diff options
89 files changed, 1081 insertions, 361 deletions
diff --git a/Documentation/devicetree/bindings/net/sti-dwmac.txt b/Documentation/devicetree/bindings/net/sti-dwmac.txt new file mode 100644 index 0000000..3dd3d0b --- /dev/null +++ b/Documentation/devicetree/bindings/net/sti-dwmac.txt @@ -0,0 +1,58 @@ +STMicroelectronics SoC DWMAC glue layer controller + +The device node has following properties. + +Required properties: + - compatible : Can be "st,stih415-dwmac", "st,stih416-dwmac" or + "st,stid127-dwmac". + - reg : Offset of the glue configuration register map in system + configuration regmap pointed by st,syscon property and size. + + - reg-names : Should be "sti-ethconf". + + - st,syscon : Should be phandle to system configuration node which + encompases this glue registers. + + - st,tx-retime-src: On STi Parts for Giga bit speeds, 125Mhz clocks can be + wired up in from different sources. One via TXCLK pin and other via CLK_125 + pin. This wiring is totally board dependent. However the retiming glue + logic should be configured accordingly. Possible values for this property + + "txclk" - if 125Mhz clock is wired up via txclk line. + "clk_125" - if 125Mhz clock is wired up via clk_125 line. + + This property is only valid for Giga bit setup( GMII, RGMII), and it is + un-used for non-giga bit (MII and RMII) setups. Also note that internal + clockgen can not generate stable 125Mhz clock. + + - st,ext-phyclk: This boolean property indicates who is generating the clock + for tx and rx. This property is only valid for RMII case where the clock can + be generated from the MAC or PHY. + + - clock-names: should be "sti-ethclk". + - clocks: Should point to ethernet clockgen which can generate phyclk. + + +Example: + +ethernet0: dwmac@fe810000 { + device_type = "network"; + compatible = "st,stih416-dwmac", "snps,dwmac", "snps,dwmac-3.710"; + reg = <0xfe810000 0x8000>, <0x8bc 0x4>; + reg-names = "stmmaceth", "sti-ethconf"; + interrupts = <0 133 0>, <0 134 0>, <0 135 0>; + interrupt-names = "macirq", "eth_wake_irq", "eth_lpi"; + phy-mode = "mii"; + + st,syscon = <&syscfg_rear>; + + snps,pbl = <32>; + snps,mixed-burst; + + resets = <&softreset STIH416_ETH0_SOFTRESET>; + reset-names = "stmmaceth"; + pinctrl-0 = <&pinctrl_mii0>; + pinctrl-names = "default"; + clocks = <&CLK_S_GMAC0_PHY>; + clock-names = "stmmaceth"; +}; diff --git a/Documentation/networking/3c505.txt b/Documentation/networking/3c505.txt deleted file mode 100644 index 72f38b1..0000000 --- a/Documentation/networking/3c505.txt +++ /dev/null @@ -1,45 +0,0 @@ -The 3Com Etherlink Plus (3c505) driver. - -This driver now uses DMA. There is currently no support for PIO operation. -The default DMA channel is 6; this is _not_ autoprobed, so you must -make sure you configure it correctly. If loading the driver as a -module, you can do this with "modprobe 3c505 dma=n". If the driver is -linked statically into the kernel, you must either use an "ether=" -statement on the command line, or change the definition of ELP_DMA in 3c505.h. - -The driver will warn you if it has to fall back on the compiled in -default DMA channel. - -If no base address is given at boot time, the driver will autoprobe -ports 0x300, 0x280 and 0x310 (in that order). If no IRQ is given, the driver -will try to probe for it. - -The driver can be used as a loadable module. - -Theoretically, one instance of the driver can now run multiple cards, -in the standard way (when loading a module, say "modprobe 3c505 -io=0x300,0x340 irq=10,11 dma=6,7" or whatever). I have not tested -this, though. - -The driver may now support revision 2 hardware; the dependency on -being able to read the host control register has been removed. This -is also untested, since I don't have a suitable card. - -Known problems: - I still see "DMA upload timed out" messages from time to time. These -seem to be fairly non-fatal though. - The card is old and slow. - -To do: - Improve probe/setup code - Test multicast and promiscuous operation - -Authors: - The driver is mainly written by Craig Southeren, email - <craigs@ineluki.apana.org.au>. - Parts of the driver (adapting the driver to 1.1.4+ kernels, - IRQ/address detection, some changes) and this README by - Juha Laiho <jlaiho@ichaos.nullnet.fi>. - DMA mode, more fixes, etc, by Philip Blundell <pjb27@cam.ac.uk> - Multicard support, Software configurable DMA, etc., by - Christopher Collins <ccollins@pcug.org.au> diff --git a/MAINTAINERS b/MAINTAINERS index fb08dce..0dba50b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3324,6 +3324,17 @@ S: Maintained F: include/linux/netfilter_bridge/ F: net/bridge/ +ETHERNET PHY LIBRARY +M: Florian Fainelli <f.fainelli@gmail.com> +L: netdev@vger.kernel.org +S: Maintained +F: include/linux/phy.h +F: include/linux/phy_fixed.h +F: drivers/net/phy/ +F: Documentation/networking/phy.txt +F: drivers/of/of_mdio.c +F: drivers/of/of_net.c + EXT2 FILE SYSTEM M: Jan Kara <jack@suse.cz> L: linux-ext4@vger.kernel.org diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index f342278..494b888 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -139,7 +139,7 @@ config MACVTAP This adds a specialized tap character device driver that is based on the MAC-VLAN network interface, called macvtap. A macvtap device can be added in the same way as a macvlan device, using 'type - macvlan', and then be accessed through the tap user space interface. + macvtap', and then be accessed through the tap user space interface. To compile this driver as a module, choose M here: the module will be called macvtap. diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index cce1f1b..6d20fbd 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1796,8 +1796,6 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) BOND_AD_INFO(bond).agg_select_timer = timeout; } -static u16 aggregator_identifier; - /** * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures * @bond: bonding struct to work on @@ -1811,7 +1809,7 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr), bond->dev->dev_addr)) { - aggregator_identifier = 0; + BOND_AD_INFO(bond).aggregator_identifier = 0; BOND_AD_INFO(bond).system.sys_priority = 0xFFFF; BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); @@ -1880,7 +1878,7 @@ void bond_3ad_bind_slave(struct slave *slave) ad_initialize_agg(aggregator); aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr); - aggregator->aggregator_identifier = (++aggregator_identifier); + aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier; aggregator->slave = slave; aggregator->is_active = 0; aggregator->num_of_ports = 0; diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index 13dc9d3..f4dd959 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -253,6 +253,7 @@ struct ad_system { struct ad_bond_info { struct ad_system system; /* 802.3ad system structure */ u32 agg_select_timer; // Timer to select aggregator after all adapter's hand shakes + u16 aggregator_identifier; }; struct ad_slave_info { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 71ba18e..1c6104d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1543,9 +1543,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); if (USES_PRIMARY(bond->params.mode)) { + block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); } pr_info("%s: enslaving %s as a%s interface with a%s link.\n", @@ -1571,10 +1573,12 @@ err_detach: if (bond->primary_slave == new_slave) bond->primary_slave = NULL; if (bond->curr_active_slave == new_slave) { + block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); } slave_disable_netpoll(new_slave); @@ -2864,9 +2868,12 @@ static int bond_slave_netdev_event(unsigned long event, pr_info("%s: Primary slave changed to %s, reselecting active slave.\n", bond->dev->name, bond->primary_slave ? slave_dev->name : "none"); + + block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: bond_compute_features(bond); @@ -3700,7 +3707,7 @@ static inline int bond_slave_override(struct bonding *bond, static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 11cb943..c378784 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/if.h> #include <linux/netdevice.h> -#include <linux/rwlock.h> +#include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/ctype.h> #include <linux/inet.h> diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 6c859bb..e77d110 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -473,6 +473,8 @@ static int kvaser_usb_get_card_info(struct kvaser_usb *dev) return err; dev->nchannels = msg.u.cardinfo.nchannels; + if (dev->nchannels > MAX_NET_DEVICES) + return -EINVAL; return 0; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9d7419e..66c0df7 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1873,7 +1873,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) } u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct bnx2x *bp = netdev_priv(dev); @@ -1895,7 +1895,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); + return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index bfc58d4..a89a40f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -496,7 +496,7 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index add05f1..1642de7 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1939,6 +1939,7 @@ static void tulip_remove_one(struct pci_dev *pdev) pci_iounmap(pdev, tp->base_addr); free_netdev (dev); pci_release_regions (pdev); + pci_disable_device(pdev); /* pci_power_off (pdev, -1); */ } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d4782b4..903362a 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1778,8 +1778,6 @@ fec_enet_open(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); int ret; - napi_enable(&fep->napi); - /* I should reset the ring buffers here, but I don't yet know * a simple way to do that. */ @@ -1794,6 +1792,8 @@ fec_enet_open(struct net_device *ndev) fec_enet_free_buffers(ndev); return ret; } + + napi_enable(&fep->napi); phy_start(fep->phy_dev); netif_start_queue(ndev); fep->opened = 1; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6d4ada7..18076c4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6881,7 +6881,7 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) } static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; #ifdef IXGBE_FCOE @@ -6907,7 +6907,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) break; default: - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); } f = &adapter->ring_feature[RING_F_FCOE]; @@ -6920,7 +6920,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, return txq + f->offset; #else - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); #endif } diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 8f9266c..fd4b6ae 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -619,7 +619,7 @@ ltq_etop_set_multicast_list(struct net_device *dev) static u16 ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* we are currently only using the first queue */ return 0; diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index 6300fd2..68e6a66 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -43,12 +43,12 @@ config MVMDIO This driver is used by the MV643XX_ETH and MVNETA drivers. config MVNETA - tristate "Marvell Armada 370/XP network interface support" - depends on MACH_ARMADA_370_XP + tristate "Marvell Armada 370/38x/XP network interface support" + depends on PLAT_ORION select MVMDIO ---help--- This driver supports the network interface units in the - Marvell ARMADA XP and ARMADA 370 SoC family. + Marvell ARMADA XP, ARMADA 370 and ARMADA 38x SoC family. Note that this driver is distinct from the mv643xx_eth driver, which should be used for the older Marvell SoCs diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8e8a7eb..1345703 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -629,7 +629,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk } u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; @@ -641,7 +641,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, if (vlan_tx_tag_present(skb)) up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT; - return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up; + return fallback(dev, skb) % rings_p_up + up * rings_p_up; } static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 3af04c3..9ca223b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -723,7 +723,7 @@ int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index e2f202e..f2d7c70 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -37,6 +37,17 @@ config DWMAC_SUNXI stmmac device driver. This driver is used for A20/A31 GMAC ethernet controller. +config DWMAC_STI + bool "STi GMAC support" + depends on STMMAC_PLATFORM && ARCH_STI + default y + ---help--- + Support for ethernet controller on STi SOCs. + + This selects STi SoC glue layer support for the stmmac + device driver. This driver is used on for the STi series + SOCs GMAC ethernet controller. + config STMMAC_PCI bool "STMMAC PCI bus support" depends on STMMAC_ETH && PCI diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index ecadece..dcef287 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_STMMAC_ETH) += stmmac.o stmmac-$(CONFIG_STMMAC_PLATFORM) += stmmac_platform.o stmmac-$(CONFIG_STMMAC_PCI) += stmmac_pci.o stmmac-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o +stmmac-$(CONFIG_DWMAC_STI) += dwmac-sti.o stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \ dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c new file mode 100644 index 0000000..552bbc1 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -0,0 +1,330 @@ +/** + * dwmac-sti.c - STMicroelectronics DWMAC Specific Glue layer + * + * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited + * Author: Srinivas Kandagatla <srinivas.kandagatla@st.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/slab.h> +#include <linux/platform_device.h> +#include <linux/stmmac.h> +#include <linux/phy.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/of_net.h> + +/** + * STi GMAC glue logic. + * -------------------- + * + * _ + * | \ + * --------|0 \ ETH_SEL_INTERNAL_NOTEXT_PHYCLK + * phyclk | |___________________________________________ + * | | | (phyclk-in) + * --------|1 / | + * int-clk |_ / | + * | _ + * | | \ + * |_______|1 \ ETH_SEL_TX_RETIME_CLK + * | |___________________________ + * | | (tx-retime-clk) + * _______|0 / + * | |_ / + * _ | + * | \ | + * --------|0 \ | + * clk_125 | |__| + * | | ETH_SEL_TXCLK_NOT_CLK125 + * --------|1 / + * txclk |_ / + * + * + * ETH_SEL_INTERNAL_NOTEXT_PHYCLK is valid only for RMII where PHY can + * generate 50MHz clock or MAC can generate it. + * This bit is configured by "st,ext-phyclk" property. + * + * ETH_SEL_TXCLK_NOT_CLK125 is only valid for gigabit modes, where the 125Mhz + * clock either comes from clk-125 pin or txclk pin. This configuration is + * totally driven by the board wiring. This bit is configured by + * "st,tx-retime-src" property. + * + * TXCLK configuration is different for different phy interface modes + * and changes according to link speed in modes like RGMII. + * + * Below table summarizes the clock requirement and clock sources for + * supported phy interface modes with link speeds. + * ________________________________________________ + *| PHY_MODE | 1000 Mbit Link | 100 Mbit Link | + * ------------------------------------------------ + *| MII | n/a | 25Mhz | + *| | | txclk | + * ------------------------------------------------ + *| GMII | 125Mhz | 25Mhz | + *| | clk-125/txclk | txclk | + * ------------------------------------------------ + *| RGMII | 125Mhz | 25Mhz | + *| | clk-125/txclk | clkgen | + * ------------------------------------------------ + *| RMII | n/a | 25Mhz | + *| | |clkgen/phyclk-in | + * ------------------------------------------------ + * + * TX lines are always retimed with a clk, which can vary depending + * on the board configuration. Below is the table of these bits + * in eth configuration register depending on source of retime clk. + * + *--------------------------------------------------------------- + * src | tx_rt_clk | int_not_ext_phyclk | txclk_n_clk125| + *--------------------------------------------------------------- + * txclk | 0 | n/a | 1 | + *--------------------------------------------------------------- + * ck_125| 0 | n/a | 0 | + *--------------------------------------------------------------- + * phyclk| 1 | 0 | n/a | + *--------------------------------------------------------------- + * clkgen| 1 | 1 | n/a | + *--------------------------------------------------------------- + */ + + /* Register definition */ + + /* 3 bits [8:6] + * [6:6] ETH_SEL_TXCLK_NOT_CLK125 + * [7:7] ETH_SEL_INTERNAL_NOTEXT_PHYCLK + * [8:8] ETH_SEL_TX_RETIME_CLK + * + */ + +#define TX_RETIME_SRC_MASK GENMASK(8, 6) +#define ETH_SEL_TX_RETIME_CLK BIT(8) +#define ETH_SEL_INTERNAL_NOTEXT_PHYCLK BIT(7) +#define ETH_SEL_TXCLK_NOT_CLK125 BIT(6) + +#define ENMII_MASK GENMASK(5, 5) +#define ENMII BIT(5) + +/** + * 3 bits [4:2] + * 000-GMII/MII + * 001-RGMII + * 010-SGMII + * 100-RMII +*/ +#define MII_PHY_SEL_MASK GENMASK(4, 2) +#define ETH_PHY_SEL_RMII BIT(4) +#define ETH_PHY_SEL_SGMII BIT(3) +#define ETH_PHY_SEL_RGMII BIT(2) +#define ETH_PHY_SEL_GMII 0x0 +#define ETH_PHY_SEL_MII 0x0 + +#define IS_PHY_IF_MODE_RGMII(iface) (iface == PHY_INTERFACE_MODE_RGMII || \ + iface == PHY_INTERFACE_MODE_RGMII_ID || \ + iface == PHY_INTERFACE_MODE_RGMII_RXID || \ + iface == PHY_INTERFACE_MODE_RGMII_TXID) + +#define IS_PHY_IF_MODE_GBIT(iface) (IS_PHY_IF_MODE_RGMII(iface) || \ + iface == PHY_INTERFACE_MODE_GMII) + +struct sti_dwmac { + int interface; + bool ext_phyclk; + bool is_tx_retime_src_clk_125; + struct clk *clk; + int reg; + struct device *dev; + struct regmap *regmap; +}; + +static u32 phy_intf_sels[] = { + [PHY_INTERFACE_MODE_MII] = ETH_PHY_SEL_MII, + [PHY_INTERFACE_MODE_GMII] = ETH_PHY_SEL_GMII, + [PHY_INTERFACE_MODE_RGMII] = ETH_PHY_SEL_RGMII, + [PHY_INTERFACE_MODE_RGMII_ID] = ETH_PHY_SEL_RGMII, + [PHY_INTERFACE_MODE_SGMII] = ETH_PHY_SEL_SGMII, + [PHY_INTERFACE_MODE_RMII] = ETH_PHY_SEL_RMII, +}; + +enum { + TX_RETIME_SRC_NA = 0, + TX_RETIME_SRC_TXCLK = 1, + TX_RETIME_SRC_CLK_125, + TX_RETIME_SRC_PHYCLK, + TX_RETIME_SRC_CLKGEN, +}; + +static const char *const tx_retime_srcs[] = { + [TX_RETIME_SRC_NA] = "", + [TX_RETIME_SRC_TXCLK] = "txclk", + [TX_RETIME_SRC_CLK_125] = "clk_125", + [TX_RETIME_SRC_PHYCLK] = "phyclk", + [TX_RETIME_SRC_CLKGEN] = "clkgen", +}; + +static u32 tx_retime_val[] = { + [TX_RETIME_SRC_TXCLK] = ETH_SEL_TXCLK_NOT_CLK125, + [TX_RETIME_SRC_CLK_125] = 0x0, + [TX_RETIME_SRC_PHYCLK] = ETH_SEL_TX_RETIME_CLK, + [TX_RETIME_SRC_CLKGEN] = ETH_SEL_TX_RETIME_CLK | + ETH_SEL_INTERNAL_NOTEXT_PHYCLK, +}; + +static void setup_retime_src(struct sti_dwmac *dwmac, u32 spd) +{ + u32 src = 0, freq = 0; + + if (spd == SPEED_100) { + if (dwmac->interface == PHY_INTERFACE_MODE_MII || + dwmac->interface == PHY_INTERFACE_MODE_GMII) { + src = TX_RETIME_SRC_TXCLK; + } else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) { + if (dwmac->ext_phyclk) { + src = TX_RETIME_SRC_PHYCLK; + } else { + src = TX_RETIME_SRC_CLKGEN; + freq = 50000000; + } + + } else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) { + src = TX_RETIME_SRC_CLKGEN; + freq = 25000000; + } + + if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk) + clk_set_rate(dwmac->clk, freq); + + } else if (spd == SPEED_1000) { + if (dwmac->is_tx_retime_src_clk_125) + src = TX_RETIME_SRC_CLK_125; + else + src = TX_RETIME_SRC_TXCLK; + } + + regmap_update_bits(dwmac->regmap, dwmac->reg, + TX_RETIME_SRC_MASK, tx_retime_val[src]); +} + +static void sti_dwmac_exit(struct platform_device *pdev, void *priv) +{ + struct sti_dwmac *dwmac = priv; + + if (dwmac->clk) + clk_disable_unprepare(dwmac->clk); +} + +static void sti_fix_mac_speed(void *priv, unsigned int spd) +{ + struct sti_dwmac *dwmac = priv; + + setup_retime_src(dwmac, spd); + + return; +} + +static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, + struct platform_device *pdev) +{ + struct resource *res; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct regmap *regmap; + int err; + + if (!np) + return -EINVAL; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-ethconf"); + if (!res) + return -ENODATA; + + regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon"); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + dwmac->dev = dev; + dwmac->interface = of_get_phy_mode(np); + dwmac->regmap = regmap; + dwmac->reg = res->start; + dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk"); + dwmac->is_tx_retime_src_clk_125 = false; + + if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) { + const char *rs; + + err = of_property_read_string(np, "st,tx-retime-src", &rs); + if (err < 0) { + dev_err(dev, "st,tx-retime-src not specified\n"); + return err; + } + + if (!strcasecmp(rs, "clk_125")) + dwmac->is_tx_retime_src_clk_125 = true; + } + + dwmac->clk = devm_clk_get(dev, "sti-ethclk"); + + if (IS_ERR(dwmac->clk)) + dwmac->clk = NULL; + + return 0; +} + +static int sti_dwmac_init(struct platform_device *pdev, void *priv) +{ + struct sti_dwmac *dwmac = priv; + struct regmap *regmap = dwmac->regmap; + int iface = dwmac->interface; + u32 reg = dwmac->reg; + u32 val, spd; + + if (dwmac->clk) + clk_prepare_enable(dwmac->clk); + + regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]); + + val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII; + regmap_update_bits(regmap, reg, ENMII_MASK, val); + + if (IS_PHY_IF_MODE_GBIT(iface)) + spd = SPEED_1000; + else + spd = SPEED_100; + + setup_retime_src(dwmac, spd); + + return 0; +} + +static void *sti_dwmac_setup(struct platform_device *pdev) +{ + struct sti_dwmac *dwmac; + int ret; + + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); + if (!dwmac) + return ERR_PTR(-ENOMEM); + + ret = sti_dwmac_parse_data(dwmac, pdev); + if (ret) { + dev_err(&pdev->dev, "Unable to parse OF data\n"); + return ERR_PTR(ret); + } + + return dwmac; +} + +const struct stmmac_of_data sti_gmac_data = { + .fix_mac_speed = sti_fix_mac_speed, + .setup = sti_dwmac_setup, + .init = sti_dwmac_init, + .exit = sti_dwmac_exit, +}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index d9af26e..f9e60d7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -133,6 +133,9 @@ bool stmmac_eee_init(struct stmmac_priv *priv); #ifdef CONFIG_DWMAC_SUNXI extern const struct stmmac_of_data sun7i_gmac_data; #endif +#ifdef CONFIG_DWMAC_STI +extern const struct stmmac_of_data sti_gmac_data; +#endif extern struct platform_driver stmmac_pltfr_driver; static inline int stmmac_register_platform(void) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5884a7d..c61bc72b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -33,6 +33,11 @@ static const struct of_device_id stmmac_dt_ids[] = { #ifdef CONFIG_DWMAC_SUNXI { .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data}, #endif +#ifdef CONFIG_DWMAC_STI + { .compatible = "st,stih415-dwmac", .data = &sti_gmac_data}, + { .compatible = "st,stih416-dwmac", .data = &sti_gmac_data}, + { .compatible = "st,stih127-dwmac", .data = &sti_gmac_data}, +#endif /* SoC specific glue layers should come before generic bindings */ { .compatible = "st,spear600-gmac"}, { .compatible = "snps,dwmac-3.610"}, diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1d860ce..651087b 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -554,7 +554,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) * common for both the interface as the interface shares * the same hardware resource. */ - for (i = 0; i <= priv->data.slaves; i++) + for (i = 0; i < priv->data.slaves; i++) if (priv->slaves[i].ndev->flags & IFF_PROMISC) flag = true; @@ -578,7 +578,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) unsigned long timeout = jiffies + HZ; /* Disable Learn for all ports */ - for (i = 0; i <= priv->data.slaves; i++) { + for (i = 0; i < priv->data.slaves; i++) { cpsw_ale_control_set(ale, i, ALE_PORT_NOLEARN, 1); cpsw_ale_control_set(ale, i, @@ -606,7 +606,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 0); /* Enable Learn for all ports */ - for (i = 0; i <= priv->data.slaves; i++) { + for (i = 0; i < priv->data.slaves; i++) { cpsw_ale_control_set(ale, i, ALE_PORT_NOLEARN, 0); cpsw_ale_control_set(ale, i, @@ -1896,6 +1896,11 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); slave_data->phy_if = of_get_phy_mode(slave_node); + if (slave_data->phy_if < 0) { + pr_err("Missing or malformed slave[%d] phy-mode property\n", + i); + return slave_data->phy_if; + } if (data->dual_emac) { if (of_property_read_u32(slave_node, "dual_emac_res_vlan", diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 023237a..17503da 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -2071,7 +2071,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) /* Return subqueue id on this core (one per core). */ static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return smp_processor_id(); } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 1ec65fe..4bfdf8c 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -26,6 +26,7 @@ #include <linux/netdevice.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> +#include <linux/of_irq.h> #include <linux/of_address.h> #include <linux/skbuff.h> #include <linux/spinlock.h> @@ -600,7 +601,8 @@ static void axienet_start_xmit_done(struct net_device *ndev) size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK; packets++; - lp->tx_bd_ci = ++lp->tx_bd_ci % TX_BD_NUM; + ++lp->tx_bd_ci; + lp->tx_bd_ci %= TX_BD_NUM; cur_p = &lp->tx_bd_v[lp->tx_bd_ci]; status = cur_p->status; } @@ -686,7 +688,8 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_headlen(skb), DMA_TO_DEVICE); for (ii = 0; ii < num_frag; ii++) { - lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM; + ++lp->tx_bd_tail; + lp->tx_bd_tail %= TX_BD_NUM; cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; frag = &skb_shinfo(skb)->frags[ii]; cur_p->phys = dma_map_single(ndev->dev.parent, @@ -702,7 +705,8 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail; /* Start the transfer */ axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p); - lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM; + ++lp->tx_bd_tail; + lp->tx_bd_tail %= TX_BD_NUM; return NETDEV_TX_OK; } @@ -774,7 +778,8 @@ static void axienet_recv(struct net_device *ndev) cur_p->status = 0; cur_p->sw_id_offset = (u32) new_skb; - lp->rx_bd_ci = ++lp->rx_bd_ci % RX_BD_NUM; + ++lp->rx_bd_ci; + lp->rx_bd_ci %= RX_BD_NUM; cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 7756118..7141a19 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -88,8 +88,12 @@ static int netvsc_open(struct net_device *net) { struct net_device_context *net_device_ctx = netdev_priv(net); struct hv_device *device_obj = net_device_ctx->device_ctx; + struct netvsc_device *nvdev; + struct rndis_device *rdev; int ret = 0; + netif_carrier_off(net); + /* Open up the device */ ret = rndis_filter_open(device_obj); if (ret != 0) { @@ -99,6 +103,11 @@ static int netvsc_open(struct net_device *net) netif_start_queue(net); + nvdev = hv_get_drvdata(device_obj); + rdev = nvdev->extension; + if (!rdev->link_state) + netif_carrier_on(net); + return ret; } @@ -229,23 +238,24 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, struct net_device *net; struct net_device_context *ndev_ctx; struct netvsc_device *net_device; + struct rndis_device *rdev; net_device = hv_get_drvdata(device_obj); + rdev = net_device->extension; + + rdev->link_state = status != 1; + net = net_device->ndev; - if (!net) { - netdev_err(net, "got link status but net device " - "not initialized yet\n"); + if (!net || net->reg_state != NETREG_REGISTERED) return; - } + ndev_ctx = netdev_priv(net); if (status == 1) { - netif_carrier_on(net); - ndev_ctx = netdev_priv(net); schedule_delayed_work(&ndev_ctx->dwork, 0); schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20)); } else { - netif_carrier_off(net); + schedule_delayed_work(&ndev_ctx->dwork, 0); } } @@ -388,17 +398,35 @@ static const struct net_device_ops device_ops = { * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add * another netif_notify_peers() into a delayed work, otherwise GARP packet * will not be sent after quick migration, and cause network disconnection. + * Also, we update the carrier status here. */ -static void netvsc_send_garp(struct work_struct *w) +static void netvsc_link_change(struct work_struct *w) { struct net_device_context *ndev_ctx; struct net_device *net; struct netvsc_device *net_device; + struct rndis_device *rdev; + bool notify; + + rtnl_lock(); ndev_ctx = container_of(w, struct net_device_context, dwork.work); net_device = hv_get_drvdata(ndev_ctx->device_ctx); + rdev = net_device->extension; net = net_device->ndev; - netdev_notify_peers(net); + + if (rdev->link_state) { + netif_carrier_off(net); + notify = false; + } else { + netif_carrier_on(net); + notify = true; + } + + rtnl_unlock(); + + if (notify) + netdev_notify_peers(net); } @@ -414,13 +442,10 @@ static int netvsc_probe(struct hv_device *dev, if (!net) return -ENOMEM; - /* Set initial state */ - netif_carrier_off(net); - net_device_ctx = netdev_priv(net); net_device_ctx->device_ctx = dev; hv_set_drvdata(dev, net); - INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_send_garp); + INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); INIT_WORK(&net_device_ctx->work, do_set_multicast); net->netdev_ops = &device_ops; @@ -443,8 +468,6 @@ static int netvsc_probe(struct hv_device *dev, } memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); - netif_carrier_on(net); - ret = register_netdev(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c index 177441a..24b6ddd 100644 --- a/drivers/net/irda/irtty-sir.c +++ b/drivers/net/irda/irtty-sir.c @@ -522,7 +522,6 @@ static void irtty_close(struct tty_struct *tty) sirdev_put_instance(priv->dev); /* Stop tty */ - irtty_stop_receiver(tty, TRUE); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (tty->ops->stop) tty->ops->stop(tty); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 8433de4..a5d2189 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -879,14 +879,15 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev); if (err) - goto destroy_port; - + goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); netif_stacked_transfer_operstate(lowerdev, dev); return 0; +unregister_netdev: + unregister_netdevice(dev); destroy_port: port->count -= 1; if (!port->count) diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 9414fa2..98e7cbf 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1006,11 +1006,6 @@ static int dp83640_probe(struct phy_device *phydev) } else list_add_tail(&dp83640->list, &clock->phylist); - if (clock->chosen && !list_empty(&clock->phylist)) - recalibrate(clock); - else - enable_broadcast(dp83640->phydev, clock->page, 1); - dp83640_clock_put(clock); return 0; @@ -1063,6 +1058,14 @@ static void dp83640_remove(struct phy_device *phydev) static int dp83640_config_init(struct phy_device *phydev) { + struct dp83640_private *dp83640 = phydev->priv; + struct dp83640_clock *clock = dp83640->clock; + + if (clock->chosen && !list_empty(&clock->phylist)) + recalibrate(clock); + else + enable_broadcast(phydev, clock->page, 1); + enable_status_frames(phydev, true); ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE); return 0; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 2840742..c8624a8 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1648,7 +1648,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 44c4db8..8fe9cb7 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -366,7 +366,7 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) * hope the rxq no. may help here. */ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 409499f..7e7269f 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -296,7 +296,6 @@ config USB_NET_SR9800 tristate "CoreChip-sz SR9800 based USB 2.0 10/100 ethernet devices" depends on USB_USBNET select CRC32 - default y ---help--- Say Y if you want to use one of the following 100Mbps USB Ethernet device based on the CoreChip-sz SR9800 chip. diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 9765a7d..5d19409 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -917,7 +917,8 @@ static const struct driver_info ax88178_info = { .status = asix_status, .link_reset = ax88178_link_reset, .reset = ax88178_reset, - .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | + FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, }; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index d6f64da..955df81 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1118,6 +1118,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) u16 hdr_off; u32 *pkt_hdr; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + skb_trim(skb, skb->len - 4); memcpy(&rx_hdr, skb_tail_pointer(skb), 4); le32_to_cpus(&rx_hdr); diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c index e4a8a93..1cc24e6 100644 --- a/drivers/net/usb/gl620a.c +++ b/drivers/net/usb/gl620a.c @@ -84,6 +84,10 @@ static int genelink_rx_fixup(struct usbnet *dev, struct sk_buff *skb) u32 size; u32 count; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + header = (struct gl_header *) skb->data; // get the packet count of the received skb diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index a305a7b..82d844a 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -526,8 +526,9 @@ static int mcs7830_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { u8 status; - if (skb->len == 0) { - dev_err(&dev->udev->dev, "unexpected empty rx frame\n"); + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) { + dev_err(&dev->udev->dev, "unexpected tiny rx frame\n"); return 0; } diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c index 0a85d92..4cbdb13 100644 --- a/drivers/net/usb/net1080.c +++ b/drivers/net/usb/net1080.c @@ -364,6 +364,10 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) struct nc_trailer *trailer; u16 hdr_len, packet_len; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + if (!(skb->len & 0x01)) { netdev_dbg(dev->net, "rx framesize %d range %d..%d mtu %d\n", skb->len, dev->net->hard_header_len, dev->hard_mtu, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index ff5c871..313cb6c 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -80,10 +80,10 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { __be16 proto; - /* usbnet rx_complete guarantees that skb->len is at least - * hard_header_len, so we can inspect the dest address without - * checking skb->len - */ + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + switch (skb->data[0] & 0xf0) { case 0x40: proto = htons(ETH_P_IP); @@ -732,6 +732,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ + {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index a48bc0f..524a47a281 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -492,6 +492,10 @@ EXPORT_SYMBOL_GPL(rndis_unbind); */ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + /* peripheral may have batched packets to us... */ while (likely(skb->len)) { struct rndis_data_hdr *hdr = (void *)skb->data; diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index f17b9e0..d9e7892 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2106,6 +2106,10 @@ static void smsc75xx_rx_csum_offload(struct usbnet *dev, struct sk_buff *skb, static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + while (skb->len > 0) { u32 rx_cmd_a, rx_cmd_b, align_count, size; struct sk_buff *ax_skb; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 8dd54a0..424db65e 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1723,6 +1723,10 @@ static void smsc95xx_rx_csum_offload(struct sk_buff *skb) static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + while (skb->len > 0) { u32 header, align_count; struct sk_buff *ax_skb; diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 4175eb9..b94a0fb 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -63,6 +63,10 @@ static int sr_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { int offset = 0; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + while (offset + sizeof(u32) < skb->len) { struct sk_buff *sr_skb; u16 size; @@ -823,7 +827,7 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) dev->rx_urb_size = SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].size; } - netdev_dbg(dev->net, "%s : setting rx_urb_size with : %ld\n", __func__, + netdev_dbg(dev->net, "%s : setting rx_urb_size with : %zu\n", __func__, dev->rx_urb_size); return 0; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 4671da7..dd10d58 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -542,17 +542,19 @@ static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) } // else network stack removes extra byte if we forced a short packet - if (skb->len) { - /* all data was already cloned from skb inside the driver */ - if (dev->driver_info->flags & FLAG_MULTI_PACKET) - dev_kfree_skb_any(skb); - else - usbnet_skb_return(dev, skb); + /* all data was already cloned from skb inside the driver */ + if (dev->driver_info->flags & FLAG_MULTI_PACKET) + goto done; + + if (skb->len < ETH_HLEN) { + dev->net->stats.rx_errors++; + dev->net->stats.rx_length_errors++; + netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len); + } else { + usbnet_skb_return(dev, skb); return; } - netif_dbg(dev, rx_err, dev->net, "drop\n"); - dev->net->stats.rx_errors++; done: skb_queue_tail(&dev->done, skb); } @@ -574,13 +576,6 @@ static void rx_complete (struct urb *urb) switch (urb_status) { /* success */ case 0: - if (skb->len < dev->net->hard_header_len) { - state = rx_cleanup; - dev->net->stats.rx_errors++; - dev->net->stats.rx_length_errors++; - netif_dbg(dev, rx_err, dev->net, - "rx length %d\n", skb->len); - } break; /* stalls need manual reset. this is rare ... except that diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c index d6bc7cb..1a2973b 100644 --- a/drivers/net/wireless/ath/ath5k/phy.c +++ b/drivers/net/wireless/ath/ath5k/phy.c @@ -110,7 +110,7 @@ ath5k_hw_radio_revision(struct ath5k_hw *ah, enum ieee80211_band band) ath5k_hw_reg_write(ah, 0x00010000, AR5K_PHY(0x20)); if (ah->ah_version == AR5K_AR5210) { - srev = ath5k_hw_reg_read(ah, AR5K_PHY(256) >> 28) & 0xf; + srev = (ath5k_hw_reg_read(ah, AR5K_PHY(256)) >> 28) & 0xf; ret = (u16)ath5k_hw_bitswap(srev, 4) + 1; } else { srev = (ath5k_hw_reg_read(ah, AR5K_PHY(0x100)) >> 24) & 0xff; diff --git a/drivers/net/wireless/hostap/hostap_proc.c b/drivers/net/wireless/hostap/hostap_proc.c index aa7ad3a..4e5c0f8 100644 --- a/drivers/net/wireless/hostap/hostap_proc.c +++ b/drivers/net/wireless/hostap/hostap_proc.c @@ -496,7 +496,7 @@ void hostap_init_proc(local_info_t *local) void hostap_remove_proc(local_info_t *local) { - remove_proc_subtree(local->ddev->name, hostap_proc); + proc_remove(local->proc); } diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c index c24d1d3..73086c1 100644 --- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c @@ -696,6 +696,24 @@ static int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, return ret; } +static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg) +{ + if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) + return false; + return true; +} + +static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg) +{ + if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) + return false; + if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG) + return true; + + /* disabled by default */ + return false; +} + static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, @@ -717,7 +735,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, switch (action) { case IEEE80211_AMPDU_RX_START: - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) + if (!iwl_enable_rx_ampdu(priv->cfg)) break; IWL_DEBUG_HT(priv, "start Rx\n"); ret = iwl_sta_rx_agg_start(priv, sta, tid, *ssn); @@ -729,7 +747,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, case IEEE80211_AMPDU_TX_START: if (!priv->trans->ops->txq_enable) break; - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) + if (!iwl_enable_tx_ampdu(priv->cfg)) break; IWL_DEBUG_HT(priv, "start Tx\n"); ret = iwlagn_tx_agg_start(priv, vif, sta, tid, ssn); diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c index c372816..7510355 100644 --- a/drivers/net/wireless/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/iwlwifi/iwl-drv.c @@ -1286,7 +1286,7 @@ module_param_named(swcrypto, iwlwifi_mod_params.sw_crypto, int, S_IRUGO); MODULE_PARM_DESC(swcrypto, "using crypto in software (default 0 [hardware])"); module_param_named(11n_disable, iwlwifi_mod_params.disable_11n, uint, S_IRUGO); MODULE_PARM_DESC(11n_disable, - "disable 11n functionality, bitmap: 1: full, 2: agg TX, 4: agg RX"); + "disable 11n functionality, bitmap: 1: full, 2: disable agg TX, 4: disable agg RX, 8 enable agg TX"); module_param_named(amsdu_size_8K, iwlwifi_mod_params.amsdu_size_8K, int, S_IRUGO); MODULE_PARM_DESC(amsdu_size_8K, "enable 8K amsdu size (default 0)"); diff --git a/drivers/net/wireless/iwlwifi/iwl-modparams.h b/drivers/net/wireless/iwlwifi/iwl-modparams.h index 0a84ade..b29075c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-modparams.h +++ b/drivers/net/wireless/iwlwifi/iwl-modparams.h @@ -79,9 +79,12 @@ enum iwl_power_level { IWL_POWER_NUM }; -#define IWL_DISABLE_HT_ALL BIT(0) -#define IWL_DISABLE_HT_TXAGG BIT(1) -#define IWL_DISABLE_HT_RXAGG BIT(2) +enum iwl_disable_11n { + IWL_DISABLE_HT_ALL = BIT(0), + IWL_DISABLE_HT_TXAGG = BIT(1), + IWL_DISABLE_HT_RXAGG = BIT(2), + IWL_ENABLE_HT_TXAGG = BIT(3), +}; /** * struct iwl_mod_params @@ -90,7 +93,7 @@ enum iwl_power_level { * * @sw_crypto: using hardware encryption, default = 0 * @disable_11n: disable 11n capabilities, default = 0, - * use IWL_DISABLE_HT_* constants + * use IWL_[DIS,EN]ABLE_HT_* constants * @amsdu_size_8K: enable 8K amsdu size, default = 0 * @restart_fw: restart firmware, default = 1 * @wd_disable: enable stuck queue check, default = 0 diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c index 6bf9766..c35b866 100644 --- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c @@ -328,6 +328,24 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, ieee80211_free_txskb(hw, skb); } +static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg) +{ + if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) + return false; + return true; +} + +static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg) +{ + if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) + return false; + if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG) + return true; + + /* enabled by default */ + return true; +} + static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, @@ -347,7 +365,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, switch (action) { case IEEE80211_AMPDU_RX_START: - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) { + if (!iwl_enable_rx_ampdu(mvm->cfg)) { ret = -EINVAL; break; } @@ -357,7 +375,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, ret = iwl_mvm_sta_rx_agg(mvm, sta, tid, 0, false); break; case IEEE80211_AMPDU_TX_START: - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) { + if (!iwl_enable_tx_ampdu(mvm->cfg)) { ret = -EINVAL; break; } diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index 4d79761..9d3d275 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -748,7 +748,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) static u16 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h index 56aee06..a6ad79f 100644 --- a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h +++ b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h @@ -15,6 +15,8 @@ #ifndef RTL8187_H #define RTL8187_H +#include <linux/cache.h> + #include "rtl818x.h" #include "leds.h" @@ -139,7 +141,10 @@ struct rtl8187_priv { u8 aifsn[4]; u8 rfkill_mask; struct { - __le64 buf; + union { + __le64 buf; + u8 dummy1[L1_CACHE_BYTES]; + } ____cacheline_aligned; struct sk_buff_head queue; } b_tx_status; /* This queue is used by both -b and non-b devices */ struct mutex io_mutex; @@ -147,7 +152,8 @@ struct rtl8187_priv { u8 bits8; __le16 bits16; __le32 bits32; - } *io_dmabuf; + u8 dummy2[L1_CACHE_BYTES]; + } *io_dmabuf ____cacheline_aligned; bool rfkill_off; u16 seqno; }; diff --git a/drivers/net/wireless/rtlwifi/ps.c b/drivers/net/wireless/rtlwifi/ps.c index deedae3..d1c0191 100644 --- a/drivers/net/wireless/rtlwifi/ps.c +++ b/drivers/net/wireless/rtlwifi/ps.c @@ -48,7 +48,7 @@ bool rtl_ps_enable_nic(struct ieee80211_hw *hw) /*<2> Enable Adapter */ if (rtlpriv->cfg->ops->hw_init(hw)) - return 1; + return false; RT_CLEAR_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC); /*<3> Enable Interrupt */ diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c index a82b30a..2eb0b38 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c @@ -937,14 +937,26 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw) bool is92c; int err; u8 tmp_u1b; + unsigned long flags; rtlpci->being_init_adapter = true; + + /* Since this function can take a very long time (up to 350 ms) + * and can be called with irqs disabled, reenable the irqs + * to let the other devices continue being serviced. + * + * It is safe doing so since our own interrupts will only be enabled + * in a subsequent step. + */ + local_save_flags(flags); + local_irq_enable(); + rtlpriv->intf_ops->disable_aspm(hw); rtstatus = _rtl92ce_init_mac(hw); if (!rtstatus) { RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n"); err = 1; - return err; + goto exit; } err = rtl92c_download_fw(hw); @@ -952,7 +964,7 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING, "Failed to download FW. Init HW without FW now..\n"); err = 1; - return err; + goto exit; } rtlhal->last_hmeboxnum = 0; @@ -1032,6 +1044,8 @@ int rtl92ce_hw_init(struct ieee80211_hw *hw) RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n"); } rtl92c_dm_init(hw); +exit: + local_irq_restore(flags); rtlpci->being_init_adapter = false; return err; } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 875b7b6..5b3c24f 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -24,7 +24,11 @@ MODULE_LICENSE("GPL"); static void of_set_phy_supported(struct phy_device *phydev, u32 max_speed) { - phydev->supported |= PHY_DEFAULT_FEATURES; + /* The default values for phydev->supported are provided by the PHY + * driver "features" member, we want to reset to sane defaults fist + * before supporting higher speeds. + */ + phydev->supported &= PHY_DEFAULT_FEATURES; switch (max_speed) { default: @@ -44,7 +48,7 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *chi { struct phy_device *phy; bool is_c45; - int rc, prev_irq; + int rc; u32 max_speed = 0; is_c45 = of_device_is_compatible(child, @@ -54,12 +58,14 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *chi if (!phy || IS_ERR(phy)) return 1; - if (mdio->irq) { - prev_irq = mdio->irq[addr]; - mdio->irq[addr] = - irq_of_parse_and_map(child, 0); - if (!mdio->irq[addr]) - mdio->irq[addr] = prev_irq; + rc = irq_of_parse_and_map(child, 0); + if (rc > 0) { + phy->irq = rc; + if (mdio->irq) + mdio->irq[addr] = rc; + } else { + if (mdio->irq) + phy->irq = mdio->irq[addr]; } /* Associate the OF node with the device structure so it diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c index 8dfdd27..95a2358 100644 --- a/drivers/staging/bcm/Bcmnet.c +++ b/drivers/staging/bcm/Bcmnet.c @@ -40,7 +40,7 @@ static INT bcm_close(struct net_device *dev) } static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return ClassifyPacket(netdev_priv(dev), skb); } diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c index d8ea254..31b269a 100644 --- a/drivers/staging/netlogic/xlr_net.c +++ b/drivers/staging/netlogic/xlr_net.c @@ -307,7 +307,7 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, } static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return (u16)smp_processor_id(); } diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index 68f98fa..7c9ee58 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -653,7 +653,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9a68409..a0fa5de 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -70,7 +70,12 @@ enum { }; struct vhost_net_ubuf_ref { - struct kref kref; + /* refcount follows semantics similar to kref: + * 0: object is released + * 1: no outstanding ubufs + * >1: outstanding ubufs + */ + atomic_t refcount; wait_queue_head_t wait; struct vhost_virtqueue *vq; }; @@ -116,14 +121,6 @@ static void vhost_net_enable_zcopy(int vq) vhost_net_zcopy_mask |= 0x1 << vq; } -static void vhost_net_zerocopy_done_signal(struct kref *kref) -{ - struct vhost_net_ubuf_ref *ubufs; - - ubufs = container_of(kref, struct vhost_net_ubuf_ref, kref); - wake_up(&ubufs->wait); -} - static struct vhost_net_ubuf_ref * vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) { @@ -134,21 +131,24 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL); if (!ubufs) return ERR_PTR(-ENOMEM); - kref_init(&ubufs->kref); + atomic_set(&ubufs->refcount, 1); init_waitqueue_head(&ubufs->wait); ubufs->vq = vq; return ubufs; } -static void vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) +static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) { - kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal); + int r = atomic_sub_return(1, &ubufs->refcount); + if (unlikely(!r)) + wake_up(&ubufs->wait); + return r; } static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs) { - kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal); - wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount)); + vhost_net_ubuf_put(ubufs); + wait_event(ubufs->wait, !atomic_read(&ubufs->refcount)); } static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs) @@ -306,23 +306,26 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) { struct vhost_net_ubuf_ref *ubufs = ubuf->ctx; struct vhost_virtqueue *vq = ubufs->vq; - int cnt = atomic_read(&ubufs->kref.refcount); + int cnt; + + rcu_read_lock_bh(); /* set len to mark this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; - vhost_net_ubuf_put(ubufs); + cnt = vhost_net_ubuf_put(ubufs); /* * Trigger polling thread if guest stopped submitting new buffers: - * in this case, the refcount after decrement will eventually reach 1 - * so here it is 2. + * in this case, the refcount after decrement will eventually reach 1. * We also trigger polling periodically after each 16 packets * (the value 16 here is more or less arbitrary, it's tuned to trigger * less than 10% of times). */ - if (cnt <= 2 || !(cnt % 16)) + if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); + + rcu_read_unlock_bh(); } /* Expects to be always run from workqueue - which acts as @@ -420,7 +423,7 @@ static void handle_tx(struct vhost_net *net) msg.msg_control = ubuf; msg.msg_controllen = sizeof(ubuf); ubufs = nvq->ubufs; - kref_get(&ubufs->kref); + atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; } else { msg.msg_control = NULL; @@ -780,7 +783,7 @@ static void vhost_net_flush(struct vhost_net *n) vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs); mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = false; - kref_init(&n->vqs[VHOST_NET_VQ_TX].ubufs->kref); + atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1); mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); } } @@ -800,6 +803,8 @@ static int vhost_net_release(struct inode *inode, struct file *f) fput(tx_sock->file); if (rx_sock) fput(rx_sock->file); + /* Make sure no callbacks are outstanding */ + synchronize_rcu_bh(); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_net_flush(n); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 440a02e..e8eeebd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -752,6 +752,9 @@ struct netdev_phys_port_id { unsigned char id_len; }; +typedef u16 (*select_queue_fallback_t)(struct net_device *dev, + struct sk_buff *skb); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -783,7 +786,7 @@ struct netdev_phys_port_id { * Required can not be NULL. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv); + * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -1005,7 +1008,8 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, + select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1551,7 +1555,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines @@ -2276,6 +2279,26 @@ static inline void netdev_reset_queue(struct net_device *dev_queue) } /** + * netdev_cap_txqueue - check if selected tx queue exceeds device queues + * @dev: network device + * @queue_index: given tx queue index + * + * Returns 0 if given tx queue index >= number of device tx queues, + * otherwise returns the originally passed tx queue index. + */ +static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + + return queue_index; +} + +/** * netif_running - test if up * @dev: network device * @@ -3068,7 +3091,12 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -netdev_features_t netif_skb_features(struct sk_buff *skb); +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev); +static inline netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + return netif_skb_dev_features(skb, skb->dev); +} static inline bool net_gso_ok(netdev_features_t features, int gso_type) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af..3ebbbe7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2916,5 +2916,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d992ca3..6ee76c8 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1653,17 +1653,6 @@ struct sctp_association { /* This is the last advertised value of rwnd over a SACK chunk. */ __u32 a_rwnd; - /* Number of bytes by which the rwnd has slopped. The rwnd is allowed - * to slop over a maximum of the association's frag_point. - */ - __u32 rwnd_over; - - /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one - * is releases slowly (1 PMTU at a time ). - */ - __u32 rwnd_press; - /* This is the sndbuf size in use for the association. * This corresponds to the sndbuf size for the association, * as specified in the sk->sndbuf. @@ -1892,8 +1881,7 @@ void sctp_assoc_update(struct sctp_association *old, __u32 sctp_association_get_next_tsn(struct sctp_association *); void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *); -void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); -void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); +void sctp_assoc_rwnd_update(struct sctp_association *, bool); void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 512159b..8323bce 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -241,19 +241,19 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) size = bat_priv->num_ifaces * sizeof(uint8_t); orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); if (!orig_node->bat_iv.bcast_own_sum) - goto free_bcast_own; + goto free_orig_node; hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) - goto free_bcast_own; + goto free_orig_node; return orig_node; -free_bcast_own: - kfree(orig_node->bat_iv.bcast_own); free_orig_node: + /* free twice, as batadv_orig_node_new sets refcount to 2 */ + batadv_orig_node_free_ref(orig_node); batadv_orig_node_free_ref(orig_node); return NULL; @@ -266,7 +266,7 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, struct batadv_orig_node *orig_neigh) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_neigh_node *neigh_node; + struct batadv_neigh_node *neigh_node, *tmp_neigh_node; neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node); if (!neigh_node) @@ -281,14 +281,24 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, neigh_node->orig_node = orig_neigh; neigh_node->if_incoming = hard_iface; - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM for orig_node %pM on interface %s\n", - neigh_addr, orig_node->orig, hard_iface->net_dev->name); - spin_lock_bh(&orig_node->neigh_list_lock); - hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface, + neigh_addr); + if (!tmp_neigh_node) { + hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + } else { + kfree(neigh_node); + batadv_hardif_free_ref(hard_iface); + neigh_node = tmp_neigh_node; + } spin_unlock_bh(&orig_node->neigh_list_lock); + if (!tmp_neigh_node) + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new neighbor %pM for orig_node %pM on interface %s\n", + neigh_addr, orig_node->orig, + hard_iface->net_dev->name); + out: return neigh_node; } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 3d417d3..b851cc5 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -241,7 +241,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); const struct batadv_hard_iface *hard_iface; - int min_mtu = ETH_DATA_LEN; + int min_mtu = INT_MAX; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -256,8 +256,6 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) } rcu_read_unlock(); - atomic_set(&bat_priv->packet_size_max, min_mtu); - if (atomic_read(&bat_priv->fragmentation) == 0) goto out; @@ -268,13 +266,21 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); min_mtu -= sizeof(struct batadv_frag_packet); min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; - atomic_set(&bat_priv->packet_size_max, min_mtu); - - /* with fragmentation enabled we can fragment external packets easily */ - min_mtu = min_t(int, min_mtu, ETH_DATA_LEN); out: - return min_mtu - batadv_max_header_len(); + /* report to the other components the maximum amount of bytes that + * batman-adv can send over the wire (without considering the payload + * overhead). For example, this value is used by TT to compute the + * maximum local table table size + */ + atomic_set(&bat_priv->packet_size_max, min_mtu); + + /* the real soft-interface MTU is computed by removing the payload + * overhead from the maximum amount of bytes that was just computed. + * + * However batman-adv does not support MTUs bigger than ETH_DATA_LEN + */ + return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN); } /* adjusts the MTU if a new interface with a smaller MTU appeared. */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 6df12a2..8539416 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -458,6 +458,42 @@ out: } /** + * batadv_neigh_node_get - retrieve a neighbour from the list + * @orig_node: originator which the neighbour belongs to + * @hard_iface: the interface where this neighbour is connected to + * @addr: the address of the neighbour + * + * Looks for and possibly returns a neighbour belonging to this originator list + * which is connected through the provided hard interface. + * Returns NULL if the neighbour is not found. + */ +struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr) +{ + struct batadv_neigh_node *tmp_neigh_node, *res = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { + if (!batadv_compare_eth(tmp_neigh_node->addr, addr)) + continue; + + if (tmp_neigh_node->if_incoming != hard_iface) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + res = tmp_neigh_node; + break; + } + rcu_read_unlock(); + + return res; +} + +/** * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object * @rcu: rcu pointer of the orig_ifinfo object */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 37be290..db3a9ed 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -29,6 +29,10 @@ void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr); +struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, const uint8_t *neigh_addr, struct batadv_orig_node *orig_node); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 1ed9f7c..a953d5b 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -688,7 +688,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, int is_old_ttvn; /* check if there is enough data before accessing it */ - if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0) + if (!pskb_may_pull(skb, hdr_len + ETH_HLEN)) return 0; /* create a copy of the skb (in case of for re-routing) to modify it. */ @@ -918,6 +918,8 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, if (ret != NET_RX_SUCCESS) ret = batadv_route_unicast_packet(skb, recv_if); + else + consume_skb(skb); return ret; } diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 579f5f0..843febd 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -254,9 +254,9 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { - struct ethhdr *ethhdr = (struct ethhdr *)skb->data; + struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; - int ret = NET_XMIT_DROP; + int ret = NET_XMIT_DROP, hdr_size; if (!orig_node) goto out; @@ -265,12 +265,16 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; + + hdr_size = sizeof(*unicast_packet); break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; + + hdr_size = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -279,6 +283,7 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, goto out; } + ethhdr = (struct ethhdr *)(skb->data + hdr_size); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b6071f6..959dde7 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1975,6 +1975,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2011,8 +2012,11 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, orig_node)) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2046,6 +2050,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2064,8 +2069,11 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, if (tt_common->flags & BATADV_TT_CLIENT_NEW) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2262,6 +2270,7 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; + uint32_t crc; int i; /* check if each received CRC matches the locally stored one */ @@ -2281,7 +2290,10 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, if (!vlan) return false; - if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc)) + crc = vlan->tt.crc; + batadv_orig_node_vlan_free_ref(vlan); + + if (crc != ntohl(tt_vlan_tmp->crc)) return false; } @@ -3218,7 +3230,6 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, spin_lock_bh(&orig_node->tt_lock); - tt_change = (struct batadv_tvlv_tt_change *)tt_buff; batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, tt_change); diff --git a/net/core/dev.c b/net/core/dev.c index 4ad1b78..b1b0c8d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2420,7 +2420,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2495,34 +2495,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - netdev_features_t features) + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { + } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev) { __be16 protocol = skb->protocol; - netdev_features_t features = skb->dev->features; + netdev_features_t features = dev->features; - if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2530,9 +2532,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } -EXPORT_SYMBOL(netif_skb_features); +EXPORT_SYMBOL(netif_skb_dev_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 87577d4..e29e810 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb) return poff; } -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -372,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -392,7 +381,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } -EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, @@ -403,13 +391,13 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, - accel_priv); + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); else queue_index = __netdev_pick_tx(dev, skb); if (!accel_priv) - queue_index = dev_cap_txqueue(dev, queue_index); + queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 048dc8d..1a0dac2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1963,16 +1963,21 @@ replay: dev->ifindex = ifm->ifi_index; - if (ops->newlink) + if (ops->newlink) { err = ops->newlink(net, dev, tb, data); - else + /* Drivers should call free_netdev() in ->destructor + * and unregister it on failure so that device could be + * finally freed in rtnl_unlock. + */ + if (err < 0) + goto out; + } else { err = register_netdevice(dev); - - if (err < 0) { - free_netdev(dev); - goto out; + if (err < 0) { + free_netdev(dev); + goto out; + } } - err = rtnl_configure_link(dev, ifm); if (err < 0) unregister_netdevice(dev); diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index c073b81..62b5828 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -8,7 +8,7 @@ #include "tfrc.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG -static bool tfrc_debug; +bool tfrc_debug; module_param(tfrc_debug, bool, 0644); MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages"); #endif diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index a3d8f7c..40ee7d6 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -21,6 +21,7 @@ #include "packet_history.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG +extern bool tfrc_debug; #define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a) #else #define tfrc_pr_debug(format, a...) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e9f1217..f3869c1 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include <net/route.h> #include <net/xfrm.h> +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + !skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (unlikely(skb->len > mtu && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index efa1138..b3e86ea 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -273,7 +273,7 @@ static int __init ic_open_devs(void) msleep(1); - if time_before(jiffies, next_msg) + if (time_before(jiffies, next_msg)) continue; elapsed = jiffies_to_msecs(jiffies - start); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 25071b4..4c011ec 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1597,6 +1597,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1695,10 +1696,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) + if (err != 0) { + if (!IN_DEV_FORWARD(in_dev)) + err = -EHOSTUNREACH; goto no_route; - - RT_CACHE_STAT_INC(in_slow_tot); + } if (res.type == RTN_BROADCAST) goto brd_input; @@ -1712,8 +1714,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto local_input; } - if (!IN_DEV_FORWARD(in_dev)) + if (!IN_DEV_FORWARD(in_dev)) { + err = -EHOSTUNREACH; goto no_route; + } if (res.type != RTN_UNICAST) goto martian_destination; @@ -1768,6 +1772,7 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ad23569..fdbfeca 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2783,6 +2783,8 @@ static void addrconf_gre_config(struct net_device *dev) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) addrconf_add_linklocal(idev, &addr); + else + addrconf_prefix_route(&addr, 64, dev, 0, 0); } #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26..070a2fa 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d6d1f1d..ce1c443 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1057,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1075,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6a2bb37..48a6a93 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -308,11 +308,27 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) return po->xmit == packet_direct_xmit; } -static u16 packet_pick_tx_queue(struct net_device *dev) +static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) { return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; } +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +{ + const struct net_device_ops *ops = dev->netdev_ops; + u16 queue_index; + + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb, NULL, + __packet_pick_tx_queue); + queue_index = netdev_cap_txqueue(dev, queue_index); + } else { + queue_index = __packet_pick_tx_queue(dev, skb); + } + + skb_set_queue_mapping(skb, queue_index); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -2285,7 +2301,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } } - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + packet_pick_tx_queue(dev, skb); + skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2499,7 +2516,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + + packet_pick_tx_queue(dev, skb); if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { @@ -3786,7 +3804,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, */ if (!tx_ring) init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring); - break; + break; default: break; } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index a255d02..fefeeb7 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -15,6 +15,11 @@ * * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no> * University of Oslo, Norway. + * + * References: + * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00 + * IEEE Conference on High Performance Switching and Routing 2013 : + * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem" */ #include <linux/module.h> @@ -36,7 +41,7 @@ struct pie_params { psched_time_t target; /* user specified target delay in pschedtime */ u32 tupdate; /* timer frequency (in jiffies) */ u32 limit; /* number of packets that can be enqueued */ - u32 alpha; /* alpha and beta are between -4 and 4 */ + u32 alpha; /* alpha and beta are between 0 and 32 */ u32 beta; /* and are used for shift relative to 1 */ bool ecn; /* true if ecn is enabled */ bool bytemode; /* to scale drop early prob based on pkt size */ @@ -326,10 +331,16 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay == 0 && qlen != 0) update_prob = false; - /* Add ranges for alpha and beta, more aggressive for high dropping - * mode and gentle steps for light dropping mode - * In light dropping mode, take gentle steps; in medium dropping mode, - * take medium steps; in high dropping mode, take big steps. + /* In the algorithm, alpha and beta are between 0 and 2 with typical + * value for alpha as 0.125. In this implementation, we use values 0-32 + * passed from user space to represent this. Also, alpha and beta have + * unit of HZ and need to be scaled before they can used to update + * probability. alpha/beta are updated locally below by 1) scaling them + * appropriately 2) scaling down by 16 to come to 0-2 range. + * Please see paper for details. + * + * We scale alpha and beta differently depending on whether we are in + * light, medium or high dropping mode. */ if (q->vars.prob < MAX_PROB / 100) { alpha = diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5ae6092..f558433 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1367,44 +1367,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) +/* Update asoc's rwnd for the approximated state in the buffer, + * and check whether SACK needs to be sent. + */ +void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) { + int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->rwnd_over) { - if (asoc->rwnd_over >= len) { - asoc->rwnd_over -= len; - } else { - asoc->rwnd += (len - asoc->rwnd_over); - asoc->rwnd_over = 0; - } - } else { - asoc->rwnd += len; - } + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - /* If we had window pressure, start recovering it - * once our rwnd had reached the accumulated pressure - * threshold. The idea is to recover slowly, but up - * to the initial advertised window. - */ - if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { - int change = min(asoc->pathmtu, asoc->rwnd_press); - asoc->rwnd += change; - asoc->rwnd_press -= change; - } + if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) + asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; + else + asoc->rwnd = 0; - pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->a_rwnd); + pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", + __func__, asoc, asoc->rwnd, rx_count, + asoc->base.sk->sk_rcvbuf); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (sctp_peer_needs_update(asoc)) { + if (update_peer && sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1426,45 +1417,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) } } -/* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) -{ - int rx_count; - int over = 0; - - if (unlikely(!asoc->rwnd || asoc->rwnd_over)) - pr_debug("%s: association:%p has asoc->rwnd:%u, " - "asoc->rwnd_over:%u!\n", __func__, asoc, - asoc->rwnd, asoc->rwnd_over); - - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - - /* If we've reached or overflowed our receive buffer, announce - * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored - * back to original value. - */ - if (rx_count >= asoc->base.sk->sk_rcvbuf) - over = 1; - - if (asoc->rwnd >= len) { - asoc->rwnd -= len; - if (over) { - asoc->rwnd_press += asoc->rwnd; - asoc->rwnd = 0; - } - } else { - asoc->rwnd_over = len - asoc->rwnd; - asoc->rwnd = 0; - } - - pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->rwnd_press); -} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 483dcd7..591b44d 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6176,7 +6176,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || + if ((!chunk->data_accepted) && (!asoc->rwnd || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e91d6e..981aaf8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -64,6 +64,7 @@ #include <linux/crypto.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/ip.h> #include <net/icmp.h> @@ -1368,11 +1369,19 @@ static int sctp_setsockopt_connectx(struct sock *sk, /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library - * can avoid any unnecessary allocations. The only defferent part + * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the - * addrs_num structure member. That way we can re-use the existing + * addrs_num structure member. That way we can re-use the existing * code. */ +#ifdef CONFIG_COMPAT +struct compat_sctp_getaddrs_old { + sctp_assoc_t assoc_id; + s32 addr_num; + compat_uptr_t addrs; /* struct sockaddr * */ +}; +#endif + static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -1381,16 +1390,30 @@ static int sctp_getsockopt_connectx3(struct sock *sk, int len, sctp_assoc_t assoc_id = 0; int err = 0; - if (len < sizeof(param)) - return -EINVAL; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sctp_getaddrs_old param32; - if (copy_from_user(¶m, optval, sizeof(param))) - return -EFAULT; + if (len < sizeof(param32)) + return -EINVAL; + if (copy_from_user(¶m32, optval, sizeof(param32))) + return -EFAULT; - err = __sctp_setsockopt_connectx(sk, - (struct sockaddr __user *)param.addrs, - param.addr_num, &assoc_id); + param.assoc_id = param32.assoc_id; + param.addr_num = param32.addr_num; + param.addrs = compat_ptr(param32.addrs); + } else +#endif + { + if (len < sizeof(param)) + return -EINVAL; + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + } + err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *) + param.addrs, param.addr_num, + &assoc_id); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; @@ -2092,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); - /* When only partial message is copied to the user, increase - * rwnd by that amount. If all the data in the skb is read, - * rwnd is updated when the event is freed. - */ - if (!sctp_ulpevent_is_notification(event)) - sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 7135e61..35c8923 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -151,6 +151,7 @@ static struct ctl_table sctp_net_table[] = { }, { .procname = "cookie_hmac_alg", + .data = &init_net.sctp.sctp_hmac_alg, .maxlen = 8, .mode = 0644, .proc_handler = proc_sctp_do_hmac_alg, @@ -401,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, int sctp_sysctl_net_register(struct net *net) { - struct ctl_table *table; - int i; + struct ctl_table *table = sctp_net_table; + + if (!net_eq(net, &init_net)) { + int i; - table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); - if (!table) - return -ENOMEM; + table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); + if (!table) + return -ENOMEM; - for (i = 0; table[i].data; i++) - table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + for (i = 0; table[i].data; i++) + table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + } net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); return 0; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 85c6465..8d198ae 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); + sctp_assoc_rwnd_update(asoc, false); if (!skb->data_len) return; @@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; + struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - sctp_assoc_rwnd_increase(event->asoc, len); + asoc = event->asoc; + sctp_association_hold(asoc); sctp_ulpevent_release_owner(event); + sctp_assoc_rwnd_update(asoc, true); + sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) diff --git a/net/tipc/core.h b/net/tipc/core.h index 1ff477b..5569d96 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -192,6 +192,7 @@ static inline void k_term_timer(struct timer_list *timer) struct tipc_skb_cb { void *handle; + bool deferred; }; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) diff --git a/net/tipc/link.c b/net/tipc/link.c index d4b5de4..da6018b 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1391,6 +1391,12 @@ static int link_recv_buf_validate(struct sk_buff *buf) u32 hdr_size; u32 min_hdr_size; + /* If this packet comes from the defer queue, the skb has already + * been validated + */ + if (unlikely(TIPC_SKB_CB(buf)->deferred)) + return 1; + if (unlikely(buf->len < MIN_H_SIZE)) return 0; @@ -1703,6 +1709,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, &l_ptr->newest_deferred_in, buf)) { l_ptr->deferred_inqueue_sz++; l_ptr->stats.deferred_recv++; + TIPC_SKB_CB(buf)->deferred = true; if ((l_ptr->deferred_inqueue_sz % 16) == 1) tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } else |