->rt_gateway = peer->redirect_learned.a4; + if (arp_bind_neighbour(&rt->dst) || + !(rt->dst.neighbour->nud_state & NUD_VALID)) { + if (rt->dst.neighbour) + neigh_event_send(rt->dst.neighbour, NULL); + rt->rt_gateway = orig_gw; + return -EAGAIN; + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, + rt->dst.neighbour); } + return 0; } static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { - if (rt_is_expired((struct rtable *)dst)) + struct rtable *rt = (struct rtable *) dst; + + if (rt_is_expired(rt)) return NULL; + if (rt->rt_peer_genid != rt_peer_genid()) { + struct inet_peer *peer; + + if (!rt->peer) + rt_bind_peer(rt, 0); + + peer = rt->peer; + if (peer && peer->pmtu_expires) + check_peer_pmtu(dst, peer); + + if (peer && peer->redirect_learned.a4 && + peer->redirect_learned.a4 != rt->rt_gateway) { + if (check_peer_redir(dst, peer)) + return NULL; + } + + rt->rt_peer_genid = rt_peer_genid(); + } return dst; } @@ -1720,6 +1647,10 @@ static void ipv4_dst_destroy(struct dst_entry *dst) struct rtable *rt = (struct rtable *) dst; struct inet_peer *peer = rt->peer; + if (rt->fi) { + fib_info_put(rt->fi); + rt->fi = NULL; + } if (peer) { rt->peer = NULL; inet_putpeer(peer); @@ -1734,8 +1665,14 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); rt = skb_rtable(skb); - if (rt) - dst_set_expires(&rt->dst, 0); + if (rt && + rt->peer && + rt->peer->pmtu_expires) { + unsigned long orig = rt->peer->pmtu_expires; + + if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) + dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); + } } static int ip_rt_bug(struct sk_buff *skb) @@ -1775,7 +1712,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) memcpy(addr, &src, 4); } -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) @@ -1815,17 +1752,52 @@ static unsigned int ipv4_default_mtu(const struct dst_entry *dst) return mtu; } -static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) +static void rt_init_metrics(struct rtable *rt, struct fib_info *fi) +{ + struct inet_peer *peer; + int create = 0; + + /* If a peer entry exists for this destination, we must hook + * it up in order to get at cached metrics. + */ + if (rt->fl.flags & FLOWI_FLAG_PRECOW_METRICS) + create = 1; + + rt_bind_peer(rt, create); + peer = rt->peer; + if (peer) { + if (inet_metrics_new(peer)) + memcpy(peer->metrics, fi->fib_metrics, + sizeof(u32) * RTAX_MAX); + dst_init_metrics(&rt->dst, peer->metrics, false); + + if (peer->pmtu_expires) + check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_learned.a4 && + peer->redirect_learned.a4 != rt->rt_gateway) { + rt->rt_gateway = peer->redirect_learned.a4; + rt->rt_flags |= RTCF_REDIRECTED; + } + } else { + if (fi->fib_metrics != (u32 *) dst_default_metrics) { + rt->fi = fi; + atomic_inc(&fi->fib_clntref); + } + dst_init_metrics(&rt->dst, fi->fib_metrics, true); + } +} + +static void rt_set_nexthop(struct rtable *rt, const struct fib_result *res, + struct fib_info *fi, u16 type, u32 itag) { struct dst_entry *dst = &rt->dst; - struct fib_info *fi = res->fi; if (fi) { if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = FIB_RES_GW(*res); - dst_import_metrics(dst, fi->fib_metrics); -#ifdef CONFIG_NET_CLS_ROUTE + rt_init_metrics(rt, fi); +#ifdef CONFIG_IP_ROUTE_CLASSID dst->tclassid = FIB_RES_NH(*res).nh_tclassid; #endif } @@ -1835,13 +1807,26 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40) dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, fib_rules_tclass(res)); #endif set_class_tag(rt, itag); #endif - rt->rt_type = res->type; + rt->rt_type = type; +} + +static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm) +{ + struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1); + if (rt) { + rt->dst.obsolete = -1; + + rt->dst.flags = DST_HOST | + (nopolicy ? DST_NOPOLICY : 0) | + (noxfrm ? DST_NOXFRM : 0); + } + return rt; } /* called in rcu_read_lock() section */ @@ -1874,24 +1859,19 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err < 0) goto e_err; } - rth = dst_alloc(&ipv4_dst_ops); + rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs; rth->dst.output = ip_rt_bug; - rth->dst.obsolete = -1; - atomic_set(&rth->dst.__refcnt, 1); - rth->dst.flags= DST_HOST; - if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->dst.flags |= DST_NOPOLICY; rth->fl.fl4_dst = daddr; rth->rt_dst = daddr; rth->fl.fl4_tos = tos; rth->fl.mark = skb->mark; rth->fl.fl4_src = saddr; rth->rt_src = saddr; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_iif = @@ -1959,7 +1939,7 @@ static void ip_handle_martian_source(struct net_device *dev, /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, - struct fib_result *res, + const struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos, struct rtable **result) @@ -2013,19 +1993,13 @@ static int __mkroute_input(struct sk_buff *skb, } } - - rth = dst_alloc(&ipv4_dst_ops); + rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), + IN_DEV_CONF_GET(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; goto cleanup; } - atomic_set(&rth->dst.__refcnt, 1); - rth->dst.flags= DST_HOST; - if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->dst.flags |= DST_NOPOLICY; - if (IN_DEV_CONF_GET(out_dev, NOXFRM)) - rth->dst.flags |= DST_NOXFRM; rth->fl.fl4_dst = daddr; rth->rt_dst = daddr; rth->fl.fl4_tos = tos; @@ -2040,12 +2014,11 @@ static int __mkroute_input(struct sk_buff *skb, rth->fl.oif = 0; rth->rt_spec_dst= spec_dst; - rth->dst.obsolete = -1; rth->dst.input = ip_forward; rth->dst.output = ip_output; rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); - rt_set_nexthop(rth, res, itag); + rt_set_nexthop(rth, res, res->fi, res->type, itag); rth->rt_flags = flags; @@ -2190,25 +2163,20 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: - rth = dst_alloc(&ipv4_dst_ops); + rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs; rth->dst.output= ip_rt_bug; - rth->dst.obsolete = -1; rth->rt_genid = rt_genid(net); - atomic_set(&rth->dst.__refcnt, 1); - rth->dst.flags= DST_HOST; - if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->dst.flags |= DST_NOPOLICY; rth->fl.fl4_dst = daddr; rth->rt_dst = daddr; rth->fl.fl4_tos = tos; rth->fl.mark = skb->mark; rth->fl.fl4_src = saddr; rth->rt_src = saddr; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_iif = @@ -2351,38 +2319,39 @@ skip_cache: EXPORT_SYMBOL(ip_route_input_common); /* called with rcu_read_lock() */ -static int __mkroute_output(struct rtable **result, - struct fib_result *res, - const struct flowi *fl, - const struct flowi *oldflp, - struct net_device *dev_out, - unsigned flags) +static struct rtable *__mkroute_output(const struct fib_result *res, + const struct flowi *fl, + const struct flowi *oldflp, + struct net_device *dev_out, + unsigned int flags) { - struct rtable *rth; - struct in_device *in_dev; + struct fib_info *fi = res->fi; u32 tos = RT_FL_TOS(oldflp); + struct in_device *in_dev; + u16 type = res->type; + struct rtable *rth; if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags & IFF_LOOPBACK)) - return -EINVAL; + return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl->fl4_dst)) - res->type = RTN_BROADCAST; + type = RTN_BROADCAST; else if (ipv4_is_multicast(fl->fl4_dst)) - res->type = RTN_MULTICAST; + type = RTN_MULTICAST; else if (ipv4_is_zeronet(fl->fl4_dst)) - return -EINVAL; + return ERR_PTR(-EINVAL); if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) - return -EINVAL; + return ERR_PTR(-EINVAL); - if (res->type == RTN_BROADCAST) { + if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; - res->fi = NULL; - } else if (res->type == RTN_MULTICAST) { + fi = NULL; + } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src, oldflp->proto)) @@ -2391,21 +2360,14 @@ static int __mkroute_output(struct rtable **result, * default one, but do not gateway in this case. * Yes, it is hack. */ - if (res->fi && res->prefixlen < 4) - res->fi = NULL; + if (fi && res->prefixlen < 4) + fi = NULL; } - - rth = dst_alloc(&ipv4_dst_ops); + rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), + IN_DEV_CONF_GET(in_dev, NOXFRM)); if (!rth) - return -ENOBUFS; - - atomic_set(&rth->dst.__refcnt, 1); - rth->dst.flags= DST_HOST; - if (IN_DEV_CONF_GET(in_dev, NOXFRM)) - rth->dst.flags |= DST_NOXFRM; - if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->dst.flags |= DST_NOPOLICY; + return ERR_PTR(-ENOBUFS); rth->fl.fl4_dst = oldflp->fl4_dst; rth->fl.fl4_tos = tos; @@ -2423,7 +2385,6 @@ static int __mkroute_output(struct rtable **result, rth->rt_spec_dst= fl->fl4_src; rth->dst.output=ip_output; - rth->dst.obsolete = -1; rth->rt_genid = rt_genid(dev_net(dev_out)); RT_CACHE_STAT_INC(out_slow_tot); @@ -2440,7 +2401,7 @@ static int __mkroute_output(struct rtable **result, RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE - if (res->type == RTN_MULTICAST) { + if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(oldflp->fl4_dst)) { rth->dst.input = ip_mr_input; @@ -2450,31 +2411,10 @@ static int __mkroute_output(struct rtable **result, #endif } - rt_set_nexthop(rth, res, 0); + rt_set_nexthop(rth, res, fi, type, 0); rth->rt_flags = flags; - *result = rth; - return 0; -} - -/* called with rcu_read_lock() */ -static int ip_mkroute_output(struct rtable **rp, - struct fib_result *res, - const struct flowi *fl, - const struct flowi *oldflp, - struct net_device *dev_out, - unsigned flags) -{ - struct rtable *rth = NULL; - int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags); - unsigned hash; - if (err == 0) { - hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, - rt_genid(dev_net(dev_out))); - err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif); - } - - return err; + return rth; } /* @@ -2497,6 +2437,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, struct fib_result res; unsigned int flags = 0; struct net_device *dev_out = NULL; + struct rtable *rth; int err; @@ -2505,6 +2446,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, res.r = NULL; #endif + rcu_read_lock(); if (oldflp->fl4_src) { err = -EINVAL; if (ipv4_is_multicast(oldflp->fl4_src) || @@ -2645,7 +2587,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, else #endif if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif) - fib_select_default(net, &fl, &res); + fib_select_default(&res); if (!fl.fl4_src) fl.fl4_src = FIB_RES_PREFSRC(res); @@ -2655,17 +2597,27 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, make_route: - err = ip_mkroute_output(rp, &res, &fl, oldflp, dev_out, flags); + rth = __mkroute_output(&res, &fl, oldflp, dev_out, flags); + if (IS_ERR(rth)) + err = PTR_ERR(rth); + else { + unsigned int hash; -out: return err; + hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, + rt_genid(dev_net(dev_out))); + err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif); + } + +out: + rcu_read_unlock(); + return err; } int __ip_route_output_key(struct net *net, struct rtable **rp, const struct flowi *flp) { - unsigned int hash; - int res; struct rtable *rth; + unsigned int hash; if (!rt_caching(net)) goto slow_output; @@ -2695,10 +2647,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rcu_read_unlock_bh(); slow_output: - rcu_read_lock(); - res = ip_route_output_slow(net, rp, flp); - rcu_read_unlock(); - return res; + return ip_route_output_slow(net, rp, flp); } EXPORT_SYMBOL_GPL(__ip_route_output_key); @@ -2731,12 +2680,11 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi { struct rtable *ort = *rp; struct rtable *rt = (struct rtable *) - dst_alloc(&ipv4_dst_blackhole_ops); + dst_alloc(&ipv4_dst_blackhole_ops, 1); if (rt) { struct dst_entry *new = &rt->dst; - atomic_set(&new->__refcnt, 1); new->__use = 1; new->input = dst_discard; new->output = dst_discard; @@ -2759,6 +2707,9 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi rt->peer = ort->peer; if (rt->peer) atomic_inc(&rt->peer->refcnt); + rt->fi = ort->fi; + if (rt->fi) + atomic_inc(&rt->fi->fib_clntref); dst_free(new); } @@ -2835,7 +2786,7 @@ static int rt_fill_info(struct net *net, } if (rt->dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid) NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); #endif @@ -2854,7 +2805,8 @@ static int rt_fill_info(struct net *net, NLA_PUT_BE32(skb, RTA_MARK, rt->fl.mark); error = rt->dst.error; - expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; + expires = (rt->peer && rt->peer->pmtu_expires) ? + rt->peer->pmtu_expires - jiffies : 0; if (rt->peer) { inet_peer_refcheck(rt->peer); id = atomic_read(&rt->peer->ip_id_count) & 0xffff; @@ -3256,9 +3208,9 @@ static __net_initdata struct pernet_operations rt_genid_ops = { }; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; -#endif /* CONFIG_NET_CLS_ROUTE */ +#endif /* CONFIG_IP_ROUTE_CLASSID */ static __initdata unsigned long rhash_entries; static int __init set_rhash_entries(char *str) @@ -3274,7 +3226,7 @@ int __init ip_rt_init(void) { int rc = 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); @@ -3311,14 +3263,6 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); - /* All the timers, started at system startup tend - to synchronize. Perturb it a bit. - */ - INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); - expires_ljiffies = jiffies; - schedule_delayed_work(&expires_work, - net_random() % ip_rt_gc_interval + ip_rt_gc_interval); - if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6c11eec..f9867d2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2653,7 +2653,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_getsockopt); #endif -struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) +struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb7f82e..2f692ce 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -817,7 +817,7 @@ __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst) __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); if (!cwnd) - cwnd = rfc3390_bytes_to_packets(tp->mss_cache); + cwnd = TCP_INIT_CWND; return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 02f583b..e2b9be2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1341,7 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_death_row.sysctl_tw_recycle && (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && - peer->daddr.a4 == saddr) { + peer->daddr.addr.a4 == saddr) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8157b17..d37baaa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2199,7 +2199,7 @@ int udp4_ufo_send_check(struct sk_buff *skb) return 0; } -struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features) +struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index b057d40..19fbdec 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -196,8 +196,11 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + dst_destroy_metrics_generic(dst); + if (likely(xdst->u.rt.peer)) inet_putpeer(xdst->u.rt.peer); + xfrm_dst_destroy(xdst); } @@ -215,6 +218,7 @@ static struct dst_ops xfrm4_dst_ops = { .protocol = cpu_to_be16(ETH_P_IP), .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, + .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 978e80e..3194aa9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -772,7 +772,7 @@ out: return err; } -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 03e62f9..a31d91b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -157,20 +157,20 @@ static int is_ineligible(struct sk_buff *skb) /* * Check the ICMP output rate limit */ -static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, - struct flowi *fl) +static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, + struct flowi *fl) { struct dst_entry *dst; struct net *net = sock_net(sk); - int res = 0; + bool res = false; /* Informational messages are not limited. */ if (type & ICMPV6_INFOMSG_MASK) - return 1; + return true; /* Do not limit pmtu discovery, it would break it. */ if (type == ICMPV6_PKT_TOOBIG) - return 1; + return true; /* * Look up the output route. @@ -182,7 +182,7 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { - res = 1; + res = true; } else { struct rt6_info *rt = (struct rt6_info *)dst; int tmo = net->ipv6.sysctl.icmpv6_time; @@ -191,7 +191,9 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - res = xrlim_allow(dst, tmo); + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo); } dst_release(dst); return res; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5f8d242..2600e22 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -479,10 +479,13 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (xrlim_allow(dst, 1*HZ)) + if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) ndisc_send_redirect(skb, n, target); } else { int addrtype = ipv6_addr_type(&hdr->saddr); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2342545..7254ce3 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1553,7 +1553,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, "ICMPv6 Redirect: destination is not a neighbour.\n"); goto release; } - if (!xrlim_allow(dst, 1*HZ)) + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7d227c6..47b7b8d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1076,6 +1076,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET6, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1679,6 +1680,7 @@ translate_compat_table(struct net *net, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET6); + xt_compat_init_offsets(AF_INET6, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index de33803..e6af8d7 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -452,8 +452,7 @@ ip6t_log_packet(u_int8_t pf, in ? in->name : "", out ? out->name : ""); - /* MAC logging for input path only. */ - if (in && !out) + if (in != NULL) dump_mac_header(m, loginfo, skb); dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 79d43aa..0857272 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -45,6 +45,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/kernel.h> #include <linux/module.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> struct nf_ct_frag6_skb_cb @@ -73,7 +74,7 @@ static struct inet_frags nf_frags; static struct netns_frags nf_init_frags; #ifdef CONFIG_SYSCTL -struct ctl_table nf_ct_frag6_sysctl_table[] = { +static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .data = &nf_init_frags.timeout, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c5b0915..364e866 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -124,18 +124,18 @@ static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) -static int (*mh_filter)(struct sock *sock, struct sk_buff *skb); +typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); -int rawv6_mh_filter_register(int (*filter)(struct sock *sock, - struct sk_buff *skb)) +static mh_filter_t __rcu *mh_filter __read_mostly; + +int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); -int rawv6_mh_filter_unregister(int (*filter)(struct sock *sock, - struct sk_buff *skb)) +int rawv6_mh_filter_unregister(mh_filter_t filter) { rcu_assign_pointer(mh_filter, NULL); synchronize_rcu(); @@ -193,10 +193,10 @@ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) * policy is placed in rawv6_rcv() because it is * required for each socket. */ - int (*filter)(struct sock *sock, struct sk_buff *skb); + mh_filter_t *filter; filter = rcu_dereference(mh_filter); - filtered = filter ? filter(sk, skb) : 0; + filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a998db6..f786aed 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -97,6 +97,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net, struct in6_addr *gwaddr, int ifindex); #endif +static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + struct rt6_info *rt = (struct rt6_info *) dst; + struct inet_peer *peer; + u32 *p = NULL; + + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + + peer = rt->rt6i_peer; + if (peer) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + p = peer->metrics; + if (inet_metrics_new(peer)) + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} + static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -105,6 +135,7 @@ static struct dst_ops ip6_dst_ops_template = { .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .default_mtu = ip6_default_mtu, + .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, @@ -132,6 +163,10 @@ static struct dst_ops ip6_dst_blackhole_ops = { .update_pmtu = ip6_rt_blackhole_update_pmtu, }; +static const u32 ip6_template_metrics[RTAX_MAX] = { + [RTAX_HOPLIMIT - 1] = 255, +}; + static struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -187,7 +222,7 @@ static struct rt6_info ip6_blk_hole_entry_template = { /* allocate dst with ip6_dst_ops */ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops) { - return (struct rt6_info *)dst_alloc(ops); + return (struct rt6_info *)dst_alloc(ops, 0); } static void ip6_dst_destroy(struct dst_entry *dst) @@ -206,6 +241,13 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } +static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); + +static u32 rt6_peer_genid(void) +{ + return atomic_read(&__rt6_peer_genid); +} + void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer *peer; @@ -213,6 +255,8 @@ void rt6_bind_peer(struct rt6_info *rt, int create) peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) inet_putpeer(peer); + else + rt->rt6i_peer_genid = rt6_peer_genid(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -830,13 +874,12 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl { struct rt6_info *ort = (struct rt6_info *) *dstp; struct rt6_info *rt = (struct rt6_info *) - dst_alloc(&ip6_dst_blackhole_ops); + dst_alloc(&ip6_dst_blackhole_ops, 1); struct dst_entry *new = NULL; if (rt) { new = &rt->dst; - atomic_set(&new->__refcnt, 1); new->__use = 1; new->input = dst_discard; new->output = dst_discard; @@ -878,9 +921,14 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { + if (rt->rt6i_peer_genid != rt6_peer_genid()) { + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 0); + rt->rt6i_peer_genid = rt6_peer_genid(); + } return dst; - + } return NULL; } @@ -931,7 +979,6 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst_metric_set(dst, RTAX_FEATURES, features); } dst_metric_set(dst, RTAX_MTU, mtu); - call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } @@ -2684,7 +2731,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_null_entry->dst, + ip6_template_metrics, true); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2695,7 +2743,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_prohibit_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, + ip6_template_metrics, true); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2705,7 +2754,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_blk_hole_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, + ip6_template_metrics, true); #endif net->ipv6.sysctl.flush_delay = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 8ce38f1..b1599a3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -412,7 +412,7 @@ static void prl_list_destroy_rcu(struct rcu_head *head) p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { - n = p->next; + n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); @@ -421,15 +421,17 @@ static void prl_list_destroy_rcu(struct rcu_head *head) static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { - struct ip_tunnel_prl_entry *x, **p; + struct ip_tunnel_prl_entry *x; + struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { - for (p = &t->prl; *p; p = &(*p)->next) { - if ((*p)->addr == a->addr) { - x = *p; + for (p = &t->prl; + (x = rtnl_dereference(*p)) != NULL; + p = &x->next) { + if (x->addr == a->addr) { *p = x->next; call_rcu(&x->rcu_head, prl_entry_destroy_rcu); t->prl_count--; @@ -438,9 +440,9 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) } err = -ENXIO; } else { - if (t->prl) { + x = rtnl_dereference(t->prl); + if (x) { t->prl_count = 0; - x = t->prl; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } @@ -1179,7 +1181,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; dev_hold(dev); - sitn->tunnels_wc[0] = tunnel; + rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; } @@ -1196,11 +1198,12 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = sitn->tunnels[prio][h]; + struct ip_tunnel *t; + t = rtnl_dereference(sitn->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 20aa95e..d6954e3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1323,7 +1323,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_death_row.sysctl_tw_recycle && (dst = inet6_csk_route_req(sk, req)) != NULL && (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL && - ipv6_addr_equal((struct in6_addr *)peer->daddr.a6, + ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6, &treq->rmt_addr)) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9a009c6..a419a78 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1299,7 +1299,7 @@ static int udp6_ufo_send_check(struct sk_buff *skb) return 0; } -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features) +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index da87428..834dc02 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -220,6 +220,7 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); + dst_destroy_metrics_generic(dst); if (likely(xdst->u.rt6.rt6i_peer)) inet_putpeer(xdst->u.rt6.rt6i_peer); xfrm_dst_destroy(xdst); @@ -257,6 +258,7 @@ static struct dst_ops xfrm6_dst_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 227ca82..0c9d0c0 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -76,7 +76,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, #endif /* CONFIG_MAC80211_HT_DEBUG */ if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP, - &sta->sta, tid, NULL)) + &sta->sta, tid, NULL, 0)) printk(KERN_DEBUG "HW problem - can not stop rx " "aggregation for tid %d\n", tid); @@ -232,6 +232,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, if (buf_size == 0) buf_size = IEEE80211_MAX_AMPDU_BUF; + /* make sure the size doesn't exceed the maximum supported by the hw */ + if (buf_size > local->hw.max_rx_aggregation_subframes) + buf_size = local->hw.max_rx_aggregation_subframes; /* examine state machine */ mutex_lock(&sta->ampdu_mlme.mtx); @@ -287,7 +290,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, } ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num); + &sta->sta, tid, &start_seq_num, 0); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "Rx A-MPDU request on tid %d result %d\n", tid, ret); #endif /* CONFIG_MAC80211_HT_DEBUG */ diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 9cc472c..63d852c 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -190,7 +190,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_STOP, - &sta->sta, tid, NULL); + &sta->sta, tid, NULL, 0); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { @@ -311,7 +311,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) start_seq_num = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START, - &sta->sta, tid, &start_seq_num); + &sta->sta, tid, &start_seq_num, 0); if (ret) { #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "BA request denied - HW unavailable for" @@ -342,7 +342,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, tid_tx->dialog_token, start_seq_num, - 0x40, tid_tx->timeout); + local->hw.max_tx_aggregation_subframes, + tid_tx->timeout); } int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, @@ -487,7 +488,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_OPERATIONAL, - &sta->sta, tid, NULL); + &sta->sta, tid, NULL, + sta->ampdu_mlme.tid_tx[tid]->buf_size); /* * synchronize with TX path, while splicing the TX path @@ -742,9 +744,11 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, { struct tid_ampdu_tx *tid_tx; u16 capab, tid; + u8 buf_size; capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; + buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; mutex_lock(&sta->ampdu_mlme.mtx); @@ -767,12 +771,23 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, if (le16_to_cpu(mgmt->u.action.u.addba_resp.status) == WLAN_STATUS_SUCCESS) { + /* + * IEEE 802.11-2007 7.3.1.14: + * In an ADDBA Response frame, when the Status Code field + * is set to 0, the Buffer Size subfield is set to a value + * of at least 1. + */ + if (!buf_size) + goto out; + if (test_and_set_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { /* ignore duplicate response */ goto out; } + tid_tx->buf_size = buf_size; + if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 9cd73b1..2ba3af8 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1215,6 +1215,9 @@ static int ieee80211_set_channel(struct wiphy *wiphy, { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = NULL; + struct ieee80211_channel *old_oper; + enum nl80211_channel_type old_oper_type; + enum nl80211_channel_type old_vif_oper_type= NL80211_CHAN_NO_HT; if (netdev) sdata = IEEE80211_DEV_TO_SUB_IF(netdev); @@ -1232,13 +1235,23 @@ static int ieee80211_set_channel(struct wiphy *wiphy, break; } - local->oper_channel = chan; + if (sdata) + old_vif_oper_type = sdata->vif.bss_conf.channel_type; + old_oper_type = local->_oper_channel_type; if (!ieee80211_set_channel_type(local, sdata, channel_type)) return -EBUSY; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - if (sdata && sdata->vif.type != NL80211_IFTYPE_MONITOR) + old_oper = local->oper_channel; + local->oper_channel = chan; + + /* Update driver if changes were actually made. */ + if ((old_oper != local->oper_channel) || + (old_oper_type != local->_oper_channel_type)) + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + + if ((sdata && sdata->vif.type != NL80211_IFTYPE_MONITOR) && + old_vif_oper_type != sdata->vif.bss_conf.channel_type) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); return 0; @@ -1274,8 +1287,11 @@ static int ieee80211_scan(struct wiphy *wiphy, case NL80211_IFTYPE_P2P_GO: if (sdata->local->ops->hw_scan) break; - /* FIXME: implement NoA while scanning in software */ - return -EOPNOTSUPP; + /* + * FIXME: implement NoA while scanning in software, + * for now fall through to allow scanning only when + * beaconing hasn't been configured yet + */ case NL80211_IFTYPE_AP: if (sdata->u.ap.beacon) return -EOPNOTSUPP; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 2dabdf7..dacace6 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -36,7 +36,7 @@ static ssize_t ieee80211_if_read( ret = (*format)(sdata, buf, sizeof(buf)); read_unlock(&dev_base_lock); - if (ret != -EINVAL) + if (ret >= 0) ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret); return ret; @@ -81,6 +81,8 @@ static ssize_t ieee80211_if_fmt_##name( \ IEEE80211_IF_FMT(name, field, "%d\n") #define IEEE80211_IF_FMT_HEX(name, field) \ IEEE80211_IF_FMT(name, field, "%#x\n") +#define IEEE80211_IF_FMT_LHEX(name, field) \ + IEEE80211_IF_FMT(name, field, "%#lx\n") #define IEEE80211_IF_FMT_SIZE(name, field) \ IEEE80211_IF_FMT(name, field, "%zd\n") @@ -145,6 +147,9 @@ IEEE80211_IF_FILE(rc_rateidx_mask_2ghz, rc_rateidx_mask[IEEE80211_BAND_2GHZ], HEX); IEEE80211_IF_FILE(rc_rateidx_mask_5ghz, rc_rateidx_mask[IEEE80211_BAND_5GHZ], HEX); +IEEE80211_IF_FILE(flags, flags, HEX); +IEEE80211_IF_FILE(state, state, LHEX); +IEEE80211_IF_FILE(channel_type, vif.bss_conf.channel_type, DEC); /* STA attributes */ IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC); @@ -216,6 +221,104 @@ static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata, __IEEE80211_IF_FILE_W(smps); +static ssize_t ieee80211_if_fmt_tkip_mic_test( + const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) +{ + return -EOPNOTSUPP; +} + +static int hwaddr_aton(const char *txt, u8 *addr) +{ + int i; + + for (i = 0; i < ETH_ALEN; i++) { + int a, b; + + a = hex_to_bin(*txt++); + if (a < 0) + return -1; + b = hex_to_bin(*txt++); + if (b < 0) + return -1; + *addr++ = (a << 4) | b; + if (i < 5 && *txt++ != ':') + return -1; + } + + return 0; +} + +static ssize_t ieee80211_if_parse_tkip_mic_test( + struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) +{ + struct ieee80211_local *local = sdata->local; + u8 addr[ETH_ALEN]; + struct sk_buff *skb; + struct ieee80211_hdr *hdr; + __le16 fc; + + /* + * Assume colon-delimited MAC address with possible white space + * following. + */ + if (buflen < 3 * ETH_ALEN - 1) + return -EINVAL; + if (hwaddr_aton(buf, addr) < 0) + return -EINVAL; + + if (!ieee80211_sdata_running(sdata)) + return -ENOTCONN; + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24 + 100); + if (!skb) + return -ENOMEM; + skb_reserve(skb, local->hw.extra_tx_headroom); + + hdr = (struct ieee80211_hdr *) skb_put(skb, 24); + memset(hdr, 0, 24); + fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP: + fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); + /* DA BSSID SA */ + memcpy(hdr->addr1, addr, ETH_ALEN); + memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); + memcpy(hdr->addr3, sdata->vif.addr, ETH_ALEN); + break; + case NL80211_IFTYPE_STATION: + fc |= cpu_to_le16(IEEE80211_FCTL_TODS); + /* BSSID SA DA */ + if (sdata->vif.bss_conf.bssid == NULL) { + dev_kfree_skb(skb); + return -ENOTCONN; + } + memcpy(hdr->addr1, sdata->vif.bss_conf.bssid, ETH_ALEN); + memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); + memcpy(hdr->addr3, addr, ETH_ALEN); + break; + default: + dev_kfree_skb(skb); + return -EOPNOTSUPP; + } + hdr->frame_control = fc; + + /* + * Add some length to the test frame to make it look bit more valid. + * The exact contents does not matter since the recipient is required + * to drop this because of the Michael MIC failure. + */ + memset(skb_put(skb, 50), 0, 50); + + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_TKIP_MIC_FAILURE; + + ieee80211_tx_skb(sdata, skb); + + return buflen; +} + +__IEEE80211_IF_FILE_W(tkip_mic_test); + /* AP attributes */ IEEE80211_IF_FILE(num_sta_ps, u.ap.num_sta_ps, ATOMIC); IEEE80211_IF_FILE(dtim_count, u.ap.dtim_count, DEC); @@ -283,6 +386,9 @@ IEEE80211_IF_FILE(dot11MeshHWMPRootMode, static void add_sta_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(drop_unencrypted); + DEBUGFS_ADD(flags); + DEBUGFS_ADD(state); + DEBUGFS_ADD(channel_type); DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); @@ -291,22 +397,30 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(last_beacon); DEBUGFS_ADD(ave_beacon); DEBUGFS_ADD_MODE(smps, 0600); + DEBUGFS_ADD_MODE(tkip_mic_test, 0200); } static void add_ap_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(drop_unencrypted); + DEBUGFS_ADD(flags); + DEBUGFS_ADD(state); + DEBUGFS_ADD(channel_type); DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(num_sta_ps); DEBUGFS_ADD(dtim_count); DEBUGFS_ADD(num_buffered_multicast); + DEBUGFS_ADD_MODE(tkip_mic_test, 0200); } static void add_wds_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(drop_unencrypted); + DEBUGFS_ADD(flags); + DEBUGFS_ADD(state); + DEBUGFS_ADD(channel_type); DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); @@ -316,12 +430,18 @@ static void add_wds_files(struct ieee80211_sub_if_data *sdata) static void add_vlan_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(drop_unencrypted); + DEBUGFS_ADD(flags); + DEBUGFS_ADD(state); + DEBUGFS_ADD(channel_type); DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); } static void add_monitor_files(struct ieee80211_sub_if_data *sdata) { + DEBUGFS_ADD(flags); + DEBUGFS_ADD(state); + DEBUGFS_ADD(channel_type); } #ifdef CONFIG_MAC80211_MESH diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 98d5899..78af32d 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -382,17 +382,17 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn) + u16 *ssn, u8 buf_size) { int ret = -EOPNOTSUPP; might_sleep(); - trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn); + trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size); if (local->ops->ampdu_action) ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action, - sta, tid, ssn); + sta, tid, ssn, buf_size); trace_drv_return_int(local, ret); diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 49c8421..e5cce19 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -9,6 +9,11 @@ #undef TRACE_EVENT #define TRACE_EVENT(name, proto, ...) \ static inline void trace_ ## name(proto) {} +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(...) +#undef DEFINE_EVENT +#define DEFINE_EVENT(evt_class, name, proto, ...) \ +static inline void trace_ ## name(proto) {} #endif #undef TRACE_SYSTEM @@ -38,7 +43,7 @@ static inline void trace_ ## name(proto) {} * Tracing for driver callbacks. */ -TRACE_EVENT(drv_return_void, +DECLARE_EVENT_CLASS(local_only_evt, TP_PROTO(struct ieee80211_local *local), TP_ARGS(local), TP_STRUCT__entry( @@ -50,6 +55,11 @@ TRACE_EVENT(drv_return_void, TP_printk(LOCAL_PR_FMT, LOCAL_PR_ARG) ); +DEFINE_EVENT(local_only_evt, drv_return_void, + TP_PROTO(struct ieee80211_local *local), + TP_ARGS(local) +); + TRACE_EVENT(drv_return_int, TP_PROTO(struct ieee80211_local *local, int ret), TP_ARGS(local, ret), @@ -78,40 +88,14 @@ TRACE_EVENT(drv_return_u64, TP_printk(LOCAL_PR_FMT " - %llu", LOCAL_PR_ARG, __entry->ret) ); -TRACE_EVENT(drv_start, +DEFINE_EVENT(local_only_evt, drv_start, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(drv_stop, +DEFINE_EVENT(local_only_evt, drv_stop, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_add_interface, @@ -439,40 +423,14 @@ TRACE_EVENT(drv_hw_scan, ) ); -TRACE_EVENT(drv_sw_scan_start, +DEFINE_EVENT(local_only_evt, drv_sw_scan_start, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(drv_sw_scan_complete, +DEFINE_EVENT(local_only_evt, drv_sw_scan_complete, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_get_stats, @@ -702,23 +660,9 @@ TRACE_EVENT(drv_conf_tx, ) ); -TRACE_EVENT(drv_get_tsf, +DEFINE_EVENT(local_only_evt, drv_get_tsf, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, - LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_set_tsf, @@ -742,41 +686,14 @@ TRACE_EVENT(drv_set_tsf, ) ); -TRACE_EVENT(drv_reset_tsf, +DEFINE_EVENT(local_only_evt, drv_reset_tsf, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(drv_tx_last_beacon, +DEFINE_EVENT(local_only_evt, drv_tx_last_beacon, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, - LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_ampdu_action, @@ -784,9 +701,9 @@ TRACE_EVENT(drv_ampdu_action, struct ieee80211_sub_if_data *sdata, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn), + u16 *ssn, u8 buf_size), - TP_ARGS(local, sdata, action, sta, tid, ssn), + TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size), TP_STRUCT__entry( LOCAL_ENTRY @@ -794,6 +711,7 @@ TRACE_EVENT(drv_ampdu_action, __field(u32, action) __field(u16, tid) __field(u16, ssn) + __field(u8, buf_size) VIF_ENTRY ), @@ -804,11 +722,13 @@ TRACE_EVENT(drv_ampdu_action, __entry->action = action; __entry->tid = tid; __entry->ssn = ssn ? *ssn : 0; + __entry->buf_size = buf_size; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d", - LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, __entry->tid + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, + __entry->tid, __entry->buf_size ) ); @@ -959,22 +879,9 @@ TRACE_EVENT(drv_remain_on_channel, ) ); -TRACE_EVENT(drv_cancel_remain_on_channel, +DEFINE_EVENT(local_only_evt, drv_cancel_remain_on_channel, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); /* @@ -1069,23 +976,9 @@ TRACE_EVENT(api_stop_tx_ba_cb, ) ); -TRACE_EVENT(api_restart_hw, +DEFINE_EVENT(local_only_evt, api_restart_hw, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, - LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(api_beacon_loss, @@ -1214,40 +1107,14 @@ TRACE_EVENT(api_chswitch_done, ) ); -TRACE_EVENT(api_ready_on_channel, +DEFINE_EVENT(local_only_evt, api_ready_on_channel, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(api_remain_on_channel_expired, +DEFINE_EVENT(local_only_evt, api_remain_on_channel_expired, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); /* diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 53c7077..775fb63 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -270,7 +270,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band = rx_status->band; if (elems->ds_params && elems->ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems->ds_params[0]); + freq = ieee80211_channel_to_frequency(elems->ds_params[0], + band); else freq = rx_status->freq; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 533fd32..f2ef15d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -225,6 +225,7 @@ struct ieee80211_if_ap { struct sk_buff_head ps_bc_buf; atomic_t num_sta_ps; /* number of stations in PS mode */ int dtim_count; + bool dtim_bc_mc; }; struct ieee80211_if_wds { @@ -654,8 +655,6 @@ struct tpt_led_trigger { * well be on the operating channel * @SCAN_HW_SCANNING: The hardware is scanning for us, we have no way to * determine if we are on the operating channel or not - * @SCAN_OFF_CHANNEL: We're off our operating channel for scanning, - * gets only set in conjunction with SCAN_SW_SCANNING * @SCAN_COMPLETED: Set for our scan work function when the driver reported * that the scan completed. * @SCAN_ABORTED: Set for our scan work function when the driver reported @@ -664,7 +663,6 @@ struct tpt_led_trigger { enum { SCAN_SW_SCANNING, SCAN_HW_SCANNING, - SCAN_OFF_CHANNEL, SCAN_COMPLETED, SCAN_ABORTED, }; @@ -1147,10 +1145,14 @@ void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss); /* off-channel helpers */ -void ieee80211_offchannel_stop_beaconing(struct ieee80211_local *local); -void ieee80211_offchannel_stop_station(struct ieee80211_local *local); +bool ieee80211_cfg_on_oper_channel(struct ieee80211_local *local); +void ieee80211_offchannel_enable_all_ps(struct ieee80211_local *local, + bool tell_ap); +void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, + bool offchannel_ps_enable); void ieee80211_offchannel_return(struct ieee80211_local *local, - bool enable_beaconing); + bool enable_beaconing, + bool offchannel_ps_disable); void ieee80211_hw_roc_setup(struct ieee80211_local *local); /* interface handling */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8acba45..5a4e19b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -382,6 +382,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; int i; + enum nl80211_channel_type orig_ct; if (local->scan_sdata == sdata) ieee80211_scan_cancel(local); @@ -542,8 +543,14 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, hw_reconf_flags = 0; } + /* Re-calculate channel-type, in case there are multiple vifs + * on different channel types. + */ + orig_ct = local->_oper_channel_type; + ieee80211_set_channel_type(local, NULL, NL80211_CHAN_NO_HT); + /* do after stop to avoid reconfiguring when we stop anyway */ - if (hw_reconf_flags) + if (hw_reconf_flags || (orig_ct != local->_oper_channel_type)) ieee80211_hw_config(local, hw_reconf_flags); spin_lock_irqsave(&local->queue_stop_reason_lock, flags); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index a46ff06..c155c0b 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -98,6 +98,41 @@ static void ieee80211_reconfig_filter(struct work_struct *work) ieee80211_configure_filter(local); } +/* + * Returns true if we are logically configured to be on + * the operating channel AND the hardware-conf is currently + * configured on the operating channel. Compares channel-type + * as well. + */ +bool ieee80211_cfg_on_oper_channel(struct ieee80211_local *local) +{ + struct ieee80211_channel *chan, *scan_chan; + enum nl80211_channel_type channel_type; + + /* This logic needs to match logic in ieee80211_hw_config */ + if (local->scan_channel) { + chan = local->scan_channel; + channel_type = NL80211_CHAN_NO_HT; + } else if (local->tmp_channel) { + chan = scan_chan = local->tmp_channel; + channel_type = local->tmp_channel_type; + } else { + chan = local->oper_channel; + channel_type = local->_oper_channel_type; + } + + if (chan != local->oper_channel || + channel_type != local->_oper_channel_type) + return false; + + /* Check current hardware-config against oper_channel. */ + if ((local->oper_channel != local->hw.conf.channel) || + (local->_oper_channel_type != local->hw.conf.channel_type)) + return false; + + return true; +} + int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) { struct ieee80211_channel *chan, *scan_chan; @@ -110,21 +145,27 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) scan_chan = local->scan_channel; + /* If this off-channel logic ever changes, ieee80211_on_oper_channel + * may need to change as well. + */ offchannel_flag = local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; if (scan_chan) { chan = scan_chan; channel_type = NL80211_CHAN_NO_HT; - local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; - } else if (local->tmp_channel && - local->oper_channel != local->tmp_channel) { + } else if (local->tmp_channel) { chan = scan_chan = local->tmp_channel; channel_type = local->tmp_channel_type; - local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; } else { chan = local->oper_channel; channel_type = local->_oper_channel_type; - local->hw.conf.flags &= ~IEEE80211_CONF_OFFCHANNEL; } + + if (chan != local->oper_channel || + channel_type != local->_oper_channel_type) + local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; + else + local->hw.conf.flags &= ~IEEE80211_CONF_OFFCHANNEL; + offchannel_flag ^= local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; if (offchannel_flag || chan != local->hw.conf.channel || @@ -231,7 +272,7 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, if (changed & BSS_CHANGED_BEACON_ENABLED) { if (local->quiescing || !ieee80211_sdata_running(sdata) || - test_bit(SCAN_SW_SCANNING, &local->scanning)) { + test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) { sdata->vif.bss_conf.enable_beacon = false; } else { /* @@ -554,6 +595,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.queues = 1; local->hw.max_rates = 1; local->hw.max_report_rates = 0; + local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; local->user_power_level = -1; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index ca3af46..2a57cc0 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -574,7 +574,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, &elems); if (elems.ds_params && elems.ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems.ds_params[0]); + freq = ieee80211_channel_to_frequency(elems.ds_params[0], band); else freq = rx_status->freq; @@ -645,7 +645,7 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata) if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) mesh_mpath_table_grow(); - if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) + if (test_and_clear_bit(MESH_WORK_GROW_MPP_TABLE, &ifmsh->wrkq_flags)) mesh_mpp_table_grow(); if (test_and_clear_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags)) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 45fbb9e..f77adf1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -28,8 +28,15 @@ #include "rate.h" #include "led.h" -#define IEEE80211_MAX_NULLFUNC_TRIES 2 -#define IEEE80211_MAX_PROBE_TRIES 5 +static int max_nullfunc_tries = 2; +module_param(max_nullfunc_tries, int, 0644); +MODULE_PARM_DESC(max_nullfunc_tries, + "Maximum nullfunc tx tries before disconnecting (reason 4)."); + +static int max_probe_tries = 5; +module_param(max_probe_tries, int, 0644); +MODULE_PARM_DESC(max_probe_tries, + "Maximum probe tries before disconnecting (reason 4)."); /* * Beacon loss timeout is calculated as N frames times the @@ -51,7 +58,11 @@ * a probe request because of beacon loss or for * checking the connection still works. */ -#define IEEE80211_PROBE_WAIT (HZ / 2) +static int probe_wait_ms = 500; +module_param(probe_wait_ms, int, 0644); +MODULE_PARM_DESC(probe_wait_ms, + "Maximum time(ms) to wait for probe response" + " before disconnecting (reason 4)."); /* * Weight given to the latest Beacon frame when calculating average signal @@ -161,6 +172,7 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband; struct sta_info *sta; u32 changed = 0; + int hti_cfreq; u16 ht_opmode; bool enable_ht = true; enum nl80211_channel_type prev_chantype; @@ -174,10 +186,27 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, if (!sband->ht_cap.ht_supported) enable_ht = false; - /* check that channel matches the right operating channel */ - if (local->hw.conf.channel->center_freq != - ieee80211_channel_to_frequency(hti->control_chan)) - enable_ht = false; + if (enable_ht) { + hti_cfreq = ieee80211_channel_to_frequency(hti->control_chan, + sband->band); + /* check that channel matches the right operating channel */ + if (local->hw.conf.channel->center_freq != hti_cfreq) { + /* Some APs mess this up, evidently. + * Netgear WNDR3700 sometimes reports 4 higher than + * the actual channel, for instance. + */ + printk(KERN_DEBUG + "%s: Wrong control channel in association" + " response: configured center-freq: %d" + " hti-cfreq: %d hti->control_chan: %d" + " band: %d. Disabling HT.\n", + sdata->name, + local->hw.conf.channel->center_freq, + hti_cfreq, hti->control_chan, + sband->band); + enable_ht = false; + } + } if (enable_ht) { channel_type = NL80211_CHAN_HT20; @@ -429,7 +458,8 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, container_of((void *)bss, struct cfg80211_bss, priv); struct ieee80211_channel *new_ch; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num); + int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num, + cbss->channel->band); ASSERT_MGD_MTX(ifmgd); @@ -600,6 +630,14 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; + if (sdata->vif.type == NL80211_IFTYPE_AP) { + /* If an AP vif is found, then disable PS + * by setting the count to zero thereby setting + * ps_sdata to NULL. + */ + count = 0; + break; + } if (sdata->vif.type != NL80211_IFTYPE_STATION) continue; found = sdata; @@ -1089,7 +1127,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; const u8 *ssid; u8 *dst = ifmgd->associated->bssid; - u8 unicast_limit = max(1, IEEE80211_MAX_PROBE_TRIES - 3); + u8 unicast_limit = max(1, max_probe_tries - 3); /* * Try sending broadcast probe requests for the last three @@ -1115,7 +1153,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) } ifmgd->probe_send_count++; - ifmgd->probe_timeout = jiffies + IEEE80211_PROBE_WAIT; + ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); run_again(ifmgd, ifmgd->probe_timeout); } @@ -1216,7 +1254,8 @@ static void __ieee80211_connection_loss(struct ieee80211_sub_if_data *sdata) memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); - printk(KERN_DEBUG "Connection to AP %pM lost.\n", bssid); + printk(KERN_DEBUG "%s: Connection to AP %pM lost.\n", + sdata->name, bssid); ieee80211_set_disassoc(sdata, true, true); mutex_unlock(&ifmgd->mtx); @@ -1519,7 +1558,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, } if (elems->ds_params && elems->ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems->ds_params[0]); + freq = ieee80211_channel_to_frequency(elems->ds_params[0], + rx_status->band); else freq = rx_status->freq; @@ -1960,9 +2000,9 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) - max_tries = IEEE80211_MAX_NULLFUNC_TRIES; + max_tries = max_nullfunc_tries; else - max_tries = IEEE80211_MAX_PROBE_TRIES; + max_tries = max_probe_tries; /* ACK received for nullfunc probing frame */ if (!ifmgd->probe_send_count) @@ -1972,9 +2012,9 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) #ifdef CONFIG_MAC80211_VERBOSE_DEBUG wiphy_debug(local->hw.wiphy, "%s: No ack for nullfunc frame to" - " AP %pM, try %d\n", + " AP %pM, try %d/%i\n", sdata->name, bssid, - ifmgd->probe_send_count); + ifmgd->probe_send_count, max_tries); #endif ieee80211_mgd_probe_ap_send(sdata); } else { @@ -1994,17 +2034,17 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) "%s: Failed to send nullfunc to AP %pM" " after %dms, disconnecting.\n", sdata->name, - bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ); + bssid, probe_wait_ms); #endif ieee80211_sta_connection_lost(sdata, bssid); } else if (ifmgd->probe_send_count < max_tries) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG wiphy_debug(local->hw.wiphy, "%s: No probe response from AP %pM" - " after %dms, try %d\n", + " after %dms, try %d/%i\n", sdata->name, - bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ, - ifmgd->probe_send_count); + bssid, probe_wait_ms, + ifmgd->probe_send_count, max_tries); #endif ieee80211_mgd_probe_ap_send(sdata); } else { @@ -2016,7 +2056,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) "%s: No probe response from AP %pM" " after %dms, disconnecting.\n", sdata->name, - bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ); + bssid, probe_wait_ms); ieee80211_sta_connection_lost(sdata, bssid); } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index b4e5267..13427b1 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -17,10 +17,14 @@ #include "driver-trace.h" /* - * inform AP that we will go to sleep so that it will buffer the frames - * while we scan + * Tell our hardware to disable PS. + * Optionally inform AP that we will go to sleep so that it will buffer + * the frames while we are doing off-channel work. This is optional + * because we *may* be doing work on-operating channel, and want our + * hardware unconditionally awake, but still let the AP send us normal frames. */ -static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) +static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata, + bool tell_ap) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -41,8 +45,8 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); } - if (!(local->offchannel_ps_enabled) || - !(local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK)) + if (tell_ap && (!local->offchannel_ps_enabled || + !(local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK))) /* * If power save was enabled, no need to send a nullfunc * frame because AP knows that we are sleeping. But if the @@ -77,6 +81,9 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata) * we are sleeping, let's just enable power save mode in * hardware. */ + /* TODO: Only set hardware if CONF_PS changed? + * TODO: Should we set offchannel_ps_enabled to false? + */ local->hw.conf.flags |= IEEE80211_CONF_PS; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); } else if (local->hw.conf.dynamic_ps_timeout > 0) { @@ -95,63 +102,61 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata) ieee80211_sta_reset_conn_monitor(sdata); } -void ieee80211_offchannel_stop_beaconing(struct ieee80211_local *local) +void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, + bool offchannel_ps_enable) { struct ieee80211_sub_if_data *sdata; + /* + * notify the AP about us leaving the channel and stop all + * STA interfaces. + */ mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; - /* disable beaconing */ + if (sdata->vif.type != NL80211_IFTYPE_MONITOR) + set_bit(SDATA_STATE_OFFCHANNEL, &sdata->state); + + /* Check to see if we should disable beaconing. */ if (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_ADHOC || sdata->vif.type == NL80211_IFTYPE_MESH_POINT) ieee80211_bss_info_change_notify( sdata, BSS_CHANGED_BEACON_ENABLED); - /* - * only handle non-STA interfaces here, STA interfaces - * are handled in ieee80211_offchannel_stop_station(), - * e.g., from the background scan state machine. - * - * In addition, do not stop monitor interface to allow it to be - * used from user space controlled off-channel operations. - */ - if (sdata->vif.type != NL80211_IFTYPE_STATION && - sdata->vif.type != NL80211_IFTYPE_MONITOR) { - set_bit(SDATA_STATE_OFFCHANNEL, &sdata->state); + if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { netif_tx_stop_all_queues(sdata->dev); + if (offchannel_ps_enable && + (sdata->vif.type == NL80211_IFTYPE_STATION) && + sdata->u.mgd.associated) + ieee80211_offchannel_ps_enable(sdata, true); } } mutex_unlock(&local->iflist_mtx); } -void ieee80211_offchannel_stop_station(struct ieee80211_local *local) +void ieee80211_offchannel_enable_all_ps(struct ieee80211_local *local, + bool tell_ap) { struct ieee80211_sub_if_data *sdata; - /* - * notify the AP about us leaving the channel and stop all STA interfaces - */ mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - set_bit(SDATA_STATE_OFFCHANNEL, &sdata->state); - netif_tx_stop_all_queues(sdata->dev); - if (sdata->u.mgd.associated) - ieee80211_offchannel_ps_enable(sdata); - } + if (sdata->vif.type == NL80211_IFTYPE_STATION && + sdata->u.mgd.associated) + ieee80211_offchannel_ps_enable(sdata, tell_ap); } mutex_unlock(&local->iflist_mtx); } void ieee80211_offchannel_return(struct ieee80211_local *local, - bool enable_beaconing) + bool enable_beaconing, + bool offchannel_ps_disable) { struct ieee80211_sub_if_data *sdata; @@ -161,7 +166,8 @@ void ieee80211_offchannel_return(struct ieee80211_local *local, continue; /* Tell AP we're back */ - if (sdata->vif.type == NL80211_IFTYPE_STATION) { + if (offchannel_ps_disable && + sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.associated) ieee80211_offchannel_ps_disable(sdata); } @@ -181,7 +187,7 @@ void ieee80211_offchannel_return(struct ieee80211_local *local, netif_tx_wake_all_queues(sdata->dev); } - /* re-enable beaconing */ + /* Check to see if we should re-enable beaconing */ if (enable_beaconing && (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_ADHOC || diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a6701ed..045b2fe 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -85,6 +85,9 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local, if (len & 1) /* padding for RX_FLAGS if necessary */ len++; + if (status->flag & RX_FLAG_HT) /* HT info */ + len += 3; + return len; } @@ -139,11 +142,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, /* IEEE80211_RADIOTAP_RATE */ if (status->flag & RX_FLAG_HT) { /* - * TODO: add following information into radiotap header once - * suitable fields are defined for it: - * - MCS index (status->rate_idx) - * - HT40 (status->flag & RX_FLAG_40MHZ) - * - short-GI (status->flag & RX_FLAG_SHORT_GI) + * MCS information is a separate field in radiotap, + * added below. */ *pos = 0; } else { @@ -193,6 +193,20 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, rx_flags |= IEEE80211_RADIOTAP_F_RX_BADPLCP; put_unaligned_le16(rx_flags, pos); pos += 2; + + if (status->flag & RX_FLAG_HT) { + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + *pos++ = IEEE80211_RADIOTAP_MCS_HAVE_MCS | + IEEE80211_RADIOTAP_MCS_HAVE_GI | + IEEE80211_RADIOTAP_MCS_HAVE_BW; + *pos = 0; + if (status->flag & RX_FLAG_SHORT_GI) + *pos |= IEEE80211_RADIOTAP_MCS_SGI; + if (status->flag & RX_FLAG_40MHZ) + *pos |= IEEE80211_RADIOTAP_MCS_BW_40; + pos++; + *pos++ = status->rate_idx; + } } /* @@ -392,16 +406,10 @@ ieee80211_rx_h_passive_scan(struct ieee80211_rx_data *rx) if (likely(!(status->rx_flags & IEEE80211_RX_IN_SCAN))) return RX_CONTINUE; - if (test_bit(SCAN_HW_SCANNING, &local->scanning)) + if (test_bit(SCAN_HW_SCANNING, &local->scanning) || + test_bit(SCAN_SW_SCANNING, &local->scanning)) return ieee80211_scan_rx(rx->sdata, skb); - if (test_bit(SCAN_SW_SCANNING, &local->scanning)) { - /* drop all the other packets during a software scan anyway */ - if (ieee80211_scan_rx(rx->sdata, skb) != RX_QUEUED) - dev_kfree_skb(skb); - return RX_QUEUED; - } - /* scanning finished during invoking of handlers */ I802_DEBUG_INC(local->rx_handlers_drop_passive_scan); return RX_DROP_UNUSABLE; @@ -798,7 +806,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) rx->local->dot11FrameDuplicateCount++; rx->sta->num_duplicates++; } - return RX_DROP_MONITOR; + return RX_DROP_UNUSABLE; } else rx->sta->last_seq_ctrl[rx->queue] = hdr->seq_ctrl; } @@ -1088,7 +1096,8 @@ static void ap_sta_ps_start(struct sta_info *sta) atomic_inc(&sdata->bss->num_sta_ps); set_sta_flags(sta, WLAN_STA_PS_STA); - drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta); + if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) + drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta); #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "%s: STA %pM aid %d enters power save mode\n", sdata->name, sta->sta.addr, sta->sta.aid); @@ -1117,6 +1126,27 @@ static void ap_sta_ps_end(struct sta_info *sta) ieee80211_sta_ps_deliver_wakeup(sta); } +int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start) +{ + struct sta_info *sta_inf = container_of(sta, struct sta_info, sta); + bool in_ps; + + WARN_ON(!(sta_inf->local->hw.flags & IEEE80211_HW_AP_LINK_PS)); + + /* Don't let the same PS state be set twice */ + in_ps = test_sta_flags(sta_inf, WLAN_STA_PS_STA); + if ((start && in_ps) || (!start && !in_ps)) + return -EINVAL; + + if (start) + ap_sta_ps_start(sta_inf); + else + ap_sta_ps_end(sta_inf); + + return 0; +} +EXPORT_SYMBOL(ieee80211_sta_ps_transition); + static ieee80211_rx_result debug_noinline ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) { @@ -1161,7 +1191,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) * Change STA power saving mode only at the end of a frame * exchange sequence. */ - if (!ieee80211_has_morefrags(hdr->frame_control) && + if (!(sta->local->hw.flags & IEEE80211_HW_AP_LINK_PS) && + !ieee80211_has_morefrags(hdr->frame_control) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && (rx->sdata->vif.type == NL80211_IFTYPE_AP || rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) { @@ -1556,17 +1587,36 @@ __ieee80211_data_to_8023(struct ieee80211_rx_data *rx) { struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; + bool check_port_control = false; + struct ethhdr *ehdr; + int ret; if (ieee80211_has_a4(hdr->frame_control) && sdata->vif.type == NL80211_IFTYPE_AP_VLAN && !sdata->u.vlan.sta) return -1; + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !!sdata->u.mgd.use_4addr != !!ieee80211_has_a4(hdr->frame_control)) { + + if (!sdata->u.mgd.use_4addr) + return -1; + else + check_port_control = true; + } + if (is_multicast_ether_addr(hdr->addr1) && - ((sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sdata->u.vlan.sta) || - (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.use_4addr))) + sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sdata->u.vlan.sta) + return -1; + + ret = ieee80211_data_to_8023(rx->skb, sdata->vif.addr, sdata->vif.type); + if (ret < 0 || !check_port_control) + return ret; + + ehdr = (struct ethhdr *) rx->skb->data; + if (ehdr->h_proto != rx->sdata->control_port_protocol) return -1; - return ieee80211_data_to_8023(rx->skb, sdata->vif.addr, sdata->vif.type); + return 0; } /* @@ -1893,7 +1943,10 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) dev->stats.rx_bytes += rx->skb->len; if (local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 && - !is_multicast_ether_addr(((struct ethhdr *)rx->skb->data)->h_dest)) { + !is_multicast_ether_addr( + ((struct ethhdr *)rx->skb->data)->h_dest) && + (!local->scanning && + !test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state))) { mod_timer(&local->dynamic_ps_timer, jiffies + msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); } @@ -2590,7 +2643,8 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, return 0; if (!multicast && compare_ether_addr(sdata->vif.addr, hdr->addr1) != 0) { - if (!(sdata->dev->flags & IFF_PROMISC)) + if (!(sdata->dev->flags & IFF_PROMISC) || + sdata->u.mgd.use_4addr) return 0; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } @@ -2639,7 +2693,8 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, return 0; } else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { - if (!(status->rx_flags & IEEE80211_RX_IN_SCAN)) + if (!(status->rx_flags & IEEE80211_RX_IN_SCAN) && + !ieee80211_is_beacon(hdr->frame_control)) return 0; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } @@ -2692,7 +2747,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, if (!skb) { if (net_ratelimit()) wiphy_debug(local->hw.wiphy, - "failed to copy multicast frame for %s\n", + "failed to copy skb for %s\n", sdata->name); return true; } @@ -2730,7 +2785,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, local->dot11ReceivedFragmentCount++; if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning) || - test_bit(SCAN_OFF_CHANNEL, &local->scanning))) + test_bit(SCAN_SW_SCANNING, &local->scanning))) status->rx_flags |= IEEE80211_RX_IN_SCAN; if (ieee80211_is_mgmt(fc)) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index fb274db..0ea6ada 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -196,7 +196,8 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) ieee802_11_parse_elems(elements, skb->len - baselen, &elems); if (elems.ds_params && elems.ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems.ds_params[0]); + freq = ieee80211_channel_to_frequency(elems.ds_params[0], + rx_status->band); else freq = rx_status->freq; @@ -211,6 +212,14 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) if (bss) ieee80211_rx_bss_put(sdata->local, bss); + /* If we are on-operating-channel, and this packet is for the + * current channel, pass the pkt on up the stack so that + * the rest of the stack can make use of it. + */ + if (ieee80211_cfg_on_oper_channel(sdata->local) + && (channel == sdata->local->oper_channel)) + return RX_CONTINUE; + dev_kfree_skb(skb); return RX_QUEUED; } @@ -292,15 +301,31 @@ static void __ieee80211_scan_completed_finish(struct ieee80211_hw *hw, bool was_hw_scan) { struct ieee80211_local *local = hw_to_local(hw); + bool on_oper_chan; + bool enable_beacons = false; + + mutex_lock(&local->mtx); + on_oper_chan = ieee80211_cfg_on_oper_channel(local); + + if (was_hw_scan || !on_oper_chan) { + if (WARN_ON(local->scan_channel)) + local->scan_channel = NULL; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + } - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); if (!was_hw_scan) { + bool on_oper_chan2; ieee80211_configure_filter(local); drv_sw_scan_complete(local); - ieee80211_offchannel_return(local, true); + on_oper_chan2 = ieee80211_cfg_on_oper_channel(local); + /* We should always be on-channel at this point. */ + WARN_ON(!on_oper_chan2); + if (on_oper_chan2 && (on_oper_chan != on_oper_chan2)) + enable_beacons = true; + + ieee80211_offchannel_return(local, enable_beacons, true); } - mutex_lock(&local->mtx); ieee80211_recalc_idle(local); mutex_unlock(&local->mtx); @@ -340,13 +365,15 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) */ drv_sw_scan_start(local); - ieee80211_offchannel_stop_beaconing(local); - local->leave_oper_channel_time = 0; local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; - drv_flush(local, false); + /* We always want to use off-channel PS, even if we + * are not really leaving oper-channel. Don't + * tell the AP though, as long as we are on-channel. + */ + ieee80211_offchannel_enable_all_ps(local, false); ieee80211_configure_filter(local); @@ -486,7 +513,21 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local, } mutex_unlock(&local->iflist_mtx); - if (local->scan_channel) { + next_chan = local->scan_req->channels[local->scan_channel_idx]; + + if (ieee80211_cfg_on_oper_channel(local)) { + /* We're currently on operating channel. */ + if ((next_chan == local->oper_channel) && + (local->_oper_channel_type == NL80211_CHAN_NO_HT)) + /* We don't need to move off of operating channel. */ + local->next_scan_state = SCAN_SET_CHANNEL; + else + /* + * We do need to leave operating channel, as next + * scan is somewhere else. + */ + local->next_scan_state = SCAN_LEAVE_OPER_CHANNEL; + } else { /* * we're currently scanning a different channel, let's * see if we can scan another channel without interfering @@ -502,7 +543,6 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local, * * Otherwise switch back to the operating channel. */ - next_chan = local->scan_req->channels[local->scan_channel_idx]; bad_latency = time_after(jiffies + ieee80211_scan_get_channel_time(next_chan), @@ -520,12 +560,6 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local, local->next_scan_state = SCAN_ENTER_OPER_CHANNEL; else local->next_scan_state = SCAN_SET_CHANNEL; - } else { - /* - * we're on the operating channel currently, let's - * leave that channel now to scan another one - */ - local->next_scan_state = SCAN_LEAVE_OPER_CHANNEL; } *next_delay = 0; @@ -534,9 +568,10 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local, static void ieee80211_scan_state_leave_oper_channel(struct ieee80211_local *local, unsigned long *next_delay) { - ieee80211_offchannel_stop_station(local); - - __set_bit(SCAN_OFF_CHANNEL, &local->scanning); + /* PS will already be in off-channel mode, + * we do that once at the beginning of scanning. + */ + ieee80211_offchannel_stop_vifs(local, false); /* * What if the nullfunc frames didn't arrive? @@ -559,15 +594,15 @@ static void ieee80211_scan_state_enter_oper_channel(struct ieee80211_local *loca { /* switch back to the operating channel */ local->scan_channel = NULL; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (!ieee80211_cfg_on_oper_channel(local)) + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); /* - * Only re-enable station mode interface now; beaconing will be - * re-enabled once the full scan has been completed. + * Re-enable vifs and beaconing. Leave PS + * in off-channel state..will put that back + * on-channel at the end of scanning. */ - ieee80211_offchannel_return(local, false); - - __clear_bit(SCAN_OFF_CHANNEL, &local->scanning); + ieee80211_offchannel_return(local, true, false); *next_delay = HZ / 5; local->next_scan_state = SCAN_DECISION; @@ -583,8 +618,12 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, chan = local->scan_req->channels[local->scan_channel_idx]; local->scan_channel = chan; - if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL)) - skip = 1; + + /* Only call hw-config if we really need to change channels. */ + if ((chan != local->hw.conf.channel) || + (local->hw.conf.channel_type != NL80211_CHAN_NO_HT)) + if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL)) + skip = 1; /* advance state machine to next channel/band */ local->scan_channel_idx++; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c426504..5a11078 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -899,7 +899,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) struct ieee80211_local *local = sdata->local; int sent, buffered; - drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); + if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) + drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); if (!skb_queue_empty(&sta->ps_tx_buf)) sta_info_clear_tim_bit(sta); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index bbdd2a8..ca0b690 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -82,6 +82,7 @@ enum ieee80211_sta_info_flags { * @state: session state (see above) * @stop_initiator: initiator of a session stop * @tx_stop: TX DelBA frame when stopping + * @buf_size: reorder buffer size at receiver * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -101,6 +102,7 @@ struct tid_ampdu_tx { u8 dialog_token; u8 stop_initiator; bool tx_stop; + u8 buf_size; }; /** diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 071ac95..010a559 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -98,6 +98,10 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, * (b) always process RX events before TX status events if ordering * can be unknown, for example with different interrupt status * bits. + * (c) if PS mode transitions are manual (i.e. the flag + * %IEEE80211_HW_AP_LINK_PS is set), always process PS state + * changes before calling TX status events if ordering can be + * unknown. */ if (test_sta_flags(sta, WLAN_STA_PS_STA) && skb_queue_len(&sta->tx_filtered) < STA_MAX_TX_BUFFER) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b0beaa5..17ef4f4 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -257,7 +257,8 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (unlikely(info->flags & IEEE80211_TX_CTL_INJECTED)) return TX_CONTINUE; - if (unlikely(test_bit(SCAN_OFF_CHANNEL, &tx->local->scanning)) && + if (unlikely(test_bit(SCAN_SW_SCANNING, &tx->local->scanning)) && + test_bit(SDATA_STATE_OFFCHANNEL, &tx->sdata->state) && !ieee80211_is_probe_req(hdr->frame_control) && !ieee80211_is_nullfunc(hdr->frame_control)) /* @@ -1394,7 +1395,8 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx) /* handlers after fragment must be aware of tx info fragmentation! */ CALL_TXH(ieee80211_tx_h_stats); CALL_TXH(ieee80211_tx_h_encrypt); - CALL_TXH(ieee80211_tx_h_calculate_duration); + if (!(tx->local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL)) + CALL_TXH(ieee80211_tx_h_calculate_duration); #undef CALL_TXH txh_done: @@ -1750,7 +1752,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, __le16 fc; struct ieee80211_hdr hdr; struct ieee80211s_hdr mesh_hdr __maybe_unused; - struct mesh_path *mppath = NULL; + struct mesh_path __maybe_unused *mppath = NULL; const u8 *encaps_data; int encaps_len, skip_header_bytes; int nh_pos, h_pos; @@ -1815,19 +1817,19 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, mppath = mpp_path_lookup(skb->data, sdata); /* - * Do not use address extension, if it is a packet from - * the same interface and the destination is not being - * proxied by any other mest point. + * Use address extension if it is a packet from + * another interface or if we know the destination + * is being proxied by a portal (i.e. portal address + * differs from proxied address) */ if (compare_ether_addr(sdata->vif.addr, skb->data + ETH_ALEN) == 0 && - (!mppath || !compare_ether_addr(mppath->mpp, skb->data))) { + !(mppath && compare_ether_addr(mppath->mpp, skb->data))) { hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, skb->data, skb->data + ETH_ALEN); meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, NULL, NULL); } else { - /* packet from other interface */ int is_mesh_mcast = 1; const u8 *mesh_da; @@ -2178,6 +2180,8 @@ static void ieee80211_beacon_add_tim(struct ieee80211_if_ap *bss, if (bss->dtim_count == 0 && !skb_queue_empty(&bss->ps_bc_buf)) aid0 = 1; + bss->dtim_bc_mc = aid0 == 1; + if (have_bits) { /* Find largest even number N1 so that bits numbered 1 through * (N1 x 8) - 1 in the bitmap are 0 and number N2 so that bits @@ -2241,7 +2245,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (sdata->vif.type == NL80211_IFTYPE_AP) { ap = &sdata->u.ap; beacon = rcu_dereference(ap->beacon); - if (ap && beacon) { + if (beacon) { /* * headroom, head length, * tail length and maximum TIM length @@ -2302,6 +2306,11 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct ieee80211_mgmt *mgmt; u8 *pos; +#ifdef CONFIG_MAC80211_MESH + if (!sdata->u.mesh.mesh_id_len) + goto out; +#endif + /* headroom, head length, tail length and maximum TIM length */ skb = dev_alloc_skb(local->tx_headroom + 400 + sdata->u.mesh.vendor_ie_len); @@ -2543,7 +2552,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, if (sdata->vif.type != NL80211_IFTYPE_AP || !beacon || !beacon->head) goto out; - if (bss->dtim_count != 0) + if (bss->dtim_count != 0 || !bss->dtim_bc_mc) goto out; /* send buffered bc/mc only after DTIM beacon */ while (1) { diff --git a/net/mac80211/work.c b/net/mac80211/work.c index 36305e0..6bf787a 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -924,18 +924,44 @@ static void ieee80211_work_work(struct work_struct *work) } if (!started && !local->tmp_channel) { - /* - * TODO: could optimize this by leaving the - * station vifs in awake mode if they - * happen to be on the same channel as - * the requested channel - */ - ieee80211_offchannel_stop_beaconing(local); - ieee80211_offchannel_stop_station(local); + bool on_oper_chan; + bool tmp_chan_changed = false; + bool on_oper_chan2; + on_oper_chan = ieee80211_cfg_on_oper_channel(local); + if (local->tmp_channel) + if ((local->tmp_channel != wk->chan) || + (local->tmp_channel_type != wk->chan_type)) + tmp_chan_changed = true; local->tmp_channel = wk->chan; local->tmp_channel_type = wk->chan_type; - ieee80211_hw_config(local, 0); + /* + * Leave the station vifs in awake mode if they + * happen to be on the same channel as + * the requested channel. + */ + on_oper_chan2 = ieee80211_cfg_on_oper_channel(local); + if (on_oper_chan != on_oper_chan2) { + if (on_oper_chan2) { + /* going off oper channel, PS too */ + ieee80211_offchannel_stop_vifs(local, + true); + ieee80211_hw_config(local, 0); + } else { + /* going on channel, but leave PS + * off-channel. */ + ieee80211_hw_config(local, 0); + ieee80211_offchannel_return(local, + true, + false); + } + } else if (tmp_chan_changed) + /* Still off-channel, but on some other + * channel, so update hardware. + * PS should already be off-channel. + */ + ieee80211_hw_config(local, 0); + started = true; wk->timeout = jiffies; } @@ -1011,9 +1037,27 @@ static void ieee80211_work_work(struct work_struct *work) } if (!remain_off_channel && local->tmp_channel) { + bool on_oper_chan = ieee80211_cfg_on_oper_channel(local); local->tmp_channel = NULL; - ieee80211_hw_config(local, 0); - ieee80211_offchannel_return(local, true); + /* If tmp_channel wasn't operating channel, then + * we need to go back on-channel. + * NOTE: If we can ever be here while scannning, + * or if the hw_config() channel config logic changes, + * then we may need to do a more thorough check to see if + * we still need to do a hardware config. Currently, + * we cannot be here while scanning, however. + */ + if (ieee80211_cfg_on_oper_channel(local) && !on_oper_chan) + ieee80211_hw_config(local, 0); + + /* At the least, we need to disable offchannel_ps, + * so just go ahead and run the entire offchannel + * return logic here. We *could* skip enabling + * beaconing if we were already on-oper-channel + * as a future optimization. + */ + ieee80211_offchannel_return(local, true, true); + /* give connection some time to breathe */ run_again(local, jiffies + HZ/2); } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index bee230d..f1765de 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -26,13 +26,12 @@ ieee80211_tx_result ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) { - u8 *data, *key, *mic, key_offset; + u8 *data, *key, *mic; size_t data_len; unsigned int hdrlen; struct ieee80211_hdr *hdr; struct sk_buff *skb = tx->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - int authenticator; int tail; hdr = (struct ieee80211_hdr *)skb->data; @@ -47,6 +46,11 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) data = skb->data + hdrlen; data_len = skb->len - hdrlen; + if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) { + /* Need to use software crypto for the test */ + info->control.hw_key = NULL; + } + if (info->control.hw_key && !(tx->flags & IEEE80211_TX_FRAGMENTED) && !(tx->key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) { @@ -62,17 +66,11 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) skb_headroom(skb) < TKIP_IV_LEN)) return TX_DROP; -#if 0 - authenticator = fc & IEEE80211_FCTL_FROMDS; /* FIX */ -#else - authenticator = 1; -#endif - key_offset = authenticator ? - NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY : - NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY; - key = &tx->key->conf.key[key_offset]; + key = &tx->key->conf.key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY]; mic = skb_put(skb, MICHAEL_MIC_LEN); michael_mic(key, hdr, data, data_len, mic); + if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) + mic[0]++; return TX_CONTINUE; } @@ -81,14 +79,13 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) ieee80211_rx_result ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) { - u8 *data, *key = NULL, key_offset; + u8 *data, *key = NULL; size_t data_len; unsigned int hdrlen; u8 mic[MICHAEL_MIC_LEN]; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - int authenticator = 1, wpa_test = 0; /* No way to verify the MIC if the hardware stripped it */ if (status->flag & RX_FLAG_MMIC_STRIPPED) @@ -106,17 +103,9 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) data = skb->data + hdrlen; data_len = skb->len - hdrlen - MICHAEL_MIC_LEN; -#if 0 - authenticator = fc & IEEE80211_FCTL_TODS; /* FIX */ -#else - authenticator = 1; -#endif - key_offset = authenticator ? - NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY : - NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY; - key = &rx->key->conf.key[key_offset]; + key = &rx->key->conf.key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY]; michael_mic(key, hdr, data, data_len, mic); - if (memcmp(mic, data + data_len, MICHAEL_MIC_LEN) != 0 || wpa_test) { + if (memcmp(mic, data + data_len, MICHAEL_MIC_LEN) != 0) { if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_DROP_UNUSABLE; @@ -208,7 +197,7 @@ ieee80211_rx_result ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) rx->skb->data; - int hdrlen, res, hwaccel = 0, wpa_test = 0; + int hdrlen, res, hwaccel = 0; struct ieee80211_key *key = rx->key; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -235,7 +224,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) hdr->addr1, hwaccel, rx->queue, &rx->tkip_iv32, &rx->tkip_iv16); - if (res != TKIP_DECRYPT_OK || wpa_test) + if (res != TKIP_DECRYPT_OK) return RX_DROP_UNUSABLE; /* Trim ICV */ diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 1534f2b..82a6e0d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -85,6 +85,17 @@ config NF_CONNTRACK_EVENTS If unsure, say `N'. +config NF_CONNTRACK_TIMESTAMP + bool 'Connection tracking timestamping' + depends on NETFILTER_ADVANCED + help + This option enables support for connection tracking timestamping. + This allows you to store the flow start-time and to obtain + the flow-stop time (once it has been destroyed) via Connection + tracking events. + + If unsure, say `N'. + config NF_CT_PROTO_DCCP tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)' depends on EXPERIMENTAL @@ -185,9 +196,13 @@ config NF_CONNTRACK_IRC To compile it as a module, choose M here. If unsure, say N. +config NF_CONNTRACK_BROADCAST + tristate + config NF_CONNTRACK_NETBIOS_NS tristate "NetBIOS name service protocol support" depends on NETFILTER_ADVANCED + select NF_CONNTRACK_BROADCAST help NetBIOS name service requests are sent as broadcast messages from an unprivileged port and responded to with unicast messages to the @@ -204,6 +219,21 @@ config NF_CONNTRACK_NETBIOS_NS To compile it as a module, choose M here. If unsure, say N. +config NF_CONNTRACK_SNMP + tristate "SNMP service protocol support" + depends on NETFILTER_ADVANCED + select NF_CONNTRACK_BROADCAST + help + SNMP service requests are sent as broadcast messages from an + unprivileged port and responded to with unicast messages to the + same port. This make them hard to firewall properly because connection + tracking doesn't deal with broadcasts. This helper tracks locally + originating SNMP service requests and the corresponding + responses. It relies on correct IP address configuration, specifically + netmask and broadcast address. + + To compile it as a module, choose M here. If unsure, say N. + config NF_CONNTRACK_PPTP tristate "PPtP protocol support" depends on NETFILTER_ADVANCED @@ -322,10 +352,32 @@ config NETFILTER_XT_CONNMARK ctmark), similarly to the packet mark (nfmark). Using this target and match, you can set and match on this mark. +config NETFILTER_XT_SET + tristate 'set target and match support' + depends on IP_SET + depends on NETFILTER_ADVANCED + help + This option adds the "SET" target and "set" match. + + Using this target and match, you can add/delete and match + elements in the sets created by ipset(8). + + To compile it as a module, choose M here. If unsure, say N. + # alphabetically ordered list of targets comment "Xtables targets" +config NETFILTER_XT_TARGET_AUDIT + tristate "AUDIT target support" + depends on AUDIT + depends on NETFILTER_ADVANCED + ---help--- + This option adds a 'AUDIT' target, which can be used to create + audit records for packets dropped/accepted. + + To compileit as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_CHECKSUM tristate "CHECKSUM target support" depends on IP_NF_MANGLE || IP6_NF_MANGLE @@ -477,6 +529,7 @@ config NETFILTER_XT_TARGET_NFLOG config NETFILTER_XT_TARGET_NFQUEUE tristate '"NFQUEUE" target Support' depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK_QUEUE help This target replaced the old obsolete QUEUE target. @@ -685,6 +738,15 @@ config NETFILTER_XT_MATCH_DCCP If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_DEVGROUP + tristate '"devgroup" match support' + depends on NETFILTER_ADVANCED + help + This options adds a `devgroup' match, which allows to match on the + device group a network device is assigned to. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_DSCP tristate '"dscp" and "tos" match support' depends on NETFILTER_ADVANCED @@ -886,7 +948,7 @@ config NETFILTER_XT_MATCH_RATEEST config NETFILTER_XT_MATCH_REALM tristate '"realm" match support' depends on NETFILTER_ADVANCED - select NET_CLS_ROUTE + select IP_ROUTE_CLASSID help This option adds a `realm' match, which allows you to use the realm key from the routing subsystem inside iptables. @@ -1011,4 +1073,6 @@ endif # NETFILTER_XTABLES endmenu +source "net/netfilter/ipset/Kconfig" + source "net/netfilter/ipvs/Kconfig" diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 441050f..d57a890 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,6 +1,7 @@ netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -28,7 +29,9 @@ obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o +obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o +obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o @@ -43,8 +46,10 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o # combos obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o +obj-$(CONFIG_NETFILTER_XT_SET) += xt_set.o # targets +obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o @@ -72,6 +77,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o +obj-$(CONFIG_NETFILTER_XT_MATCH_DEVGROUP) += xt_devgroup.o obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o @@ -101,5 +107,8 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o obj-$(CONFIG_NETFILTER_XT_MATCH_U32) += xt_u32.o +# ipset +obj-$(CONFIG_IP_SET) += ipset/ + # IPVS obj-$(CONFIG_IP_VS) += ipvs/ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 4aa614b..899b71c 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -176,13 +176,21 @@ next_hook: ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { kfree_skb(skb); - ret = -(verdict >> NF_VERDICT_BITS); + ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { - if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn, - verdict >> NF_VERDICT_BITS)) - goto next_hook; + ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn, + verdict >> NF_VERDICT_QBITS); + if (ret < 0) { + if (ret == -ECANCELED) + goto next_hook; + if (ret == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + goto next_hook; + kfree_skb(skb); + } + ret = 0; } rcu_read_unlock(); return ret; @@ -215,7 +223,7 @@ EXPORT_SYMBOL(skb_make_writable); /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence manufactured ICMP or RST packets will not be associated with it. */ -void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) @@ -232,7 +240,7 @@ void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) } EXPORT_SYMBOL(nf_ct_attach); -void (*nf_ct_destroy)(struct nf_conntrack *); +void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly; EXPORT_SYMBOL(nf_ct_destroy); void nf_conntrack_destroy(struct nf_conntrack *nfct) diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig new file mode 100644 index 0000000..3b970d3 --- /dev/null +++ b/net/netfilter/ipset/Kconfig @@ -0,0 +1,121 @@ +menuconfig IP_SET + tristate "IP set support" + depends on INET && NETFILTER + help + This option adds IP set support to the kernel. + In order to define and use the sets, you need the userspace utility + ipset(8). You can use the sets in netfilter via the "set" match + and "SET" target. + + To compile it as a module, choose M here. If unsure, say N. + +if IP_SET + +config IP_SET_MAX + int "Maximum number of IP sets" + default 256 + range 2 65534 + depends on IP_SET + help + You can define here default value of the maximum number + of IP sets for the kernel. + + The value can be overriden by the 'max_sets' module + parameter of the 'ip_set' module. + +config IP_SET_BITMAP_IP + tristate "bitmap:ip set support" + depends on IP_SET + help + This option adds the bitmap:ip set type support, by which one + can store IPv4 addresses (or network addresse) from a range. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_BITMAP_IPMAC + tristate "bitmap:ip,mac set support" + depends on IP_SET + help + This option adds the bitmap:ip,mac set type support, by which one + can store IPv4 address and (source) MAC address pairs from a range. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_BITMAP_PORT + tristate "bitmap:port set support" + depends on IP_SET + help + This option adds the bitmap:port set type support, by which one + can store TCP/UDP port numbers from a range. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_HASH_IP + tristate "hash:ip set support" + depends on IP_SET + help + This option adds the hash:ip set type support, by which one + can store arbitrary IPv4 or IPv6 addresses (or network addresses) + in a set. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_HASH_IPPORT + tristate "hash:ip,port set support" + depends on IP_SET + help + This option adds the hash:ip,port set type support, by which one + can store IPv4/IPv6 address and protocol/port pairs. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_HASH_IPPORTIP + tristate "hash:ip,port,ip set support" + depends on IP_SET + help + This option adds the hash:ip,port,ip set type support, by which + one can store IPv4/IPv6 address, protocol/port, and IPv4/IPv6 + address triples in a set. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_HASH_IPPORTNET + tristate "hash:ip,port,net set support" + depends on IP_SET + help + This option adds the hash:ip,port,net set type support, by which + one can store IPv4/IPv6 address, protocol/port, and IPv4/IPv6 + network address/prefix triples in a set. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_HASH_NET + tristate "hash:net set support" + depends on IP_SET + help + This option adds the hash:net set type support, by which + one can store IPv4/IPv6 network address/prefix elements in a set. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_HASH_NETPORT + tristate "hash:net,port set support" + depends on IP_SET + help + This option adds the hash:net,port set type support, by which + one can store IPv4/IPv6 network address/prefix and + protocol/port pairs as elements in a set. + + To compile it as a module, choose M here. If unsure, say N. + +config IP_SET_LIST_SET + tristate "list:set set support" + depends on IP_SET + help + This option adds the list:set set type support. In this + kind of set one can store the name of other sets and it forms + an ordered union of the member sets. + + To compile it as a module, choose M here. If unsure, say N. + +endif # IP_SET diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile new file mode 100644 index 0000000..5adbdab --- /dev/null +++ b/net/netfilter/ipset/Makefile @@ -0,0 +1,24 @@ +# +# Makefile for the ipset modules +# + +ip_set-y := ip_set_core.o ip_set_getport.o pfxlen.o + +# ipset core +obj-$(CONFIG_IP_SET) += ip_set.o + +# bitmap types +obj-$(CONFIG_IP_SET_BITMAP_IP) += ip_set_bitmap_ip.o +obj-$(CONFIG_IP_SET_BITMAP_IPMAC) += ip_set_bitmap_ipmac.o +obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o + +# hash types +obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o +obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o +obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o +obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o +obj-$(CONFIG_IP_SET_HASH_NET) += ip_set_hash_net.o +obj-$(CONFIG_IP_SET_HASH_NETPORT) += ip_set_hash_netport.o + +# list types +obj-$(CONFIG_IP_SET_LIST_SET) += ip_set_list_set.o diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c new file mode 100644 index 0000000..bca9699 --- /dev/null +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -0,0 +1,587 @@ +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the bitmap:ip type */ + +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/bitops.h> +#include <linux/spinlock.h> +#include <linux/netlink.h> +#include <linux/jiffies.h> +#include <linux/timer.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_bitmap.h> +#define IP_SET_BITMAP_TIMEOUT +#include <linux/netfilter/ipset/ip_set_timeout.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("bitmap:ip type of IP sets"); +MODULE_ALIAS("ip_set_bitmap:ip"); + +/* Type structure */ +struct bitmap_ip { + void *members; /* the set members */ + u32 first_ip; /* host byte order, included in range */ + u32 last_ip; /* host byte order, included in range */ + u32 elements; /* number of max elements in the set */ + u32 hosts; /* number of hosts in a subnet */ + size_t memsize; /* members size */ + u8 netmask; /* subnet netmask */ + u32 timeout; /* timeout parameter */ + struct timer_list gc; /* garbage collection */ +}; + +/* Base variant */ + +static inline u32 +ip_to_id(const struct bitmap_ip *m, u32 ip) +{ + return ((ip & ip_set_hostmask(m->netmask)) - m->first_ip)/m->hosts; +} + +static int +bitmap_ip_test(struct ip_set *set, void *value, u32 timeout) +{ + const struct bitmap_ip *map = set->data; + u16 id = *(u16 *)value; + + return !!test_bit(id, map->members); +} + +static int +bitmap_ip_add(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ip *map = set->data; + u16 id = *(u16 *)value; + + if (test_and_set_bit(id, map->members)) + return -IPSET_ERR_EXIST; + + return 0; +} + +static int +bitmap_ip_del(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ip *map = set->data; + u16 id = *(u16 *)value; + + if (!test_and_clear_bit(id, map->members)) + return -IPSET_ERR_EXIST; + + return 0; +} + +static int +bitmap_ip_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct bitmap_ip *map = set->data; + struct nlattr *atd, *nested; + u32 id, first = cb->args[2]; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] < map->elements; cb->args[2]++) { + id = cb->args[2]; + if (!test_bit(id, map->members)) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (id == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id * map->hosts)); + ipset_nest_end(skb, nested); + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, atd); + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +/* Timeout variant */ + +static int +bitmap_ip_ttest(struct ip_set *set, void *value, u32 timeout) +{ + const struct bitmap_ip *map = set->data; + const unsigned long *members = map->members; + u16 id = *(u16 *)value; + + return ip_set_timeout_test(members[id]); +} + +static int +bitmap_ip_tadd(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ip *map = set->data; + unsigned long *members = map->members; + u16 id = *(u16 *)value; + + if (ip_set_timeout_test(members[id])) + return -IPSET_ERR_EXIST; + + members[id] = ip_set_timeout_set(timeout); + + return 0; +} + +static int +bitmap_ip_tdel(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ip *map = set->data; + unsigned long *members = map->members; + u16 id = *(u16 *)value; + int ret = -IPSET_ERR_EXIST; + + if (ip_set_timeout_test(members[id])) + ret = 0; + + members[id] = IPSET_ELEM_UNSET; + return ret; +} + +static int +bitmap_ip_tlist(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct bitmap_ip *map = set->data; + struct nlattr *adt, *nested; + u32 id, first = cb->args[2]; + const unsigned long *members = map->members; + + adt = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!adt) + return -EMSGSIZE; + for (; cb->args[2] < map->elements; cb->args[2]++) { + id = cb->args[2]; + if (!ip_set_timeout_test(members[id])) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (id == first) { + nla_nest_cancel(skb, adt); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id * map->hosts)); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(members[id]))); + ipset_nest_end(skb, nested); + } + ipset_nest_end(skb, adt); + + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, adt); + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static int +bitmap_ip_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + struct bitmap_ip *map = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + u32 ip; + + ip = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); + if (ip < map->first_ip || ip > map->last_ip) + return -IPSET_ERR_BITMAP_RANGE; + + ip = ip_to_id(map, ip); + + return adtfn(set, &ip, map->timeout); +} + +static int +bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + struct bitmap_ip *map = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + u32 timeout = map->timeout; + u32 ip, ip_to, id; + int ret = 0; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + if (ip < map->first_ip || ip > map->last_ip) + return -IPSET_ERR_BITMAP_RANGE; + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(map->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST) { + id = ip_to_id(map, ip); + return adtfn(set, &id, timeout); + } + + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) { + swap(ip, ip_to); + if (ip < map->first_ip) + return -IPSET_ERR_BITMAP_RANGE; + } + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip &= ip_set_hostmask(cidr); + ip_to = ip | ~ip_set_hostmask(cidr); + } else + ip_to = ip; + + if (ip_to > map->last_ip) + return -IPSET_ERR_BITMAP_RANGE; + + for (; !before(ip_to, ip); ip += map->hosts) { + id = ip_to_id(map, ip); + ret = adtfn(set, &id, timeout);; + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static void +bitmap_ip_destroy(struct ip_set *set) +{ + struct bitmap_ip *map = set->data; + + if (with_timeout(map->timeout)) + del_timer_sync(&map->gc); + + ip_set_free(map->members); + kfree(map); + + set->data = NULL; +} + +static void +bitmap_ip_flush(struct ip_set *set) +{ + struct bitmap_ip *map = set->data; + + memset(map->members, 0, map->memsize); +} + +static int +bitmap_ip_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct bitmap_ip *map = set->data; + struct nlattr *nested; + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); + if (map->netmask != 32) + NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + map->memsize)); + if (with_timeout(map->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +static bool +bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct bitmap_ip *x = a->data; + const struct bitmap_ip *y = b->data; + + return x->first_ip == y->first_ip && + x->last_ip == y->last_ip && + x->netmask == y->netmask && + x->timeout == y->timeout; +} + +static const struct ip_set_type_variant bitmap_ip = { + .kadt = bitmap_ip_kadt, + .uadt = bitmap_ip_uadt, + .adt = { + [IPSET_ADD] = bitmap_ip_add, + [IPSET_DEL] = bitmap_ip_del, + [IPSET_TEST] = bitmap_ip_test, + }, + .destroy = bitmap_ip_destroy, + .flush = bitmap_ip_flush, + .head = bitmap_ip_head, + .list = bitmap_ip_list, + .same_set = bitmap_ip_same_set, +}; + +static const struct ip_set_type_variant bitmap_tip = { + .kadt = bitmap_ip_kadt, + .uadt = bitmap_ip_uadt, + .adt = { + [IPSET_ADD] = bitmap_ip_tadd, + [IPSET_DEL] = bitmap_ip_tdel, + [IPSET_TEST] = bitmap_ip_ttest, + }, + .destroy = bitmap_ip_destroy, + .flush = bitmap_ip_flush, + .head = bitmap_ip_head, + .list = bitmap_ip_tlist, + .same_set = bitmap_ip_same_set, +}; + +static void +bitmap_ip_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct bitmap_ip *map = set->data; + unsigned long *table = map->members; + u32 id; + + /* We run parallel with other readers (test element) + * but adding/deleting new entries is locked out */ + read_lock_bh(&set->lock); + for (id = 0; id < map->elements; id++) + if (ip_set_timeout_expired(table[id])) + table[id] = IPSET_ELEM_UNSET; + read_unlock_bh(&set->lock); + + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +static void +bitmap_ip_gc_init(struct ip_set *set) +{ + struct bitmap_ip *map = set->data; + + init_timer(&map->gc); + map->gc.data = (unsigned long) set; + map->gc.function = bitmap_ip_gc; + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +/* Create bitmap:ip type of sets */ + +static bool +init_map_ip(struct ip_set *set, struct bitmap_ip *map, + u32 first_ip, u32 last_ip, + u32 elements, u32 hosts, u8 netmask) +{ + map->members = ip_set_alloc(map->memsize); + if (!map->members) + return false; + map->first_ip = first_ip; + map->last_ip = last_ip; + map->elements = elements; + map->hosts = hosts; + map->netmask = netmask; + map->timeout = IPSET_NO_TIMEOUT; + + set->data = map; + set->family = AF_INET; + + return true; +} + +static int +bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + struct bitmap_ip *map; + u32 first_ip, last_ip, hosts, elements; + u8 netmask = 32; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &first_ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip); + if (ret) + return ret; + if (first_ip > last_ip) { + u32 tmp = first_ip; + + first_ip = last_ip; + last_ip = tmp; + } + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr >= 32) + return -IPSET_ERR_INVALID_CIDR; + last_ip = first_ip | ~ip_set_hostmask(cidr); + } else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_NETMASK]) { + netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); + + if (netmask > 32) + return -IPSET_ERR_INVALID_NETMASK; + + first_ip &= ip_set_hostmask(netmask); + last_ip |= ~ip_set_hostmask(netmask); + } + + if (netmask == 32) { + hosts = 1; + elements = last_ip - first_ip + 1; + } else { + u8 mask_bits; + u32 mask; + + mask = range_to_mask(first_ip, last_ip, &mask_bits); + + if ((!mask && (first_ip || last_ip != 0xFFFFFFFF)) || + netmask <= mask_bits) + return -IPSET_ERR_BITMAP_RANGE; + + pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask); + hosts = 2 << (32 - netmask - 1); + elements = 2 << (netmask - mask_bits - 1); + } + if (elements > IPSET_BITMAP_MAX_RANGE + 1) + return -IPSET_ERR_BITMAP_RANGE_SIZE; + + pr_debug("hosts %u, elements %u\n", hosts, elements); + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return -ENOMEM; + + if (tb[IPSET_ATTR_TIMEOUT]) { + map->memsize = elements * sizeof(unsigned long); + + if (!init_map_ip(set, map, first_ip, last_ip, + elements, hosts, netmask)) { + kfree(map); + return -ENOMEM; + } + + map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + set->variant = &bitmap_tip; + + bitmap_ip_gc_init(set); + } else { + map->memsize = bitmap_bytes(0, elements - 1); + + if (!init_map_ip(set, map, first_ip, last_ip, + elements, hosts, netmask)) { + kfree(map); + return -ENOMEM; + } + + set->variant = &bitmap_ip; + } + return 0; +} + +static struct ip_set_type bitmap_ip_type __read_mostly = { + .name = "bitmap:ip", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP, + .dimension = IPSET_DIM_ONE, + .family = AF_INET, + .revision = 0, + .create = bitmap_ip_create, + .create_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +bitmap_ip_init(void) +{ + return ip_set_type_register(&bitmap_ip_type); +} + +static void __exit +bitmap_ip_fini(void) +{ + ip_set_type_unregister(&bitmap_ip_type); +} + +module_init(bitmap_ip_init); +module_exit(bitmap_ip_fini); diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c new file mode 100644 index 0000000..5e79017 --- /dev/null +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -0,0 +1,652 @@ +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Martin Josefsson <gandalf@wlug.westbo.se> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the bitmap:ip,mac type */ + +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/if_ether.h> +#include <linux/netlink.h> +#include <linux/jiffies.h> +#include <linux/timer.h> +#include <net/netlink.h> + +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_bitmap.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("bitmap:ip,mac type of IP sets"); +MODULE_ALIAS("ip_set_bitmap:ip,mac"); + +enum { + MAC_EMPTY, /* element is not set */ + MAC_FILLED, /* element is set with MAC */ + MAC_UNSET, /* element is set, without MAC */ +}; + +/* Type structure */ +struct bitmap_ipmac { + void *members; /* the set members */ + u32 first_ip; /* host byte order, included in range */ + u32 last_ip; /* host byte order, included in range */ + u32 timeout; /* timeout value */ + struct timer_list gc; /* garbage collector */ + size_t dsize; /* size of element */ +}; + +/* ADT structure for generic function args */ +struct ipmac { + u32 id; /* id in array */ + unsigned char *ether; /* ethernet address */ +}; + +/* Member element without and with timeout */ + +struct ipmac_elem { + unsigned char ether[ETH_ALEN]; + unsigned char match; +} __attribute__ ((aligned)); + +struct ipmac_telem { + unsigned char ether[ETH_ALEN]; + unsigned char match; + unsigned long timeout; +} __attribute__ ((aligned)); + +static inline void * +bitmap_ipmac_elem(const struct bitmap_ipmac *map, u32 id) +{ + return (void *)((char *)map->members + id * map->dsize); +} + +static inline bool +bitmap_timeout(const struct bitmap_ipmac *map, u32 id) +{ + const struct ipmac_telem *elem = bitmap_ipmac_elem(map, id); + + return ip_set_timeout_test(elem->timeout); +} + +static inline bool +bitmap_expired(const struct bitmap_ipmac *map, u32 id) +{ + const struct ipmac_telem *elem = bitmap_ipmac_elem(map, id); + + return ip_set_timeout_expired(elem->timeout); +} + +static inline int +bitmap_ipmac_exist(const struct ipmac_telem *elem) +{ + return elem->match == MAC_UNSET || + (elem->match == MAC_FILLED && + !ip_set_timeout_expired(elem->timeout)); +} + +/* Base variant */ + +static int +bitmap_ipmac_test(struct ip_set *set, void *value, u32 timeout) +{ + const struct bitmap_ipmac *map = set->data; + const struct ipmac *data = value; + const struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id); + + switch (elem->match) { + case MAC_UNSET: + /* Trigger kernel to fill out the ethernet address */ + return -EAGAIN; + case MAC_FILLED: + return data->ether == NULL || + compare_ether_addr(data->ether, elem->ether) == 0; + } + return 0; +} + +static int +bitmap_ipmac_add(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ipmac *map = set->data; + const struct ipmac *data = value; + struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id); + + switch (elem->match) { + case MAC_UNSET: + if (!data->ether) + /* Already added without ethernet address */ + return -IPSET_ERR_EXIST; + /* Fill the MAC address */ + memcpy(elem->ether, data->ether, ETH_ALEN); + elem->match = MAC_FILLED; + break; + case MAC_FILLED: + return -IPSET_ERR_EXIST; + case MAC_EMPTY: + if (data->ether) { + memcpy(elem->ether, data->ether, ETH_ALEN); + elem->match = MAC_FILLED; + } else + elem->match = MAC_UNSET; + } + + return 0; +} + +static int +bitmap_ipmac_del(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ipmac *map = set->data; + const struct ipmac *data = value; + struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id); + + if (elem->match == MAC_EMPTY) + return -IPSET_ERR_EXIST; + + elem->match = MAC_EMPTY; + + return 0; +} + +static int +bitmap_ipmac_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct bitmap_ipmac *map = set->data; + const struct ipmac_elem *elem; + struct nlattr *atd, *nested; + u32 id, first = cb->args[2]; + u32 last = map->last_ip - map->first_ip; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] <= last; cb->args[2]++) { + id = cb->args[2]; + elem = bitmap_ipmac_elem(map, id); + if (elem->match == MAC_EMPTY) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (id == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id)); + if (elem->match == MAC_FILLED) + NLA_PUT(skb, IPSET_ATTR_ETHER, ETH_ALEN, + elem->ether); + ipset_nest_end(skb, nested); + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, atd); + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +/* Timeout variant */ + +static int +bitmap_ipmac_ttest(struct ip_set *set, void *value, u32 timeout) +{ + const struct bitmap_ipmac *map = set->data; + const struct ipmac *data = value; + const struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id); + + switch (elem->match) { + case MAC_UNSET: + /* Trigger kernel to fill out the ethernet address */ + return -EAGAIN; + case MAC_FILLED: + return (data->ether == NULL || + compare_ether_addr(data->ether, elem->ether) == 0) && + !bitmap_expired(map, data->id); + } + return 0; +} + +static int +bitmap_ipmac_tadd(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ipmac *map = set->data; + const struct ipmac *data = value; + struct ipmac_telem *elem = bitmap_ipmac_elem(map, data->id); + + switch (elem->match) { + case MAC_UNSET: + if (!data->ether) + /* Already added without ethernet address */ + return -IPSET_ERR_EXIST; + /* Fill the MAC address and activate the timer */ + memcpy(elem->ether, data->ether, ETH_ALEN); + elem->match = MAC_FILLED; + if (timeout == map->timeout) + /* Timeout was not specified, get stored one */ + timeout = elem->timeout; + elem->timeout = ip_set_timeout_set(timeout); + break; + case MAC_FILLED: + if (!bitmap_expired(map, data->id)) + return -IPSET_ERR_EXIST; + /* Fall through */ + case MAC_EMPTY: + if (data->ether) { + memcpy(elem->ether, data->ether, ETH_ALEN); + elem->match = MAC_FILLED; + } else + elem->match = MAC_UNSET; + /* If MAC is unset yet, we store plain timeout value + * because the timer is not activated yet + * and we can reuse it later when MAC is filled out, + * possibly by the kernel */ + elem->timeout = data->ether ? ip_set_timeout_set(timeout) + : timeout; + break; + } + + return 0; +} + +static int +bitmap_ipmac_tdel(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_ipmac *map = set->data; + const struct ipmac *data = value; + struct ipmac_telem *elem = bitmap_ipmac_elem(map, data->id); + + if (elem->match == MAC_EMPTY || bitmap_expired(map, data->id)) + return -IPSET_ERR_EXIST; + + elem->match = MAC_EMPTY; + + return 0; +} + +static int +bitmap_ipmac_tlist(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct bitmap_ipmac *map = set->data; + const struct ipmac_telem *elem; + struct nlattr *atd, *nested; + u32 id, first = cb->args[2]; + u32 timeout, last = map->last_ip - map->first_ip; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] <= last; cb->args[2]++) { + id = cb->args[2]; + elem = bitmap_ipmac_elem(map, id); + if (!bitmap_ipmac_exist(elem)) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (id == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, + htonl(map->first_ip + id)); + if (elem->match == MAC_FILLED) + NLA_PUT(skb, IPSET_ATTR_ETHER, ETH_ALEN, + elem->ether); + timeout = elem->match == MAC_UNSET ? elem->timeout + : ip_set_timeout_get(elem->timeout); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(timeout)); + ipset_nest_end(skb, nested); + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, atd); + return -EMSGSIZE; +} + +static int +bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + struct bitmap_ipmac *map = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct ipmac data; + + data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); + if (data.id < map->first_ip || data.id > map->last_ip) + return -IPSET_ERR_BITMAP_RANGE; + + /* Backward compatibility: we don't check the second flag */ + if (skb_mac_header(skb) < skb->head || + (skb_mac_header(skb) + ETH_HLEN) > skb->data) + return -EINVAL; + + data.id -= map->first_ip; + data.ether = eth_hdr(skb)->h_source; + + return adtfn(set, &data, map->timeout); +} + +static int +bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct bitmap_ipmac *map = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct ipmac data; + u32 timeout = map->timeout; + int ret = 0; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &data.id); + if (ret) + return ret; + + if (data.id < map->first_ip || data.id > map->last_ip) + return -IPSET_ERR_BITMAP_RANGE; + + if (tb[IPSET_ATTR_ETHER]) + data.ether = nla_data(tb[IPSET_ATTR_ETHER]); + else + data.ether = NULL; + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(map->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + data.id -= map->first_ip; + + ret = adtfn(set, &data, timeout); + + return ip_set_eexist(ret, flags) ? 0 : ret; +} + +static void +bitmap_ipmac_destroy(struct ip_set *set) +{ + struct bitmap_ipmac *map = set->data; + + if (with_timeout(map->timeout)) + del_timer_sync(&map->gc); + + ip_set_free(map->members); + kfree(map); + + set->data = NULL; +} + +static void +bitmap_ipmac_flush(struct ip_set *set) +{ + struct bitmap_ipmac *map = set->data; + + memset(map->members, 0, + (map->last_ip - map->first_ip + 1) * map->dsize); +} + +static int +bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct bitmap_ipmac *map = set->data; + struct nlattr *nested; + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + + (map->last_ip - map->first_ip + 1) * map->dsize)); + if (with_timeout(map->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +static bool +bitmap_ipmac_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct bitmap_ipmac *x = a->data; + const struct bitmap_ipmac *y = b->data; + + return x->first_ip == y->first_ip && + x->last_ip == y->last_ip && + x->timeout == y->timeout; +} + +static const struct ip_set_type_variant bitmap_ipmac = { + .kadt = bitmap_ipmac_kadt, + .uadt = bitmap_ipmac_uadt, + .adt = { + [IPSET_ADD] = bitmap_ipmac_add, + [IPSET_DEL] = bitmap_ipmac_del, + [IPSET_TEST] = bitmap_ipmac_test, + }, + .destroy = bitmap_ipmac_destroy, + .flush = bitmap_ipmac_flush, + .head = bitmap_ipmac_head, + .list = bitmap_ipmac_list, + .same_set = bitmap_ipmac_same_set, +}; + +static const struct ip_set_type_variant bitmap_tipmac = { + .kadt = bitmap_ipmac_kadt, + .uadt = bitmap_ipmac_uadt, + .adt = { + [IPSET_ADD] = bitmap_ipmac_tadd, + [IPSET_DEL] = bitmap_ipmac_tdel, + [IPSET_TEST] = bitmap_ipmac_ttest, + }, + .destroy = bitmap_ipmac_destroy, + .flush = bitmap_ipmac_flush, + .head = bitmap_ipmac_head, + .list = bitmap_ipmac_tlist, + .same_set = bitmap_ipmac_same_set, +}; + +static void +bitmap_ipmac_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct bitmap_ipmac *map = set->data; + struct ipmac_telem *elem; + u32 id, last = map->last_ip - map->first_ip; + + /* We run parallel with other readers (test element) + * but adding/deleting new entries is locked out */ + read_lock_bh(&set->lock); + for (id = 0; id <= last; id++) { + elem = bitmap_ipmac_elem(map, id); + if (elem->match == MAC_FILLED && + ip_set_timeout_expired(elem->timeout)) + elem->match = MAC_EMPTY; + } + read_unlock_bh(&set->lock); + + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +static void +bitmap_ipmac_gc_init(struct ip_set *set) +{ + struct bitmap_ipmac *map = set->data; + + init_timer(&map->gc); + map->gc.data = (unsigned long) set; + map->gc.function = bitmap_ipmac_gc; + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +/* Create bitmap:ip,mac type of sets */ + +static bool +init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, + u32 first_ip, u32 last_ip) +{ + map->members = ip_set_alloc((last_ip - first_ip + 1) * map->dsize); + if (!map->members) + return false; + map->first_ip = first_ip; + map->last_ip = last_ip; + map->timeout = IPSET_NO_TIMEOUT; + + set->data = map; + set->family = AF_INET; + + return true; +} + +static int +bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[], + u32 flags) +{ + u32 first_ip, last_ip, elements; + struct bitmap_ipmac *map; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &first_ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip); + if (ret) + return ret; + if (first_ip > last_ip) { + u32 tmp = first_ip; + + first_ip = last_ip; + last_ip = tmp; + } + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr >= 32) + return -IPSET_ERR_INVALID_CIDR; + last_ip = first_ip | ~ip_set_hostmask(cidr); + } else + return -IPSET_ERR_PROTOCOL; + + elements = last_ip - first_ip + 1; + + if (elements > IPSET_BITMAP_MAX_RANGE + 1) + return -IPSET_ERR_BITMAP_RANGE_SIZE; + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return -ENOMEM; + + if (tb[IPSET_ATTR_TIMEOUT]) { + map->dsize = sizeof(struct ipmac_telem); + + if (!init_map_ipmac(set, map, first_ip, last_ip)) { + kfree(map); + return -ENOMEM; + } + + map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = &bitmap_tipmac; + + bitmap_ipmac_gc_init(set); + } else { + map->dsize = sizeof(struct ipmac_elem); + + if (!init_map_ipmac(set, map, first_ip, last_ip)) { + kfree(map); + return -ENOMEM; + } + set->variant = &bitmap_ipmac; + + } + return 0; +} + +static struct ip_set_type bitmap_ipmac_type = { + .name = "bitmap:ip,mac", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_MAC, + .dimension = IPSET_DIM_TWO, + .family = AF_INET, + .revision = 0, + .create = bitmap_ipmac_create, + .create_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_ETHER] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +bitmap_ipmac_init(void) +{ + return ip_set_type_register(&bitmap_ipmac_type); +} + +static void __exit +bitmap_ipmac_fini(void) +{ + ip_set_type_unregister(&bitmap_ipmac_type); +} + +module_init(bitmap_ipmac_init); +module_exit(bitmap_ipmac_fini); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c new file mode 100644 index 0000000..165f09b --- /dev/null +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -0,0 +1,515 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the bitmap:port type */ + +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/netlink.h> +#include <linux/jiffies.h> +#include <linux/timer.h> +#include <net/netlink.h> + +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_bitmap.h> +#include <linux/netfilter/ipset/ip_set_getport.h> +#define IP_SET_BITMAP_TIMEOUT +#include <linux/netfilter/ipset/ip_set_timeout.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("bitmap:port type of IP sets"); +MODULE_ALIAS("ip_set_bitmap:port"); + +/* Type structure */ +struct bitmap_port { + void *members; /* the set members */ + u16 first_port; /* host byte order, included in range */ + u16 last_port; /* host byte order, included in range */ + size_t memsize; /* members size */ + u32 timeout; /* timeout parameter */ + struct timer_list gc; /* garbage collection */ +}; + +/* Base variant */ + +static int +bitmap_port_test(struct ip_set *set, void *value, u32 timeout) +{ + const struct bitmap_port *map = set->data; + u16 id = *(u16 *)value; + + return !!test_bit(id, map->members); +} + +static int +bitmap_port_add(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_port *map = set->data; + u16 id = *(u16 *)value; + + if (test_and_set_bit(id, map->members)) + return -IPSET_ERR_EXIST; + + return 0; +} + +static int +bitmap_port_del(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_port *map = set->data; + u16 id = *(u16 *)value; + + if (!test_and_clear_bit(id, map->members)) + return -IPSET_ERR_EXIST; + + return 0; +} + +static int +bitmap_port_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct bitmap_port *map = set->data; + struct nlattr *atd, *nested; + u16 id, first = cb->args[2]; + u16 last = map->last_port - map->first_port; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] <= last; cb->args[2]++) { + id = cb->args[2]; + if (!test_bit(id, map->members)) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (id == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, + htons(map->first_port + id)); + ipset_nest_end(skb, nested); + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, atd); + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +/* Timeout variant */ + +static int +bitmap_port_ttest(struct ip_set *set, void *value, u32 timeout) +{ + const struct bitmap_port *map = set->data; + const unsigned long *members = map->members; + u16 id = *(u16 *)value; + + return ip_set_timeout_test(members[id]); +} + +static int +bitmap_port_tadd(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_port *map = set->data; + unsigned long *members = map->members; + u16 id = *(u16 *)value; + + if (ip_set_timeout_test(members[id])) + return -IPSET_ERR_EXIST; + + members[id] = ip_set_timeout_set(timeout); + + return 0; +} + +static int +bitmap_port_tdel(struct ip_set *set, void *value, u32 timeout) +{ + struct bitmap_port *map = set->data; + unsigned long *members = map->members; + u16 id = *(u16 *)value; + int ret = -IPSET_ERR_EXIST; + + if (ip_set_timeout_test(members[id])) + ret = 0; + + members[id] = IPSET_ELEM_UNSET; + return ret; +} + +static int +bitmap_port_tlist(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct bitmap_port *map = set->data; + struct nlattr *adt, *nested; + u16 id, first = cb->args[2]; + u16 last = map->last_port - map->first_port; + const unsigned long *members = map->members; + + adt = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!adt) + return -EMSGSIZE; + for (; cb->args[2] <= last; cb->args[2]++) { + id = cb->args[2]; + if (!ip_set_timeout_test(members[id])) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (id == first) { + nla_nest_cancel(skb, adt); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, + htons(map->first_port + id)); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(members[id]))); + ipset_nest_end(skb, nested); + } + ipset_nest_end(skb, adt); + + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, adt); + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static int +bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + struct bitmap_port *map = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + __be16 __port; + u16 port = 0; + + if (!ip_set_get_ip_port(skb, pf, flags & IPSET_DIM_ONE_SRC, &__port)) + return -EINVAL; + + port = ntohs(__port); + + if (port < map->first_port || port > map->last_port) + return -IPSET_ERR_BITMAP_RANGE; + + port -= map->first_port; + + return adtfn(set, &port, map->timeout); +} + +static int +bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + struct bitmap_port *map = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + u32 timeout = map->timeout; + u32 port; /* wraparound */ + u16 id, port_to; + int ret = 0; + + if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + port = ip_set_get_h16(tb[IPSET_ATTR_PORT]); + if (port < map->first_port || port > map->last_port) + return -IPSET_ERR_BITMAP_RANGE; + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(map->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST) { + id = port - map->first_port; + return adtfn(set, &id, timeout); + } + + if (tb[IPSET_ATTR_PORT_TO]) { + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) { + swap(port, port_to); + if (port < map->first_port) + return -IPSET_ERR_BITMAP_RANGE; + } + } else + port_to = port; + + if (port_to > map->last_port) + return -IPSET_ERR_BITMAP_RANGE; + + for (; port <= port_to; port++) { + id = port - map->first_port; + ret = adtfn(set, &id, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static void +bitmap_port_destroy(struct ip_set *set) +{ + struct bitmap_port *map = set->data; + + if (with_timeout(map->timeout)) + del_timer_sync(&map->gc); + + ip_set_free(map->members); + kfree(map); + + set->data = NULL; +} + +static void +bitmap_port_flush(struct ip_set *set) +{ + struct bitmap_port *map = set->data; + + memset(map->members, 0, map->memsize); +} + +static int +bitmap_port_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct bitmap_port *map = set->data; + struct nlattr *nested; + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port)); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + map->memsize)); + if (with_timeout(map->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +static bool +bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct bitmap_port *x = a->data; + const struct bitmap_port *y = b->data; + + return x->first_port == y->first_port && + x->last_port == y->last_port && + x->timeout == y->timeout; +} + +static const struct ip_set_type_variant bitmap_port = { + .kadt = bitmap_port_kadt, + .uadt = bitmap_port_uadt, + .adt = { + [IPSET_ADD] = bitmap_port_add, + [IPSET_DEL] = bitmap_port_del, + [IPSET_TEST] = bitmap_port_test, + }, + .destroy = bitmap_port_destroy, + .flush = bitmap_port_flush, + .head = bitmap_port_head, + .list = bitmap_port_list, + .same_set = bitmap_port_same_set, +}; + +static const struct ip_set_type_variant bitmap_tport = { + .kadt = bitmap_port_kadt, + .uadt = bitmap_port_uadt, + .adt = { + [IPSET_ADD] = bitmap_port_tadd, + [IPSET_DEL] = bitmap_port_tdel, + [IPSET_TEST] = bitmap_port_ttest, + }, + .destroy = bitmap_port_destroy, + .flush = bitmap_port_flush, + .head = bitmap_port_head, + .list = bitmap_port_tlist, + .same_set = bitmap_port_same_set, +}; + +static void +bitmap_port_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct bitmap_port *map = set->data; + unsigned long *table = map->members; + u32 id; /* wraparound */ + u16 last = map->last_port - map->first_port; + + /* We run parallel with other readers (test element) + * but adding/deleting new entries is locked out */ + read_lock_bh(&set->lock); + for (id = 0; id <= last; id++) + if (ip_set_timeout_expired(table[id])) + table[id] = IPSET_ELEM_UNSET; + read_unlock_bh(&set->lock); + + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +static void +bitmap_port_gc_init(struct ip_set *set) +{ + struct bitmap_port *map = set->data; + + init_timer(&map->gc); + map->gc.data = (unsigned long) set; + map->gc.function = bitmap_port_gc; + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +/* Create bitmap:ip type of sets */ + +static bool +init_map_port(struct ip_set *set, struct bitmap_port *map, + u16 first_port, u16 last_port) +{ + map->members = ip_set_alloc(map->memsize); + if (!map->members) + return false; + map->first_port = first_port; + map->last_port = last_port; + map->timeout = IPSET_NO_TIMEOUT; + + set->data = map; + set->family = AF_UNSPEC; + + return true; +} + +static int +bitmap_port_create(struct ip_set *set, struct nlattr *tb[], + u32 flags) +{ + struct bitmap_port *map; + u16 first_port, last_port; + + if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + first_port = ip_set_get_h16(tb[IPSET_ATTR_PORT]); + last_port = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (first_port > last_port) { + u16 tmp = first_port; + + first_port = last_port; + last_port = tmp; + } + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return -ENOMEM; + + if (tb[IPSET_ATTR_TIMEOUT]) { + map->memsize = (last_port - first_port + 1) + * sizeof(unsigned long); + + if (!init_map_port(set, map, first_port, last_port)) { + kfree(map); + return -ENOMEM; + } + + map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + set->variant = &bitmap_tport; + + bitmap_port_gc_init(set); + } else { + map->memsize = bitmap_bytes(0, last_port - first_port); + pr_debug("memsize: %zu\n", map->memsize); + if (!init_map_port(set, map, first_port, last_port)) { + kfree(map); + return -ENOMEM; + } + + set->variant = &bitmap_port; + } + return 0; +} + +static struct ip_set_type bitmap_port_type = { + .name = "bitmap:port", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_PORT, + .dimension = IPSET_DIM_ONE, + .family = AF_UNSPEC, + .revision = 0, + .create = bitmap_port_create, + .create_policy = { + [IPSET_ATTR_PORT] = { .type = NLA_U16 }, + [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_PORT] = { .type = NLA_U16 }, + [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +bitmap_port_init(void) +{ + return ip_set_type_register(&bitmap_port_type); +} + +static void __exit +bitmap_port_fini(void) +{ + ip_set_type_unregister(&bitmap_port_type); +} + +module_init(bitmap_port_init); +module_exit(bitmap_port_fini); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c new file mode 100644 index 0000000..8b1a54c --- /dev/null +++ b/net/netfilter/ipset/ip_set_core.c @@ -0,0 +1,1671 @@ +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module for IP set management */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <linux/netlink.h> +#include <linux/rculist.h> +#include <linux/version.h> +#include <net/netlink.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/ipset/ip_set.h> + +static LIST_HEAD(ip_set_type_list); /* all registered set types */ +static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ + +static struct ip_set **ip_set_list; /* all individual sets */ +static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */ + +#define STREQ(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0) + +static unsigned int max_sets; + +module_param(max_sets, int, 0600); +MODULE_PARM_DESC(max_sets, "maximal number of sets"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("core IP set support"); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); + +/* + * The set types are implemented in modules and registered set types + * can be found in ip_set_type_list. Adding/deleting types is + * serialized by ip_set_type_mutex. + */ + +static inline void +ip_set_type_lock(void) +{ + mutex_lock(&ip_set_type_mutex); +} + +static inline void +ip_set_type_unlock(void) +{ + mutex_unlock(&ip_set_type_mutex); +} + +/* Register and deregister settype */ + +static struct ip_set_type * +find_set_type(const char *name, u8 family, u8 revision) +{ + struct ip_set_type *type; + + list_for_each_entry_rcu(type, &ip_set_type_list, list) + if (STREQ(type->name, name) && + (type->family == family || type->family == AF_UNSPEC) && + type->revision == revision) + return type; + return NULL; +} + +/* Unlock, try to load a set type module and lock again */ +static int +try_to_load_type(const char *name) +{ + nfnl_unlock(); + pr_debug("try to load ip_set_%s\n", name); + if (request_module("ip_set_%s", name) < 0) { + pr_warning("Can't find ip_set type %s\n", name); + nfnl_lock(); + return -IPSET_ERR_FIND_TYPE; + } + nfnl_lock(); + return -EAGAIN; +} + +/* Find a set type and reference it */ +static int +find_set_type_get(const char *name, u8 family, u8 revision, + struct ip_set_type **found) +{ + rcu_read_lock(); + *found = find_set_type(name, family, revision); + if (*found) { + int err = !try_module_get((*found)->me); + rcu_read_unlock(); + return err ? -EFAULT : 0; + } + rcu_read_unlock(); + + return try_to_load_type(name); +} + +/* Find a given set type by name and family. + * If we succeeded, the supported minimal and maximum revisions are + * filled out. + */ +static int +find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max) +{ + struct ip_set_type *type; + bool found = false; + + *min = *max = 0; + rcu_read_lock(); + list_for_each_entry_rcu(type, &ip_set_type_list, list) + if (STREQ(type->name, name) && + (type->family == family || type->family == AF_UNSPEC)) { + found = true; + if (type->revision < *min) + *min = type->revision; + else if (type->revision > *max) + *max = type->revision; + } + rcu_read_unlock(); + if (found) + return 0; + + return try_to_load_type(name); +} + +#define family_name(f) ((f) == AF_INET ? "inet" : \ + (f) == AF_INET6 ? "inet6" : "any") + +/* Register a set type structure. The type is identified by + * the unique triple of name, family and revision. + */ +int +ip_set_type_register(struct ip_set_type *type) +{ + int ret = 0; + + if (type->protocol != IPSET_PROTOCOL) { + pr_warning("ip_set type %s, family %s, revision %u uses " + "wrong protocol version %u (want %u)\n", + type->name, family_name(type->family), + type->revision, type->protocol, IPSET_PROTOCOL); + return -EINVAL; + } + + ip_set_type_lock(); + if (find_set_type(type->name, type->family, type->revision)) { + /* Duplicate! */ + pr_warning("ip_set type %s, family %s, revision %u " + "already registered!\n", type->name, + family_name(type->family), type->revision); + ret = -EINVAL; + goto unlock; + } + list_add_rcu(&type->list, &ip_set_type_list); + pr_debug("type %s, family %s, revision %u registered.\n", + type->name, family_name(type->family), type->revision); +unlock: + ip_set_type_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(ip_set_type_register); + +/* Unregister a set type. There's a small race with ip_set_create */ +void +ip_set_type_unregister(struct ip_set_type *type) +{ + ip_set_type_lock(); + if (!find_set_type(type->name, type->family, type->revision)) { + pr_warning("ip_set type %s, family %s, revision %u " + "not registered\n", type->name, + family_name(type->family), type->revision); + goto unlock; + } + list_del_rcu(&type->list); + pr_debug("type %s, family %s, revision %u unregistered.\n", + type->name, family_name(type->family), type->revision); +unlock: + ip_set_type_unlock(); + + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(ip_set_type_unregister); + +/* Utility functions */ +void * +ip_set_alloc(size_t size) +{ + void *members = NULL; + + if (size < KMALLOC_MAX_SIZE) + members = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + + if (members) { + pr_debug("%p: allocated with kmalloc\n", members); + return members; + } + + members = vzalloc(size); + if (!members) + return NULL; + pr_debug("%p: allocated with vmalloc\n", members); + + return members; +} +EXPORT_SYMBOL_GPL(ip_set_alloc); + +void +ip_set_free(void *members) +{ + pr_debug("%p: free with %s\n", members, + is_vmalloc_addr(members) ? "vfree" : "kfree"); + if (is_vmalloc_addr(members)) + vfree(members); + else + kfree(members); +} +EXPORT_SYMBOL_GPL(ip_set_free); + +static inline bool +flag_nested(const struct nlattr *nla) +{ + return nla->nla_type & NLA_F_NESTED; +} + +static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = { + [IPSET_ATTR_IPADDR_IPV4] = { .type = NLA_U32 }, + [IPSET_ATTR_IPADDR_IPV6] = { .type = NLA_BINARY, + .len = sizeof(struct in6_addr) }, +}; + +int +ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr) +{ + struct nlattr *tb[IPSET_ATTR_IPADDR_MAX+1]; + + if (unlikely(!flag_nested(nla))) + return -IPSET_ERR_PROTOCOL; + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy)) + return -IPSET_ERR_PROTOCOL; + if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4))) + return -IPSET_ERR_PROTOCOL; + + *ipaddr = nla_get_be32(tb[IPSET_ATTR_IPADDR_IPV4]); + return 0; +} +EXPORT_SYMBOL_GPL(ip_set_get_ipaddr4); + +int +ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) +{ + struct nlattr *tb[IPSET_ATTR_IPADDR_MAX+1]; + + if (unlikely(!flag_nested(nla))) + return -IPSET_ERR_PROTOCOL; + + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy)) + return -IPSET_ERR_PROTOCOL; + if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6))) + return -IPSET_ERR_PROTOCOL; + + memcpy(ipaddr, nla_data(tb[IPSET_ATTR_IPADDR_IPV6]), + sizeof(struct in6_addr)); + return 0; +} +EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); + +/* + * Creating/destroying/renaming/swapping affect the existence and + * the properties of a set. All of these can be executed from userspace + * only and serialized by the nfnl mutex indirectly from nfnetlink. + * + * Sets are identified by their index in ip_set_list and the index + * is used by the external references (set/SET netfilter modules). + * + * The set behind an index may change by swapping only, from userspace. + */ + +static inline void +__ip_set_get(ip_set_id_t index) +{ + atomic_inc(&ip_set_list[index]->ref); +} + +static inline void +__ip_set_put(ip_set_id_t index) +{ + atomic_dec(&ip_set_list[index]->ref); +} + +/* + * Add, del and test set entries from kernel. + * + * The set behind the index must exist and must be referenced + * so it can't be destroyed (or changed) under our foot. + */ + +int +ip_set_test(ip_set_id_t index, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags) +{ + struct ip_set *set = ip_set_list[index]; + int ret = 0; + + BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + pr_debug("set %s, index %u\n", set->name, index); + + if (dim < set->type->dimension || + !(family == set->family || set->family == AF_UNSPEC)) + return 0; + + read_lock_bh(&set->lock); + ret = set->variant->kadt(set, skb, IPSET_TEST, family, dim, flags); + read_unlock_bh(&set->lock); + + if (ret == -EAGAIN) { + /* Type requests element to be completed */ + pr_debug("element must be competed, ADD is triggered\n"); + write_lock_bh(&set->lock); + set->variant->kadt(set, skb, IPSET_ADD, family, dim, flags); + write_unlock_bh(&set->lock); + ret = 1; + } + + /* Convert error codes to nomatch */ + return (ret < 0 ? 0 : ret); +} +EXPORT_SYMBOL_GPL(ip_set_test); + +int +ip_set_add(ip_set_id_t index, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags) +{ + struct ip_set *set = ip_set_list[index]; + int ret; + + BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + pr_debug("set %s, index %u\n", set->name, index); + + if (dim < set->type->dimension || + !(family == set->family || set->family == AF_UNSPEC)) + return 0; + + write_lock_bh(&set->lock); + ret = set->variant->kadt(set, skb, IPSET_ADD, family, dim, flags); + write_unlock_bh(&set->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(ip_set_add); + +int +ip_set_del(ip_set_id_t index, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags) +{ + struct ip_set *set = ip_set_list[index]; + int ret = 0; + + BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + pr_debug("set %s, index %u\n", set->name, index); + + if (dim < set->type->dimension || + !(family == set->family || set->family == AF_UNSPEC)) + return 0; + + write_lock_bh(&set->lock); + ret = set->variant->kadt(set, skb, IPSET_DEL, family, dim, flags); + write_unlock_bh(&set->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(ip_set_del); + +/* + * Find set by name, reference it once. The reference makes sure the + * thing pointed to, does not go away under our feet. + * + * The nfnl mutex must already be activated. + */ +ip_set_id_t +ip_set_get_byname(const char *name, struct ip_set **set) +{ + ip_set_id_t i, index = IPSET_INVALID_ID; + struct ip_set *s; + + for (i = 0; i < ip_set_max; i++) { + s = ip_set_list[i]; + if (s != NULL && STREQ(s->name, name)) { + __ip_set_get(i); + index = i; + *set = s; + } + } + + return index; +} +EXPORT_SYMBOL_GPL(ip_set_get_byname); + +/* + * If the given set pointer points to a valid set, decrement + * reference count by 1. The caller shall not assume the index + * to be valid, after calling this function. + * + * The nfnl mutex must already be activated. + */ +void +ip_set_put_byindex(ip_set_id_t index) +{ + if (ip_set_list[index] != NULL) { + BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); + __ip_set_put(index); + } +} +EXPORT_SYMBOL_GPL(ip_set_put_byindex); + +/* + * Get the name of a set behind a set index. + * We assume the set is referenced, so it does exist and + * can't be destroyed. The set cannot be renamed due to + * the referencing either. + * + * The nfnl mutex must already be activated. + */ +const char * +ip_set_name_byindex(ip_set_id_t index) +{ + const struct ip_set *set = ip_set_list[index]; + + BUG_ON(set == NULL); + BUG_ON(atomic_read(&set->ref) == 0); + + /* Referenced, so it's safe */ + return set->name; +} +EXPORT_SYMBOL_GPL(ip_set_name_byindex); + +/* + * Routines to call by external subsystems, which do not + * call nfnl_lock for us. + */ + +/* + * Find set by name, reference it once. The reference makes sure the + * thing pointed to, does not go away under our feet. + * + * The nfnl mutex is used in the function. + */ +ip_set_id_t +ip_set_nfnl_get(const char *name) +{ + struct ip_set *s; + ip_set_id_t index; + + nfnl_lock(); + index = ip_set_get_byname(name, &s); + nfnl_unlock(); + + return index; +} +EXPORT_SYMBOL_GPL(ip_set_nfnl_get); + +/* + * Find set by index, reference it once. The reference makes sure the + * thing pointed to, does not go away under our feet. + * + * The nfnl mutex is used in the function. + */ +ip_set_id_t +ip_set_nfnl_get_byindex(ip_set_id_t index) +{ + if (index > ip_set_max) + return IPSET_INVALID_ID; + + nfnl_lock(); + if (ip_set_list[index]) + __ip_set_get(index); + else + index = IPSET_INVALID_ID; + nfnl_unlock(); + + return index; +} +EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex); + +/* + * If the given set pointer points to a valid set, decrement + * reference count by 1. The caller shall not assume the index + * to be valid, after calling this function. + * + * The nfnl mutex is used in the function. + */ +void +ip_set_nfnl_put(ip_set_id_t index) +{ + nfnl_lock(); + if (ip_set_list[index] != NULL) { + BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); + __ip_set_put(index); + } + nfnl_unlock(); +} +EXPORT_SYMBOL_GPL(ip_set_nfnl_put); + +/* + * Communication protocol with userspace over netlink. + * + * We already locked by nfnl_lock. + */ + +static inline bool +protocol_failed(const struct nlattr * const tb[]) +{ + return !tb[IPSET_ATTR_PROTOCOL] || + nla_get_u8(tb[IPSET_ATTR_PROTOCOL]) != IPSET_PROTOCOL; +} + +static inline u32 +flag_exist(const struct nlmsghdr *nlh) +{ + return nlh->nlmsg_flags & NLM_F_EXCL ? 0 : IPSET_FLAG_EXIST; +} + +static struct nlmsghdr * +start_msg(struct sk_buff *skb, u32 pid, u32 seq, unsigned int flags, + enum ipset_cmd cmd) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + + nlh = nlmsg_put(skb, pid, seq, cmd | (NFNL_SUBSYS_IPSET << 8), + sizeof(*nfmsg), flags); + if (nlh == NULL) + return NULL; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_INET; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + return nlh; +} + +/* Create a set */ + +static const struct nla_policy ip_set_create_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_TYPENAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1}, + [IPSET_ATTR_REVISION] = { .type = NLA_U8 }, + [IPSET_ATTR_FAMILY] = { .type = NLA_U8 }, + [IPSET_ATTR_DATA] = { .type = NLA_NESTED }, +}; + +static ip_set_id_t +find_set_id(const char *name) +{ + ip_set_id_t i, index = IPSET_INVALID_ID; + const struct ip_set *set; + + for (i = 0; index == IPSET_INVALID_ID && i < ip_set_max; i++) { + set = ip_set_list[i]; + if (set != NULL && STREQ(set->name, name)) + index = i; + } + return index; +} + +static inline struct ip_set * +find_set(const char *name) +{ + ip_set_id_t index = find_set_id(name); + + return index == IPSET_INVALID_ID ? NULL : ip_set_list[index]; +} + +static int +find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set) +{ + ip_set_id_t i; + + *index = IPSET_INVALID_ID; + for (i = 0; i < ip_set_max; i++) { + if (ip_set_list[i] == NULL) { + if (*index == IPSET_INVALID_ID) + *index = i; + } else if (STREQ(name, ip_set_list[i]->name)) { + /* Name clash */ + *set = ip_set_list[i]; + return -EEXIST; + } + } + if (*index == IPSET_INVALID_ID) + /* No free slot remained */ + return -IPSET_ERR_MAX_SETS; + return 0; +} + +static int +ip_set_create(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct ip_set *set, *clash; + ip_set_id_t index = IPSET_INVALID_ID; + struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {}; + const char *name, *typename; + u8 family, revision; + u32 flags = flag_exist(nlh); + int ret = 0; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL || + attr[IPSET_ATTR_TYPENAME] == NULL || + attr[IPSET_ATTR_REVISION] == NULL || + attr[IPSET_ATTR_FAMILY] == NULL || + (attr[IPSET_ATTR_DATA] != NULL && + !flag_nested(attr[IPSET_ATTR_DATA])))) + return -IPSET_ERR_PROTOCOL; + + name = nla_data(attr[IPSET_ATTR_SETNAME]); + typename = nla_data(attr[IPSET_ATTR_TYPENAME]); + family = nla_get_u8(attr[IPSET_ATTR_FAMILY]); + revision = nla_get_u8(attr[IPSET_ATTR_REVISION]); + pr_debug("setname: %s, typename: %s, family: %s, revision: %u\n", + name, typename, family_name(family), revision); + + /* + * First, and without any locks, allocate and initialize + * a normal base set structure. + */ + set = kzalloc(sizeof(struct ip_set), GFP_KERNEL); + if (!set) + return -ENOMEM; + rwlock_init(&set->lock); + strlcpy(set->name, name, IPSET_MAXNAMELEN); + atomic_set(&set->ref, 0); + set->family = family; + + /* + * Next, check that we know the type, and take + * a reference on the type, to make sure it stays available + * while constructing our new set. + * + * After referencing the type, we try to create the type + * specific part of the set without holding any locks. + */ + ret = find_set_type_get(typename, family, revision, &(set->type)); + if (ret) + goto out; + + /* + * Without holding any locks, create private part. + */ + if (attr[IPSET_ATTR_DATA] && + nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], + set->type->create_policy)) { + ret = -IPSET_ERR_PROTOCOL; + goto put_out; + } + + ret = set->type->create(set, tb, flags); + if (ret != 0) + goto put_out; + + /* BTW, ret==0 here. */ + + /* + * Here, we have a valid, constructed set and we are protected + * by nfnl_lock. Find the first free index in ip_set_list and + * check clashing. + */ + if ((ret = find_free_id(set->name, &index, &clash)) != 0) { + /* If this is the same set and requested, ignore error */ + if (ret == -EEXIST && + (flags & IPSET_FLAG_EXIST) && + STREQ(set->type->name, clash->type->name) && + set->type->family == clash->type->family && + set->type->revision == clash->type->revision && + set->variant->same_set(set, clash)) + ret = 0; + goto cleanup; + } + + /* + * Finally! Add our shiny new set to the list, and be done. + */ + pr_debug("create: '%s' created with index %u!\n", set->name, index); + ip_set_list[index] = set; + + return ret; + +cleanup: + set->variant->destroy(set); +put_out: + module_put(set->type->me); +out: + kfree(set); + return ret; +} + +/* Destroy sets */ + +static const struct nla_policy +ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, +}; + +static void +ip_set_destroy_set(ip_set_id_t index) +{ + struct ip_set *set = ip_set_list[index]; + + pr_debug("set: %s\n", set->name); + ip_set_list[index] = NULL; + + /* Must call it without holding any lock */ + set->variant->destroy(set); + module_put(set->type->me); + kfree(set); +} + +static int +ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + ip_set_id_t i; + + if (unlikely(protocol_failed(attr))) + return -IPSET_ERR_PROTOCOL; + + /* References are protected by the nfnl mutex */ + if (!attr[IPSET_ATTR_SETNAME]) { + for (i = 0; i < ip_set_max; i++) { + if (ip_set_list[i] != NULL && + (atomic_read(&ip_set_list[i]->ref))) + return -IPSET_ERR_BUSY; + } + for (i = 0; i < ip_set_max; i++) { + if (ip_set_list[i] != NULL) + ip_set_destroy_set(i); + } + } else { + i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); + if (i == IPSET_INVALID_ID) + return -ENOENT; + else if (atomic_read(&ip_set_list[i]->ref)) + return -IPSET_ERR_BUSY; + + ip_set_destroy_set(i); + } + return 0; +} + +/* Flush sets */ + +static void +ip_set_flush_set(struct ip_set *set) +{ + pr_debug("set: %s\n", set->name); + + write_lock_bh(&set->lock); + set->variant->flush(set); + write_unlock_bh(&set->lock); +} + +static int +ip_set_flush(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + ip_set_id_t i; + + if (unlikely(protocol_failed(attr))) + return -EPROTO; + + if (!attr[IPSET_ATTR_SETNAME]) { + for (i = 0; i < ip_set_max; i++) + if (ip_set_list[i] != NULL) + ip_set_flush_set(ip_set_list[i]); + } else { + i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); + if (i == IPSET_INVALID_ID) + return -ENOENT; + + ip_set_flush_set(ip_set_list[i]); + } + + return 0; +} + +/* Rename a set */ + +static const struct nla_policy +ip_set_setname2_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_SETNAME2] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, +}; + +static int +ip_set_rename(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct ip_set *set; + const char *name2; + ip_set_id_t i; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL || + attr[IPSET_ATTR_SETNAME2] == NULL)) + return -IPSET_ERR_PROTOCOL; + + set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); + if (set == NULL) + return -ENOENT; + if (atomic_read(&set->ref) != 0) + return -IPSET_ERR_REFERENCED; + + name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); + for (i = 0; i < ip_set_max; i++) { + if (ip_set_list[i] != NULL && + STREQ(ip_set_list[i]->name, name2)) + return -IPSET_ERR_EXIST_SETNAME2; + } + strncpy(set->name, name2, IPSET_MAXNAMELEN); + + return 0; +} + +/* Swap two sets so that name/index points to the other. + * References and set names are also swapped. + * + * We are protected by the nfnl mutex and references are + * manipulated only by holding the mutex. The kernel interfaces + * do not hold the mutex but the pointer settings are atomic + * so the ip_set_list always contains valid pointers to the sets. + */ + +static int +ip_set_swap(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct ip_set *from, *to; + ip_set_id_t from_id, to_id; + char from_name[IPSET_MAXNAMELEN]; + u32 from_ref; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL || + attr[IPSET_ATTR_SETNAME2] == NULL)) + return -IPSET_ERR_PROTOCOL; + + from_id = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); + if (from_id == IPSET_INVALID_ID) + return -ENOENT; + + to_id = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME2])); + if (to_id == IPSET_INVALID_ID) + return -IPSET_ERR_EXIST_SETNAME2; + + from = ip_set_list[from_id]; + to = ip_set_list[to_id]; + + /* Features must not change. + * Not an artifical restriction anymore, as we must prevent + * possible loops created by swapping in setlist type of sets. */ + if (!(from->type->features == to->type->features && + from->type->family == to->type->family)) + return -IPSET_ERR_TYPE_MISMATCH; + + /* No magic here: ref munging protected by the nfnl_lock */ + strncpy(from_name, from->name, IPSET_MAXNAMELEN); + from_ref = atomic_read(&from->ref); + + strncpy(from->name, to->name, IPSET_MAXNAMELEN); + atomic_set(&from->ref, atomic_read(&to->ref)); + strncpy(to->name, from_name, IPSET_MAXNAMELEN); + atomic_set(&to->ref, from_ref); + + ip_set_list[from_id] = to; + ip_set_list[to_id] = from; + + return 0; +} + +/* List/save set data */ + +#define DUMP_INIT 0L +#define DUMP_ALL 1L +#define DUMP_ONE 2L +#define DUMP_LAST 3L + +static int +ip_set_dump_done(struct netlink_callback *cb) +{ + if (cb->args[2]) { + pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name); + __ip_set_put((ip_set_id_t) cb->args[1]); + } + return 0; +} + +static inline void +dump_attrs(struct nlmsghdr *nlh) +{ + const struct nlattr *attr; + int rem; + + pr_debug("dump nlmsg\n"); + nlmsg_for_each_attr(attr, nlh, sizeof(struct nfgenmsg), rem) { + pr_debug("type: %u, len %u\n", nla_type(attr), attr->nla_len); + } +} + +static int +dump_init(struct netlink_callback *cb) +{ + struct nlmsghdr *nlh = nlmsg_hdr(cb->skb); + int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg)); + struct nlattr *cda[IPSET_ATTR_CMD_MAX+1]; + struct nlattr *attr = (void *)nlh + min_len; + ip_set_id_t index; + + /* Second pass, so parser can't fail */ + nla_parse(cda, IPSET_ATTR_CMD_MAX, + attr, nlh->nlmsg_len - min_len, ip_set_setname_policy); + + /* cb->args[0] : dump single set/all sets + * [1] : set index + * [..]: type specific + */ + + if (!cda[IPSET_ATTR_SETNAME]) { + cb->args[0] = DUMP_ALL; + return 0; + } + + index = find_set_id(nla_data(cda[IPSET_ATTR_SETNAME])); + if (index == IPSET_INVALID_ID) + return -ENOENT; + + cb->args[0] = DUMP_ONE; + cb->args[1] = index; + return 0; +} + +static int +ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) +{ + ip_set_id_t index = IPSET_INVALID_ID, max; + struct ip_set *set = NULL; + struct nlmsghdr *nlh = NULL; + unsigned int flags = NETLINK_CB(cb->skb).pid ? NLM_F_MULTI : 0; + int ret = 0; + + if (cb->args[0] == DUMP_INIT) { + ret = dump_init(cb); + if (ret < 0) { + nlh = nlmsg_hdr(cb->skb); + /* We have to create and send the error message + * manually :-( */ + if (nlh->nlmsg_flags & NLM_F_ACK) + netlink_ack(cb->skb, nlh, ret); + return ret; + } + } + + if (cb->args[1] >= ip_set_max) + goto out; + + pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); + max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max; + for (; cb->args[1] < max; cb->args[1]++) { + index = (ip_set_id_t) cb->args[1]; + set = ip_set_list[index]; + if (set == NULL) { + if (cb->args[0] == DUMP_ONE) { + ret = -ENOENT; + goto out; + } + continue; + } + /* When dumping all sets, we must dump "sorted" + * so that lists (unions of sets) are dumped last. + */ + if (cb->args[0] != DUMP_ONE && + !((cb->args[0] == DUMP_ALL) ^ + (set->type->features & IPSET_DUMP_LAST))) + continue; + pr_debug("List set: %s\n", set->name); + if (!cb->args[2]) { + /* Start listing: make sure set won't be destroyed */ + pr_debug("reference set\n"); + __ip_set_get(index); + } + nlh = start_msg(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, flags, + IPSET_CMD_LIST); + if (!nlh) { + ret = -EMSGSIZE; + goto release_refcount; + } + NLA_PUT_U8(skb, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); + NLA_PUT_STRING(skb, IPSET_ATTR_SETNAME, set->name); + switch (cb->args[2]) { + case 0: + /* Core header data */ + NLA_PUT_STRING(skb, IPSET_ATTR_TYPENAME, + set->type->name); + NLA_PUT_U8(skb, IPSET_ATTR_FAMILY, + set->family); + NLA_PUT_U8(skb, IPSET_ATTR_REVISION, + set->type->revision); + ret = set->variant->head(set, skb); + if (ret < 0) + goto release_refcount; + /* Fall through and add elements */ + default: + read_lock_bh(&set->lock); + ret = set->variant->list(set, skb, cb); + read_unlock_bh(&set->lock); + if (!cb->args[2]) { + /* Set is done, proceed with next one */ + if (cb->args[0] == DUMP_ONE) + cb->args[1] = IPSET_INVALID_ID; + else + cb->args[1]++; + } + goto release_refcount; + } + } + goto out; + +nla_put_failure: + ret = -EFAULT; +release_refcount: + /* If there was an error or set is done, release set */ + if (ret || !cb->args[2]) { + pr_debug("release set %s\n", ip_set_list[index]->name); + __ip_set_put(index); + } + + /* If we dump all sets, continue with dumping last ones */ + if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2]) + cb->args[0] = DUMP_LAST; + +out: + if (nlh) { + nlmsg_end(skb, nlh); + pr_debug("nlmsg_len: %u\n", nlh->nlmsg_len); + dump_attrs(nlh); + } + + return ret < 0 ? ret : skb->len; +} + +static int +ip_set_dump(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + if (unlikely(protocol_failed(attr))) + return -IPSET_ERR_PROTOCOL; + + return netlink_dump_start(ctnl, skb, nlh, + ip_set_dump_start, + ip_set_dump_done); +} + +/* Add, del and test */ + +static const struct nla_policy ip_set_adt_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + [IPSET_ATTR_DATA] = { .type = NLA_NESTED }, + [IPSET_ATTR_ADT] = { .type = NLA_NESTED }, +}; + +static int +call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, + struct nlattr *tb[], enum ipset_adt adt, + u32 flags, bool use_lineno) +{ + int ret, retried = 0; + u32 lineno = 0; + bool eexist = flags & IPSET_FLAG_EXIST; + + do { + write_lock_bh(&set->lock); + ret = set->variant->uadt(set, tb, adt, &lineno, flags); + write_unlock_bh(&set->lock); + } while (ret == -EAGAIN && + set->variant->resize && + (ret = set->variant->resize(set, retried++)) == 0); + + if (!ret || (ret == -IPSET_ERR_EXIST && eexist)) + return 0; + if (lineno && use_lineno) { + /* Error in restore/batch mode: send back lineno */ + struct nlmsghdr *rep, *nlh = nlmsg_hdr(skb); + struct sk_buff *skb2; + struct nlmsgerr *errmsg; + size_t payload = sizeof(*errmsg) + nlmsg_len(nlh); + int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg)); + struct nlattr *cda[IPSET_ATTR_CMD_MAX+1]; + struct nlattr *cmdattr; + u32 *errline; + + skb2 = nlmsg_new(payload, GFP_KERNEL); + if (skb2 == NULL) + return -ENOMEM; + rep = __nlmsg_put(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, NLMSG_ERROR, payload, 0); + errmsg = nlmsg_data(rep); + errmsg->error = ret; + memcpy(&errmsg->msg, nlh, nlh->nlmsg_len); + cmdattr = (void *)&errmsg->msg + min_len; + + nla_parse(cda, IPSET_ATTR_CMD_MAX, + cmdattr, nlh->nlmsg_len - min_len, + ip_set_adt_policy); + + errline = nla_data(cda[IPSET_ATTR_LINENO]); + + *errline = lineno; + + netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + /* Signal netlink not to send its ACK/errmsg. */ + return -EINTR; + } + + return ret; +} + +static int +ip_set_uadd(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct ip_set *set; + struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {}; + const struct nlattr *nla; + u32 flags = flag_exist(nlh); + bool use_lineno; + int ret = 0; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL || + !((attr[IPSET_ATTR_DATA] != NULL) ^ + (attr[IPSET_ATTR_ADT] != NULL)) || + (attr[IPSET_ATTR_DATA] != NULL && + !flag_nested(attr[IPSET_ATTR_DATA])) || + (attr[IPSET_ATTR_ADT] != NULL && + (!flag_nested(attr[IPSET_ATTR_ADT]) || + attr[IPSET_ATTR_LINENO] == NULL)))) + return -IPSET_ERR_PROTOCOL; + + set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); + if (set == NULL) + return -ENOENT; + + use_lineno = !!attr[IPSET_ATTR_LINENO]; + if (attr[IPSET_ATTR_DATA]) { + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, + attr[IPSET_ATTR_DATA], + set->type->adt_policy)) + return -IPSET_ERR_PROTOCOL; + ret = call_ad(ctnl, skb, set, tb, IPSET_ADD, flags, + use_lineno); + } else { + int nla_rem; + + nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) { + memset(tb, 0, sizeof(tb)); + if (nla_type(nla) != IPSET_ATTR_DATA || + !flag_nested(nla) || + nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, + set->type->adt_policy)) + return -IPSET_ERR_PROTOCOL; + ret = call_ad(ctnl, skb, set, tb, IPSET_ADD, + flags, use_lineno); + if (ret < 0) + return ret; + } + } + return ret; +} + +static int +ip_set_udel(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct ip_set *set; + struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {}; + const struct nlattr *nla; + u32 flags = flag_exist(nlh); + bool use_lineno; + int ret = 0; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL || + !((attr[IPSET_ATTR_DATA] != NULL) ^ + (attr[IPSET_ATTR_ADT] != NULL)) || + (attr[IPSET_ATTR_DATA] != NULL && + !flag_nested(attr[IPSET_ATTR_DATA])) || + (attr[IPSET_ATTR_ADT] != NULL && + (!flag_nested(attr[IPSET_ATTR_ADT]) || + attr[IPSET_ATTR_LINENO] == NULL)))) + return -IPSET_ERR_PROTOCOL; + + set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); + if (set == NULL) + return -ENOENT; + + use_lineno = !!attr[IPSET_ATTR_LINENO]; + if (attr[IPSET_ATTR_DATA]) { + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, + attr[IPSET_ATTR_DATA], + set->type->adt_policy)) + return -IPSET_ERR_PROTOCOL; + ret = call_ad(ctnl, skb, set, tb, IPSET_DEL, flags, + use_lineno); + } else { + int nla_rem; + + nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) { + memset(tb, 0, sizeof(*tb)); + if (nla_type(nla) != IPSET_ATTR_DATA || + !flag_nested(nla) || + nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, + set->type->adt_policy)) + return -IPSET_ERR_PROTOCOL; + ret = call_ad(ctnl, skb, set, tb, IPSET_DEL, + flags, use_lineno); + if (ret < 0) + return ret; + } + } + return ret; +} + +static int +ip_set_utest(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct ip_set *set; + struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {}; + int ret = 0; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL || + attr[IPSET_ATTR_DATA] == NULL || + !flag_nested(attr[IPSET_ATTR_DATA]))) + return -IPSET_ERR_PROTOCOL; + + set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); + if (set == NULL) + return -ENOENT; + + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], + set->type->adt_policy)) + return -IPSET_ERR_PROTOCOL; + + read_lock_bh(&set->lock); + ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0); + read_unlock_bh(&set->lock); + /* Userspace can't trigger element to be re-added */ + if (ret == -EAGAIN) + ret = 1; + + return ret < 0 ? ret : ret > 0 ? 0 : -IPSET_ERR_EXIST; +} + +/* Get headed data of a set */ + +static int +ip_set_header(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + const struct ip_set *set; + struct sk_buff *skb2; + struct nlmsghdr *nlh2; + ip_set_id_t index; + int ret = 0; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_SETNAME] == NULL)) + return -IPSET_ERR_PROTOCOL; + + index = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); + if (index == IPSET_INVALID_ID) + return -ENOENT; + set = ip_set_list[index]; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) + return -ENOMEM; + + nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + IPSET_CMD_HEADER); + if (!nlh2) + goto nlmsg_failure; + NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); + NLA_PUT_STRING(skb2, IPSET_ATTR_SETNAME, set->name); + NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, set->type->name); + NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, set->family); + NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, set->type->revision); + nlmsg_end(skb2, nlh2); + + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (ret < 0) + return ret; + + return 0; + +nla_put_failure: + nlmsg_cancel(skb2, nlh2); +nlmsg_failure: + kfree_skb(skb2); + return -EMSGSIZE; +} + +/* Get type data */ + +static const struct nla_policy ip_set_type_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_TYPENAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_FAMILY] = { .type = NLA_U8 }, +}; + +static int +ip_set_type(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct sk_buff *skb2; + struct nlmsghdr *nlh2; + u8 family, min, max; + const char *typename; + int ret = 0; + + if (unlikely(protocol_failed(attr) || + attr[IPSET_ATTR_TYPENAME] == NULL || + attr[IPSET_ATTR_FAMILY] == NULL)) + return -IPSET_ERR_PROTOCOL; + + family = nla_get_u8(attr[IPSET_ATTR_FAMILY]); + typename = nla_data(attr[IPSET_ATTR_TYPENAME]); + ret = find_set_type_minmax(typename, family, &min, &max); + if (ret) + return ret; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) + return -ENOMEM; + + nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + IPSET_CMD_TYPE); + if (!nlh2) + goto nlmsg_failure; + NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); + NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, typename); + NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, family); + NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, max); + NLA_PUT_U8(skb2, IPSET_ATTR_REVISION_MIN, min); + nlmsg_end(skb2, nlh2); + + pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (ret < 0) + return ret; + + return 0; + +nla_put_failure: + nlmsg_cancel(skb2, nlh2); +nlmsg_failure: + kfree_skb(skb2); + return -EMSGSIZE; +} + +/* Get protocol version */ + +static const struct nla_policy +ip_set_protocol_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, +}; + +static int +ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + struct sk_buff *skb2; + struct nlmsghdr *nlh2; + int ret = 0; + + if (unlikely(attr[IPSET_ATTR_PROTOCOL] == NULL)) + return -IPSET_ERR_PROTOCOL; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) + return -ENOMEM; + + nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + IPSET_CMD_PROTOCOL); + if (!nlh2) + goto nlmsg_failure; + NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); + nlmsg_end(skb2, nlh2); + + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (ret < 0) + return ret; + + return 0; + +nla_put_failure: + nlmsg_cancel(skb2, nlh2); +nlmsg_failure: + kfree_skb(skb2); + return -EMSGSIZE; +} + +static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { + [IPSET_CMD_CREATE] = { + .call = ip_set_create, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_create_policy, + }, + [IPSET_CMD_DESTROY] = { + .call = ip_set_destroy, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname_policy, + }, + [IPSET_CMD_FLUSH] = { + .call = ip_set_flush, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname_policy, + }, + [IPSET_CMD_RENAME] = { + .call = ip_set_rename, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname2_policy, + }, + [IPSET_CMD_SWAP] = { + .call = ip_set_swap, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname2_policy, + }, + [IPSET_CMD_LIST] = { + .call = ip_set_dump, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname_policy, + }, + [IPSET_CMD_SAVE] = { + .call = ip_set_dump, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname_policy, + }, + [IPSET_CMD_ADD] = { + .call = ip_set_uadd, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_adt_policy, + }, + [IPSET_CMD_DEL] = { + .call = ip_set_udel, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_adt_policy, + }, + [IPSET_CMD_TEST] = { + .call = ip_set_utest, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_adt_policy, + }, + [IPSET_CMD_HEADER] = { + .call = ip_set_header, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_setname_policy, + }, + [IPSET_CMD_TYPE] = { + .call = ip_set_type, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_type_policy, + }, + [IPSET_CMD_PROTOCOL] = { + .call = ip_set_protocol, + .attr_count = IPSET_ATTR_CMD_MAX, + .policy = ip_set_protocol_policy, + }, +}; + +static struct nfnetlink_subsystem ip_set_netlink_subsys __read_mostly = { + .name = "ip_set", + .subsys_id = NFNL_SUBSYS_IPSET, + .cb_count = IPSET_MSG_MAX, + .cb = ip_set_netlink_subsys_cb, +}; + +/* Interface to iptables/ip6tables */ + +static int +ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) +{ + unsigned *op; + void *data; + int copylen = *len, ret = 0; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (optval != SO_IP_SET) + return -EBADF; + if (*len < sizeof(unsigned)) + return -EINVAL; + + data = vmalloc(*len); + if (!data) + return -ENOMEM; + if (copy_from_user(data, user, *len) != 0) { + ret = -EFAULT; + goto done; + } + op = (unsigned *) data; + + if (*op < IP_SET_OP_VERSION) { + /* Check the version at the beginning of operations */ + struct ip_set_req_version *req_version = data; + if (req_version->version != IPSET_PROTOCOL) { + ret = -EPROTO; + goto done; + } + } + + switch (*op) { + case IP_SET_OP_VERSION: { + struct ip_set_req_version *req_version = data; + + if (*len != sizeof(struct ip_set_req_version)) { + ret = -EINVAL; + goto done; + } + + req_version->version = IPSET_PROTOCOL; + ret = copy_to_user(user, req_version, + sizeof(struct ip_set_req_version)); + goto done; + } + case IP_SET_OP_GET_BYNAME: { + struct ip_set_req_get_set *req_get = data; + + if (*len != sizeof(struct ip_set_req_get_set)) { + ret = -EINVAL; + goto done; + } + req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0'; + nfnl_lock(); + req_get->set.index = find_set_id(req_get->set.name); + nfnl_unlock(); + goto copy; + } + case IP_SET_OP_GET_BYINDEX: { + struct ip_set_req_get_set *req_get = data; + + if (*len != sizeof(struct ip_set_req_get_set) || + req_get->set.index >= ip_set_max) { + ret = -EINVAL; + goto done; + } + nfnl_lock(); + strncpy(req_get->set.name, + ip_set_list[req_get->set.index] + ? ip_set_list[req_get->set.index]->name : "", + IPSET_MAXNAMELEN); + nfnl_unlock(); + goto copy; + } + default: + ret = -EBADMSG; + goto done; + } /* end of switch(op) */ + +copy: + ret = copy_to_user(user, data, copylen); + +done: + vfree(data); + if (ret > 0) + ret = 0; + return ret; +} + +static struct nf_sockopt_ops so_set __read_mostly = { + .pf = PF_INET, + .get_optmin = SO_IP_SET, + .get_optmax = SO_IP_SET + 1, + .get = &ip_set_sockfn_get, + .owner = THIS_MODULE, +}; + +static int __init +ip_set_init(void) +{ + int ret; + + if (max_sets) + ip_set_max = max_sets; + if (ip_set_max >= IPSET_INVALID_ID) + ip_set_max = IPSET_INVALID_ID - 1; + + ip_set_list = kzalloc(sizeof(struct ip_set *) * ip_set_max, + GFP_KERNEL); + if (!ip_set_list) { + pr_err("ip_set: Unable to create ip_set_list\n"); + return -ENOMEM; + } + + ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); + if (ret != 0) { + pr_err("ip_set: cannot register with nfnetlink.\n"); + kfree(ip_set_list); + return ret; + } + ret = nf_register_sockopt(&so_set); + if (ret != 0) { + pr_err("SO_SET registry failed: %d\n", ret); + nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + kfree(ip_set_list); + return ret; + } + + pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL); + return 0; +} + +static void __exit +ip_set_fini(void) +{ + /* There can't be any existing set */ + nf_unregister_sockopt(&so_set); + nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + kfree(ip_set_list); + pr_debug("these are the famous last words\n"); +} + +module_init(ip_set_init); +module_exit(ip_set_fini); diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c new file mode 100644 index 0000000..8d52272 --- /dev/null +++ b/net/netfilter/ipset/ip_set_getport.c @@ -0,0 +1,141 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Get Layer-4 data from the packets */ + +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/ip.h> +#include <net/ipv6.h> + +#include <linux/netfilter/ipset/ip_set_getport.h> + +/* We must handle non-linear skbs */ +static bool +get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, + bool src, __be16 *port, u8 *proto) +{ + switch (protocol) { + case IPPROTO_TCP: { + struct tcphdr _tcph; + const struct tcphdr *th; + + th = skb_header_pointer(skb, protooff, sizeof(_tcph), &_tcph); + if (th == NULL) + /* No choice either */ + return false; + + *port = src ? th->source : th->dest; + break; + } + case IPPROTO_UDP: { + struct udphdr _udph; + const struct udphdr *uh; + + uh = skb_header_pointer(skb, protooff, sizeof(_udph), &_udph); + if (uh == NULL) + /* No choice either */ + return false; + + *port = src ? uh->source : uh->dest; + break; + } + case IPPROTO_ICMP: { + struct icmphdr _ich; + const struct icmphdr *ic; + + ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich); + if (ic == NULL) + return false; + + *port = (__force __be16)htons((ic->type << 8) | ic->code); + break; + } + case IPPROTO_ICMPV6: { + struct icmp6hdr _ich; + const struct icmp6hdr *ic; + + ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich); + if (ic == NULL) + return false; + + *port = (__force __be16) + htons((ic->icmp6_type << 8) | ic->icmp6_code); + break; + } + default: + break; + } + *proto = protocol; + + return true; +} + +bool +ip_set_get_ip4_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto) +{ + const struct iphdr *iph = ip_hdr(skb); + unsigned int protooff = ip_hdrlen(skb); + int protocol = iph->protocol; + + /* See comments at tcp_match in ip_tables.c */ + if (protocol <= 0 || (ntohs(iph->frag_off) & IP_OFFSET)) + return false; + + return get_port(skb, protocol, protooff, src, port, proto); +} +EXPORT_SYMBOL_GPL(ip_set_get_ip4_port); + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +bool +ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto) +{ + int protoff; + u8 nexthdr; + + nexthdr = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr); + if (protoff < 0) + return false; + + return get_port(skb, nexthdr, protoff, src, port, proto); +} +EXPORT_SYMBOL_GPL(ip_set_get_ip6_port); +#endif + +bool +ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port) +{ + bool ret; + u8 proto; + + switch (pf) { + case AF_INET: + ret = ip_set_get_ip4_port(skb, src, port, &proto); + break; + case AF_INET6: + ret = ip_set_get_ip6_port(skb, src, port, &proto); + break; + default: + return false; + } + if (!ret) + return ret; + switch (proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + return true; + default: + return false; + } +} +EXPORT_SYMBOL_GPL(ip_set_get_ip_port); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c new file mode 100644 index 0000000..43bcce2 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -0,0 +1,464 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:ip type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:ip type of IP sets"); +MODULE_ALIAS("ip_set_hash:ip"); + +/* Type specific function prefix */ +#define TYPE hash_ip + +static bool +hash_ip_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_ip4_same_set hash_ip_same_set +#define hash_ip6_same_set hash_ip_same_set + +/* The type variant functions: IPv4 */ + +/* Member elements without timeout */ +struct hash_ip4_elem { + __be32 ip; +}; + +/* Member elements with timeout support */ +struct hash_ip4_telem { + __be32 ip; + unsigned long timeout; +}; + +static inline bool +hash_ip4_data_equal(const struct hash_ip4_elem *ip1, + const struct hash_ip4_elem *ip2) +{ + return ip1->ip == ip2->ip; +} + +static inline bool +hash_ip4_data_isnull(const struct hash_ip4_elem *elem) +{ + return elem->ip == 0; +} + +static inline void +hash_ip4_data_copy(struct hash_ip4_elem *dst, const struct hash_ip4_elem *src) +{ + dst->ip = src->ip; +} + +/* Zero valued IP addresses cannot be stored */ +static inline void +hash_ip4_data_zero_out(struct hash_ip4_elem *elem) +{ + elem->ip = 0; +} + +static inline bool +hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *data) +{ + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ip4_data_tlist(struct sk_buff *skb, const struct hash_ip4_elem *data) +{ + const struct hash_ip4_telem *tdata = + (const struct hash_ip4_telem *)data; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define IP_SET_HASH_WITH_NETMASK +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + __be32 ip; + + ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &ip); + ip &= ip_set_netmask(h->netmask); + if (ip == 0) + return -EINVAL; + + return adtfn(set, &ip, h->timeout); +} + +static int +hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + u32 ip, ip_to, hosts, timeout = h->timeout; + __be32 nip; + int ret = 0; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ip &= ip_set_hostmask(h->netmask); + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST) { + nip = htonl(ip); + if (nip == 0) + return -IPSET_ERR_HASH_ELEM; + return adtfn(set, &nip, timeout); + } + + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) + swap(ip, ip_to); + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip &= ip_set_hostmask(cidr); + ip_to = ip | ~ip_set_hostmask(cidr); + } else + ip_to = ip; + + hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + + for (; !before(ip_to, ip); ip += hosts) { + nip = htonl(ip); + if (nip == 0) + return -IPSET_ERR_HASH_ELEM; + ret = adtfn(set, &nip, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static bool +hash_ip_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout && + x->netmask == y->netmask; +} + +/* The type variant functions: IPv6 */ + +struct hash_ip6_elem { + union nf_inet_addr ip; +}; + +struct hash_ip6_telem { + union nf_inet_addr ip; + unsigned long timeout; +}; + +static inline bool +hash_ip6_data_equal(const struct hash_ip6_elem *ip1, + const struct hash_ip6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0; +} + +static inline bool +hash_ip6_data_isnull(const struct hash_ip6_elem *elem) +{ + return ipv6_addr_any(&elem->ip.in6); +} + +static inline void +hash_ip6_data_copy(struct hash_ip6_elem *dst, const struct hash_ip6_elem *src) +{ + ipv6_addr_copy(&dst->ip.in6, &src->ip.in6); +} + +static inline void +hash_ip6_data_zero_out(struct hash_ip6_elem *elem) +{ + ipv6_addr_set(&elem->ip.in6, 0, 0, 0, 0); +} + +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + +static bool +hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *data) +{ + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ip6_data_tlist(struct sk_buff *skb, const struct hash_ip6_elem *data) +{ + const struct hash_ip6_telem *e = + (const struct hash_ip6_telem *)data; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + union nf_inet_addr ip; + + ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &ip.in6); + ip6_netmask(&ip, h->netmask); + if (ipv6_addr_any(&ip.in6)) + return -EINVAL; + + return adtfn(set, &ip, h->timeout); +} + +static const struct nla_policy hash_ip6_adt_policy[IPSET_ATTR_ADT_MAX + 1] = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, +}; + +static int +hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + union nf_inet_addr ip; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + tb[IPSET_ATTR_IP_TO] || + tb[IPSET_ATTR_CIDR])) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + ip6_netmask(&ip, h->netmask); + if (ipv6_addr_any(&ip.in6)) + return -IPSET_ERR_HASH_ELEM; + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + ret = adtfn(set, &ip, timeout); + + return ip_set_eexist(ret, flags) ? 0 : ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + u8 netmask, hbits; + struct ip_set_hash *h; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + netmask = set->family == AF_INET ? 32 : 128; + pr_debug("Create set %s with family %s\n", + set->name, set->family == AF_INET ? "inet" : "inet6"); + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + if (tb[IPSET_ATTR_NETMASK]) { + netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); + + if ((set->family == AF_INET && netmask > 32) || + (set->family == AF_INET6 && netmask > 128) || + netmask == 0) + return -IPSET_ERR_INVALID_NETMASK; + } + + h = kzalloc(sizeof(*h), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + h->netmask = netmask; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_ip4_tvariant : &hash_ip6_tvariant; + + if (set->family == AF_INET) + hash_ip4_gc_init(set); + else + hash_ip6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_ip4_variant : &hash_ip6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_ip_type __read_mostly = { + .name = "hash:ip", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP, + .dimension = IPSET_DIM_ONE, + .family = AF_UNSPEC, + .revision = 0, + .create = hash_ip_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_ip_init(void) +{ + return ip_set_type_register(&hash_ip_type); +} + +static void __exit +hash_ip_fini(void) +{ + ip_set_type_unregister(&hash_ip_type); +} + +module_init(hash_ip_init); +module_exit(hash_ip_fini); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c new file mode 100644 index 0000000..adbe787 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -0,0 +1,544 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:ip,port type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_getport.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:ip,port type of IP sets"); +MODULE_ALIAS("ip_set_hash:ip,port"); + +/* Type specific function prefix */ +#define TYPE hash_ipport + +static bool +hash_ipport_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_ipport4_same_set hash_ipport_same_set +#define hash_ipport6_same_set hash_ipport_same_set + +/* The type variant functions: IPv4 */ + +/* Member elements without timeout */ +struct hash_ipport4_elem { + __be32 ip; + __be16 port; + u8 proto; + u8 padding; +}; + +/* Member elements with timeout support */ +struct hash_ipport4_telem { + __be32 ip; + __be16 port; + u8 proto; + u8 padding; + unsigned long timeout; +}; + +static inline bool +hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1, + const struct hash_ipport4_elem *ip2) +{ + return ip1->ip == ip2->ip && + ip1->port == ip2->port && + ip1->proto == ip2->proto; +} + +static inline bool +hash_ipport4_data_isnull(const struct hash_ipport4_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_ipport4_data_copy(struct hash_ipport4_elem *dst, + const struct hash_ipport4_elem *src) +{ + dst->ip = src->ip; + dst->port = src->port; + dst->proto = src->proto; +} + +static inline void +hash_ipport4_data_zero_out(struct hash_ipport4_elem *elem) +{ + elem->proto = 0; +} + +static bool +hash_ipport4_data_list(struct sk_buff *skb, + const struct hash_ipport4_elem *data) +{ + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ipport4_data_tlist(struct sk_buff *skb, + const struct hash_ipport4_elem *data) +{ + const struct hash_ipport4_telem *tdata = + (const struct hash_ipport4_telem *)data; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipport4_elem data = { }; + + if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipport4_elem data = { }; + u32 ip, ip_to, p, port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMP: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || + tb[IPSET_ATTR_PORT_TO])) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ip = ntohl(data.ip); + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) + swap(ip, ip_to); + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip &= ip_set_hostmask(cidr); + ip_to = ip | ~ip_set_hostmask(cidr); + } else + ip_to = ip; + + port = ntohs(data.port); + if (tb[IPSET_ATTR_PORT_TO]) { + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + } else + port_to = port; + + for (; !before(ip_to, ip); ip++) + for (p = port; p <= port_to; p++) { + data.ip = htonl(ip); + data.port = htons(p); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static bool +hash_ipport_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout; +} + +/* The type variant functions: IPv6 */ + +struct hash_ipport6_elem { + union nf_inet_addr ip; + __be16 port; + u8 proto; + u8 padding; +}; + +struct hash_ipport6_telem { + union nf_inet_addr ip; + __be16 port; + u8 proto; + u8 padding; + unsigned long timeout; +}; + +static inline bool +hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1, + const struct hash_ipport6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ip1->port == ip2->port && + ip1->proto == ip2->proto; +} + +static inline bool +hash_ipport6_data_isnull(const struct hash_ipport6_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_ipport6_data_copy(struct hash_ipport6_elem *dst, + const struct hash_ipport6_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_ipport6_data_zero_out(struct hash_ipport6_elem *elem) +{ + elem->proto = 0; +} + +static bool +hash_ipport6_data_list(struct sk_buff *skb, + const struct hash_ipport6_elem *data) +{ + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ipport6_data_tlist(struct sk_buff *skb, + const struct hash_ipport6_elem *data) +{ + const struct hash_ipport6_telem *e = + (const struct hash_ipport6_telem *)data; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipport6_elem data = { }; + + if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipport6_elem data = { }; + u32 port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + tb[IPSET_ATTR_IP_TO] || + tb[IPSET_ATTR_CIDR])) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMPV6: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !tb[IPSET_ATTR_PORT_TO]) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + port = ntohs(data.port); + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + + for (; port <= port_to; port++) { + data.port = htons(port); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_ipport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + struct ip_set_hash *h; + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + u8 hbits; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + h = kzalloc(sizeof(*h), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_ipport4_tvariant : &hash_ipport6_tvariant; + + if (set->family == AF_INET) + hash_ipport4_gc_init(set); + else + hash_ipport6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_ipport4_variant : &hash_ipport6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_ipport_type __read_mostly = { + .name = "hash:ip,port", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, + .dimension = IPSET_DIM_TWO, + .family = AF_UNSPEC, + .revision = 0, + .create = hash_ipport_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_PORT] = { .type = NLA_U16 }, + [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_ipport_init(void) +{ + return ip_set_type_register(&hash_ipport_type); +} + +static void __exit +hash_ipport_fini(void) +{ + ip_set_type_unregister(&hash_ipport_type); +} + +module_init(hash_ipport_init); +module_exit(hash_ipport_fini); diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c new file mode 100644 index 0000000..22e23ab --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -0,0 +1,562 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:ip,port,ip type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_getport.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:ip,port,ip type of IP sets"); +MODULE_ALIAS("ip_set_hash:ip,port,ip"); + +/* Type specific function prefix */ +#define TYPE hash_ipportip + +static bool +hash_ipportip_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_ipportip4_same_set hash_ipportip_same_set +#define hash_ipportip6_same_set hash_ipportip_same_set + +/* The type variant functions: IPv4 */ + +/* Member elements without timeout */ +struct hash_ipportip4_elem { + __be32 ip; + __be32 ip2; + __be16 port; + u8 proto; + u8 padding; +}; + +/* Member elements with timeout support */ +struct hash_ipportip4_telem { + __be32 ip; + __be32 ip2; + __be16 port; + u8 proto; + u8 padding; + unsigned long timeout; +}; + +static inline bool +hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1, + const struct hash_ipportip4_elem *ip2) +{ + return ip1->ip == ip2->ip && + ip1->ip2 == ip2->ip2 && + ip1->port == ip2->port && + ip1->proto == ip2->proto; +} + +static inline bool +hash_ipportip4_data_isnull(const struct hash_ipportip4_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_ipportip4_data_copy(struct hash_ipportip4_elem *dst, + const struct hash_ipportip4_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_ipportip4_data_zero_out(struct hash_ipportip4_elem *elem) +{ + elem->proto = 0; +} + +static bool +hash_ipportip4_data_list(struct sk_buff *skb, + const struct hash_ipportip4_elem *data) +{ + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, data->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ipportip4_data_tlist(struct sk_buff *skb, + const struct hash_ipportip4_elem *data) +{ + const struct hash_ipportip4_telem *tdata = + (const struct hash_ipportip4_telem *)data; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, tdata->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportip4_elem data = { }; + + if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportip4_elem data = { }; + u32 ip, ip_to, p, port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &data.ip2); + if (ret) + return ret; + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMP: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || + tb[IPSET_ATTR_PORT_TO])) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ip = ntohl(data.ip); + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) + swap(ip, ip_to); + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip &= ip_set_hostmask(cidr); + ip_to = ip | ~ip_set_hostmask(cidr); + } else + ip_to = ip; + + port = ntohs(data.port); + if (tb[IPSET_ATTR_PORT_TO]) { + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + } else + port_to = port; + + for (; !before(ip_to, ip); ip++) + for (p = port; p <= port_to; p++) { + data.ip = htonl(ip); + data.port = htons(p); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static bool +hash_ipportip_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout; +} + +/* The type variant functions: IPv6 */ + +struct hash_ipportip6_elem { + union nf_inet_addr ip; + union nf_inet_addr ip2; + __be16 port; + u8 proto; + u8 padding; +}; + +struct hash_ipportip6_telem { + union nf_inet_addr ip; + union nf_inet_addr ip2; + __be16 port; + u8 proto; + u8 padding; + unsigned long timeout; +}; + +static inline bool +hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1, + const struct hash_ipportip6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && + ip1->port == ip2->port && + ip1->proto == ip2->proto; +} + +static inline bool +hash_ipportip6_data_isnull(const struct hash_ipportip6_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_ipportip6_data_copy(struct hash_ipportip6_elem *dst, + const struct hash_ipportip6_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_ipportip6_data_zero_out(struct hash_ipportip6_elem *elem) +{ + elem->proto = 0; +} + +static bool +hash_ipportip6_data_list(struct sk_buff *skb, + const struct hash_ipportip6_elem *data) +{ + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ipportip6_data_tlist(struct sk_buff *skb, + const struct hash_ipportip6_elem *data) +{ + const struct hash_ipportip6_telem *e = + (const struct hash_ipportip6_telem *)data; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportip6_elem data = { }; + + if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportip6_elem data = { }; + u32 port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + tb[IPSET_ATTR_IP_TO] || + tb[IPSET_ATTR_CIDR])) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &data.ip2); + if (ret) + return ret; + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMPV6: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !tb[IPSET_ATTR_PORT_TO]) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + port = ntohs(data.port); + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + + for (; port <= port_to; port++) { + data.port = htons(port); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_ipportip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + struct ip_set_hash *h; + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + u8 hbits; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + h = kzalloc(sizeof(*h), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_ipportip4_tvariant : &hash_ipportip6_tvariant; + + if (set->family == AF_INET) + hash_ipportip4_gc_init(set); + else + hash_ipportip6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_ipportip4_variant : &hash_ipportip6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_ipportip_type __read_mostly = { + .name = "hash:ip,port,ip", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, + .dimension = IPSET_DIM_THREE, + .family = AF_UNSPEC, + .revision = 0, + .create = hash_ipportip_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, + [IPSET_ATTR_PORT] = { .type = NLA_U16 }, + [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_ipportip_init(void) +{ + return ip_set_type_register(&hash_ipportip_type); +} + +static void __exit +hash_ipportip_fini(void) +{ + ip_set_type_unregister(&hash_ipportip_type); +} + +module_init(hash_ipportip_init); +module_exit(hash_ipportip_fini); diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c new file mode 100644 index 0000000..6033e8b --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -0,0 +1,628 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:ip,port,net type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_getport.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:ip,port,net type of IP sets"); +MODULE_ALIAS("ip_set_hash:ip,port,net"); + +/* Type specific function prefix */ +#define TYPE hash_ipportnet + +static bool +hash_ipportnet_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_ipportnet4_same_set hash_ipportnet_same_set +#define hash_ipportnet6_same_set hash_ipportnet_same_set + +/* The type variant functions: IPv4 */ + +/* Member elements without timeout */ +struct hash_ipportnet4_elem { + __be32 ip; + __be32 ip2; + __be16 port; + u8 cidr; + u8 proto; +}; + +/* Member elements with timeout support */ +struct hash_ipportnet4_telem { + __be32 ip; + __be32 ip2; + __be16 port; + u8 cidr; + u8 proto; + unsigned long timeout; +}; + +static inline bool +hash_ipportnet4_data_equal(const struct hash_ipportnet4_elem *ip1, + const struct hash_ipportnet4_elem *ip2) +{ + return ip1->ip == ip2->ip && + ip1->ip2 == ip2->ip2 && + ip1->cidr == ip2->cidr && + ip1->port == ip2->port && + ip1->proto == ip2->proto; +} + +static inline bool +hash_ipportnet4_data_isnull(const struct hash_ipportnet4_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_ipportnet4_data_copy(struct hash_ipportnet4_elem *dst, + const struct hash_ipportnet4_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_ipportnet4_data_netmask(struct hash_ipportnet4_elem *elem, u8 cidr) +{ + elem->ip2 &= ip_set_netmask(cidr); + elem->cidr = cidr; +} + +static inline void +hash_ipportnet4_data_zero_out(struct hash_ipportnet4_elem *elem) +{ + elem->proto = 0; +} + +static bool +hash_ipportnet4_data_list(struct sk_buff *skb, + const struct hash_ipportnet4_elem *data) +{ + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, data->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ipportnet4_data_tlist(struct sk_buff *skb, + const struct hash_ipportnet4_elem *data) +{ + const struct hash_ipportnet4_telem *tdata = + (const struct hash_ipportnet4_telem *)data; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP2, tdata->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define IP_SET_HASH_WITH_PROTO +#define IP_SET_HASH_WITH_NETS + +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportnet4_elem data = + { .cidr = h->nets[0].cidr || HOST_MASK }; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2); + data.ip2 &= ip_set_netmask(data.cidr); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; + u32 ip, ip_to, p, port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &data.ip2); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR2]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); + + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + + data.ip2 &= ip_set_netmask(data.cidr); + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMP: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || + tb[IPSET_ATTR_PORT_TO])) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ip = ntohl(data.ip); + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) + swap(ip, ip_to); + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip &= ip_set_hostmask(cidr); + ip_to = ip | ~ip_set_hostmask(cidr); + } else + ip_to = ip; + + port = ntohs(data.port); + if (tb[IPSET_ATTR_PORT_TO]) { + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + } else + port_to = port; + + for (; !before(ip_to, ip); ip++) + for (p = port; p <= port_to; p++) { + data.ip = htonl(ip); + data.port = htons(p); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static bool +hash_ipportnet_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout; +} + +/* The type variant functions: IPv6 */ + +struct hash_ipportnet6_elem { + union nf_inet_addr ip; + union nf_inet_addr ip2; + __be16 port; + u8 cidr; + u8 proto; +}; + +struct hash_ipportnet6_telem { + union nf_inet_addr ip; + union nf_inet_addr ip2; + __be16 port; + u8 cidr; + u8 proto; + unsigned long timeout; +}; + +static inline bool +hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1, + const struct hash_ipportnet6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && + ip1->cidr == ip2->cidr && + ip1->port == ip2->port && + ip1->proto == ip2->proto; +} + +static inline bool +hash_ipportnet6_data_isnull(const struct hash_ipportnet6_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_ipportnet6_data_copy(struct hash_ipportnet6_elem *dst, + const struct hash_ipportnet6_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_ipportnet6_data_zero_out(struct hash_ipportnet6_elem *elem) +{ + elem->proto = 0; +} + +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + +static inline void +hash_ipportnet6_data_netmask(struct hash_ipportnet6_elem *elem, u8 cidr) +{ + ip6_netmask(&elem->ip2, cidr); + elem->cidr = cidr; +} + +static bool +hash_ipportnet6_data_list(struct sk_buff *skb, + const struct hash_ipportnet6_elem *data) +{ + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_ipportnet6_data_tlist(struct sk_buff *skb, + const struct hash_ipportnet6_elem *data) +{ + const struct hash_ipportnet6_telem *e = + (const struct hash_ipportnet6_telem *)data; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP2, &data->ip2); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR2, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportnet6_elem data = + { .cidr = h->nets[0].cidr || HOST_MASK }; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); + ip6_netmask(&data.ip2, data.cidr); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipportnet6_elem data = { .cidr = HOST_MASK }; + u32 port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + tb[IPSET_ATTR_IP_TO] || + tb[IPSET_ATTR_CIDR])) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &data.ip2); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR2]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); + + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + + ip6_netmask(&data.ip2, data.cidr); + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMPV6: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !tb[IPSET_ATTR_PORT_TO]) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + port = ntohs(data.port); + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + + for (; port <= port_to; port++) { + data.port = htons(port); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + struct ip_set_hash *h; + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + u8 hbits; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + h = kzalloc(sizeof(*h) + + sizeof(struct ip_set_hash_nets) + * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_ipportnet4_tvariant + : &hash_ipportnet6_tvariant; + + if (set->family == AF_INET) + hash_ipportnet4_gc_init(set); + else + hash_ipportnet6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_ipportnet4_variant : &hash_ipportnet6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_ipportnet_type __read_mostly = { + .name = "hash:ip,port,net", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, + .dimension = IPSET_DIM_THREE, + .family = AF_UNSPEC, + .revision = 0, + .create = hash_ipportnet_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, + [IPSET_ATTR_PORT] = { .type = NLA_U16 }, + [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_ipportnet_init(void) +{ + return ip_set_type_register(&hash_ipportnet_type); +} + +static void __exit +hash_ipportnet_fini(void) +{ + ip_set_type_unregister(&hash_ipportnet_type); +} + +module_init(hash_ipportnet_init); +module_exit(hash_ipportnet_fini); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c new file mode 100644 index 0000000..c4db202 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -0,0 +1,458 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:net type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:net type of IP sets"); +MODULE_ALIAS("ip_set_hash:net"); + +/* Type specific function prefix */ +#define TYPE hash_net + +static bool +hash_net_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_net4_same_set hash_net_same_set +#define hash_net6_same_set hash_net_same_set + +/* The type variant functions: IPv4 */ + +/* Member elements without timeout */ +struct hash_net4_elem { + __be32 ip; + u16 padding0; + u8 padding1; + u8 cidr; +}; + +/* Member elements with timeout support */ +struct hash_net4_telem { + __be32 ip; + u16 padding0; + u8 padding1; + u8 cidr; + unsigned long timeout; +}; + +static inline bool +hash_net4_data_equal(const struct hash_net4_elem *ip1, + const struct hash_net4_elem *ip2) +{ + return ip1->ip == ip2->ip && ip1->cidr == ip2->cidr; +} + +static inline bool +hash_net4_data_isnull(const struct hash_net4_elem *elem) +{ + return elem->cidr == 0; +} + +static inline void +hash_net4_data_copy(struct hash_net4_elem *dst, + const struct hash_net4_elem *src) +{ + dst->ip = src->ip; + dst->cidr = src->cidr; +} + +static inline void +hash_net4_data_netmask(struct hash_net4_elem *elem, u8 cidr) +{ + elem->ip &= ip_set_netmask(cidr); + elem->cidr = cidr; +} + +/* Zero CIDR values cannot be stored */ +static inline void +hash_net4_data_zero_out(struct hash_net4_elem *elem) +{ + elem->cidr = 0; +} + +static bool +hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data) +{ + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_net4_data_tlist(struct sk_buff *skb, const struct hash_net4_elem *data) +{ + const struct hash_net4_telem *tdata = + (const struct hash_net4_telem *)data; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, tdata->cidr); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define IP_SET_HASH_WITH_NETS + +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_net4_elem data = { .cidr = h->nets[0].cidr || HOST_MASK }; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + data.ip &= ip_set_netmask(data.cidr); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_net4_elem data = { .cidr = HOST_MASK }; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + + data.ip &= ip_set_netmask(data.cidr); + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + ret = adtfn(set, &data, timeout); + + return ip_set_eexist(ret, flags) ? 0 : ret; +} + +static bool +hash_net_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout; +} + +/* The type variant functions: IPv6 */ + +struct hash_net6_elem { + union nf_inet_addr ip; + u16 padding0; + u8 padding1; + u8 cidr; +}; + +struct hash_net6_telem { + union nf_inet_addr ip; + u16 padding0; + u8 padding1; + u8 cidr; + unsigned long timeout; +}; + +static inline bool +hash_net6_data_equal(const struct hash_net6_elem *ip1, + const struct hash_net6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ip1->cidr == ip2->cidr; +} + +static inline bool +hash_net6_data_isnull(const struct hash_net6_elem *elem) +{ + return elem->cidr == 0; +} + +static inline void +hash_net6_data_copy(struct hash_net6_elem *dst, + const struct hash_net6_elem *src) +{ + ipv6_addr_copy(&dst->ip.in6, &src->ip.in6); + dst->cidr = src->cidr; +} + +static inline void +hash_net6_data_zero_out(struct hash_net6_elem *elem) +{ + elem->cidr = 0; +} + +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + +static inline void +hash_net6_data_netmask(struct hash_net6_elem *elem, u8 cidr) +{ + ip6_netmask(&elem->ip, cidr); + elem->cidr = cidr; +} + +static bool +hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data) +{ + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_net6_data_tlist(struct sk_buff *skb, const struct hash_net6_elem *data) +{ + const struct hash_net6_telem *e = + (const struct hash_net6_telem *)data; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, e->cidr); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_net6_elem data = { .cidr = h->nets[0].cidr || HOST_MASK }; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6_netmask(&data.ip, data.cidr); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_net6_elem data = { .cidr = HOST_MASK }; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + + ip6_netmask(&data.ip, data.cidr); + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + ret = adtfn(set, &data, timeout); + + return ip_set_eexist(ret, flags) ? 0 : ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + struct ip_set_hash *h; + u8 hbits; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + h = kzalloc(sizeof(*h) + + sizeof(struct ip_set_hash_nets) + * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_net4_tvariant : &hash_net6_tvariant; + + if (set->family == AF_INET) + hash_net4_gc_init(set); + else + hash_net6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_net4_variant : &hash_net6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_net_type __read_mostly = { + .name = "hash:net", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP, + .dimension = IPSET_DIM_ONE, + .family = AF_UNSPEC, + .revision = 0, + .create = hash_net_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_net_init(void) +{ + return ip_set_type_register(&hash_net_type); +} + +static void __exit +hash_net_fini(void) +{ + ip_set_type_unregister(&hash_net_type); +} + +module_init(hash_net_init); +module_exit(hash_net_fini); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c new file mode 100644 index 0000000..34a1656 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -0,0 +1,578 @@ +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:net,port type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_getport.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:net,port type of IP sets"); +MODULE_ALIAS("ip_set_hash:net,port"); + +/* Type specific function prefix */ +#define TYPE hash_netport + +static bool +hash_netport_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_netport4_same_set hash_netport_same_set +#define hash_netport6_same_set hash_netport_same_set + +/* The type variant functions: IPv4 */ + +/* Member elements without timeout */ +struct hash_netport4_elem { + __be32 ip; + __be16 port; + u8 proto; + u8 cidr; +}; + +/* Member elements with timeout support */ +struct hash_netport4_telem { + __be32 ip; + __be16 port; + u8 proto; + u8 cidr; + unsigned long timeout; +}; + +static inline bool +hash_netport4_data_equal(const struct hash_netport4_elem *ip1, + const struct hash_netport4_elem *ip2) +{ + return ip1->ip == ip2->ip && + ip1->port == ip2->port && + ip1->proto == ip2->proto && + ip1->cidr == ip2->cidr; +} + +static inline bool +hash_netport4_data_isnull(const struct hash_netport4_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_netport4_data_copy(struct hash_netport4_elem *dst, + const struct hash_netport4_elem *src) +{ + dst->ip = src->ip; + dst->port = src->port; + dst->proto = src->proto; + dst->cidr = src->cidr; +} + +static inline void +hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr) +{ + elem->ip &= ip_set_netmask(cidr); + elem->cidr = cidr; +} + +static inline void +hash_netport4_data_zero_out(struct hash_netport4_elem *elem) +{ + elem->proto = 0; +} + +static bool +hash_netport4_data_list(struct sk_buff *skb, + const struct hash_netport4_elem *data) +{ + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_netport4_data_tlist(struct sk_buff *skb, + const struct hash_netport4_elem *data) +{ + const struct hash_netport4_telem *tdata = + (const struct hash_netport4_telem *)data; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, tdata->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define IP_SET_HASH_WITH_PROTO +#define IP_SET_HASH_WITH_NETS + +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netport4_elem data = { + .cidr = h->nets[0].cidr || HOST_MASK }; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + data.ip &= ip_set_netmask(data.cidr); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netport4_elem data = { .cidr = HOST_MASK }; + u32 port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + data.ip &= ip_set_netmask(data.cidr); + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMP: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !tb[IPSET_ATTR_PORT_TO]) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + port = ntohs(data.port); + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + + for (; port <= port_to; port++) { + data.port = htons(port); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +static bool +hash_netport_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout; +} + +/* The type variant functions: IPv6 */ + +struct hash_netport6_elem { + union nf_inet_addr ip; + __be16 port; + u8 proto; + u8 cidr; +}; + +struct hash_netport6_telem { + union nf_inet_addr ip; + __be16 port; + u8 proto; + u8 cidr; + unsigned long timeout; +}; + +static inline bool +hash_netport6_data_equal(const struct hash_netport6_elem *ip1, + const struct hash_netport6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ip1->port == ip2->port && + ip1->proto == ip2->proto && + ip1->cidr == ip2->cidr; +} + +static inline bool +hash_netport6_data_isnull(const struct hash_netport6_elem *elem) +{ + return elem->proto == 0; +} + +static inline void +hash_netport6_data_copy(struct hash_netport6_elem *dst, + const struct hash_netport6_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_netport6_data_zero_out(struct hash_netport6_elem *elem) +{ + elem->proto = 0; +} + +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + +static inline void +hash_netport6_data_netmask(struct hash_netport6_elem *elem, u8 cidr) +{ + ip6_netmask(&elem->ip, cidr); + elem->cidr = cidr; +} + +static bool +hash_netport6_data_list(struct sk_buff *skb, + const struct hash_netport6_elem *data) +{ + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_netport6_data_tlist(struct sk_buff *skb, + const struct hash_netport6_elem *data) +{ + const struct hash_netport6_telem *e = + (const struct hash_netport6_telem *)data; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_NET16(skb, IPSET_ATTR_PORT, data->port); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_U8(skb, IPSET_ATTR_PROTO, data->proto); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static int +hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netport6_elem data = { + .cidr = h->nets[0].cidr || HOST_MASK }; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + &data.port, &data.proto)) + return -EINVAL; + + ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6_netmask(&data.ip, data.cidr); + + return adtfn(set, &data, h->timeout); +} + +static int +hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + const struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netport6_elem data = { .cidr = HOST_MASK }; + u32 port, port_to; + u32 timeout = h->timeout; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + ip6_netmask(&data.ip, data.cidr); + + if (tb[IPSET_ATTR_PORT]) + data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); + else + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_PROTO]) { + data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); + + if (data.proto == 0) + return -IPSET_ERR_INVALID_PROTO; + } else + return -IPSET_ERR_MISSING_PROTO; + + switch (data.proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_ICMPV6: + break; + default: + data.port = 0; + break; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + if (adt == IPSET_TEST || + !(data.proto == IPPROTO_TCP || data.proto == IPPROTO_UDP) || + !tb[IPSET_ATTR_PORT_TO]) { + ret = adtfn(set, &data, timeout); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + port = ntohs(data.port); + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port > port_to) + swap(port, port_to); + + for (; port <= port_to; port++) { + data.port = htons(port); + ret = adtfn(set, &data, timeout); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + struct ip_set_hash *h; + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + u8 hbits; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + h = kzalloc(sizeof(*h) + + sizeof(struct ip_set_hash_nets) + * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_netport4_tvariant : &hash_netport6_tvariant; + + if (set->family == AF_INET) + hash_netport4_gc_init(set); + else + hash_netport6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_netport4_variant : &hash_netport6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_netport_type __read_mostly = { + .name = "hash:net,port", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, + .dimension = IPSET_DIM_TWO, + .family = AF_UNSPEC, + .revision = 0, + .create = hash_netport_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_PORT] = { .type = NLA_U16 }, + [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_netport_init(void) +{ + return ip_set_type_register(&hash_netport_type); +} + +static void __exit +hash_netport_fini(void) +{ + ip_set_type_unregister(&hash_netport_type); +} + +module_init(hash_netport_init); +module_exit(hash_netport_fini); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c new file mode 100644 index 0000000..a47c329 --- /dev/null +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -0,0 +1,584 @@ +/* Copyright (C) 2008-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the list:set type */ + +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> + +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_list.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("list:set type of IP sets"); +MODULE_ALIAS("ip_set_list:set"); + +/* Member elements without and with timeout */ +struct set_elem { + ip_set_id_t id; +}; + +struct set_telem { + ip_set_id_t id; + unsigned long timeout; +}; + +/* Type structure */ +struct list_set { + size_t dsize; /* element size */ + u32 size; /* size of set list array */ + u32 timeout; /* timeout value */ + struct timer_list gc; /* garbage collection */ + struct set_elem members[0]; /* the set members */ +}; + +static inline struct set_elem * +list_set_elem(const struct list_set *map, u32 id) +{ + return (struct set_elem *)((char *)map->members + id * map->dsize); +} + +static inline bool +list_set_timeout(const struct list_set *map, u32 id) +{ + const struct set_telem *elem = + (const struct set_telem *) list_set_elem(map, id); + + return ip_set_timeout_test(elem->timeout); +} + +static inline bool +list_set_expired(const struct list_set *map, u32 id) +{ + const struct set_telem *elem = + (const struct set_telem *) list_set_elem(map, id); + + return ip_set_timeout_expired(elem->timeout); +} + +static inline int +list_set_exist(const struct set_telem *elem) +{ + return elem->id != IPSET_INVALID_ID && + !ip_set_timeout_expired(elem->timeout); +} + +/* Set list without and with timeout */ + +static int +list_set_kadt(struct ip_set *set, const struct sk_buff *skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags) +{ + struct list_set *map = set->data; + struct set_elem *elem; + u32 i; + int ret; + + for (i = 0; i < map->size; i++) { + elem = list_set_elem(map, i); + if (elem->id == IPSET_INVALID_ID) + return 0; + if (with_timeout(map->timeout) && list_set_expired(map, i)) + continue; + switch (adt) { + case IPSET_TEST: + ret = ip_set_test(elem->id, skb, pf, dim, flags); + if (ret > 0) + return ret; + break; + case IPSET_ADD: + ret = ip_set_add(elem->id, skb, pf, dim, flags); + if (ret == 0) + return ret; + break; + case IPSET_DEL: + ret = ip_set_del(elem->id, skb, pf, dim, flags); + if (ret == 0) + return ret; + break; + default: + break; + } + } + return -EINVAL; +} + +static bool +next_id_eq(const struct list_set *map, u32 i, ip_set_id_t id) +{ + const struct set_elem *elem; + + if (i + 1 < map->size) { + elem = list_set_elem(map, i + 1); + return !!(elem->id == id && + !(with_timeout(map->timeout) && + list_set_expired(map, i + 1))); + } + + return 0; +} + +static void +list_elem_add(struct list_set *map, u32 i, ip_set_id_t id) +{ + struct set_elem *e; + + for (; i < map->size; i++) { + e = list_set_elem(map, i); + swap(e->id, id); + if (e->id == IPSET_INVALID_ID) + break; + } +} + +static void +list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id, + unsigned long timeout) +{ + struct set_telem *e; + + for (; i < map->size; i++) { + e = (struct set_telem *)list_set_elem(map, i); + swap(e->id, id); + if (e->id == IPSET_INVALID_ID) + break; + swap(e->timeout, timeout); + } +} + +static int +list_set_add(struct list_set *map, u32 i, ip_set_id_t id, + unsigned long timeout) +{ + const struct set_elem *e = list_set_elem(map, i); + + if (i == map->size - 1 && e->id != IPSET_INVALID_ID) + /* Last element replaced: e.g. add new,before,last */ + ip_set_put_byindex(e->id); + if (with_timeout(map->timeout)) + list_elem_tadd(map, i, id, timeout); + else + list_elem_add(map, i, id); + + return 0; +} + +static int +list_set_del(struct list_set *map, ip_set_id_t id, u32 i) +{ + struct set_elem *a = list_set_elem(map, i), *b; + + ip_set_put_byindex(id); + + for (; i < map->size - 1; i++) { + b = list_set_elem(map, i + 1); + a->id = b->id; + if (with_timeout(map->timeout)) + ((struct set_telem *)a)->timeout = + ((struct set_telem *)b)->timeout; + a = b; + if (a->id == IPSET_INVALID_ID) + break; + } + /* Last element */ + a->id = IPSET_INVALID_ID; + return 0; +} + +static int +list_set_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags) +{ + struct list_set *map = set->data; + bool with_timeout = with_timeout(map->timeout); + int before = 0; + u32 timeout = map->timeout; + ip_set_id_t id, refid = IPSET_INVALID_ID; + const struct set_elem *elem; + struct ip_set *s; + u32 i; + int ret = 0; + + if (unlikely(!tb[IPSET_ATTR_NAME] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + id = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAME]), &s); + if (id == IPSET_INVALID_ID) + return -IPSET_ERR_NAME; + /* "Loop detection" */ + if (s->type->features & IPSET_TYPE_NAME) { + ret = -IPSET_ERR_LOOP; + goto finish; + } + + if (tb[IPSET_ATTR_CADT_FLAGS]) { + u32 f = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + before = f & IPSET_FLAG_BEFORE; + } + + if (before && !tb[IPSET_ATTR_NAMEREF]) { + ret = -IPSET_ERR_BEFORE; + goto finish; + } + + if (tb[IPSET_ATTR_NAMEREF]) { + refid = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAMEREF]), + &s); + if (refid == IPSET_INVALID_ID) { + ret = -IPSET_ERR_NAMEREF; + goto finish; + } + if (!before) + before = -1; + } + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout) { + ret = -IPSET_ERR_TIMEOUT; + goto finish; + } + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + switch (adt) { + case IPSET_TEST: + for (i = 0; i < map->size && !ret; i++) { + elem = list_set_elem(map, i); + if (elem->id == IPSET_INVALID_ID || + (before != 0 && i + 1 >= map->size)) + break; + else if (with_timeout && list_set_expired(map, i)) + continue; + else if (before > 0 && elem->id == id) + ret = next_id_eq(map, i, refid); + else if (before < 0 && elem->id == refid) + ret = next_id_eq(map, i, id); + else if (before == 0 && elem->id == id) + ret = 1; + } + break; + case IPSET_ADD: + for (i = 0; i < map->size && !ret; i++) { + elem = list_set_elem(map, i); + if (elem->id == id && + !(with_timeout && list_set_expired(map, i))) + ret = -IPSET_ERR_EXIST; + } + if (ret == -IPSET_ERR_EXIST) + break; + ret = -IPSET_ERR_LIST_FULL; + for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) { + elem = list_set_elem(map, i); + if (elem->id == IPSET_INVALID_ID) + ret = before != 0 ? -IPSET_ERR_REF_EXIST + : list_set_add(map, i, id, timeout); + else if (elem->id != refid) + continue; + else if (with_timeout && list_set_expired(map, i)) + ret = -IPSET_ERR_REF_EXIST; + else if (before) + ret = list_set_add(map, i, id, timeout); + else if (i + 1 < map->size) + ret = list_set_add(map, i + 1, id, timeout); + } + break; + case IPSET_DEL: + ret = -IPSET_ERR_EXIST; + for (i = 0; i < map->size && ret == -IPSET_ERR_EXIST; i++) { + elem = list_set_elem(map, i); + if (elem->id == IPSET_INVALID_ID) { + ret = before != 0 ? -IPSET_ERR_REF_EXIST + : -IPSET_ERR_EXIST; + break; + } else if (with_timeout && list_set_expired(map, i)) + continue; + else if (elem->id == id && + (before == 0 || + (before > 0 && + next_id_eq(map, i, refid)))) + ret = list_set_del(map, id, i); + else if (before < 0 && + elem->id == refid && + next_id_eq(map, i, id)) + ret = list_set_del(map, id, i + 1); + } + break; + default: + break; + } + +finish: + if (refid != IPSET_INVALID_ID) + ip_set_put_byindex(refid); + if (adt != IPSET_ADD || ret) + ip_set_put_byindex(id); + + return ip_set_eexist(ret, flags) ? 0 : ret; +} + +static void +list_set_flush(struct ip_set *set) +{ + struct list_set *map = set->data; + struct set_elem *elem; + u32 i; + + for (i = 0; i < map->size; i++) { + elem = list_set_elem(map, i); + if (elem->id != IPSET_INVALID_ID) { + ip_set_put_byindex(elem->id); + elem->id = IPSET_INVALID_ID; + } + } +} + +static void +list_set_destroy(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (with_timeout(map->timeout)) + del_timer_sync(&map->gc); + list_set_flush(set); + kfree(map); + + set->data = NULL; +} + +static int +list_set_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct list_set *map = set->data; + struct nlattr *nested; + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size)); + if (with_timeout(map->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, + htonl(sizeof(*map) + map->size * map->dsize)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +static int +list_set_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct list_set *map = set->data; + struct nlattr *atd, *nested; + u32 i, first = cb->args[2]; + const struct set_elem *e; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] < map->size; cb->args[2]++) { + i = cb->args[2]; + e = list_set_elem(map, i); + if (e->id == IPSET_INVALID_ID) + goto finish; + if (with_timeout(map->timeout) && list_set_expired(map, i)) + continue; + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (i == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + NLA_PUT_STRING(skb, IPSET_ATTR_NAME, + ip_set_name_byindex(e->id)); + if (with_timeout(map->timeout)) { + const struct set_telem *te = + (const struct set_telem *) e; + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(te->timeout))); + } + ipset_nest_end(skb, nested); + } +finish: + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nested); + ipset_nest_end(skb, atd); + if (unlikely(i == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static bool +list_set_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct list_set *x = a->data; + const struct list_set *y = b->data; + + return x->size == y->size && + x->timeout == y->timeout; +} + +static const struct ip_set_type_variant list_set = { + .kadt = list_set_kadt, + .uadt = list_set_uadt, + .destroy = list_set_destroy, + .flush = list_set_flush, + .head = list_set_head, + .list = list_set_list, + .same_set = list_set_same_set, +}; + +static void +list_set_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct list_set *map = set->data; + struct set_telem *e; + u32 i; + + /* We run parallel with other readers (test element) + * but adding/deleting new entries is locked out */ + read_lock_bh(&set->lock); + for (i = map->size - 1; i >= 0; i--) { + e = (struct set_telem *) list_set_elem(map, i); + if (e->id != IPSET_INVALID_ID && + list_set_expired(map, i)) + list_set_del(map, e->id, i); + } + read_unlock_bh(&set->lock); + + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +static void +list_set_gc_init(struct ip_set *set) +{ + struct list_set *map = set->data; + + init_timer(&map->gc); + map->gc.data = (unsigned long) set; + map->gc.function = list_set_gc; + map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; + add_timer(&map->gc); +} + +/* Create list:set type of sets */ + +static bool +init_list_set(struct ip_set *set, u32 size, size_t dsize, + unsigned long timeout) +{ + struct list_set *map; + struct set_elem *e; + u32 i; + + map = kzalloc(sizeof(*map) + size * dsize, GFP_KERNEL); + if (!map) + return false; + + map->size = size; + map->dsize = dsize; + map->timeout = timeout; + set->data = map; + + for (i = 0; i < size; i++) { + e = list_set_elem(map, i); + e->id = IPSET_INVALID_ID; + } + + return true; +} + +static int +list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + u32 size = IP_SET_LIST_DEFAULT_SIZE; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_SIZE]) + size = ip_set_get_h32(tb[IPSET_ATTR_SIZE]); + if (size < IP_SET_LIST_MIN_SIZE) + size = IP_SET_LIST_MIN_SIZE; + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!init_list_set(set, size, sizeof(struct set_telem), + ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]))) + return -ENOMEM; + + list_set_gc_init(set); + } else { + if (!init_list_set(set, size, sizeof(struct set_elem), + IPSET_NO_TIMEOUT)) + return -ENOMEM; + } + set->variant = &list_set; + return 0; +} + +static struct ip_set_type list_set_type __read_mostly = { + .name = "list:set", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_NAME | IPSET_DUMP_LAST, + .dimension = IPSET_DIM_ONE, + .family = AF_UNSPEC, + .revision = 0, + .create = list_set_create, + .create_policy = { + [IPSET_ATTR_SIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_NAME] = { .type = NLA_STRING, + .len = IPSET_MAXNAMELEN }, + [IPSET_ATTR_NAMEREF] = { .type = NLA_STRING, + .len = IPSET_MAXNAMELEN }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +list_set_init(void) +{ + return ip_set_type_register(&list_set_type); +} + +static void __exit +list_set_fini(void) +{ + ip_set_type_unregister(&list_set_type); +} + +module_init(list_set_init); +module_exit(list_set_fini); diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c new file mode 100644 index 0000000..23f8c81 --- /dev/null +++ b/net/netfilter/ipset/pfxlen.c @@ -0,0 +1,291 @@ +#include <linux/netfilter/ipset/pfxlen.h> + +/* + * Prefixlen maps for fast conversions, by Jan Engelhardt. + */ + +#define E(a, b, c, d) \ + {.ip6 = { \ + __constant_htonl(a), __constant_htonl(b), \ + __constant_htonl(c), __constant_htonl(d), \ + } } + +/* + * This table works for both IPv4 and IPv6; + * just use prefixlen_netmask_map[prefixlength].ip. + */ +const union nf_inet_addr ip_set_netmask_map[] = { + E(0x00000000, 0x00000000, 0x00000000, 0x00000000), + E(0x80000000, 0x00000000, 0x00000000, 0x00000000), + E(0xC0000000, 0x00000000, 0x00000000, 0x00000000), + E(0xE0000000, 0x00000000, 0x00000000, 0x00000000), + E(0xF0000000, 0x00000000, 0x00000000, 0x00000000), + E(0xF8000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFC000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFE000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFF000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFF800000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), +}; +EXPORT_SYMBOL_GPL(ip_set_netmask_map); + +#undef E +#define E(a, b, c, d) \ + {.ip6 = { (__force __be32) a, (__force __be32) b, \ + (__force __be32) c, (__force __be32) d, \ + } } + +/* + * This table works for both IPv4 and IPv6; + * just use prefixlen_hostmask_map[prefixlength].ip. + */ +const union nf_inet_addr ip_set_hostmask_map[] = { + E(0x00000000, 0x00000000, 0x00000000, 0x00000000), + E(0x80000000, 0x00000000, 0x00000000, 0x00000000), + E(0xC0000000, 0x00000000, 0x00000000, 0x00000000), + E(0xE0000000, 0x00000000, 0x00000000, 0x00000000), + E(0xF0000000, 0x00000000, 0x00000000, 0x00000000), + E(0xF8000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFC000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFE000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFF000000, 0x00000000, 0x00000000, 0x00000000), + E(0xFF800000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE), + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), +}; +EXPORT_SYMBOL_GPL(ip_set_hostmask_map); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index a475ede..5c48ffb 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -43,11 +43,6 @@ EXPORT_SYMBOL(register_ip_vs_app); EXPORT_SYMBOL(unregister_ip_vs_app); EXPORT_SYMBOL(register_ip_vs_app_inc); -/* ipvs application list head */ -static LIST_HEAD(ip_vs_app_list); -static DEFINE_MUTEX(__ip_vs_app_mutex); - - /* * Get an ip_vs_app object */ @@ -67,7 +62,8 @@ static inline void ip_vs_app_put(struct ip_vs_app *app) * Allocate/initialize app incarnation and register it in proto apps. */ static int -ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) +ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, + __u16 port) { struct ip_vs_protocol *pp; struct ip_vs_app *inc; @@ -98,7 +94,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) } } - ret = pp->register_app(inc); + ret = pp->register_app(net, inc); if (ret) goto out; @@ -119,7 +115,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) * Release app incarnation */ static void -ip_vs_app_inc_release(struct ip_vs_app *inc) +ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc) { struct ip_vs_protocol *pp; @@ -127,7 +123,7 @@ ip_vs_app_inc_release(struct ip_vs_app *inc) return; if (pp->unregister_app) - pp->unregister_app(inc); + pp->unregister_app(net, inc); IP_VS_DBG(9, "%s App %s:%u unregistered\n", pp->name, inc->name, ntohs(inc->port)); @@ -168,15 +164,17 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc) * Register an application incarnation in protocol applications */ int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port) +register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, + __u16 port) { + struct netns_ipvs *ipvs = net_ipvs(net); int result; - mutex_lock(&__ip_vs_app_mutex); + mutex_lock(&ipvs->app_mutex); - result = ip_vs_app_inc_new(app, proto, port); + result = ip_vs_app_inc_new(net, app, proto, port); - mutex_unlock(&__ip_vs_app_mutex); + mutex_unlock(&ipvs->app_mutex); return result; } @@ -185,16 +183,17 @@ register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port) /* * ip_vs_app registration routine */ -int register_ip_vs_app(struct ip_vs_app *app) +int register_ip_vs_app(struct net *net, struct ip_vs_app *app) { + struct netns_ipvs *ipvs = net_ipvs(net); /* increase the module use count */ ip_vs_use_count_inc(); - mutex_lock(&__ip_vs_app_mutex); + mutex_lock(&ipvs->app_mutex); - list_add(&app->a_list, &ip_vs_app_list); + list_add(&app->a_list, &ipvs->app_list); - mutex_unlock(&__ip_vs_app_mutex); + mutex_unlock(&ipvs->app_mutex); return 0; } @@ -204,19 +203,20 @@ int register_ip_vs_app(struct ip_vs_app *app) * ip_vs_app unregistration routine * We are sure there are no app incarnations attached to services */ -void unregister_ip_vs_app(struct ip_vs_app *app) +void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *inc, *nxt; - mutex_lock(&__ip_vs_app_mutex); + mutex_lock(&ipvs->app_mutex); list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) { - ip_vs_app_inc_release(inc); + ip_vs_app_inc_release(net, inc); } list_del(&app->a_list); - mutex_unlock(&__ip_vs_app_mutex); + mutex_unlock(&ipvs->app_mutex); /* decrease the module use count */ ip_vs_use_count_dec(); @@ -226,7 +226,8 @@ void unregister_ip_vs_app(struct ip_vs_app *app) /* * Bind ip_vs_conn to its ip_vs_app (called by cp constructor) */ -int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp) +int ip_vs_bind_app(struct ip_vs_conn *cp, + struct ip_vs_protocol *pp) { return pp->app_conn_bind(cp); } @@ -481,11 +482,11 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb) * /proc/net/ip_vs_app entry function */ -static struct ip_vs_app *ip_vs_app_idx(loff_t pos) +static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos) { struct ip_vs_app *app, *inc; - list_for_each_entry(app, &ip_vs_app_list, a_list) { + list_for_each_entry(app, &ipvs->app_list, a_list) { list_for_each_entry(inc, &app->incs_list, a_list) { if (pos-- == 0) return inc; @@ -497,19 +498,24 @@ static struct ip_vs_app *ip_vs_app_idx(loff_t pos) static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos) { - mutex_lock(&__ip_vs_app_mutex); + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); - return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN; + mutex_lock(&ipvs->app_mutex); + + return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN; } static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_app *inc, *app; struct list_head *e; + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); ++*pos; if (v == SEQ_START_TOKEN) - return ip_vs_app_idx(0); + return ip_vs_app_idx(ipvs, 0); inc = v; app = inc->app; @@ -518,7 +524,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) return list_entry(e, struct ip_vs_app, a_list); /* go on to next application */ - for (e = app->a_list.next; e != &ip_vs_app_list; e = e->next) { + for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) { app = list_entry(e, struct ip_vs_app, a_list); list_for_each_entry(inc, &app->incs_list, a_list) { return inc; @@ -529,7 +535,9 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ip_vs_app_seq_stop(struct seq_file *seq, void *v) { - mutex_unlock(&__ip_vs_app_mutex); + struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq)); + + mutex_unlock(&ipvs->app_mutex); } static int ip_vs_app_seq_show(struct seq_file *seq, void *v) @@ -557,7 +565,8 @@ static const struct seq_operations ip_vs_app_seq_ops = { static int ip_vs_app_open(struct inode *inode, struct file *file) { - return seq_open(file, &ip_vs_app_seq_ops); + return seq_open_net(inode, file, &ip_vs_app_seq_ops, + sizeof(struct seq_net_private)); } static const struct file_operations ip_vs_app_fops = { @@ -569,15 +578,36 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -int __init ip_vs_app_init(void) +static int __net_init __ip_vs_app_init(struct net *net) { - /* we will replace it with proc_net_ipvs_create() soon */ - proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops); + struct netns_ipvs *ipvs = net_ipvs(net); + + INIT_LIST_HEAD(&ipvs->app_list); + __mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key); + proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops); return 0; } +static void __net_exit __ip_vs_app_cleanup(struct net *net) +{ + proc_net_remove(net, "ip_vs_app"); +} + +static struct pernet_operations ip_vs_app_ops = { + .init = __ip_vs_app_init, + .exit = __ip_vs_app_cleanup, +}; + +int __init ip_vs_app_init(void) +{ + int rv; + + rv = register_pernet_subsys(&ip_vs_app_ops); + return rv; +} + void ip_vs_app_cleanup(void) { - proc_net_remove(&init_net, "ip_vs_app"); + unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index e9adecd..83233fe 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -48,35 +48,32 @@ /* * Connection hash size. Default is what was selected at compile time. */ -int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; +static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); /* size and mask values */ -int ip_vs_conn_tab_size; -int ip_vs_conn_tab_mask; +int ip_vs_conn_tab_size __read_mostly; +static int ip_vs_conn_tab_mask __read_mostly; /* * Connection hash table: for input and output packets lookups of IPVS */ -static struct list_head *ip_vs_conn_tab; +static struct list_head *ip_vs_conn_tab __read_mostly; /* SLAB cache for IPVS connections */ static struct kmem_cache *ip_vs_conn_cachep __read_mostly; -/* counter for current IPVS connections */ -static atomic_t ip_vs_conn_count = ATOMIC_INIT(0); - /* counter for no client port connections */ static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0); /* random value for IPVS connection hash */ -static unsigned int ip_vs_conn_rnd; +static unsigned int ip_vs_conn_rnd __read_mostly; /* * Fine locking granularity for big connection hash table */ -#define CT_LOCKARRAY_BITS 4 +#define CT_LOCKARRAY_BITS 5 #define CT_LOCKARRAY_SIZE (1<<CT_LOCKARRAY_BITS) #define CT_LOCKARRAY_MASK (CT_LOCKARRAY_SIZE-1) @@ -133,19 +130,19 @@ static inline void ct_write_unlock_bh(unsigned key) /* * Returns hash value for IPVS connection entry */ -static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, +static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto, const union nf_inet_addr *addr, __be16 port) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), - (__force u32)port, proto, ip_vs_conn_rnd) - & ip_vs_conn_tab_mask; + return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), + (__force u32)port, proto, ip_vs_conn_rnd) ^ + ((size_t)net>>8)) & ip_vs_conn_tab_mask; #endif - return jhash_3words((__force u32)addr->ip, (__force u32)port, proto, - ip_vs_conn_rnd) - & ip_vs_conn_tab_mask; + return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto, + ip_vs_conn_rnd) ^ + ((size_t)net>>8)) & ip_vs_conn_tab_mask; } static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, @@ -166,18 +163,18 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, port = p->vport; } - return ip_vs_conn_hashkey(p->af, p->protocol, addr, port); + return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port); } static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport, - NULL, 0, &p); + ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol, + &cp->caddr, cp->cport, NULL, 0, &p); - if (cp->dest && cp->dest->svc->pe) { - p.pe = cp->dest->svc->pe; + if (cp->pe) { + p.pe = cp->pe; p.pe_data = cp->pe_data; p.pe_data_len = cp->pe_data_len; } @@ -186,7 +183,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) } /* - * Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port. + * Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port. * returns bool success. */ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) @@ -269,11 +266,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && + p->cport == cp->cport && p->vport == cp->vport && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && - p->cport == cp->cport && p->vport == cp->vport && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && - p->protocol == cp->protocol) { + p->protocol == cp->protocol && + ip_vs_conn_net_eq(cp, p->net)) { /* HIT */ atomic_inc(&cp->refcnt); ct_read_unlock(hash); @@ -313,23 +311,23 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; + struct net *net = skb_net(skb); pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) return 1; if (likely(!inverse)) - ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0], - &iph->daddr, pptr[1], p); + ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr, + pptr[0], &iph->daddr, pptr[1], p); else - ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1], - &iph->saddr, pptr[0], p); + ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr, + pptr[1], &iph->saddr, pptr[0], p); return 0; } struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { @@ -353,8 +351,10 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + if (!ip_vs_conn_net_eq(cp, p->net)) + continue; if (p->pe_data && p->pe->ct_match) { - if (p->pe->ct_match(p, cp)) + if (p->pe == cp->pe && p->pe->ct_match(p, cp)) goto out; continue; } @@ -404,10 +404,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && + p->vport == cp->cport && p->cport == cp->dport && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && - p->vport == cp->cport && p->cport == cp->dport && - p->protocol == cp->protocol) { + p->protocol == cp->protocol && + ip_vs_conn_net_eq(cp, p->net)) { /* HIT */ atomic_inc(&cp->refcnt); ret = cp; @@ -428,7 +429,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { @@ -611,9 +611,9 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) struct ip_vs_dest *dest; if ((cp) && (!cp->dest)) { - dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport, - &cp->vaddr, cp->vport, - cp->protocol); + dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr, + cp->dport, &cp->vaddr, cp->vport, + cp->protocol, cp->fwmark); ip_vs_bind_dest(cp, dest); return dest; } else @@ -686,13 +686,14 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) int ip_vs_check_template(struct ip_vs_conn *ct) { struct ip_vs_dest *dest = ct->dest; + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct)); /* * Checking the dest server status. */ if ((dest == NULL) || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || - (sysctl_ip_vs_expire_quiescent_template && + (ipvs->sysctl_expire_quiescent_template && (atomic_read(&dest->weight) == 0))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " "protocol %s s:%s:%d v:%s:%d " @@ -730,6 +731,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); cp->timeout = 60*HZ; @@ -765,13 +767,14 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->flags & IP_VS_CONN_F_NFCT) ip_vs_conn_drop_conntrack(cp); + ip_vs_pe_put(cp->pe); kfree(cp->pe_data); if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); if (cp->flags & IP_VS_CONN_F_NO_CPORT) atomic_dec(&ip_vs_conn_no_cport_cnt); - atomic_dec(&ip_vs_conn_count); + atomic_dec(&ipvs->conn_count); kmem_cache_free(ip_vs_conn_cachep, cp); return; @@ -802,10 +805,12 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) struct ip_vs_conn * ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest) + struct ip_vs_dest *dest, __u32 fwmark) { struct ip_vs_conn *cp; - struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol); + struct netns_ipvs *ipvs = net_ipvs(p->net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net, + p->protocol); cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); if (cp == NULL) { @@ -815,6 +820,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, INIT_LIST_HEAD(&cp->c_list); setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); + ip_vs_conn_net_set(cp, p->net); cp->af = p->af; cp->protocol = p->protocol; ip_vs_addr_copy(p->af, &cp->caddr, p->caddr); @@ -826,7 +832,10 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; - if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) { + cp->fwmark = fwmark; + if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) { + ip_vs_pe_get(p->pe); + cp->pe = p->pe; cp->pe_data = p->pe_data; cp->pe_data_len = p->pe_data_len; } @@ -842,7 +851,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, atomic_set(&cp->n_control, 0); atomic_set(&cp->in_pkts, 0); - atomic_inc(&ip_vs_conn_count); + atomic_inc(&ipvs->conn_count); if (flags & IP_VS_CONN_F_NO_CPORT) atomic_inc(&ip_vs_conn_no_cport_cnt); @@ -861,8 +870,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, #endif ip_vs_bind_xmit(cp); - if (unlikely(pp && atomic_read(&pp->appcnt))) - ip_vs_bind_app(cp, pp); + if (unlikely(pd && atomic_read(&pd->appcnt))) + ip_vs_bind_app(cp, pd->pp); /* * Allow conntrack to be preserved. By default, conntrack @@ -871,7 +880,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, * IP_VS_CONN_F_ONE_PACKET too. */ - if (ip_vs_conntrack_enabled()) + if (ip_vs_conntrack_enabled(ipvs)) cp->flags |= IP_VS_CONN_F_NFCT; /* Hash it in the ip_vs_conn_tab finally */ @@ -884,17 +893,22 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, * /proc/net/ip_vs_conn entries */ #ifdef CONFIG_PROC_FS +struct ip_vs_iter_state { + struct seq_net_private p; + struct list_head *l; +}; static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) { int idx; struct ip_vs_conn *cp; + struct ip_vs_iter_state *iter = seq->private; for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { ct_read_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (pos-- == 0) { - seq->private = &ip_vs_conn_tab[idx]; + iter->l = &ip_vs_conn_tab[idx]; return cp; } } @@ -906,14 +920,17 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos) { - seq->private = NULL; + struct ip_vs_iter_state *iter = seq->private; + + iter->l = NULL; return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; } static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_conn *cp = v; - struct list_head *e, *l = seq->private; + struct ip_vs_iter_state *iter = seq->private; + struct list_head *e, *l = iter->l; int idx; ++*pos; @@ -930,18 +947,19 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) while (++idx < ip_vs_conn_tab_size) { ct_read_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { - seq->private = &ip_vs_conn_tab[idx]; + iter->l = &ip_vs_conn_tab[idx]; return cp; } ct_read_unlock_bh(idx); } - seq->private = NULL; + iter->l = NULL; return NULL; } static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) { - struct list_head *l = seq->private; + struct ip_vs_iter_state *iter = seq->private; + struct list_head *l = iter->l; if (l) ct_read_unlock_bh(l - ip_vs_conn_tab); @@ -955,18 +973,19 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires PEName PEData\n"); else { const struct ip_vs_conn *cp = v; + struct net *net = seq_file_net(seq); char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3]; size_t len = 0; - if (cp->dest && cp->pe_data && - cp->dest->svc->pe->show_pe_data) { + if (!ip_vs_conn_net_eq(cp, net)) + return 0; + if (cp->pe_data) { pe_data[0] = ' '; - len = strlen(cp->dest->svc->pe->name); - memcpy(pe_data + 1, cp->dest->svc->pe->name, len); + len = strlen(cp->pe->name); + memcpy(pe_data + 1, cp->pe->name, len); pe_data[len + 1] = ' '; len += 2; - len += cp->dest->svc->pe->show_pe_data(cp, - pe_data + len); + len += cp->pe->show_pe_data(cp, pe_data + len); } pe_data[len] = '\0'; @@ -1004,7 +1023,8 @@ static const struct seq_operations ip_vs_conn_seq_ops = { static int ip_vs_conn_open(struct inode *inode, struct file *file) { - return seq_open(file, &ip_vs_conn_seq_ops); + return seq_open_net(inode, file, &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state)); } static const struct file_operations ip_vs_conn_fops = { @@ -1031,6 +1051,10 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Origin Expires\n"); else { const struct ip_vs_conn *cp = v; + struct net *net = seq_file_net(seq); + + if (!ip_vs_conn_net_eq(cp, net)) + return 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -1067,7 +1091,8 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = { static int ip_vs_conn_sync_open(struct inode *inode, struct file *file) { - return seq_open(file, &ip_vs_conn_sync_seq_ops); + return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state)); } static const struct file_operations ip_vs_conn_sync_fops = { @@ -1113,7 +1138,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp) } /* Called from keventd and must protect itself from softirqs */ -void ip_vs_random_dropentry(void) +void ip_vs_random_dropentry(struct net *net) { int idx; struct ip_vs_conn *cp; @@ -1133,7 +1158,8 @@ void ip_vs_random_dropentry(void) if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; - + if (!ip_vs_conn_net_eq(cp, net)) + continue; if (cp->protocol == IPPROTO_TCP) { switch(cp->state) { case IP_VS_TCP_S_SYN_RECV: @@ -1168,12 +1194,13 @@ void ip_vs_random_dropentry(void) /* * Flush all the connection entries in the ip_vs_conn_tab */ -static void ip_vs_conn_flush(void) +static void ip_vs_conn_flush(struct net *net) { int idx; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net_ipvs(net); - flush_again: +flush_again: for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { /* * Lock is actually needed in this loop. @@ -1181,7 +1208,8 @@ static void ip_vs_conn_flush(void) ct_write_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { - + if (!ip_vs_conn_net_eq(cp, net)) + continue; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); if (cp->control) { @@ -1194,16 +1222,41 @@ static void ip_vs_conn_flush(void) /* the counter may be not NULL, because maybe some conn entries are run by slow timer handler or unhashed but still referred */ - if (atomic_read(&ip_vs_conn_count) != 0) { + if (atomic_read(&ipvs->conn_count) != 0) { schedule(); goto flush_again; } } +/* + * per netns init and exit + */ +int __net_init __ip_vs_conn_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + atomic_set(&ipvs->conn_count, 0); + + proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops); + proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops); + return 0; +} +static void __net_exit __ip_vs_conn_cleanup(struct net *net) +{ + /* flush all the connection entries first */ + ip_vs_conn_flush(net); + proc_net_remove(net, "ip_vs_conn"); + proc_net_remove(net, "ip_vs_conn_sync"); +} +static struct pernet_operations ipvs_conn_ops = { + .init = __ip_vs_conn_init, + .exit = __ip_vs_conn_cleanup, +}; int __init ip_vs_conn_init(void) { int idx; + int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1241,24 +1294,18 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - proc_net_fops_create(&init_net, "ip_vs_conn", 0, &ip_vs_conn_fops); - proc_net_fops_create(&init_net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops); + retc = register_pernet_subsys(&ipvs_conn_ops); /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return 0; + return retc; } - void ip_vs_conn_cleanup(void) { - /* flush all the connection entries first */ - ip_vs_conn_flush(); - + unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); - proc_net_remove(&init_net, "ip_vs_conn"); - proc_net_remove(&init_net, "ip_vs_conn_sync"); vfree(ip_vs_conn_tab); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b4e51e9..4d06617 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -41,6 +41,7 @@ #include <net/icmp.h> /* for icmp_send */ #include <net/route.h> #include <net/ip6_checksum.h> +#include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> @@ -68,6 +69,12 @@ EXPORT_SYMBOL(ip_vs_conn_put); EXPORT_SYMBOL(ip_vs_get_debug_level); #endif +int ip_vs_net_id __read_mostly; +#ifdef IP_VS_GENERIC_NETNS +EXPORT_SYMBOL(ip_vs_net_id); +#endif +/* netns cnt used for uniqueness */ +static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) @@ -108,21 +115,28 @@ static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { - spin_lock(&dest->stats.lock); - dest->stats.ustats.inpkts++; - dest->stats.ustats.inbytes += skb->len; - spin_unlock(&dest->stats.lock); - - spin_lock(&dest->svc->stats.lock); - dest->svc->stats.ustats.inpkts++; - dest->svc->stats.ustats.inbytes += skb->len; - spin_unlock(&dest->svc->stats.lock); - - spin_lock(&ip_vs_stats.lock); - ip_vs_stats.ustats.inpkts++; - ip_vs_stats.ustats.inbytes += skb->len; - spin_unlock(&ip_vs_stats.lock); + struct ip_vs_cpu_stats *s; + + s = this_cpu_ptr(dest->stats.cpustats); + s->ustats.inpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.inbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(dest->svc->stats.cpustats); + s->ustats.inpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.inbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(ipvs->cpustats); + s->ustats.inpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.inbytes += skb->len; + u64_stats_update_end(&s->syncp); } } @@ -131,21 +145,28 @@ static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { - spin_lock(&dest->stats.lock); - dest->stats.ustats.outpkts++; - dest->stats.ustats.outbytes += skb->len; - spin_unlock(&dest->stats.lock); - - spin_lock(&dest->svc->stats.lock); - dest->svc->stats.ustats.outpkts++; - dest->svc->stats.ustats.outbytes += skb->len; - spin_unlock(&dest->svc->stats.lock); - - spin_lock(&ip_vs_stats.lock); - ip_vs_stats.ustats.outpkts++; - ip_vs_stats.ustats.outbytes += skb->len; - spin_unlock(&ip_vs_stats.lock); + struct ip_vs_cpu_stats *s; + + s = this_cpu_ptr(dest->stats.cpustats); + s->ustats.outpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.outbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(dest->svc->stats.cpustats); + s->ustats.outpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.outbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(ipvs->cpustats); + s->ustats.outpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.outbytes += skb->len; + u64_stats_update_end(&s->syncp); } } @@ -153,41 +174,44 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { - spin_lock(&cp->dest->stats.lock); - cp->dest->stats.ustats.conns++; - spin_unlock(&cp->dest->stats.lock); + struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct ip_vs_cpu_stats *s; + + s = this_cpu_ptr(cp->dest->stats.cpustats); + s->ustats.conns++; - spin_lock(&svc->stats.lock); - svc->stats.ustats.conns++; - spin_unlock(&svc->stats.lock); + s = this_cpu_ptr(svc->stats.cpustats); + s->ustats.conns++; - spin_lock(&ip_vs_stats.lock); - ip_vs_stats.ustats.conns++; - spin_unlock(&ip_vs_stats.lock); + s = this_cpu_ptr(ipvs->cpustats); + s->ustats.conns++; } static inline int ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { - if (unlikely(!pp->state_transition)) + if (unlikely(!pd->pp->state_transition)) return 0; - return pp->state_transition(cp, direction, skb, pp); + return pd->pp->state_transition(cp, direction, skb, pd); } -static inline void +static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p); + ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr, + vport, p); p->pe = svc->pe; if (p->pe && p->pe->fill_param) - p->pe->fill_param(p, skb); + return p->pe->fill_param(p, skb); + + return 0; } /* @@ -200,7 +224,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, - __be16 ports[2]) + __be16 src_port, __be16 dst_port, int *ignored) { struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; @@ -224,8 +248,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc, IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", - IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]), - IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]), + IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port), + IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* @@ -247,14 +271,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc, const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; __be16 vport = 0; - if (ports[1] == svc->port) { + if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) - vport = ports[1]; + vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. @@ -268,24 +292,31 @@ ip_vs_sched_persist(struct ip_vs_service *svc, vaddr = &fwmark; } } - ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, - vaddr, vport, ¶m); + /* return *ignored = -1 so NF_DROP can be used */ + if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, + vaddr, vport, ¶m) < 0) { + *ignored = -1; + return NULL; + } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct)) { - /* No template found or the dest of the connection + /* + * No template found or the dest of the connection * template is not available. + * return *ignored=0 i.e. ICMP and NF_DROP */ dest = svc->scheduler->schedule(svc, skb); if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); + *ignored = 0; return NULL; } - if (ports[1] == svc->port && svc->port != FTPPORT) + if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template @@ -293,9 +324,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, &dest->addr, dport, - IP_VS_CONN_F_TEMPLATE, dest); + IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); + *ignored = -1; return NULL; } @@ -306,7 +338,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, kfree(param.pe_data); } - dport = ports[1]; + dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; @@ -317,11 +349,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0], - &iph.daddr, ports[1], ¶m); - cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest); + ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr, + src_port, &iph.daddr, dst_port, ¶m); + + cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); + *ignored = -1; return NULL; } @@ -341,11 +375,27 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP + * + * Usage of *ignored + * + * 1 : protocol tried to schedule (eg. on SYN), found svc but the + * svc/scheduler decides that this packet should be accepted with + * NF_ACCEPT because it must not be scheduled. + * + * 0 : scheduler can not find destination, so try bypass or + * return ICMP and then NF_DROP (ip_vs_leave). + * + * -1 : scheduler tried to schedule but fatal error occurred, eg. + * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param + * failure such as missing Call-ID, ENOMEM on skb_linearize + * or pe_data. In this case we should return NF_DROP without + * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored) + struct ip_vs_proto_data *pd, int *ignored) { + struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; struct ip_vs_dest *dest; @@ -371,12 +421,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } /* - * Do not schedule replies from local real server. It is risky - * for fwmark services but mostly for persistent services. + * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && - (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) && - (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) { + (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) { IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, "Not scheduling reply for existing connection"); __ip_vs_conn_put(cp); @@ -386,10 +434,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, /* * Persistent service */ - if (svc->flags & IP_VS_SVC_F_PERSISTENT) { - *ignored = 0; - return ip_vs_sched_persist(svc, skb, pptr); - } + if (svc->flags & IP_VS_SVC_F_PERSISTENT) + return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored); + + *ignored = 0; /* * Non-persistent service @@ -402,8 +450,6 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, return NULL; } - *ignored = 0; - dest = svc->scheduler->schedule(svc, skb); if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); @@ -419,13 +465,17 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, - pptr[0], &iph.daddr, pptr[1], &p); + + ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, + &iph.saddr, pptr[0], &iph.daddr, pptr[1], + &p); cp = ip_vs_conn_new(&p, &dest->addr, dest->port ? dest->port : pptr[1], - flags, dest); - if (!cp) + flags, dest, skb->mark); + if (!cp) { + *ignored = -1; return NULL; + } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " @@ -447,11 +497,14 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { + struct net *net; + struct netns_ipvs *ipvs; __be16 _ports[2], *pptr; struct ip_vs_iphdr iph; int unicast; + ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); @@ -459,18 +512,20 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_service_put(svc); return NF_DROP; } + net = skb_net(skb); #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST; else #endif - unicast = (inet_addr_type(&init_net, iph.daddr.ip) == RTN_UNICAST); + unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST); /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ - if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) { + ipvs = net_ipvs(net); + if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) { int ret, cs; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && @@ -484,12 +539,12 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->af, iph.protocol, + ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr, pptr[0], &iph.daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, - NULL); + NULL, skb->mark); if (!cp) return NF_DROP; } @@ -498,10 +553,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_in_stats(cp, skb); /* set state */ - cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp); + cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ - ret = cp->packet_xmit(skb, cp, pp); + ret = cp->packet_xmit(skb, cp, pd->pp); /* do not touch skb anymore */ atomic_inc(&cp->in_pkts); @@ -682,6 +737,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl) { + struct netns_ipvs *ipvs; unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != 0) { @@ -703,6 +759,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, if (!skb_make_writable(skb, offset)) goto out; + ipvs = net_ipvs(skb_net(skb)); + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); @@ -712,11 +770,11 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0) + if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0) goto out; } else #endif - if ((sysctl_ip_vs_snat_reroute || + if ((ipvs->sysctl_snat_reroute || skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) goto out; @@ -808,7 +866,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, ip_vs_fill_iphdr(AF_INET, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1); if (!cp) return NF_ACCEPT; @@ -885,7 +943,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, ip_vs_fill_iphdr(AF_INET6, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1); if (!cp) return NF_ACCEPT; @@ -924,9 +982,12 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) * Used for NAT and local client. */ static unsigned int -handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int ihl) { + struct ip_vs_protocol *pp = pd->pp; + struct netns_ipvs *ipvs; + IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); if (!skb_make_writable(skb, ihl)) @@ -961,13 +1022,15 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * if it came from this machine itself. So re-compute * the routing information. */ + ipvs = net_ipvs(skb_net(skb)); + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0) + if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0) goto drop; } else #endif - if ((sysctl_ip_vs_snat_reroute || + if ((ipvs->sysctl_snat_reroute || skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) goto drop; @@ -975,7 +1038,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); ip_vs_out_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); @@ -999,9 +1062,12 @@ drop: static unsigned int ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) { + struct net *net = NULL; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs; EnterFunction(11); @@ -1022,6 +1088,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely(!skb_dst(skb))) return NF_ACCEPT; + net = skb_net(skb); ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1045,9 +1112,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - pp = ip_vs_proto_get(iph.protocol); - if (unlikely(!pp)) + pd = ip_vs_proto_data_get(net, iph.protocol); + if (unlikely(!pd)) return NF_ACCEPT; + pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 @@ -1073,11 +1141,12 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0); + cp = pp->conn_out_get(af, skb, &iph, iph.len, 0); + ipvs = net_ipvs(net); if (likely(cp)) - return handle_response(af, skb, pp, cp, iph.len); - if (sysctl_ip_vs_nat_icmp_send && + return handle_response(af, skb, pd, cp, iph.len); + if (ipvs->sysctl_nat_icmp_send && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { @@ -1087,7 +1156,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ - if (ip_vs_lookup_real_service(af, iph.protocol, + if (ip_vs_lookup_real_service(net, af, iph.protocol, &iph.saddr, pptr[0])) { /* @@ -1202,12 +1271,14 @@ ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb, static int ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) { + struct net *net = NULL; struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; unsigned int offset, ihl, verdict; union nf_inet_addr snet; @@ -1249,9 +1320,11 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->protocol); - if (!pp) + net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); + if (!pd) return NF_ACCEPT; + pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && @@ -1265,10 +1338,10 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ip_vs_fill_iphdr(AF_INET, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET, skb, pp, &ciph, offset, 1); + cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1); if (!cp) { /* The packet could also belong to a local client */ - cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1); if (cp) { snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, @@ -1312,6 +1385,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) { + struct net *net = NULL; struct ipv6hdr *iph; struct icmp6hdr _icmph, *ic; struct ipv6hdr _ciph, *cih; /* The ip header contained @@ -1319,6 +1393,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; unsigned int offset, verdict; union nf_inet_addr snet; struct rt6_info *rt; @@ -1361,9 +1436,11 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->nexthdr); - if (!pp) + net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->nexthdr); + if (!pd) return NF_ACCEPT; + pp = pd->pp; /* Is the embedded protocol header present? */ /* TODO: we don't support fragmentation at the moment anyways */ @@ -1377,10 +1454,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) ip_vs_fill_iphdr(AF_INET6, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET6, skb, pp, &ciph, offset, 1); + cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1); if (!cp) { /* The packet could also belong to a local client */ - cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1); if (cp) { ipv6_addr_copy(&snet.in6, &iph->saddr); return handle_response_icmp(AF_INET6, skb, &snet, @@ -1423,10 +1500,13 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) static unsigned int ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) { + struct net *net; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, restart, pkts; + struct netns_ipvs *ipvs; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -1480,20 +1560,21 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } + net = skb_net(skb); /* Protocol supported? */ - pp = ip_vs_proto_get(iph.protocol); - if (unlikely(!pp)) + pd = ip_vs_proto_data_get(net, iph.protocol); + if (unlikely(!pd)) return NF_ACCEPT; - + pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(af, skb, pp, &iph, iph.len, 0); + cp = pp->conn_in_get(af, skb, &iph, iph.len, 0); if (unlikely(!cp)) { int v; - if (!pp->conn_schedule(af, skb, pp, &v, &cp)) + if (!pp->conn_schedule(af, skb, pd, &v, &cp)) return v; } @@ -1505,12 +1586,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - + net = skb_net(skb); + ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ - if (sysctl_ip_vs_expire_nodest_conn) { + if (ipvs->sysctl_expire_nodest_conn) { /* try to expire the connection immediately */ ip_vs_conn_expire_now(cp); } @@ -1521,7 +1603,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } ip_vs_in_stats(cp, skb); - restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp); + restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp); /* do not touch skb anymore */ @@ -1535,35 +1617,41 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout + * + * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ - pkts = atomic_add_return(1, &cp->in_pkts); - if (af == AF_INET && (ip_vs_sync_state & IP_VS_STATE_MASTER) && + + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + pkts = ipvs->sysctl_sync_threshold[0]; + else + pkts = atomic_add_return(1, &cp->in_pkts); + + if ((ipvs->sync_state & IP_VS_STATE_MASTER) && cp->protocol == IPPROTO_SCTP) { if ((cp->state == IP_VS_SCTP_S_ESTABLISHED && - (pkts % sysctl_ip_vs_sync_threshold[1] - == sysctl_ip_vs_sync_threshold[0])) || + (pkts % ipvs->sysctl_sync_threshold[1] + == ipvs->sysctl_sync_threshold[0])) || (cp->old_state != cp->state && ((cp->state == IP_VS_SCTP_S_CLOSED) || (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) || (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) { - ip_vs_sync_conn(cp); + ip_vs_sync_conn(net, cp); goto out; } } /* Keep this block last: TCP and others with pp->num_states <= 1 */ - else if (af == AF_INET && - (ip_vs_sync_state & IP_VS_STATE_MASTER) && + else if ((ipvs->sync_state & IP_VS_STATE_MASTER) && (((cp->protocol != IPPROTO_TCP || cp->state == IP_VS_TCP_S_ESTABLISHED) && - (pkts % sysctl_ip_vs_sync_threshold[1] - == sysctl_ip_vs_sync_threshold[0])) || + (pkts % ipvs->sysctl_sync_threshold[1] + == ipvs->sysctl_sync_threshold[0])) || ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && ((cp->state == IP_VS_TCP_S_FIN_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || (cp->state == IP_VS_TCP_S_CLOSE_WAIT) || (cp->state == IP_VS_TCP_S_TIME_WAIT))))) - ip_vs_sync_conn(cp); + ip_vs_sync_conn(net, cp); out: cp->old_state = cp->state; @@ -1782,7 +1870,39 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { }, #endif }; +/* + * Initialize IP Virtual Server netns mem. + */ +static int __net_init __ip_vs_init(struct net *net) +{ + struct netns_ipvs *ipvs; + + ipvs = net_generic(net, ip_vs_net_id); + if (ipvs == NULL) { + pr_err("%s(): no memory.\n", __func__); + return -ENOMEM; + } + ipvs->net = net; + /* Counters used for creating unique names */ + ipvs->gen = atomic_read(&ipvs_netns_cnt); + atomic_inc(&ipvs_netns_cnt); + net->ipvs = ipvs; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", + sizeof(struct netns_ipvs), ipvs->gen); + return 0; +} +static void __net_exit __ip_vs_cleanup(struct net *net) +{ + IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); +} + +static struct pernet_operations ipvs_core_ops = { + .init = __ip_vs_init, + .exit = __ip_vs_cleanup, + .id = &ip_vs_net_id, + .size = sizeof(struct netns_ipvs), +}; /* * Initialize IP Virtual Server @@ -1791,8 +1911,11 @@ static int __init ip_vs_init(void) { int ret; - ip_vs_estimator_init(); + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + return ret; + ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); @@ -1813,15 +1936,23 @@ static int __init ip_vs_init(void) goto cleanup_app; } + ret = ip_vs_sync_init(); + if (ret < 0) { + pr_err("can't setup sync data.\n"); + goto cleanup_conn; + } + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_conn; + goto cleanup_sync; } pr_info("ipvs loaded.\n"); return ret; +cleanup_sync: + ip_vs_sync_cleanup(); cleanup_conn: ip_vs_conn_cleanup(); cleanup_app: @@ -1831,17 +1962,20 @@ static int __init ip_vs_init(void) ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 22f7ad5..c73b0c8 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -38,6 +38,7 @@ #include <linux/mutex.h> #include <net/net_namespace.h> +#include <linux/nsproxy.h> #include <net/ip.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> @@ -57,42 +58,7 @@ static DEFINE_MUTEX(__ip_vs_mutex); /* lock for service table */ static DEFINE_RWLOCK(__ip_vs_svc_lock); -/* lock for table with the real services */ -static DEFINE_RWLOCK(__ip_vs_rs_lock); - -/* lock for state and timeout tables */ -static DEFINE_SPINLOCK(ip_vs_securetcp_lock); - -/* lock for drop entry handling */ -static DEFINE_SPINLOCK(__ip_vs_dropentry_lock); - -/* lock for drop packet handling */ -static DEFINE_SPINLOCK(__ip_vs_droppacket_lock); - -/* 1/rate drop and drop-entry variables */ -int ip_vs_drop_rate = 0; -int ip_vs_drop_counter = 0; -static atomic_t ip_vs_dropentry = ATOMIC_INIT(0); - -/* number of virtual services */ -static int ip_vs_num_services = 0; - /* sysctl variables */ -static int sysctl_ip_vs_drop_entry = 0; -static int sysctl_ip_vs_drop_packet = 0; -static int sysctl_ip_vs_secure_tcp = 0; -static int sysctl_ip_vs_amemthresh = 1024; -static int sysctl_ip_vs_am_droprate = 10; -int sysctl_ip_vs_cache_bypass = 0; -int sysctl_ip_vs_expire_nodest_conn = 0; -int sysctl_ip_vs_expire_quiescent_template = 0; -int sysctl_ip_vs_sync_threshold[2] = { 3, 50 }; -int sysctl_ip_vs_nat_icmp_send = 0; -#ifdef CONFIG_IP_VS_NFCT -int sysctl_ip_vs_conntrack; -#endif -int sysctl_ip_vs_snat_reroute = 1; - #ifdef CONFIG_IP_VS_DEBUG static int sysctl_ip_vs_debug_level = 0; @@ -105,7 +71,8 @@ int ip_vs_get_debug_level(void) #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ -static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) +static int __ip_vs_addr_is_local_v6(struct net *net, + const struct in6_addr *addr) { struct rt6_info *rt; struct flowi fl = { @@ -114,7 +81,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) .fl6_src = { .s6_addr32 = {0, 0, 0, 0} }, }; - rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); + rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl); if (rt && rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK)) return 1; @@ -125,7 +92,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) * update_defense_level is called from keventd and from sysctl, * so it needs to protect itself from softirqs */ -static void update_defense_level(void) +static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; static int old_secure_tcp = 0; @@ -141,73 +108,73 @@ static void update_defense_level(void) /* si_swapinfo(&i); */ /* availmem = availmem - (i.totalswap - i.freeswap); */ - nomem = (availmem < sysctl_ip_vs_amemthresh); + nomem = (availmem < ipvs->sysctl_amemthresh); local_bh_disable(); /* drop_entry */ - spin_lock(&__ip_vs_dropentry_lock); - switch (sysctl_ip_vs_drop_entry) { + spin_lock(&ipvs->dropentry_lock); + switch (ipvs->sysctl_drop_entry) { case 0: - atomic_set(&ip_vs_dropentry, 0); + atomic_set(&ipvs->dropentry, 0); break; case 1: if (nomem) { - atomic_set(&ip_vs_dropentry, 1); - sysctl_ip_vs_drop_entry = 2; + atomic_set(&ipvs->dropentry, 1); + ipvs->sysctl_drop_entry = 2; } else { - atomic_set(&ip_vs_dropentry, 0); + atomic_set(&ipvs->dropentry, 0); } break; case 2: if (nomem) { - atomic_set(&ip_vs_dropentry, 1); + atomic_set(&ipvs->dropentry, 1); } else { - atomic_set(&ip_vs_dropentry, 0); - sysctl_ip_vs_drop_entry = 1; + atomic_set(&ipvs->dropentry, 0); + ipvs->sysctl_drop_entry = 1; }; break; case 3: - atomic_set(&ip_vs_dropentry, 1); + atomic_set(&ipvs->dropentry, 1); break; } - spin_unlock(&__ip_vs_dropentry_lock); + spin_unlock(&ipvs->dropentry_lock); /* drop_packet */ - spin_lock(&__ip_vs_droppacket_lock); - switch (sysctl_ip_vs_drop_packet) { + spin_lock(&ipvs->droppacket_lock); + switch (ipvs->sysctl_drop_packet) { case 0: - ip_vs_drop_rate = 0; + ipvs->drop_rate = 0; break; case 1: if (nomem) { - ip_vs_drop_rate = ip_vs_drop_counter - = sysctl_ip_vs_amemthresh / - (sysctl_ip_vs_amemthresh-availmem); - sysctl_ip_vs_drop_packet = 2; + ipvs->drop_rate = ipvs->drop_counter + = ipvs->sysctl_amemthresh / + (ipvs->sysctl_amemthresh-availmem); + ipvs->sysctl_drop_packet = 2; } else { - ip_vs_drop_rate = 0; + ipvs->drop_rate = 0; } break; case 2: if (nomem) { - ip_vs_drop_rate = ip_vs_drop_counter - = sysctl_ip_vs_amemthresh / - (sysctl_ip_vs_amemthresh-availmem); + ipvs->drop_rate = ipvs->drop_counter + = ipvs->sysctl_amemthresh / + (ipvs->sysctl_amemthresh-availmem); } else { - ip_vs_drop_rate = 0; - sysctl_ip_vs_drop_packet = 1; + ipvs->drop_rate = 0; + ipvs->sysctl_drop_packet = 1; } break; case 3: - ip_vs_drop_rate = sysctl_ip_vs_am_droprate; + ipvs->drop_rate = ipvs->sysctl_am_droprate; break; } - spin_unlock(&__ip_vs_droppacket_lock); + spin_unlock(&ipvs->droppacket_lock); /* secure_tcp */ - spin_lock(&ip_vs_securetcp_lock); - switch (sysctl_ip_vs_secure_tcp) { + spin_lock(&ipvs->securetcp_lock); + switch (ipvs->sysctl_secure_tcp) { case 0: if (old_secure_tcp >= 2) to_change = 0; @@ -216,7 +183,7 @@ static void update_defense_level(void) if (nomem) { if (old_secure_tcp < 2) to_change = 1; - sysctl_ip_vs_secure_tcp = 2; + ipvs->sysctl_secure_tcp = 2; } else { if (old_secure_tcp >= 2) to_change = 0; @@ -229,7 +196,7 @@ static void update_defense_level(void) } else { if (old_secure_tcp >= 2) to_change = 0; - sysctl_ip_vs_secure_tcp = 1; + ipvs->sysctl_secure_tcp = 1; } break; case 3: @@ -237,10 +204,11 @@ static void update_defense_level(void) to_change = 1; break; } - old_secure_tcp = sysctl_ip_vs_secure_tcp; + old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) - ip_vs_protocol_timeout_change(sysctl_ip_vs_secure_tcp>1); - spin_unlock(&ip_vs_securetcp_lock); + ip_vs_protocol_timeout_change(ipvs, + ipvs->sysctl_secure_tcp > 1); + spin_unlock(&ipvs->securetcp_lock); local_bh_enable(); } @@ -250,16 +218,16 @@ static void update_defense_level(void) * Timer for checking the defense */ #define DEFENSE_TIMER_PERIOD 1*HZ -static void defense_work_handler(struct work_struct *work); -static DECLARE_DELAYED_WORK(defense_work, defense_work_handler); static void defense_work_handler(struct work_struct *work) { - update_defense_level(); - if (atomic_read(&ip_vs_dropentry)) - ip_vs_random_dropentry(); + struct netns_ipvs *ipvs = + container_of(work, struct netns_ipvs, defense_work.work); - schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD); + update_defense_level(ipvs); + if (atomic_read(&ipvs->dropentry)) + ip_vs_random_dropentry(ipvs->net); + schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); } int @@ -287,33 +255,13 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE]; /* the service table hashed by fwmark */ static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE]; -/* - * Hash table: for real service lookups - */ -#define IP_VS_RTAB_BITS 4 -#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) -#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) - -static struct list_head ip_vs_rtable[IP_VS_RTAB_SIZE]; - -/* - * Trash for destinations - */ -static LIST_HEAD(ip_vs_dest_trash); - -/* - * FTP & NULL virtual service counters - */ -static atomic_t ip_vs_ftpsvc_counter = ATOMIC_INIT(0); -static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0); - /* * Returns hash value for virtual service */ -static __inline__ unsigned -ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, - __be16 port) +static inline unsigned +ip_vs_svc_hashkey(struct net *net, int af, unsigned proto, + const union nf_inet_addr *addr, __be16 port) { register unsigned porth = ntohs(port); __be32 addr_fold = addr->ip; @@ -323,6 +271,7 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif + addr_fold ^= ((size_t)net>>8); return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth) & IP_VS_SVC_TAB_MASK; @@ -331,13 +280,13 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, /* * Returns hash value of fwmark for virtual service lookup */ -static __inline__ unsigned ip_vs_svc_fwm_hashkey(__u32 fwmark) +static inline unsigned ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark) { - return fwmark & IP_VS_SVC_TAB_MASK; + return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK; } /* - * Hashes a service in the ip_vs_svc_table by <proto,addr,port> + * Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port> * or in the ip_vs_svc_fwm_table by fwmark. * Should be called with locked tables. */ @@ -353,16 +302,16 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) if (svc->fwmark == 0) { /* - * Hash it by <protocol,addr,port> in ip_vs_svc_table + * Hash it by <netns,protocol,addr,port> in ip_vs_svc_table */ - hash = ip_vs_svc_hashkey(svc->af, svc->protocol, &svc->addr, - svc->port); + hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol, + &svc->addr, svc->port); list_add(&svc->s_list, &ip_vs_svc_table[hash]); } else { /* - * Hash it by fwmark in ip_vs_svc_fwm_table + * Hash it by fwmark in svc_fwm_table */ - hash = ip_vs_svc_fwm_hashkey(svc->fwmark); + hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark); list_add(&svc->f_list, &ip_vs_svc_fwm_table[hash]); } @@ -374,7 +323,7 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) /* - * Unhashes a service from ip_vs_svc_table/ip_vs_svc_fwm_table. + * Unhashes a service from svc_table / svc_fwm_table. * Should be called with locked tables. */ static int ip_vs_svc_unhash(struct ip_vs_service *svc) @@ -386,10 +335,10 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) } if (svc->fwmark == 0) { - /* Remove it from the ip_vs_svc_table table */ + /* Remove it from the svc_table table */ list_del(&svc->s_list); } else { - /* Remove it from the ip_vs_svc_fwm_table table */ + /* Remove it from the svc_fwm_table table */ list_del(&svc->f_list); } @@ -400,23 +349,24 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) /* - * Get service by {proto,addr,port} in the service table. + * Get service by {netns, proto,addr,port} in the service table. */ static inline struct ip_vs_service * -__ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr, - __be16 vport) +__ip_vs_service_find(struct net *net, int af, __u16 protocol, + const union nf_inet_addr *vaddr, __be16 vport) { unsigned hash; struct ip_vs_service *svc; /* Check for "full" addressed entries */ - hash = ip_vs_svc_hashkey(af, protocol, vaddr, vport); + hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport); list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){ if ((svc->af == af) && ip_vs_addr_equal(af, &svc->addr, vaddr) && (svc->port == vport) - && (svc->protocol == protocol)) { + && (svc->protocol == protocol) + && net_eq(svc->net, net)) { /* HIT */ return svc; } @@ -430,16 +380,17 @@ __ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr, * Get service by {fwmark} in the service table. */ static inline struct ip_vs_service * -__ip_vs_svc_fwm_find(int af, __u32 fwmark) +__ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) { unsigned hash; struct ip_vs_service *svc; /* Check for fwmark addressed entries */ - hash = ip_vs_svc_fwm_hashkey(fwmark); + hash = ip_vs_svc_fwm_hashkey(net, fwmark); list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) { - if (svc->fwmark == fwmark && svc->af == af) { + if (svc->fwmark == fwmark && svc->af == af + && net_eq(svc->net, net)) { /* HIT */ return svc; } @@ -449,42 +400,44 @@ __ip_vs_svc_fwm_find(int af, __u32 fwmark) } struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { struct ip_vs_service *svc; + struct netns_ipvs *ipvs = net_ipvs(net); read_lock(&__ip_vs_svc_lock); /* * Check the table hashed by fwmark first */ - if (fwmark && (svc = __ip_vs_svc_fwm_find(af, fwmark))) + svc = __ip_vs_svc_fwm_find(net, af, fwmark); + if (fwmark && svc) goto out; /* * Check the table hashed by <protocol,addr,port> * for "full" addressed entries */ - svc = __ip_vs_service_find(af, protocol, vaddr, vport); + svc = __ip_vs_service_find(net, af, protocol, vaddr, vport); if (svc == NULL && protocol == IPPROTO_TCP - && atomic_read(&ip_vs_ftpsvc_counter) + && atomic_read(&ipvs->ftpsvc_counter) && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) { /* * Check if ftp service entry exists, the packet * might belong to FTP data connections. */ - svc = __ip_vs_service_find(af, protocol, vaddr, FTPPORT); + svc = __ip_vs_service_find(net, af, protocol, vaddr, FTPPORT); } if (svc == NULL - && atomic_read(&ip_vs_nullsvc_counter)) { + && atomic_read(&ipvs->nullsvc_counter)) { /* * Check if the catch-all port (port zero) exists */ - svc = __ip_vs_service_find(af, protocol, vaddr, 0); + svc = __ip_vs_service_find(net, af, protocol, vaddr, 0); } out: @@ -519,6 +472,7 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest) svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port), atomic_read(&svc->usecnt)); + free_percpu(svc->stats.cpustats); kfree(svc); } } @@ -545,10 +499,10 @@ static inline unsigned ip_vs_rs_hashkey(int af, } /* - * Hashes ip_vs_dest in ip_vs_rtable by <proto,addr,port>. + * Hashes ip_vs_dest in rs_table by <proto,addr,port>. * should be called with locked tables. */ -static int ip_vs_rs_hash(struct ip_vs_dest *dest) +static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { unsigned hash; @@ -562,19 +516,19 @@ static int ip_vs_rs_hash(struct ip_vs_dest *dest) */ hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port); - list_add(&dest->d_list, &ip_vs_rtable[hash]); + list_add(&dest->d_list, &ipvs->rs_table[hash]); return 1; } /* - * UNhashes ip_vs_dest from ip_vs_rtable. + * UNhashes ip_vs_dest from rs_table. * should be called with locked tables. */ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) { /* - * Remove it from the ip_vs_rtable table. + * Remove it from the rs_table table. */ if (!list_empty(&dest->d_list)) { list_del(&dest->d_list); @@ -588,10 +542,11 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) * Lookup real service by <proto,addr,port> in the real service table. */ struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport) { + struct netns_ipvs *ipvs = net_ipvs(net); unsigned hash; struct ip_vs_dest *dest; @@ -601,19 +556,19 @@ ip_vs_lookup_real_service(int af, __u16 protocol, */ hash = ip_vs_rs_hashkey(af, daddr, dport); - read_lock(&__ip_vs_rs_lock); - list_for_each_entry(dest, &ip_vs_rtable[hash], d_list) { + read_lock(&ipvs->rs_lock); + list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) { if ((dest->af == af) && ip_vs_addr_equal(af, &dest->addr, daddr) && (dest->port == dport) && ((dest->protocol == protocol) || dest->vfwmark)) { /* HIT */ - read_unlock(&__ip_vs_rs_lock); + read_unlock(&ipvs->rs_lock); return dest; } } - read_unlock(&__ip_vs_rs_lock); + read_unlock(&ipvs->rs_lock); return NULL; } @@ -652,15 +607,16 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, * ip_vs_lookup_real_service() looked promissing, but * seems not working as expected. */ -struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr, +struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af, + const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, - __be16 vport, __u16 protocol) + __be16 vport, __u16 protocol, __u32 fwmark) { struct ip_vs_dest *dest; struct ip_vs_service *svc; - svc = ip_vs_service_get(af, 0, protocol, vaddr, vport); + svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; dest = ip_vs_lookup_dest(svc, daddr, dport); @@ -685,11 +641,12 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, __be16 dport) { struct ip_vs_dest *dest, *nxt; + struct netns_ipvs *ipvs = net_ipvs(svc->net); /* * Find the destination in trash */ - list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) { + list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) { IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, " "dest->refcnt=%d\n", dest->vfwmark, @@ -720,6 +677,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, list_del(&dest->n_list); ip_vs_dst_reset(dest); __ip_vs_unbind_svc(dest); + free_percpu(dest->stats.cpustats); kfree(dest); } } @@ -737,14 +695,16 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, * are expired, and the refcnt of each destination in the trash must * be 1, so we simply release them here. */ -static void ip_vs_trash_cleanup(void) +static void ip_vs_trash_cleanup(struct net *net) { struct ip_vs_dest *dest, *nxt; + struct netns_ipvs *ipvs = net_ipvs(net); - list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) { + list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) { list_del(&dest->n_list); ip_vs_dst_reset(dest); __ip_vs_unbind_svc(dest); + free_percpu(dest->stats.cpustats); kfree(dest); } } @@ -768,6 +728,7 @@ static void __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { + struct netns_ipvs *ipvs = net_ipvs(svc->net); int conn_flags; /* set the weight and the flags */ @@ -780,12 +741,12 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { /* - * Put the real service in ip_vs_rtable if not present. + * Put the real service in rs_table if not present. * For now only for NAT! */ - write_lock_bh(&__ip_vs_rs_lock); - ip_vs_rs_hash(dest); - write_unlock_bh(&__ip_vs_rs_lock); + write_lock_bh(&ipvs->rs_lock); + ip_vs_rs_hash(ipvs, dest); + write_unlock_bh(&ipvs->rs_lock); } atomic_set(&dest->conn_flags, conn_flags); @@ -813,7 +774,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock(&dest->dst_lock); if (add) - ip_vs_new_estimator(&dest->stats); + ip_vs_new_estimator(svc->net, &dest->stats); write_lock_bh(&__ip_vs_svc_lock); @@ -850,12 +811,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && - !__ip_vs_addr_is_local_v6(&udest->addr.in6)) + !__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6)) return -EINVAL; } else #endif { - atype = inet_addr_type(&init_net, udest->addr.ip); + atype = inet_addr_type(svc->net, udest->addr.ip); if (atype != RTN_LOCAL && atype != RTN_UNICAST) return -EINVAL; } @@ -865,6 +826,11 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!dest->stats.cpustats) { + pr_err("%s() alloc_percpu failed\n", __func__); + goto err_alloc; + } dest->af = svc->af; dest->protocol = svc->protocol; @@ -888,6 +854,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, LeaveFunction(2); return 0; + +err_alloc: + kfree(dest); + return -ENOMEM; } @@ -1006,16 +976,18 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete a destination (must be already unlinked from the service) */ -static void __ip_vs_del_dest(struct ip_vs_dest *dest) +static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest) { - ip_vs_kill_estimator(&dest->stats); + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_kill_estimator(net, &dest->stats); /* * Remove it from the d-linked list with the real services. */ - write_lock_bh(&__ip_vs_rs_lock); + write_lock_bh(&ipvs->rs_lock); ip_vs_rs_unhash(dest); - write_unlock_bh(&__ip_vs_rs_lock); + write_unlock_bh(&ipvs->rs_lock); /* * Decrease the refcnt of the dest, and free the dest @@ -1034,6 +1006,7 @@ static void __ip_vs_del_dest(struct ip_vs_dest *dest) and only one user context can update virtual service at a time, so the operation here is OK */ atomic_dec(&dest->svc->refcnt); + free_percpu(dest->stats.cpustats); kfree(dest); } else { IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, " @@ -1041,7 +1014,7 @@ static void __ip_vs_del_dest(struct ip_vs_dest *dest) IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); - list_add(&dest->n_list, &ip_vs_dest_trash); + list_add(&dest->n_list, &ipvs->dest_trash); atomic_inc(&dest->refcnt); } } @@ -1105,7 +1078,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete the destination */ - __ip_vs_del_dest(dest); + __ip_vs_del_dest(svc->net, dest); LeaveFunction(2); @@ -1117,13 +1090,14 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) * Add a service into the service hash table */ static int -ip_vs_add_service(struct ip_vs_service_user_kern *u, +ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, struct ip_vs_service **svc_p) { int ret = 0; struct ip_vs_scheduler *sched = NULL; struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; + struct netns_ipvs *ipvs = net_ipvs(net); /* increase the module use count */ ip_vs_use_count_inc(); @@ -1137,7 +1111,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, } if (u->pe_name && *u->pe_name) { - pe = ip_vs_pe_get(u->pe_name); + pe = ip_vs_pe_getbyname(u->pe_name); if (pe == NULL) { pr_info("persistence engine module ip_vs_pe_%s " "not found\n", u->pe_name); @@ -1159,6 +1133,11 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, ret = -ENOMEM; goto out_err; } + svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!svc->stats.cpustats) { + pr_err("%s() alloc_percpu failed\n", __func__); + goto out_err; + } /* I'm the first user of the service */ atomic_set(&svc->usecnt, 0); @@ -1172,6 +1151,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, svc->flags = u->flags; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; + svc->net = net; INIT_LIST_HEAD(&svc->destinations); rwlock_init(&svc->sched_lock); @@ -1189,15 +1169,15 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, /* Update the virtual service counters */ if (svc->port == FTPPORT) - atomic_inc(&ip_vs_ftpsvc_counter); + atomic_inc(&ipvs->ftpsvc_counter); else if (svc->port == 0) - atomic_inc(&ip_vs_nullsvc_counter); + atomic_inc(&ipvs->nullsvc_counter); - ip_vs_new_estimator(&svc->stats); + ip_vs_new_estimator(net, &svc->stats); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) - ip_vs_num_services++; + ipvs->num_services++; /* Hash the service into the service table */ write_lock_bh(&__ip_vs_svc_lock); @@ -1207,6 +1187,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, *svc_p = svc; return 0; + out_err: if (svc != NULL) { ip_vs_unbind_scheduler(svc); @@ -1215,6 +1196,8 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, ip_vs_app_inc_put(svc->inc); local_bh_enable(); } + if (svc->stats.cpustats) + free_percpu(svc->stats.cpustats); kfree(svc); } ip_vs_scheduler_put(sched); @@ -1248,7 +1231,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = sched; if (u->pe_name && *u->pe_name) { - pe = ip_vs_pe_get(u->pe_name); + pe = ip_vs_pe_getbyname(u->pe_name); if (pe == NULL) { pr_info("persistence engine module ip_vs_pe_%s " "not found\n", u->pe_name); @@ -1334,14 +1317,15 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; struct ip_vs_pe *old_pe; + struct netns_ipvs *ipvs = net_ipvs(svc->net); pr_info("%s: enter\n", __func__); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) - ip_vs_num_services--; + ipvs->num_services--; - ip_vs_kill_estimator(&svc->stats); + ip_vs_kill_estimator(svc->net, &svc->stats); /* Unbind scheduler */ old_sched = svc->scheduler; @@ -1364,16 +1348,16 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) */ list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) { __ip_vs_unlink_dest(svc, dest, 0); - __ip_vs_del_dest(dest); + __ip_vs_del_dest(svc->net, dest); } /* * Update the virtual service counters */ if (svc->port == FTPPORT) - atomic_dec(&ip_vs_ftpsvc_counter); + atomic_dec(&ipvs->ftpsvc_counter); else if (svc->port == 0) - atomic_dec(&ip_vs_nullsvc_counter); + atomic_dec(&ipvs->nullsvc_counter); /* * Free the service if nobody refers to it @@ -1383,6 +1367,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port), atomic_read(&svc->usecnt)); + free_percpu(svc->stats.cpustats); kfree(svc); } @@ -1428,17 +1413,19 @@ static int ip_vs_del_service(struct ip_vs_service *svc) /* * Flush all the virtual services */ -static int ip_vs_flush(void) +static int ip_vs_flush(struct net *net) { int idx; struct ip_vs_service *svc, *nxt; /* - * Flush the service table hashed by <protocol,addr,port> + * Flush the service table hashed by <netns,protocol,addr,port> */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { - list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], s_list) { - ip_vs_unlink_service(svc); + list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], + s_list) { + if (net_eq(svc->net, net)) + ip_vs_unlink_service(svc); } } @@ -1448,7 +1435,8 @@ static int ip_vs_flush(void) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry_safe(svc, nxt, &ip_vs_svc_fwm_table[idx], f_list) { - ip_vs_unlink_service(svc); + if (net_eq(svc->net, net)) + ip_vs_unlink_service(svc); } } @@ -1472,24 +1460,26 @@ static int ip_vs_zero_service(struct ip_vs_service *svc) return 0; } -static int ip_vs_zero_all(void) +static int ip_vs_zero_all(struct net *net) { int idx; struct ip_vs_service *svc; for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - ip_vs_zero_service(svc); + if (net_eq(svc->net, net)) + ip_vs_zero_service(svc); } } for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - ip_vs_zero_service(svc); + if (net_eq(svc->net, net)) + ip_vs_zero_service(svc); } } - ip_vs_zero_stats(&ip_vs_stats); + ip_vs_zero_stats(net_ipvs(net)->tot_stats); return 0; } @@ -1498,6 +1488,7 @@ static int proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = current->nsproxy->net_ns; int *valp = table->data; int val = *valp; int rc; @@ -1508,7 +1499,7 @@ proc_do_defense_mode(ctl_table *table, int write, /* Restore the correct value */ *valp = val; } else { - update_defense_level(); + update_defense_level(net_ipvs(net)); } } return rc; @@ -1534,45 +1525,54 @@ proc_do_sync_threshold(ctl_table *table, int write, return rc; } +static int +proc_do_sync_mode(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = table->data; + int val = *valp; + int rc; + + rc = proc_dointvec(table, write, buffer, lenp, ppos); + if (write && (*valp != val)) { + if ((*valp < 0) || (*valp > 1)) { + /* Restore the correct value */ + *valp = val; + } else { + struct net *net = current->nsproxy->net_ns; + ip_vs_sync_switch_mode(net, val); + } + } + return rc; +} /* * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/) + * Do not change order or insert new entries without + * align with netns init in __ip_vs_control_init() */ static struct ctl_table vs_vars[] = { { .procname = "amemthresh", - .data = &sysctl_ip_vs_amemthresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, -#ifdef CONFIG_IP_VS_DEBUG - { - .procname = "debug_level", - .data = &sysctl_ip_vs_debug_level, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif { .procname = "am_droprate", - .data = &sysctl_ip_vs_am_droprate, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "drop_entry", - .data = &sysctl_ip_vs_drop_entry, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, { .procname = "drop_packet", - .data = &sysctl_ip_vs_drop_packet, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, @@ -1580,7 +1580,6 @@ static struct ctl_table vs_vars[] = { #ifdef CONFIG_IP_VS_NFCT { .procname = "conntrack", - .data = &sysctl_ip_vs_conntrack, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, @@ -1588,18 +1587,62 @@ static struct ctl_table vs_vars[] = { #endif { .procname = "secure_tcp", - .data = &sysctl_ip_vs_secure_tcp, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, { .procname = "snat_reroute", - .data = &sysctl_ip_vs_snat_reroute, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, }, + { + .procname = "sync_version", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_do_sync_mode, + }, + { + .procname = "cache_bypass", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "expire_nodest_conn", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "expire_quiescent_template", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sync_threshold", + .maxlen = + sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold), + .mode = 0644, + .proc_handler = proc_do_sync_threshold, + }, + { + .procname = "nat_icmp_send", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_IP_VS_DEBUG + { + .procname = "debug_level", + .data = &sysctl_ip_vs_debug_level, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif #if 0 { .procname = "timeout_established", @@ -1686,41 +1729,6 @@ static struct ctl_table vs_vars[] = { .proc_handler = proc_dointvec_jiffies, }, #endif - { - .procname = "cache_bypass", - .data = &sysctl_ip_vs_cache_bypass, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "expire_nodest_conn", - .data = &sysctl_ip_vs_expire_nodest_conn, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "expire_quiescent_template", - .data = &sysctl_ip_vs_expire_quiescent_template, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "sync_threshold", - .data = &sysctl_ip_vs_sync_threshold, - .maxlen = sizeof(sysctl_ip_vs_sync_threshold), - .mode = 0644, - .proc_handler = proc_do_sync_threshold, - }, - { - .procname = "nat_icmp_send", - .data = &sysctl_ip_vs_nat_icmp_send, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { } }; @@ -1732,11 +1740,10 @@ const struct ctl_path net_vs_ctl_path[] = { }; EXPORT_SYMBOL_GPL(net_vs_ctl_path); -static struct ctl_table_header * sysctl_header; - #ifdef CONFIG_PROC_FS struct ip_vs_iter { + struct seq_net_private p; /* Do not move this, netns depends upon it*/ struct list_head *table; int bucket; }; @@ -1763,6 +1770,7 @@ static inline const char *ip_vs_fwd_name(unsigned flags) /* Get the Nth entry in the two lists */ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) { + struct net *net = seq_file_net(seq); struct ip_vs_iter *iter = seq->private; int idx; struct ip_vs_service *svc; @@ -1770,7 +1778,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) /* look in hash by protocol */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - if (pos-- == 0){ + if (net_eq(svc->net, net) && pos-- == 0) { iter->table = ip_vs_svc_table; iter->bucket = idx; return svc; @@ -1781,7 +1789,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) /* keep looking in fwmark */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (pos-- == 0) { + if (net_eq(svc->net, net) && pos-- == 0) { iter->table = ip_vs_svc_fwm_table; iter->bucket = idx; return svc; @@ -1935,7 +1943,7 @@ static const struct seq_operations ip_vs_info_seq_ops = { static int ip_vs_info_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &ip_vs_info_seq_ops, + return seq_open_net(inode, file, &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter)); } @@ -1949,13 +1957,11 @@ static const struct file_operations ip_vs_info_fops = { #endif -struct ip_vs_stats ip_vs_stats = { - .lock = __SPIN_LOCK_UNLOCKED(ip_vs_stats.lock), -}; - #ifdef CONFIG_PROC_FS static int ip_vs_stats_show(struct seq_file *seq, void *v) { + struct net *net = seq_file_single_net(seq); + struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, @@ -1963,29 +1969,29 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) seq_printf(seq, " Conns Packets Packets Bytes Bytes\n"); - spin_lock_bh(&ip_vs_stats.lock); - seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.ustats.conns, - ip_vs_stats.ustats.inpkts, ip_vs_stats.ustats.outpkts, - (unsigned long long) ip_vs_stats.ustats.inbytes, - (unsigned long long) ip_vs_stats.ustats.outbytes); + spin_lock_bh(&tot_stats->lock); + seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns, + tot_stats->ustats.inpkts, tot_stats->ustats.outpkts, + (unsigned long long) tot_stats->ustats.inbytes, + (unsigned long long) tot_stats->ustats.outbytes); /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); seq_printf(seq,"%8X %8X %8X %16X %16X\n", - ip_vs_stats.ustats.cps, - ip_vs_stats.ustats.inpps, - ip_vs_stats.ustats.outpps, - ip_vs_stats.ustats.inbps, - ip_vs_stats.ustats.outbps); - spin_unlock_bh(&ip_vs_stats.lock); + tot_stats->ustats.cps, + tot_stats->ustats.inpps, + tot_stats->ustats.outpps, + tot_stats->ustats.inbps, + tot_stats->ustats.outbps); + spin_unlock_bh(&tot_stats->lock); return 0; } static int ip_vs_stats_seq_open(struct inode *inode, struct file *file) { - return single_open(file, ip_vs_stats_show, NULL); + return single_open_net(inode, file, ip_vs_stats_show); } static const struct file_operations ip_vs_stats_fops = { @@ -1996,13 +2002,70 @@ static const struct file_operations ip_vs_stats_fops = { .release = single_release, }; +static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) +{ + struct net *net = seq_file_single_net(seq); + struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats; + int i; + +/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ + seq_puts(seq, + " Total Incoming Outgoing Incoming Outgoing\n"); + seq_printf(seq, + "CPU Conns Packets Packets Bytes Bytes\n"); + + for_each_possible_cpu(i) { + struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i); + seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n", + i, u->ustats.conns, u->ustats.inpkts, + u->ustats.outpkts, (__u64)u->ustats.inbytes, + (__u64)u->ustats.outbytes); + } + + spin_lock_bh(&tot_stats->lock); + seq_printf(seq, " ~ %8X %8X %8X %16LX %16LX\n\n", + tot_stats->ustats.conns, tot_stats->ustats.inpkts, + tot_stats->ustats.outpkts, + (unsigned long long) tot_stats->ustats.inbytes, + (unsigned long long) tot_stats->ustats.outbytes); + +/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ + seq_puts(seq, + " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); + seq_printf(seq, " %8X %8X %8X %16X %16X\n", + tot_stats->ustats.cps, + tot_stats->ustats.inpps, + tot_stats->ustats.outpps, + tot_stats->ustats.inbps, + tot_stats->ustats.outbps); + spin_unlock_bh(&tot_stats->lock); + + return 0; +} + +static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file) +{ + return single_open_net(inode, file, ip_vs_stats_percpu_show); +} + +static const struct file_operations ip_vs_stats_percpu_fops = { + .owner = THIS_MODULE, + .open = ip_vs_stats_percpu_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif /* * Set timeout values for tcp tcpfin udp in the timeout_table. */ -static int ip_vs_set_timeout(struct ip_vs_timeout_user *u) +static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) { +#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) + struct ip_vs_proto_data *pd; +#endif + IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n", u->tcp_timeout, u->tcp_fin_timeout, @@ -2010,19 +2073,22 @@ static int ip_vs_set_timeout(struct ip_vs_timeout_user *u) #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] + pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] = u->tcp_timeout * HZ; } if (u->tcp_fin_timeout) { - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] + pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] = u->tcp_fin_timeout * HZ; } #endif #ifdef CONFIG_IP_VS_PROTO_UDP if (u->udp_timeout) { - ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] + pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + pd->timeout_table[IP_VS_UDP_S_NORMAL] = u->udp_timeout * HZ; } #endif @@ -2087,6 +2153,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest, static int do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { + struct net *net = sock_net(sk); int ret; unsigned char arg[MAX_ARG_LEN]; struct ip_vs_service_user *usvc_compat; @@ -2121,19 +2188,20 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (cmd == IP_VS_SO_SET_FLUSH) { /* Flush the virtual service */ - ret = ip_vs_flush(); + ret = ip_vs_flush(net); goto out_unlock; } else if (cmd == IP_VS_SO_SET_TIMEOUT) { /* Set timeout values for (tcp tcpfin udp) */ - ret = ip_vs_set_timeout((struct ip_vs_timeout_user *)arg); + ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg); goto out_unlock; } else if (cmd == IP_VS_SO_SET_STARTDAEMON) { struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = start_sync_thread(dm->state, dm->mcast_ifn, dm->syncid); + ret = start_sync_thread(net, dm->state, dm->mcast_ifn, + dm->syncid); goto out_unlock; } else if (cmd == IP_VS_SO_SET_STOPDAEMON) { struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = stop_sync_thread(dm->state); + ret = stop_sync_thread(net, dm->state); goto out_unlock; } @@ -2148,7 +2216,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (cmd == IP_VS_SO_SET_ZERO) { /* if no service address is set, zero counters in all */ if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) { - ret = ip_vs_zero_all(); + ret = ip_vs_zero_all(net); goto out_unlock; } } @@ -2165,10 +2233,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Lookup the exact service by <protocol, addr, port> or fwmark */ if (usvc.fwmark == 0) - svc = __ip_vs_service_find(usvc.af, usvc.protocol, + svc = __ip_vs_service_find(net, usvc.af, usvc.protocol, &usvc.addr, usvc.port); else - svc = __ip_vs_svc_fwm_find(usvc.af, usvc.fwmark); + svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark); if (cmd != IP_VS_SO_SET_ADD && (svc == NULL || svc->protocol != usvc.protocol)) { @@ -2181,7 +2249,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (svc != NULL) ret = -EEXIST; else - ret = ip_vs_add_service(&usvc, &svc); + ret = ip_vs_add_service(net, &usvc, &svc); break; case IP_VS_SO_SET_EDIT: ret = ip_vs_edit_service(svc, &usvc); @@ -2241,7 +2309,8 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) } static inline int -__ip_vs_get_service_entries(const struct ip_vs_get_services *get, +__ip_vs_get_service_entries(struct net *net, + const struct ip_vs_get_services *get, struct ip_vs_get_services __user *uptr) { int idx, count=0; @@ -2252,7 +2321,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET) + if (svc->af != AF_INET || !net_eq(svc->net, net)) continue; if (count >= get->num_services) @@ -2271,7 +2340,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET) + if (svc->af != AF_INET || !net_eq(svc->net, net)) continue; if (count >= get->num_services) @@ -2291,7 +2360,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, } static inline int -__ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, +__ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, struct ip_vs_get_dests __user *uptr) { struct ip_vs_service *svc; @@ -2299,9 +2368,9 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, int ret = 0; if (get->fwmark) - svc = __ip_vs_svc_fwm_find(AF_INET, get->fwmark); + svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark); else - svc = __ip_vs_service_find(AF_INET, get->protocol, &addr, + svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr, get->port); if (svc) { @@ -2336,17 +2405,21 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, } static inline void -__ip_vs_get_timeouts(struct ip_vs_timeout_user *u) +__ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) { +#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) + struct ip_vs_proto_data *pd; +#endif + #ifdef CONFIG_IP_VS_PROTO_TCP - u->tcp_timeout = - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; - u->tcp_fin_timeout = - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; + pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; + u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; #endif #ifdef CONFIG_IP_VS_PROTO_UDP + pd = ip_vs_proto_data_get(net, IPPROTO_UDP); u->udp_timeout = - ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] / HZ; + pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ; #endif } @@ -2375,7 +2448,10 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) unsigned char arg[128]; int ret = 0; unsigned int copylen; + struct net *net = sock_net(sk); + struct netns_ipvs *ipvs = net_ipvs(net); + BUG_ON(!net); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -2418,7 +2494,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct ip_vs_getinfo info; info.version = IP_VS_VERSION_CODE; info.size = ip_vs_conn_tab_size; - info.num_services = ip_vs_num_services; + info.num_services = ipvs->num_services; if (copy_to_user(user, &info, sizeof(info)) != 0) ret = -EFAULT; } @@ -2437,7 +2513,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; goto out; } - ret = __ip_vs_get_service_entries(get, user); + ret = __ip_vs_get_service_entries(net, get, user); } break; @@ -2450,10 +2526,11 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) entry = (struct ip_vs_service_entry *)arg; addr.ip = entry->addr; if (entry->fwmark) - svc = __ip_vs_svc_fwm_find(AF_INET, entry->fwmark); + svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark); else - svc = __ip_vs_service_find(AF_INET, entry->protocol, - &addr, entry->port); + svc = __ip_vs_service_find(net, AF_INET, + entry->protocol, &addr, + entry->port); if (svc) { ip_vs_copy_service(entry, svc); if (copy_to_user(user, entry, sizeof(*entry)) != 0) @@ -2476,7 +2553,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; goto out; } - ret = __ip_vs_get_dest_entries(get, user); + ret = __ip_vs_get_dest_entries(net, get, user); } break; @@ -2484,7 +2561,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(&t); + __ip_vs_get_timeouts(net, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; } @@ -2495,15 +2572,17 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct ip_vs_daemon_user d[2]; memset(&d, 0, sizeof(d)); - if (ip_vs_sync_state & IP_VS_STATE_MASTER) { + if (ipvs->sync_state & IP_VS_STATE_MASTER) { d[0].state = IP_VS_STATE_MASTER; - strlcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn, sizeof(d[0].mcast_ifn)); - d[0].syncid = ip_vs_master_syncid; + strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, + sizeof(d[0].mcast_ifn)); + d[0].syncid = ipvs->master_syncid; } - if (ip_vs_sync_state & IP_VS_STATE_BACKUP) { + if (ipvs->sync_state & IP_VS_STATE_BACKUP) { d[1].state = IP_VS_STATE_BACKUP; - strlcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn, sizeof(d[1].mcast_ifn)); - d[1].syncid = ip_vs_backup_syncid; + strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, + sizeof(d[1].mcast_ifn)); + d[1].syncid = ipvs->backup_syncid; } if (copy_to_user(user, &d, sizeof(d)) != 0) ret = -EFAULT; @@ -2542,6 +2621,7 @@ static struct genl_family ip_vs_genl_family = { .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, .maxattr = IPVS_CMD_MAX, + .netnsok = true, /* Make ipvsadm to work on netns */ }; /* Policy used for first-level command attributes */ @@ -2696,11 +2776,12 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, int idx = 0, i; int start = cb->args[0]; struct ip_vs_service *svc; + struct net *net = skb_sknet(skb); mutex_lock(&__ip_vs_mutex); for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) { - if (++idx <= start) + if (++idx <= start || !net_eq(svc->net, net)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -2711,7 +2792,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) { - if (++idx <= start) + if (++idx <= start || !net_eq(svc->net, net)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -2727,7 +2808,8 @@ nla_put_failure: return skb->len; } -static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, +static int ip_vs_genl_parse_service(struct net *net, + struct ip_vs_service_user_kern *usvc, struct nlattr *nla, int full_entry, struct ip_vs_service **ret_svc) { @@ -2770,9 +2852,9 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, } if (usvc->fwmark) - svc = __ip_vs_svc_fwm_find(usvc->af, usvc->fwmark); + svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark); else - svc = __ip_vs_service_find(usvc->af, usvc->protocol, + svc = __ip_vs_service_find(net, usvc->af, usvc->protocol, &usvc->addr, usvc->port); *ret_svc = svc; @@ -2809,13 +2891,14 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, return 0; } -static struct ip_vs_service *ip_vs_genl_find_service(struct nlattr *nla) +static struct ip_vs_service *ip_vs_genl_find_service(struct net *net, + struct nlattr *nla) { struct ip_vs_service_user_kern usvc; struct ip_vs_service *svc; int ret; - ret = ip_vs_genl_parse_service(&usvc, nla, 0, &svc); + ret = ip_vs_genl_parse_service(net, &usvc, nla, 0, &svc); return ret ? ERR_PTR(ret) : svc; } @@ -2883,6 +2966,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, struct ip_vs_service *svc; struct ip_vs_dest *dest; struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1]; + struct net *net = skb_sknet(skb); mutex_lock(&__ip_vs_mutex); @@ -2891,7 +2975,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy)) goto out_err; - svc = ip_vs_genl_find_service(attrs[IPVS_CMD_ATTR_SERVICE]); + + svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc) || svc == NULL) goto out_err; @@ -3005,20 +3090,23 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(net); + mutex_lock(&__ip_vs_mutex); - if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { + if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, - ip_vs_master_mcast_ifn, - ip_vs_master_syncid, cb) < 0) + ipvs->master_mcast_ifn, + ipvs->master_syncid, cb) < 0) goto nla_put_failure; cb->args[0] = 1; } - if ((ip_vs_sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { + if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP, - ip_vs_backup_mcast_ifn, - ip_vs_backup_syncid, cb) < 0) + ipvs->backup_mcast_ifn, + ipvs->backup_syncid, cb) < 0) goto nla_put_failure; cb->args[1] = 1; @@ -3030,31 +3118,33 @@ nla_put_failure: return skb->len; } -static int ip_vs_genl_new_daemon(struct nlattr **attrs) +static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs) { if (!(attrs[IPVS_DAEMON_ATTR_STATE] && attrs[IPVS_DAEMON_ATTR_MCAST_IFN] && attrs[IPVS_DAEMON_ATTR_SYNC_ID])) return -EINVAL; - return start_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]), + return start_sync_thread(net, + nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]), nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]), nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID])); } -static int ip_vs_genl_del_daemon(struct nlattr **attrs) +static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs) { if (!attrs[IPVS_DAEMON_ATTR_STATE]) return -EINVAL; - return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); + return stop_sync_thread(net, + nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); } -static int ip_vs_genl_set_config(struct nlattr **attrs) +static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(&t); + __ip_vs_get_timeouts(net, &t); if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]) t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]); @@ -3066,7 +3156,7 @@ static int ip_vs_genl_set_config(struct nlattr **attrs) if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]) t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]); - return ip_vs_set_timeout(&t); + return ip_vs_set_timeout(net, &t); } static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) @@ -3076,16 +3166,20 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) struct ip_vs_dest_user_kern udest; int ret = 0, cmd; int need_full_svc = 0, need_full_dest = 0; + struct net *net; + struct netns_ipvs *ipvs; + net = skb_sknet(skb); + ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; mutex_lock(&__ip_vs_mutex); if (cmd == IPVS_CMD_FLUSH) { - ret = ip_vs_flush(); + ret = ip_vs_flush(net); goto out; } else if (cmd == IPVS_CMD_SET_CONFIG) { - ret = ip_vs_genl_set_config(info->attrs); + ret = ip_vs_genl_set_config(net, info->attrs); goto out; } else if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { @@ -3101,13 +3195,13 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) } if (cmd == IPVS_CMD_NEW_DAEMON) - ret = ip_vs_genl_new_daemon(daemon_attrs); + ret = ip_vs_genl_new_daemon(net, daemon_attrs); else - ret = ip_vs_genl_del_daemon(daemon_attrs); + ret = ip_vs_genl_del_daemon(net, daemon_attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { - ret = ip_vs_zero_all(); + ret = ip_vs_zero_all(net); goto out; } @@ -3117,7 +3211,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE) need_full_svc = 1; - ret = ip_vs_genl_parse_service(&usvc, + ret = ip_vs_genl_parse_service(net, &usvc, info->attrs[IPVS_CMD_ATTR_SERVICE], need_full_svc, &svc); if (ret) @@ -3147,7 +3241,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) switch (cmd) { case IPVS_CMD_NEW_SERVICE: if (svc == NULL) - ret = ip_vs_add_service(&usvc, &svc); + ret = ip_vs_add_service(net, &usvc, &svc); else ret = -EEXIST; break; @@ -3185,7 +3279,11 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; void *reply; int ret, cmd, reply_cmd; + struct net *net; + struct netns_ipvs *ipvs; + net = skb_sknet(skb); + ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_GET_SERVICE) @@ -3214,7 +3312,8 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct ip_vs_service *svc; - svc = ip_vs_genl_find_service(info->attrs[IPVS_CMD_ATTR_SERVICE]); + svc = ip_vs_genl_find_service(net, + info->attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc)) { ret = PTR_ERR(svc); goto out_err; @@ -3234,7 +3333,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(&t); + __ip_vs_get_timeouts(net, &t); #ifdef CONFIG_IP_VS_PROTO_TCP NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout); NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, @@ -3380,62 +3479,173 @@ static void ip_vs_genl_unregister(void) /* End of Generic Netlink interface definitions */ +/* + * per netns intit/exit func. + */ +int __net_init __ip_vs_control_init(struct net *net) +{ + int idx; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ctl_table *tbl; + + atomic_set(&ipvs->dropentry, 0); + spin_lock_init(&ipvs->dropentry_lock); + spin_lock_init(&ipvs->droppacket_lock); + spin_lock_init(&ipvs->securetcp_lock); + ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock); + + /* Initialize rs_table */ + for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) + INIT_LIST_HEAD(&ipvs->rs_table[idx]); + + INIT_LIST_HEAD(&ipvs->dest_trash); + atomic_set(&ipvs->ftpsvc_counter, 0); + atomic_set(&ipvs->nullsvc_counter, 0); + + /* procfs stats */ + ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL); + if (ipvs->tot_stats == NULL) { + pr_err("%s(): no memory.\n", __func__); + return -ENOMEM; + } + ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!ipvs->cpustats) { + pr_err("%s() alloc_percpu failed\n", __func__); + goto err_alloc; + } + spin_lock_init(&ipvs->tot_stats->lock); + + proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); + proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops); + proc_net_fops_create(net, "ip_vs_stats_percpu", 0, + &ip_vs_stats_percpu_fops); + + if (!net_eq(net, &init_net)) { + tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); + if (tbl == NULL) + goto err_dup; + } else + tbl = vs_vars; + /* Initialize sysctl defaults */ + idx = 0; + ipvs->sysctl_amemthresh = 1024; + tbl[idx++].data = &ipvs->sysctl_amemthresh; + ipvs->sysctl_am_droprate = 10; + tbl[idx++].data = &ipvs->sysctl_am_droprate; + tbl[idx++].data = &ipvs->sysctl_drop_entry; + tbl[idx++].data = &ipvs->sysctl_drop_packet; +#ifdef CONFIG_IP_VS_NFCT + tbl[idx++].data = &ipvs->sysctl_conntrack; +#endif + tbl[idx++].data = &ipvs->sysctl_secure_tcp; + ipvs->sysctl_snat_reroute = 1; + tbl[idx++].data = &ipvs->sysctl_snat_reroute; + ipvs->sysctl_sync_ver = 1; + tbl[idx++].data = &ipvs->sysctl_sync_ver; + tbl[idx++].data = &ipvs->sysctl_cache_bypass; + tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; + tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template; + ipvs->sysctl_sync_threshold[0] = 3; + ipvs->sysctl_sync_threshold[1] = 50; + tbl[idx].data = &ipvs->sysctl_sync_threshold; + tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); + tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; + + +#ifdef CONFIG_SYSCTL + ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path, + tbl); + if (ipvs->sysctl_hdr == NULL) { + if (!net_eq(net, &init_net)) + kfree(tbl); + goto err_dup; + } +#endif + ip_vs_new_estimator(net, ipvs->tot_stats); + ipvs->sysctl_tbl = tbl; + /* Schedule defense work */ + INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); + schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); + return 0; + +err_dup: + free_percpu(ipvs->cpustats); +err_alloc: + kfree(ipvs->tot_stats); + return -ENOMEM; +} + +static void __net_exit __ip_vs_control_cleanup(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_trash_cleanup(net); + ip_vs_kill_estimator(net, ipvs->tot_stats); + cancel_delayed_work_sync(&ipvs->defense_work); + cancel_work_sync(&ipvs->defense_work.work); +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(ipvs->sysctl_hdr); +#endif + proc_net_remove(net, "ip_vs_stats_percpu"); + proc_net_remove(net, "ip_vs_stats"); + proc_net_remove(net, "ip_vs"); + free_percpu(ipvs->cpustats); + kfree(ipvs->tot_stats); +} + +static struct pernet_operations ipvs_control_ops = { + .init = __ip_vs_control_init, + .exit = __ip_vs_control_cleanup, +}; int __init ip_vs_control_init(void) { - int ret; int idx; + int ret; EnterFunction(2); - /* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */ + /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { INIT_LIST_HEAD(&ip_vs_svc_table[idx]); INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++) { - INIT_LIST_HEAD(&ip_vs_rtable[idx]); + + ret = register_pernet_subsys(&ipvs_control_ops); + if (ret) { + pr_err("cannot register namespace.\n"); + goto err; } - smp_wmb(); + + smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - return ret; + goto err_net; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); nf_unregister_sockopt(&ip_vs_sockopts); - return ret; + goto err_net; } - proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops); - proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops); - - sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars); - - ip_vs_new_estimator(&ip_vs_stats); - - /* Hook the defense timer */ - schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD); - LeaveFunction(2); return 0; + +err_net: + unregister_pernet_subsys(&ipvs_control_ops); +err: + return ret; } void ip_vs_control_cleanup(void) { EnterFunction(2); - ip_vs_trash_cleanup(); - cancel_delayed_work_sync(&defense_work); - cancel_work_sync(&defense_work.work); - ip_vs_kill_estimator(&ip_vs_stats); - unregister_sysctl_table(sysctl_header); - proc_net_remove(&init_net, "ip_vs_stats"); - proc_net_remove(&init_net, "ip_vs"); + unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ff28801..f560a05 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -8,8 +8,12 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Changes: - * + * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> + * Network name space (netns) aware. + * Global data moved to netns i.e struct netns_ipvs + * Affected data: est_list and est_lock. + * estimation_timer() runs with timer per netns. + * get_stats()) do the per cpu summing. */ #define KMSG_COMPONENT "IPVS" @@ -48,11 +52,42 @@ */ -static void estimation_timer(unsigned long arg); +/* + * Make a summary from each cpu + */ +static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, + struct ip_vs_cpu_stats *stats) +{ + int i; + + for_each_possible_cpu(i) { + struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); + unsigned int start; + __u64 inbytes, outbytes; + if (i) { + sum->conns += s->ustats.conns; + sum->inpkts += s->ustats.inpkts; + sum->outpkts += s->ustats.outpkts; + do { + start = u64_stats_fetch_begin_bh(&s->syncp); + inbytes = s->ustats.inbytes; + outbytes = s->ustats.outbytes; + } while (u64_stats_fetch_retry_bh(&s->syncp, start)); + sum->inbytes += inbytes; + sum->outbytes += outbytes; + } else { + sum->conns = s->ustats.conns; + sum->inpkts = s->ustats.inpkts; + sum->outpkts = s->ustats.outpkts; + do { + start = u64_stats_fetch_begin_bh(&s->syncp); + sum->inbytes = s->ustats.inbytes; + sum->outbytes = s->ustats.outbytes; + } while (u64_stats_fetch_retry_bh(&s->syncp, start)); + } + } +} -static LIST_HEAD(est_list); -static DEFINE_SPINLOCK(est_lock); -static DEFINE_TIMER(est_timer, estimation_timer, 0, 0); static void estimation_timer(unsigned long arg) { @@ -62,11 +97,16 @@ static void estimation_timer(unsigned long arg) u32 n_inpkts, n_outpkts; u64 n_inbytes, n_outbytes; u32 rate; + struct net *net = (struct net *)arg; + struct netns_ipvs *ipvs; - spin_lock(&est_lock); - list_for_each_entry(e, &est_list, list) { + ipvs = net_ipvs(net); + ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats); + spin_lock(&ipvs->est_lock); + list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); + ip_vs_read_cpu_stats(&s->ustats, s->cpustats); spin_lock(&s->lock); n_conns = s->ustats.conns; n_inpkts = s->ustats.inpkts; @@ -75,38 +115,39 @@ static void estimation_timer(unsigned long arg) n_outbytes = s->ustats.outbytes; /* scaled by 2^10, but divided 2 seconds */ - rate = (n_conns - e->last_conns)<<9; + rate = (n_conns - e->last_conns) << 9; e->last_conns = n_conns; - e->cps += ((long)rate - (long)e->cps)>>2; - s->ustats.cps = (e->cps+0x1FF)>>10; + e->cps += ((long)rate - (long)e->cps) >> 2; + s->ustats.cps = (e->cps + 0x1FF) >> 10; - rate = (n_inpkts - e->last_inpkts)<<9; + rate = (n_inpkts - e->last_inpkts) << 9; e->last_inpkts = n_inpkts; - e->inpps += ((long)rate - (long)e->inpps)>>2; - s->ustats.inpps = (e->inpps+0x1FF)>>10; + e->inpps += ((long)rate - (long)e->inpps) >> 2; + s->ustats.inpps = (e->inpps + 0x1FF) >> 10; - rate = (n_outpkts - e->last_outpkts)<<9; + rate = (n_outpkts - e->last_outpkts) << 9; e->last_outpkts = n_outpkts; - e->outpps += ((long)rate - (long)e->outpps)>>2; - s->ustats.outpps = (e->outpps+0x1FF)>>10; + e->outpps += ((long)rate - (long)e->outpps) >> 2; + s->ustats.outpps = (e->outpps + 0x1FF) >> 10; - rate = (n_inbytes - e->last_inbytes)<<4; + rate = (n_inbytes - e->last_inbytes) << 4; e->last_inbytes = n_inbytes; - e->inbps += ((long)rate - (long)e->inbps)>>2; - s->ustats.inbps = (e->inbps+0xF)>>5; + e->inbps += ((long)rate - (long)e->inbps) >> 2; + s->ustats.inbps = (e->inbps + 0xF) >> 5; - rate = (n_outbytes - e->last_outbytes)<<4; + rate = (n_outbytes - e->last_outbytes) << 4; e->last_outbytes = n_outbytes; - e->outbps += ((long)rate - (long)e->outbps)>>2; - s->ustats.outbps = (e->outbps+0xF)>>5; + e->outbps += ((long)rate - (long)e->outbps) >> 2; + s->ustats.outbps = (e->outbps + 0xF) >> 5; spin_unlock(&s->lock); } - spin_unlock(&est_lock); - mod_timer(&est_timer, jiffies + 2*HZ); + spin_unlock(&ipvs->est_lock); + mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } -void ip_vs_new_estimator(struct ip_vs_stats *stats) +void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; INIT_LIST_HEAD(&est->list); @@ -126,18 +167,19 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats) est->last_outbytes = stats->ustats.outbytes; est->outbps = stats->ustats.outbps<<5; - spin_lock_bh(&est_lock); - list_add(&est->list, &est_list); - spin_unlock_bh(&est_lock); + spin_lock_bh(&ipvs->est_lock); + list_add(&est->list, &ipvs->est_list); + spin_unlock_bh(&ipvs->est_lock); } -void ip_vs_kill_estimator(struct ip_vs_stats *stats) +void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; - spin_lock_bh(&est_lock); + spin_lock_bh(&ipvs->est_lock); list_del(&est->list); - spin_unlock_bh(&est_lock); + spin_unlock_bh(&ipvs->est_lock); } void ip_vs_zero_estimator(struct ip_vs_stats *stats) @@ -157,13 +199,35 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats) est->outbps = 0; } -int __init ip_vs_estimator_init(void) +static int __net_init __ip_vs_estimator_init(struct net *net) { - mod_timer(&est_timer, jiffies + 2 * HZ); + struct netns_ipvs *ipvs = net_ipvs(net); + + INIT_LIST_HEAD(&ipvs->est_list); + spin_lock_init(&ipvs->est_lock); + setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net); + mod_timer(&ipvs->est_timer, jiffies + 2 * HZ); return 0; } +static void __net_exit __ip_vs_estimator_exit(struct net *net) +{ + del_timer_sync(&net_ipvs(net)->est_timer); +} +static struct pernet_operations ip_vs_app_ops = { + .init = __ip_vs_estimator_init, + .exit = __ip_vs_estimator_exit, +}; + +int __init ip_vs_estimator_init(void) +{ + int rv; + + rv = register_pernet_subsys(&ip_vs_app_ops); + return rv; +} + void ip_vs_estimator_cleanup(void) { - del_timer_sync(&est_timer); + unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 7545500..6b5dd6d 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -157,6 +157,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; + struct net *net; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -197,18 +198,20 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(AF_INET, iph->protocol, - &from, port, &cp->caddr, 0, &p); + ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + iph->protocol, &from, port, + &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr, + ip_vs_conn_fill_param(ip_vs_conn_net(cp), + AF_INET, IPPROTO_TCP, &cp->caddr, 0, &cp->vaddr, port, &p); n_cp = ip_vs_conn_new(&p, &from, port, IP_VS_CONN_F_NO_CPORT | IP_VS_CONN_F_NFCT, - cp->dest); + cp->dest, skb->mark); if (!n_cp) return 0; @@ -257,8 +260,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * would be adjusted twice. */ + net = skb_net(skb); cp->app_data = NULL; - ip_vs_tcp_conn_listen(n_cp); + ip_vs_tcp_conn_listen(net, n_cp); ip_vs_conn_put(n_cp); return ret; } @@ -287,6 +291,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; + struct net *net; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -358,14 +363,15 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port, - &cp->vaddr, htons(ntohs(cp->vport)-1), - &p); + ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + iph->protocol, &to, port, &cp->vaddr, + htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); if (!n_cp) { n_cp = ip_vs_conn_new(&p, &cp->daddr, htons(ntohs(cp->dport)-1), - IP_VS_CONN_F_NFCT, cp->dest); + IP_VS_CONN_F_NFCT, cp->dest, + skb->mark); if (!n_cp) return 0; @@ -377,7 +383,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, /* * Move tunnel to listen state */ - ip_vs_tcp_conn_listen(n_cp); + net = skb_net(skb); + ip_vs_tcp_conn_listen(net, n_cp); ip_vs_conn_put(n_cp); return 1; @@ -398,23 +405,22 @@ static struct ip_vs_app ip_vs_ftp = { .pkt_in = ip_vs_ftp_in, }; - /* - * ip_vs_ftp initialization + * per netns ip_vs_ftp initialization */ -static int __init ip_vs_ftp_init(void) +static int __net_init __ip_vs_ftp_init(struct net *net) { int i, ret; struct ip_vs_app *app = &ip_vs_ftp; - ret = register_ip_vs_app(app); + ret = register_ip_vs_app(net, app); if (ret) return ret; for (i=0; i<IP_VS_APP_MAX_PORTS; i++) { if (!ports[i]) continue; - ret = register_ip_vs_app_inc(app, app->protocol, ports[i]); + ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]); if (ret) break; pr_info("%s: loaded support on port[%d] = %d\n", @@ -422,18 +428,39 @@ static int __init ip_vs_ftp_init(void) } if (ret) - unregister_ip_vs_app(app); + unregister_ip_vs_app(net, app); return ret; } +/* + * netns exit + */ +static void __ip_vs_ftp_exit(struct net *net) +{ + struct ip_vs_app *app = &ip_vs_ftp; + + unregister_ip_vs_app(net, app); +} + +static struct pernet_operations ip_vs_ftp_ops = { + .init = __ip_vs_ftp_init, + .exit = __ip_vs_ftp_exit, +}; +int __init ip_vs_ftp_init(void) +{ + int rv; + + rv = register_pernet_subsys(&ip_vs_ftp_ops); + return rv; +} /* * ip_vs_ftp finish. */ static void __exit ip_vs_ftp_exit(void) { - unregister_ip_vs_app(&ip_vs_ftp); + unregister_pernet_subsys(&ip_vs_ftp_ops); } diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 9323f89..00b5ffa 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -70,7 +70,6 @@ * entries that haven't been touched for a day. */ #define COUNT_FOR_FULL_EXPIRATION 30 -static int sysctl_ip_vs_lblc_expiration = 24*60*60*HZ; /* @@ -117,7 +116,7 @@ struct ip_vs_lblc_table { static ctl_table vs_vars_table[] = { { .procname = "lblc_expiration", - .data = &sysctl_ip_vs_lblc_expiration, + .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -125,8 +124,6 @@ static ctl_table vs_vars_table[] = { { } }; -static struct ctl_table_header * sysctl_header; - static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) { list_del(&en->list); @@ -248,6 +245,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) struct ip_vs_lblc_entry *en, *nxt; unsigned long now = jiffies; int i, j; + struct netns_ipvs *ipvs = net_ipvs(svc->net); for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; @@ -255,7 +253,8 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_before(now, - en->lastuse + sysctl_ip_vs_lblc_expiration)) + en->lastuse + + ipvs->sysctl_lblc_expiration)) continue; ip_vs_lblc_free(en); @@ -543,23 +542,73 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = .schedule = ip_vs_lblc_schedule, }; +/* + * per netns init. + */ +static int __net_init __ip_vs_lblc_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!net_eq(net, &init_net)) { + ipvs->lblc_ctl_table = kmemdup(vs_vars_table, + sizeof(vs_vars_table), + GFP_KERNEL); + if (ipvs->lblc_ctl_table == NULL) + return -ENOMEM; + } else + ipvs->lblc_ctl_table = vs_vars_table; + ipvs->sysctl_lblc_expiration = 24*60*60*HZ; + ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration; + +#ifdef CONFIG_SYSCTL + ipvs->lblc_ctl_header = + register_net_sysctl_table(net, net_vs_ctl_path, + ipvs->lblc_ctl_table); + if (!ipvs->lblc_ctl_header) { + if (!net_eq(net, &init_net)) + kfree(ipvs->lblc_ctl_table); + return -ENOMEM; + } +#endif + + return 0; +} + +static void __net_exit __ip_vs_lblc_exit(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(ipvs->lblc_ctl_header); +#endif + + if (!net_eq(net, &init_net)) + kfree(ipvs->lblc_ctl_table); +} + +static struct pernet_operations ip_vs_lblc_ops = { + .init = __ip_vs_lblc_init, + .exit = __ip_vs_lblc_exit, +}; static int __init ip_vs_lblc_init(void) { int ret; - sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); + ret = register_pernet_subsys(&ip_vs_lblc_ops); + if (ret) + return ret; + ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler); if (ret) - unregister_sysctl_table(sysctl_header); + unregister_pernet_subsys(&ip_vs_lblc_ops); return ret; } - static void __exit ip_vs_lblc_cleanup(void) { - unregister_sysctl_table(sysctl_header); unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler); + unregister_pernet_subsys(&ip_vs_lblc_ops); } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index dbeed8e..bfa25f1 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -70,8 +70,6 @@ * entries that haven't been touched for a day. */ #define COUNT_FOR_FULL_EXPIRATION 30 -static int sysctl_ip_vs_lblcr_expiration = 24*60*60*HZ; - /* * for IPVS lblcr entry hash table @@ -296,7 +294,7 @@ struct ip_vs_lblcr_table { static ctl_table vs_vars_table[] = { { .procname = "lblcr_expiration", - .data = &sysctl_ip_vs_lblcr_expiration, + .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -304,8 +302,6 @@ static ctl_table vs_vars_table[] = { { } }; -static struct ctl_table_header * sysctl_header; - static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) { list_del(&en->list); @@ -425,14 +421,15 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) unsigned long now = jiffies; int i, j; struct ip_vs_lblcr_entry *en, *nxt; + struct netns_ipvs *ipvs = net_ipvs(svc->net); for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { - if (time_after(en->lastuse+sysctl_ip_vs_lblcr_expiration, - now)) + if (time_after(en->lastuse + + ipvs->sysctl_lblcr_expiration, now)) continue; ip_vs_lblcr_free(en); @@ -664,6 +661,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) read_lock(&svc->sched_lock); en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr); if (en) { + struct netns_ipvs *ipvs = net_ipvs(svc->net); /* We only hold a read lock, but this is atomic */ en->lastuse = jiffies; @@ -675,7 +673,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* More than one destination + enough time passed by, cleanup */ if (atomic_read(&en->set.size) > 1 && time_after(jiffies, en->set.lastmod + - sysctl_ip_vs_lblcr_expiration)) { + ipvs->sysctl_lblcr_expiration)) { struct ip_vs_dest *m; write_lock(&en->set.lock); @@ -744,23 +742,73 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = .schedule = ip_vs_lblcr_schedule, }; +/* + * per netns init. + */ +static int __net_init __ip_vs_lblcr_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!net_eq(net, &init_net)) { + ipvs->lblcr_ctl_table = kmemdup(vs_vars_table, + sizeof(vs_vars_table), + GFP_KERNEL); + if (ipvs->lblcr_ctl_table == NULL) + return -ENOMEM; + } else + ipvs->lblcr_ctl_table = vs_vars_table; + ipvs->sysctl_lblcr_expiration = 24*60*60*HZ; + ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration; + +#ifdef CONFIG_SYSCTL + ipvs->lblcr_ctl_header = + register_net_sysctl_table(net, net_vs_ctl_path, + ipvs->lblcr_ctl_table); + if (!ipvs->lblcr_ctl_header) { + if (!net_eq(net, &init_net)) + kfree(ipvs->lblcr_ctl_table); + return -ENOMEM; + } +#endif + + return 0; +} + +static void __net_exit __ip_vs_lblcr_exit(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(ipvs->lblcr_ctl_header); +#endif + + if (!net_eq(net, &init_net)) + kfree(ipvs->lblcr_ctl_table); +} + +static struct pernet_operations ip_vs_lblcr_ops = { + .init = __ip_vs_lblcr_init, + .exit = __ip_vs_lblcr_exit, +}; static int __init ip_vs_lblcr_init(void) { int ret; - sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); + ret = register_pernet_subsys(&ip_vs_lblcr_ops); + if (ret) + return ret; + ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler); if (ret) - unregister_sysctl_table(sysctl_header); + unregister_pernet_subsys(&ip_vs_lblcr_ops); return ret; } - static void __exit ip_vs_lblcr_cleanup(void) { - unregister_sysctl_table(sysctl_header); unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); + unregister_pernet_subsys(&ip_vs_lblcr_ops); } diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 4680647..f454c80 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -141,6 +141,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, struct nf_conntrack_tuple *orig, new_reply; struct ip_vs_conn *cp; struct ip_vs_conn_param p; + struct net *net = nf_ct_net(ct); if (exp->tuple.src.l3num != PF_INET) return; @@ -155,7 +156,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, /* RS->CLIENT */ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum, + ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum, &orig->src.u3, orig->src.u.tcp.port, &orig->dst.u3, orig->dst.u.tcp.port, &p); cp = ip_vs_conn_out_get(&p); @@ -268,7 +269,8 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) " for conn " FMT_CONN "\n", __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); - h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple); + h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE, + &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); /* Show what happens instead of calling nf_ct_kill() */ diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c index 3414af7..5cf859c 100644 --- a/net/netfilter/ipvs/ip_vs_pe.c +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -29,12 +29,11 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc) } /* Get pe in the pe list by name */ -static struct ip_vs_pe * -ip_vs_pe_getbyname(const char *pe_name) +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name) { struct ip_vs_pe *pe; - IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__, + IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__, pe_name); spin_lock_bh(&ip_vs_pe_lock); @@ -60,28 +59,22 @@ ip_vs_pe_getbyname(const char *pe_name) } /* Lookup pe and try to load it if it doesn't exist */ -struct ip_vs_pe *ip_vs_pe_get(const char *name) +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name) { struct ip_vs_pe *pe; /* Search for the pe by name */ - pe = ip_vs_pe_getbyname(name); + pe = __ip_vs_pe_getbyname(name); /* If pe not found, load the module and search again */ if (!pe) { request_module("ip_vs_pe_%s", name); - pe = ip_vs_pe_getbyname(name); + pe = __ip_vs_pe_getbyname(name); } return pe; } -void ip_vs_pe_put(struct ip_vs_pe *pe) -{ - if (pe && pe->module) - module_put(pe->module); -} - /* Register a pe in the pe list */ int register_ip_vs_pe(struct ip_vs_pe *pe) { diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index b8b4e96..0d83bc0 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -71,6 +71,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) struct ip_vs_iphdr iph; unsigned int dataoff, datalen, matchoff, matchlen; const char *dptr; + int retc; ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph); @@ -83,6 +84,8 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) if (dataoff >= skb->len) return -EINVAL; + if ((retc=skb_linearize(skb)) < 0) + return retc; dptr = skb->data + dataoff; datalen = skb->len - dataoff; diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index c539983..17484a4 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -60,6 +60,35 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) return 0; } +#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) || \ + defined(CONFIG_IP_VS_PROTO_SCTP) || defined(CONFIG_IP_VS_PROTO_AH) || \ + defined(CONFIG_IP_VS_PROTO_ESP) +/* + * register an ipvs protocols netns related data + */ +static int +register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + unsigned hash = IP_VS_PROTO_HASH(pp->protocol); + struct ip_vs_proto_data *pd = + kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC); + + if (!pd) { + pr_err("%s(): no memory.\n", __func__); + return -ENOMEM; + } + pd->pp = pp; /* For speed issues */ + pd->next = ipvs->proto_data_table[hash]; + ipvs->proto_data_table[hash] = pd; + atomic_set(&pd->appcnt, 0); /* Init app counter */ + + if (pp->init_netns != NULL) + pp->init_netns(net, pd); + + return 0; +} +#endif /* * unregister an ipvs protocol @@ -82,6 +111,29 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) return -ESRCH; } +/* + * unregister an ipvs protocols netns data + */ +static int +unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data **pd_p; + unsigned hash = IP_VS_PROTO_HASH(pd->pp->protocol); + + pd_p = &ipvs->proto_data_table[hash]; + for (; *pd_p; pd_p = &(*pd_p)->next) { + if (*pd_p == pd) { + *pd_p = pd->next; + if (pd->pp->exit_netns != NULL) + pd->pp->exit_netns(net, pd); + kfree(pd); + return 0; + } + } + + return -ESRCH; +} /* * get ip_vs_protocol object by its proto. @@ -100,19 +152,44 @@ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto) } EXPORT_SYMBOL(ip_vs_proto_get); +/* + * get ip_vs_protocol object data by netns and proto + */ +struct ip_vs_proto_data * +__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) +{ + struct ip_vs_proto_data *pd; + unsigned hash = IP_VS_PROTO_HASH(proto); + + for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) { + if (pd->pp->protocol == proto) + return pd; + } + + return NULL; +} + +struct ip_vs_proto_data * +ip_vs_proto_data_get(struct net *net, unsigned short proto) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + return __ipvs_proto_data_get(ipvs, proto); +} +EXPORT_SYMBOL(ip_vs_proto_data_get); /* * Propagate event for state change to all protocols */ -void ip_vs_protocol_timeout_change(int flags) +void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags) { - struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; int i; for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { - for (pp = ip_vs_proto_table[i]; pp; pp = pp->next) { - if (pp->timeout_change) - pp->timeout_change(pp, flags); + for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) { + if (pd->pp->timeout_change) + pd->pp->timeout_change(pd, flags); } } } @@ -236,6 +313,46 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg); } +/* + * per network name-space init + */ +static int __net_init __ip_vs_protocol_init(struct net *net) +{ +#ifdef CONFIG_IP_VS_PROTO_TCP + register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); +#endif +#ifdef CONFIG_IP_VS_PROTO_UDP + register_ip_vs_proto_netns(net, &ip_vs_protocol_udp); +#endif +#ifdef CONFIG_IP_VS_PROTO_SCTP + register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp); +#endif +#ifdef CONFIG_IP_VS_PROTO_AH + register_ip_vs_proto_netns(net, &ip_vs_protocol_ah); +#endif +#ifdef CONFIG_IP_VS_PROTO_ESP + register_ip_vs_proto_netns(net, &ip_vs_protocol_esp); +#endif + return 0; +} + +static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd; + int i; + + /* unregister all the ipvs proto data for this netns */ + for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { + while ((pd = ipvs->proto_data_table[i]) != NULL) + unregister_ip_vs_proto_netns(net, pd); + } +} + +static struct pernet_operations ipvs_proto_ops = { + .init = __ip_vs_protocol_init, + .exit = __ip_vs_protocol_cleanup, +}; int __init ip_vs_protocol_init(void) { @@ -265,6 +382,7 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); + return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -275,6 +393,7 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; + unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 3a04611..5b8eb8b 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -41,28 +41,30 @@ struct isakmp_hdr { #define PORT_ISAKMP 500 static void -ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph, - int inverse, struct ip_vs_conn_param *p) +ah_esp_conn_fill_param_proto(struct net *net, int af, + const struct ip_vs_iphdr *iph, int inverse, + struct ip_vs_conn_param *p) { if (likely(!inverse)) - ip_vs_conn_fill_param(af, IPPROTO_UDP, + ip_vs_conn_fill_param(net, af, IPPROTO_UDP, &iph->saddr, htons(PORT_ISAKMP), &iph->daddr, htons(PORT_ISAKMP), p); else - ip_vs_conn_fill_param(af, IPPROTO_UDP, + ip_vs_conn_fill_param(net, af, IPPROTO_UDP, &iph->daddr, htons(PORT_ISAKMP), &iph->saddr, htons(PORT_ISAKMP), p); } static struct ip_vs_conn * -ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, +ah_esp_conn_in_get(int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; + struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); cp = ip_vs_conn_in_get(&p); if (!cp) { /* @@ -72,7 +74,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet " "%s%s %s->%s\n", inverse ? "ICMP+" : "", - pp->name, + ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); } @@ -83,21 +85,21 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, static struct ip_vs_conn * ah_esp_conn_out_get(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; + struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " "%s%s %s->%s\n", inverse ? "ICMP+" : "", - pp->name, + ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); } @@ -107,7 +109,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb, static int -ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { /* @@ -117,26 +119,14 @@ ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; } -static void ah_esp_init(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - -static void ah_esp_exit(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - #ifdef CONFIG_IP_VS_PROTO_AH struct ip_vs_protocol ip_vs_protocol_ah = { .name = "AH", .protocol = IPPROTO_AH, .num_states = 1, .dont_defrag = 1, - .init = ah_esp_init, - .exit = ah_esp_exit, + .init = NULL, + .exit = NULL, .conn_schedule = ah_esp_conn_schedule, .conn_in_get = ah_esp_conn_in_get, .conn_out_get = ah_esp_conn_out_get, @@ -149,7 +139,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = { .app_conn_bind = NULL, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, /* ISAKMP */ - .set_state_timeout = NULL, }; #endif @@ -159,8 +148,8 @@ struct ip_vs_protocol ip_vs_protocol_esp = { .protocol = IPPROTO_ESP, .num_states = 1, .dont_defrag = 1, - .init = ah_esp_init, - .exit = ah_esp_exit, + .init = NULL, + .exit = NULL, .conn_schedule = ah_esp_conn_schedule, .conn_in_get = ah_esp_conn_in_get, .conn_out_get = ah_esp_conn_out_get, diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1ea96bcd..b027ccc 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -9,9 +9,10 @@ #include <net/ip_vs.h> static int -sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { + struct net *net; struct ip_vs_service *svc; sctp_chunkhdr_t _schunkh, *sch; sctp_sctphdr_t *sh, _sctph; @@ -27,13 +28,13 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, sizeof(_schunkh), &_schunkh); if (sch == NULL) return 0; - + net = skb_net(skb); if ((sch->type == SCTP_CID_INIT) && - (svc = ip_vs_service_get(af, skb->mark, iph.protocol, + (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, &iph.daddr, sh->dest))) { int ignored; - if (ip_vs_todrop()) { + if (ip_vs_todrop(net_ipvs(net))) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -46,14 +47,19 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pp, &ignored); - if (!*cpp && !ignored) { - *verdict = ip_vs_leave(svc, skb, pp); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + if (!*cpp && ignored <= 0) { + if (!ignored) + *verdict = ip_vs_leave(svc, skb, pd); + else { + ip_vs_service_put(svc); + *verdict = NF_DROP; + } return 0; } ip_vs_service_put(svc); } - + /* NF_ACCEPT */ return 1; } @@ -856,7 +862,7 @@ static struct ipvs_sctp_nextstate /* * Timeout table[state] */ -static int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = { +static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = { [IP_VS_SCTP_S_NONE] = 2 * HZ, [IP_VS_SCTP_S_INIT_CLI] = 1 * 60 * HZ, [IP_VS_SCTP_S_INIT_SER] = 1 * 60 * HZ, @@ -900,20 +906,8 @@ static const char *sctp_state_name(int state) return "?"; } -static void sctp_timeout_change(struct ip_vs_protocol *pp, int flags) -{ -} - -static int -sctp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to) -{ - -return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_SCTP_S_LAST, - sctp_state_name_table, sname, to); -} - static inline int -set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, +set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, const struct sk_buff *skb) { sctp_chunkhdr_t _sctpch, *sch; @@ -971,7 +965,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, IP_VS_DBG_BUF(8, "%s %s %s:%d->" "%s:%d state: %s->%s conn->refcnt:%d\n", - pp->name, + pd->pp->name, ((direction == IP_VS_DIR_OUTPUT) ? "output " : "input "), IP_VS_DBG_ADDR(cp->af, &cp->daddr), @@ -995,75 +989,73 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, } } } + if (likely(pd)) + cp->timeout = pd->timeout_table[cp->state = next_state]; + else /* What to do ? */ + cp->timeout = sctp_timeouts[cp->state = next_state]; - cp->timeout = pp->timeout_table[cp->state = next_state]; - - return 1; + return 1; } static int sctp_state_transition(struct ip_vs_conn *cp, int direction, - const struct sk_buff *skb, struct ip_vs_protocol *pp) + const struct sk_buff *skb, struct ip_vs_proto_data *pd) { int ret = 0; spin_lock(&cp->lock); - ret = set_sctp_state(pp, cp, direction, skb); + ret = set_sctp_state(pd, cp, direction, skb); spin_unlock(&cp->lock); return ret; } -/* - * Hash table for SCTP application incarnations - */ -#define SCTP_APP_TAB_BITS 4 -#define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) -#define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) - -static struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; -static DEFINE_SPINLOCK(sctp_app_lock); - static inline __u16 sctp_app_hashkey(__be16 port) { return (((__force u16)port >> SCTP_APP_TAB_BITS) ^ (__force u16)port) & SCTP_APP_TAB_MASK; } -static int sctp_register_app(struct ip_vs_app *inc) +static int sctp_register_app(struct net *net, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); hash = sctp_app_hashkey(port); - spin_lock_bh(&sctp_app_lock); - list_for_each_entry(i, &sctp_apps[hash], p_list) { + spin_lock_bh(&ipvs->sctp_app_lock); + list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } - list_add(&inc->p_list, &sctp_apps[hash]); - atomic_inc(&ip_vs_protocol_sctp.appcnt); + list_add(&inc->p_list, &ipvs->sctp_apps[hash]); + atomic_inc(&pd->appcnt); out: - spin_unlock_bh(&sctp_app_lock); + spin_unlock_bh(&ipvs->sctp_app_lock); return ret; } -static void sctp_unregister_app(struct ip_vs_app *inc) +static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) { - spin_lock_bh(&sctp_app_lock); - atomic_dec(&ip_vs_protocol_sctp.appcnt); + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); + + spin_lock_bh(&ipvs->sctp_app_lock); + atomic_dec(&pd->appcnt); list_del(&inc->p_list); - spin_unlock_bh(&sctp_app_lock); + spin_unlock_bh(&ipvs->sctp_app_lock); } static int sctp_app_conn_bind(struct ip_vs_conn *cp) { + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); int hash; struct ip_vs_app *inc; int result = 0; @@ -1074,12 +1066,12 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp) /* Lookup application incarnations and bind the right one */ hash = sctp_app_hashkey(cp->vport); - spin_lock(&sctp_app_lock); - list_for_each_entry(inc, &sctp_apps[hash], p_list) { + spin_lock(&ipvs->sctp_app_lock); + list_for_each_entry(inc, &ipvs->sctp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; - spin_unlock(&sctp_app_lock); + spin_unlock(&ipvs->sctp_app_lock); IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" "%s:%u to app %s on port %u\n", @@ -1095,43 +1087,50 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp) goto out; } } - spin_unlock(&sctp_app_lock); + spin_unlock(&ipvs->sctp_app_lock); out: return result; } -static void ip_vs_sctp_init(struct ip_vs_protocol *pp) +/* --------------------------------------------- + * timeouts is netns related now. + * --------------------------------------------- + */ +static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) { - IP_VS_INIT_HASH_TABLE(sctp_apps); - pp->timeout_table = sctp_timeouts; -} + struct netns_ipvs *ipvs = net_ipvs(net); + ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE); + spin_lock_init(&ipvs->sctp_app_lock); + pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, + sizeof(sctp_timeouts)); +} -static void ip_vs_sctp_exit(struct ip_vs_protocol *pp) +static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd) { - + kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_sctp = { - .name = "SCTP", - .protocol = IPPROTO_SCTP, - .num_states = IP_VS_SCTP_S_LAST, - .dont_defrag = 0, - .appcnt = ATOMIC_INIT(0), - .init = ip_vs_sctp_init, - .exit = ip_vs_sctp_exit, - .register_app = sctp_register_app, + .name = "SCTP", + .protocol = IPPROTO_SCTP, + .num_states = IP_VS_SCTP_S_LAST, + .dont_defrag = 0, + .init = NULL, + .exit = NULL, + .init_netns = __ip_vs_sctp_init, + .exit_netns = __ip_vs_sctp_exit, + .register_app = sctp_register_app, .unregister_app = sctp_unregister_app, - .conn_schedule = sctp_conn_schedule, - .conn_in_get = ip_vs_conn_in_get_proto, - .conn_out_get = ip_vs_conn_out_get_proto, - .snat_handler = sctp_snat_handler, - .dnat_handler = sctp_dnat_handler, - .csum_check = sctp_csum_check, - .state_name = sctp_state_name, + .conn_schedule = sctp_conn_schedule, + .conn_in_get = ip_vs_conn_in_get_proto, + .conn_out_get = ip_vs_conn_out_get_proto, + .snat_handler = sctp_snat_handler, + .dnat_handler = sctp_dnat_handler, + .csum_check = sctp_csum_check, + .state_name = sctp_state_name, .state_transition = sctp_state_transition, - .app_conn_bind = sctp_app_conn_bind, - .debug_packet = ip_vs_tcpudp_debug_packet, - .timeout_change = sctp_timeout_change, - .set_state_timeout = sctp_set_state_timeout, + .app_conn_bind = sctp_app_conn_bind, + .debug_packet = ip_vs_tcpudp_debug_packet, + .timeout_change = NULL, }; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index f6c5200..c0cc341 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -9,8 +9,12 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Changes: + * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * + * Network name space (netns) aware. + * Global data moved to netns i.e struct netns_ipvs + * tcp_timeouts table has copy per netns in a hash table per + * protocol ip_vs_proto_data and is handled by netns */ #define KMSG_COMPONENT "IPVS" @@ -28,9 +32,10 @@ #include <net/ip_vs.h> static int -tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { + struct net *net; struct ip_vs_service *svc; struct tcphdr _tcph, *th; struct ip_vs_iphdr iph; @@ -42,14 +47,14 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, *verdict = NF_DROP; return 0; } - + net = skb_net(skb); /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (th->syn && - (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr, - th->dest))) { + (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, + &iph.daddr, th->dest))) { int ignored; - if (ip_vs_todrop()) { + if (ip_vs_todrop(net_ipvs(net))) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -63,13 +68,19 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pp, &ignored); - if (!*cpp && !ignored) { - *verdict = ip_vs_leave(svc, skb, pp); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + if (!*cpp && ignored <= 0) { + if (!ignored) + *verdict = ip_vs_leave(svc, skb, pd); + else { + ip_vs_service_put(svc); + *verdict = NF_DROP; + } return 0; } ip_vs_service_put(svc); } + /* NF_ACCEPT */ return 1; } @@ -338,7 +349,7 @@ static const int tcp_state_off[IP_VS_DIR_LAST] = { /* * Timeout table[state] */ -static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { +static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = 2*HZ, [IP_VS_TCP_S_ESTABLISHED] = 15*60*HZ, [IP_VS_TCP_S_SYN_SENT] = 2*60*HZ, @@ -437,10 +448,7 @@ static struct tcp_states_t tcp_states_dos [] = { /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; -static struct tcp_states_t *tcp_state_table = tcp_states; - - -static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags) +static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags) { int on = (flags & 1); /* secure_tcp */ @@ -450,14 +458,7 @@ static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags) ** for most if not for all of the applications. Something ** like "capabilities" (flags) for each object. */ - tcp_state_table = (on? tcp_states_dos : tcp_states); -} - -static int -tcp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to) -{ - return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_TCP_S_LAST, - tcp_state_name_table, sname, to); + pd->tcp_state_table = (on ? tcp_states_dos : tcp_states); } static inline int tcp_state_idx(struct tcphdr *th) @@ -474,7 +475,7 @@ static inline int tcp_state_idx(struct tcphdr *th) } static inline void -set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, +set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, struct tcphdr *th) { int state_idx; @@ -497,7 +498,8 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, goto tcp_state_out; } - new_state = tcp_state_table[state_off+state_idx].next_state[cp->state]; + new_state = + pd->tcp_state_table[state_off+state_idx].next_state[cp->state]; tcp_state_out: if (new_state != cp->state) { @@ -505,7 +507,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->" "%s:%d state: %s->%s conn->refcnt:%d\n", - pp->name, + pd->pp->name, ((state_off == TCP_DIR_OUTPUT) ? "output " : "input "), th->syn ? 'S' : '.', @@ -535,17 +537,19 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, } } - cp->timeout = pp->timeout_table[cp->state = new_state]; + if (likely(pd)) + cp->timeout = pd->timeout_table[cp->state = new_state]; + else /* What to do ? */ + cp->timeout = tcp_timeouts[cp->state = new_state]; } - /* * Handle state transitions */ static int tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { struct tcphdr _tcph, *th; @@ -560,23 +564,12 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction, return 0; spin_lock(&cp->lock); - set_tcp_state(pp, cp, direction, th); + set_tcp_state(pd, cp, direction, th); spin_unlock(&cp->lock); return 1; } - -/* - * Hash table for TCP application incarnations - */ -#define TCP_APP_TAB_BITS 4 -#define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) -#define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) - -static struct list_head tcp_apps[TCP_APP_TAB_SIZE]; -static DEFINE_SPINLOCK(tcp_app_lock); - static inline __u16 tcp_app_hashkey(__be16 port) { return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port) @@ -584,44 +577,50 @@ static inline __u16 tcp_app_hashkey(__be16 port) } -static int tcp_register_app(struct ip_vs_app *inc) +static int tcp_register_app(struct net *net, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); hash = tcp_app_hashkey(port); - spin_lock_bh(&tcp_app_lock); - list_for_each_entry(i, &tcp_apps[hash], p_list) { + spin_lock_bh(&ipvs->tcp_app_lock); + list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } - list_add(&inc->p_list, &tcp_apps[hash]); - atomic_inc(&ip_vs_protocol_tcp.appcnt); + list_add(&inc->p_list, &ipvs->tcp_apps[hash]); + atomic_inc(&pd->appcnt); out: - spin_unlock_bh(&tcp_app_lock); + spin_unlock_bh(&ipvs->tcp_app_lock); return ret; } static void -tcp_unregister_app(struct ip_vs_app *inc) +tcp_unregister_app(struct net *net, struct ip_vs_app *inc) { - spin_lock_bh(&tcp_app_lock); - atomic_dec(&ip_vs_protocol_tcp.appcnt); + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + + spin_lock_bh(&ipvs->tcp_app_lock); + atomic_dec(&pd->appcnt); list_del(&inc->p_list); - spin_unlock_bh(&tcp_app_lock); + spin_unlock_bh(&ipvs->tcp_app_lock); } static int tcp_app_conn_bind(struct ip_vs_conn *cp) { + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); int hash; struct ip_vs_app *inc; int result = 0; @@ -633,12 +632,12 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) /* Lookup application incarnations and bind the right one */ hash = tcp_app_hashkey(cp->vport); - spin_lock(&tcp_app_lock); - list_for_each_entry(inc, &tcp_apps[hash], p_list) { + spin_lock(&ipvs->tcp_app_lock); + list_for_each_entry(inc, &ipvs->tcp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; - spin_unlock(&tcp_app_lock); + spin_unlock(&ipvs->tcp_app_lock); IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", @@ -655,7 +654,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) goto out; } } - spin_unlock(&tcp_app_lock); + spin_unlock(&ipvs->tcp_app_lock); out: return result; @@ -665,24 +664,35 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ -void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) +void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) { + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + spin_lock(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; - cp->timeout = ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_LISTEN]; + cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN] + : tcp_timeouts[IP_VS_TCP_S_LISTEN]); spin_unlock(&cp->lock); } - -static void ip_vs_tcp_init(struct ip_vs_protocol *pp) +/* --------------------------------------------- + * timeouts is netns related now. + * --------------------------------------------- + */ +static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) { - IP_VS_INIT_HASH_TABLE(tcp_apps); - pp->timeout_table = tcp_timeouts; -} + struct netns_ipvs *ipvs = net_ipvs(net); + ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); + spin_lock_init(&ipvs->tcp_app_lock); + pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, + sizeof(tcp_timeouts)); + pd->tcp_state_table = tcp_states; +} -static void ip_vs_tcp_exit(struct ip_vs_protocol *pp) +static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd) { + kfree(pd->timeout_table); } @@ -691,9 +701,10 @@ struct ip_vs_protocol ip_vs_protocol_tcp = { .protocol = IPPROTO_TCP, .num_states = IP_VS_TCP_S_LAST, .dont_defrag = 0, - .appcnt = ATOMIC_INIT(0), - .init = ip_vs_tcp_init, - .exit = ip_vs_tcp_exit, + .init = NULL, + .exit = NULL, + .init_netns = __ip_vs_tcp_init, + .exit_netns = __ip_vs_tcp_exit, .register_app = tcp_register_app, .unregister_app = tcp_unregister_app, .conn_schedule = tcp_conn_schedule, @@ -707,5 +718,4 @@ struct ip_vs_protocol ip_vs_protocol_tcp = { .app_conn_bind = tcp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = tcp_timeout_change, - .set_state_timeout = tcp_set_state_timeout, }; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 9d106a0..f1282cb 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -9,7 +9,8 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Changes: + * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> + * Network name space (netns) aware. * */ @@ -28,9 +29,10 @@ #include <net/ip6_checksum.h> static int -udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { + struct net *net; struct ip_vs_service *svc; struct udphdr _udph, *uh; struct ip_vs_iphdr iph; @@ -42,13 +44,13 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, *verdict = NF_DROP; return 0; } - - svc = ip_vs_service_get(af, skb->mark, iph.protocol, + net = skb_net(skb); + svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, &iph.daddr, uh->dest); if (svc) { int ignored; - if (ip_vs_todrop()) { + if (ip_vs_todrop(net_ipvs(net))) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -62,13 +64,19 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pp, &ignored); - if (!*cpp && !ignored) { - *verdict = ip_vs_leave(svc, skb, pp); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + if (!*cpp && ignored <= 0) { + if (!ignored) + *verdict = ip_vs_leave(svc, skb, pd); + else { + ip_vs_service_put(svc); + *verdict = NF_DROP; + } return 0; } ip_vs_service_put(svc); } + /* NF_ACCEPT */ return 1; } @@ -338,19 +346,6 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) return 1; } - -/* - * Note: the caller guarantees that only one of register_app, - * unregister_app or app_conn_bind is called each time. - */ - -#define UDP_APP_TAB_BITS 4 -#define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) -#define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) - -static struct list_head udp_apps[UDP_APP_TAB_SIZE]; -static DEFINE_SPINLOCK(udp_app_lock); - static inline __u16 udp_app_hashkey(__be16 port) { return (((__force u16)port >> UDP_APP_TAB_BITS) ^ (__force u16)port) @@ -358,44 +353,50 @@ static inline __u16 udp_app_hashkey(__be16 port) } -static int udp_register_app(struct ip_vs_app *inc) +static int udp_register_app(struct net *net, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); hash = udp_app_hashkey(port); - spin_lock_bh(&udp_app_lock); - list_for_each_entry(i, &udp_apps[hash], p_list) { + spin_lock_bh(&ipvs->udp_app_lock); + list_for_each_entry(i, &ipvs->udp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } - list_add(&inc->p_list, &udp_apps[hash]); - atomic_inc(&ip_vs_protocol_udp.appcnt); + list_add(&inc->p_list, &ipvs->udp_apps[hash]); + atomic_inc(&pd->appcnt); out: - spin_unlock_bh(&udp_app_lock); + spin_unlock_bh(&ipvs->udp_app_lock); return ret; } static void -udp_unregister_app(struct ip_vs_app *inc) +udp_unregister_app(struct net *net, struct ip_vs_app *inc) { - spin_lock_bh(&udp_app_lock); - atomic_dec(&ip_vs_protocol_udp.appcnt); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + struct netns_ipvs *ipvs = net_ipvs(net); + + spin_lock_bh(&ipvs->udp_app_lock); + atomic_dec(&pd->appcnt); list_del(&inc->p_list); - spin_unlock_bh(&udp_app_lock); + spin_unlock_bh(&ipvs->udp_app_lock); } static int udp_app_conn_bind(struct ip_vs_conn *cp) { + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); int hash; struct ip_vs_app *inc; int result = 0; @@ -407,12 +408,12 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp) /* Lookup application incarnations and bind the right one */ hash = udp_app_hashkey(cp->vport); - spin_lock(&udp_app_lock); - list_for_each_entry(inc, &udp_apps[hash], p_list) { + spin_lock(&ipvs->udp_app_lock); + list_for_each_entry(inc, &ipvs->udp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; - spin_unlock(&udp_app_lock); + spin_unlock(&ipvs->udp_app_lock); IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", @@ -429,14 +430,14 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp) goto out; } } - spin_unlock(&udp_app_lock); + spin_unlock(&ipvs->udp_app_lock); out: return result; } -static int udp_timeouts[IP_VS_UDP_S_LAST+1] = { +static const int udp_timeouts[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_NORMAL] = 5*60*HZ, [IP_VS_UDP_S_LAST] = 2*HZ, }; @@ -446,14 +447,6 @@ static const char *const udp_state_name_table[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_LAST] = "BUG!", }; - -static int -udp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to) -{ - return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_UDP_S_LAST, - udp_state_name_table, sname, to); -} - static const char * udp_state_name(int state) { if (state >= IP_VS_UDP_S_LAST) @@ -464,20 +457,30 @@ static const char * udp_state_name(int state) static int udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { - cp->timeout = pp->timeout_table[IP_VS_UDP_S_NORMAL]; + if (unlikely(!pd)) { + pr_err("UDP no ns data\n"); + return 0; + } + + cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; return 1; } -static void udp_init(struct ip_vs_protocol *pp) +static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) { - IP_VS_INIT_HASH_TABLE(udp_apps); - pp->timeout_table = udp_timeouts; + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE); + spin_lock_init(&ipvs->udp_app_lock); + pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, + sizeof(udp_timeouts)); } -static void udp_exit(struct ip_vs_protocol *pp) +static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd) { + kfree(pd->timeout_table); } @@ -486,8 +489,10 @@ struct ip_vs_protocol ip_vs_protocol_udp = { .protocol = IPPROTO_UDP, .num_states = IP_VS_UDP_S_LAST, .dont_defrag = 0, - .init = udp_init, - .exit = udp_exit, + .init = NULL, + .exit = NULL, + .init_netns = __udp_init, + .exit_netns = __udp_exit, .conn_schedule = udp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, @@ -501,5 +506,4 @@ struct ip_vs_protocol ip_vs_protocol_udp = { .app_conn_bind = udp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, - .set_state_timeout = udp_set_state_timeout, }; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index ab85aed..d1b7298 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -5,6 +5,18 @@ * high-performance and highly available server based on a * cluster of servers. * + * Version 1, is capable of handling both version 0 and 1 messages. + * Version 0 is the plain old format. + * Note Version 0 receivers will just drop Ver 1 messages. + * Version 1 is capable of handle IPv6, Persistence data, + * time-outs, and firewall marks. + * In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order. + * Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0 + * + * Definitions Message: is a complete datagram + * Sync_conn: is a part of a Message + * Param Data is an option to a Sync_conn. + * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * ip_vs_sync: sync connection info from master load balancer to backups @@ -15,6 +27,8 @@ * Alexandre Cassen : Added SyncID support for incoming sync * messages filtering. * Justin Ossevoort : Fix endian problem on sync message size. + * Hans Schillstrom : Added Version 1: i.e. IPv6, + * Persistence support, fwmark and time-out. */ #define KMSG_COMPONENT "IPVS" @@ -35,6 +49,8 @@ #include <linux/wait.h> #include <linux/kernel.h> +#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */ + #include <net/ip.h> #include <net/sock.h> @@ -43,11 +59,13 @@ #define IP_VS_SYNC_GROUP 0xe0000051 /* multicast addr - 224.0.0.81 */ #define IP_VS_SYNC_PORT 8848 /* multicast port */ +#define SYNC_PROTO_VER 1 /* Protocol version in header */ /* * IPVS sync connection entry + * Version 0, i.e. original version. */ -struct ip_vs_sync_conn { +struct ip_vs_sync_conn_v0 { __u8 reserved; /* Protocol, addresses and port numbers */ @@ -71,41 +89,159 @@ struct ip_vs_sync_conn_options { struct ip_vs_seq out_seq; /* outgoing seq. struct */ }; +/* + Sync Connection format (sync_conn) + + 0 1 2 3 + 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Type | Protocol | Ver. | Size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Flags | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | State | cport | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | vport | dport | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | fwmark | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | timeout (in sec.) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | ... | + | IP-Addresses (v4 or v6) | + | ... | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + Optional Parameters. + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Param. Type | Param. Length | Param. data | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | + | ... | + | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | | Param Type | Param. Length | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Param data | + | Last Param data should be padded for 32 bit alignment | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +*/ + +/* + * Type 0, IPv4 sync connection format + */ +struct ip_vs_sync_v4 { + __u8 type; + __u8 protocol; /* Which protocol (TCP/UDP) */ + __be16 ver_size; /* Version msb 4 bits */ + /* Flags and state transition */ + __be32 flags; /* status flags */ + __be16 state; /* state info */ + /* Protocol, addresses and port numbers */ + __be16 cport; + __be16 vport; + __be16 dport; + __be32 fwmark; /* Firewall mark from skb */ + __be32 timeout; /* cp timeout */ + __be32 caddr; /* client address */ + __be32 vaddr; /* virtual address */ + __be32 daddr; /* destination address */ + /* The sequence options start here */ + /* PE data padded to 32bit alignment after seq. options */ +}; +/* + * Type 2 messages IPv6 + */ +struct ip_vs_sync_v6 { + __u8 type; + __u8 protocol; /* Which protocol (TCP/UDP) */ + __be16 ver_size; /* Version msb 4 bits */ + /* Flags and state transition */ + __be32 flags; /* status flags */ + __be16 state; /* state info */ + /* Protocol, addresses and port numbers */ + __be16 cport; + __be16 vport; + __be16 dport; + __be32 fwmark; /* Firewall mark from skb */ + __be32 timeout; /* cp timeout */ + struct in6_addr caddr; /* client address */ + struct in6_addr vaddr; /* virtual address */ + struct in6_addr daddr; /* destination address */ + /* The sequence options start here */ + /* PE data padded to 32bit alignment after seq. options */ +}; + +union ip_vs_sync_conn { + struct ip_vs_sync_v4 v4; + struct ip_vs_sync_v6 v6; +}; + +/* Bits in Type field in above */ +#define STYPE_INET6 0 +#define STYPE_F_INET6 (1 << STYPE_INET6) + +#define SVER_SHIFT 12 /* Shift to get version */ +#define SVER_MASK 0x0fff /* Mask to strip version */ + +#define IPVS_OPT_SEQ_DATA 1 +#define IPVS_OPT_PE_DATA 2 +#define IPVS_OPT_PE_NAME 3 +#define IPVS_OPT_PARAM 7 + +#define IPVS_OPT_F_SEQ_DATA (1 << (IPVS_OPT_SEQ_DATA-1)) +#define IPVS_OPT_F_PE_DATA (1 << (IPVS_OPT_PE_DATA-1)) +#define IPVS_OPT_F_PE_NAME (1 << (IPVS_OPT_PE_NAME-1)) +#define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1)) + struct ip_vs_sync_thread_data { + struct net *net; struct socket *sock; char *buf; }; -#define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn)) +/* Version 0 definition of packet sizes */ +#define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn_v0)) #define FULL_CONN_SIZE \ -(sizeof(struct ip_vs_sync_conn) + sizeof(struct ip_vs_sync_conn_options)) +(sizeof(struct ip_vs_sync_conn_v0) + sizeof(struct ip_vs_sync_conn_options)) /* - The master mulitcasts messages to the backup load balancers in the - following format. + The master mulitcasts messages (Datagrams) to the backup load balancers + in the following format. + + Version 1: + Note, first byte should be Zero, so ver 0 receivers will drop the packet. 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Count Conns | SyncID | Size | + | 0 | SyncID | Size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Count Conns | Version | Reserved, set to Zero | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (1) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | . | - | . | + ~ . ~ | . | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (n) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Version 0 Header + 0 1 2 3 + 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Count Conns | SyncID | Size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | IPVS Sync Connection (1) | */ #define SYNC_MESG_HEADER_LEN 4 #define MAX_CONNS_PER_SYNCBUFF 255 /* nr_conns in ip_vs_sync_mesg is 8 bit */ -struct ip_vs_sync_mesg { +/* Version 0 header */ +struct ip_vs_sync_mesg_v0 { __u8 nr_conns; __u8 syncid; __u16 size; @@ -113,9 +249,16 @@ struct ip_vs_sync_mesg { /* ip_vs_sync_conn entries start here */ }; -/* the maximum length of sync (sending/receiving) message */ -static int sync_send_mesg_maxlen; -static int sync_recv_mesg_maxlen; +/* Version 1 header */ +struct ip_vs_sync_mesg { + __u8 reserved; /* must be zero */ + __u8 syncid; + __u16 size; + __u8 nr_conns; + __s8 version; /* SYNC_PROTO_VER */ + __u16 spare; + /* ip_vs_sync_conn entries start here */ +}; struct ip_vs_sync_buff { struct list_head list; @@ -127,28 +270,6 @@ struct ip_vs_sync_buff { unsigned char *end; }; - -/* the sync_buff list head and the lock */ -static LIST_HEAD(ip_vs_sync_queue); -static DEFINE_SPINLOCK(ip_vs_sync_lock); - -/* current sync_buff for accepting new conn entries */ -static struct ip_vs_sync_buff *curr_sb = NULL; -static DEFINE_SPINLOCK(curr_sb_lock); - -/* ipvs sync daemon state */ -volatile int ip_vs_sync_state = IP_VS_STATE_NONE; -volatile int ip_vs_master_syncid = 0; -volatile int ip_vs_backup_syncid = 0; - -/* multicast interface name */ -char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; - -/* sync daemon tasks */ -static struct task_struct *sync_master_thread; -static struct task_struct *sync_backup_thread; - /* multicast addr */ static struct sockaddr_in mcast_addr = { .sin_family = AF_INET, @@ -156,41 +277,71 @@ static struct sockaddr_in mcast_addr = { .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), }; +/* + * Copy of struct ip_vs_seq + * From unaligned network order to aligned host order + */ +static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) +{ + ho->init_seq = get_unaligned_be32(&no->init_seq); + ho->delta = get_unaligned_be32(&no->delta); + ho->previous_delta = get_unaligned_be32(&no->previous_delta); +} + +/* + * Copy of struct ip_vs_seq + * From Aligned host order to unaligned network order + */ +static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no) +{ + put_unaligned_be32(ho->init_seq, &no->init_seq); + put_unaligned_be32(ho->delta, &no->delta); + put_unaligned_be32(ho->previous_delta, &no->previous_delta); +} -static inline struct ip_vs_sync_buff *sb_dequeue(void) +static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs) { struct ip_vs_sync_buff *sb; - spin_lock_bh(&ip_vs_sync_lock); - if (list_empty(&ip_vs_sync_queue)) { + spin_lock_bh(&ipvs->sync_lock); + if (list_empty(&ipvs->sync_queue)) { sb = NULL; } else { - sb = list_entry(ip_vs_sync_queue.next, + sb = list_entry(ipvs->sync_queue.next, struct ip_vs_sync_buff, list); list_del(&sb->list); } - spin_unlock_bh(&ip_vs_sync_lock); + spin_unlock_bh(&ipvs->sync_lock); return sb; } -static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void) +/* + * Create a new sync buffer for Version 1 proto. + */ +static inline struct ip_vs_sync_buff * +ip_vs_sync_buff_create(struct netns_ipvs *ipvs) { struct ip_vs_sync_buff *sb; if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) return NULL; - if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) { + sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC); + if (!sb->mesg) { kfree(sb); return NULL; } + sb->mesg->reserved = 0; /* old nr_conns i.e. must be zeo now */ + sb->mesg->version = SYNC_PROTO_VER; + sb->mesg->syncid = ipvs->master_syncid; + sb->mesg->size = sizeof(struct ip_vs_sync_mesg); sb->mesg->nr_conns = 0; - sb->mesg->syncid = ip_vs_master_syncid; - sb->mesg->size = 4; - sb->head = (unsigned char *)sb->mesg + 4; - sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen; + sb->mesg->spare = 0; + sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg); + sb->end = (unsigned char *)sb->mesg + ipvs->send_mesg_maxlen; + sb->firstuse = jiffies; return sb; } @@ -201,14 +352,16 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb) kfree(sb); } -static inline void sb_queue_tail(struct ip_vs_sync_buff *sb) +static inline void sb_queue_tail(struct netns_ipvs *ipvs) { - spin_lock(&ip_vs_sync_lock); - if (ip_vs_sync_state & IP_VS_STATE_MASTER) - list_add_tail(&sb->list, &ip_vs_sync_queue); + struct ip_vs_sync_buff *sb = ipvs->sync_buff; + + spin_lock(&ipvs->sync_lock); + if (ipvs->sync_state & IP_VS_STATE_MASTER) + list_add_tail(&sb->list, &ipvs->sync_queue); else ip_vs_sync_buff_release(sb); - spin_unlock(&ip_vs_sync_lock); + spin_unlock(&ipvs->sync_lock); } /* @@ -216,36 +369,101 @@ static inline void sb_queue_tail(struct ip_vs_sync_buff *sb) * than the specified time or the specified time is zero. */ static inline struct ip_vs_sync_buff * -get_curr_sync_buff(unsigned long time) +get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time) { struct ip_vs_sync_buff *sb; - spin_lock_bh(&curr_sb_lock); - if (curr_sb && (time == 0 || - time_before(jiffies - curr_sb->firstuse, time))) { - sb = curr_sb; - curr_sb = NULL; + spin_lock_bh(&ipvs->sync_buff_lock); + if (ipvs->sync_buff && (time == 0 || + time_before(jiffies - ipvs->sync_buff->firstuse, time))) { + sb = ipvs->sync_buff; + ipvs->sync_buff = NULL; } else sb = NULL; - spin_unlock_bh(&curr_sb_lock); + spin_unlock_bh(&ipvs->sync_buff_lock); return sb; } +/* + * Switch mode from sending version 0 or 1 + * - must handle sync_buf + */ +void ip_vs_sync_switch_mode(struct net *net, int mode) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) + return; + if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff) + return; + + spin_lock_bh(&ipvs->sync_buff_lock); + /* Buffer empty ? then let buf_create do the job */ + if (ipvs->sync_buff->mesg->size <= sizeof(struct ip_vs_sync_mesg)) { + kfree(ipvs->sync_buff); + ipvs->sync_buff = NULL; + } else { + spin_lock_bh(&ipvs->sync_lock); + if (ipvs->sync_state & IP_VS_STATE_MASTER) + list_add_tail(&ipvs->sync_buff->list, + &ipvs->sync_queue); + else + ip_vs_sync_buff_release(ipvs->sync_buff); + spin_unlock_bh(&ipvs->sync_lock); + } + spin_unlock_bh(&ipvs->sync_buff_lock); +} /* + * Create a new sync buffer for Version 0 proto. + */ +static inline struct ip_vs_sync_buff * +ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) +{ + struct ip_vs_sync_buff *sb; + struct ip_vs_sync_mesg_v0 *mesg; + + if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) + return NULL; + + sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC); + if (!sb->mesg) { + kfree(sb); + return NULL; + } + mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg; + mesg->nr_conns = 0; + mesg->syncid = ipvs->master_syncid; + mesg->size = sizeof(struct ip_vs_sync_mesg_v0); + sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0); + sb->end = (unsigned char *)mesg + ipvs->send_mesg_maxlen; + sb->firstuse = jiffies; + return sb; +} + +/* + * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. - * Called by ip_vs_in. */ -void ip_vs_sync_conn(struct ip_vs_conn *cp) +void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp) { - struct ip_vs_sync_mesg *m; - struct ip_vs_sync_conn *s; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_sync_mesg_v0 *m; + struct ip_vs_sync_conn_v0 *s; int len; - spin_lock(&curr_sb_lock); - if (!curr_sb) { - if (!(curr_sb=ip_vs_sync_buff_create())) { - spin_unlock(&curr_sb_lock); + if (unlikely(cp->af != AF_INET)) + return; + /* Do not sync ONE PACKET */ + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + return; + + spin_lock(&ipvs->sync_buff_lock); + if (!ipvs->sync_buff) { + ipvs->sync_buff = + ip_vs_sync_buff_create_v0(ipvs); + if (!ipvs->sync_buff) { + spin_unlock(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } @@ -253,10 +471,11 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : SIMPLE_CONN_SIZE; - m = curr_sb->mesg; - s = (struct ip_vs_sync_conn *)curr_sb->head; + m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg; + s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head; /* copy members */ + s->reserved = 0; s->protocol = cp->protocol; s->cport = cp->cport; s->vport = cp->vport; @@ -274,83 +493,366 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) m->nr_conns++; m->size += len; - curr_sb->head += len; + ipvs->sync_buff->head += len; /* check if there is a space for next one */ - if (curr_sb->head+FULL_CONN_SIZE > curr_sb->end) { - sb_queue_tail(curr_sb); - curr_sb = NULL; + if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) { + sb_queue_tail(ipvs); + ipvs->sync_buff = NULL; } - spin_unlock(&curr_sb_lock); + spin_unlock(&ipvs->sync_buff_lock); /* synchronize its controller if it has */ if (cp->control) - ip_vs_sync_conn(cp->control); + ip_vs_sync_conn(net, cp->control); +} + +/* + * Add an ip_vs_conn information into the current sync_buff. + * Called by ip_vs_in. + * Sending Version 1 messages + */ +void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_sync_mesg *m; + union ip_vs_sync_conn *s; + __u8 *p; + unsigned int len, pe_name_len, pad; + + /* Handle old version of the protocol */ + if (ipvs->sysctl_sync_ver == 0) { + ip_vs_sync_conn_v0(net, cp); + return; + } + /* Do not sync ONE PACKET */ + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + goto control; +sloop: + /* Sanity checks */ + pe_name_len = 0; + if (cp->pe_data_len) { + if (!cp->pe_data || !cp->dest) { + IP_VS_ERR_RL("SYNC, connection pe_data invalid\n"); + return; + } + pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN); + } + + spin_lock(&ipvs->sync_buff_lock); + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + len = sizeof(struct ip_vs_sync_v6); + else +#endif + len = sizeof(struct ip_vs_sync_v4); + + if (cp->flags & IP_VS_CONN_F_SEQ_MASK) + len += sizeof(struct ip_vs_sync_conn_options) + 2; + + if (cp->pe_data_len) + len += cp->pe_data_len + 2; /* + Param hdr field */ + if (pe_name_len) + len += pe_name_len + 2; + + /* check if there is a space for this one */ + pad = 0; + if (ipvs->sync_buff) { + pad = (4 - (size_t)ipvs->sync_buff->head) & 3; + if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) { + sb_queue_tail(ipvs); + ipvs->sync_buff = NULL; + pad = 0; + } + } + + if (!ipvs->sync_buff) { + ipvs->sync_buff = ip_vs_sync_buff_create(ipvs); + if (!ipvs->sync_buff) { + spin_unlock(&ipvs->sync_buff_lock); + pr_err("ip_vs_sync_buff_create failed.\n"); + return; + } + } + + m = ipvs->sync_buff->mesg; + p = ipvs->sync_buff->head; + ipvs->sync_buff->head += pad + len; + m->size += pad + len; + /* Add ev. padding from prev. sync_conn */ + while (pad--) + *(p++) = 0; + + s = (union ip_vs_sync_conn *)p; + + /* Set message type & copy members */ + s->v4.type = (cp->af == AF_INET6 ? STYPE_F_INET6 : 0); + s->v4.ver_size = htons(len & SVER_MASK); /* Version 0 */ + s->v4.flags = htonl(cp->flags & ~IP_VS_CONN_F_HASHED); + s->v4.state = htons(cp->state); + s->v4.protocol = cp->protocol; + s->v4.cport = cp->cport; + s->v4.vport = cp->vport; + s->v4.dport = cp->dport; + s->v4.fwmark = htonl(cp->fwmark); + s->v4.timeout = htonl(cp->timeout / HZ); + m->nr_conns++; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) { + p += sizeof(struct ip_vs_sync_v6); + ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6); + ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6); + ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6); + } else +#endif + { + p += sizeof(struct ip_vs_sync_v4); /* options ptr */ + s->v4.caddr = cp->caddr.ip; + s->v4.vaddr = cp->vaddr.ip; + s->v4.daddr = cp->daddr.ip; + } + if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { + *(p++) = IPVS_OPT_SEQ_DATA; + *(p++) = sizeof(struct ip_vs_sync_conn_options); + hton_seq((struct ip_vs_seq *)p, &cp->in_seq); + p += sizeof(struct ip_vs_seq); + hton_seq((struct ip_vs_seq *)p, &cp->out_seq); + p += sizeof(struct ip_vs_seq); + } + /* Handle pe data */ + if (cp->pe_data_len && cp->pe_data) { + *(p++) = IPVS_OPT_PE_DATA; + *(p++) = cp->pe_data_len; + memcpy(p, cp->pe_data, cp->pe_data_len); + p += cp->pe_data_len; + if (pe_name_len) { + /* Add PE_NAME */ + *(p++) = IPVS_OPT_PE_NAME; + *(p++) = pe_name_len; + memcpy(p, cp->pe->name, pe_name_len); + p += pe_name_len; + } + } + + spin_unlock(&ipvs->sync_buff_lock); + +control: + /* synchronize its controller if it has */ + cp = cp->control; + if (!cp) + return; + /* + * Reduce sync rate for templates + * i.e only increment in_pkts for Templates. + */ + if (cp->flags & IP_VS_CONN_F_TEMPLATE) { + int pkts = atomic_add_return(1, &cp->in_pkts); + + if (pkts % ipvs->sysctl_sync_threshold[1] != 1) + return; + } + goto sloop; } +/* + * fill_param used by version 1 + */ static inline int -ip_vs_conn_fill_param_sync(int af, int protocol, - const union nf_inet_addr *caddr, __be16 cport, - const union nf_inet_addr *vaddr, __be16 vport, - struct ip_vs_conn_param *p) +ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc, + struct ip_vs_conn_param *p, + __u8 *pe_data, unsigned int pe_data_len, + __u8 *pe_name, unsigned int pe_name_len) { - /* XXX: Need to take into account persistence engine */ - ip_vs_conn_fill_param(af, protocol, caddr, cport, vaddr, vport, p); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + ip_vs_conn_fill_param(net, af, sc->v6.protocol, + (const union nf_inet_addr *)&sc->v6.caddr, + sc->v6.cport, + (const union nf_inet_addr *)&sc->v6.vaddr, + sc->v6.vport, p); + else +#endif + ip_vs_conn_fill_param(net, af, sc->v4.protocol, + (const union nf_inet_addr *)&sc->v4.caddr, + sc->v4.cport, + (const union nf_inet_addr *)&sc->v4.vaddr, + sc->v4.vport, p); + /* Handle pe data */ + if (pe_data_len) { + if (pe_name_len) { + char buff[IP_VS_PENAME_MAXLEN+1]; + + memcpy(buff, pe_name, pe_name_len); + buff[pe_name_len]=0; + p->pe = __ip_vs_pe_getbyname(buff); + if (!p->pe) { + IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", + buff); + return 1; + } + } else { + IP_VS_ERR_RL("BACKUP, Invalid PE parameters\n"); + return 1; + } + + p->pe_data = kmalloc(pe_data_len, GFP_ATOMIC); + if (!p->pe_data) { + if (p->pe->module) + module_put(p->pe->module); + return -ENOMEM; + } + memcpy(p->pe_data, pe_data, pe_data_len); + p->pe_data_len = pe_data_len; + } return 0; } /* - * Process received multicast message and create the corresponding - * ip_vs_conn entries. + * Connection Add / Update. + * Common for version 0 and 1 reception of backup sync_conns. + * Param: ... + * timeout is in sec. */ -static void ip_vs_process_message(const char *buffer, const size_t buflen) +static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, + unsigned int flags, unsigned int state, + unsigned int protocol, unsigned int type, + const union nf_inet_addr *daddr, __be16 dport, + unsigned long timeout, __u32 fwmark, + struct ip_vs_sync_conn_options *opt) { - struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer; - struct ip_vs_sync_conn *s; - struct ip_vs_sync_conn_options *opt; - struct ip_vs_conn *cp; - struct ip_vs_protocol *pp; struct ip_vs_dest *dest; - struct ip_vs_conn_param param; - char *p; - int i; + struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net_ipvs(net); - if (buflen < sizeof(struct ip_vs_sync_mesg)) { - IP_VS_ERR_RL("sync message header too short\n"); - return; - } + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + cp = ip_vs_conn_in_get(param); + else + cp = ip_vs_ct_in_get(param); - /* Convert size back to host byte order */ - m->size = ntohs(m->size); + if (cp && param->pe_data) /* Free pe_data */ + kfree(param->pe_data); + if (!cp) { + /* + * Find the appropriate destination for the connection. + * If it is not found the connection will remain unbound + * but still handled. + */ + dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr, + param->vport, protocol, fwmark); - if (buflen != m->size) { - IP_VS_ERR_RL("bogus sync message size\n"); - return; + /* Set the approprite ativity flag */ + if (protocol == IPPROTO_TCP) { + if (state != IP_VS_TCP_S_ESTABLISHED) + flags |= IP_VS_CONN_F_INACTIVE; + else + flags &= ~IP_VS_CONN_F_INACTIVE; + } else if (protocol == IPPROTO_SCTP) { + if (state != IP_VS_SCTP_S_ESTABLISHED) + flags |= IP_VS_CONN_F_INACTIVE; + else + flags &= ~IP_VS_CONN_F_INACTIVE; + } + cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark); + if (dest) + atomic_dec(&dest->refcnt); + if (!cp) { + if (param->pe_data) + kfree(param->pe_data); + IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); + return; + } + } else if (!cp->dest) { + dest = ip_vs_try_bind_dest(cp); + if (dest) + atomic_dec(&dest->refcnt); + } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) && + (cp->state != state)) { + /* update active/inactive flag for the connection */ + dest = cp->dest; + if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && + (state != IP_VS_TCP_S_ESTABLISHED)) { + atomic_dec(&dest->activeconns); + atomic_inc(&dest->inactconns); + cp->flags |= IP_VS_CONN_F_INACTIVE; + } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && + (state == IP_VS_TCP_S_ESTABLISHED)) { + atomic_inc(&dest->activeconns); + atomic_dec(&dest->inactconns); + cp->flags &= ~IP_VS_CONN_F_INACTIVE; + } + } else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) && + (cp->state != state)) { + dest = cp->dest; + if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && + (state != IP_VS_SCTP_S_ESTABLISHED)) { + atomic_dec(&dest->activeconns); + atomic_inc(&dest->inactconns); + cp->flags &= ~IP_VS_CONN_F_INACTIVE; + } } - /* SyncID sanity check */ - if (ip_vs_backup_syncid != 0 && m->syncid != ip_vs_backup_syncid) { - IP_VS_DBG(7, "Ignoring incoming msg with syncid = %d\n", - m->syncid); - return; + if (opt) + memcpy(&cp->in_seq, opt, sizeof(*opt)); + atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]); + cp->state = state; + cp->old_state = cp->state; + /* + * For Ver 0 messages style + * - Not possible to recover the right timeout for templates + * - can not find the right fwmark + * virtual service. If needed, we can do it for + * non-fwmark persistent services. + * Ver 1 messages style. + * - No problem. + */ + if (timeout) { + if (timeout > MAX_SCHEDULE_TIMEOUT / HZ) + timeout = MAX_SCHEDULE_TIMEOUT / HZ; + cp->timeout = timeout*HZ; + } else { + struct ip_vs_proto_data *pd; + + pd = ip_vs_proto_data_get(net, protocol); + if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table) + cp->timeout = pd->timeout_table[state]; + else + cp->timeout = (3*60*HZ); } + ip_vs_conn_put(cp); +} - p = (char *)buffer + sizeof(struct ip_vs_sync_mesg); +/* + * Process received multicast message for Version 0 + */ +static void ip_vs_process_message_v0(struct net *net, const char *buffer, + const size_t buflen) +{ + struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer; + struct ip_vs_sync_conn_v0 *s; + struct ip_vs_sync_conn_options *opt; + struct ip_vs_protocol *pp; + struct ip_vs_conn_param param; + char *p; + int i; + + p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0); for (i=0; i<m->nr_conns; i++) { unsigned flags, state; if (p + SIMPLE_CONN_SIZE > buffer+buflen) { - IP_VS_ERR_RL("bogus conn in sync message\n"); + IP_VS_ERR_RL("BACKUP v0, bogus conn\n"); return; } - s = (struct ip_vs_sync_conn *) p; + s = (struct ip_vs_sync_conn_v0 *) p; flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC; flags &= ~IP_VS_CONN_F_HASHED; if (flags & IP_VS_CONN_F_SEQ_MASK) { opt = (struct ip_vs_sync_conn_options *)&s[1]; p += FULL_CONN_SIZE; if (p > buffer+buflen) { - IP_VS_ERR_RL("bogus conn options in sync message\n"); + IP_VS_ERR_RL("BACKUP v0, Dropping buffer bogus conn options\n"); return; } } else { @@ -362,118 +864,286 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) if (!(flags & IP_VS_CONN_F_TEMPLATE)) { pp = ip_vs_proto_get(s->protocol); if (!pp) { - IP_VS_ERR_RL("Unsupported protocol %u in sync msg\n", + IP_VS_DBG(2, "BACKUP v0, Unsupported protocol %u\n", s->protocol); continue; } if (state >= pp->num_states) { - IP_VS_DBG(2, "Invalid %s state %u in sync msg\n", + IP_VS_DBG(2, "BACKUP v0, Invalid %s state %u\n", pp->name, state); continue; } } else { /* protocol in templates is not used for state/timeout */ - pp = NULL; if (state > 0) { - IP_VS_DBG(2, "Invalid template state %u in sync msg\n", + IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n", state); state = 0; } } - { - if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol, - (union nf_inet_addr *)&s->caddr, - s->cport, - (union nf_inet_addr *)&s->vaddr, - s->vport, ¶m)) { - pr_err("ip_vs_conn_fill_param_sync failed"); - return; + ip_vs_conn_fill_param(net, AF_INET, s->protocol, + (const union nf_inet_addr *)&s->caddr, + s->cport, + (const union nf_inet_addr *)&s->vaddr, + s->vport, ¶m); + + /* Send timeout as Zero */ + ip_vs_proc_conn(net, ¶m, flags, state, s->protocol, AF_INET, + (union nf_inet_addr *)&s->daddr, s->dport, + 0, 0, opt); + } +} + +/* + * Handle options + */ +static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen, + __u32 *opt_flags, + struct ip_vs_sync_conn_options *opt) +{ + struct ip_vs_sync_conn_options *topt; + + topt = (struct ip_vs_sync_conn_options *)p; + + if (plen != sizeof(struct ip_vs_sync_conn_options)) { + IP_VS_DBG(2, "BACKUP, bogus conn options length\n"); + return -EINVAL; + } + if (*opt_flags & IPVS_OPT_F_SEQ_DATA) { + IP_VS_DBG(2, "BACKUP, conn options found twice\n"); + return -EINVAL; + } + ntoh_seq(&topt->in_seq, &opt->in_seq); + ntoh_seq(&topt->out_seq, &opt->out_seq); + *opt_flags |= IPVS_OPT_F_SEQ_DATA; + return 0; +} + +static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len, + __u8 **data, unsigned int maxlen, + __u32 *opt_flags, __u32 flag) +{ + if (plen > maxlen) { + IP_VS_DBG(2, "BACKUP, bogus par.data len > %d\n", maxlen); + return -EINVAL; + } + if (*opt_flags & flag) { + IP_VS_DBG(2, "BACKUP, Par.data found twice 0x%x\n", flag); + return -EINVAL; + } + *data_len = plen; + *data = p; + *opt_flags |= flag; + return 0; +} +/* + * Process a Version 1 sync. connection + */ +static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) +{ + struct ip_vs_sync_conn_options opt; + union ip_vs_sync_conn *s; + struct ip_vs_protocol *pp; + struct ip_vs_conn_param param; + __u32 flags; + unsigned int af, state, pe_data_len=0, pe_name_len=0; + __u8 *pe_data=NULL, *pe_name=NULL; + __u32 opt_flags=0; + int retc=0; + + s = (union ip_vs_sync_conn *) p; + + if (s->v6.type & STYPE_F_INET6) { +#ifdef CONFIG_IP_VS_IPV6 + af = AF_INET6; + p += sizeof(struct ip_vs_sync_v6); +#else + IP_VS_DBG(3,"BACKUP, IPv6 msg received, and IPVS is not compiled for IPv6\n"); + retc = 10; + goto out; +#endif + } else if (!s->v4.type) { + af = AF_INET; + p += sizeof(struct ip_vs_sync_v4); + } else { + return -10; + } + if (p > msg_end) + return -20; + + /* Process optional params check Type & Len. */ + while (p < msg_end) { + int ptype; + int plen; + + if (p+2 > msg_end) + return -30; + ptype = *(p++); + plen = *(p++); + + if (!plen || ((p + plen) > msg_end)) + return -40; + /* Handle seq option p = param data */ + switch (ptype & ~IPVS_OPT_F_PARAM) { + case IPVS_OPT_SEQ_DATA: + if (ip_vs_proc_seqopt(p, plen, &opt_flags, &opt)) + return -50; + break; + + case IPVS_OPT_PE_DATA: + if (ip_vs_proc_str(p, plen, &pe_data_len, &pe_data, + IP_VS_PEDATA_MAXLEN, &opt_flags, + IPVS_OPT_F_PE_DATA)) + return -60; + break; + + case IPVS_OPT_PE_NAME: + if (ip_vs_proc_str(p, plen,&pe_name_len, &pe_name, + IP_VS_PENAME_MAXLEN, &opt_flags, + IPVS_OPT_F_PE_NAME)) + return -70; + break; + + default: + /* Param data mandatory ? */ + if (!(ptype & IPVS_OPT_F_PARAM)) { + IP_VS_DBG(3, "BACKUP, Unknown mandatory param %d found\n", + ptype & ~IPVS_OPT_F_PARAM); + retc = 20; + goto out; } - if (!(flags & IP_VS_CONN_F_TEMPLATE)) - cp = ip_vs_conn_in_get(¶m); - else - cp = ip_vs_ct_in_get(¶m); } - if (!cp) { - /* - * Find the appropriate destination for the connection. - * If it is not found the connection will remain unbound - * but still handled. - */ - dest = ip_vs_find_dest(AF_INET, - (union nf_inet_addr *)&s->daddr, - s->dport, - (union nf_inet_addr *)&s->vaddr, - s->vport, - s->protocol); - /* Set the approprite ativity flag */ - if (s->protocol == IPPROTO_TCP) { - if (state != IP_VS_TCP_S_ESTABLISHED) - flags |= IP_VS_CONN_F_INACTIVE; - else - flags &= ~IP_VS_CONN_F_INACTIVE; - } else if (s->protocol == IPPROTO_SCTP) { - if (state != IP_VS_SCTP_S_ESTABLISHED) - flags |= IP_VS_CONN_F_INACTIVE; - else - flags &= ~IP_VS_CONN_F_INACTIVE; + p += plen; /* Next option */ + } + + /* Get flags and Mask off unsupported */ + flags = ntohl(s->v4.flags) & IP_VS_CONN_F_BACKUP_MASK; + flags |= IP_VS_CONN_F_SYNC; + state = ntohs(s->v4.state); + + if (!(flags & IP_VS_CONN_F_TEMPLATE)) { + pp = ip_vs_proto_get(s->v4.protocol); + if (!pp) { + IP_VS_DBG(3,"BACKUP, Unsupported protocol %u\n", + s->v4.protocol); + retc = 30; + goto out; + } + if (state >= pp->num_states) { + IP_VS_DBG(3, "BACKUP, Invalid %s state %u\n", + pp->name, state); + retc = 40; + goto out; + } + } else { + /* protocol in templates is not used for state/timeout */ + if (state > 0) { + IP_VS_DBG(3, "BACKUP, Invalid template state %u\n", + state); + state = 0; + } + } + if (ip_vs_conn_fill_param_sync(net, af, s, ¶m, pe_data, + pe_data_len, pe_name, pe_name_len)) { + retc = 50; + goto out; + } + /* If only IPv4, just silent skip IPv6 */ + if (af == AF_INET) + ip_vs_proc_conn(net, ¶m, flags, state, s->v4.protocol, af, + (union nf_inet_addr *)&s->v4.daddr, s->v4.dport, + ntohl(s->v4.timeout), ntohl(s->v4.fwmark), + (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) + ); +#ifdef CONFIG_IP_VS_IPV6 + else + ip_vs_proc_conn(net, ¶m, flags, state, s->v6.protocol, af, + (union nf_inet_addr *)&s->v6.daddr, s->v6.dport, + ntohl(s->v6.timeout), ntohl(s->v6.fwmark), + (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) + ); +#endif + return 0; + /* Error exit */ +out: + IP_VS_DBG(2, "BACKUP, Single msg dropped err:%d\n", retc); + return retc; + +} +/* + * Process received multicast message and create the corresponding + * ip_vs_conn entries. + * Handles Version 0 & 1 + */ +static void ip_vs_process_message(struct net *net, __u8 *buffer, + const size_t buflen) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer; + __u8 *p, *msg_end; + int i, nr_conns; + + if (buflen < sizeof(struct ip_vs_sync_mesg_v0)) { + IP_VS_DBG(2, "BACKUP, message header too short\n"); + return; + } + /* Convert size back to host byte order */ + m2->size = ntohs(m2->size); + + if (buflen != m2->size) { + IP_VS_DBG(2, "BACKUP, bogus message size\n"); + return; + } + /* SyncID sanity check */ + if (ipvs->backup_syncid != 0 && m2->syncid != ipvs->backup_syncid) { + IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid); + return; + } + /* Handle version 1 message */ + if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0) + && (m2->spare == 0)) { + + msg_end = buffer + sizeof(struct ip_vs_sync_mesg); + nr_conns = m2->nr_conns; + + for (i=0; i<nr_conns; i++) { + union ip_vs_sync_conn *s; + unsigned size; + int retc; + + p = msg_end; + if (p + sizeof(s->v4) > buffer+buflen) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n"); + return; } - cp = ip_vs_conn_new(¶m, - (union nf_inet_addr *)&s->daddr, - s->dport, flags, dest); - if (dest) - atomic_dec(&dest->refcnt); - if (!cp) { - pr_err("ip_vs_conn_new failed\n"); + s = (union ip_vs_sync_conn *)p; + size = ntohs(s->v4.ver_size) & SVER_MASK; + msg_end = p + size; + /* Basic sanity checks */ + if (msg_end > buffer+buflen) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, msg > buffer\n"); return; } - } else if (!cp->dest) { - dest = ip_vs_try_bind_dest(cp); - if (dest) - atomic_dec(&dest->refcnt); - } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) && - (cp->state != state)) { - /* update active/inactive flag for the connection */ - dest = cp->dest; - if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (state != IP_VS_TCP_S_ESTABLISHED)) { - atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - cp->flags |= IP_VS_CONN_F_INACTIVE; - } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && - (state == IP_VS_TCP_S_ESTABLISHED)) { - atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); - cp->flags &= ~IP_VS_CONN_F_INACTIVE; + if (ntohs(s->v4.ver_size) >> SVER_SHIFT) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, Unknown version %d\n", + ntohs(s->v4.ver_size) >> SVER_SHIFT); + return; } - } else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) && - (cp->state != state)) { - dest = cp->dest; - if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (state != IP_VS_SCTP_S_ESTABLISHED)) { - atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - cp->flags &= ~IP_VS_CONN_F_INACTIVE; + /* Process a single sync_conn */ + retc = ip_vs_proc_sync_conn(net, p, msg_end); + if (retc < 0) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n", + retc); + return; } + /* Make sure we have 32 bit alignment */ + msg_end = p + ((size + 3) & ~3); } - - if (opt) - memcpy(&cp->in_seq, opt, sizeof(*opt)); - atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]); - cp->state = state; - cp->old_state = cp->state; - /* - * We can not recover the right timeout for templates - * in all cases, we can not find the right fwmark - * virtual service. If needed, we can do it for - * non-fwmark persistent services. - */ - if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table) - cp->timeout = pp->timeout_table[state]; - else - cp->timeout = (3*60*HZ); - ip_vs_conn_put(cp); + } else { + /* Old type of message */ + ip_vs_process_message_v0(net, buffer, buflen); + return; } } @@ -511,8 +1181,10 @@ static int set_mcast_if(struct sock *sk, char *ifname) { struct net_device *dev; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); - if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL) + dev = __dev_get_by_name(net, ifname); + if (!dev) return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) @@ -531,30 +1203,33 @@ static int set_mcast_if(struct sock *sk, char *ifname) * Set the maximum length of sync message according to the * specified interface's MTU. */ -static int set_sync_mesg_maxlen(int sync_state) +static int set_sync_mesg_maxlen(struct net *net, int sync_state) { + struct netns_ipvs *ipvs = net_ipvs(net); struct net_device *dev; int num; if (sync_state == IP_VS_STATE_MASTER) { - if ((dev = __dev_get_by_name(&init_net, ip_vs_master_mcast_ifn)) == NULL) + dev = __dev_get_by_name(net, ipvs->master_mcast_ifn); + if (!dev) return -ENODEV; num = (dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr) - SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE; - sync_send_mesg_maxlen = SYNC_MESG_HEADER_LEN + + ipvs->send_mesg_maxlen = SYNC_MESG_HEADER_LEN + SIMPLE_CONN_SIZE * min(num, MAX_CONNS_PER_SYNCBUFF); IP_VS_DBG(7, "setting the maximum length of sync sending " - "message %d.\n", sync_send_mesg_maxlen); + "message %d.\n", ipvs->send_mesg_maxlen); } else if (sync_state == IP_VS_STATE_BACKUP) { - if ((dev = __dev_get_by_name(&init_net, ip_vs_backup_mcast_ifn)) == NULL) + dev = __dev_get_by_name(net, ipvs->backup_mcast_ifn); + if (!dev) return -ENODEV; - sync_recv_mesg_maxlen = dev->mtu - + ipvs->recv_mesg_maxlen = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); IP_VS_DBG(7, "setting the maximum length of sync receiving " - "message %d.\n", sync_recv_mesg_maxlen); + "message %d.\n", ipvs->recv_mesg_maxlen); } return 0; @@ -569,6 +1244,7 @@ static int set_sync_mesg_maxlen(int sync_state) static int join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) { + struct net *net = sock_net(sk); struct ip_mreqn mreq; struct net_device *dev; int ret; @@ -576,7 +1252,8 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); - if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL) + dev = __dev_get_by_name(net, ifname); + if (!dev) return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -593,11 +1270,13 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) static int bind_mcastif_addr(struct socket *sock, char *ifname) { + struct net *net = sock_net(sock->sk); struct net_device *dev; __be32 addr; struct sockaddr_in sin; - if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL) + dev = __dev_get_by_name(net, ifname); + if (!dev) return -ENODEV; addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); @@ -619,19 +1298,20 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname) /* * Set up sending multicast socket over UDP */ -static struct socket * make_send_sock(void) +static struct socket *make_send_sock(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); struct socket *sock; int result; /* First create a socket */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - result = set_mcast_if(sock->sk, ip_vs_master_mcast_ifn); + result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; @@ -640,7 +1320,7 @@ static struct socket * make_send_sock(void) set_mcast_loop(sock->sk, 0); set_mcast_ttl(sock->sk, 1); - result = bind_mcastif_addr(sock, ip_vs_master_mcast_ifn); + result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error binding address of the mcast interface\n"); goto error; @@ -664,13 +1344,14 @@ static struct socket * make_send_sock(void) /* * Set up receiving multicast socket over UDP */ -static struct socket * make_receive_sock(void) +static struct socket *make_receive_sock(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); struct socket *sock; int result; /* First create a socket */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); @@ -689,7 +1370,7 @@ static struct socket * make_receive_sock(void) /* join the multicast group */ result = join_mcast_group(sock->sk, (struct in_addr *) &mcast_addr.sin_addr, - ip_vs_backup_mcast_ifn); + ipvs->backup_mcast_ifn); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; @@ -760,20 +1441,21 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) static int sync_thread_master(void *data) { struct ip_vs_sync_thread_data *tinfo = data; + struct netns_ipvs *ipvs = net_ipvs(tinfo->net); struct ip_vs_sync_buff *sb; pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " "syncid = %d\n", - ip_vs_master_mcast_ifn, ip_vs_master_syncid); + ipvs->master_mcast_ifn, ipvs->master_syncid); while (!kthread_should_stop()) { - while ((sb = sb_dequeue())) { + while ((sb = sb_dequeue(ipvs))) { ip_vs_send_sync_msg(tinfo->sock, sb->mesg); ip_vs_sync_buff_release(sb); } - /* check if entries stay in curr_sb for 2 seconds */ - sb = get_curr_sync_buff(2 * HZ); + /* check if entries stay in ipvs->sync_buff for 2 seconds */ + sb = get_curr_sync_buff(ipvs, 2 * HZ); if (sb) { ip_vs_send_sync_msg(tinfo->sock, sb->mesg); ip_vs_sync_buff_release(sb); @@ -783,14 +1465,13 @@ static int sync_thread_master(void *data) } /* clean up the sync_buff queue */ - while ((sb=sb_dequeue())) { + while ((sb = sb_dequeue(ipvs))) ip_vs_sync_buff_release(sb); - } /* clean up the current sync_buff */ - if ((sb = get_curr_sync_buff(0))) { + sb = get_curr_sync_buff(ipvs, 0); + if (sb) ip_vs_sync_buff_release(sb); - } /* release the sending multicast socket */ sock_release(tinfo->sock); @@ -803,11 +1484,12 @@ static int sync_thread_master(void *data) static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; + struct netns_ipvs *ipvs = net_ipvs(tinfo->net); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " "syncid = %d\n", - ip_vs_backup_mcast_ifn, ip_vs_backup_syncid); + ipvs->backup_mcast_ifn, ipvs->backup_syncid); while (!kthread_should_stop()) { wait_event_interruptible(*sk_sleep(tinfo->sock->sk), @@ -817,7 +1499,7 @@ static int sync_thread_backup(void *data) /* do we have data now? */ while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { len = ip_vs_receive(tinfo->sock, tinfo->buf, - sync_recv_mesg_maxlen); + ipvs->recv_mesg_maxlen); if (len <= 0) { pr_err("receiving message error\n"); break; @@ -826,7 +1508,7 @@ static int sync_thread_backup(void *data) /* disable bottom half, because it accesses the data shared by softirq while getting/creating conns */ local_bh_disable(); - ip_vs_process_message(tinfo->buf, len); + ip_vs_process_message(tinfo->net, tinfo->buf, len); local_bh_enable(); } } @@ -840,41 +1522,42 @@ static int sync_thread_backup(void *data) } -int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) +int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) { struct ip_vs_sync_thread_data *tinfo; struct task_struct **realtask, *task; struct socket *sock; + struct netns_ipvs *ipvs = net_ipvs(net); char *name, *buf = NULL; int (*threadfn)(void *data); int result = -ENOMEM; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", - sizeof(struct ip_vs_sync_conn)); + sizeof(struct ip_vs_sync_conn_v0)); if (state == IP_VS_STATE_MASTER) { - if (sync_master_thread) + if (ipvs->master_thread) return -EEXIST; - strlcpy(ip_vs_master_mcast_ifn, mcast_ifn, - sizeof(ip_vs_master_mcast_ifn)); - ip_vs_master_syncid = syncid; - realtask = &sync_master_thread; - name = "ipvs_syncmaster"; + strlcpy(ipvs->master_mcast_ifn, mcast_ifn, + sizeof(ipvs->master_mcast_ifn)); + ipvs->master_syncid = syncid; + realtask = &ipvs->master_thread; + name = "ipvs_master:%d"; threadfn = sync_thread_master; - sock = make_send_sock(); + sock = make_send_sock(net); } else if (state == IP_VS_STATE_BACKUP) { - if (sync_backup_thread) + if (ipvs->backup_thread) return -EEXIST; - strlcpy(ip_vs_backup_mcast_ifn, mcast_ifn, - sizeof(ip_vs_backup_mcast_ifn)); - ip_vs_backup_syncid = syncid; - realtask = &sync_backup_thread; - name = "ipvs_syncbackup"; + strlcpy(ipvs->backup_mcast_ifn, mcast_ifn, + sizeof(ipvs->backup_mcast_ifn)); + ipvs->backup_syncid = syncid; + realtask = &ipvs->backup_thread; + name = "ipvs_backup:%d"; threadfn = sync_thread_backup; - sock = make_receive_sock(); + sock = make_receive_sock(net); } else { return -EINVAL; } @@ -884,9 +1567,9 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) goto out; } - set_sync_mesg_maxlen(state); + set_sync_mesg_maxlen(net, state); if (state == IP_VS_STATE_BACKUP) { - buf = kmalloc(sync_recv_mesg_maxlen, GFP_KERNEL); + buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL); if (!buf) goto outsocket; } @@ -895,10 +1578,11 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) if (!tinfo) goto outbuf; + tinfo->net = net; tinfo->sock = sock; tinfo->buf = buf; - task = kthread_run(threadfn, tinfo, name); + task = kthread_run(threadfn, tinfo, name, ipvs->gen); if (IS_ERR(task)) { result = PTR_ERR(task); goto outtinfo; @@ -906,7 +1590,7 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) /* mark as active */ *realtask = task; - ip_vs_sync_state |= state; + ipvs->sync_state |= state; /* increase the module use count */ ip_vs_use_count_inc(); @@ -924,16 +1608,18 @@ out: } -int stop_sync_thread(int state) +int stop_sync_thread(struct net *net, int state) { + struct netns_ipvs *ipvs = net_ipvs(net); + IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); if (state == IP_VS_STATE_MASTER) { - if (!sync_master_thread) + if (!ipvs->master_thread) return -ESRCH; pr_info("stopping master sync thread %d ...\n", - task_pid_nr(sync_master_thread)); + task_pid_nr(ipvs->master_thread)); /* * The lock synchronizes with sb_queue_tail(), so that we don't @@ -941,21 +1627,21 @@ int stop_sync_thread(int state) * progress of stopping the master sync daemon. */ - spin_lock_bh(&ip_vs_sync_lock); - ip_vs_sync_state &= ~IP_VS_STATE_MASTER; - spin_unlock_bh(&ip_vs_sync_lock); - kthread_stop(sync_master_thread); - sync_master_thread = NULL; + spin_lock_bh(&ipvs->sync_lock); + ipvs->sync_state &= ~IP_VS_STATE_MASTER; + spin_unlock_bh(&ipvs->sync_lock); + kthread_stop(ipvs->master_thread); + ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { - if (!sync_backup_thread) + if (!ipvs->backup_thread) return -ESRCH; pr_info("stopping backup sync thread %d ...\n", - task_pid_nr(sync_backup_thread)); + task_pid_nr(ipvs->backup_thread)); - ip_vs_sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(sync_backup_thread); - sync_backup_thread = NULL; + ipvs->sync_state &= ~IP_VS_STATE_BACKUP; + kthread_stop(ipvs->backup_thread); + ipvs->backup_thread = NULL; } else { return -EINVAL; } @@ -965,3 +1651,42 @@ int stop_sync_thread(int state) return 0; } + +/* + * Initialize data struct for each netns + */ +static int __net_init __ip_vs_sync_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + INIT_LIST_HEAD(&ipvs->sync_queue); + spin_lock_init(&ipvs->sync_lock); + spin_lock_init(&ipvs->sync_buff_lock); + + ipvs->sync_mcast_addr.sin_family = AF_INET; + ipvs->sync_mcast_addr.sin_port = cpu_to_be16(IP_VS_SYNC_PORT); + ipvs->sync_mcast_addr.sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP); + return 0; +} + +static void __ip_vs_sync_cleanup(struct net *net) +{ + stop_sync_thread(net, IP_VS_STATE_MASTER); + stop_sync_thread(net, IP_VS_STATE_BACKUP); +} + +static struct pernet_operations ipvs_sync_ops = { + .init = __ip_vs_sync_init, + .exit = __ip_vs_sync_cleanup, +}; + + +int __init ip_vs_sync_init(void) +{ + return register_pernet_subsys(&ipvs_sync_ops); +} + +void ip_vs_sync_cleanup(void) +{ + unregister_pernet_subsys(&ipvs_sync_ops); +} diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 5325a3fb..1f2a4e3 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -175,7 +175,6 @@ __ip_vs_reroute_locally(struct sk_buff *skb) .fl4_tos = RT_TOS(iph->tos), .mark = skb->mark, }; - struct rtable *rt; if (ip_route_output_key(net, &rt, &fl)) return 0; @@ -390,7 +389,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { + if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) && + !skb_is_gso(skb)) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); @@ -443,7 +443,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -543,7 +543,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { + if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) && + !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for"); @@ -658,7 +659,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -773,8 +774,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, df |= (old_iph->frag_off & htons(IP_DF)); - if ((old_iph->frag_off & htons(IP_DF)) - && mtu < ntohs(old_iph->tot_len)) { + if ((old_iph->frag_off & htons(IP_DF) && + mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; @@ -886,7 +887,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); - if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { + if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && + !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -991,7 +993,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) { + if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu && + !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); IP_VS_DBG_RL("%s(): frag needed\n", __func__); @@ -1158,7 +1161,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) { + if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) && + !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; @@ -1272,7 +1276,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c new file mode 100644 index 0000000..4e99cca --- /dev/null +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -0,0 +1,82 @@ +/* + * broadcast connection tracking helper + * + * (c) 2005 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/ip.h> +#include <net/route.h> +#include <linux/inetdevice.h> +#include <linux/skbuff.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> + +int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout) +{ + struct nf_conntrack_expect *exp; + struct iphdr *iph = ip_hdr(skb); + struct rtable *rt = skb_rtable(skb); + struct in_device *in_dev; + struct nf_conn_help *help = nfct_help(ct); + __be32 mask = 0; + + /* we're only interested in locally generated packets */ + if (skb->sk == NULL) + goto out; + if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) + goto out; + if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) + goto out; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(rt->dst.dev); + if (in_dev != NULL) { + for_primary_ifa(in_dev) { + if (ifa->ifa_broadcast == iph->daddr) { + mask = ifa->ifa_mask; + break; + } + } endfor_ifa(in_dev); + } + rcu_read_unlock(); + + if (mask == 0) + goto out; + + exp = nf_ct_expect_alloc(ct); + if (exp == NULL) + goto out; + + exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; + exp->tuple.src.u.udp.port = help->helper->tuple.src.u.udp.port; + + exp->mask.src.u3.ip = mask; + exp->mask.src.u.udp.port = htons(0xFFFF); + + exp->expectfn = NULL; + exp->flags = NF_CT_EXPECT_PERMANENT; + exp->class = NF_CT_EXPECT_CLASS_DEFAULT; + exp->helper = NULL; + + nf_ct_expect_related(exp); + nf_ct_expect_put(exp); + + nf_ct_refresh(ct, skb, timeout * HZ); +out: + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help); + +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 84f4fcc..2f454ef 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -43,6 +43,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -282,6 +283,11 @@ EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list); static void death_by_timeout(unsigned long ul_conntrack) { struct nf_conn *ct = (void *)ul_conntrack; + struct nf_conn_tstamp *tstamp; + + tstamp = nf_conn_tstamp_find(ct); + if (tstamp && tstamp->stop == 0) + tstamp->stop = ktime_to_ns(ktime_get_real()); if (!test_bit(IPS_DYING_BIT, &ct->status) && unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { @@ -419,6 +425,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; + struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -486,8 +493,16 @@ __nf_conntrack_confirm(struct sk_buff *skb) ct->timeout.expires += jiffies; add_timer(&ct->timeout); atomic_inc(&ct->ct_general.use); - set_bit(IPS_CONFIRMED_BIT, &ct->status); + ct->status |= IPS_CONFIRMED; + + /* set conntrack timestamp, if enabled. */ + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) { + if (skb->tstamp.tv64 == 0) + __net_timestamp((struct sk_buff *)skb); + tstamp->start = ktime_to_ns(skb->tstamp); + } /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers * guarantee that no other CPU can find the conntrack before the above @@ -655,7 +670,8 @@ __nf_conntrack_alloc(struct net *net, u16 zone, * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged. */ memset(&ct->tuplehash[IP_CT_DIR_MAX], 0, - sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); + offsetof(struct nf_conn, proto) - + offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); spin_lock_init(&ct->lock); ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; @@ -745,6 +761,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); + nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, @@ -1192,6 +1209,11 @@ struct __nf_ct_flush_report { static int kill_report(struct nf_conn *i, void *data) { struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data; + struct nf_conn_tstamp *tstamp; + + tstamp = nf_conn_tstamp_find(i); + if (tstamp && tstamp->stop == 0) + tstamp->stop = ktime_to_ns(ktime_get_real()); /* If we fail to deliver the event, death_by_timeout() will retry */ if (nf_conntrack_event_report(IPCT_DESTROY, i, @@ -1208,9 +1230,9 @@ static int kill_all(struct nf_conn *i, void *data) return 1; } -void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size) +void nf_ct_free_hashtable(void *hash, unsigned int size) { - if (vmalloced) + if (is_vmalloc_addr(hash)) vfree(hash); else free_pages((unsigned long)hash, @@ -1277,8 +1299,7 @@ static void nf_conntrack_cleanup_net(struct net *net) goto i_see_dead_people; } - nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - net->ct.htable_size); + nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); nf_conntrack_ecache_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); @@ -1307,21 +1328,18 @@ void nf_conntrack_cleanup(struct net *net) } } -void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls) +void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; unsigned int nr_slots, i; size_t sz; - *vmalloced = 0; - BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); if (!hash) { - *vmalloced = 1; printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); hash = __vmalloc(sz, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); @@ -1337,7 +1355,7 @@ EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable); int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) { - int i, bucket, vmalloced, old_vmalloced; + int i, bucket; unsigned int hashsize, old_size; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; @@ -1354,7 +1372,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hashsize) return -EINVAL; - hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1); + hash = nf_ct_alloc_hashtable(&hashsize, 1); if (!hash) return -ENOMEM; @@ -1376,15 +1394,13 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) } } old_size = init_net.ct.htable_size; - old_vmalloced = init_net.ct.hash_vmalloc; old_hash = init_net.ct.hash; init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; - init_net.ct.hash_vmalloc = vmalloced; init_net.ct.hash = hash; spin_unlock_bh(&nf_conntrack_lock); - nf_ct_free_hashtable(old_hash, old_vmalloced, old_size); + nf_ct_free_hashtable(old_hash, old_size); return 0; } EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); @@ -1497,8 +1513,7 @@ static int nf_conntrack_init_net(struct net *net) } net->ct.htable_size = nf_conntrack_htable_size; - net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, - &net->ct.hash_vmalloc, 1); + net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1); if (!net->ct.hash) { ret = -ENOMEM; printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); @@ -1510,6 +1525,9 @@ static int nf_conntrack_init_net(struct net *net) ret = nf_conntrack_acct_init(net); if (ret < 0) goto err_acct; + ret = nf_conntrack_tstamp_init(net); + if (ret < 0) + goto err_tstamp; ret = nf_conntrack_ecache_init(net); if (ret < 0) goto err_ecache; @@ -1517,12 +1535,13 @@ static int nf_conntrack_init_net(struct net *net) return 0; err_ecache: + nf_conntrack_tstamp_fini(net); +err_tstamp: nf_conntrack_acct_fini(net); err_acct: nf_conntrack_expect_fini(net); err_expect: - nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - net->ct.htable_size); + nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); err_hash: kmem_cache_destroy(net->ct.nf_conntrack_cachep); err_cache: diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index a20fb0b..cd1e8e0 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -319,7 +319,8 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) const struct nf_conntrack_expect_policy *p; unsigned int h = nf_ct_expect_dst_hash(&exp->tuple); - atomic_inc(&exp->use); + /* two references : one for hash insert, one for the timer */ + atomic_add(2, &exp->use); if (master_help) { hlist_add_head(&exp->lnode, &master_help->expectations); @@ -333,12 +334,14 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) setup_timer(&exp->timeout, nf_ct_expectation_timed_out, (unsigned long)exp); if (master_help) { - p = &master_help->helper->expect_policy[exp->class]; + p = &rcu_dereference_protected( + master_help->helper, + lockdep_is_held(&nf_conntrack_lock) + )->expect_policy[exp->class]; exp->timeout.expires = jiffies + p->timeout * HZ; } add_timer(&exp->timeout); - atomic_inc(&exp->use); NF_CT_STAT_INC(net, expect_create); } @@ -369,7 +372,10 @@ static inline int refresh_timer(struct nf_conntrack_expect *i) if (!del_timer(&i->timeout)) return 0; - p = &master_help->helper->expect_policy[i->class]; + p = &rcu_dereference_protected( + master_help->helper, + lockdep_is_held(&nf_conntrack_lock) + )->expect_policy[i->class]; i->timeout.expires = jiffies + p->timeout * HZ; add_timer(&i->timeout); return 1; @@ -407,7 +413,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } /* Will be over limit? */ if (master_help) { - p = &master_help->helper->expect_policy[expect->class]; + p = &rcu_dereference_protected( + master_help->helper, + lockdep_is_held(&nf_conntrack_lock) + )->expect_policy[expect->class]; if (p->max_expected && master_help->expecting[expect->class] >= p->max_expected) { evict_oldest_expect(master, expect); @@ -478,7 +487,7 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq) struct hlist_node *n; for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) { - n = rcu_dereference(net->ct.expect_hash[st->bucket].first); + n = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket])); if (n) return n; } @@ -491,11 +500,11 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_expect_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_next_rcu(head)); while (head == NULL) { if (++st->bucket >= nf_ct_expect_hsize) return NULL; - head = rcu_dereference(net->ct.expect_hash[st->bucket].first); + head = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket])); } return head; } @@ -630,8 +639,7 @@ int nf_conntrack_expect_init(struct net *net) } net->ct.expect_count = 0; - net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, - &net->ct.expect_vmalloc, 0); + net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0); if (net->ct.expect_hash == NULL) goto err1; @@ -653,8 +661,7 @@ err3: if (net_eq(net, &init_net)) kmem_cache_destroy(nf_ct_expect_cachep); err2: - nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, - nf_ct_expect_hsize); + nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); err1: return err; } @@ -666,6 +673,5 @@ void nf_conntrack_expect_fini(struct net *net) rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); } - nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, - nf_ct_expect_hsize); + nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index bd82450..80a23ed 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -140,15 +140,16 @@ static void update_alloc_size(struct nf_ct_ext_type *type) /* This assumes that extended areas in conntrack for the types whose NF_CT_EXT_F_PREALLOC bit set are allocated in order */ for (i = min; i <= max; i++) { - t1 = nf_ct_ext_types[i]; + t1 = rcu_dereference_protected(nf_ct_ext_types[i], + lockdep_is_held(&nf_ct_ext_type_mutex)); if (!t1) continue; - t1->alloc_size = sizeof(struct nf_ct_ext) - + ALIGN(sizeof(struct nf_ct_ext), t1->align) - + t1->len; + t1->alloc_size = ALIGN(sizeof(struct nf_ct_ext), t1->align) + + t1->len; for (j = 0; j < NF_CT_EXT_NUM; j++) { - t2 = nf_ct_ext_types[j]; + t2 = rcu_dereference_protected(nf_ct_ext_types[j], + lockdep_is_held(&nf_ct_ext_type_mutex)); if (t2 == NULL || t2 == t1 || (t2->flags & NF_CT_EXT_F_PREALLOC) == 0) continue; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 59e1a4c..1bdfea3 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -33,7 +33,6 @@ static DEFINE_MUTEX(nf_ct_helper_mutex); static struct hlist_head *nf_ct_helper_hash __read_mostly; static unsigned int nf_ct_helper_hsize __read_mostly; static unsigned int nf_ct_helper_count __read_mostly; -static int nf_ct_helper_vmalloc; /* Stupid hash, but collision free for the default registrations of the @@ -158,7 +157,10 @@ static inline int unhelp(struct nf_conntrack_tuple_hash *i, struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); - if (help && help->helper == me) { + if (help && rcu_dereference_protected( + help->helper, + lockdep_is_held(&nf_conntrack_lock) + ) == me) { nf_conntrack_event(IPCT_HELPER, ct); rcu_assign_pointer(help->helper, NULL); } @@ -210,7 +212,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, hlist_for_each_entry_safe(exp, n, next, &net->ct.expect_hash[i], hnode) { struct nf_conn_help *help = nfct_help(exp->master); - if ((help->helper == me || exp->helper == me) && + if ((rcu_dereference_protected( + help->helper, + lockdep_is_held(&nf_conntrack_lock) + ) == me || exp->helper == me) && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); @@ -261,8 +266,7 @@ int nf_conntrack_helper_init(void) int err; nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ - nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, - &nf_ct_helper_vmalloc, 0); + nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); if (!nf_ct_helper_hash) return -ENOMEM; @@ -273,14 +277,12 @@ int nf_conntrack_helper_init(void) return 0; err1: - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc, - nf_ct_helper_hsize); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); return err; } void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc, - nf_ct_helper_hsize); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); } diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index aadde01..4c8f30a 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -18,14 +18,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/if_addr.h> #include <linux/in.h> -#include <linux/ip.h> -#include <linux/netfilter.h> -#include <net/route.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> @@ -40,75 +33,26 @@ MODULE_ALIAS("ip_conntrack_netbios_ns"); MODULE_ALIAS_NFCT_HELPER("netbios_ns"); static unsigned int timeout __read_mostly = 3; -module_param(timeout, uint, 0400); +module_param(timeout, uint, S_IRUSR); MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds"); -static int help(struct sk_buff *skb, unsigned int protoff, - struct nf_conn *ct, enum ip_conntrack_info ctinfo) -{ - struct nf_conntrack_expect *exp; - struct iphdr *iph = ip_hdr(skb); - struct rtable *rt = skb_rtable(skb); - struct in_device *in_dev; - __be32 mask = 0; - - /* we're only interested in locally generated packets */ - if (skb->sk == NULL) - goto out; - if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) - goto out; - if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) - goto out; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(rt->dst.dev); - if (in_dev != NULL) { - for_primary_ifa(in_dev) { - if (ifa->ifa_broadcast == iph->daddr) { - mask = ifa->ifa_mask; - break; - } - } endfor_ifa(in_dev); - } - rcu_read_unlock(); - - if (mask == 0) - goto out; - - exp = nf_ct_expect_alloc(ct); - if (exp == NULL) - goto out; - - exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - exp->tuple.src.u.udp.port = htons(NMBD_PORT); - - exp->mask.src.u3.ip = mask; - exp->mask.src.u.udp.port = htons(0xFFFF); - - exp->expectfn = NULL; - exp->flags = NF_CT_EXPECT_PERMANENT; - exp->class = NF_CT_EXPECT_CLASS_DEFAULT; - exp->helper = NULL; - - nf_ct_expect_related(exp); - nf_ct_expect_put(exp); - - nf_ct_refresh(ct, skb, timeout * HZ); -out: - return NF_ACCEPT; -} - static struct nf_conntrack_expect_policy exp_policy = { .max_expected = 1, }; +static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + return nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout); +} + static struct nf_conntrack_helper helper __read_mostly = { .name = "netbios-ns", - .tuple.src.l3num = AF_INET, + .tuple.src.l3num = NFPROTO_IPV4, .tuple.src.u.udp.port = cpu_to_be16(NMBD_PORT), .tuple.dst.protonum = IPPROTO_UDP, .me = THIS_MODULE, - .help = help, + .help = netbios_ns_help, .expect_policy = &exp_policy, }; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index eead9db..30bf8a1 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -42,6 +42,7 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_protocol.h> @@ -230,6 +231,33 @@ nla_put_failure: return -1; } +static int +ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nlattr *nest_count; + const struct nf_conn_tstamp *tstamp; + + tstamp = nf_conn_tstamp_find(ct); + if (!tstamp) + return 0; + + nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED); + if (!nest_count) + goto nla_put_failure; + + NLA_PUT_BE64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start)); + if (tstamp->stop != 0) { + NLA_PUT_BE64(skb, CTA_TIMESTAMP_STOP, + cpu_to_be64(tstamp->stop)); + } + nla_nest_end(skb, nest_count); + + return 0; + +nla_put_failure: + return -1; +} + #ifdef CONFIG_NF_CONNTRACK_MARK static inline int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) @@ -404,6 +432,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, ctnetlink_dump_timeout(skb, ct) < 0 || ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 || + ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_protoinfo(skb, ct) < 0 || ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct) < 0 || @@ -471,6 +500,18 @@ ctnetlink_secctx_size(const struct nf_conn *ct) } static inline size_t +ctnetlink_timestamp_size(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) + return 0; + return nla_total_size(0) + 2 * nla_total_size(sizeof(uint64_t)); +#else + return 0; +#endif +} + +static inline size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) { return NLMSG_ALIGN(sizeof(struct nfgenmsg)) @@ -481,6 +522,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + ctnetlink_counters_size(ct) + + ctnetlink_timestamp_size(ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ @@ -571,7 +613,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || - ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0) + ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 || + ctnetlink_dump_timestamp(skb, ct) < 0) goto nla_put_failure; } else { if (ctnetlink_dump_timeout(skb, ct) < 0) @@ -761,7 +804,7 @@ static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, - enum ctattr_tuple type, u_int8_t l3num) + enum ctattr_type type, u_int8_t l3num) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; @@ -1358,6 +1401,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); + nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; @@ -1376,6 +1420,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } #endif + memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index dc7bb74..5701c8d 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -166,6 +166,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct nf_conntrack_l3proto *l3proto int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; + struct nf_conntrack_l3proto *old; if (proto->l3proto >= AF_MAX) return -EBUSY; @@ -174,7 +175,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) return -EINVAL; mutex_lock(&nf_ct_proto_mutex); - if (nf_ct_l3protos[proto->l3proto] != &nf_conntrack_l3proto_generic) { + old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], + lockdep_is_held(&nf_ct_proto_mutex)); + if (old != &nf_conntrack_l3proto_generic) { ret = -EBUSY; goto out_unlock; } @@ -201,7 +204,9 @@ void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) BUG_ON(proto->l3proto >= AF_MAX); mutex_lock(&nf_ct_proto_mutex); - BUG_ON(nf_ct_l3protos[proto->l3proto] != proto); + BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], + lockdep_is_held(&nf_ct_proto_mutex) + ) != proto); rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], &nf_conntrack_l3proto_generic); nf_ct_l3proto_unregister_sysctl(proto); @@ -279,7 +284,7 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) mutex_lock(&nf_ct_proto_mutex); if (!nf_ct_protos[l4proto->l3proto]) { /* l3proto may be loaded latter. */ - struct nf_conntrack_l4proto **proto_array; + struct nf_conntrack_l4proto __rcu **proto_array; int i; proto_array = kmalloc(MAX_NF_CT_PROTO * @@ -291,7 +296,7 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) } for (i = 0; i < MAX_NF_CT_PROTO; i++) - proto_array[i] = &nf_conntrack_l4proto_generic; + RCU_INIT_POINTER(proto_array[i], &nf_conntrack_l4proto_generic); /* Before making proto_array visible to lockless readers, * we must make sure its content is committed to memory. @@ -299,8 +304,10 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) smp_wmb(); nf_ct_protos[l4proto->l3proto] = proto_array; - } else if (nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != - &nf_conntrack_l4proto_generic) { + } else if (rcu_dereference_protected( + nf_ct_protos[l4proto->l3proto][l4proto->l4proto], + lockdep_is_held(&nf_ct_proto_mutex) + ) != &nf_conntrack_l4proto_generic) { ret = -EBUSY; goto out_unlock; } @@ -331,7 +338,10 @@ void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) BUG_ON(l4proto->l3proto >= PF_MAX); mutex_lock(&nf_ct_proto_mutex); - BUG_ON(nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != l4proto); + BUG_ON(rcu_dereference_protected( + nf_ct_protos[l4proto->l3proto][l4proto->l4proto], + lockdep_is_held(&nf_ct_proto_mutex) + ) != l4proto); rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], &nf_conntrack_l4proto_generic); nf_ct_l4proto_unregister_sysctl(l4proto); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 5292560..9ae57c5 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -452,6 +452,9 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.state = CT_DCCP_NONE; + ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST; + ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL; + ct->proto.dccp.handshake_seq = 0; return true; out_invalid: diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c6049c2..6f4ee70 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -413,6 +413,7 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, test_bit(SCTP_CID_COOKIE_ACK, map)) return false; + memset(&ct->proto.sctp, 0, sizeof(ct->proto.sctp)); new_state = SCTP_CONNTRACK_MAX; for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Don't need lock here: this conntrack not in circulation yet */ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3fb2b73..6f38d0e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1066,9 +1066,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, BUG_ON(th == NULL); /* Don't need lock here: this conntrack not in circulation yet */ - new_state - = tcp_conntracks[0][get_conntrack_index(th)] - [TCP_CONNTRACK_NONE]; + new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE]; /* Invalid: delete conntrack */ if (new_state >= TCP_CONNTRACK_MAX) { @@ -1077,6 +1075,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, } if (new_state == TCP_CONNTRACK_SYN_SENT) { + memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* SYN packet */ ct->proto.tcp.seen[0].td_end = segment_seq_plus_len(ntohl(th->seq), skb->len, @@ -1088,11 +1087,11 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[0].td_end; tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]); - ct->proto.tcp.seen[1].flags = 0; } else if (nf_ct_tcp_loose == 0) { /* Don't try to pick up connections. */ return false; } else { + memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* * We are in the middle of a connection, * its history is lost for us. @@ -1107,7 +1106,6 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[0].td_maxend = ct->proto.tcp.seen[0].td_end + ct->proto.tcp.seen[0].td_maxwin; - ct->proto.tcp.seen[0].td_scale = 0; /* We assume SACK and liberal window checking to handle * window scaling */ @@ -1116,13 +1114,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, IP_CT_TCP_FLAG_BE_LIBERAL; } - ct->proto.tcp.seen[1].td_end = 0; - ct->proto.tcp.seen[1].td_maxend = 0; - ct->proto.tcp.seen[1].td_maxwin = 0; - ct->proto.tcp.seen[1].td_scale = 0; - /* tcp_packet will set them */ - ct->proto.tcp.state = TCP_CONNTRACK_NONE; ct->proto.tcp.last_index = TCP_NONE_SET; pr_debug("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i " diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c new file mode 100644 index 0000000..6e545e2 --- /dev/null +++ b/net/netfilter/nf_conntrack_snmp.c @@ -0,0 +1,77 @@ +/* + * SNMP service broadcast connection tracking helper + * + * (c) 2011 Jiri Olsa <jolsa@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/in.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> + +#define SNMP_PORT 161 + +MODULE_AUTHOR("Jiri Olsa <jolsa@redhat.com>"); +MODULE_DESCRIPTION("SNMP service broadcast connection tracking helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFCT_HELPER("snmp"); + +static unsigned int timeout __read_mostly = 30; +module_param(timeout, uint, S_IRUSR); +MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds"); + +int (*nf_nat_snmp_hook)(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo); +EXPORT_SYMBOL_GPL(nf_nat_snmp_hook); + +static int snmp_conntrack_help(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + typeof(nf_nat_snmp_hook) nf_nat_snmp; + + nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout); + + nf_nat_snmp = rcu_dereference(nf_nat_snmp_hook); + if (nf_nat_snmp && ct->status & IPS_NAT_MASK) + return nf_nat_snmp(skb, protoff, ct, ctinfo); + + return NF_ACCEPT; +} + +static struct nf_conntrack_expect_policy exp_policy = { + .max_expected = 1, +}; + +static struct nf_conntrack_helper helper __read_mostly = { + .name = "snmp", + .tuple.src.l3num = NFPROTO_IPV4, + .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT), + .tuple.dst.protonum = IPPROTO_UDP, + .me = THIS_MODULE, + .help = snmp_conntrack_help, + .expect_policy = &exp_policy, +}; + +static int __init nf_conntrack_snmp_init(void) +{ + exp_policy.timeout = timeout; + return nf_conntrack_helper_register(&helper); +} + +static void __exit nf_conntrack_snmp_fini(void) +{ + nf_conntrack_helper_unregister(&helper); +} + +module_init(nf_conntrack_snmp_init); +module_exit(nf_conntrack_snmp_fini); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index b4d7f0f..0ae1428 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -29,6 +29,8 @@ #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> +#include <linux/rculist_nulls.h> MODULE_LICENSE("GPL"); @@ -45,6 +47,7 @@ EXPORT_SYMBOL_GPL(print_tuple); struct ct_iter_state { struct seq_net_private p; unsigned int bucket; + u_int64_t time_now; }; static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) @@ -56,7 +59,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) for (st->bucket = 0; st->bucket < net->ct.htable_size; st->bucket++) { - n = rcu_dereference(net->ct.hash[st->bucket].first); + n = rcu_dereference(hlist_nulls_first_rcu(&net->ct.hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -69,13 +72,15 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { if (++st->bucket >= net->ct.htable_size) return NULL; } - head = rcu_dereference(net->ct.hash[st->bucket].first); + head = rcu_dereference( + hlist_nulls_first_rcu( + &net->ct.hash[st->bucket])); } return head; } @@ -93,6 +98,9 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) static void *ct_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { + struct ct_iter_state *st = seq->private; + + st->time_now = ktime_to_ns(ktime_get_real()); rcu_read_lock(); return ct_get_idx(seq, *pos); } @@ -132,6 +140,34 @@ static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) } #endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) +{ + struct ct_iter_state *st = s->private; + struct nf_conn_tstamp *tstamp; + s64 delta_time; + + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) { + delta_time = st->time_now - tstamp->start; + if (delta_time > 0) + delta_time = div_s64(delta_time, NSEC_PER_SEC); + else + delta_time = 0; + + return seq_printf(s, "delta-time=%llu ", + (unsigned long long)delta_time); + } + return 0; +} +#else +static inline int +ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) +{ + return 0; +} +#endif + /* return 0 on success, 1 in case of error */ static int ct_seq_show(struct seq_file *s, void *v) { @@ -200,6 +236,9 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #endif + if (ct_show_delta_time(s, ct)) + goto release; + if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) goto release; diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c new file mode 100644 index 0000000..af7dd31 --- /dev/null +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -0,0 +1,120 @@ +/* + * (C) 2010 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation (or any later at your option). + */ + +#include <linux/netfilter.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/moduleparam.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_timestamp.h> + +static int nf_ct_tstamp __read_mostly; + +module_param_named(tstamp, nf_ct_tstamp, bool, 0644); +MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping."); + +#ifdef CONFIG_SYSCTL +static struct ctl_table tstamp_sysctl_table[] = { + { + .procname = "nf_conntrack_timestamp", + .data = &init_net.ct.sysctl_tstamp, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; +#endif /* CONFIG_SYSCTL */ + +static struct nf_ct_ext_type tstamp_extend __read_mostly = { + .len = sizeof(struct nf_conn_tstamp), + .align = __alignof__(struct nf_conn_tstamp), + .id = NF_CT_EXT_TSTAMP, +}; + +#ifdef CONFIG_SYSCTL +static int nf_conntrack_tstamp_init_sysctl(struct net *net) +{ + struct ctl_table *table; + + table = kmemdup(tstamp_sysctl_table, sizeof(tstamp_sysctl_table), + GFP_KERNEL); + if (!table) + goto out; + + table[0].data = &net->ct.sysctl_tstamp; + + net->ct.tstamp_sysctl_header = register_net_sysctl_table(net, + nf_net_netfilter_sysctl_path, table); + if (!net->ct.tstamp_sysctl_header) { + printk(KERN_ERR "nf_ct_tstamp: can't register to sysctl.\n"); + goto out_register; + } + return 0; + +out_register: + kfree(table); +out: + return -ENOMEM; +} + +static void nf_conntrack_tstamp_fini_sysctl(struct net *net) +{ + struct ctl_table *table; + + table = net->ct.tstamp_sysctl_header->ctl_table_arg; + unregister_net_sysctl_table(net->ct.tstamp_sysctl_header); + kfree(table); +} +#else +static int nf_conntrack_tstamp_init_sysctl(struct net *net) +{ + return 0; +} + +static void nf_conntrack_tstamp_fini_sysctl(struct net *net) +{ +} +#endif + +int nf_conntrack_tstamp_init(struct net *net) +{ + int ret; + + net->ct.sysctl_tstamp = nf_ct_tstamp; + + if (net_eq(net, &init_net)) { + ret = nf_ct_extend_register(&tstamp_extend); + if (ret < 0) { + printk(KERN_ERR "nf_ct_tstamp: Unable to register " + "extension\n"); + goto out_extend_register; + } + } + + ret = nf_conntrack_tstamp_init_sysctl(net); + if (ret < 0) + goto out_sysctl; + + return 0; + +out_sysctl: + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&tstamp_extend); +out_extend_register: + return ret; +} + +void nf_conntrack_tstamp_fini(struct net *net) +{ + nf_conntrack_tstamp_fini_sysctl(net); + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&tstamp_extend); +} diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index b07393e..20c775c 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -161,7 +161,8 @@ static int seq_show(struct seq_file *s, void *v) struct nf_logger *t; int ret; - logger = nf_loggers[*pos]; + logger = rcu_dereference_protected(nf_loggers[*pos], + lockdep_is_held(&nf_log_mutex)); if (!logger) ret = seq_printf(s, "%2lld NONE (", *pos); @@ -249,7 +250,8 @@ static int nf_log_proc_dostring(ctl_table *table, int write, mutex_unlock(&nf_log_mutex); } else { mutex_lock(&nf_log_mutex); - logger = nf_loggers[tindex]; + logger = rcu_dereference_protected(nf_loggers[tindex], + lockdep_is_held(&nf_log_mutex)); if (!logger) table->data = "NONE"; else diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 74aebed..5ab22e2 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -27,14 +27,17 @@ static DEFINE_MUTEX(queue_handler_mutex); int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) { int ret; + const struct nf_queue_handler *old; if (pf >= ARRAY_SIZE(queue_handler)) return -EINVAL; mutex_lock(&queue_handler_mutex); - if (queue_handler[pf] == qh) + old = rcu_dereference_protected(queue_handler[pf], + lockdep_is_held(&queue_handler_mutex)); + if (old == qh) ret = -EEXIST; - else if (queue_handler[pf]) + else if (old) ret = -EBUSY; else { rcu_assign_pointer(queue_handler[pf], qh); @@ -49,11 +52,15 @@ EXPORT_SYMBOL(nf_register_queue_handler); /* The caller must flush their queue before this */ int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) { + const struct nf_queue_handler *old; + if (pf >= ARRAY_SIZE(queue_handler)) return -EINVAL; mutex_lock(&queue_handler_mutex); - if (queue_handler[pf] && queue_handler[pf] != qh) { + old = rcu_dereference_protected(queue_handler[pf], + lockdep_is_held(&queue_handler_mutex)); + if (old && old != qh) { mutex_unlock(&queue_handler_mutex); return -EINVAL; } @@ -73,7 +80,10 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh) mutex_lock(&queue_handler_mutex); for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++) { - if (queue_handler[pf] == qh) + if (rcu_dereference_protected( + queue_handler[pf], + lockdep_is_held(&queue_handler_mutex) + ) == qh) rcu_assign_pointer(queue_handler[pf], NULL); } mutex_unlock(&queue_handler_mutex); @@ -115,7 +125,7 @@ static int __nf_queue(struct sk_buff *skb, int (*okfn)(struct sk_buff *), unsigned int queuenum) { - int status; + int status = -ENOENT; struct nf_queue_entry *entry = NULL; #ifdef CONFIG_BRIDGE_NETFILTER struct net_device *physindev; @@ -128,16 +138,20 @@ static int __nf_queue(struct sk_buff *skb, rcu_read_lock(); qh = rcu_dereference(queue_handler[pf]); - if (!qh) + if (!qh) { + status = -ESRCH; goto err_unlock; + } afinfo = nf_get_afinfo(pf); if (!afinfo) goto err_unlock; entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC); - if (!entry) + if (!entry) { + status = -ENOMEM; goto err_unlock; + } *entry = (struct nf_queue_entry) { .skb = skb, @@ -151,11 +165,9 @@ static int __nf_queue(struct sk_buff *skb, /* If it's going away, ignore hook. */ if (!try_module_get(entry->elem->owner)) { - rcu_read_unlock(); - kfree(entry); - return 0; + status = -ECANCELED; + goto err_unlock; } - /* Bump dev refs so they don't vanish while packet is out */ if (indev) dev_hold(indev); @@ -182,14 +194,13 @@ static int __nf_queue(struct sk_buff *skb, goto err; } - return 1; + return 0; err_unlock: rcu_read_unlock(); err: - kfree_skb(skb); kfree(entry); - return 1; + return status; } int nf_queue(struct sk_buff *skb, @@ -201,6 +212,8 @@ int nf_queue(struct sk_buff *skb, unsigned int queuenum) { struct sk_buff *segs; + int err; + unsigned int queued; if (!skb_is_gso(skb)) return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn, @@ -216,20 +229,35 @@ int nf_queue(struct sk_buff *skb, } segs = skb_gso_segment(skb, 0); - kfree_skb(skb); + /* Does not use PTR_ERR to limit the number of error codes that can be + * returned by nf_queue. For instance, callers rely on -ECANCELED to mean + * 'ignore this hook'. + */ if (IS_ERR(segs)) - return 1; + return -EINVAL; + queued = 0; + err = 0; do { struct sk_buff *nskb = segs->next; segs->next = NULL; - if (!__nf_queue(segs, elem, pf, hook, indev, outdev, okfn, - queuenum)) + if (err == 0) + err = __nf_queue(segs, elem, pf, hook, indev, + outdev, okfn, queuenum); + if (err == 0) + queued++; + else kfree_skb(segs); segs = nskb; } while (segs); - return 1; + + /* also free orig skb if only some segments were queued */ + if (unlikely(err && queued)) + err = 0; + if (err == 0) + kfree_skb(skb); + return err; } void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) @@ -237,6 +265,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) struct sk_buff *skb = entry->skb; struct list_head *elem = &entry->elem->list; const struct nf_afinfo *afinfo; + int err; rcu_read_lock(); @@ -270,10 +299,17 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) local_bh_enable(); break; case NF_QUEUE: - if (!__nf_queue(skb, elem, entry->pf, entry->hook, - entry->indev, entry->outdev, entry->okfn, - verdict >> NF_VERDICT_BITS)) - goto next_hook; + err = __nf_queue(skb, elem, entry->pf, entry->hook, + entry->indev, entry->outdev, entry->okfn, + verdict >> NF_VERDICT_QBITS); + if (err < 0) { + if (err == -ECANCELED) + goto next_hook; + if (err == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + goto next_hook; + kfree_skb(skb); + } break; case NF_STOLEN: default: diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 6a1572b..91592da 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -874,19 +874,19 @@ static struct hlist_node *get_first(struct iter_state *st) for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { if (!hlist_empty(&instance_table[st->bucket])) - return rcu_dereference_bh(instance_table[st->bucket].first); + return rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket])); } return NULL; } static struct hlist_node *get_next(struct iter_state *st, struct hlist_node *h) { - h = rcu_dereference_bh(h->next); + h = rcu_dereference_bh(hlist_next_rcu(h)); while (!h) { if (++st->bucket >= INSTANCE_BUCKETS) return NULL; - h = rcu_dereference_bh(instance_table[st->bucket].first); + h = rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket])); } return h; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 68e67d1..b83123f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -387,25 +387,31 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { struct sk_buff *nskb; struct nfqnl_instance *queue; - int err; + int err = -ENOBUFS; /* rcu_read_lock()ed by nf_hook_slow() */ queue = instance_lookup(queuenum); - if (!queue) + if (!queue) { + err = -ESRCH; goto err_out; + } - if (queue->copy_mode == NFQNL_COPY_NONE) + if (queue->copy_mode == NFQNL_COPY_NONE) { + err = -EINVAL; goto err_out; + } nskb = nfqnl_build_packet_message(queue, entry); - if (nskb == NULL) + if (nskb == NULL) { + err = -ENOMEM; goto err_out; - + } spin_lock_bh(&queue->lock); - if (!queue->peer_pid) + if (!queue->peer_pid) { + err = -EINVAL; goto err_out_free_nskb; - + } if (queue->queue_total >= queue->queue_maxlen) { queue->queue_dropped++; if (net_ratelimit()) @@ -432,7 +438,7 @@ err_out_free_nskb: err_out_unlock: spin_unlock_bh(&queue->lock); err_out: - return -1; + return err; } static int diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index c942376..0a77d2f 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -23,6 +23,7 @@ #include <linux/mutex.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/audit.h> #include <net/net_namespace.h> #include <linux/netfilter/x_tables.h> @@ -38,9 +39,8 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) struct compat_delta { - struct compat_delta *next; - unsigned int offset; - int delta; + unsigned int offset; /* offset in kernel */ + int delta; /* delta in 32bit user land */ }; struct xt_af { @@ -49,7 +49,9 @@ struct xt_af { struct list_head target; #ifdef CONFIG_COMPAT struct mutex compat_mutex; - struct compat_delta *compat_offsets; + struct compat_delta *compat_tab; + unsigned int number; /* number of slots in compat_tab[] */ + unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; @@ -414,54 +416,67 @@ int xt_check_match(struct xt_mtchk_param *par, EXPORT_SYMBOL_GPL(xt_check_match); #ifdef CONFIG_COMPAT -int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta) +int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { - struct compat_delta *tmp; + struct xt_af *xp = &xt[af]; - tmp = kmalloc(sizeof(struct compat_delta), GFP_KERNEL); - if (!tmp) - return -ENOMEM; + if (!xp->compat_tab) { + if (!xp->number) + return -EINVAL; + xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number); + if (!xp->compat_tab) + return -ENOMEM; + xp->cur = 0; + } - tmp->offset = offset; - tmp->delta = delta; + if (xp->cur >= xp->number) + return -EINVAL; - if (xt[af].compat_offsets) { - tmp->next = xt[af].compat_offsets->next; - xt[af].compat_offsets->next = tmp; - } else { - xt[af].compat_offsets = tmp; - tmp->next = NULL; - } + if (xp->cur) + delta += xp->compat_tab[xp->cur - 1].delta; + xp->compat_tab[xp->cur].offset = offset; + xp->compat_tab[xp->cur].delta = delta; + xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); void xt_compat_flush_offsets(u_int8_t af) { - struct compat_delta *tmp, *next; - - if (xt[af].compat_offsets) { - for (tmp = xt[af].compat_offsets; tmp; tmp = next) { - next = tmp->next; - kfree(tmp); - } - xt[af].compat_offsets = NULL; + if (xt[af].compat_tab) { + vfree(xt[af].compat_tab); + xt[af].compat_tab = NULL; + xt[af].number = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { - struct compat_delta *tmp; - int delta; - - for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next) - if (tmp->offset < offset) - delta += tmp->delta; - return delta; + struct compat_delta *tmp = xt[af].compat_tab; + int mid, left = 0, right = xt[af].cur - 1; + + while (left <= right) { + mid = (left + right) >> 1; + if (offset > tmp[mid].offset) + left = mid + 1; + else if (offset < tmp[mid].offset) + right = mid - 1; + else + return mid ? tmp[mid - 1].delta : 0; + } + WARN_ON_ONCE(1); + return 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); +void xt_compat_init_offsets(u_int8_t af, unsigned int number) +{ + xt[af].number = number; + xt[af].cur = 0; +} +EXPORT_SYMBOL(xt_compat_init_offsets); + int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; @@ -820,6 +835,21 @@ xt_replace_table(struct xt_table *table, */ local_bh_enable(); +#ifdef CONFIG_AUDIT + if (audit_enabled) { + struct audit_buffer *ab; + + ab = audit_log_start(current->audit_context, GFP_KERNEL, + AUDIT_NETFILTER_CFG); + if (ab) { + audit_log_format(ab, "table=%s family=%u entries=%u", + table->name, table->af, + private->number); + audit_log_end(ab); + } + } +#endif + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); @@ -1338,7 +1368,7 @@ static int __init xt_init(void) mutex_init(&xt[i].mutex); #ifdef CONFIG_COMPAT mutex_init(&xt[i].compat_mutex); - xt[i].compat_offsets = NULL; + xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c new file mode 100644 index 0000000..81802d2 --- /dev/null +++ b/net/netfilter/xt_AUDIT.c @@ -0,0 +1,204 @@ +/* + * Creates audit record for dropped/accepted packets + * + * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> + * (C) 2010-2011 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. +*/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/audit.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/if_arp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_AUDIT.h> +#include <net/ipv6.h> +#include <net/ip.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Thomas Graf <tgraf@redhat.com>"); +MODULE_DESCRIPTION("Xtables: creates audit records for dropped/accepted packets"); +MODULE_ALIAS("ipt_AUDIT"); +MODULE_ALIAS("ip6t_AUDIT"); +MODULE_ALIAS("ebt_AUDIT"); +MODULE_ALIAS("arpt_AUDIT"); + +static void audit_proto(struct audit_buffer *ab, struct sk_buff *skb, + unsigned int proto, unsigned int offset) +{ + switch (proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: { + const __be16 *pptr; + __be16 _ports[2]; + + pptr = skb_header_pointer(skb, offset, sizeof(_ports), _ports); + if (pptr == NULL) { + audit_log_format(ab, " truncated=1"); + return; + } + + audit_log_format(ab, " sport=%hu dport=%hu", + ntohs(pptr[0]), ntohs(pptr[1])); + } + break; + + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: { + const u8 *iptr; + u8 _ih[2]; + + iptr = skb_header_pointer(skb, offset, sizeof(_ih), &_ih); + if (iptr == NULL) { + audit_log_format(ab, " truncated=1"); + return; + } + + audit_log_format(ab, " icmptype=%hhu icmpcode=%hhu", + iptr[0], iptr[1]); + + } + break; + } +} + +static void audit_ip4(struct audit_buffer *ab, struct sk_buff *skb) +{ + struct iphdr _iph; + const struct iphdr *ih; + + ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); + if (!ih) { + audit_log_format(ab, " truncated=1"); + return; + } + + audit_log_format(ab, " saddr=%pI4 daddr=%pI4 ipid=%hu proto=%hhu", + &ih->saddr, &ih->daddr, ntohs(ih->id), ih->protocol); + + if (ntohs(ih->frag_off) & IP_OFFSET) { + audit_log_format(ab, " frag=1"); + return; + } + + audit_proto(ab, skb, ih->protocol, ih->ihl * 4); +} + +static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb) +{ + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + u8 nexthdr; + int offset; + + ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h); + if (!ih) { + audit_log_format(ab, " truncated=1"); + return; + } + + nexthdr = ih->nexthdr; + offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h), + &nexthdr); + + audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu", + &ih->saddr, &ih->daddr, nexthdr); + + if (offset) + audit_proto(ab, skb, nexthdr, offset); +} + +static unsigned int +audit_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_audit_info *info = par->targinfo; + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); + if (ab == NULL) + goto errout; + + audit_log_format(ab, "action=%hhu hook=%u len=%u inif=%s outif=%s", + info->type, par->hooknum, skb->len, + par->in ? par->in->name : "?", + par->out ? par->out->name : "?"); + + if (skb->mark) + audit_log_format(ab, " mark=%#x", skb->mark); + + if (skb->dev && skb->dev->type == ARPHRD_ETHER) { + audit_log_format(ab, " smac=%pM dmac=%pM macproto=0x%04x", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + + if (par->family == NFPROTO_BRIDGE) { + switch (eth_hdr(skb)->h_proto) { + case __constant_htons(ETH_P_IP): + audit_ip4(ab, skb); + break; + + case __constant_htons(ETH_P_IPV6): + audit_ip6(ab, skb); + break; + } + } + } + + switch (par->family) { + case NFPROTO_IPV4: + audit_ip4(ab, skb); + break; + + case NFPROTO_IPV6: + audit_ip6(ab, skb); + break; + } + + audit_log_end(ab); + +errout: + return XT_CONTINUE; +} + +static int audit_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_audit_info *info = par->targinfo; + + if (info->type > XT_AUDIT_TYPE_MAX) { + pr_info("Audit type out of range (valid range: 0..%hhu)\n", + XT_AUDIT_TYPE_MAX); + return -ERANGE; + } + + return 0; +} + +static struct xt_target audit_tg_reg __read_mostly = { + .name = "AUDIT", + .family = NFPROTO_UNSPEC, + .target = audit_tg, + .targetsize = sizeof(struct xt_audit_info), + .checkentry = audit_tg_check, + .me = THIS_MODULE, +}; + +static int __init audit_tg_init(void) +{ + return xt_register_target(&audit_tg_reg); +} + +static void __exit audit_tg_exit(void) +{ + xt_unregister_target(&audit_tg_reg); +} + +module_init(audit_tg_init); +module_exit(audit_tg_exit); diff --git a/net/netfilter/xt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c index c2c0e4a..af9c4da 100644 --- a/net/netfilter/xt_CLASSIFY.c +++ b/net/netfilter/xt_CLASSIFY.c @@ -19,12 +19,14 @@ #include <linux/netfilter_ipv6.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CLASSIFY.h> +#include <linux/netfilter_arp.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: Qdisc classification"); MODULE_ALIAS("ipt_CLASSIFY"); MODULE_ALIAS("ip6t_CLASSIFY"); +MODULE_ALIAS("arpt_CLASSIFY"); static unsigned int classify_tg(struct sk_buff *skb, const struct xt_action_param *par) @@ -35,26 +37,36 @@ classify_tg(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static struct xt_target classify_tg_reg __read_mostly = { - .name = "CLASSIFY", - .revision = 0, - .family = NFPROTO_UNSPEC, - .table = "mangle", - .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | - (1 << NF_INET_POST_ROUTING), - .target = classify_tg, - .targetsize = sizeof(struct xt_classify_target_info), - .me = THIS_MODULE, +static struct xt_target classify_tg_reg[] __read_mostly = { + { + .name = "CLASSIFY", + .revision = 0, + .family = NFPROTO_UNSPEC, + .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | + (1 << NF_INET_POST_ROUTING), + .target = classify_tg, + .targetsize = sizeof(struct xt_classify_target_info), + .me = THIS_MODULE, + }, + { + .name = "CLASSIFY", + .revision = 0, + .family = NFPROTO_ARP, + .hooks = (1 << NF_ARP_OUT) | (1 << NF_ARP_FORWARD), + .target = classify_tg, + .targetsize = sizeof(struct xt_classify_target_info), + .me = THIS_MODULE, + }, }; static int __init classify_tg_init(void) { - return xt_register_target(&classify_tg_reg); + return xt_register_targets(classify_tg_reg, ARRAY_SIZE(classify_tg_reg)); } static void __exit classify_tg_exit(void) { - xt_unregister_target(&classify_tg_reg); + xt_unregister_targets(classify_tg_reg, ARRAY_SIZE(classify_tg_reg)); } module_init(classify_tg_init); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index be1f22e..3bdd443 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -313,3 +313,5 @@ MODULE_AUTHOR("Timo Teras <ext-timo.teras@nokia.com>"); MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); MODULE_DESCRIPTION("Xtables: idle time monitor"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("ipt_IDLETIMER"); +MODULE_ALIAS("ip6t_IDLETIMER"); diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index a414050..993de2b 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -31,6 +31,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adam Nielsen <a.nielsen@shikadi.net>"); MODULE_DESCRIPTION("Xtables: trigger LED devices on packet match"); +MODULE_ALIAS("ipt_LED"); +MODULE_ALIAS("ip6t_LED"); static LIST_HEAD(xt_led_triggers); static DEFINE_MUTEX(xt_led_mutex); diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 039cce1..d4f4b5d 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -72,18 +72,31 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) if (info->queues_total > 1) { if (par->family == NFPROTO_IPV4) - queue = hash_v4(skb) % info->queues_total + queue; + queue = (((u64) hash_v4(skb) * info->queues_total) >> + 32) + queue; #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) else if (par->family == NFPROTO_IPV6) - queue = hash_v6(skb) % info->queues_total + queue; + queue = (((u64) hash_v6(skb) * info->queues_total) >> + 32) + queue; #endif } return NF_QUEUE_NR(queue); } -static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par) +static unsigned int +nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_NFQ_info_v1 *info = par->targinfo; + const struct xt_NFQ_info_v2 *info = par->targinfo; + unsigned int ret = nfqueue_tg_v1(skb, par); + + if (info->bypass) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + return ret; +} + +static int nfqueue_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_NFQ_info_v2 *info = par->targinfo; u32 maxid; if (unlikely(!rnd_inited)) { @@ -100,6 +113,8 @@ static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par) info->queues_total, maxid); return -ERANGE; } + if (par->target->revision == 2 && info->bypass > 1) + return -EINVAL; return 0; } @@ -115,11 +130,20 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = { .name = "NFQUEUE", .revision = 1, .family = NFPROTO_UNSPEC, - .checkentry = nfqueue_tg_v1_check, + .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v1, .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, + { + .name = "NFQUEUE", + .revision = 2, + .family = NFPROTO_UNSPEC, + .checkentry = nfqueue_tg_check, + .target = nfqueue_tg_v2, + .targetsize = sizeof(struct xt_NFQ_info_v2), + .me = THIS_MODULE, + }, }; static int __init nfqueue_tg_init(void) diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 5c5b6b9..e029c48 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -185,18 +185,24 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) int connections; ct = nf_ct_get(skb, &ctinfo); - if (ct != NULL) - tuple_ptr = &ct->tuplehash[0].tuple; - else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - par->family, &tuple)) + if (ct != NULL) { + if (info->flags & XT_CONNLIMIT_DADDR) + tuple_ptr = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; + else + tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + } else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + par->family, &tuple)) { goto hotdrop; + } if (par->family == NFPROTO_IPV6) { const struct ipv6hdr *iph = ipv6_hdr(skb); - memcpy(&addr.ip6, &iph->saddr, sizeof(iph->saddr)); + memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ? + &iph->daddr : &iph->saddr, sizeof(addr.ip6)); } else { const struct iphdr *iph = ip_hdr(skb); - addr.ip = iph->saddr; + addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ? + iph->daddr : iph->saddr; } spin_lock_bh(&info->data->lock); @@ -204,13 +210,12 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) &info->mask, par->family); spin_unlock_bh(&info->data->lock); - if (connections < 0) { + if (connections < 0) /* kmalloc failed, drop it entirely */ - par->hotdrop = true; - return false; - } + goto hotdrop; - return (connections > info->limit) ^ info->inverse; + return (connections > info->limit) ^ + !!(info->flags & XT_CONNLIMIT_INVERT); hotdrop: par->hotdrop = true; @@ -268,25 +273,38 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) kfree(info->data); } -static struct xt_match connlimit_mt_reg __read_mostly = { - .name = "connlimit", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = connlimit_mt_check, - .match = connlimit_mt, - .matchsize = sizeof(struct xt_connlimit_info), - .destroy = connlimit_mt_destroy, - .me = THIS_MODULE, +static struct xt_match connlimit_mt_reg[] __read_mostly = { + { + .name = "connlimit", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = connlimit_mt_check, + .match = connlimit_mt, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_mt_destroy, + .me = THIS_MODULE, + }, + { + .name = "connlimit", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = connlimit_mt_check, + .match = connlimit_mt, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_mt_destroy, + .me = THIS_MODULE, + }, }; static int __init connlimit_mt_init(void) { - return xt_register_match(&connlimit_mt_reg); + return xt_register_matches(connlimit_mt_reg, + ARRAY_SIZE(connlimit_mt_reg)); } static void __exit connlimit_mt_exit(void) { - xt_unregister_match(&connlimit_mt_reg); + xt_unregister_matches(connlimit_mt_reg, ARRAY_SIZE(connlimit_mt_reg)); } module_init(connlimit_mt_init); diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index e536710..4ef1b63 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -112,6 +112,54 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info, return true; } +static inline bool +port_match(u16 min, u16 max, u16 port, bool invert) +{ + return (port >= min && port <= max) ^ invert; +} + +static inline bool +ct_proto_port_check_v3(const struct xt_conntrack_mtinfo3 *info, + const struct nf_conn *ct) +{ + const struct nf_conntrack_tuple *tuple; + + tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + if ((info->match_flags & XT_CONNTRACK_PROTO) && + (nf_ct_protonum(ct) == info->l4proto) ^ + !(info->invert_flags & XT_CONNTRACK_PROTO)) + return false; + + /* Shortcut to match all recognized protocols by using ->src.all. */ + if ((info->match_flags & XT_CONNTRACK_ORIGSRC_PORT) && + !port_match(info->origsrc_port, info->origsrc_port_high, + ntohs(tuple->src.u.all), + info->invert_flags & XT_CONNTRACK_ORIGSRC_PORT)) + return false; + + if ((info->match_flags & XT_CONNTRACK_ORIGDST_PORT) && + !port_match(info->origdst_port, info->origdst_port_high, + ntohs(tuple->dst.u.all), + info->invert_flags & XT_CONNTRACK_ORIGDST_PORT)) + return false; + + tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; + + if ((info->match_flags & XT_CONNTRACK_REPLSRC_PORT) && + !port_match(info->replsrc_port, info->replsrc_port_high, + ntohs(tuple->src.u.all), + info->invert_flags & XT_CONNTRACK_REPLSRC_PORT)) + return false; + + if ((info->match_flags & XT_CONNTRACK_REPLDST_PORT) && + !port_match(info->repldst_port, info->repldst_port_high, + ntohs(tuple->dst.u.all), + info->invert_flags & XT_CONNTRACK_REPLDST_PORT)) + return false; + + return true; +} + static bool conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 state_mask, u16 status_mask) @@ -170,8 +218,13 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, !(info->invert_flags & XT_CONNTRACK_REPLDST)) return false; - if (!ct_proto_port_check(info, ct)) - return false; + if (par->match->revision != 3) { + if (!ct_proto_port_check(info, ct)) + return false; + } else { + if (!ct_proto_port_check_v3(par->matchinfo, ct)) + return false; + } if ((info->match_flags & XT_CONNTRACK_STATUS) && (!!(status_mask & ct->status) ^ @@ -207,6 +260,14 @@ conntrack_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) return conntrack_mt(skb, par, info->state_mask, info->status_mask); } +static bool +conntrack_mt_v3(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_conntrack_mtinfo3 *info = par->matchinfo; + + return conntrack_mt(skb, par, info->state_mask, info->status_mask); +} + static int conntrack_mt_check(const struct xt_mtchk_param *par) { int ret; @@ -244,6 +305,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .destroy = conntrack_mt_destroy, .me = THIS_MODULE, }, + { + .name = "conntrack", + .revision = 3, + .family = NFPROTO_UNSPEC, + .matchsize = sizeof(struct xt_conntrack_mtinfo3), + .match = conntrack_mt_v3, + .checkentry = conntrack_mt_check, + .destroy = conntrack_mt_destroy, + .me = THIS_MODULE, + }, }; static int __init conntrack_mt_init(void) diff --git a/net/netfilter/xt_cpu.c b/net/netfilter/xt_cpu.c index b39db8a..c7a2e54 100644 --- a/net/netfilter/xt_cpu.c +++ b/net/netfilter/xt_cpu.c @@ -22,6 +22,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Eric Dumazet <eric.dumazet@gmail.com>"); MODULE_DESCRIPTION("Xtables: CPU match"); +MODULE_ALIAS("ipt_cpu"); +MODULE_ALIAS("ip6t_cpu"); static int cpu_mt_check(const struct xt_mtchk_param *par) { diff --git a/net/netfilter/xt_devgroup.c b/net/netfilter/xt_devgroup.c new file mode 100644 index 0000000..d9202cd --- /dev/null +++ b/net/netfilter/xt_devgroup.c @@ -0,0 +1,82 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> + +#include <linux/netfilter/xt_devgroup.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: Device group match"); +MODULE_ALIAS("ipt_devgroup"); +MODULE_ALIAS("ip6t_devgroup"); + +static bool devgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_devgroup_info *info = par->matchinfo; + + if (info->flags & XT_DEVGROUP_MATCH_SRC && + (((info->src_group ^ par->in->group) & info->src_mask ? 1 : 0) ^ + ((info->flags & XT_DEVGROUP_INVERT_SRC) ? 1 : 0))) + return false; + + if (info->flags & XT_DEVGROUP_MATCH_DST && + (((info->dst_group ^ par->out->group) & info->dst_mask ? 1 : 0) ^ + ((info->flags & XT_DEVGROUP_INVERT_DST) ? 1 : 0))) + return false; + + return true; +} + +static int devgroup_mt_checkentry(const struct xt_mtchk_param *par) +{ + const struct xt_devgroup_info *info = par->matchinfo; + + if (info->flags & ~(XT_DEVGROUP_MATCH_SRC | XT_DEVGROUP_INVERT_SRC | + XT_DEVGROUP_MATCH_DST | XT_DEVGROUP_INVERT_DST)) + return -EINVAL; + + if (info->flags & XT_DEVGROUP_MATCH_SRC && + par->hook_mask & ~((1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD))) + return -EINVAL; + + if (info->flags & XT_DEVGROUP_MATCH_DST && + par->hook_mask & ~((1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING))) + return -EINVAL; + + return 0; +} + +static struct xt_match devgroup_mt_reg __read_mostly = { + .name = "devgroup", + .match = devgroup_mt, + .checkentry = devgroup_mt_checkentry, + .matchsize = sizeof(struct xt_devgroup_info), + .family = NFPROTO_UNSPEC, + .me = THIS_MODULE +}; + +static int __init devgroup_mt_init(void) +{ + return xt_register_match(&devgroup_mt_reg); +} + +static void __exit devgroup_mt_exit(void) +{ + xt_unregister_match(&devgroup_mt_reg); +} + +module_init(devgroup_mt_init); +module_exit(devgroup_mt_exit); diff --git a/net/netfilter/xt_iprange.c b/net/netfilter/xt_iprange.c index 73c33a4..b46626c 100644 --- a/net/netfilter/xt_iprange.c +++ b/net/netfilter/xt_iprange.c @@ -31,7 +31,7 @@ iprange_mt4(const struct sk_buff *skb, struct xt_action_param *par) pr_debug("src IP %pI4 NOT in range %s%pI4-%pI4\n", &iph->saddr, (info->flags & IPRANGE_SRC_INV) ? "(INV) " : "", - &info->src_max.ip, + &info->src_min.ip, &info->src_max.ip); return false; } @@ -76,15 +76,27 @@ iprange_mt6(const struct sk_buff *skb, struct xt_action_param *par) m = iprange_ipv6_lt(&iph->saddr, &info->src_min.in6); m |= iprange_ipv6_lt(&info->src_max.in6, &iph->saddr); m ^= !!(info->flags & IPRANGE_SRC_INV); - if (m) + if (m) { + pr_debug("src IP %pI6 NOT in range %s%pI6-%pI6\n", + &iph->saddr, + (info->flags & IPRANGE_SRC_INV) ? "(INV) " : "", + &info->src_min.in6, + &info->src_max.in6); return false; + } } if (info->flags & IPRANGE_DST) { m = iprange_ipv6_lt(&iph->daddr, &info->dst_min.in6); m |= iprange_ipv6_lt(&info->dst_max.in6, &iph->daddr); m ^= !!(info->flags & IPRANGE_DST_INV); - if (m) + if (m) { + pr_debug("dst IP %pI6 NOT in range %s%pI6-%pI6\n", + &iph->daddr, + (info->flags & IPRANGE_DST_INV) ? "(INV) " : "", + &info->dst_min.in6, + &info->dst_max.in6); return false; + } } return true; } diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 9127a3d..bb10b07 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */); + cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */); if (unlikely(cp == NULL)) { match = false; goto out; diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c new file mode 100644 index 0000000..061d48c --- /dev/null +++ b/net/netfilter/xt_set.c @@ -0,0 +1,359 @@ +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Martin Josefsson <gandalf@wlug.westbo.se> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module which implements the set match and SET target + * for netfilter/iptables. */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/version.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_set.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("Xtables: IP set match and target module"); +MODULE_ALIAS("xt_SET"); +MODULE_ALIAS("ipt_set"); +MODULE_ALIAS("ip6t_set"); +MODULE_ALIAS("ipt_SET"); +MODULE_ALIAS("ip6t_SET"); + +static inline int +match_set(ip_set_id_t index, const struct sk_buff *skb, + u8 pf, u8 dim, u8 flags, int inv) +{ + if (ip_set_test(index, skb, pf, dim, flags)) + inv = !inv; + return inv; +} + +/* Revision 0 interface: backward compatible with netfilter/iptables */ + +static bool +set_match_v0(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_set_info_match_v0 *info = par->matchinfo; + + return match_set(info->match_set.index, skb, par->family, + info->match_set.u.compat.dim, + info->match_set.u.compat.flags, + info->match_set.u.compat.flags & IPSET_INV_MATCH); +} + +static void +compat_flags(struct xt_set_info_v0 *info) +{ + u_int8_t i; + + /* Fill out compatibility data according to enum ip_set_kopt */ + info->u.compat.dim = IPSET_DIM_ZERO; + if (info->u.flags[0] & IPSET_MATCH_INV) + info->u.compat.flags |= IPSET_INV_MATCH; + for (i = 0; i < IPSET_DIM_MAX-1 && info->u.flags[i]; i++) { + info->u.compat.dim++; + if (info->u.flags[i] & IPSET_SRC) + info->u.compat.flags |= (1<<info->u.compat.dim); + } +} + +static int +set_match_v0_checkentry(const struct xt_mtchk_param *par) +{ + struct xt_set_info_match_v0 *info = par->matchinfo; + ip_set_id_t index; + + index = ip_set_nfnl_get_byindex(info->match_set.index); + + if (index == IPSET_INVALID_ID) { + pr_warning("Cannot find set indentified by id %u to match\n", + info->match_set.index); + return -ENOENT; + } + if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) { + pr_warning("Protocol error: set match dimension " + "is over the limit!\n"); + return -ERANGE; + } + + /* Fill out compatibility data */ + compat_flags(&info->match_set); + + return 0; +} + +static void +set_match_v0_destroy(const struct xt_mtdtor_param *par) +{ + struct xt_set_info_match_v0 *info = par->matchinfo; + + ip_set_nfnl_put(info->match_set.index); +} + +static unsigned int +set_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_set_info_target_v0 *info = par->targinfo; + + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_add(info->add_set.index, skb, par->family, + info->add_set.u.compat.dim, + info->add_set.u.compat.flags); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_del(info->del_set.index, skb, par->family, + info->del_set.u.compat.dim, + info->del_set.u.compat.flags); + + return XT_CONTINUE; +} + +static int +set_target_v0_checkentry(const struct xt_tgchk_param *par) +{ + struct xt_set_info_target_v0 *info = par->targinfo; + ip_set_id_t index; + + if (info->add_set.index != IPSET_INVALID_ID) { + index = ip_set_nfnl_get_byindex(info->add_set.index); + if (index == IPSET_INVALID_ID) { + pr_warning("Cannot find add_set index %u as target\n", + info->add_set.index); + return -ENOENT; + } + } + + if (info->del_set.index != IPSET_INVALID_ID) { + index = ip_set_nfnl_get_byindex(info->del_set.index); + if (index == IPSET_INVALID_ID) { + pr_warning("Cannot find del_set index %u as target\n", + info->del_set.index); + return -ENOENT; + } + } + if (info->add_set.u.flags[IPSET_DIM_MAX-1] != 0 || + info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) { + pr_warning("Protocol error: SET target dimension " + "is over the limit!\n"); + return -ERANGE; + } + + /* Fill out compatibility data */ + compat_flags(&info->add_set); + compat_flags(&info->del_set); + + return 0; +} + +static void +set_target_v0_destroy(const struct xt_tgdtor_param *par) +{ + const struct xt_set_info_target_v0 *info = par->targinfo; + + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); +} + +/* Revision 1: current interface to netfilter/iptables */ + +static bool +set_match(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_set_info_match *info = par->matchinfo; + + return match_set(info->match_set.index, skb, par->family, + info->match_set.dim, + info->match_set.flags, + info->match_set.flags & IPSET_INV_MATCH); +} + +static int +set_match_checkentry(const struct xt_mtchk_param *par) +{ + struct xt_set_info_match *info = par->matchinfo; + ip_set_id_t index; + + index = ip_set_nfnl_get_byindex(info->match_set.index); + + if (index == IPSET_INVALID_ID) { + pr_warning("Cannot find set indentified by id %u to match\n", + info->match_set.index); + return -ENOENT; + } + if (info->match_set.dim > IPSET_DIM_MAX) { + pr_warning("Protocol error: set match dimension " + "is over the limit!\n"); + return -ERANGE; + } + + return 0; +} + +static void +set_match_destroy(const struct xt_mtdtor_param *par) +{ + struct xt_set_info_match *info = par->matchinfo; + + ip_set_nfnl_put(info->match_set.index); +} + +static unsigned int +set_target(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_set_info_target *info = par->targinfo; + + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_add(info->add_set.index, + skb, par->family, + info->add_set.dim, + info->add_set.flags); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_del(info->del_set.index, + skb, par->family, + info->add_set.dim, + info->del_set.flags); + + return XT_CONTINUE; +} + +static int +set_target_checkentry(const struct xt_tgchk_param *par) +{ + const struct xt_set_info_target *info = par->targinfo; + ip_set_id_t index; + + if (info->add_set.index != IPSET_INVALID_ID) { + index = ip_set_nfnl_get_byindex(info->add_set.index); + if (index == IPSET_INVALID_ID) { + pr_warning("Cannot find add_set index %u as target\n", + info->add_set.index); + return -ENOENT; + } + } + + if (info->del_set.index != IPSET_INVALID_ID) { + index = ip_set_nfnl_get_byindex(info->del_set.index); + if (index == IPSET_INVALID_ID) { + pr_warning("Cannot find del_set index %u as target\n", + info->del_set.index); + return -ENOENT; + } + } + if (info->add_set.dim > IPSET_DIM_MAX || + info->del_set.flags > IPSET_DIM_MAX) { + pr_warning("Protocol error: SET target dimension " + "is over the limit!\n"); + return -ERANGE; + } + + return 0; +} + +static void +set_target_destroy(const struct xt_tgdtor_param *par) +{ + const struct xt_set_info_target *info = par->targinfo; + + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); +} + +static struct xt_match set_matches[] __read_mostly = { + { + .name = "set", + .family = NFPROTO_IPV4, + .revision = 0, + .match = set_match_v0, + .matchsize = sizeof(struct xt_set_info_match_v0), + .checkentry = set_match_v0_checkentry, + .destroy = set_match_v0_destroy, + .me = THIS_MODULE + }, + { + .name = "set", + .family = NFPROTO_IPV4, + .revision = 1, + .match = set_match, + .matchsize = sizeof(struct xt_set_info_match), + .checkentry = set_match_checkentry, + .destroy = set_match_destroy, + .me = THIS_MODULE + }, + { + .name = "set", + .family = NFPROTO_IPV6, + .revision = 1, + .match = set_match, + .matchsize = sizeof(struct xt_set_info_match), + .checkentry = set_match_checkentry, + .destroy = set_match_destroy, + .me = THIS_MODULE + }, +}; + +static struct xt_target set_targets[] __read_mostly = { + { + .name = "SET", + .revision = 0, + .family = NFPROTO_IPV4, + .target = set_target_v0, + .targetsize = sizeof(struct xt_set_info_target_v0), + .checkentry = set_target_v0_checkentry, + .destroy = set_target_v0_destroy, + .me = THIS_MODULE + }, + { + .name = "SET", + .revision = 1, + .family = NFPROTO_IPV4, + .target = set_target, + .targetsize = sizeof(struct xt_set_info_target), + .checkentry = set_target_checkentry, + .destroy = set_target_destroy, + .me = THIS_MODULE + }, + { + .name = "SET", + .revision = 1, + .family = NFPROTO_IPV6, + .target = set_target, + .targetsize = sizeof(struct xt_set_info_target), + .checkentry = set_target_checkentry, + .destroy = set_target_destroy, + .me = THIS_MODULE + }, +}; + +static int __init xt_set_init(void) +{ + int ret = xt_register_matches(set_matches, ARRAY_SIZE(set_matches)); + + if (!ret) { + ret = xt_register_targets(set_targets, + ARRAY_SIZE(set_targets)); + if (ret) + xt_unregister_matches(set_matches, + ARRAY_SIZE(set_matches)); + } + return ret; +} + +static void __exit xt_set_fini(void) +{ + xt_unregister_matches(set_matches, ARRAY_SIZE(set_matches)); + xt_unregister_targets(set_targets, ARRAY_SIZE(set_targets)); +} + +module_init(xt_set_init); +module_exit(xt_set_fini); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 91cb1d7..5efef5b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -164,7 +164,6 @@ struct packet_mreq_max { static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing, int tx_ring); -#define PGV_FROM_VMALLOC 1 struct pgv { char *buffer; }; @@ -466,7 +465,7 @@ retry: */ err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len) + if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN) goto out_unlock; if (!skb) { @@ -497,6 +496,19 @@ retry: goto retry; } + if (len > (dev->mtu + dev->hard_header_len)) { + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + struct ethhdr *ehdr; + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) { + err = -EMSGSIZE; + goto out_unlock; + } + } skb->protocol = proto; skb->dev = dev; @@ -523,11 +535,11 @@ static inline unsigned int run_filter(const struct sk_buff *skb, { struct sk_filter *filter; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = sk_run_filter(skb, filter->insns); - rcu_read_unlock_bh(); + rcu_read_unlock(); return res; } @@ -1200,7 +1212,7 @@ static int packet_snd(struct socket *sock, } err = -EMSGSIZE; - if (!gso_type && (len > dev->mtu+reserve)) + if (!gso_type && (len > dev->mtu + reserve + VLAN_HLEN)) goto out_unlock; err = -ENOBUFS; @@ -1225,6 +1237,20 @@ static int packet_snd(struct socket *sock, if (err < 0) goto out_free; + if (!gso_type && (len > dev->mtu + reserve)) { + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + struct ethhdr *ehdr; + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) { + err = -EMSGSIZE; + goto out_free; + } + } + skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; diff --git a/net/rds/rds.h b/net/rds/rds.h index 9542449..da8adac 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -50,7 +50,6 @@ rdsdebug(char *fmt, ...) #define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT)) #define RDS_CONG_MAP_BYTES (65536 / 8) -#define RDS_CONG_MAP_LONGS (RDS_CONG_MAP_BYTES / sizeof(unsigned long)) #define RDS_CONG_MAP_PAGES (PAGE_ALIGN(RDS_CONG_MAP_BYTES) / PAGE_SIZE) #define RDS_CONG_MAP_PAGE_BITS (PAGE_SIZE * 8) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index d952e7e..5ee0c62 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -803,7 +803,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le rose_insert_socket(sk); /* Finish the bind */ } -rose_try_next_neigh: rose->dest_addr = addr->srose_addr; rose->dest_call = addr->srose_call; rose->rand = ((long)rose & 0xFFFF) + rose->lci; @@ -865,12 +864,6 @@ rose_try_next_neigh: } if (sk->sk_state != TCP_ESTABLISHED) { - /* Try next neighbour */ - rose->neighbour = rose_get_neigh(&addr->srose_addr, &cause, &diagnostic, 0); - if (rose->neighbour) - goto rose_try_next_neigh; - - /* No more neighbours */ sock->state = SS_UNCONNECTED; err = sock_error(sk); /* Always set at this point */ goto out_release; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index b4fdaac..88a77e9 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -674,29 +674,34 @@ struct rose_route *rose_route_free_lci(unsigned int lci, struct rose_neigh *neig * Find a neighbour or a route given a ROSE address. */ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause, - unsigned char *diagnostic, int new) + unsigned char *diagnostic, int route_frame) { struct rose_neigh *res = NULL; struct rose_node *node; int failed = 0; int i; - if (!new) spin_lock_bh(&rose_node_list_lock); + if (!route_frame) spin_lock_bh(&rose_node_list_lock); for (node = rose_node_list; node != NULL; node = node->next) { if (rosecmpm(addr, &node->address, node->mask) == 0) { for (i = 0; i < node->count; i++) { - if (new) { - if (node->neighbour[i]->restarted) { - res = node->neighbour[i]; - goto out; - } + if (node->neighbour[i]->restarted) { + res = node->neighbour[i]; + goto out; } - else { + } + } + } + if (!route_frame) { /* connect request */ + for (node = rose_node_list; node != NULL; node = node->next) { + if (rosecmpm(addr, &node->address, node->mask) == 0) { + for (i = 0; i < node->count; i++) { if (!rose_ftimer_running(node->neighbour[i])) { res = node->neighbour[i]; + failed = 0; goto out; - } else - failed = 1; + } + failed = 1; } } } @@ -711,8 +716,7 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause, } out: - if (!new) spin_unlock_bh(&rose_node_list_lock); - + if (!route_frame) spin_unlock_bh(&rose_node_list_lock); return res; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index f04d4a4..8c19b6e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -205,6 +205,29 @@ config NET_SCH_DRR If unsure, say N. +config NET_SCH_MQPRIO + tristate "Multi-queue priority scheduler (MQPRIO)" + help + Say Y here if you want to use the Multi-queue Priority scheduler. + This scheduler allows QOS to be offloaded on NICs that have support + for offloading QOS schedulers. + + To compile this driver as a module, choose M here: the module will + be called sch_mqprio. + + If unsure, say N. + +config NET_SCH_CHOKE + tristate "CHOose and Keep responsive flow scheduler (CHOKE)" + help + Say Y here if you want to use the CHOKe packet scheduler (CHOose + and Keep for responsive flows, CHOose and Kill for unresponsive + flows). This is a variation of RED which trys to penalize flows + that monopolize the queue. + + To compile this code as a module, choose M here: the + module will be called sch_choke. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT @@ -243,7 +266,7 @@ config NET_CLS_TCINDEX config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" - select NET_CLS_ROUTE + select IP_ROUTE_CLASSID select NET_CLS ---help--- If you say Y here, you will be able to classify packets @@ -252,9 +275,6 @@ config NET_CLS_ROUTE4 To compile this code as a module, choose M here: the module will be called cls_route. -config NET_CLS_ROUTE - bool - config NET_CLS_FW tristate "Netfilter mark (FW)" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 960f5db..06c6cdf 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -32,6 +32,9 @@ obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o +obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o + obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 23b25f8..15873e1 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -78,7 +78,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, struct tc_action *a, struct tcf_hashinfo *hinfo) { struct tcf_common *p; - int err = 0, index = -1,i = 0, s_i = 0, n_i = 0; + int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct nlattr *nest; read_lock_bh(hinfo->lock); @@ -126,7 +126,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, { struct tcf_common *p, *s_p; struct nlattr *nest; - int i= 0, n_i = 0; + int i = 0, n_i = 0; nest = nla_nest_start(skb, a->order); if (nest == NULL) @@ -138,7 +138,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, while (p != NULL) { s_p = p->tcfc_next; if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) - module_put(a->ops->owner); + module_put(a->ops->owner); n_i++; p = s_p; } @@ -447,7 +447,8 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if ((err = tcf_action_dump_old(skb, a, bind, ref)) > 0) { + err = tcf_action_dump_old(skb, a, bind, ref); + if (err > 0) { nla_nest_end(skb, nest); return err; } @@ -491,7 +492,7 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, struct tc_action *a; struct tc_action_ops *a_o; char act_name[IFNAMSIZ]; - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; int err; @@ -549,9 +550,9 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, goto err_free; /* module count goes up only when brand new policy is created - if it exists and is only bound to in a_o->init() then - ACT_P_CREATED is not returned (a zero is). - */ + * if it exists and is only bound to in a_o->init() then + * ACT_P_CREATED is not returned (a zero is). + */ if (err != ACT_P_CREATED) module_put(a_o->owner); a->ops = a_o; @@ -569,7 +570,7 @@ err_out: struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind) { - struct nlattr *tb[TCA_ACT_MAX_PRIO+1]; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; int err; int i; @@ -697,7 +698,7 @@ act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n, static struct tc_action * tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 pid) { - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action *a; int index; int err; @@ -770,7 +771,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, struct tcamsg *t; struct netlink_callback dcb; struct nlattr *nest; - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; struct tc_action *a = create_a(0); int err = -ENOMEM; @@ -821,7 +822,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, nlh->nlmsg_flags |= NLM_F_ROOT; module_put(a->ops->owner); kfree(a); - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err > 0) return 0; @@ -842,14 +844,14 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 pid, int event) { int i, ret; - struct nlattr *tb[TCA_ACT_MAX_PRIO+1]; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL); if (ret < 0) return ret; - if (event == RTM_DELACTION && n->nlmsg_flags&NLM_F_ROOT) { + if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { if (tb[1] != NULL) return tca_action_flush(net, tb[1], n, pid); else @@ -892,7 +894,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* now do the delete */ tcf_action_destroy(head, 0); ret = rtnetlink_send(skb, net, pid, RTNLGRP_TC, - n->nlmsg_flags&NLM_F_ECHO); + n->nlmsg_flags & NLM_F_ECHO); if (ret > 0) return 0; return ret; @@ -936,7 +938,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, nlh->nlmsg_len = skb_tail_pointer(skb) - b; NETLINK_CB(skb).dst_group = RTNLGRP_TC; - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags&NLM_F_ECHO); + err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags & NLM_F_ECHO); if (err > 0) err = 0; return err; @@ -967,7 +969,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* dump then free all the actions after update; inserted policy * stays intact - * */ + */ ret = tcf_add_notify(net, act, pid, seq, RTM_NEWACTION, n->nlmsg_flags); for (a = act; a; a = act) { act = a->next; @@ -993,8 +995,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -EINVAL; } - /* n->nlmsg_flags&NLM_F_CREATE - * */ + /* n->nlmsg_flags & NLM_F_CREATE */ switch (n->nlmsg_type) { case RTM_NEWACTION: /* we are going to assume all other flags @@ -1003,7 +1004,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) * but since we want avoid ambiguity (eg when flags * is zero) then just set this */ - if (n->nlmsg_flags&NLM_F_REPLACE) + if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; replay: ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, pid, ovr); @@ -1028,7 +1029,7 @@ replay: static struct nlattr * find_dump_kind(const struct nlmsghdr *n) { - struct nlattr *tb1, *tb2[TCA_ACT_MAX+1]; + struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct nlattr *nla[TCAA_MAX + 1]; struct nlattr *kind; @@ -1071,9 +1072,8 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) } a_o = tc_lookup_action(kind); - if (a_o == NULL) { + if (a_o == NULL) return 0; - } memset(&a, 0, sizeof(struct tc_action)); a.ops = a_o; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 83ddfc0..6cdf9ab 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -63,7 +63,7 @@ static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_CSUM_MAX, nla,csum_policy); + err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy); if (err < 0) return err; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index c2ed90a..2b4ab4b 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -50,7 +50,7 @@ static int gact_determ(struct tcf_gact *gact) } typedef int (*g_rand)(struct tcf_gact *gact); -static g_rand gact_rand[MAX_RAND]= { NULL, gact_net_rand, gact_determ }; +static g_rand gact_rand[MAX_RAND] = { NULL, gact_net_rand, gact_determ }; #endif /* CONFIG_GACT_PROB */ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { @@ -89,7 +89,7 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind, &gact_idx_gen, &gact_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (!ovr) { @@ -205,9 +205,9 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { #ifdef CONFIG_GACT_PROB - printk(KERN_INFO "GACT probability on\n"); + pr_info("GACT probability on\n"); #else - printk(KERN_INFO "GACT probability NOT on\n"); + pr_info("GACT probability NOT on\n"); #endif return tcf_register_action(&act_gact_ops); } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index c2a7c20..9fc211a 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -138,7 +138,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, &ipt_idx_gen, &ipt_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (!ovr) { @@ -162,7 +162,8 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, if (unlikely(!t)) goto err2; - if ((err = ipt_init_target(t, tname, hook)) < 0) + err = ipt_init_target(t, tname, hook); + if (err < 0) goto err3; spin_lock_bh(&ipt->tcf_lock); @@ -212,8 +213,9 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, bstats_update(&ipt->tcf_bstats, skb); /* yes, we have to worry about both in and out dev - worry later - danger - this API seems to have changed - from earlier kernels */ + * worry later - danger - this API seems to have changed + * from earlier kernels + */ par.in = skb->dev; par.out = NULL; par.hooknum = ipt->tcfi_hook; @@ -253,9 +255,9 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int struct tc_cnt c; /* for simple targets kernel size == user size - ** user name = target name - ** for foolproof you need to not assume this - */ + * user name = target name + * for foolproof you need to not assume this + */ t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC); if (unlikely(!t)) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index d765067..961386e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -41,13 +41,13 @@ static struct tcf_hashinfo mirred_hash_info = { .lock = &mirred_lock, }; -static inline int tcf_mirred_release(struct tcf_mirred *m, int bind) +static int tcf_mirred_release(struct tcf_mirred *m, int bind) { if (m) { if (bind) m->tcf_bindcnt--; m->tcf_refcnt--; - if(!m->tcf_bindcnt && m->tcf_refcnt <= 0) { + if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) { list_del(&m->tcfm_list); if (m->tcfm_dev) dev_put(m->tcfm_dev); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 178a4bd..762b027 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -69,7 +69,7 @@ static int tcf_nat_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &nat_idx_gen, &nat_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); p = to_tcf_nat(pc); ret = ACT_P_CREATED; } else { diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 445bef7..50c7c06 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -70,7 +70,7 @@ static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &pedit_idx_gen, &pedit_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); p = to_pedit(pc); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { @@ -127,11 +127,9 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, int i, munged = 0; unsigned int off; - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { - return p->tcf_action; - } - } + if (skb_cloned(skb) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + return p->tcf_action; off = skb_network_offset(skb); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index e2f08b1..8a16307 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,8 @@ #include <net/act_api.h> #include <net/netlink.h> -#define L2T(p,L) qdisc_l2t((p)->tcfp_R_tab, L) -#define L2T_P(p,L) qdisc_l2t((p)->tcfp_P_tab, L) +#define L2T(p, L) qdisc_l2t((p)->tcfp_R_tab, L) +#define L2T_P(p, L) qdisc_l2t((p)->tcfp_P_tab, L) #define POL_TAB_MASK 15 static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1]; @@ -37,8 +37,7 @@ static struct tcf_hashinfo police_hash_info = { }; /* old policer structure from before tc actions */ -struct tc_police_compat -{ +struct tc_police_compat { u32 index; int action; u32 limit; @@ -139,7 +138,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_act_police_locate(struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { - unsigned h; + unsigned int h; int ret = 0, err; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tc_police *parm; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 7287cff..a34a22d 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -47,7 +47,7 @@ static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) - **/ + */ pr_info("simple: %s_%d\n", (char *)d->tcfd_defdata, d->tcf_bstats.packets); spin_unlock(&d->tcf_lock); @@ -125,7 +125,7 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, &simp_idx_gen, &simp_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); d = to_defact(pc); ret = alloc_defdata(d, defdata); @@ -149,7 +149,7 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, return ret; } -static inline int tcf_simp_cleanup(struct tc_action *a, int bind) +static int tcf_simp_cleanup(struct tc_action *a, int bind) { struct tcf_defact *d = a->priv; @@ -158,8 +158,8 @@ static inline int tcf_simp_cleanup(struct tc_action *a, int bind) return 0; } -static inline int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, - int bind, int ref) +static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_defact *d = a->priv; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 836f5fe..5f6f0c7 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -113,7 +113,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, &skbedit_idx_gen, &skbedit_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); d = to_skbedit(pc); ret = ACT_P_CREATED; @@ -144,7 +144,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, return ret; } -static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind) +static int tcf_skbedit_cleanup(struct tc_action *a, int bind) { struct tcf_skbedit *d = a->priv; @@ -153,8 +153,8 @@ static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind) return 0; } -static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, - int bind, int ref) +static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_skbedit *d = a->priv; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 5fd0c28..bb2c523 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -85,7 +85,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) int rc = -ENOENT; write_lock(&cls_mod_lock); - for (tp = &tcf_proto_base; (t=*tp) != NULL; tp = &t->next) + for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next) if (t == ops) break; @@ -111,7 +111,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) u32 first = TC_H_MAKE(0xC0000000U, 0U); if (tp) - first = tp->prio-1; + first = tp->prio - 1; return first; } @@ -149,7 +149,8 @@ replay: if (prio == 0) { /* If no priority is given, user wants we allocated it. */ - if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTFILTER || + !(n->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; prio = TC_H_MAKE(0x80000000U, 0U); } @@ -176,7 +177,8 @@ replay: } /* Is it classful? */ - if ((cops = q->ops->cl_ops) == NULL) + cops = q->ops->cl_ops; + if (!cops) return -EINVAL; if (cops->tcf_chain == NULL) @@ -196,10 +198,11 @@ replay: goto errout; /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; (tp=*back) != NULL; back = &tp->next) { + for (back = chain; (tp = *back) != NULL; back = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { - if (!nprio || (tp->protocol != protocol && protocol)) + if (!nprio || + (tp->protocol != protocol && protocol)) goto errout; } else tp = NULL; @@ -216,7 +219,8 @@ replay: goto errout; err = -ENOENT; - if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTFILTER || + !(n->nlmsg_flags & NLM_F_CREATE)) goto errout; @@ -420,7 +424,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) return skb->len; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return skb->len; if (!tcm->tcm_parent) @@ -429,7 +434,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); if (!q) goto out; - if ((cops = q->ops->cl_ops) == NULL) + cops = q->ops->cl_ops; + if (!cops) goto errout; if (cops->tcf_chain == NULL) goto errout; @@ -444,8 +450,9 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; - for (tp=*chain, t=0; tp; tp = tp->next, t++) { - if (t < s_t) continue; + for (tp = *chain, t = 0; tp; tp = tp->next, t++) { + if (t < s_t) + continue; if (TC_H_MAJ(tcm->tcm_info) && TC_H_MAJ(tcm->tcm_info) != tp->prio) continue; @@ -468,10 +475,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) arg.skb = skb; arg.cb = cb; arg.w.stop = 0; - arg.w.skip = cb->args[1]-1; + arg.w.skip = cb->args[1] - 1; arg.w.count = 0; tp->ops->walk(tp, &arg.w); - cb->args[1] = arg.w.count+1; + cb->args[1] = arg.w.count + 1; if (arg.w.stop) break; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index f23d915..8be8872 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -21,14 +21,12 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -struct basic_head -{ +struct basic_head { u32 hgenerator; struct list_head flist; }; -struct basic_filter -{ +struct basic_filter { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; @@ -92,8 +90,7 @@ static int basic_init(struct tcf_proto *tp) return 0; } -static inline void basic_delete_filter(struct tcf_proto *tp, - struct basic_filter *f) +static void basic_delete_filter(struct tcf_proto *tp, struct basic_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); @@ -135,9 +132,9 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { [TCA_BASIC_EMATCHES] = { .type = NLA_NESTED }, }; -static inline int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, - unsigned long base, struct nlattr **tb, - struct nlattr *est) +static int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, + unsigned long base, struct nlattr **tb, + struct nlattr *est) { int err = -EINVAL; struct tcf_exts e; @@ -203,7 +200,7 @@ static int basic_change(struct tcf_proto *tp, unsigned long base, u32 handle, } while (--i > 0 && basic_get(tp, head->hgenerator)); if (i <= 0) { - printk(KERN_ERR "Insufficient number of handles\n"); + pr_err("Insufficient number of handles\n"); goto errout; } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index d49c40f..32a3351 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -56,7 +56,8 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, { struct cgroup_cls_state *cs; - if (!(cs = kzalloc(sizeof(*cs), GFP_KERNEL))) + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) return ERR_PTR(-ENOMEM); if (cgrp->parent) @@ -94,8 +95,7 @@ static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); } -struct cls_cgroup_head -{ +struct cls_cgroup_head { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; @@ -166,7 +166,7 @@ static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { - struct nlattr *tb[TCA_CGROUP_MAX+1]; + struct nlattr *tb[TCA_CGROUP_MAX + 1]; struct cls_cgroup_head *head = tp->root; struct tcf_ematch_tree t; struct tcf_exts e; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 5b271a1..8ec0139 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -121,7 +121,7 @@ static u32 flow_get_proto_src(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -276,7 +276,7 @@ fallback: static u32 flow_get_rtclassid(const struct sk_buff *skb) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (skb_dst(skb)) return skb_dst(skb)->tclassid; #endif diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 93b0a7b..26e7bc4 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -31,14 +31,12 @@ #define HTSIZE (PAGE_SIZE/sizeof(struct fw_filter *)) -struct fw_head -{ +struct fw_head { struct fw_filter *ht[HTSIZE]; u32 mask; }; -struct fw_filter -{ +struct fw_filter { struct fw_filter *next; u32 id; struct tcf_result res; @@ -53,7 +51,7 @@ static const struct tcf_ext_map fw_ext_map = { .police = TCA_FW_POLICE }; -static __inline__ int fw_hash(u32 handle) +static inline int fw_hash(u32 handle) { if (HTSIZE == 4096) return ((handle >> 24) & 0xFFF) ^ @@ -82,14 +80,14 @@ static __inline__ int fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f; int r; u32 id = skb->mark; if (head != NULL) { id &= head->mask; - for (f=head->ht[fw_hash(id)]; f; f=f->next) { + for (f = head->ht[fw_hash(id)]; f; f = f->next) { if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND @@ -105,7 +103,8 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, } } else { /* old method */ - if (id && (TC_H_MAJ(id) == 0 || !(TC_H_MAJ(id^tp->q->handle)))) { + if (id && (TC_H_MAJ(id) == 0 || + !(TC_H_MAJ(id ^ tp->q->handle)))) { res->classid = id; res->class = 0; return 0; @@ -117,13 +116,13 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f; if (head == NULL) return 0; - for (f=head->ht[fw_hash(handle)]; f; f=f->next) { + for (f = head->ht[fw_hash(handle)]; f; f = f->next) { if (f->id == handle) return (unsigned long)f; } @@ -139,8 +138,7 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static inline void -fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) +static void fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); @@ -156,8 +154,8 @@ static void fw_destroy(struct tcf_proto *tp) if (head == NULL) return; - for (h=0; h<HTSIZE; h++) { - while ((f=head->ht[h]) != NULL) { + for (h = 0; h < HTSIZE; h++) { + while ((f = head->ht[h]) != NULL) { head->ht[h] = f->next; fw_delete_filter(tp, f); } @@ -167,14 +165,14 @@ static void fw_destroy(struct tcf_proto *tp) static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = (struct fw_head*)tp->root; - struct fw_filter *f = (struct fw_filter*)arg; + struct fw_head *head = (struct fw_head *)tp->root; + struct fw_filter *f = (struct fw_filter *)arg; struct fw_filter **fp; if (head == NULL || f == NULL) goto out; - for (fp=&head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { + for (fp = &head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -240,7 +238,7 @@ static int fw_change(struct tcf_proto *tp, unsigned long base, struct nlattr **tca, unsigned long *arg) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -302,7 +300,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; int h; if (head == NULL) @@ -332,7 +330,7 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct fw_head *head = (struct fw_head *)tp->root; - struct fw_filter *f = (struct fw_filter*)fh; + struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 694dcd8..d580cdf 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -23,34 +23,30 @@ #include <net/pkt_cls.h> /* - 1. For now we assume that route tags < 256. - It allows to use direct table lookups, instead of hash tables. - 2. For now we assume that "from TAG" and "fromdev DEV" statements - are mutually exclusive. - 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" + * 1. For now we assume that route tags < 256. + * It allows to use direct table lookups, instead of hash tables. + * 2. For now we assume that "from TAG" and "fromdev DEV" statements + * are mutually exclusive. + * 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" */ -struct route4_fastmap -{ +struct route4_fastmap { struct route4_filter *filter; u32 id; int iif; }; -struct route4_head -{ +struct route4_head { struct route4_fastmap fastmap[16]; - struct route4_bucket *table[256+1]; + struct route4_bucket *table[256 + 1]; }; -struct route4_bucket -{ +struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ - struct route4_filter *ht[16+16+1]; + struct route4_filter *ht[16 + 16 + 1]; }; -struct route4_filter -{ +struct route4_filter { struct route4_filter *next; u32 id; int iif; @@ -61,20 +57,20 @@ struct route4_filter struct route4_bucket *bkt; }; -#define ROUTE4_FAILURE ((struct route4_filter*)(-1L)) +#define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) static const struct tcf_ext_map route_ext_map = { .police = TCA_ROUTE4_POLICE, .action = TCA_ROUTE4_ACT }; -static __inline__ int route4_fastmap_hash(u32 id, int iif) +static inline int route4_fastmap_hash(u32 id, int iif) { - return id&0xF; + return id & 0xF; } -static inline -void route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) +static void +route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) { spinlock_t *root_lock = qdisc_root_sleeping_lock(q); @@ -83,32 +79,33 @@ void route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) spin_unlock_bh(root_lock); } -static inline void +static void route4_set_fastmap(struct route4_head *head, u32 id, int iif, struct route4_filter *f) { int h = route4_fastmap_hash(id, iif); + head->fastmap[h].id = id; head->fastmap[h].iif = iif; head->fastmap[h].filter = f; } -static __inline__ int route4_hash_to(u32 id) +static inline int route4_hash_to(u32 id) { - return id&0xFF; + return id & 0xFF; } -static __inline__ int route4_hash_from(u32 id) +static inline int route4_hash_from(u32 id) { - return (id>>16)&0xF; + return (id >> 16) & 0xF; } -static __inline__ int route4_hash_iif(int iif) +static inline int route4_hash_iif(int iif) { - return 16 + ((iif>>16)&0xF); + return 16 + ((iif >> 16) & 0xF); } -static __inline__ int route4_hash_wild(void) +static inline int route4_hash_wild(void) { return 32; } @@ -131,21 +128,22 @@ static __inline__ int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = (struct route4_head*)tp->root; + struct route4_head *head = (struct route4_head *)tp->root; struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; u32 id, h; int iif, dont_cache = 0; - if ((dst = skb_dst(skb)) == NULL) + dst = skb_dst(skb); + if (!dst) goto failure; id = dst->tclassid; if (head == NULL) goto old_method; - iif = ((struct rtable*)dst)->fl.iif; + iif = ((struct rtable *)dst)->fl.iif; h = route4_fastmap_hash(id, iif); if (id == head->fastmap[h].id && @@ -161,7 +159,8 @@ static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, h = route4_hash_to(id); restart: - if ((b = head->table[h]) != NULL) { + b = head->table[h]; + if (b) { for (f = b->ht[route4_hash_from(id)]; f; f = f->next) if (f->id == id) ROUTE4_APPLY_RESULT(); @@ -197,8 +196,9 @@ old_method: static inline u32 to_hash(u32 id) { - u32 h = id&0xFF; - if (id&0x8000) + u32 h = id & 0xFF; + + if (id & 0x8000) h += 256; return h; } @@ -211,17 +211,17 @@ static inline u32 from_hash(u32 id) if (!(id & 0x8000)) { if (id > 255) return 256; - return id&0xF; + return id & 0xF; } - return 16 + (id&0xF); + return 16 + (id & 0xF); } static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = (struct route4_head*)tp->root; + struct route4_head *head = (struct route4_head *)tp->root; struct route4_bucket *b; struct route4_filter *f; - unsigned h1, h2; + unsigned int h1, h2; if (!head) return 0; @@ -230,11 +230,12 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) if (h1 > 256) return 0; - h2 = from_hash(handle>>16); + h2 = from_hash(handle >> 16); if (h2 > 32) return 0; - if ((b = head->table[h1]) != NULL) { + b = head->table[h1]; + if (b) { for (f = b->ht[h2]; f; f = f->next) if (f->handle == handle) return (unsigned long)f; @@ -251,7 +252,7 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static inline void +static void route4_delete_filter(struct tcf_proto *tp, struct route4_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -267,11 +268,12 @@ static void route4_destroy(struct tcf_proto *tp) if (head == NULL) return; - for (h1=0; h1<=256; h1++) { + for (h1 = 0; h1 <= 256; h1++) { struct route4_bucket *b; - if ((b = head->table[h1]) != NULL) { - for (h2=0; h2<=32; h2++) { + b = head->table[h1]; + if (b) { + for (h2 = 0; h2 <= 32; h2++) { struct route4_filter *f; while ((f = b->ht[h2]) != NULL) { @@ -287,9 +289,9 @@ static void route4_destroy(struct tcf_proto *tp) static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = (struct route4_head*)tp->root; - struct route4_filter **fp, *f = (struct route4_filter*)arg; - unsigned h = 0; + struct route4_head *head = (struct route4_head *)tp->root; + struct route4_filter **fp, *f = (struct route4_filter *)arg; + unsigned int h = 0; struct route4_bucket *b; int i; @@ -299,7 +301,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) h = f->handle; b = f->bkt; - for (fp = &b->ht[from_hash(h>>16)]; *fp; fp = &(*fp)->next) { + for (fp = &b->ht[from_hash(h >> 16)]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -310,7 +312,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) /* Strip tree */ - for (i=0; i<=32; i++) + for (i = 0; i <= 32; i++) if (b->ht[i]) return 0; @@ -380,7 +382,8 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, } h1 = to_hash(nhandle); - if ((b = head->table[h1]) == NULL) { + b = head->table[h1]; + if (!b) { err = -ENOBUFS; b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) @@ -391,6 +394,7 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, tcf_tree_unlock(tp); } else { unsigned int h2 = from_hash(nhandle >> 16); + err = -EEXIST; for (fp = b->ht[h2]; fp; fp = fp->next) if (fp->handle == f->handle) @@ -444,7 +448,8 @@ static int route4_change(struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - if ((f = (struct route4_filter*)*arg) != NULL) { + f = (struct route4_filter *)*arg; + if (f) { if (f->handle != handle && handle) return -EINVAL; @@ -481,7 +486,7 @@ static int route4_change(struct tcf_proto *tp, unsigned long base, reinsert: h = from_hash(f->handle >> 16); - for (fp = &f->bkt->ht[h]; (f1=*fp) != NULL; fp = &f1->next) + for (fp = &f->bkt->ht[h]; (f1 = *fp) != NULL; fp = &f1->next) if (f->handle < f1->handle) break; @@ -492,7 +497,8 @@ reinsert: if (old_handle && f->handle != old_handle) { th = to_hash(old_handle); h = from_hash(old_handle >> 16); - if ((b = head->table[th]) != NULL) { + b = head->table[th]; + if (b) { for (fp = &b->ht[h]; *fp; fp = &(*fp)->next) { if (*fp == f) { *fp = f->next; @@ -515,7 +521,7 @@ errout: static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct route4_head *head = tp->root; - unsigned h, h1; + unsigned int h, h1; if (head == NULL) arg->stop = 1; @@ -549,7 +555,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int route4_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct route4_filter *f = (struct route4_filter*)fh; + struct route4_filter *f = (struct route4_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; u32 id; @@ -563,15 +569,15 @@ static int route4_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (!(f->handle&0x8000)) { - id = f->id&0xFF; + if (!(f->handle & 0x8000)) { + id = f->id & 0xFF; NLA_PUT_U32(skb, TCA_ROUTE4_TO, id); } - if (f->handle&0x80000000) { - if ((f->handle>>16) != 0xFFFF) + if (f->handle & 0x80000000) { + if ((f->handle >> 16) != 0xFFFF) NLA_PUT_U32(skb, TCA_ROUTE4_IIF, f->iif); } else { - id = f->id>>16; + id = f->id >> 16; NLA_PUT_U32(skb, TCA_ROUTE4_FROM, id); } if (f->res.classid) diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 425a179..402c44b 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -66,28 +66,25 @@ powerful classification engine. */ -struct rsvp_head -{ +struct rsvp_head { u32 tmap[256/32]; u32 hgenerator; u8 tgenerator; struct rsvp_session *ht[256]; }; -struct rsvp_session -{ +struct rsvp_session { struct rsvp_session *next; __be32 dst[RSVP_DST_LEN]; struct tc_rsvp_gpi dpi; u8 protocol; u8 tunnelid; /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter *ht[16+1]; + struct rsvp_filter *ht[16 + 1]; }; -struct rsvp_filter -{ +struct rsvp_filter { struct rsvp_filter *next; __be32 src[RSVP_DST_LEN]; struct tc_rsvp_gpi spi; @@ -100,17 +97,19 @@ struct rsvp_filter struct rsvp_session *sess; }; -static __inline__ unsigned hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) +static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) { - unsigned h = (__force __u32)dst[RSVP_DST_LEN-1]; + unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; + h ^= h>>16; h ^= h>>8; return (h ^ protocol ^ tunnelid) & 0xFF; } -static __inline__ unsigned hash_src(__be32 *src) +static inline unsigned int hash_src(__be32 *src) { - unsigned h = (__force __u32)src[RSVP_DST_LEN-1]; + unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; + h ^= h>>16; h ^= h>>8; h ^= h>>4; @@ -134,10 +133,10 @@ static struct tcf_ext_map rsvp_ext_map = { static int rsvp_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct rsvp_session **sht = ((struct rsvp_head*)tp->root)->ht; + struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; struct rsvp_session *s; struct rsvp_filter *f; - unsigned h1, h2; + unsigned int h1, h2; __be32 *dst, *src; u8 protocol; u8 tunnelid = 0; @@ -162,13 +161,13 @@ restart: src = &nhptr->saddr.s6_addr32[0]; dst = &nhptr->daddr.s6_addr32[0]; protocol = nhptr->nexthdr; - xprt = ((u8*)nhptr) + sizeof(struct ipv6hdr); + xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); #else src = &nhptr->saddr; dst = &nhptr->daddr; protocol = nhptr->protocol; - xprt = ((u8*)nhptr) + (nhptr->ihl<<2); - if (nhptr->frag_off & htons(IP_MF|IP_OFFSET)) + xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); + if (nhptr->frag_off & htons(IP_MF | IP_OFFSET)) return -1; #endif @@ -176,10 +175,10 @@ restart: h2 = hash_src(src); for (s = sht[h1]; s; s = s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && + if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && protocol == s->protocol && !(s->dpi.mask & - (*(u32*)(xprt+s->dpi.offset)^s->dpi.key)) && + (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && #if RSVP_DST_LEN == 4 dst[0] == s->dst[0] && dst[1] == s->dst[1] && @@ -188,8 +187,8 @@ restart: tunnelid == s->tunnelid) { for (f = s->ht[h2]; f; f = f->next) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN-1] && - !(f->spi.mask & (*(u32*)(xprt+f->spi.offset)^f->spi.key)) + if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && + !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) #if RSVP_DST_LEN == 4 && src[0] == f->src[0] && @@ -205,7 +204,7 @@ matched: return 0; tunnelid = f->res.classid; - nhptr = (void*)(xprt + f->tunnelhdr - sizeof(*nhptr)); + nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); goto restart; } } @@ -224,11 +223,11 @@ matched: static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) { - struct rsvp_session **sht = ((struct rsvp_head*)tp->root)->ht; + struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; struct rsvp_session *s; struct rsvp_filter *f; - unsigned h1 = handle&0xFF; - unsigned h2 = (handle>>8)&0xFF; + unsigned int h1 = handle & 0xFF; + unsigned int h2 = (handle >> 8) & 0xFF; if (h2 > 16) return 0; @@ -258,7 +257,7 @@ static int rsvp_init(struct tcf_proto *tp) return -ENOBUFS; } -static inline void +static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -277,13 +276,13 @@ static void rsvp_destroy(struct tcf_proto *tp) sht = data->ht; - for (h1=0; h1<256; h1++) { + for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; while ((s = sht[h1]) != NULL) { sht[h1] = s->next; - for (h2=0; h2<=16; h2++) { + for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; while ((f = s->ht[h2]) != NULL) { @@ -299,13 +298,13 @@ static void rsvp_destroy(struct tcf_proto *tp) static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) { - struct rsvp_filter **fp, *f = (struct rsvp_filter*)arg; - unsigned h = f->handle; + struct rsvp_filter **fp, *f = (struct rsvp_filter *)arg; + unsigned int h = f->handle; struct rsvp_session **sp; struct rsvp_session *s = f->sess; int i; - for (fp = &s->ht[(h>>8)&0xFF]; *fp; fp = &(*fp)->next) { + for (fp = &s->ht[(h >> 8) & 0xFF]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -314,12 +313,12 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) /* Strip tree */ - for (i=0; i<=16; i++) + for (i = 0; i <= 16; i++) if (s->ht[i]) return 0; /* OK, session has no flows */ - for (sp = &((struct rsvp_head*)tp->root)->ht[h&0xFF]; + for (sp = &((struct rsvp_head *)tp->root)->ht[h & 0xFF]; *sp; sp = &(*sp)->next) { if (*sp == s) { tcf_tree_lock(tp); @@ -337,13 +336,14 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) return 0; } -static unsigned gen_handle(struct tcf_proto *tp, unsigned salt) +static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) { struct rsvp_head *data = tp->root; int i = 0xFFFF; while (i-- > 0) { u32 h; + if ((data->hgenerator += 0x10000) == 0) data->hgenerator = 0x10000; h = data->hgenerator|salt; @@ -355,10 +355,10 @@ static unsigned gen_handle(struct tcf_proto *tp, unsigned salt) static int tunnel_bts(struct rsvp_head *data) { - int n = data->tgenerator>>5; - u32 b = 1<<(data->tgenerator&0x1F); + int n = data->tgenerator >> 5; + u32 b = 1 << (data->tgenerator & 0x1F); - if (data->tmap[n]&b) + if (data->tmap[n] & b) return 0; data->tmap[n] |= b; return 1; @@ -372,10 +372,10 @@ static void tunnel_recycle(struct rsvp_head *data) memset(tmap, 0, sizeof(tmap)); - for (h1=0; h1<256; h1++) { + for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; for (s = sht[h1]; s; s = s->next) { - for (h2=0; h2<=16; h2++) { + for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; for (f = s->ht[h2]; f; f = f->next) { @@ -395,8 +395,8 @@ static u32 gen_tunnel(struct rsvp_head *data) { int i, k; - for (k=0; k<2; k++) { - for (i=255; i>0; i--) { + for (k = 0; k < 2; k++) { + for (i = 255; i > 0; i--) { if (++data->tgenerator == 0) data->tgenerator = 1; if (tunnel_bts(data)) @@ -428,7 +428,7 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, struct nlattr *opt = tca[TCA_OPTIONS-1]; struct nlattr *tb[TCA_RSVP_MAX + 1]; struct tcf_exts e; - unsigned h1, h2; + unsigned int h1, h2; __be32 *dst; int err; @@ -443,7 +443,8 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - if ((f = (struct rsvp_filter*)*arg) != NULL) { + f = (struct rsvp_filter *)*arg; + if (f) { /* Node exists: adjust only classid */ if (f->handle != handle && handle) @@ -500,7 +501,7 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, goto errout; } - for (sp = &data->ht[h1]; (s=*sp) != NULL; sp = &s->next) { + for (sp = &data->ht[h1]; (s = *sp) != NULL; sp = &s->next) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && pinfo && pinfo->protocol == s->protocol && memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && @@ -523,7 +524,7 @@ insert: tcf_exts_change(tp, &f->exts, &e); for (fp = &s->ht[h2]; *fp; fp = &(*fp)->next) - if (((*fp)->spi.mask&f->spi.mask) != f->spi.mask) + if (((*fp)->spi.mask & f->spi.mask) != f->spi.mask) break; f->next = *fp; wmb(); @@ -567,7 +568,7 @@ errout2: static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct rsvp_head *head = tp->root; - unsigned h, h1; + unsigned int h, h1; if (arg->stop) return; @@ -598,7 +599,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct rsvp_filter *f = (struct rsvp_filter*)fh; + struct rsvp_filter *f = (struct rsvp_filter *)fh; struct rsvp_session *s; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -624,7 +625,7 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, NLA_PUT(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo); if (f->res.classid) NLA_PUT_U32(skb, TCA_RSVP_CLASSID, f->res.classid); - if (((f->handle>>8)&0xFF) != 16) + if (((f->handle >> 8) & 0xFF) != 16) NLA_PUT(skb, TCA_RSVP_SRC, sizeof(f->src), f->src); if (tcf_exts_dump(skb, &f->exts, &rsvp_ext_map) < 0) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 20ef330..36667fa 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -249,7 +249,7 @@ tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, * of the hashing index is below the threshold. */ if ((cp.mask >> cp.shift) < PERFECT_HASH_THRESHOLD) - cp.hash = (cp.mask >> cp.shift)+1; + cp.hash = (cp.mask >> cp.shift) + 1; else cp.hash = DEFAULT_HASH_SIZE; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b0c2a82..966920c 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -42,8 +42,7 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -struct tc_u_knode -{ +struct tc_u_knode { struct tc_u_knode *next; u32 handle; struct tc_u_hnode *ht_up; @@ -63,19 +62,17 @@ struct tc_u_knode struct tc_u32_sel sel; }; -struct tc_u_hnode -{ +struct tc_u_hnode { struct tc_u_hnode *next; u32 handle; u32 prio; struct tc_u_common *tp_c; int refcnt; - unsigned divisor; + unsigned int divisor; struct tc_u_knode *ht[1]; }; -struct tc_u_common -{ +struct tc_u_common { struct tc_u_hnode *hlist; struct Qdisc *q; int refcnt; @@ -87,9 +84,11 @@ static const struct tcf_ext_map u32_ext_map = { .police = TCA_U32_POLICE }; -static __inline__ unsigned u32_hash_fold(__be32 key, struct tc_u32_sel *sel, u8 fshift) +static inline unsigned int u32_hash_fold(__be32 key, + const struct tc_u32_sel *sel, + u8 fshift) { - unsigned h = ntohl(key & sel->hmask)>>fshift; + unsigned int h = ntohl(key & sel->hmask) >> fshift; return h; } @@ -101,7 +100,7 @@ static int u32_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_re unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = (struct tc_u_hnode*)tp->root; + struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root; unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -120,7 +119,7 @@ next_knode: struct tc_u32_key *key = n->sel.keys; #ifdef CONFIG_CLS_U32_PERF - n->pf->rcnt +=1; + n->pf->rcnt += 1; j = 0; #endif @@ -133,7 +132,7 @@ next_knode: } #endif - for (i = n->sel.nkeys; i>0; i--, key++) { + for (i = n->sel.nkeys; i > 0; i--, key++) { int toff = off + key->off + (off2 & key->offmask); __be32 *data, _data; @@ -148,13 +147,13 @@ next_knode: goto next_knode; } #ifdef CONFIG_CLS_U32_PERF - n->pf->kcnts[j] +=1; + n->pf->kcnts[j] += 1; j++; #endif } if (n->ht_down == NULL) { check_terminal: - if (n->sel.flags&TC_U32_TERMINAL) { + if (n->sel.flags & TC_U32_TERMINAL) { *res = n->res; #ifdef CONFIG_NET_CLS_IND @@ -164,7 +163,7 @@ check_terminal: } #endif #ifdef CONFIG_CLS_U32_PERF - n->pf->rhit +=1; + n->pf->rhit += 1; #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { @@ -197,10 +196,10 @@ check_terminal: sel = ht->divisor & u32_hash_fold(*data, &n->sel, n->fshift); } - if (!(n->sel.flags&(TC_U32_VAROFFSET|TC_U32_OFFSET|TC_U32_EAT))) + if (!(n->sel.flags & (TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT))) goto next_ht; - if (n->sel.flags&(TC_U32_OFFSET|TC_U32_VAROFFSET)) { + if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags & TC_U32_VAROFFSET) { __be16 *data, _data; @@ -215,7 +214,7 @@ check_terminal: } off2 &= ~3; } - if (n->sel.flags&TC_U32_EAT) { + if (n->sel.flags & TC_U32_EAT) { off += off2; off2 = 0; } @@ -236,11 +235,11 @@ out: deadloop: if (net_ratelimit()) - printk(KERN_WARNING "cls_u32: dead loop\n"); + pr_warning("cls_u32: dead loop\n"); return -1; } -static __inline__ struct tc_u_hnode * +static struct tc_u_hnode * u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) { struct tc_u_hnode *ht; @@ -252,10 +251,10 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) return ht; } -static __inline__ struct tc_u_knode * +static struct tc_u_knode * u32_lookup_key(struct tc_u_hnode *ht, u32 handle) { - unsigned sel; + unsigned int sel; struct tc_u_knode *n = NULL; sel = TC_U32_HASH(handle); @@ -300,7 +299,7 @@ static u32 gen_new_htid(struct tc_u_common *tp_c) do { if (++tp_c->hgenerator == 0x7FF) tp_c->hgenerator = 1; - } while (--i>0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); + } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; } @@ -378,9 +377,9 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key) static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) { struct tc_u_knode *n; - unsigned h; + unsigned int h; - for (h=0; h<=ht->divisor; h++) { + for (h = 0; h <= ht->divisor; h++) { while ((n = ht->ht[h]) != NULL) { ht->ht[h] = n->next; @@ -446,13 +445,13 @@ static void u32_destroy(struct tcf_proto *tp) static int u32_delete(struct tcf_proto *tp, unsigned long arg) { - struct tc_u_hnode *ht = (struct tc_u_hnode*)arg; + struct tc_u_hnode *ht = (struct tc_u_hnode *)arg; if (ht == NULL) return 0; if (TC_U32_KEY(ht->handle)) - return u32_delete_key(tp, (struct tc_u_knode*)ht); + return u32_delete_key(tp, (struct tc_u_knode *)ht); if (tp->root == ht) return -EINVAL; @@ -470,14 +469,14 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) { struct tc_u_knode *n; - unsigned i = 0x7FF; + unsigned int i = 0x7FF; - for (n=ht->ht[TC_U32_HASH(handle)]; n; n = n->next) + for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next) if (i < TC_U32_NODE(n->handle)) i = TC_U32_NODE(n->handle); i++; - return handle|(i>0xFFF ? 0xFFF : i); + return handle | (i > 0xFFF ? 0xFFF : i); } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -566,7 +565,8 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (err < 0) return err; - if ((n = (struct tc_u_knode*)*arg) != NULL) { + n = (struct tc_u_knode *)*arg; + if (n) { if (TC_U32_KEY(n->handle) == 0) return -EINVAL; @@ -574,7 +574,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, } if (tb[TCA_U32_DIVISOR]) { - unsigned divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); + unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); if (--divisor > 0x100) return -EINVAL; @@ -585,7 +585,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (handle == 0) return -ENOMEM; } - ht = kzalloc(sizeof(*ht) + divisor*sizeof(void*), GFP_KERNEL); + ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; ht->tp_c = tp_c; @@ -683,7 +683,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; struct tc_u_knode *n; - unsigned h; + unsigned int h; if (arg->stop) return; @@ -717,7 +717,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int u32_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tc_u_knode *n = (struct tc_u_knode*)fh; + struct tc_u_knode *n = (struct tc_u_knode *)fh; struct nlattr *nest; if (n == NULL) @@ -730,8 +730,9 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; if (TC_U32_KEY(n->handle) == 0) { - struct tc_u_hnode *ht = (struct tc_u_hnode*)fh; - u32 divisor = ht->divisor+1; + struct tc_u_hnode *ht = (struct tc_u_hnode *)fh; + u32 divisor = ht->divisor + 1; + NLA_PUT_U32(skb, TCA_U32_DIVISOR, divisor); } else { NLA_PUT(skb, TCA_U32_SEL, @@ -755,7 +756,7 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if(strlen(n->indev)) + if (strlen(n->indev)) NLA_PUT_STRING(skb, TCA_U32_INDEV, n->indev); #endif #ifdef CONFIG_CLS_U32_PERF diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index bc45039..1c8360a 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -33,40 +33,41 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, return 0; switch (cmp->align) { - case TCF_EM_ALIGN_U8: - val = *ptr; - break; + case TCF_EM_ALIGN_U8: + val = *ptr; + break; - case TCF_EM_ALIGN_U16: - val = get_unaligned_be16(ptr); + case TCF_EM_ALIGN_U16: + val = get_unaligned_be16(ptr); - if (cmp_needs_transformation(cmp)) - val = be16_to_cpu(val); - break; + if (cmp_needs_transformation(cmp)) + val = be16_to_cpu(val); + break; - case TCF_EM_ALIGN_U32: - /* Worth checking boundries? The branching seems - * to get worse. Visit again. */ - val = get_unaligned_be32(ptr); + case TCF_EM_ALIGN_U32: + /* Worth checking boundries? The branching seems + * to get worse. Visit again. + */ + val = get_unaligned_be32(ptr); - if (cmp_needs_transformation(cmp)) - val = be32_to_cpu(val); - break; + if (cmp_needs_transformation(cmp)) + val = be32_to_cpu(val); + break; - default: - return 0; + default: + return 0; } if (cmp->mask) val &= cmp->mask; switch (cmp->opnd) { - case TCF_EM_OPND_EQ: - return val == cmp->val; - case TCF_EM_OPND_LT: - return val < cmp->val; - case TCF_EM_OPND_GT: - return val > cmp->val; + case TCF_EM_OPND_EQ: + return val == cmp->val; + case TCF_EM_OPND_LT: + return val < cmp->val; + case TCF_EM_OPND_GT: + return val > cmp->val; } return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 34da5e2..a889d09 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -73,21 +73,18 @@ #include <net/pkt_cls.h> #include <net/sock.h> -struct meta_obj -{ +struct meta_obj { unsigned long value; unsigned int len; }; -struct meta_value -{ +struct meta_value { struct tcf_meta_val hdr; unsigned long val; unsigned int len; }; -struct meta_match -{ +struct meta_match { struct meta_value lvalue; struct meta_value rvalue; }; @@ -255,7 +252,7 @@ META_COLLECTOR(int_rtclassid) if (unlikely(skb_dst(skb) == NULL)) *err = -1; else -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID dst->value = skb_dst(skb)->tclassid; #else dst->value = 0; @@ -483,8 +480,7 @@ META_COLLECTOR(int_sk_write_pend) * Meta value collectors assignment table **************************************************************************/ -struct meta_ops -{ +struct meta_ops { void (*get)(struct sk_buff *, struct tcf_pkt_info *, struct meta_value *, struct meta_obj *, int *); }; @@ -494,7 +490,7 @@ struct meta_ops /* Meta value operations table listing all meta value collectors and * assigns them to a type and meta id. */ -static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { +static struct meta_ops __meta_ops[TCF_META_TYPE_MAX + 1][TCF_META_ID_MAX + 1] = { [TCF_META_TYPE_VAR] = { [META_ID(DEV)] = META_FUNC(var_dev), [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), @@ -550,7 +546,7 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { } }; -static inline struct meta_ops * meta_ops(struct meta_value *val) +static inline struct meta_ops *meta_ops(struct meta_value *val) { return &__meta_ops[meta_type(val)][meta_id(val)]; } @@ -649,9 +645,8 @@ static int meta_int_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { if (v->len == sizeof(unsigned long)) NLA_PUT(skb, tlv, sizeof(unsigned long), &v->val); - else if (v->len == sizeof(u32)) { + else if (v->len == sizeof(u32)) NLA_PUT_U32(skb, tlv, v->val); - } return 0; @@ -663,8 +658,7 @@ nla_put_failure: * Type specific operations table **************************************************************************/ -struct meta_type_ops -{ +struct meta_type_ops { void (*destroy)(struct meta_value *); int (*compare)(struct meta_obj *, struct meta_obj *); int (*change)(struct meta_value *, struct nlattr *); @@ -672,7 +666,7 @@ struct meta_type_ops int (*dump)(struct sk_buff *, struct meta_value *, int); }; -static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX+1] = { +static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX + 1] = { [TCF_META_TYPE_VAR] = { .destroy = meta_var_destroy, .compare = meta_var_compare, @@ -688,7 +682,7 @@ static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX+1] = { } }; -static inline struct meta_type_ops * meta_type_ops(struct meta_value *v) +static inline struct meta_type_ops *meta_type_ops(struct meta_value *v) { return &__meta_type_ops[meta_type(v)]; } @@ -713,7 +707,7 @@ static int meta_get(struct sk_buff *skb, struct tcf_pkt_info *info, return err; if (meta_type_ops(v)->apply_extras) - meta_type_ops(v)->apply_extras(v, dst); + meta_type_ops(v)->apply_extras(v, dst); return 0; } @@ -732,12 +726,12 @@ static int em_meta_match(struct sk_buff *skb, struct tcf_ematch *m, r = meta_type_ops(&meta->lvalue)->compare(&l_value, &r_value); switch (meta->lvalue.hdr.op) { - case TCF_EM_OPND_EQ: - return !r; - case TCF_EM_OPND_LT: - return r < 0; - case TCF_EM_OPND_GT: - return r > 0; + case TCF_EM_OPND_EQ: + return !r; + case TCF_EM_OPND_LT: + return r < 0; + case TCF_EM_OPND_GT: + return r > 0; } return 0; @@ -771,7 +765,7 @@ static inline int meta_change_data(struct meta_value *dst, struct nlattr *nla) static inline int meta_is_supported(struct meta_value *val) { - return (!meta_id(val) || meta_ops(val)->get); + return !meta_id(val) || meta_ops(val)->get; } static const struct nla_policy meta_policy[TCA_EM_META_MAX + 1] = { diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index 1a4176a..a3bed07 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -18,8 +18,7 @@ #include <linux/tc_ematch/tc_em_nbyte.h> #include <net/pkt_cls.h> -struct nbyte_data -{ +struct nbyte_data { struct tcf_em_nbyte hdr; char pattern[0]; }; diff --git a/net/sched/em_text.c b/net/sched/em_text.c index ea8f566..15d353d 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -19,8 +19,7 @@ #include <linux/tc_ematch/tc_em_text.h> #include <net/pkt_cls.h> -struct text_match -{ +struct text_match { u16 from_offset; u16 to_offset; u8 from_layer; diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 953f147..797bdb8 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -35,7 +35,7 @@ static int em_u32_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, sizeof(u32))) return 0; - return !(((*(__be32*) ptr) ^ key->val) & key->mask); + return !(((*(__be32 *) ptr) ^ key->val) & key->mask); } static struct tcf_ematch_ops em_u32_ops = { diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 5e37da9..88d93eb 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -93,7 +93,7 @@ static LIST_HEAD(ematch_ops); static DEFINE_RWLOCK(ematch_mod_lock); -static inline struct tcf_ematch_ops * tcf_em_lookup(u16 kind) +static struct tcf_ematch_ops *tcf_em_lookup(u16 kind) { struct tcf_ematch_ops *e = NULL; @@ -163,8 +163,8 @@ void tcf_em_unregister(struct tcf_ematch_ops *ops) } EXPORT_SYMBOL(tcf_em_unregister); -static inline struct tcf_ematch * tcf_em_get_match(struct tcf_ematch_tree *tree, - int index) +static inline struct tcf_ematch *tcf_em_get_match(struct tcf_ematch_tree *tree, + int index) { return &tree->matches[index]; } @@ -184,7 +184,8 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em_hdr->kind == TCF_EM_CONTAINER) { /* Special ematch called "container", carries an index - * referencing an external ematch sequence. */ + * referencing an external ematch sequence. + */ u32 ref; if (data_len < sizeof(ref)) @@ -195,7 +196,8 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; /* We do not allow backward jumps to avoid loops and jumps - * to our own position are of course illegal. */ + * to our own position are of course illegal. + */ if (ref <= idx) goto errout; @@ -208,7 +210,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * which automatically releases the reference again, therefore * the module MUST not be given back under any circumstances * here. Be aware, the destroy function assumes that the - * module is held if the ops field is non zero. */ + * module is held if the ops field is non zero. + */ em->ops = tcf_em_lookup(em_hdr->kind); if (em->ops == NULL) { @@ -221,7 +224,8 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em->ops) { /* We dropped the RTNL mutex in order to * perform the module load. Tell the caller - * to replay the request. */ + * to replay the request. + */ module_put(em->ops->owner); err = -EAGAIN; } @@ -230,7 +234,8 @@ static int tcf_em_validate(struct tcf_proto *tp, } /* ematch module provides expected length of data, so we - * can do a basic sanity check. */ + * can do a basic sanity check. + */ if (em->ops->datalen && data_len < em->ops->datalen) goto errout; @@ -246,7 +251,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * TCF_EM_SIMPLE may be specified stating that the * data only consists of a u32 integer and the module * does not expected a memory reference but rather - * the value carried. */ + * the value carried. + */ if (em_hdr->flags & TCF_EM_SIMPLE) { if (data_len < sizeof(u32)) goto errout; @@ -334,7 +340,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, * The array of rt attributes is parsed in the order as they are * provided, their type must be incremental from 1 to n. Even * if it does not serve any real purpose, a failure of sticking - * to this policy will result in parsing failure. */ + * to this policy will result in parsing failure. + */ for (idx = 0; nla_ok(rt_match, list_len); idx++) { err = -EINVAL; @@ -359,7 +366,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, /* Check if the number of matches provided by userspace actually * complies with the array of matches. The number was used for * the validation of references and a mismatch could lead to - * undefined references during the matching process. */ + * undefined references during the matching process. + */ if (idx != tree_hdr->nmatches) { err = -EINVAL; goto errout_abort; @@ -449,7 +457,7 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) .flags = em->flags }; - NLA_PUT(skb, i+1, sizeof(em_hdr), &em_hdr); + NLA_PUT(skb, i + 1, sizeof(em_hdr), &em_hdr); if (em->ops && em->ops->dump) { if (em->ops->dump(skb, em) < 0) @@ -478,6 +486,7 @@ static inline int tcf_em_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { int r = em->ops->match(skb, em, info); + return tcf_em_is_inverted(em) ? !r : r; } @@ -527,8 +536,8 @@ pop_stack: stack_overflow: if (net_ratelimit()) - printk(KERN_WARNING "tc ematch: local stack overflow," - " increase NET_EMATCH_STACK\n"); + pr_warning("tc ematch: local stack overflow," + " increase NET_EMATCH_STACK\n"); return -1; } EXPORT_SYMBOL(__tcf_em_tree_match); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b22ca2d..1507415 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -187,7 +187,7 @@ int unregister_qdisc(struct Qdisc_ops *qops) int err = -ENOENT; write_lock(&qdisc_mod_lock); - for (qp = &qdisc_base; (q=*qp)!=NULL; qp = &q->next) + for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (q == qops) break; if (q) { @@ -321,7 +321,9 @@ void qdisc_put_rtab(struct qdisc_rate_table *tab) if (!tab || --tab->refcnt) return; - for (rtabp = &qdisc_rtab_list; (rtab=*rtabp) != NULL; rtabp = &rtab->next) { + for (rtabp = &qdisc_rtab_list; + (rtab = *rtabp) != NULL; + rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; kfree(rtab); @@ -396,6 +398,11 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) return stab; } +static void stab_kfree_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct qdisc_size_table, rcu)); +} + void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) @@ -405,7 +412,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab) if (--tab->refcnt == 0) { list_del(&tab->list); - kfree(tab); + call_rcu_bh(&tab->rcu, stab_kfree_rcu); } spin_unlock(&qdisc_stab_lock); @@ -428,7 +435,7 @@ nla_put_failure: return -1; } -void qdisc_calculate_pkt_len(struct sk_buff *skb, struct qdisc_size_table *stab) +void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) { int pkt_len, slot; @@ -454,14 +461,13 @@ out: pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } -EXPORT_SYMBOL(qdisc_calculate_pkt_len); +EXPORT_SYMBOL(__qdisc_calculate_pkt_len); void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc) { if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { - printk(KERN_WARNING - "%s: %s qdisc %X: is non-work-conserving?\n", - txt, qdisc->ops->id, qdisc->handle >> 16); + pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", + txt, qdisc->ops->id, qdisc->handle >> 16); qdisc->flags |= TCQ_F_WARN_NONWC; } } @@ -472,7 +478,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, timer); - wd->qdisc->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(wd->qdisc); __netif_schedule(qdisc_root(wd->qdisc)); return HRTIMER_NORESTART; @@ -494,7 +500,7 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) &qdisc_root_sleeping(wd->qdisc)->state)) return; - wd->qdisc->flags |= TCQ_F_THROTTLED; + qdisc_throttled(wd->qdisc); time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); @@ -504,7 +510,7 @@ EXPORT_SYMBOL(qdisc_watchdog_schedule); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { hrtimer_cancel(&wd->timer); - wd->qdisc->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(wd->qdisc); } EXPORT_SYMBOL(qdisc_watchdog_cancel); @@ -625,7 +631,7 @@ static u32 qdisc_alloc_handle(struct net_device *dev) autohandle = TC_H_MAKE(0x80000000U, 0); } while (qdisc_lookup(dev, autohandle) && --i > 0); - return i>0 ? autohandle : 0; + return i > 0 ? autohandle : 0; } void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) @@ -834,7 +840,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, err = PTR_ERR(stab); goto err_out4; } - sch->stab = stab; + rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { spinlock_t *root_lock; @@ -874,7 +880,7 @@ err_out4: * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. */ - qdisc_put_stab(sch->stab); + qdisc_put_stab(rtnl_dereference(sch->stab)); if (ops->destroy) ops->destroy(sch); goto err_out3; @@ -882,7 +888,7 @@ err_out4: static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) { - struct qdisc_size_table *stab = NULL; + struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { @@ -899,8 +905,9 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) return PTR_ERR(stab); } - qdisc_put_stab(sch->stab); - sch->stab = stab; + ostab = rtnl_dereference(sch->stab); + rcu_assign_pointer(sch->stab, stab); + qdisc_put_stab(ostab); if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator @@ -915,9 +922,8 @@ out: return 0; } -struct check_loop_arg -{ - struct qdisc_walker w; +struct check_loop_arg { + struct qdisc_walker w; struct Qdisc *p; int depth; }; @@ -970,7 +976,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *p = NULL; int err; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -980,12 +987,12 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { - if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) + p = qdisc_lookup(dev, TC_H_MAJ(clid)); + if (!p) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /* ingress */ - if (dev_ingress_queue(dev)) - q = dev_ingress_queue(dev)->qdisc_sleeping; + } else if (dev_ingress_queue(dev)) { + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -996,7 +1003,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (tcm->tcm_handle && q->handle != tcm->tcm_handle) return -EINVAL; } else { - if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL) + q = qdisc_lookup(dev, tcm->tcm_handle); + if (!q) return -ENOENT; } @@ -1008,7 +1016,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -EINVAL; if (q->handle == 0) return -ENOENT; - if ((err = qdisc_graft(dev, p, skb, n, clid, NULL, q)) != 0) + err = qdisc_graft(dev, p, skb, n, clid, NULL, q); + if (err != 0) return err; } else { qdisc_notify(net, skb, n, clid, NULL, q); @@ -1017,7 +1026,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } /* - Create/change qdisc. + * Create/change qdisc. */ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) @@ -1036,7 +1045,8 @@ replay: clid = tcm->tcm_parent; q = p = NULL; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1046,12 +1056,12 @@ replay: if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { - if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) + p = qdisc_lookup(dev, TC_H_MAJ(clid)); + if (!p) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /* ingress */ - if (dev_ingress_queue_create(dev)) - q = dev_ingress_queue(dev)->qdisc_sleeping; + } else if (dev_ingress_queue_create(dev)) { + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1063,13 +1073,14 @@ replay: if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { - if (q && !(n->nlmsg_flags&NLM_F_REPLACE)) + if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; if (TC_H_MIN(tcm->tcm_handle)) return -EINVAL; - if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL) + q = qdisc_lookup(dev, tcm->tcm_handle); + if (!q) goto create_n_graft; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) return -EINVAL; @@ -1079,7 +1090,7 @@ replay: atomic_inc(&q->refcnt); goto graft; } else { - if (q == NULL) + if (!q) goto create_n_graft; /* This magic test requires explanation. @@ -1101,9 +1112,9 @@ replay: * For now we select create/graft, if * user gave KIND, which does not match existing. */ - if ((n->nlmsg_flags&NLM_F_CREATE) && - (n->nlmsg_flags&NLM_F_REPLACE) && - ((n->nlmsg_flags&NLM_F_EXCL) || + if ((n->nlmsg_flags & NLM_F_CREATE) && + (n->nlmsg_flags & NLM_F_REPLACE) && + ((n->nlmsg_flags & NLM_F_EXCL) || (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)))) goto create_n_graft; @@ -1118,7 +1129,7 @@ replay: /* Change qdisc parameters */ if (q == NULL) return -ENOENT; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) return -EINVAL; @@ -1128,7 +1139,7 @@ replay: return err; create_n_graft: - if (!(n->nlmsg_flags&NLM_F_CREATE)) + if (!(n->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) @@ -1175,6 +1186,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; + struct qdisc_size_table *stab; nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); @@ -1190,7 +1202,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, goto nla_put_failure; q->qstats.qlen = q->q.qlen; - if (q->stab && qdisc_dump_stab(skb, q->stab) < 0) + stab = rtnl_dereference(q->stab); + if (stab && qdisc_dump_stab(skb, stab) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, @@ -1234,16 +1247,19 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old)) { - if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) + if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, + 0, RTM_DELQDISC) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new)) { - if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) + if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, + old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; } if (skb->len) - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); @@ -1275,7 +1291,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; continue; } - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; @@ -1356,7 +1372,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 qid = TC_H_MAJ(clid); int err; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1391,9 +1408,9 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) qid = dev->qdisc->handle; /* Now qid is genuine qdisc handle consistent - both with parent and child. - - TC_H_MAJ(pid) still may be unspecified, complete it now. + * both with parent and child. + * + * TC_H_MAJ(pid) still may be unspecified, complete it now. */ if (pid) pid = TC_H_MAKE(qid, pid); @@ -1403,7 +1420,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } /* OK. Locate qdisc */ - if ((q = qdisc_lookup(dev, qid)) == NULL) + q = qdisc_lookup(dev, qid); + if (!q) return -ENOENT; /* An check that it supports classes */ @@ -1423,13 +1441,14 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (cl == 0) { err = -ENOENT; - if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTCLASS || + !(n->nlmsg_flags & NLM_F_CREATE)) goto out; } else { switch (n->nlmsg_type) { case RTM_NEWTCLASS: err = -EEXIST; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) goto out; break; case RTM_DELTCLASS: @@ -1521,14 +1540,14 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, return -EINVAL; } - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } -struct qdisc_dump_args -{ - struct qdisc_walker w; - struct sk_buff *skb; - struct netlink_callback *cb; +struct qdisc_dump_args { + struct qdisc_walker w; + struct sk_buff *skb; + struct netlink_callback *cb; }; static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) @@ -1590,7 +1609,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { - struct tcmsg *tcm = (struct tcmsg*)NLMSG_DATA(cb->nlh); + struct tcmsg *tcm = (struct tcmsg *)NLMSG_DATA(cb->nlh); struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; struct net_device *dev; @@ -1598,7 +1617,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) return 0; - if ((dev = dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return 0; s_t = cb->args[0]; @@ -1621,19 +1641,22 @@ done: } /* Main classifier routine: scans classifier chain attached - to this qdisc, (optionally) tests for protocol and asks - specific classifiers. + * to this qdisc, (optionally) tests for protocol and asks + * specific classifiers. */ int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { __be16 protocol = skb->protocol; - int err = 0; + int err; for (; tp; tp = tp->next) { - if ((tp->protocol == protocol || - tp->protocol == htons(ETH_P_ALL)) && - (err = tp->classify(skb, tp, res)) >= 0) { + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + err = tp->classify(skb, tp, res); + + if (err >= 0) { #ifdef CONFIG_NET_CLS_ACT if (err != TC_ACT_RECLASSIFY && skb->tc_verd) skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0); @@ -1664,11 +1687,11 @@ reclassify: if (verd++ >= MAX_REC_LOOP) { if (net_ratelimit()) - printk(KERN_NOTICE - "%s: packet reclassify loop" + pr_notice("%s: packet reclassify loop" " rule prio %u protocol %02x\n", - tp->q->ops->id, - tp->prio & 0xffff, ntohs(tp->protocol)); + tp->q->ops->id, + tp->prio & 0xffff, + ntohs(tp->protocol)); return TC_ACT_SHOT; } skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); @@ -1761,7 +1784,7 @@ static int __init pktsched_init(void) err = register_pernet_subsys(&psched_net_ops); if (err) { - printk(KERN_ERR "pktsched_init: " + pr_err("pktsched_init: " "cannot initialize per netns operations\n"); return err; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 943d733..3f08158 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -319,7 +319,7 @@ static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) * creation), and one for the reference held when calling delete. */ if (flow->ref < 2) { - printk(KERN_ERR "atm_tc_delete: flow->ref == %d\n", flow->ref); + pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); return -EINVAL; } if (flow->ref > 2) @@ -384,12 +384,12 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) } } flow = NULL; - done: - ; +done: + ; } - if (!flow) + if (!flow) { flow = &p->link; - else { + } else { if (flow->vcc) ATM_SKB(skb)->atm_options = flow->vcc->atm_options; /*@@@ looks good ... but it's not supposed to work :-) */ @@ -576,8 +576,7 @@ static void atm_tc_destroy(struct Qdisc *sch) list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) - printk(KERN_ERR "atm_destroy: %p->ref = %d\n", flow, - flow->ref); + pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); atm_tc_put(sch, (unsigned long)flow); } tasklet_kill(&p->task); @@ -616,9 +615,8 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, } if (flow->excess) NLA_PUT_U32(skb, TCA_ATM_EXCESS, flow->classid); - else { + else NLA_PUT_U32(skb, TCA_ATM_EXCESS, 0); - } nla_nest_end(skb, nest); return skb->len; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 5f63ec5..24d94c0 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -72,8 +72,7 @@ struct cbq_sched_data; -struct cbq_class -{ +struct cbq_class { struct Qdisc_class_common common; struct cbq_class *next_alive; /* next class with backlog in this priority band */ @@ -139,19 +138,18 @@ struct cbq_class int refcnt; int filters; - struct cbq_class *defaults[TC_PRIO_MAX+1]; + struct cbq_class *defaults[TC_PRIO_MAX + 1]; }; -struct cbq_sched_data -{ +struct cbq_sched_data { struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO+1]; - unsigned quanta[TC_CBQ_MAXPRIO+1]; + int nclasses[TC_CBQ_MAXPRIO + 1]; + unsigned int quanta[TC_CBQ_MAXPRIO + 1]; struct cbq_class link; - unsigned activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO+1]; /* List of all classes + unsigned int activemask; + struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes with backlog */ #ifdef CONFIG_NET_CLS_ACT @@ -162,7 +160,7 @@ struct cbq_sched_data int tx_len; psched_time_t now; /* Cached timestamp */ psched_time_t now_rt; /* Cached real time */ - unsigned pmask; + unsigned int pmask; struct hrtimer delay_timer; struct qdisc_watchdog watchdog; /* Watchdog timer, @@ -175,9 +173,9 @@ struct cbq_sched_data }; -#define L2T(cl,len) qdisc_l2t((cl)->R_tab,len) +#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) -static __inline__ struct cbq_class * +static inline struct cbq_class * cbq_class_lookup(struct cbq_sched_data *q, u32 classid) { struct Qdisc_class_common *clc; @@ -193,25 +191,27 @@ cbq_class_lookup(struct cbq_sched_data *q, u32 classid) static struct cbq_class * cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) { - struct cbq_class *cl, *new; + struct cbq_class *cl; - for (cl = this->tparent; cl; cl = cl->tparent) - if ((new = cl->defaults[TC_PRIO_BESTEFFORT]) != NULL && new != this) - return new; + for (cl = this->tparent; cl; cl = cl->tparent) { + struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; + if (new != NULL && new != this) + return new; + } return NULL; } #endif /* Classify packet. The procedure is pretty complicated, but - it allows us to combine link sharing and priority scheduling - transparently. - - Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - so that it resolves to split nodes. Then packets are classified - by logical priority, or a more specific classifier may be attached - to the split node. + * it allows us to combine link sharing and priority scheduling + * transparently. + * + * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, + * so that it resolves to split nodes. Then packets are classified + * by logical priority, or a more specific classifier may be attached + * to the split node. */ static struct cbq_class * @@ -227,7 +227,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 1. If skb->priority points to one of our classes, use it. */ - if (TC_H_MAJ(prio^sch->handle) == 0 && + if (TC_H_MAJ(prio ^ sch->handle) == 0 && (cl = cbq_class_lookup(q, prio)) != NULL) return cl; @@ -243,10 +243,11 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) (result = tc_classify_compat(skb, head->filter_list, &res)) < 0) goto fallback; - if ((cl = (void*)res.class) == NULL) { + cl = (void *)res.class; + if (!cl) { if (TC_H_MAJ(res.classid)) cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid&TC_PRIO_MAX]) == NULL) + else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) cl = defmap[TC_PRIO_BESTEFFORT]; if (cl == NULL || cl->level >= head->level) @@ -282,7 +283,7 @@ fallback: * Step 4. No success... */ if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio&TC_PRIO_MAX]) && + !(cl = head->defaults[prio & TC_PRIO_MAX]) && !(cl = head->defaults[TC_PRIO_BESTEFFORT])) return head; @@ -290,12 +291,12 @@ fallback: } /* - A packet has just been enqueued on the empty class. - cbq_activate_class adds it to the tail of active class list - of its priority band. + * A packet has just been enqueued on the empty class. + * cbq_activate_class adds it to the tail of active class list + * of its priority band. */ -static __inline__ void cbq_activate_class(struct cbq_class *cl) +static inline void cbq_activate_class(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); int prio = cl->cpriority; @@ -314,9 +315,9 @@ static __inline__ void cbq_activate_class(struct cbq_class *cl) } /* - Unlink class from active chain. - Note that this same procedure is done directly in cbq_dequeue* - during round-robin procedure. + * Unlink class from active chain. + * Note that this same procedure is done directly in cbq_dequeue* + * during round-robin procedure. */ static void cbq_deactivate_class(struct cbq_class *this) @@ -350,7 +351,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) { int toplevel = q->toplevel; - if (toplevel > cl->level && !(cl->q->flags&TCQ_F_THROTTLED)) { + if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) { psched_time_t now; psched_tdiff_t incr; @@ -363,7 +364,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) q->toplevel = cl->level; return; } - } while ((cl=cl->borrow) != NULL && toplevel > cl->level); + } while ((cl = cl->borrow) != NULL && toplevel > cl->level); } } @@ -417,11 +418,11 @@ static void cbq_ovl_classic(struct cbq_class *cl) delay += cl->offtime; /* - Class goes to sleep, so that it will have no - chance to work avgidle. Let's forgive it 8) - - BTW cbq-2.0 has a crap in this - place, apparently they forgot to shift it by cl->ewma_log. + * Class goes to sleep, so that it will have no + * chance to work avgidle. Let's forgive it 8) + * + * BTW cbq-2.0 has a crap in this + * place, apparently they forgot to shift it by cl->ewma_log. */ if (cl->avgidle < 0) delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); @@ -438,8 +439,8 @@ static void cbq_ovl_classic(struct cbq_class *cl) q->wd_expires = delay; /* Dirty work! We must schedule wakeups based on - real available rate, rather than leaf rate, - which may be tiny (even zero). + * real available rate, rather than leaf rate, + * which may be tiny (even zero). */ if (q->toplevel == TC_CBQ_MAXLEVEL) { struct cbq_class *b; @@ -459,7 +460,7 @@ static void cbq_ovl_classic(struct cbq_class *cl) } /* TC_CBQ_OVL_RCLASSIC: penalize by offtime classes in hierarchy, when - they go overlimit + * they go overlimit */ static void cbq_ovl_rclassic(struct cbq_class *cl) @@ -594,7 +595,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) struct Qdisc *sch = q->watchdog.qdisc; psched_time_t now; psched_tdiff_t delay = 0; - unsigned pmask; + unsigned int pmask; now = psched_get_time(); @@ -623,7 +624,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); } - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); __netif_schedule(qdisc_root(sch)); return HRTIMER_NORESTART; } @@ -663,15 +664,15 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) #endif /* - It is mission critical procedure. - - We "regenerate" toplevel cutoff, if transmitting class - has backlog and it is not regulated. It is not part of - original CBQ description, but looks more reasonable. - Probably, it is wrong. This question needs further investigation. -*/ + * It is mission critical procedure. + * + * We "regenerate" toplevel cutoff, if transmitting class + * has backlog and it is not regulated. It is not part of + * original CBQ description, but looks more reasonable. + * Probably, it is wrong. This question needs further investigation. + */ -static __inline__ void +static inline void cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, struct cbq_class *borrowed) { @@ -682,7 +683,7 @@ cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, q->toplevel = borrowed->level; return; } - } while ((borrowed=borrowed->borrow) != NULL); + } while ((borrowed = borrowed->borrow) != NULL); } #if 0 /* It is not necessary now. Uncommenting it @@ -710,10 +711,10 @@ cbq_update(struct cbq_sched_data *q) cl->bstats.bytes += len; /* - (now - last) is total time between packet right edges. - (last_pktlen/rate) is "virtual" busy time, so that - - idle = (now - last) - last_pktlen/rate + * (now - last) is total time between packet right edges. + * (last_pktlen/rate) is "virtual" busy time, so that + * + * idle = (now - last) - last_pktlen/rate */ idle = q->now - cl->last; @@ -723,9 +724,9 @@ cbq_update(struct cbq_sched_data *q) idle -= L2T(cl, len); /* true_avgidle := (1-W)*true_avgidle + W*idle, - where W=2^{-ewma_log}. But cl->avgidle is scaled: - cl->avgidle == true_avgidle/W, - hence: + * where W=2^{-ewma_log}. But cl->avgidle is scaled: + * cl->avgidle == true_avgidle/W, + * hence: */ avgidle += idle - (avgidle>>cl->ewma_log); } @@ -739,22 +740,22 @@ cbq_update(struct cbq_sched_data *q) cl->avgidle = avgidle; /* Calculate expected time, when this class - will be allowed to send. - It will occur, when: - (1-W)*true_avgidle + W*delay = 0, i.e. - idle = (1/W - 1)*(-true_avgidle) - or - idle = (1 - W)*(-cl->avgidle); + * will be allowed to send. + * It will occur, when: + * (1-W)*true_avgidle + W*delay = 0, i.e. + * idle = (1/W - 1)*(-true_avgidle) + * or + * idle = (1 - W)*(-cl->avgidle); */ idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); /* - That is not all. - To maintain the rate allocated to the class, - we add to undertime virtual clock, - necessary to complete transmitted packet. - (len/phys_bandwidth has been already passed - to the moment of cbq_update) + * That is not all. + * To maintain the rate allocated to the class, + * we add to undertime virtual clock, + * necessary to complete transmitted packet. + * (len/phys_bandwidth has been already passed + * to the moment of cbq_update) */ idle -= L2T(&q->link, len); @@ -776,7 +777,7 @@ cbq_update(struct cbq_sched_data *q) cbq_update_toplevel(q, this, q->tx_borrowed); } -static __inline__ struct cbq_class * +static inline struct cbq_class * cbq_under_limit(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); @@ -792,16 +793,17 @@ cbq_under_limit(struct cbq_class *cl) do { /* It is very suspicious place. Now overlimit - action is generated for not bounded classes - only if link is completely congested. - Though it is in agree with ancestor-only paradigm, - it looks very stupid. Particularly, - it means that this chunk of code will either - never be called or result in strong amplification - of burstiness. Dangerous, silly, and, however, - no another solution exists. + * action is generated for not bounded classes + * only if link is completely congested. + * Though it is in agree with ancestor-only paradigm, + * it looks very stupid. Particularly, + * it means that this chunk of code will either + * never be called or result in strong amplification + * of burstiness. Dangerous, silly, and, however, + * no another solution exists. */ - if ((cl = cl->borrow) == NULL) { + cl = cl->borrow; + if (!cl) { this_cl->qstats.overlimits++; this_cl->overlimit(this_cl); return NULL; @@ -814,7 +816,7 @@ cbq_under_limit(struct cbq_class *cl) return cl; } -static __inline__ struct sk_buff * +static inline struct sk_buff * cbq_dequeue_prio(struct Qdisc *sch, int prio) { struct cbq_sched_data *q = qdisc_priv(sch); @@ -838,7 +840,7 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) if (cl->deficit <= 0) { /* Class exhausted its allotment per - this round. Switch to the next one. + * this round. Switch to the next one. */ deficit = 1; cl->deficit += cl->quantum; @@ -848,8 +850,8 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) skb = cl->q->dequeue(cl->q); /* Class did not give us any skb :-( - It could occur even if cl->q->q.qlen != 0 - f.e. if cl->q == "tbf" + * It could occur even if cl->q->q.qlen != 0 + * f.e. if cl->q == "tbf" */ if (skb == NULL) goto skip_class; @@ -878,7 +880,7 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) skip_class: if (cl->q->q.qlen == 0 || prio != cl->cpriority) { /* Class is empty or penalized. - Unlink it from active chain. + * Unlink it from active chain. */ cl_prev->next_alive = cl->next_alive; cl->next_alive = NULL; @@ -917,14 +919,14 @@ next_class: return NULL; } -static __inline__ struct sk_buff * +static inline struct sk_buff * cbq_dequeue_1(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - unsigned activemask; + unsigned int activemask; - activemask = q->activemask&0xFF; + activemask = q->activemask & 0xFF; while (activemask) { int prio = ffz(~activemask); activemask &= ~(1<<prio); @@ -949,11 +951,11 @@ cbq_dequeue(struct Qdisc *sch) if (q->tx_class) { psched_tdiff_t incr2; /* Time integrator. We calculate EOS time - by adding expected packet transmission time. - If real time is greater, we warp artificial clock, - so that: - - cbq_time = max(real_time, work); + * by adding expected packet transmission time. + * If real time is greater, we warp artificial clock, + * so that: + * + * cbq_time = max(real_time, work); */ incr2 = L2T(&q->link, q->tx_len); q->now += incr2; @@ -971,27 +973,27 @@ cbq_dequeue(struct Qdisc *sch) if (skb) { qdisc_bstats_update(sch, skb); sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); return skb; } /* All the classes are overlimit. - - It is possible, if: - - 1. Scheduler is empty. - 2. Toplevel cutoff inhibited borrowing. - 3. Root class is overlimit. - - Reset 2d and 3d conditions and retry. - - Note, that NS and cbq-2.0 are buggy, peeking - an arbitrary class is appropriate for ancestor-only - sharing, but not for toplevel algorithm. - - Our version is better, but slower, because it requires - two passes, but it is unavoidable with top-level sharing. - */ + * + * It is possible, if: + * + * 1. Scheduler is empty. + * 2. Toplevel cutoff inhibited borrowing. + * 3. Root class is overlimit. + * + * Reset 2d and 3d conditions and retry. + * + * Note, that NS and cbq-2.0 are buggy, peeking + * an arbitrary class is appropriate for ancestor-only + * sharing, but not for toplevel algorithm. + * + * Our version is better, but slower, because it requires + * two passes, but it is unavoidable with top-level sharing. + */ if (q->toplevel == TC_CBQ_MAXLEVEL && q->link.undertime == PSCHED_PASTPERFECT) @@ -1002,7 +1004,8 @@ cbq_dequeue(struct Qdisc *sch) } /* No packets in scheduler or nobody wants to give them to us :-( - Sigh... start watchdog timer in the last case. */ + * Sigh... start watchdog timer in the last case. + */ if (sch->q.qlen) { sch->qstats.overlimits++; @@ -1024,13 +1027,14 @@ static void cbq_adjust_levels(struct cbq_class *this) int level = 0; struct cbq_class *cl; - if ((cl = this->children) != NULL) { + cl = this->children; + if (cl) { do { if (cl->level > level) level = cl->level; } while ((cl = cl->sibling) != this->children); } - this->level = level+1; + this->level = level + 1; } while ((this = this->tparent) != NULL); } @@ -1046,14 +1050,15 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { /* BUGGGG... Beware! This expression suffer of - arithmetic overflows! + * arithmetic overflows! */ if (cl->priority == prio) { cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ q->quanta[prio]; } if (cl->quantum <= 0 || cl->quantum>32*qdisc_dev(cl->qdisc)->mtu) { - printk(KERN_WARNING "CBQ: class %08x has bad quantum==%ld, repaired.\n", cl->common.classid, cl->quantum); + pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n", + cl->common.classid, cl->quantum); cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; } } @@ -1064,18 +1069,18 @@ static void cbq_sync_defmap(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); struct cbq_class *split = cl->split; - unsigned h; + unsigned int h; int i; if (split == NULL) return; - for (i=0; i<=TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap&(1<<i))) + for (i = 0; i <= TC_PRIO_MAX; i++) { + if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) split->defaults[i] = NULL; } - for (i=0; i<=TC_PRIO_MAX; i++) { + for (i = 0; i <= TC_PRIO_MAX; i++) { int level = split->level; if (split->defaults[i]) @@ -1088,7 +1093,7 @@ static void cbq_sync_defmap(struct cbq_class *cl) hlist_for_each_entry(c, n, &q->clhash.hash[h], common.hnode) { if (c->split == split && c->level < level && - c->defmap&(1<<i)) { + c->defmap & (1<<i)) { split->defaults[i] = c; level = c->level; } @@ -1102,7 +1107,8 @@ static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 ma struct cbq_class *split = NULL; if (splitid == 0) { - if ((split = cl->split) == NULL) + split = cl->split; + if (!split) return; splitid = split->common.classid; } @@ -1120,9 +1126,9 @@ static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 ma cl->defmap = 0; cbq_sync_defmap(cl); cl->split = split; - cl->defmap = def&mask; + cl->defmap = def & mask; } else - cl->defmap = (cl->defmap&~mask)|(def&mask); + cl->defmap = (cl->defmap & ~mask) | (def & mask); cbq_sync_defmap(cl); } @@ -1135,7 +1141,7 @@ static void cbq_unlink_class(struct cbq_class *this) qdisc_class_hash_remove(&q->clhash, &this->common); if (this->tparent) { - clp=&this->sibling; + clp = &this->sibling; cl = *clp; do { if (cl == this) { @@ -1174,7 +1180,7 @@ static void cbq_link_class(struct cbq_class *this) } } -static unsigned int cbq_drop(struct Qdisc* sch) +static unsigned int cbq_drop(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl, *cl_head; @@ -1182,7 +1188,8 @@ static unsigned int cbq_drop(struct Qdisc* sch) unsigned int len; for (prio = TC_CBQ_MAXPRIO; prio >= 0; prio--) { - if ((cl_head = q->active[prio]) == NULL) + cl_head = q->active[prio]; + if (!cl_head) continue; cl = cl_head; @@ -1199,13 +1206,13 @@ static unsigned int cbq_drop(struct Qdisc* sch) } static void -cbq_reset(struct Qdisc* sch) +cbq_reset(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; struct hlist_node *n; int prio; - unsigned h; + unsigned int h; q->activemask = 0; q->pmask = 0; @@ -1237,21 +1244,21 @@ cbq_reset(struct Qdisc* sch) static int cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) { - if (lss->change&TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags&TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags&TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; + if (lss->change & TCF_CBQ_LSS_FLAGS) { + cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; + cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; } - if (lss->change&TCF_CBQ_LSS_EWMA) + if (lss->change & TCF_CBQ_LSS_EWMA) cl->ewma_log = lss->ewma_log; - if (lss->change&TCF_CBQ_LSS_AVPKT) + if (lss->change & TCF_CBQ_LSS_AVPKT) cl->avpkt = lss->avpkt; - if (lss->change&TCF_CBQ_LSS_MINIDLE) + if (lss->change & TCF_CBQ_LSS_MINIDLE) cl->minidle = -(long)lss->minidle; - if (lss->change&TCF_CBQ_LSS_MAXIDLE) { + if (lss->change & TCF_CBQ_LSS_MAXIDLE) { cl->maxidle = lss->maxidle; cl->avgidle = lss->maxidle; } - if (lss->change&TCF_CBQ_LSS_OFFTIME) + if (lss->change & TCF_CBQ_LSS_OFFTIME) cl->offtime = lss->offtime; return 0; } @@ -1279,10 +1286,10 @@ static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) if (wrr->weight) cl->weight = wrr->weight; if (wrr->priority) { - cl->priority = wrr->priority-1; + cl->priority = wrr->priority - 1; cl->cpriority = cl->priority; if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO-1; + cl->priority2 = TC_CBQ_MAXPRIO - 1; } cbq_addprio(q, cl); @@ -1299,10 +1306,10 @@ static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl) cl->overlimit = cbq_ovl_delay; break; case TC_CBQ_OVL_LOWPRIO: - if (ovl->priority2-1 >= TC_CBQ_MAXPRIO || - ovl->priority2-1 <= cl->priority) + if (ovl->priority2 - 1 >= TC_CBQ_MAXPRIO || + ovl->priority2 - 1 <= cl->priority) return -EINVAL; - cl->priority2 = ovl->priority2-1; + cl->priority2 = ovl->priority2 - 1; cl->overlimit = cbq_ovl_lowprio; break; case TC_CBQ_OVL_DROP: @@ -1381,9 +1388,9 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) if (!q->link.q) q->link.q = &noop_qdisc; - q->link.priority = TC_CBQ_MAXPRIO-1; - q->link.priority2 = TC_CBQ_MAXPRIO-1; - q->link.cpriority = TC_CBQ_MAXPRIO-1; + q->link.priority = TC_CBQ_MAXPRIO - 1; + q->link.priority2 = TC_CBQ_MAXPRIO - 1; + q->link.cpriority = TC_CBQ_MAXPRIO - 1; q->link.ovl_strategy = TC_CBQ_OVL_CLASSIC; q->link.overlimit = cbq_ovl_classic; q->link.allot = psched_mtu(qdisc_dev(sch)); @@ -1414,7 +1421,7 @@ put_rtab: return err; } -static __inline__ int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); @@ -1426,7 +1433,7 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_lssopt opt; @@ -1451,15 +1458,15 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; opt.flags = 0; opt.allot = cl->allot; - opt.priority = cl->priority+1; - opt.cpriority = cl->cpriority+1; + opt.priority = cl->priority + 1; + opt.cpriority = cl->cpriority + 1; opt.weight = cl->weight; NLA_PUT(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt); return skb->len; @@ -1469,13 +1476,13 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_ovl opt; opt.strategy = cl->ovl_strategy; - opt.priority2 = cl->priority2+1; + opt.priority2 = cl->priority2 + 1; opt.pad = 0; opt.penalty = cl->penalty; NLA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt); @@ -1486,7 +1493,7 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_fopt opt; @@ -1505,7 +1512,7 @@ nla_put_failure: } #ifdef CONFIG_NET_CLS_ACT -static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_police opt; @@ -1569,7 +1576,7 @@ static int cbq_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; struct nlattr *nest; if (cl->tparent) @@ -1597,7 +1604,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; cl->qstats.qlen = cl->q->q.qlen; cl->xstats.avgidle = cl->avgidle; @@ -1617,7 +1624,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, @@ -1640,10 +1647,9 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return 0; } -static struct Qdisc * -cbq_leaf(struct Qdisc *sch, unsigned long arg) +static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; return cl->q; } @@ -1682,13 +1688,12 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) kfree(cl); } -static void -cbq_destroy(struct Qdisc* sch) +static void cbq_destroy(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct hlist_node *n, *next; struct cbq_class *cl; - unsigned h; + unsigned int h; #ifdef CONFIG_NET_CLS_ACT q->rx_class = NULL; @@ -1712,7 +1717,7 @@ cbq_destroy(struct Qdisc* sch) static void cbq_put(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; if (--cl->refcnt == 0) { #ifdef CONFIG_NET_CLS_ACT @@ -1735,7 +1740,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t { int err; struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)*arg; + struct cbq_class *cl = (struct cbq_class *)*arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_CBQ_MAX + 1]; struct cbq_class *parent; @@ -1827,13 +1832,14 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (classid) { err = -EINVAL; - if (TC_H_MAJ(classid^sch->handle) || cbq_class_lookup(q, classid)) + if (TC_H_MAJ(classid ^ sch->handle) || + cbq_class_lookup(q, classid)) goto failure; } else { int i; - classid = TC_H_MAKE(sch->handle,0x8000); + classid = TC_H_MAKE(sch->handle, 0x8000); - for (i=0; i<0x8000; i++) { + for (i = 0; i < 0x8000; i++) { if (++q->hgenerator >= 0x8000) q->hgenerator = 1; if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) @@ -1890,11 +1896,11 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->minidle = -0x7FFFFFFF; cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log==0) + if (cl->ewma_log == 0) cl->ewma_log = q->link.ewma_log; - if (cl->maxidle==0) + if (cl->maxidle == 0) cl->maxidle = q->link.maxidle; - if (cl->avpkt==0) + if (cl->avpkt == 0) cl->avpkt = q->link.avpkt; cl->overlimit = cbq_ovl_classic; if (tb[TCA_CBQ_OVL_STRATEGY]) @@ -1920,7 +1926,7 @@ failure: static int cbq_delete(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; unsigned int qlen; if (cl->filters || cl->children || cl == &q->link) @@ -1978,7 +1984,7 @@ static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class*)parent; + struct cbq_class *p = (struct cbq_class *)parent; struct cbq_class *cl = cbq_class_lookup(q, classid); if (cl) { @@ -1992,7 +1998,7 @@ static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; cl->filters--; } @@ -2002,7 +2008,7 @@ static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; struct hlist_node *n; - unsigned h; + unsigned int h; if (arg->stop) return; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c new file mode 100644 index 0000000..ee1e209 --- /dev/null +++ b/net/sched/sch_choke.c @@ -0,0 +1,677 @@ +/* + * net/sched/sch_choke.c CHOKE scheduler + * + * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com> + * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/reciprocal_div.h> +#include <linux/vmalloc.h> +#include <net/pkt_sched.h> +#include <net/inet_ecn.h> +#include <net/red.h> +#include <linux/ip.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> + +/* + CHOKe stateless AQM for fair bandwidth allocation + ================================================= + + CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for + unresponsive flows) is a variant of RED that penalizes misbehaving flows but + maintains no flow state. The difference from RED is an additional step + during the enqueuing process. If average queue size is over the + low threshold (qmin), a packet is chosen at random from the queue. + If both the new and chosen packet are from the same flow, both + are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it + needs to access packets in queue randomly. It has a minimal class + interface to allow overriding the builtin flow classifier with + filters. + + Source: + R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless + Active Queue Management Scheme for Approximating Fair Bandwidth Allocation", + IEEE INFOCOM, 2000. + + A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial + Characteristics", IEEE/ACM Transactions on Networking, 2004 + + */ + +/* Upper bound on size of sk_buff table (packets) */ +#define CHOKE_MAX_QUEUE (128*1024 - 1) + +struct choke_sched_data { +/* Parameters */ + u32 limit; + unsigned char flags; + + struct red_parms parms; + +/* Variables */ + struct tcf_proto *filter_list; + struct { + u32 prob_drop; /* Early probability drops */ + u32 prob_mark; /* Early probability marks */ + u32 forced_drop; /* Forced drops, qavg > max_thresh */ + u32 forced_mark; /* Forced marks, qavg > max_thresh */ + u32 pdrop; /* Drops due to queue limits */ + u32 other; /* Drops due to drop() calls */ + u32 matched; /* Drops to flow match */ + } stats; + + unsigned int head; + unsigned int tail; + + unsigned int tab_mask; /* size - 1 */ + + struct sk_buff **tab; +}; + +/* deliver a random number between 0 and N - 1 */ +static u32 random_N(unsigned int N) +{ + return reciprocal_divide(random32(), N); +} + +/* number of elements in queue including holes */ +static unsigned int choke_len(const struct choke_sched_data *q) +{ + return (q->tail - q->head) & q->tab_mask; +} + +/* Is ECN parameter configured */ +static int use_ecn(const struct choke_sched_data *q) +{ + return q->flags & TC_RED_ECN; +} + +/* Should packets over max just be dropped (versus marked) */ +static int use_harddrop(const struct choke_sched_data *q) +{ + return q->flags & TC_RED_HARDDROP; +} + +/* Move head pointer forward to skip over holes */ +static void choke_zap_head_holes(struct choke_sched_data *q) +{ + do { + q->head = (q->head + 1) & q->tab_mask; + if (q->head == q->tail) + break; + } while (q->tab[q->head] == NULL); +} + +/* Move tail pointer backwards to reuse holes */ +static void choke_zap_tail_holes(struct choke_sched_data *q) +{ + do { + q->tail = (q->tail - 1) & q->tab_mask; + if (q->head == q->tail) + break; + } while (q->tab[q->tail] == NULL); +} + +/* Drop packet from queue array by creating a "hole" */ +static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = q->tab[idx]; + + q->tab[idx] = NULL; + + if (idx == q->head) + choke_zap_head_holes(q); + if (idx == q->tail) + choke_zap_tail_holes(q); + + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_drop(skb, sch); + qdisc_tree_decrease_qlen(sch, 1); + --sch->q.qlen; +} + +/* + * Compare flow of two packets + * Returns true only if source and destination address and port match. + * false for special cases + */ +static bool choke_match_flow(struct sk_buff *skb1, + struct sk_buff *skb2) +{ + int off1, off2, poff; + const u32 *ports1, *ports2; + u8 ip_proto; + __u32 hash1; + + if (skb1->protocol != skb2->protocol) + return false; + + /* Use hash value as quick check + * Assumes that __skb_get_rxhash makes IP header and ports linear + */ + hash1 = skb_get_rxhash(skb1); + if (!hash1 || hash1 != skb_get_rxhash(skb2)) + return false; + + /* Probably match, but be sure to avoid hash collisions */ + off1 = skb_network_offset(skb1); + off2 = skb_network_offset(skb2); + + switch (skb1->protocol) { + case __constant_htons(ETH_P_IP): { + const struct iphdr *ip1, *ip2; + + ip1 = (const struct iphdr *) (skb1->data + off1); + ip2 = (const struct iphdr *) (skb2->data + off2); + + ip_proto = ip1->protocol; + if (ip_proto != ip2->protocol || + ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr) + return false; + + if ((ip1->frag_off | ip2->frag_off) & htons(IP_MF | IP_OFFSET)) + ip_proto = 0; + off1 += ip1->ihl * 4; + off2 += ip2->ihl * 4; + break; + } + + case __constant_htons(ETH_P_IPV6): { + const struct ipv6hdr *ip1, *ip2; + + ip1 = (const struct ipv6hdr *) (skb1->data + off1); + ip2 = (const struct ipv6hdr *) (skb2->data + off2); + + ip_proto = ip1->nexthdr; + if (ip_proto != ip2->nexthdr || + ipv6_addr_cmp(&ip1->saddr, &ip2->saddr) || + ipv6_addr_cmp(&ip1->daddr, &ip2->daddr)) + return false; + off1 += 40; + off2 += 40; + } + + default: /* Maybe compare MAC header here? */ + return false; + } + + poff = proto_ports_offset(ip_proto); + if (poff < 0) + return true; + + off1 += poff; + off2 += poff; + + ports1 = (__force u32 *)(skb1->data + off1); + ports2 = (__force u32 *)(skb2->data + off2); + return *ports1 == *ports2; +} + +static inline void choke_set_classid(struct sk_buff *skb, u16 classid) +{ + *(unsigned int *)(qdisc_skb_cb(skb)->data) = classid; +} + +static u16 choke_get_classid(const struct sk_buff *skb) +{ + return *(unsigned int *)(qdisc_skb_cb(skb)->data); +} + +/* + * Classify flow using either: + * 1. pre-existing classification result in skb + * 2. fast internal classification + * 3. use TC filter based classification + */ +static bool choke_classify(struct sk_buff *skb, + struct Qdisc *sch, int *qerr) + +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct tcf_result res; + int result; + + result = tc_classify(skb, q->filter_list, &res); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return false; + } +#endif + choke_set_classid(skb, TC_H_MIN(res.classid)); + return true; + } + + return false; +} + +/* + * Select a packet at random from queue + * HACK: since queue can have holes from previous deletion; retry several + * times to find a random skb but then just give up and return the head + * Will return NULL if queue is empty (q->head == q->tail) + */ +static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, + unsigned int *pidx) +{ + struct sk_buff *skb; + int retrys = 3; + + do { + *pidx = (q->head + random_N(choke_len(q))) & q->tab_mask; + skb = q->tab[*pidx]; + if (skb) + return skb; + } while (--retrys > 0); + + return q->tab[*pidx = q->head]; +} + +/* + * Compare new packet with random packet in queue + * returns true if matched and sets *pidx + */ +static bool choke_match_random(const struct choke_sched_data *q, + struct sk_buff *nskb, + unsigned int *pidx) +{ + struct sk_buff *oskb; + + if (q->head == q->tail) + return false; + + oskb = choke_peek_random(q, pidx); + if (q->filter_list) + return choke_get_classid(nskb) == choke_get_classid(oskb); + + return choke_match_flow(oskb, nskb); +} + +static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct red_parms *p = &q->parms; + int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + + if (q->filter_list) { + /* If using external classifiers, get result and record it. */ + if (!choke_classify(skb, sch, &ret)) + goto other_drop; /* Packet was eaten by filter */ + } + + /* Compute average queue usage (see RED) */ + p->qavg = red_calc_qavg(p, sch->q.qlen); + if (red_is_idling(p)) + red_end_of_idle_period(p); + + /* Is queue small? */ + if (p->qavg <= p->qth_min) + p->qcount = -1; + else { + unsigned int idx; + + /* Draw a packet at random from queue and compare flow */ + if (choke_match_random(q, skb, &idx)) { + q->stats.matched++; + choke_drop_by_idx(sch, idx); + goto congestion_drop; + } + + /* Queue is large, always mark/drop */ + if (p->qavg > p->qth_max) { + p->qcount = -1; + + sch->qstats.overlimits++; + if (use_harddrop(q) || !use_ecn(q) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + q->stats.forced_mark++; + } else if (++p->qcount) { + if (red_mark_probability(p, p->qavg)) { + p->qcount = 0; + p->qR = red_random(p); + + sch->qstats.overlimits++; + if (!use_ecn(q) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + } + } else + p->qR = red_random(p); + } + + /* Admit new packet */ + if (sch->q.qlen < q->limit) { + q->tab[q->tail] = skb; + q->tail = (q->tail + 1) & q->tab_mask; + ++sch->q.qlen; + sch->qstats.backlog += qdisc_pkt_len(skb); + return NET_XMIT_SUCCESS; + } + + q->stats.pdrop++; + sch->qstats.drops++; + kfree_skb(skb); + return NET_XMIT_DROP; + + congestion_drop: + qdisc_drop(skb, sch); + return NET_XMIT_CN; + + other_drop: + if (ret & __NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return ret; +} + +static struct sk_buff *choke_dequeue(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + + if (q->head == q->tail) { + if (!red_is_idling(&q->parms)) + red_start_of_idle_period(&q->parms); + return NULL; + } + + skb = q->tab[q->head]; + q->tab[q->head] = NULL; + choke_zap_head_holes(q); + --sch->q.qlen; + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); + + return skb; +} + +static unsigned int choke_drop(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + unsigned int len; + + len = qdisc_queue_drop(sch); + if (len > 0) + q->stats.other++; + else { + if (!red_is_idling(&q->parms)) + red_start_of_idle_period(&q->parms); + } + + return len; +} + +static void choke_reset(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + red_restart(&q->parms); +} + +static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = { + [TCA_CHOKE_PARMS] = { .len = sizeof(struct tc_red_qopt) }, + [TCA_CHOKE_STAB] = { .len = RED_STAB_SIZE }, +}; + + +static void choke_free(void *addr) +{ + if (addr) { + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); + } +} + +static int choke_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_CHOKE_MAX + 1]; + const struct tc_red_qopt *ctl; + int err; + struct sk_buff **old = NULL; + unsigned int mask; + + if (opt == NULL) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy); + if (err < 0) + return err; + + if (tb[TCA_CHOKE_PARMS] == NULL || + tb[TCA_CHOKE_STAB] == NULL) + return -EINVAL; + + ctl = nla_data(tb[TCA_CHOKE_PARMS]); + + if (ctl->limit > CHOKE_MAX_QUEUE) + return -EINVAL; + + mask = roundup_pow_of_two(ctl->limit + 1) - 1; + if (mask != q->tab_mask) { + struct sk_buff **ntab; + + ntab = kcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL); + if (!ntab) + ntab = vzalloc((mask + 1) * sizeof(struct sk_buff *)); + if (!ntab) + return -ENOMEM; + + sch_tree_lock(sch); + old = q->tab; + if (old) { + unsigned int oqlen = sch->q.qlen, tail = 0; + + while (q->head != q->tail) { + struct sk_buff *skb = q->tab[q->head]; + + q->head = (q->head + 1) & q->tab_mask; + if (!skb) + continue; + if (tail < mask) { + ntab[tail++] = skb; + continue; + } + sch->qstats.backlog -= qdisc_pkt_len(skb); + --sch->q.qlen; + qdisc_drop(skb, sch); + } + qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen); + q->head = 0; + q->tail = tail; + } + + q->tab_mask = mask; + q->tab = ntab; + } else + sch_tree_lock(sch); + + q->flags = ctl->flags; + q->limit = ctl->limit; + + red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Plog, ctl->Scell_log, + nla_data(tb[TCA_CHOKE_STAB])); + + if (q->head == q->tail) + red_end_of_idle_period(&q->parms); + + sch_tree_unlock(sch); + choke_free(old); + return 0; +} + +static int choke_init(struct Qdisc *sch, struct nlattr *opt) +{ + return choke_change(sch, opt); +} + +static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct nlattr *opts = NULL; + struct tc_red_qopt opt = { + .limit = q->limit, + .flags = q->flags, + .qth_min = q->parms.qth_min >> q->parms.Wlog, + .qth_max = q->parms.qth_max >> q->parms.Wlog, + .Wlog = q->parms.Wlog, + .Plog = q->parms.Plog, + .Scell_log = q->parms.Scell_log, + }; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + NLA_PUT(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt); + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct choke_sched_data *q = qdisc_priv(sch); + struct tc_choke_xstats st = { + .early = q->stats.prob_drop + q->stats.forced_drop, + .marked = q->stats.prob_mark + q->stats.forced_mark, + .pdrop = q->stats.pdrop, + .other = q->stats.other, + .matched = q->stats.matched, + }; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static void choke_destroy(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + tcf_destroy_chain(&q->filter_list); + choke_free(q->tab); +} + +static struct Qdisc *choke_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long choke_get(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static void choke_put(struct Qdisc *q, unsigned long cl) +{ +} + +static unsigned long choke_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static struct tcf_proto **choke_find_tcf(struct Qdisc *sch, unsigned long cl) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return &q->filter_list; +} + +static int choke_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static void choke_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + if (!arg->stop) { + if (arg->fn(sch, 1, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops choke_class_ops = { + .leaf = choke_leaf, + .get = choke_get, + .put = choke_put, + .tcf_chain = choke_find_tcf, + .bind_tcf = choke_bind, + .unbind_tcf = choke_put, + .dump = choke_dump_class, + .walk = choke_walk, +}; + +static struct sk_buff *choke_peek_head(struct Qdisc *sch) +{ + struct choke_sched_data *q = qdisc_priv(sch); + + return (q->head != q->tail) ? q->tab[q->head] : NULL; +} + +static struct Qdisc_ops choke_qdisc_ops __read_mostly = { + .id = "choke", + .priv_size = sizeof(struct choke_sched_data), + + .enqueue = choke_enqueue, + .dequeue = choke_dequeue, + .peek = choke_peek_head, + .drop = choke_drop, + .init = choke_init, + .destroy = choke_destroy, + .reset = choke_reset, + .change = choke_change, + .dump = choke_dump, + .dump_stats = choke_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init choke_module_init(void) +{ + return register_qdisc(&choke_qdisc_ops); +} + +static void __exit choke_module_exit(void) +{ + unregister_qdisc(&choke_qdisc_ops); +} + +module_init(choke_module_init) +module_exit(choke_module_exit) + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0f7bf3f..2c79020 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -137,10 +137,10 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, mask = nla_get_u8(tb[TCA_DSMARK_MASK]); if (tb[TCA_DSMARK_VALUE]) - p->value[*arg-1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); + p->value[*arg - 1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); if (tb[TCA_DSMARK_MASK]) - p->mask[*arg-1] = mask; + p->mask[*arg - 1] = mask; err = 0; @@ -155,8 +155,8 @@ static int dsmark_delete(struct Qdisc *sch, unsigned long arg) if (!dsmark_valid_index(p, arg)) return -EINVAL; - p->mask[arg-1] = 0xff; - p->value[arg-1] = 0; + p->mask[arg - 1] = 0xff; + p->value[arg - 1] = 0; return 0; } @@ -175,7 +175,7 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) if (p->mask[i] == 0xff && !p->value[i]) goto ignore; if (walker->count >= walker->skip) { - if (walker->fn(sch, i+1, walker) < 0) { + if (walker->fn(sch, i + 1, walker) < 0) { walker->stop = 1; break; } @@ -304,9 +304,8 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) * and don't need yet another qdisc as a bypass. */ if (p->mask[index] != 0xff || p->value[index]) - printk(KERN_WARNING - "dsmark_dequeue: unsupported protocol %d\n", - ntohs(skb->protocol)); + pr_warning("dsmark_dequeue: unsupported protocol %d\n", + ntohs(skb->protocol)); break; } @@ -424,14 +423,14 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, if (!dsmark_valid_index(p, cl)) return -EINVAL; - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl-1); + tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); tcm->tcm_info = p->q->handle; opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl-1]); - NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl-1]); + NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]); + NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl - 1]); return nla_nest_end(skb, opts); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index d468b47..be33f9d 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -19,12 +19,11 @@ /* 1 band FIFO pseudo-"scheduler" */ -struct fifo_sched_data -{ +struct fifo_sched_data { u32 limit; }; -static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fifo_sched_data *q = qdisc_priv(sch); @@ -34,7 +33,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) return qdisc_reshape_fail(skb, sch); } -static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fifo_sched_data *q = qdisc_priv(sch); @@ -44,7 +43,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) return qdisc_reshape_fail(skb, sch); } -static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fifo_sched_data *q = qdisc_priv(sch); @@ -62,11 +61,13 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) static int fifo_init(struct Qdisc *sch, struct nlattr *opt) { struct fifo_sched_data *q = qdisc_priv(sch); + bool bypass; + bool is_bfifo = sch->ops == &bfifo_qdisc_ops; if (opt == NULL) { u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1; - if (sch->ops == &bfifo_qdisc_ops) + if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); q->limit = limit; @@ -79,6 +80,15 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt) q->limit = ctl->limit; } + if (is_bfifo) + bypass = q->limit >= psched_mtu(qdisc_dev(sch)); + else + bypass = q->limit >= 1; + + if (bypass) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 34dc598..0da09d5 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -87,8 +87,8 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, */ kfree_skb(skb); if (net_ratelimit()) - printk(KERN_WARNING "Dead loop on netdevice %s, " - "fix it urgently!\n", dev_queue->dev->name); + pr_warning("Dead loop on netdevice %s, fix it urgently!\n", + dev_queue->dev->name); ret = qdisc_qlen(q); } else { /* @@ -137,8 +137,8 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, } else { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit())) - printk(KERN_WARNING "BUG %s code %d qlen %d\n", - dev->name, ret, q->q.qlen); + pr_warning("BUG %s code %d qlen %d\n", + dev->name, ret, q->q.qlen); ret = dev_requeue_skb(skb, q); } @@ -412,8 +412,9 @@ static struct Qdisc noqueue_qdisc = { }; -static const u8 prio2band[TC_PRIO_MAX+1] = - { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 }; +static const u8 prio2band[TC_PRIO_MAX + 1] = { + 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 +}; /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. @@ -445,7 +446,7 @@ static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv, return priv->q + band; } -static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc) { if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) { int band = prio2band[skb->priority & TC_PRIO_MAX]; @@ -460,7 +461,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) return qdisc_drop(skb, qdisc); } -static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int band = bitmap2band[priv->bitmap]; @@ -479,7 +480,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) return NULL; } -static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int band = bitmap2band[priv->bitmap]; @@ -493,7 +494,7 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) return NULL; } -static void pfifo_fast_reset(struct Qdisc* qdisc) +static void pfifo_fast_reset(struct Qdisc *qdisc) { int prio; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); @@ -510,7 +511,7 @@ static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; - memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1); + memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1); NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; @@ -526,6 +527,8 @@ static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) skb_queue_head_init(band2list(priv, prio)); + /* Can by-pass the queue discipline */ + qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } @@ -540,6 +543,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { .dump = pfifo_fast_dump, .owner = THIS_MODULE, }; +EXPORT_SYMBOL(pfifo_fast_ops); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops) @@ -630,7 +634,7 @@ void qdisc_destroy(struct Qdisc *qdisc) #ifdef CONFIG_NET_SCHED qdisc_list_del(qdisc); - qdisc_put_stab(qdisc->stab); + qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); if (ops->reset) @@ -674,25 +678,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, return oqdisc; } +EXPORT_SYMBOL(dev_graft_qdisc); static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { - struct Qdisc *qdisc; + struct Qdisc *qdisc = &noqueue_qdisc; if (dev->tx_queue_len) { qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_ROOT); if (!qdisc) { - printk(KERN_INFO "%s: activation failed\n", dev->name); + netdev_info(dev, "activation failed\n"); return; } - - /* Can by-pass the queue discipline for default qdisc */ - qdisc->flags |= TCQ_F_CAN_BYPASS; - } else { - qdisc = &noqueue_qdisc; } dev_queue->qdisc_sleeping = qdisc; } @@ -761,6 +761,7 @@ void dev_activate(struct net_device *dev) dev_watchdog_up(dev); } } +EXPORT_SYMBOL(dev_activate); static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, @@ -840,6 +841,7 @@ void dev_deactivate(struct net_device *dev) list_add(&dev->unreg_list, &single); dev_deactivate_many(&single); } +EXPORT_SYMBOL(dev_deactivate); static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 51dcc2a..b9493a0 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -32,8 +32,7 @@ struct gred_sched_data; struct gred_sched; -struct gred_sched_data -{ +struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop pramaters */ u32 bytesin; /* bytes seen on virtualQ so far*/ @@ -50,8 +49,7 @@ enum { GRED_RIO_MODE, }; -struct gred_sched -{ +struct gred_sched { struct gred_sched_data *tab[MAX_DPs]; unsigned long flags; u32 red_flags; @@ -150,17 +148,18 @@ static inline int gred_use_harddrop(struct gred_sched *t) return t->red_flags & TC_RED_HARDDROP; } -static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - struct gred_sched_data *q=NULL; - struct gred_sched *t= qdisc_priv(sch); + struct gred_sched_data *q = NULL; + struct gred_sched *t = qdisc_priv(sch); unsigned long qavg = 0; u16 dp = tc_index_to_dp(skb); - if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { + if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { dp = t->def; - if ((q = t->tab[dp]) == NULL) { + q = t->tab[dp]; + if (!q) { /* Pass through packets not assigned to a DP * if no default DP has been configured. This * allows for DP flows to be left untouched. @@ -183,7 +182,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) for (i = 0; i < t->DPs; i++) { if (t->tab[i] && t->tab[i]->prio < q->prio && !red_is_idling(&t->tab[i]->parms)) - qavg +=t->tab[i]->parms.qavg; + qavg += t->tab[i]->parms.qavg; } } @@ -203,28 +202,28 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) gred_store_wred_set(t, q); switch (red_action(&q->parms, q->parms.qavg + qavg)) { - case RED_DONT_MARK: - break; - - case RED_PROB_MARK: - sch->qstats.overlimits++; - if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; - goto congestion_drop; - } - - q->stats.prob_mark++; - break; - - case RED_HARD_MARK: - sch->qstats.overlimits++; - if (gred_use_harddrop(t) || !gred_use_ecn(t) || - !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; - goto congestion_drop; - } - q->stats.forced_mark++; - break; + case RED_DONT_MARK: + break; + + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + break; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (gred_use_harddrop(t) || !gred_use_ecn(t) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + q->stats.forced_mark++; + break; } if (q->backlog + qdisc_pkt_len(skb) <= q->limit) { @@ -241,7 +240,7 @@ congestion_drop: return NET_XMIT_CN; } -static struct sk_buff *gred_dequeue(struct Qdisc* sch) +static struct sk_buff *gred_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); @@ -254,9 +253,9 @@ static struct sk_buff *gred_dequeue(struct Qdisc* sch) if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { if (net_ratelimit()) - printk(KERN_WARNING "GRED: Unable to relocate " - "VQ 0x%x after dequeue, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + pr_warning("GRED: Unable to relocate VQ 0x%x " + "after dequeue, screwing up " + "backlog.\n", tc_index_to_dp(skb)); } else { q->backlog -= qdisc_pkt_len(skb); @@ -273,7 +272,7 @@ static struct sk_buff *gred_dequeue(struct Qdisc* sch) return NULL; } -static unsigned int gred_drop(struct Qdisc* sch) +static unsigned int gred_drop(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); @@ -286,9 +285,9 @@ static unsigned int gred_drop(struct Qdisc* sch) if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { if (net_ratelimit()) - printk(KERN_WARNING "GRED: Unable to relocate " - "VQ 0x%x while dropping, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + pr_warning("GRED: Unable to relocate VQ 0x%x " + "while dropping, screwing up " + "backlog.\n", tc_index_to_dp(skb)); } else { q->backlog -= len; q->stats.other++; @@ -308,7 +307,7 @@ static unsigned int gred_drop(struct Qdisc* sch) } -static void gred_reset(struct Qdisc* sch) +static void gred_reset(struct Qdisc *sch) { int i; struct gred_sched *t = qdisc_priv(sch); @@ -369,8 +368,8 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { - printk(KERN_WARNING "GRED: Warning: Destroying " - "shadowed VQ 0x%x\n", i); + pr_warning("GRED: Warning: Destroying " + "shadowed VQ 0x%x\n", i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 14a799d..6488e64 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -81,8 +81,7 @@ * that are expensive on 32-bit architectures. */ -struct internal_sc -{ +struct internal_sc { u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ @@ -92,8 +91,7 @@ struct internal_sc }; /* runtime service curve */ -struct runtime_sc -{ +struct runtime_sc { u64 x; /* current starting position on x-axis */ u64 y; /* current starting position on y-axis */ u64 sm1; /* scaled slope of the 1st segment */ @@ -104,15 +102,13 @@ struct runtime_sc u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; -enum hfsc_class_flags -{ +enum hfsc_class_flags { HFSC_RSC = 0x1, HFSC_FSC = 0x2, HFSC_USC = 0x4 }; -struct hfsc_class -{ +struct hfsc_class { struct Qdisc_class_common cl_common; unsigned int refcnt; /* usage count */ @@ -140,8 +136,8 @@ struct hfsc_class u64 cl_cumul; /* cumulative work in bytes done by real-time criteria */ - u64 cl_d; /* deadline*/ - u64 cl_e; /* eligible time */ + u64 cl_d; /* deadline*/ + u64 cl_e; /* eligible time */ u64 cl_vt; /* virtual time */ u64 cl_f; /* time when this class will fit for link-sharing, max(myf, cfmin) */ @@ -176,8 +172,7 @@ struct hfsc_class unsigned long cl_nactive; /* number of active children */ }; -struct hfsc_sched -{ +struct hfsc_sched { u16 defcls; /* default class id */ struct hfsc_class root; /* root class */ struct Qdisc_class_hash clhash; /* class hash */ @@ -693,7 +688,7 @@ init_vf(struct hfsc_class *cl, unsigned int len) if (go_active) { n = rb_last(&cl->cl_parent->vt_tree); if (n != NULL) { - max_cl = rb_entry(n, struct hfsc_class,vt_node); + max_cl = rb_entry(n, struct hfsc_class, vt_node); /* * set vt to the average of the min and max * classes. if the parent's period didn't @@ -1177,8 +1172,10 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) return NULL; } #endif - if ((cl = (struct hfsc_class *)res.class) == NULL) { - if ((cl = hfsc_find_class(res.classid, sch)) == NULL) + cl = (struct hfsc_class *)res.class; + if (!cl) { + cl = hfsc_find_class(res.classid, sch); + if (!cl) break; /* filter selected invalid classid */ if (cl->level >= head->level) break; /* filter may only point downwards */ @@ -1316,7 +1313,7 @@ hfsc_dump_sc(struct sk_buff *skb, int attr, struct internal_sc *sc) return -1; } -static inline int +static int hfsc_dump_curves(struct sk_buff *skb, struct hfsc_class *cl) { if ((cl->cl_flags & HFSC_RSC) && @@ -1420,7 +1417,8 @@ hfsc_schedule_watchdog(struct Qdisc *sch) struct hfsc_class *cl; u64 next_time = 0; - if ((cl = eltree_get_minel(q)) != NULL) + cl = eltree_get_minel(q); + if (cl) next_time = cl->cl_e; if (q->root.cl_cfmin != 0) { if (next_time == 0 || next_time > q->root.cl_cfmin) @@ -1625,7 +1623,8 @@ hfsc_dequeue(struct Qdisc *sch) * find the class with the minimum deadline among * the eligible classes. */ - if ((cl = eltree_get_mindl(q, cur_time)) != NULL) { + cl = eltree_get_mindl(q, cur_time); + if (cl) { realtime = 1; } else { /* @@ -1664,7 +1663,7 @@ hfsc_dequeue(struct Qdisc *sch) set_passive(cl); } - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index fc12fe6..e1429a8 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -99,9 +99,10 @@ struct htb_class { struct rb_root feed[TC_HTB_NUMPRIO]; /* feed trees */ struct rb_node *ptr[TC_HTB_NUMPRIO]; /* current class ptr */ /* When class changes from state 1->2 and disconnects from - parent's feed then we lost ptr value and start from the - first child again. Here we store classid of the - last valid ptr (used when ptr is NULL). */ + * parent's feed then we lost ptr value and start from the + * first child again. Here we store classid of the + * last valid ptr (used when ptr is NULL). + */ u32 last_ptr_id[TC_HTB_NUMPRIO]; } inner; } un; @@ -185,7 +186,7 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessfull * then finish and return direct queue. */ -#define HTB_DIRECT (struct htb_class*)-1 +#define HTB_DIRECT ((struct htb_class *)-1L) static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) @@ -197,11 +198,13 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int result; /* allow to select class by setting skb->priority to valid classid; - note that nfmark can be used too by attaching filter fw with no - rules in it */ + * note that nfmark can be used too by attaching filter fw with no + * rules in it + */ if (skb->priority == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) selected */ - if ((cl = htb_find(skb->priority, sch)) != NULL && cl->level == 0) + cl = htb_find(skb->priority, sch); + if (cl && cl->level == 0) return cl; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; @@ -216,10 +219,12 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, return NULL; } #endif - if ((cl = (void *)res.class) == NULL) { + cl = (void *)res.class; + if (!cl) { if (res.classid == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) */ - if ((cl = htb_find(res.classid, sch)) == NULL) + cl = htb_find(res.classid, sch); + if (!cl) break; /* filter selected invalid classid */ } if (!cl->level) @@ -378,7 +383,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) if (p->un.inner.feed[prio].rb_node) /* parent already has its feed in use so that - reset bit in mask as parent is already ok */ + * reset bit in mask as parent is already ok + */ mask &= ~(1 << prio); htb_add_to_id_tree(p->un.inner.feed + prio, cl, prio); @@ -413,8 +419,9 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) if (p->un.inner.ptr[prio] == cl->node + prio) { /* we are removing child which is pointed to from - parent feed - forget the pointer but remember - classid */ + * parent feed - forget the pointer but remember + * classid + */ p->un.inner.last_ptr_id[prio] = cl->common.classid; p->un.inner.ptr[prio] = NULL; } @@ -663,8 +670,9 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, unsigned long start) { /* don't run for longer than 2 jiffies; 2 is used instead of - 1 to simplify things when jiffy is going to be incremented - too soon */ + * 1 to simplify things when jiffy is going to be incremented + * too soon + */ unsigned long stop_at = start + 2; while (time_before(jiffies, stop_at)) { struct htb_class *cl; @@ -687,7 +695,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, /* too much load - let's continue after a break for scheduling */ if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) { - printk(KERN_WARNING "htb: too many events!\n"); + pr_warning("htb: too many events!\n"); q->warned |= HTB_WARN_TOOMANYEVENTS; } @@ -695,7 +703,8 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, } /* Returns class->node+prio from id-tree where classe's id is >= id. NULL - is no such one exists. */ + * is no such one exists. + */ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, u32 id) { @@ -739,12 +748,14 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, for (i = 0; i < 65535; i++) { if (!*sp->pptr && *sp->pid) { /* ptr was invalidated but id is valid - try to recover - the original or next ptr */ + * the original or next ptr + */ *sp->pptr = htb_id_find_next_upper(prio, sp->root, *sp->pid); } *sp->pid = 0; /* ptr is valid now so that remove this hint as it - can become out of date quickly */ + * can become out of date quickly + */ if (!*sp->pptr) { /* we are at right end; rewind & go up */ *sp->pptr = sp->root; while ((*sp->pptr)->rb_left) @@ -772,7 +783,8 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, } /* dequeues packet at given priority and level; call only if - you are sure that there is active class at prio/level */ + * you are sure that there is active class at prio/level + */ static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio, int level) { @@ -789,9 +801,10 @@ next: return NULL; /* class can be empty - it is unlikely but can be true if leaf - qdisc drops packets in enqueue routine or if someone used - graft operation on the leaf since last dequeue; - simply deactivate and skip such class */ + * qdisc drops packets in enqueue routine or if someone used + * graft operation on the leaf since last dequeue; + * simply deactivate and skip such class + */ if (unlikely(cl->un.leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -831,7 +844,8 @@ next: ptr[0]) + prio); } /* this used to be after charge_class but this constelation - gives us slightly better performance */ + * gives us slightly better performance + */ if (!cl->un.leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); @@ -852,7 +866,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) if (skb != NULL) { ok: qdisc_bstats_update(sch, skb); - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); sch->q.qlen--; return skb; } @@ -883,6 +897,7 @@ ok: m = ~q->row_mask[level]; while (m != (int)(-1)) { int prio = ffz(m); + m |= 1 << prio; skb = htb_dequeue_tree(q, prio, level); if (likely(skb != NULL)) @@ -987,13 +1002,12 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) return err; if (tb[TCA_HTB_INIT] == NULL) { - printk(KERN_ERR "HTB: hey probably you have bad tc tool ?\n"); + pr_err("HTB: hey probably you have bad tc tool ?\n"); return -EINVAL; } gopt = nla_data(tb[TCA_HTB_INIT]); if (gopt->version != HTB_VER >> 16) { - printk(KERN_ERR - "HTB: need tc/htb version %d (minor is %d), you have %d\n", + pr_err("HTB: need tc/htb version %d (minor is %d), you have %d\n", HTB_VER >> 16, HTB_VER & 0xffff, gopt->version); return -EINVAL; } @@ -1206,9 +1220,10 @@ static void htb_destroy(struct Qdisc *sch) cancel_work_sync(&q->work); qdisc_watchdog_cancel(&q->watchdog); /* This line used to be after htb_destroy_class call below - and surprisingly it worked in 2.4. But it must precede it - because filter need its target class alive to be able to call - unbind_filter on it (without Oops). */ + * and surprisingly it worked in 2.4. But it must precede it + * because filter need its target class alive to be able to call + * unbind_filter on it (without Oops). + */ tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { @@ -1342,11 +1357,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* check maximal depth */ if (parent && parent->parent && parent->parent->level < 2) { - printk(KERN_ERR "htb: tree is too deep\n"); + pr_err("htb: tree is too deep\n"); goto failure; } err = -ENOBUFS; - if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL) + cl = kzalloc(sizeof(*cl), GFP_KERNEL); + if (!cl) goto failure; err = gen_new_estimator(&cl->bstats, &cl->rate_est, @@ -1366,8 +1382,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, RB_CLEAR_NODE(&cl->node[prio]); /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) - so that can't be used inside of sch_tree_lock - -- thanks to Karlis Peisenieks */ + * so that can't be used inside of sch_tree_lock + * -- thanks to Karlis Peisenieks + */ new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); sch_tree_lock(sch); @@ -1419,17 +1436,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } /* it used to be a nasty bug here, we have to check that node - is really leaf before changing cl->un.leaf ! */ + * is really leaf before changing cl->un.leaf ! + */ if (!cl->level) { cl->quantum = rtab->rate.rate / q->rate2quantum; if (!hopt->quantum && cl->quantum < 1000) { - printk(KERN_WARNING + pr_warning( "HTB: quantum of class %X is small. Consider r2q change.\n", cl->common.classid); cl->quantum = 1000; } if (!hopt->quantum && cl->quantum > 200000) { - printk(KERN_WARNING + pr_warning( "HTB: quantum of class %X is big. Consider r2q change.\n", cl->common.classid); cl->quantum = 200000; @@ -1478,13 +1496,13 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, struct htb_class *cl = htb_find(classid, sch); /*if (cl && !cl->level) return 0; - The line above used to be there to prevent attaching filters to - leaves. But at least tc_index filter uses this just to get class - for other reasons so that we have to allow for it. - ---- - 19.6.2002 As Werner explained it is ok - bind filter is just - another way to "lock" the class - unlike "get" this lock can - be broken by class during destroy IIUC. + * The line above used to be there to prevent attaching filters to + * leaves. But at least tc_index filter uses this just to get class + * for other reasons so that we have to allow for it. + * ---- + * 19.6.2002 As Werner explained it is ok - bind filter is just + * another way to "lock" the class - unlike "get" this lock can + * be broken by class during destroy IIUC. */ if (cl) cl->filter_cnt++; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index ecc302f..ec5cbc8 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -61,7 +61,6 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) TC_H_MIN(ntx + 1))); if (qdisc == NULL) goto err; - qdisc->flags |= TCQ_F_CAN_BYPASS; priv->qdiscs[ntx] = qdisc; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c new file mode 100644 index 0000000..ace37f9 --- /dev/null +++ b/net/sched/sch_mqprio.c @@ -0,0 +1,416 @@ +/* + * net/sched/sch_mqprio.c + * + * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct mqprio_sched { + struct Qdisc **qdiscs; + int hw_owned; +}; + +static void mqprio_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + unsigned int ntx; + + if (priv->qdiscs) { + for (ntx = 0; + ntx < dev->num_tx_queues && priv->qdiscs[ntx]; + ntx++) + qdisc_destroy(priv->qdiscs[ntx]); + kfree(priv->qdiscs); + } + + if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) + dev->netdev_ops->ndo_setup_tc(dev, 0); + else + netdev_set_num_tc(dev, 0); +} + +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int i, j; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) + return -EINVAL; + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i < TC_BITMASK + 1; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) + return -EINVAL; + } + + /* net_device does not support requested operation */ + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) + return -EINVAL; + + /* if hw owned qcount and qoffset are taken from LLD so + * no reason to verify them here + */ + if (qopt->hw) + return 0; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + !qopt->count[i] || + last > dev->real_num_tx_queues) + return -EINVAL; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (last > qopt->offset[j]) + return -EINVAL; + } + } + + return 0; +} + +static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + int i, err = -EOPNOTSUPP; + struct tc_mqprio_qopt *qopt = NULL; + + BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); + BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + if (nla_len(opt) < sizeof(*qopt)) + return -EINVAL; + + qopt = nla_data(opt); + if (mqprio_parse_opt(dev, qopt)) + return -EINVAL; + + /* pre-allocate qdisc, attachment can't fail */ + priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), + GFP_KERNEL); + if (priv->qdiscs == NULL) { + err = -ENOMEM; + goto err; + } + + for (i = 0; i < dev->num_tx_queues; i++) { + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1))); + if (qdisc == NULL) { + err = -ENOMEM; + goto err; + } + priv->qdiscs[i] = qdisc; + } + + /* If the mqprio options indicate that hardware should own + * the queue mapping then run ndo_setup_tc otherwise use the + * supplied and verified mapping + */ + if (qopt->hw) { + priv->hw_owned = 1; + err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc); + if (err) + goto err; + } else { + netdev_set_num_tc(dev, qopt->num_tc); + for (i = 0; i < qopt->num_tc; i++) + netdev_set_tc_queue(dev, i, + qopt->count[i], qopt->offset[i]); + } + + /* Always use supplied priority mappings */ + for (i = 0; i < TC_BITMASK + 1; i++) + netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]); + + sch->flags |= TCQ_F_MQROOT; + return 0; + +err: + mqprio_destroy(sch); + return err; +} + +static void mqprio_attach(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + struct Qdisc *qdisc; + unsigned int ntx; + + /* Attach underlying qdisc */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = priv->qdiscs[ntx]; + qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (qdisc) + qdisc_destroy(qdisc); + } + kfree(priv->qdiscs); + priv->qdiscs = NULL; +} + +static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + + if (ntx >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, ntx); +} + +static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, + struct Qdisc **old) +{ + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = dev_graft_qdisc(dev_queue, new); + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + unsigned char *b = skb_tail_pointer(skb); + struct tc_mqprio_qopt opt = { 0 }; + struct Qdisc *qdisc; + unsigned int i; + + sch->q.qlen = 0; + memset(&sch->bstats, 0, sizeof(sch->bstats)); + memset(&sch->qstats, 0, sizeof(sch->qstats)); + + for (i = 0; i < dev->num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + spin_lock_bh(qdisc_lock(qdisc)); + sch->q.qlen += qdisc->q.qlen; + sch->bstats.bytes += qdisc->bstats.bytes; + sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.qlen += qdisc->qstats.qlen; + sch->qstats.backlog += qdisc->qstats.backlog; + sch->qstats.drops += qdisc->qstats.drops; + sch->qstats.requeues += qdisc->qstats.requeues; + sch->qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + + opt.num_tc = netdev_get_num_tc(dev); + memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + opt.hw = priv->hw_owned; + + for (i = 0; i < netdev_get_num_tc(dev); i++) { + opt.count[i] = dev->tc_to_txq[i].count; + opt.offset[i] = dev->tc_to_txq[i].offset; + } + + NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + + return skb->len; +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + if (!dev_queue) + return NULL; + + return dev_queue->qdisc_sleeping; +} + +static unsigned long mqprio_get(struct Qdisc *sch, u32 classid) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx = TC_H_MIN(classid); + + if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) + return 0; + return ntx; +} + +static void mqprio_put(struct Qdisc *sch, unsigned long cl) +{ +} + +static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct net_device *dev = qdisc_dev(sch); + + if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_info = 0; + } else { + int i; + struct netdev_queue *dev_queue; + + dev_queue = mqprio_queue_get(sch, cl); + tcm->tcm_parent = 0; + for (i = 0; i < netdev_get_num_tc(dev); i++) { + struct netdev_tc_txq tc = dev->tc_to_txq[i]; + int q_idx = cl - netdev_get_num_tc(dev); + + if (q_idx > tc.offset && + q_idx <= tc.offset + tc.count) { + tcm->tcm_parent = + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)); + break; + } + } + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct net_device *dev = qdisc_dev(sch); + + if (cl <= netdev_get_num_tc(dev)) { + int i; + struct Qdisc *qdisc; + struct gnet_stats_queue qstats = {0}; + struct gnet_stats_basic_packed bstats = {0}; + struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + + /* Drop lock here it will be reclaimed before touching + * statistics this is required because the d->lock we + * hold here is the look on dev_queue->qdisc_sleeping + * also acquired below. + */ + spin_unlock_bh(d->lock); + + for (i = tc.offset; i < tc.offset + tc.count; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + spin_lock_bh(qdisc_lock(qdisc)); + bstats.bytes += qdisc->bstats.bytes; + bstats.packets += qdisc->bstats.packets; + qstats.qlen += qdisc->qstats.qlen; + qstats.backlog += qdisc->qstats.backlog; + qstats.drops += qdisc->qstats.drops; + qstats.requeues += qdisc->qstats.requeues; + qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + /* Reclaim root sleeping lock before completing stats */ + spin_lock_bh(d->lock); + if (gnet_stats_copy_basic(d, &bstats) < 0 || + gnet_stats_copy_queue(d, &qstats) < 0) + return -1; + } else { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + sch->qstats.qlen = sch->q.qlen; + if (gnet_stats_copy_basic(d, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, &sch->qstats) < 0) + return -1; + } + return 0; +} + +static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + /* Walk hierarchy with a virtual class per tc */ + arg->count = arg->skip; + for (ntx = arg->skip; + ntx < dev->num_tx_queues + netdev_get_num_tc(dev); + ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops mqprio_class_ops = { + .graft = mqprio_graft, + .leaf = mqprio_leaf, + .get = mqprio_get, + .put = mqprio_put, + .walk = mqprio_walk, + .dump = mqprio_dump_class, + .dump_stats = mqprio_dump_class_stats, +}; + +struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { + .cl_ops = &mqprio_class_ops, + .id = "mqprio", + .priv_size = sizeof(struct mqprio_sched), + .init = mqprio_init, + .destroy = mqprio_destroy, + .attach = mqprio_attach, + .dump = mqprio_dump, + .owner = THIS_MODULE, +}; + +static int __init mqprio_module_init(void) +{ + return register_qdisc(&mqprio_qdisc_ops); +} + +static void __exit mqprio_module_exit(void) +{ + unregister_qdisc(&mqprio_qdisc_ops); +} + +module_init(mqprio_module_init); +module_exit(mqprio_module_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 436a2e7..edc1950 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -156,7 +156,7 @@ static unsigned int multiq_drop(struct Qdisc *sch) unsigned int len; struct Qdisc *qdisc; - for (band = q->bands-1; band >= 0; band--) { + for (band = q->bands - 1; band >= 0; band--) { qdisc = q->queues[band]; if (qdisc->ops->drop) { len = qdisc->ops->drop(qdisc); @@ -265,7 +265,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; - err = multiq_tune(sch,opt); + err = multiq_tune(sch, opt); if (err) kfree(q->queues); @@ -346,7 +346,7 @@ static int multiq_dump_class(struct Qdisc *sch, unsigned long cl, struct multiq_sched_data *q = qdisc_priv(sch); tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = q->queues[cl-1]->handle; + tcm->tcm_info = q->queues[cl - 1]->handle; return 0; } @@ -378,7 +378,7 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count++; continue; } - if (arg->fn(sch, band+1, arg) < 0) { + if (arg->fn(sch, band + 1, arg) < 0) { arg->stop = 1; break; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 6a3006b..64f0d32 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -211,8 +211,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } cb = netem_skb_cb(skb); - if (q->gap == 0 || /* not doing reordering */ - q->counter < q->gap || /* inside last reordering gap */ + if (q->gap == 0 || /* not doing reordering */ + q->counter < q->gap || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor)) { psched_time_t now; psched_tdiff_t delay; @@ -248,7 +248,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } -static unsigned int netem_drop(struct Qdisc* sch) +static unsigned int netem_drop(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); unsigned int len = 0; @@ -265,7 +265,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - if (sch->flags & TCQ_F_THROTTLED) + if (qdisc_is_throttled(sch)) return NULL; skb = q->qdisc->ops->peek(q->qdisc); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index fbd710d..2a318f2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -22,8 +22,7 @@ #include <net/pkt_sched.h> -struct prio_sched_data -{ +struct prio_sched_data { int bands; struct tcf_proto *filter_list; u8 prio2band[TC_PRIO_MAX+1]; @@ -54,7 +53,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) if (!q->filter_list || err < 0) { if (TC_H_MAJ(band)) band = 0; - return q->queues[q->prio2band[band&TC_PRIO_MAX]]; + return q->queues[q->prio2band[band & TC_PRIO_MAX]]; } band = res.classid; } @@ -106,7 +105,7 @@ static struct sk_buff *prio_peek(struct Qdisc *sch) return NULL; } -static struct sk_buff *prio_dequeue(struct Qdisc* sch) +static struct sk_buff *prio_dequeue(struct Qdisc *sch) { struct prio_sched_data *q = qdisc_priv(sch); int prio; @@ -124,7 +123,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc* sch) } -static unsigned int prio_drop(struct Qdisc* sch) +static unsigned int prio_drop(struct Qdisc *sch) { struct prio_sched_data *q = qdisc_priv(sch); int prio; @@ -143,24 +142,24 @@ static unsigned int prio_drop(struct Qdisc* sch) static void -prio_reset(struct Qdisc* sch) +prio_reset(struct Qdisc *sch) { int prio; struct prio_sched_data *q = qdisc_priv(sch); - for (prio=0; prio<q->bands; prio++) + for (prio = 0; prio < q->bands; prio++) qdisc_reset(q->queues[prio]); sch->q.qlen = 0; } static void -prio_destroy(struct Qdisc* sch) +prio_destroy(struct Qdisc *sch) { int prio; struct prio_sched_data *q = qdisc_priv(sch); tcf_destroy_chain(&q->filter_list); - for (prio=0; prio<q->bands; prio++) + for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -177,7 +176,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2) return -EINVAL; - for (i=0; i<=TC_PRIO_MAX; i++) { + for (i = 0; i <= TC_PRIO_MAX; i++) { if (qopt->priomap[i] >= qopt->bands) return -EINVAL; } @@ -186,7 +185,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); - for (i=q->bands; i<TCQ_PRIO_BANDS; i++) { + for (i = q->bands; i < TCQ_PRIO_BANDS; i++) { struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; if (child != &noop_qdisc) { @@ -196,9 +195,10 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) } sch_tree_unlock(sch); - for (i=0; i<q->bands; i++) { + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); @@ -224,7 +224,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) struct prio_sched_data *q = qdisc_priv(sch); int i; - for (i=0; i<TCQ_PRIO_BANDS; i++) + for (i = 0; i < TCQ_PRIO_BANDS; i++) q->queues[i] = &noop_qdisc; if (opt == NULL) { @@ -232,7 +232,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) } else { int err; - if ((err= prio_tune(sch, opt)) != 0) + if ((err = prio_tune(sch, opt)) != 0) return err; } return 0; @@ -245,7 +245,7 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_prio_qopt opt; opt.bands = q->bands; - memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1); + memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1); NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); @@ -342,7 +342,7 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count++; continue; } - if (arg->fn(sch, prio+1, arg) < 0) { + if (arg->fn(sch, prio + 1, arg) < 0) { arg->stop = 1; break; } @@ -350,7 +350,7 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto ** prio_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 9f98dbd..6649463 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -36,8 +36,7 @@ if RED works correctly. */ -struct red_sched_data -{ +struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct red_parms parms; @@ -55,7 +54,7 @@ static inline int red_use_harddrop(struct red_sched_data *q) return q->flags & TC_RED_HARDDROP; } -static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -67,29 +66,29 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) red_end_of_idle_period(&q->parms); switch (red_action(&q->parms, q->parms.qavg)) { - case RED_DONT_MARK: - break; - - case RED_PROB_MARK: - sch->qstats.overlimits++; - if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; - goto congestion_drop; - } - - q->stats.prob_mark++; - break; - - case RED_HARD_MARK: - sch->qstats.overlimits++; - if (red_use_harddrop(q) || !red_use_ecn(q) || - !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; - goto congestion_drop; - } - - q->stats.forced_mark++; - break; + case RED_DONT_MARK: + break; + + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + break; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (red_use_harddrop(q) || !red_use_ecn(q) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + q->stats.forced_mark++; + break; } ret = qdisc_enqueue(skb, child); @@ -106,7 +105,7 @@ congestion_drop: return NET_XMIT_CN; } -static struct sk_buff * red_dequeue(struct Qdisc* sch) +static struct sk_buff *red_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct red_sched_data *q = qdisc_priv(sch); @@ -123,7 +122,7 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch) return skb; } -static struct sk_buff * red_peek(struct Qdisc* sch) +static struct sk_buff *red_peek(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -131,7 +130,7 @@ static struct sk_buff * red_peek(struct Qdisc* sch) return child->ops->peek(child); } -static unsigned int red_drop(struct Qdisc* sch) +static unsigned int red_drop(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -150,7 +149,7 @@ static unsigned int red_drop(struct Qdisc* sch) return 0; } -static void red_reset(struct Qdisc* sch) +static void red_reset(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); @@ -217,7 +216,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int red_init(struct Qdisc* sch, struct nlattr *opt) +static int red_init(struct Qdisc *sch, struct nlattr *opt) { struct red_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index edea8ce..c2e628d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -21,6 +21,7 @@ #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> @@ -76,7 +77,8 @@ #define SFQ_DEPTH 128 /* max number of packets per flow */ #define SFQ_SLOTS 128 /* max number of flows */ #define SFQ_EMPTY_SLOT 255 -#define SFQ_HASH_DIVISOR 1024 +#define SFQ_DEFAULT_HASH_DIVISOR 1024 + /* We use 16 bits to store allot, and want to handle packets up to 64K * Scale allot by 8 (1<<3) so that no overflow occurs. */ @@ -92,8 +94,7 @@ typedef unsigned char sfq_index; * while following values [SFQ_SLOTS ... SFQ_SLOTS + SFQ_DEPTH - 1] * are 'pointers' to dep[] array */ -struct sfq_head -{ +struct sfq_head { sfq_index next; sfq_index prev; }; @@ -108,13 +109,12 @@ struct sfq_slot { short allot; /* credit for this slot */ }; -struct sfq_sched_data -{ +struct sfq_sched_data { /* Parameters */ int perturb_period; - unsigned quantum; /* Allotment per round: MUST BE >= MTU */ + unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ int limit; - + unsigned int divisor; /* number of slots in hash table */ /* Variables */ struct tcf_proto *filter_list; struct timer_list perturb_timer; @@ -122,7 +122,7 @@ struct sfq_sched_data sfq_index cur_depth; /* depth of longest slot */ unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct sfq_slot *tail; /* current slot in round */ - sfq_index ht[SFQ_HASH_DIVISOR]; /* Hash table */ + sfq_index *ht; /* Hash table (divisor slots) */ struct sfq_slot slots[SFQ_SLOTS]; struct sfq_head dep[SFQ_DEPTH]; /* Linked list of slots, indexed by depth */ }; @@ -137,12 +137,12 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index return &q->dep[val - SFQ_SLOTS]; } -static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) +static unsigned int sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) { - return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1); + return jhash_2words(h, h1, q->perturbation) & (q->divisor - 1); } -static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) +static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) { u32 h, h2; @@ -157,13 +157,13 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) iph = ip_hdr(skb); h = (__force u32)iph->daddr; h2 = (__force u32)iph->saddr ^ iph->protocol; - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) { iph = ip_hdr(skb); - h2 ^= *(u32*)((void *)iph + iph->ihl * 4 + poff); + h2 ^= *(u32 *)((void *)iph + iph->ihl * 4 + poff); } break; } @@ -181,7 +181,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) if (poff >= 0 && pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) { iph = ipv6_hdr(skb); - h2 ^= *(u32*)((void *)iph + sizeof(*iph) + poff); + h2 ^= *(u32 *)((void *)iph + sizeof(*iph) + poff); } break; } @@ -203,7 +203,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && - TC_H_MIN(skb->priority) <= SFQ_HASH_DIVISOR) + TC_H_MIN(skb->priority) <= q->divisor) return TC_H_MIN(skb->priority); if (!q->filter_list) @@ -221,7 +221,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return 0; } #endif - if (TC_H_MIN(res.classid) <= SFQ_HASH_DIVISOR) + if (TC_H_MIN(res.classid) <= q->divisor) return TC_H_MIN(res.classid); } return 0; @@ -491,13 +491,18 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (opt->nla_len < nla_attr_size(sizeof(*ctl))) return -EINVAL; + if (ctl->divisor && + (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) + return -EINVAL; + sch_tree_lock(sch); q->quantum = ctl->quantum ? : psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = ctl->perturb_period * HZ; if (ctl->limit) q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1); - + if (ctl->divisor) + q->divisor = ctl->divisor; qlen = sch->q.qlen; while (sch->q.qlen > q->limit) sfq_drop(sch); @@ -515,15 +520,13 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) static int sfq_init(struct Qdisc *sch, struct nlattr *opt) { struct sfq_sched_data *q = qdisc_priv(sch); + size_t sz; int i; q->perturb_timer.function = sfq_perturbation; q->perturb_timer.data = (unsigned long)sch; init_timer_deferrable(&q->perturb_timer); - for (i = 0; i < SFQ_HASH_DIVISOR; i++) - q->ht[i] = SFQ_EMPTY_SLOT; - for (i = 0; i < SFQ_DEPTH; i++) { q->dep[i].next = i + SFQ_SLOTS; q->dep[i].prev = i + SFQ_SLOTS; @@ -532,6 +535,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->limit = SFQ_DEPTH - 1; q->cur_depth = 0; q->tail = NULL; + q->divisor = SFQ_DEFAULT_HASH_DIVISOR; if (opt == NULL) { q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); @@ -543,10 +547,23 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) return err; } + sz = sizeof(q->ht[0]) * q->divisor; + q->ht = kmalloc(sz, GFP_KERNEL); + if (!q->ht && sz > PAGE_SIZE) + q->ht = vmalloc(sz); + if (!q->ht) + return -ENOMEM; + for (i = 0; i < q->divisor; i++) + q->ht[i] = SFQ_EMPTY_SLOT; + for (i = 0; i < SFQ_SLOTS; i++) { slot_queue_init(&q->slots[i]); sfq_link(q, i); } + if (q->limit >= 1) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } @@ -557,6 +574,10 @@ static void sfq_destroy(struct Qdisc *sch) tcf_destroy_chain(&q->filter_list); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); + if (is_vmalloc_addr(q->ht)) + vfree(q->ht); + else + kfree(q->ht); } static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -569,7 +590,7 @@ static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) opt.perturb_period = q->perturb_period / HZ; opt.limit = q->limit; - opt.divisor = SFQ_HASH_DIVISOR; + opt.divisor = q->divisor; opt.flows = q->limit; NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); @@ -594,6 +615,8 @@ static unsigned long sfq_get(struct Qdisc *sch, u32 classid) static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { + /* we cannot bypass queue discipline anymore */ + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } @@ -647,7 +670,7 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) if (arg->stop) return; - for (i = 0; i < SFQ_HASH_DIVISOR; i++) { + for (i = 0; i < q->divisor; i++) { if (q->ht[i] == SFQ_EMPTY_SLOT || arg->count < arg->skip) { arg->count++; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index e931658..1dcfb52 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -97,8 +97,7 @@ changed the limit is not effective anymore. */ -struct tbf_sched_data -{ +struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ u32 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ @@ -115,10 +114,10 @@ struct tbf_sched_data struct qdisc_watchdog watchdog; /* Watchdog timer */ }; -#define L2T(q,L) qdisc_l2t((q)->R_tab,L) -#define L2T_P(q,L) qdisc_l2t((q)->P_tab,L) +#define L2T(q, L) qdisc_l2t((q)->R_tab, L) +#define L2T_P(q, L) qdisc_l2t((q)->P_tab, L) -static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); int ret; @@ -137,7 +136,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) return NET_XMIT_SUCCESS; } -static unsigned int tbf_drop(struct Qdisc* sch) +static unsigned int tbf_drop(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); unsigned int len = 0; @@ -149,7 +148,7 @@ static unsigned int tbf_drop(struct Qdisc* sch) return len; } -static struct sk_buff *tbf_dequeue(struct Qdisc* sch) +static struct sk_buff *tbf_dequeue(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; @@ -185,7 +184,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) q->tokens = toks; q->ptokens = ptoks; sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); return skb; } @@ -209,7 +208,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) return NULL; } -static void tbf_reset(struct Qdisc* sch) +static void tbf_reset(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -227,7 +226,7 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, }; -static int tbf_change(struct Qdisc* sch, struct nlattr *opt) +static int tbf_change(struct Qdisc *sch, struct nlattr *opt) { int err; struct tbf_sched_data *q = qdisc_priv(sch); @@ -236,7 +235,7 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt) struct qdisc_rate_table *rtab = NULL; struct qdisc_rate_table *ptab = NULL; struct Qdisc *child = NULL; - int max_size,n; + int max_size, n; err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy); if (err < 0) @@ -259,15 +258,18 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt) } for (n = 0; n < 256; n++) - if (rtab->data[n] > qopt->buffer) break; - max_size = (n << qopt->rate.cell_log)-1; + if (rtab->data[n] > qopt->buffer) + break; + max_size = (n << qopt->rate.cell_log) - 1; if (ptab) { int size; for (n = 0; n < 256; n++) - if (ptab->data[n] > qopt->mtu) break; - size = (n << qopt->peakrate.cell_log)-1; - if (size < max_size) max_size = size; + if (ptab->data[n] > qopt->mtu) + break; + size = (n << qopt->peakrate.cell_log) - 1; + if (size < max_size) + max_size = size; } if (max_size < 0) goto done; @@ -310,7 +312,7 @@ done: return err; } -static int tbf_init(struct Qdisc* sch, struct nlattr *opt) +static int tbf_init(struct Qdisc *sch, struct nlattr *opt) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -422,8 +424,7 @@ static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static const struct Qdisc_class_ops tbf_class_ops = -{ +static const struct Qdisc_class_ops tbf_class_ops = { .graft = tbf_graft, .leaf = tbf_leaf, .get = tbf_get, diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index d84e732..45cd300 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -53,8 +53,7 @@ which will not break load balancing, though native slave traffic will have the highest priority. */ -struct teql_master -{ +struct teql_master { struct Qdisc_ops qops; struct net_device *dev; struct Qdisc *slaves; @@ -65,22 +64,21 @@ struct teql_master unsigned long tx_dropped; }; -struct teql_sched_data -{ +struct teql_sched_data { struct Qdisc *next; struct teql_master *m; struct neighbour *ncache; struct sk_buff_head q; }; -#define NEXT_SLAVE(q) (((struct teql_sched_data*)qdisc_priv(q))->next) +#define NEXT_SLAVE(q) (((struct teql_sched_data *)qdisc_priv(q))->next) -#define FMASK (IFF_BROADCAST|IFF_POINTOPOINT) +#define FMASK (IFF_BROADCAST | IFF_POINTOPOINT) /* "teql*" qdisc routines */ static int -teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) +teql_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct teql_sched_data *q = qdisc_priv(sch); @@ -96,7 +94,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) } static struct sk_buff * -teql_dequeue(struct Qdisc* sch) +teql_dequeue(struct Qdisc *sch) { struct teql_sched_data *dat = qdisc_priv(sch); struct netdev_queue *dat_queue; @@ -118,13 +116,13 @@ teql_dequeue(struct Qdisc* sch) } static struct sk_buff * -teql_peek(struct Qdisc* sch) +teql_peek(struct Qdisc *sch) { /* teql is meant to be used as root qdisc */ return NULL; } -static __inline__ void +static inline void teql_neigh_release(struct neighbour *n) { if (n) @@ -132,7 +130,7 @@ teql_neigh_release(struct neighbour *n) } static void -teql_reset(struct Qdisc* sch) +teql_reset(struct Qdisc *sch) { struct teql_sched_data *dat = qdisc_priv(sch); @@ -142,13 +140,14 @@ teql_reset(struct Qdisc* sch) } static void -teql_destroy(struct Qdisc* sch) +teql_destroy(struct Qdisc *sch) { struct Qdisc *q, *prev; struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; - if ((prev = master->slaves) != NULL) { + prev = master->slaves; + if (prev) { do { q = NEXT_SLAVE(prev); if (q == sch) { @@ -180,7 +179,7 @@ teql_destroy(struct Qdisc* sch) static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); - struct teql_master *m = (struct teql_master*)sch->ops; + struct teql_master *m = (struct teql_master *)sch->ops; struct teql_sched_data *q = qdisc_priv(sch); if (dev->hard_header_len > m->dev->hard_header_len) @@ -291,7 +290,8 @@ restart: nores = 0; busy = 0; - if ((q = start) == NULL) + q = start; + if (!q) goto drop; do { @@ -356,10 +356,10 @@ drop: static int teql_master_open(struct net_device *dev) { - struct Qdisc * q; + struct Qdisc *q; struct teql_master *m = netdev_priv(dev); int mtu = 0xFFFE; - unsigned flags = IFF_NOARP|IFF_MULTICAST; + unsigned int flags = IFF_NOARP | IFF_MULTICAST; if (m->slaves == NULL) return -EUNATCH; @@ -427,7 +427,7 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu) do { if (new_mtu > qdisc_dev(q)->mtu) return -EINVAL; - } while ((q=NEXT_SLAVE(q)) != m->slaves); + } while ((q = NEXT_SLAVE(q)) != m->slaves); } dev->mtu = new_mtu; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dd419d2..d8d98d5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1475,6 +1475,12 @@ restart: goto out_free; } + if (sk_filter(other, skb) < 0) { + /* Toss the packet but do not return any error to the sender */ + err = len; + goto out_free; + } + unix_state_lock(other); err = -EPERM; if (!unix_may_send(sk, other)) @@ -1978,36 +1984,38 @@ static int unix_shutdown(struct socket *sock, int mode) mode = (mode+1)&(RCV_SHUTDOWN|SEND_SHUTDOWN); - if (mode) { - unix_state_lock(sk); - sk->sk_shutdown |= mode; - other = unix_peer(sk); - if (other) - sock_hold(other); - unix_state_unlock(sk); - sk->sk_state_change(sk); - - if (other && - (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) { - - int peer_mode = 0; - - if (mode&RCV_SHUTDOWN) - peer_mode |= SEND_SHUTDOWN; - if (mode&SEND_SHUTDOWN) - peer_mode |= RCV_SHUTDOWN; - unix_state_lock(other); - other->sk_shutdown |= peer_mode; - unix_state_unlock(other); - other->sk_state_change(other); - if (peer_mode == SHUTDOWN_MASK) - sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); - else if (peer_mode & RCV_SHUTDOWN) - sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); - } - if (other) - sock_put(other); + if (!mode) + return 0; + + unix_state_lock(sk); + sk->sk_shutdown |= mode; + other = unix_peer(sk); + if (other) + sock_hold(other); + unix_state_unlock(sk); + sk->sk_state_change(sk); + + if (other && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) { + + int peer_mode = 0; + + if (mode&RCV_SHUTDOWN) + peer_mode |= SEND_SHUTDOWN; + if (mode&SEND_SHUTDOWN) + peer_mode |= RCV_SHUTDOWN; + unix_state_lock(other); + other->sk_shutdown |= peer_mode; + unix_state_unlock(other); + other->sk_state_change(other); + if (peer_mode == SHUTDOWN_MASK) + sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); + else if (peer_mode & RCV_SHUTDOWN) + sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); } + if (other) + sock_put(other); + return 0; } diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 74944a2..788a12c 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -59,8 +59,6 @@ #include <asm/uaccess.h> /* copy_to/from_user */ #include <linux/init.h> /* __initfunc et al. */ -#define KMEM_SAFETYZONE 8 - #define DEV_TO_SLAVE(dev) (*((struct net_device **)netdev_priv(dev))) /* diff --git a/net/wireless/core.c b/net/wireless/core.c index e9a5f8c..fe01de2 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -718,13 +718,6 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, wdev->ps = false; /* allow mac80211 to determine the timeout */ wdev->ps_timeout = -1; - if (rdev->ops->set_power_mgmt) - if (rdev->ops->set_power_mgmt(wdev->wiphy, dev, - wdev->ps, - wdev->ps_timeout)) { - /* assume this means it's off */ - wdev->ps = false; - } if (!dev->ethtool_ops) dev->ethtool_ops = &cfg80211_ethtool_ops; @@ -813,6 +806,19 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, rdev->opencount++; mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); + + /* + * Configure power management to the driver here so that its + * correctly set also after interface type changes etc. + */ + if (wdev->iftype == NL80211_IFTYPE_STATION && + rdev->ops->set_power_mgmt) + if (rdev->ops->set_power_mgmt(wdev->wiphy, dev, + wdev->ps, + wdev->ps_timeout)) { + /* assume this means it's off */ + wdev->ps = false; + } break; case NETDEV_UNREGISTER: /* diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9b62710..864ddfb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2718,7 +2718,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_GET_MESH_CONFIG); if (!hdr) - goto nla_put_failure; + goto out; pinfoattr = nla_nest_start(msg, NL80211_ATTR_MESH_CONFIG); if (!pinfoattr) goto nla_put_failure; @@ -2759,6 +2759,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, nla_put_failure: genlmsg_cancel(msg, hdr); + out: nlmsg_free(msg); return -ENOBUFS; } @@ -2954,7 +2955,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_GET_REG); if (!hdr) - goto nla_put_failure; + goto put_failure; NLA_PUT_STRING(msg, NL80211_ATTR_REG_ALPHA2, cfg80211_regdomain->alpha2); @@ -3001,6 +3002,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) nla_put_failure: genlmsg_cancel(msg, hdr); +put_failure: nlmsg_free(msg); err = -EMSGSIZE; out: diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 37693b6..c565689 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1801,9 +1801,9 @@ void regulatory_hint_disconnect(void) static bool freq_is_chan_12_13_14(u16 freq) { - if (freq == ieee80211_channel_to_frequency(12) || - freq == ieee80211_channel_to_frequency(13) || - freq == ieee80211_channel_to_frequency(14)) + if (freq == ieee80211_channel_to_frequency(12, IEEE80211_BAND_2GHZ) || + freq == ieee80211_channel_to_frequency(13, IEEE80211_BAND_2GHZ) || + freq == ieee80211_channel_to_frequency(14, IEEE80211_BAND_2GHZ)) return true; return false; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 7620ae2..6a750bc 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -29,29 +29,37 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, } EXPORT_SYMBOL(ieee80211_get_response_rate); -int ieee80211_channel_to_frequency(int chan) +int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band) { - if (chan < 14) - return 2407 + chan * 5; - - if (chan == 14) - return 2484; - - /* FIXME: 802.11j 17.3.8.3.2 */ - return (chan + 1000) * 5; + /* see 802.11 17.3.8.3.2 and Annex J + * there are overlapping channel numbers in 5GHz and 2GHz bands */ + if (band == IEEE80211_BAND_5GHZ) { + if (chan >= 182 && chan <= 196) + return 4000 + chan * 5; + else + return 5000 + chan * 5; + } else { /* IEEE80211_BAND_2GHZ */ + if (chan == 14) + return 2484; + else if (chan < 14) + return 2407 + chan * 5; + else + return 0; /* not supported */ + } } EXPORT_SYMBOL(ieee80211_channel_to_frequency); int ieee80211_frequency_to_channel(int freq) { + /* see 802.11 17.3.8.3.2 and Annex J */ if (freq == 2484) return 14; - - if (freq < 2484) + else if (freq < 2484) return (freq - 2407) / 5; - - /* FIXME: 802.11j 17.3.8.3.2 */ - return freq/5 - 1000; + else if (freq >= 4910 && freq <= 4980) + return (freq - 4000) / 5; + else + return (freq - 5000) / 5; } EXPORT_SYMBOL(ieee80211_frequency_to_channel); @@ -159,12 +167,15 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, /* * Disallow pairwise keys with non-zero index unless it's WEP - * (because current deployments use pairwise WEP keys with - * non-zero indizes but 802.11i clearly specifies to use zero) + * or a vendor specific cipher (because current deployments use + * pairwise WEP keys with non-zero indices and for vendor specific + * ciphers this should be validated in the driver or hardware level + * - but 802.11i clearly specifies to use zero) */ if (pairwise && key_idx && - params->cipher != WLAN_CIPHER_SUITE_WEP40 && - params->cipher != WLAN_CIPHER_SUITE_WEP104) + ((params->cipher == WLAN_CIPHER_SUITE_TKIP) || + (params->cipher == WLAN_CIPHER_SUITE_CCMP) || + (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC))) return -EINVAL; switch (params->cipher) { diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 3e5dbd4..7f1f4ec 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -267,9 +267,12 @@ int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq) * -EINVAL for impossible things. */ if (freq->e == 0) { + enum ieee80211_band band = IEEE80211_BAND_2GHZ; if (freq->m < 0) return 0; - return ieee80211_channel_to_frequency(freq->m); + if (freq->m > 14) + band = IEEE80211_BAND_5GHZ; + return ieee80211_channel_to_frequency(freq->m, band); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6459588..7a8e2c7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1340,7 +1340,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops); + xdst = dst_alloc(dst_ops, 0); xfrm_policy_put_afinfo(afinfo); if (likely(xdst)) |