diff options
84 files changed, 1036 insertions, 3650 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 78d9cbf..ea17512 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5711,13 +5711,6 @@ M: Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar> S: Maintained F: net/ipv4/netfilter/ipt_MASQUERADE.c -IP1000A 10/100/1000 GIGABIT ETHERNET DRIVER -M: Francois Romieu <romieu@fr.zoreil.com> -M: Sorbica Shieh <sorbica@icplus.com.tw> -L: netdev@vger.kernel.org -S: Maintained -F: drivers/net/ethernet/icplus/ipg.* - IPATH DRIVER M: Mike Marciniszyn <infinipath@intel.com> L: linux-rdma@vger.kernel.org @@ -6923,13 +6916,21 @@ F: drivers/scsi/megaraid.* F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) -M: Amir Vadai <amirv@mellanox.com> +M: Eugenia Emantayev <eugenia@mellanox.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* +MELLANOX ETHERNET DRIVER (mlx5e) +M: Saeed Mahameed <saeedm@mellanox.com> +L: netdev@vger.kernel.org +S: Supported +W: http://www.mellanox.com +Q: http://patchwork.ozlabs.org/project/netdev/list/ +F: drivers/net/ethernet/mellanox/mlx5/core/en_* + MELLANOX ETHERNET SWITCH DRIVERS M: Jiri Pirko <jiri@mellanox.com> M: Ido Schimmel <idosch@mellanox.com> diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 2f4b14c..591f9db 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1061,7 +1061,7 @@ void bpf_jit_compile(struct bpf_prog *fp) } build_epilogue(&ctx); - flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); + flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); #if __LINUX_ARM_ARCH__ < 7 if (ctx.imm_count) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index cf3c7d4..d6a53ef 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -50,7 +50,7 @@ static const int bpf2a64[] = { [BPF_REG_8] = A64_R(21), [BPF_REG_9] = A64_R(22), /* read-only frame pointer to access stack */ - [BPF_REG_FP] = A64_FP, + [BPF_REG_FP] = A64_R(25), /* temporary register for internal BPF JIT */ [TMP_REG_1] = A64_R(23), [TMP_REG_2] = A64_R(24), @@ -155,18 +155,49 @@ static void build_prologue(struct jit_ctx *ctx) stack_size += 4; /* extra for skb_copy_bits buffer */ stack_size = STACK_ALIGN(stack_size); + /* + * BPF prog stack layout + * + * high + * original A64_SP => 0:+-----+ BPF prologue + * |FP/LR| + * current A64_FP => -16:+-----+ + * | ... | callee saved registers + * +-----+ + * | | x25/x26 + * BPF fp register => -80:+-----+ + * | | + * | ... | BPF prog stack + * | | + * | | + * current A64_SP => +-----+ + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + * + */ + + /* Save FP and LR registers to stay align with ARM64 AAPCS */ + emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); + emit(A64_MOV(1, A64_FP, A64_SP), ctx); + /* Save callee-saved register */ emit(A64_PUSH(r6, r7, A64_SP), ctx); emit(A64_PUSH(r8, r9, A64_SP), ctx); if (ctx->tmp_used) emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx); - /* Set up BPF stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Save fp (x25) and x26. SP requires 16 bytes alignment */ + emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx); - /* Set up frame pointer */ + /* Set up BPF prog stack base register (x25) */ emit(A64_MOV(1, fp, A64_SP), ctx); + /* Set up function call stack */ + emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Clear registers A and X */ emit_a64_mov_i64(ra, 0, ctx); emit_a64_mov_i64(rx, 0, ctx); @@ -190,14 +221,17 @@ static void build_epilogue(struct jit_ctx *ctx) /* We're done with BPF stack */ emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Restore fs (x25) and x26 */ + emit(A64_POP(fp, A64_R(26), A64_SP), ctx); + /* Restore callee-saved register */ if (ctx->tmp_used) emit(A64_POP(tmp1, tmp2, A64_SP), ctx); emit(A64_POP(r8, r9, A64_SP), ctx); emit(A64_POP(r6, r7, A64_SP), ctx); - /* Restore frame pointer */ - emit(A64_MOV(1, fp, A64_SP), ctx); + /* Restore FP/LR registers */ + emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); /* Set return value */ emit(A64_MOV(1, A64_R(0), r0), ctx); @@ -758,7 +792,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog) if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, image_size, 2, ctx.image); - bpf_flush_icache(ctx.image, ctx.image + ctx.idx); + bpf_flush_icache(header, ctx.image + ctx.idx); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)ctx.image; diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 9093577..0527f48 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -15,9 +15,7 @@ #include <linux/netdevice.h> #include <linux/phy.h> #include <net/dsa.h> - -#define REG_PORT(p) (8 + (p)) -#define REG_GLOBAL 0x0f +#include "mv88e6060.h" static int reg_read(struct dsa_switch *ds, int addr, int reg) { @@ -67,13 +65,14 @@ static char *mv88e6060_probe(struct device *host_dev, int sw_addr) if (bus == NULL) return NULL; - ret = mdiobus_read(bus, sw_addr + REG_PORT(0), 0x03); + ret = mdiobus_read(bus, sw_addr + REG_PORT(0), PORT_SWITCH_ID); if (ret >= 0) { - if (ret == 0x0600) + if (ret == PORT_SWITCH_ID_6060) return "Marvell 88E6060 (A0)"; - if (ret == 0x0601 || ret == 0x0602) + if (ret == PORT_SWITCH_ID_6060_R1 || + ret == PORT_SWITCH_ID_6060_R2) return "Marvell 88E6060 (B0)"; - if ((ret & 0xfff0) == 0x0600) + if ((ret & PORT_SWITCH_ID_6060_MASK) == PORT_SWITCH_ID_6060) return "Marvell 88E6060"; } @@ -87,22 +86,26 @@ static int mv88e6060_switch_reset(struct dsa_switch *ds) unsigned long timeout; /* Set all ports to the disabled state. */ - for (i = 0; i < 6; i++) { - ret = REG_READ(REG_PORT(i), 0x04); - REG_WRITE(REG_PORT(i), 0x04, ret & 0xfffc); + for (i = 0; i < MV88E6060_PORTS; i++) { + ret = REG_READ(REG_PORT(i), PORT_CONTROL); + REG_WRITE(REG_PORT(i), PORT_CONTROL, + ret & ~PORT_CONTROL_STATE_MASK); } /* Wait for transmit queues to drain. */ usleep_range(2000, 4000); /* Reset the switch. */ - REG_WRITE(REG_GLOBAL, 0x0a, 0xa130); + REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_SWRESET | + GLOBAL_ATU_CONTROL_ATUSIZE_1024 | + GLOBAL_ATU_CONTROL_ATE_AGE_5MIN); /* Wait up to one second for reset to complete. */ timeout = jiffies + 1 * HZ; while (time_before(jiffies, timeout)) { - ret = REG_READ(REG_GLOBAL, 0x00); - if ((ret & 0x8000) == 0x0000) + ret = REG_READ(REG_GLOBAL, GLOBAL_STATUS); + if (ret & GLOBAL_STATUS_INIT_READY) break; usleep_range(1000, 2000); @@ -119,13 +122,15 @@ static int mv88e6060_setup_global(struct dsa_switch *ds) * set the maximum frame size to 1536 bytes, and mask all * interrupt sources. */ - REG_WRITE(REG_GLOBAL, 0x04, 0x0800); + REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL, GLOBAL_CONTROL_MAX_FRAME_1536); /* Enable automatic address learning, set the address * database size to 1024 entries, and set the default aging * time to 5 minutes. */ - REG_WRITE(REG_GLOBAL, 0x0a, 0x2130); + REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_ATUSIZE_1024 | + GLOBAL_ATU_CONTROL_ATE_AGE_5MIN); return 0; } @@ -139,25 +144,30 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) * state to Forwarding. Additionally, if this is the CPU * port, enable Ingress and Egress Trailer tagging mode. */ - REG_WRITE(addr, 0x04, dsa_is_cpu_port(ds, p) ? 0x4103 : 0x0003); + REG_WRITE(addr, PORT_CONTROL, + dsa_is_cpu_port(ds, p) ? + PORT_CONTROL_TRAILER | + PORT_CONTROL_INGRESS_MODE | + PORT_CONTROL_STATE_FORWARDING : + PORT_CONTROL_STATE_FORWARDING); /* Port based VLAN map: give each port its own address * database, allow the CPU port to talk to each of the 'real' * ports, and allow each of the 'real' ports to only talk to * the CPU port. */ - REG_WRITE(addr, 0x06, - ((p & 0xf) << 12) | - (dsa_is_cpu_port(ds, p) ? - ds->phys_port_mask : - (1 << ds->dst->cpu_port))); + REG_WRITE(addr, PORT_VLAN_MAP, + ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | + (dsa_is_cpu_port(ds, p) ? + ds->phys_port_mask : + BIT(ds->dst->cpu_port))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using * a port bitmap that has only the bit for this port set and * the other bits clear. */ - REG_WRITE(addr, 0x0b, 1 << p); + REG_WRITE(addr, PORT_ASSOC_VECTOR, BIT(p)); return 0; } @@ -177,7 +187,7 @@ static int mv88e6060_setup(struct dsa_switch *ds) if (ret < 0) return ret; - for (i = 0; i < 6; i++) { + for (i = 0; i < MV88E6060_PORTS; i++) { ret = mv88e6060_setup_port(ds, i); if (ret < 0) return ret; @@ -188,16 +198,17 @@ static int mv88e6060_setup(struct dsa_switch *ds) static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr) { - REG_WRITE(REG_GLOBAL, 0x01, (addr[0] << 8) | addr[1]); - REG_WRITE(REG_GLOBAL, 0x02, (addr[2] << 8) | addr[3]); - REG_WRITE(REG_GLOBAL, 0x03, (addr[4] << 8) | addr[5]); + /* Use the same MAC Address as FD Pause frames for all ports */ + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); return 0; } static int mv88e6060_port_to_phy_addr(int port) { - if (port >= 0 && port <= 5) + if (port >= 0 && port < MV88E6060_PORTS) return port; return -1; } @@ -225,54 +236,6 @@ mv88e6060_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) return reg_write(ds, addr, regnum, val); } -static void mv88e6060_poll_link(struct dsa_switch *ds) -{ - int i; - - for (i = 0; i < DSA_MAX_PORTS; i++) { - struct net_device *dev; - int uninitialized_var(port_status); - int link; - int speed; - int duplex; - int fc; - - dev = ds->ports[i]; - if (dev == NULL) - continue; - - link = 0; - if (dev->flags & IFF_UP) { - port_status = reg_read(ds, REG_PORT(i), 0x00); - if (port_status < 0) - continue; - - link = !!(port_status & 0x1000); - } - - if (!link) { - if (netif_carrier_ok(dev)) { - netdev_info(dev, "link down\n"); - netif_carrier_off(dev); - } - continue; - } - - speed = (port_status & 0x0100) ? 100 : 10; - duplex = (port_status & 0x0200) ? 1 : 0; - fc = ((port_status & 0xc000) == 0xc000) ? 1 : 0; - - if (!netif_carrier_ok(dev)) { - netdev_info(dev, - "link up, %d Mb/s, %s duplex, flow control %sabled\n", - speed, - duplex ? "full" : "half", - fc ? "en" : "dis"); - netif_carrier_on(dev); - } - } -} - static struct dsa_switch_driver mv88e6060_switch_driver = { .tag_protocol = DSA_TAG_PROTO_TRAILER, .probe = mv88e6060_probe, @@ -280,7 +243,6 @@ static struct dsa_switch_driver mv88e6060_switch_driver = { .set_addr = mv88e6060_set_addr, .phy_read = mv88e6060_phy_read, .phy_write = mv88e6060_phy_write, - .poll_link = mv88e6060_poll_link, }; static int __init mv88e6060_init(void) diff --git a/drivers/net/dsa/mv88e6060.h b/drivers/net/dsa/mv88e6060.h new file mode 100644 index 0000000..cc9b2ed --- /dev/null +++ b/drivers/net/dsa/mv88e6060.h @@ -0,0 +1,111 @@ +/* + * drivers/net/dsa/mv88e6060.h - Marvell 88e6060 switch chip support + * Copyright (c) 2015 Neil Armstrong + * + * Based on mv88e6xxx.h + * Copyright (c) 2008 Marvell Semiconductor + * + * 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. + */ + +#ifndef __MV88E6060_H +#define __MV88E6060_H + +#define MV88E6060_PORTS 6 + +#define REG_PORT(p) (0x8 + (p)) +#define PORT_STATUS 0x00 +#define PORT_STATUS_PAUSE_EN BIT(15) +#define PORT_STATUS_MY_PAUSE BIT(14) +#define PORT_STATUS_FC (PORT_STATUS_MY_PAUSE | PORT_STATUS_PAUSE_EN) +#define PORT_STATUS_RESOLVED BIT(13) +#define PORT_STATUS_LINK BIT(12) +#define PORT_STATUS_PORTMODE BIT(11) +#define PORT_STATUS_PHYMODE BIT(10) +#define PORT_STATUS_DUPLEX BIT(9) +#define PORT_STATUS_SPEED BIT(8) +#define PORT_SWITCH_ID 0x03 +#define PORT_SWITCH_ID_6060 0x0600 +#define PORT_SWITCH_ID_6060_MASK 0xfff0 +#define PORT_SWITCH_ID_6060_R1 0x0601 +#define PORT_SWITCH_ID_6060_R2 0x0602 +#define PORT_CONTROL 0x04 +#define PORT_CONTROL_FORCE_FLOW_CTRL BIT(15) +#define PORT_CONTROL_TRAILER BIT(14) +#define PORT_CONTROL_HEADER BIT(11) +#define PORT_CONTROL_INGRESS_MODE BIT(8) +#define PORT_CONTROL_VLAN_TUNNEL BIT(7) +#define PORT_CONTROL_STATE_MASK 0x03 +#define PORT_CONTROL_STATE_DISABLED 0x00 +#define PORT_CONTROL_STATE_BLOCKING 0x01 +#define PORT_CONTROL_STATE_LEARNING 0x02 +#define PORT_CONTROL_STATE_FORWARDING 0x03 +#define PORT_VLAN_MAP 0x06 +#define PORT_VLAN_MAP_DBNUM_SHIFT 12 +#define PORT_VLAN_MAP_TABLE_MASK 0x1f +#define PORT_ASSOC_VECTOR 0x0b +#define PORT_ASSOC_VECTOR_MONITOR BIT(15) +#define PORT_ASSOC_VECTOR_PAV_MASK 0x1f +#define PORT_RX_CNTR 0x10 +#define PORT_TX_CNTR 0x11 + +#define REG_GLOBAL 0x0f +#define GLOBAL_STATUS 0x00 +#define GLOBAL_STATUS_SW_MODE_MASK (0x3 << 12) +#define GLOBAL_STATUS_SW_MODE_0 (0x0 << 12) +#define GLOBAL_STATUS_SW_MODE_1 (0x1 << 12) +#define GLOBAL_STATUS_SW_MODE_2 (0x2 << 12) +#define GLOBAL_STATUS_SW_MODE_3 (0x3 << 12) +#define GLOBAL_STATUS_INIT_READY BIT(11) +#define GLOBAL_STATUS_ATU_FULL BIT(3) +#define GLOBAL_STATUS_ATU_DONE BIT(2) +#define GLOBAL_STATUS_PHY_INT BIT(1) +#define GLOBAL_STATUS_EEINT BIT(0) +#define GLOBAL_MAC_01 0x01 +#define GLOBAL_MAC_01_DIFF_ADDR BIT(8) +#define GLOBAL_MAC_23 0x02 +#define GLOBAL_MAC_45 0x03 +#define GLOBAL_CONTROL 0x04 +#define GLOBAL_CONTROL_DISCARD_EXCESS BIT(13) +#define GLOBAL_CONTROL_MAX_FRAME_1536 BIT(10) +#define GLOBAL_CONTROL_RELOAD_EEPROM BIT(9) +#define GLOBAL_CONTROL_CTRMODE BIT(8) +#define GLOBAL_CONTROL_ATU_FULL_EN BIT(3) +#define GLOBAL_CONTROL_ATU_DONE_EN BIT(2) +#define GLOBAL_CONTROL_PHYINT_EN BIT(1) +#define GLOBAL_CONTROL_EEPROM_DONE_EN BIT(0) +#define GLOBAL_ATU_CONTROL 0x0a +#define GLOBAL_ATU_CONTROL_SWRESET BIT(15) +#define GLOBAL_ATU_CONTROL_LEARNDIS BIT(14) +#define GLOBAL_ATU_CONTROL_ATUSIZE_256 (0x0 << 12) +#define GLOBAL_ATU_CONTROL_ATUSIZE_512 (0x1 << 12) +#define GLOBAL_ATU_CONTROL_ATUSIZE_1024 (0x2 << 12) +#define GLOBAL_ATU_CONTROL_ATE_AGE_SHIFT 4 +#define GLOBAL_ATU_CONTROL_ATE_AGE_MASK (0xff << 4) +#define GLOBAL_ATU_CONTROL_ATE_AGE_5MIN (0x13 << 4) +#define GLOBAL_ATU_OP 0x0b +#define GLOBAL_ATU_OP_BUSY BIT(15) +#define GLOBAL_ATU_OP_NOP (0 << 12) +#define GLOBAL_ATU_OP_FLUSH_ALL ((1 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_UNLOCKED ((2 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_LOAD_DB ((3 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_GET_NEXT_DB ((4 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_DB ((5 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_UNLOCKED_DB ((6 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_DATA 0x0c +#define GLOBAL_ATU_DATA_PORT_VECTOR_MASK 0x3f0 +#define GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT 4 +#define GLOBAL_ATU_DATA_STATE_MASK 0x0f +#define GLOBAL_ATU_DATA_STATE_UNUSED 0x00 +#define GLOBAL_ATU_DATA_STATE_UC_STATIC 0x0e +#define GLOBAL_ATU_DATA_STATE_UC_LOCKED 0x0f +#define GLOBAL_ATU_DATA_STATE_MC_STATIC 0x07 +#define GLOBAL_ATU_DATA_STATE_MC_LOCKED 0x0e +#define GLOBAL_ATU_MAC_01 0x0d +#define GLOBAL_ATU_MAC_23 0x0e +#define GLOBAL_ATU_MAC_45 0x0f + +#endif diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 05aa759..955d06b 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -78,7 +78,6 @@ source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" -source "drivers/net/ethernet/icplus/Kconfig" config JME tristate "JMicron(R) PCI-Express Gigabit Ethernet support" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index ddfc808..4a2ee98 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_NET_VENDOR_IBM) += ibm/ obj-$(CONFIG_NET_VENDOR_INTEL) += intel/ obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/ obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/ -obj-$(CONFIG_IP1000) += icplus/ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_KORINA) += korina.o obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index f1d62d5..c9b0367 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13207,7 +13207,7 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, /* VF with OLD Hypervisor or old PF do not support filtering */ if (IS_PF(bp)) { - if (CHIP_IS_E1x(bp)) + if (chip_is_e1x) bp->accept_any_vlan = true; else dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index f683d97..b895044 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -560,7 +560,7 @@ static int liquidio_resume(struct pci_dev *pdev) #endif /* For PCI-E Advanced Error Recovery (AER) Interface */ -static struct pci_error_handlers liquidio_err_handler = { +static const struct pci_error_handlers liquidio_err_handler = { .error_detected = liquidio_pcie_error_detected, .mmio_enabled = liquidio_pcie_mmio_enabled, .slot_reset = liquidio_pcie_slot_reset, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index a937772..7f709cb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1583,8 +1583,14 @@ err_disable_device: static void nicvf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct nicvf *nic = netdev_priv(netdev); - struct net_device *pnetdev = nic->pnicvf->netdev; + struct nicvf *nic; + struct net_device *pnetdev; + + if (!netdev) + return; + + nic = netdev_priv(netdev); + pnetdev = nic->pnicvf->netdev; /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig index f6e858d..ebdc832 100644 --- a/drivers/net/ethernet/dlink/Kconfig +++ b/drivers/net/ethernet/dlink/Kconfig @@ -17,15 +17,16 @@ config NET_VENDOR_DLINK if NET_VENDOR_DLINK config DL2K - tristate "DL2000/TC902x-based Gigabit Ethernet support" + tristate "DL2000/TC902x/IP1000A-based Gigabit Ethernet support" depends on PCI select CRC32 ---help--- - This driver supports DL2000/TC902x-based Gigabit ethernet cards, + This driver supports DL2000/TC902x/IP1000A-based Gigabit ethernet cards, which includes D-Link DGE-550T Gigabit Ethernet Adapter. D-Link DL2000-based Gigabit Ethernet Adapter. Sundance/Tamarack TC902x Gigabit Ethernet Adapter. + ICPlus IP1000A-based cards To compile this driver as a module, choose M here: the module will be called dl2k. diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index cf0a5fc..ccca479 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -253,6 +253,19 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_out_unmap_rx; + if (np->chip_id == CHIP_IP1000A && + (np->pdev->revision == 0x40 || np->pdev->revision == 0x41)) { + /* PHY magic taken from ipg driver, undocumented registers */ + mii_write(dev, np->phy_addr, 31, 0x0001); + mii_write(dev, np->phy_addr, 27, 0x01e0); + mii_write(dev, np->phy_addr, 31, 0x0002); + mii_write(dev, np->phy_addr, 27, 0xeb8e); + mii_write(dev, np->phy_addr, 31, 0x0000); + mii_write(dev, np->phy_addr, 30, 0x005e); + /* advertise 1000BASE-T half & full duplex, prefer MASTER */ + mii_write(dev, np->phy_addr, MII_CTRL1000, 0x0700); + } + /* Fiber device? */ np->phy_media = (dr16(ASICCtrl) & PhyMedia) ? 1 : 0; np->link_status = 0; @@ -361,6 +374,11 @@ parse_eeprom (struct net_device *dev) for (i = 0; i < 6; i++) dev->dev_addr[i] = psrom->mac_addr[i]; + if (np->chip_id == CHIP_IP1000A) { + np->led_mode = psrom->led_mode; + return 0; + } + if (np->pdev->vendor != PCI_VENDOR_ID_DLINK) { return 0; } @@ -406,6 +424,28 @@ parse_eeprom (struct net_device *dev) return 0; } +static void rio_set_led_mode(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->ioaddr; + u32 mode; + + if (np->chip_id != CHIP_IP1000A) + return; + + mode = dr32(ASICCtrl); + mode &= ~(IPG_AC_LED_MODE_BIT_1 | IPG_AC_LED_MODE | IPG_AC_LED_SPEED); + + if (np->led_mode & 0x01) + mode |= IPG_AC_LED_MODE; + if (np->led_mode & 0x02) + mode |= IPG_AC_LED_MODE_BIT_1; + if (np->led_mode & 0x08) + mode |= IPG_AC_LED_SPEED; + + dw32(ASICCtrl, mode); +} + static int rio_open (struct net_device *dev) { @@ -424,6 +464,8 @@ rio_open (struct net_device *dev) GlobalReset | DMAReset | FIFOReset | NetworkReset | HostReset); mdelay(10); + rio_set_led_mode(dev); + /* DebugCtrl bit 4, 5, 9 must set */ dw32(DebugCtrl, dr32(DebugCtrl) | 0x0230); @@ -433,9 +475,13 @@ rio_open (struct net_device *dev) alloc_list (dev); - /* Get station address */ - for (i = 0; i < 6; i++) - dw8(StationAddr0 + i, dev->dev_addr[i]); + /* Set station address */ + /* 16 or 32-bit access is required by TC9020 datasheet but 8-bit works + * too. However, it doesn't work on IP1000A so we use 16-bit access. + */ + for (i = 0; i < 3; i++) + dw16(StationAddr0 + 2 * i, + cpu_to_le16(((u16 *)dev->dev_addr)[i])); set_multicast (dev); if (np->coalesce) { @@ -780,6 +826,7 @@ tx_error (struct net_device *dev, int tx_status) break; mdelay (1); } + rio_set_led_mode(dev); rio_free_tx (dev, 1); /* Reset TFDListPtr */ dw32(TFDListPtr0, np->tx_ring_dma + @@ -799,6 +846,7 @@ tx_error (struct net_device *dev, int tx_status) break; mdelay (1); } + rio_set_led_mode(dev); /* Let TxStartThresh stay default value */ } /* Maximum Collisions */ @@ -965,6 +1013,7 @@ rio_error (struct net_device *dev, int int_status) dev->name, int_status); dw16(ASICCtrl + 2, GlobalReset | HostReset); mdelay (500); + rio_set_led_mode(dev); } } diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h index 23c07b0..8f4f612 100644 --- a/drivers/net/ethernet/dlink/dl2k.h +++ b/drivers/net/ethernet/dlink/dl2k.h @@ -211,6 +211,10 @@ enum ASICCtrl_HiWord_bits { ResetBusy = 0x0400, }; +#define IPG_AC_LED_MODE BIT(14) +#define IPG_AC_LED_SPEED BIT(27) +#define IPG_AC_LED_MODE_BIT_1 BIT(29) + /* Transmit Frame Control bits */ enum TFC_bits { DwordAlign = 0x00000000, @@ -332,7 +336,10 @@ typedef struct t_SROM { u16 asic_ctrl; /* 0x02 */ u16 sub_vendor_id; /* 0x04 */ u16 sub_system_id; /* 0x06 */ - u16 reserved1[12]; /* 0x08-0x1f */ + u16 pci_base_1; /* 0x08 (IP1000A only) */ + u16 pci_base_2; /* 0x0a (IP1000A only) */ + u16 led_mode; /* 0x0c (IP1000A only) */ + u16 reserved1[9]; /* 0x0e-0x1f */ u8 mac_addr[6]; /* 0x20-0x25 */ u8 reserved2[10]; /* 0x26-0x2f */ u8 sib[204]; /* 0x30-0xfb */ @@ -397,6 +404,7 @@ struct netdev_private { u16 advertising; /* NWay media advertisement */ u16 negotiate; /* Negotiated media */ int phy_addr; /* PHY addresses. */ + u16 led_mode; /* LED mode read from EEPROM (IP1000A only) */ }; /* The station address location in the EEPROM. */ @@ -407,10 +415,15 @@ struct netdev_private { class_mask of the class are honored during the comparison. driver_data Data private to the driver. */ +#define CHIP_IP1000A 1 static const struct pci_device_id rio_pci_tbl[] = { {0x1186, 0x4000, PCI_ANY_ID, PCI_ANY_ID, }, {0x13f0, 0x1021, PCI_ANY_ID, PCI_ANY_ID, }, + { PCI_VDEVICE(SUNDANCE, 0x1023), CHIP_IP1000A }, + { PCI_VDEVICE(SUNDANCE, 0x2021), CHIP_IP1000A }, + { PCI_VDEVICE(DLINK, 0x9021), CHIP_IP1000A }, + { PCI_VDEVICE(DLINK, 0x4020), CHIP_IP1000A }, { } }; MODULE_DEVICE_TABLE (pci, rio_pci_tbl); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index f4cb8e4..734f655 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -1062,9 +1062,7 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, static int be_set_rss_hash_opts(struct be_adapter *adapter, struct ethtool_rxnfc *cmd) { - struct be_rx_obj *rxo; - int status = 0, i, j; - u8 rsstable[128]; + int status; u32 rss_flags = adapter->rss_info.rss_flags; if (cmd->data != L3_RSS_FLAGS && @@ -1113,20 +1111,11 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter, } if (rss_flags == adapter->rss_info.rss_flags) - return status; - - if (be_multi_rxq(adapter)) { - for (j = 0; j < 128; j += adapter->num_rss_qs) { - for_all_rss_queues(adapter, rxo, i) { - if ((j + i) >= 128) - break; - rsstable[j + i] = rxo->rss_id; - } - } - } + return 0; status = be_cmd_rss_config(adapter, adapter->rss_info.rsstable, - rss_flags, 128, adapter->rss_info.rss_hkey); + rss_flags, RSS_INDIR_TABLE_LEN, + adapter->rss_info.rss_hkey); if (!status) adapter->rss_info.rss_flags = rss_flags; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index eb48a97..b6ad029 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3518,7 +3518,7 @@ static int be_rx_qs_create(struct be_adapter *adapter) netdev_rss_key_fill(rss_key, RSS_HASH_KEY_LEN); rc = be_cmd_rss_config(adapter, rss->rsstable, rss->rss_flags, - 128, rss_key); + RSS_INDIR_TABLE_LEN, rss_key); if (rc) { rss->rss_flags = RSS_ENABLE_NONE; return rc; diff --git a/drivers/net/ethernet/icplus/Kconfig b/drivers/net/ethernet/icplus/Kconfig deleted file mode 100644 index 14a66e9..0000000 --- a/drivers/net/ethernet/icplus/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# -# IC Plus device configuration -# - -config IP1000 - tristate "IP1000 Gigabit Ethernet support" - depends on PCI - select MII - ---help--- - This driver supports IP1000 gigabit Ethernet cards. - - To compile this driver as a module, choose M here: the module - will be called ipg. This is recommended. diff --git a/drivers/net/ethernet/icplus/Makefile b/drivers/net/ethernet/icplus/Makefile deleted file mode 100644 index 5bc87c1..0000000 --- a/drivers/net/ethernet/icplus/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# -# Makefile for the IC Plus device drivers -# - -obj-$(CONFIG_IP1000) += ipg.o diff --git a/drivers/net/ethernet/icplus/ipg.c b/drivers/net/ethernet/icplus/ipg.c deleted file mode 100644 index c3b6af8..0000000 --- a/drivers/net/ethernet/icplus/ipg.c +++ /dev/null @@ -1,2300 +0,0 @@ -/* - * ipg.c: Device Driver for the IP1000 Gigabit Ethernet Adapter - * - * Copyright (C) 2003, 2007 IC Plus Corp - * - * Original Author: - * - * Craig Rich - * Sundance Technology, Inc. - * www.sundanceti.com - * craig_rich@sundanceti.com - * - * Current Maintainer: - * - * Sorbica Shieh. - * http://www.icplus.com.tw - * sorbica@icplus.com.tw - * - * Jesse Huang - * http://www.icplus.com.tw - * jesse@icplus.com.tw - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/crc32.h> -#include <linux/ethtool.h> -#include <linux/interrupt.h> -#include <linux/gfp.h> -#include <linux/mii.h> -#include <linux/mutex.h> - -#include <asm/div64.h> - -#define IPG_RX_RING_BYTES (sizeof(struct ipg_rx) * IPG_RFDLIST_LENGTH) -#define IPG_TX_RING_BYTES (sizeof(struct ipg_tx) * IPG_TFDLIST_LENGTH) -#define IPG_RESET_MASK \ - (IPG_AC_GLOBAL_RESET | IPG_AC_RX_RESET | IPG_AC_TX_RESET | \ - IPG_AC_DMA | IPG_AC_FIFO | IPG_AC_NETWORK | IPG_AC_HOST | \ - IPG_AC_AUTO_INIT) - -#define ipg_w32(val32, reg) iowrite32((val32), ioaddr + (reg)) -#define ipg_w16(val16, reg) iowrite16((val16), ioaddr + (reg)) -#define ipg_w8(val8, reg) iowrite8((val8), ioaddr + (reg)) - -#define ipg_r32(reg) ioread32(ioaddr + (reg)) -#define ipg_r16(reg) ioread16(ioaddr + (reg)) -#define ipg_r8(reg) ioread8(ioaddr + (reg)) - -enum { - netdev_io_size = 128 -}; - -#include "ipg.h" -#define DRV_NAME "ipg" - -MODULE_AUTHOR("IC Plus Corp. 2003"); -MODULE_DESCRIPTION("IC Plus IP1000 Gigabit Ethernet Adapter Linux Driver"); -MODULE_LICENSE("GPL"); - -/* - * Defaults - */ -#define IPG_MAX_RXFRAME_SIZE 0x0600 -#define IPG_RXFRAG_SIZE 0x0600 -#define IPG_RXSUPPORT_SIZE 0x0600 -#define IPG_IS_JUMBO false - -/* - * Variable record -- index by leading revision/length - * Revision/Length(=N*4), Address1, Data1, Address2, Data2,...,AddressN,DataN - */ -static const unsigned short DefaultPhyParam[] = { - /* 11/12/03 IP1000A v1-3 rev=0x40 */ - /*-------------------------------------------------------------------------- - (0x4000|(15*4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 22, 0x85bd, 24, 0xfff2, - 27, 0x0c10, 28, 0x0c10, 29, 0x2c10, 31, 0x0003, 23, 0x92f6, - 31, 0x0000, 23, 0x003d, 30, 0x00de, 20, 0x20e7, 9, 0x0700, - --------------------------------------------------------------------------*/ - /* 12/17/03 IP1000A v1-4 rev=0x40 */ - (0x4000 | (07 * 4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 27, 0xeb8e, 31, - 0x0000, - 30, 0x005e, 9, 0x0700, - /* 01/09/04 IP1000A v1-5 rev=0x41 */ - (0x4100 | (07 * 4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 27, 0xeb8e, 31, - 0x0000, - 30, 0x005e, 9, 0x0700, - 0x0000 -}; - -static const char * const ipg_brand_name[] = { - "IC PLUS IP1000 1000/100/10 based NIC", - "Sundance Technology ST2021 based NIC", - "Tamarack Microelectronics TC9020/9021 based NIC", - "D-Link NIC IP1000A" -}; - -static const struct pci_device_id ipg_pci_tbl[] = { - { PCI_VDEVICE(SUNDANCE, 0x1023), 0 }, - { PCI_VDEVICE(SUNDANCE, 0x2021), 1 }, - { PCI_VDEVICE(DLINK, 0x9021), 2 }, - { PCI_VDEVICE(DLINK, 0x4020), 3 }, - { 0, } -}; - -MODULE_DEVICE_TABLE(pci, ipg_pci_tbl); - -static inline void __iomem *ipg_ioaddr(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - return sp->ioaddr; -} - -#ifdef IPG_DEBUG -static void ipg_dump_rfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - u32 offset; - - IPG_DEBUG_MSG("_dump_rfdlist\n"); - - netdev_info(dev, "rx_current = %02x\n", sp->rx_current); - netdev_info(dev, "rx_dirty = %02x\n", sp->rx_dirty); - netdev_info(dev, "RFDList start address = %016lx\n", - (unsigned long)sp->rxd_map); - netdev_info(dev, "RFDListPtr register = %08x%08x\n", - ipg_r32(IPG_RFDLISTPTR1), ipg_r32(IPG_RFDLISTPTR0)); - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - offset = (u32) &sp->rxd[i].next_desc - (u32) sp->rxd; - netdev_info(dev, "%02x %04x RFDNextPtr = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].next_desc); - offset = (u32) &sp->rxd[i].rfs - (u32) sp->rxd; - netdev_info(dev, "%02x %04x RFS = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].rfs); - offset = (u32) &sp->rxd[i].frag_info - (u32) sp->rxd; - netdev_info(dev, "%02x %04x frag_info = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].frag_info); - } -} - -static void ipg_dump_tfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - u32 offset; - - IPG_DEBUG_MSG("_dump_tfdlist\n"); - - netdev_info(dev, "tx_current = %02x\n", sp->tx_current); - netdev_info(dev, "tx_dirty = %02x\n", sp->tx_dirty); - netdev_info(dev, "TFDList start address = %016lx\n", - (unsigned long) sp->txd_map); - netdev_info(dev, "TFDListPtr register = %08x%08x\n", - ipg_r32(IPG_TFDLISTPTR1), ipg_r32(IPG_TFDLISTPTR0)); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - offset = (u32) &sp->txd[i].next_desc - (u32) sp->txd; - netdev_info(dev, "%02x %04x TFDNextPtr = %016lx\n", - i, offset, (unsigned long)sp->txd[i].next_desc); - - offset = (u32) &sp->txd[i].tfc - (u32) sp->txd; - netdev_info(dev, "%02x %04x TFC = %016lx\n", - i, offset, (unsigned long) sp->txd[i].tfc); - offset = (u32) &sp->txd[i].frag_info - (u32) sp->txd; - netdev_info(dev, "%02x %04x frag_info = %016lx\n", - i, offset, (unsigned long) sp->txd[i].frag_info); - } -} -#endif - -static void ipg_write_phy_ctl(void __iomem *ioaddr, u8 data) -{ - ipg_w8(IPG_PC_RSVD_MASK & data, PHY_CTRL); - ndelay(IPG_PC_PHYCTRLWAIT_NS); -} - -static void ipg_drive_phy_ctl_low_high(void __iomem *ioaddr, u8 data) -{ - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | data); - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | data); -} - -static void send_three_state(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - phyctrlpolarity |= (IPG_PC_MGMTDATA & 0) | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, phyctrlpolarity); -} - -static void send_end(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - ipg_w8((IPG_PC_MGMTCLK_LO | (IPG_PC_MGMTDATA & 0) | IPG_PC_MGMTDIR | - phyctrlpolarity) & IPG_PC_RSVD_MASK, PHY_CTRL); -} - -static u16 read_phy_bit(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - u16 bit_data; - - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | phyctrlpolarity); - - bit_data = ((ipg_r8(PHY_CTRL) & IPG_PC_MGMTDATA) >> 1) & 1; - - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | phyctrlpolarity); - - return bit_data; -} - -/* - * Read a register from the Physical Layer device located - * on the IPG NIC, using the IPG PHYCTRL register. - */ -static int mdio_read(struct net_device *dev, int phy_id, int phy_reg) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - /* - * The GMII mangement frame structure for a read is as follows: - * - * |Preamble|st|op|phyad|regad|ta| data |idle| - * |< 32 1s>|01|10|AAAAA|RRRRR|z0|DDDDDDDDDDDDDDDD|z | - * - * <32 1s> = 32 consecutive logic 1 values - * A = bit of Physical Layer device address (MSB first) - * R = bit of register address (MSB first) - * z = High impedance state - * D = bit of read data (MSB first) - * - * Transmission order is 'Preamble' field first, bits transmitted - * left to right (first to last). - */ - struct { - u32 field; - unsigned int len; - } p[] = { - { GMII_PREAMBLE, 32 }, /* Preamble */ - { GMII_ST, 2 }, /* ST */ - { GMII_READ, 2 }, /* OP */ - { phy_id, 5 }, /* PHYAD */ - { phy_reg, 5 }, /* REGAD */ - { 0x0000, 2 }, /* TA */ - { 0x0000, 16 }, /* DATA */ - { 0x0000, 1 } /* IDLE */ - }; - unsigned int i, j; - u8 polarity, data; - - polarity = ipg_r8(PHY_CTRL); - polarity &= (IPG_PC_DUPLEX_POLARITY | IPG_PC_LINK_POLARITY); - - /* Create the Preamble, ST, OP, PHYAD, and REGAD field. */ - for (j = 0; j < 5; j++) { - for (i = 0; i < p[j].len; i++) { - /* For each variable length field, the MSB must be - * transmitted first. Rotate through the field bits, - * starting with the MSB, and move each bit into the - * the 1st (2^1) bit position (this is the bit position - * corresponding to the MgmtData bit of the PhyCtrl - * register for the IPG). - * - * Example: ST = 01; - * - * First write a '0' to bit 1 of the PhyCtrl - * register, then write a '1' to bit 1 of the - * PhyCtrl register. - * - * To do this, right shift the MSB of ST by the value: - * [field length - 1 - #ST bits already written] - * then left shift this result by 1. - */ - data = (p[j].field >> (p[j].len - 1 - i)) << 1; - data &= IPG_PC_MGMTDATA; - data |= polarity | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, data); - } - } - - send_three_state(ioaddr, polarity); - - read_phy_bit(ioaddr, polarity); - - /* - * For a read cycle, the bits for the next two fields (TA and - * DATA) are driven by the PHY (the IPG reads these bits). - */ - for (i = 0; i < p[6].len; i++) { - p[6].field |= - (read_phy_bit(ioaddr, polarity) << (p[6].len - 1 - i)); - } - - send_three_state(ioaddr, polarity); - send_three_state(ioaddr, polarity); - send_three_state(ioaddr, polarity); - send_end(ioaddr, polarity); - - /* Return the value of the DATA field. */ - return p[6].field; -} - -/* - * Write to a register from the Physical Layer device located - * on the IPG NIC, using the IPG PHYCTRL register. - */ -static void mdio_write(struct net_device *dev, int phy_id, int phy_reg, int val) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - /* - * The GMII mangement frame structure for a read is as follows: - * - * |Preamble|st|op|phyad|regad|ta| data |idle| - * |< 32 1s>|01|10|AAAAA|RRRRR|z0|DDDDDDDDDDDDDDDD|z | - * - * <32 1s> = 32 consecutive logic 1 values - * A = bit of Physical Layer device address (MSB first) - * R = bit of register address (MSB first) - * z = High impedance state - * D = bit of write data (MSB first) - * - * Transmission order is 'Preamble' field first, bits transmitted - * left to right (first to last). - */ - struct { - u32 field; - unsigned int len; - } p[] = { - { GMII_PREAMBLE, 32 }, /* Preamble */ - { GMII_ST, 2 }, /* ST */ - { GMII_WRITE, 2 }, /* OP */ - { phy_id, 5 }, /* PHYAD */ - { phy_reg, 5 }, /* REGAD */ - { 0x0002, 2 }, /* TA */ - { val & 0xffff, 16 }, /* DATA */ - { 0x0000, 1 } /* IDLE */ - }; - unsigned int i, j; - u8 polarity, data; - - polarity = ipg_r8(PHY_CTRL); - polarity &= (IPG_PC_DUPLEX_POLARITY | IPG_PC_LINK_POLARITY); - - /* Create the Preamble, ST, OP, PHYAD, and REGAD field. */ - for (j = 0; j < 7; j++) { - for (i = 0; i < p[j].len; i++) { - /* For each variable length field, the MSB must be - * transmitted first. Rotate through the field bits, - * starting with the MSB, and move each bit into the - * the 1st (2^1) bit position (this is the bit position - * corresponding to the MgmtData bit of the PhyCtrl - * register for the IPG). - * - * Example: ST = 01; - * - * First write a '0' to bit 1 of the PhyCtrl - * register, then write a '1' to bit 1 of the - * PhyCtrl register. - * - * To do this, right shift the MSB of ST by the value: - * [field length - 1 - #ST bits already written] - * then left shift this result by 1. - */ - data = (p[j].field >> (p[j].len - 1 - i)) << 1; - data &= IPG_PC_MGMTDATA; - data |= polarity | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, data); - } - } - - /* The last cycle is a tri-state, so read from the PHY. */ - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity); - ipg_r8(PHY_CTRL); - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity); -} - -static void ipg_set_led_mode(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - u32 mode; - - mode = ipg_r32(ASIC_CTRL); - mode &= ~(IPG_AC_LED_MODE_BIT_1 | IPG_AC_LED_MODE | IPG_AC_LED_SPEED); - - if ((sp->led_mode & 0x03) > 1) - mode |= IPG_AC_LED_MODE_BIT_1; /* Write Asic Control Bit 29 */ - - if ((sp->led_mode & 0x01) == 1) - mode |= IPG_AC_LED_MODE; /* Write Asic Control Bit 14 */ - - if ((sp->led_mode & 0x08) == 8) - mode |= IPG_AC_LED_SPEED; /* Write Asic Control Bit 27 */ - - ipg_w32(mode, ASIC_CTRL); -} - -static void ipg_set_phy_set(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - int physet; - - physet = ipg_r8(PHY_SET); - physet &= ~(IPG_PS_MEM_LENB9B | IPG_PS_MEM_LEN9 | IPG_PS_NON_COMPDET); - physet |= ((sp->led_mode & 0x70) >> 4); - ipg_w8(physet, PHY_SET); -} - -static int ipg_reset(struct net_device *dev, u32 resetflags) -{ - /* Assert functional resets via the IPG AsicCtrl - * register as specified by the 'resetflags' input - * parameter. - */ - void __iomem *ioaddr = ipg_ioaddr(dev); - unsigned int timeout_count = 0; - - IPG_DEBUG_MSG("_reset\n"); - - ipg_w32(ipg_r32(ASIC_CTRL) | resetflags, ASIC_CTRL); - - /* Delay added to account for problem with 10Mbps reset. */ - mdelay(IPG_AC_RESETWAIT); - - while (IPG_AC_RESET_BUSY & ipg_r32(ASIC_CTRL)) { - mdelay(IPG_AC_RESETWAIT); - if (++timeout_count > IPG_AC_RESET_TIMEOUT) - return -ETIME; - } - /* Set LED Mode in Asic Control */ - ipg_set_led_mode(dev); - - /* Set PHYSet Register Value */ - ipg_set_phy_set(dev); - return 0; -} - -/* Find the GMII PHY address. */ -static int ipg_find_phyaddr(struct net_device *dev) -{ - unsigned int phyaddr, i; - - for (i = 0; i < 32; i++) { - u32 status; - - /* Search for the correct PHY address among 32 possible. */ - phyaddr = (IPG_NIC_PHY_ADDRESS + i) % 32; - - /* 10/22/03 Grace change verify from GMII_PHY_STATUS to - GMII_PHY_ID1 - */ - - status = mdio_read(dev, phyaddr, MII_BMSR); - - if ((status != 0xFFFF) && (status != 0)) - return phyaddr; - } - - return 0x1f; -} - -/* - * Configure IPG based on result of IEEE 802.3 PHY - * auto-negotiation. - */ -static int ipg_config_autoneg(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int txflowcontrol; - unsigned int rxflowcontrol; - unsigned int fullduplex; - u32 mac_ctrl_val; - u32 asicctrl; - u8 phyctrl; - const char *speed; - const char *duplex; - const char *tx_desc; - const char *rx_desc; - - IPG_DEBUG_MSG("_config_autoneg\n"); - - asicctrl = ipg_r32(ASIC_CTRL); - phyctrl = ipg_r8(PHY_CTRL); - mac_ctrl_val = ipg_r32(MAC_CTRL); - - /* Set flags for use in resolving auto-negotiation, assuming - * non-1000Mbps, half duplex, no flow control. - */ - fullduplex = 0; - txflowcontrol = 0; - rxflowcontrol = 0; - - /* To accommodate a problem in 10Mbps operation, - * set a global flag if PHY running in 10Mbps mode. - */ - sp->tenmbpsmode = 0; - - /* Determine actual speed of operation. */ - switch (phyctrl & IPG_PC_LINK_SPEED) { - case IPG_PC_LINK_SPEED_10MBPS: - speed = "10Mbps"; - sp->tenmbpsmode = 1; - break; - case IPG_PC_LINK_SPEED_100MBPS: - speed = "100Mbps"; - break; - case IPG_PC_LINK_SPEED_1000MBPS: - speed = "1000Mbps"; - break; - default: - speed = "undefined!"; - return 0; - } - - netdev_info(dev, "Link speed = %s\n", speed); - if (sp->tenmbpsmode == 1) - netdev_info(dev, "10Mbps operational mode enabled\n"); - - if (phyctrl & IPG_PC_DUPLEX_STATUS) { - fullduplex = 1; - txflowcontrol = 1; - rxflowcontrol = 1; - } - - /* Configure full duplex, and flow control. */ - if (fullduplex == 1) { - - /* Configure IPG for full duplex operation. */ - - duplex = "full"; - - mac_ctrl_val |= IPG_MC_DUPLEX_SELECT_FD; - - if (txflowcontrol == 1) { - tx_desc = ""; - mac_ctrl_val |= IPG_MC_TX_FLOW_CONTROL_ENABLE; - } else { - tx_desc = "no "; - mac_ctrl_val &= ~IPG_MC_TX_FLOW_CONTROL_ENABLE; - } - - if (rxflowcontrol == 1) { - rx_desc = ""; - mac_ctrl_val |= IPG_MC_RX_FLOW_CONTROL_ENABLE; - } else { - rx_desc = "no "; - mac_ctrl_val &= ~IPG_MC_RX_FLOW_CONTROL_ENABLE; - } - } else { - duplex = "half"; - tx_desc = "no "; - rx_desc = "no "; - mac_ctrl_val &= (~IPG_MC_DUPLEX_SELECT_FD & - ~IPG_MC_TX_FLOW_CONTROL_ENABLE & - ~IPG_MC_RX_FLOW_CONTROL_ENABLE); - } - - netdev_info(dev, "setting %s duplex, %sTX, %sRX flow control\n", - duplex, tx_desc, rx_desc); - ipg_w32(mac_ctrl_val, MAC_CTRL); - - return 0; -} - -/* Determine and configure multicast operation and set - * receive mode for IPG. - */ -static void ipg_nic_set_multicast_list(struct net_device *dev) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - struct netdev_hw_addr *ha; - unsigned int hashindex; - u32 hashtable[2]; - u8 receivemode; - - IPG_DEBUG_MSG("_nic_set_multicast_list\n"); - - receivemode = IPG_RM_RECEIVEUNICAST | IPG_RM_RECEIVEBROADCAST; - - if (dev->flags & IFF_PROMISC) { - /* NIC to be configured in promiscuous mode. */ - receivemode = IPG_RM_RECEIVEALLFRAMES; - } else if ((dev->flags & IFF_ALLMULTI) || - ((dev->flags & IFF_MULTICAST) && - (netdev_mc_count(dev) > IPG_MULTICAST_HASHTABLE_SIZE))) { - /* NIC to be configured to receive all multicast - * frames. */ - receivemode |= IPG_RM_RECEIVEMULTICAST; - } else if ((dev->flags & IFF_MULTICAST) && !netdev_mc_empty(dev)) { - /* NIC to be configured to receive selected - * multicast addresses. */ - receivemode |= IPG_RM_RECEIVEMULTICASTHASH; - } - - /* Calculate the bits to set for the 64 bit, IPG HASHTABLE. - * The IPG applies a cyclic-redundancy-check (the same CRC - * used to calculate the frame data FCS) to the destination - * address all incoming multicast frames whose destination - * address has the multicast bit set. The least significant - * 6 bits of the CRC result are used as an addressing index - * into the hash table. If the value of the bit addressed by - * this index is a 1, the frame is passed to the host system. - */ - - /* Clear hashtable. */ - hashtable[0] = 0x00000000; - hashtable[1] = 0x00000000; - - /* Cycle through all multicast addresses to filter. */ - netdev_for_each_mc_addr(ha, dev) { - /* Calculate CRC result for each multicast address. */ - hashindex = crc32_le(0xffffffff, ha->addr, - ETH_ALEN); - - /* Use only the least significant 6 bits. */ - hashindex = hashindex & 0x3F; - - /* Within "hashtable", set bit number "hashindex" - * to a logic 1. - */ - set_bit(hashindex, (void *)hashtable); - } - - /* Write the value of the hashtable, to the 4, 16 bit - * HASHTABLE IPG registers. - */ - ipg_w32(hashtable[0], HASHTABLE_0); - ipg_w32(hashtable[1], HASHTABLE_1); - - ipg_w8(IPG_RM_RSVD_MASK & receivemode, RECEIVE_MODE); - - IPG_DEBUG_MSG("ReceiveMode = %x\n", ipg_r8(RECEIVE_MODE)); -} - -static int ipg_io_config(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = ipg_ioaddr(dev); - u32 origmacctrl; - u32 restoremacctrl; - - IPG_DEBUG_MSG("_io_config\n"); - - origmacctrl = ipg_r32(MAC_CTRL); - - restoremacctrl = origmacctrl | IPG_MC_STATISTICS_ENABLE; - - /* Based on compilation option, determine if FCS is to be - * stripped on receive frames by IPG. - */ - if (!IPG_STRIP_FCS_ON_RX) - restoremacctrl |= IPG_MC_RCV_FCS; - - /* Determine if transmitter and/or receiver are - * enabled so we may restore MACCTRL correctly. - */ - if (origmacctrl & IPG_MC_TX_ENABLED) - restoremacctrl |= IPG_MC_TX_ENABLE; - - if (origmacctrl & IPG_MC_RX_ENABLED) - restoremacctrl |= IPG_MC_RX_ENABLE; - - /* Transmitter and receiver must be disabled before setting - * IFSSelect. - */ - ipg_w32((origmacctrl & (IPG_MC_RX_DISABLE | IPG_MC_TX_DISABLE)) & - IPG_MC_RSVD_MASK, MAC_CTRL); - - /* Now that transmitter and receiver are disabled, write - * to IFSSelect. - */ - ipg_w32((origmacctrl & IPG_MC_IFS_96BIT) & IPG_MC_RSVD_MASK, MAC_CTRL); - - /* Set RECEIVEMODE register. */ - ipg_nic_set_multicast_list(dev); - - ipg_w16(sp->max_rxframe_size, MAX_FRAME_SIZE); - - ipg_w8(IPG_RXDMAPOLLPERIOD_VALUE, RX_DMA_POLL_PERIOD); - ipg_w8(IPG_RXDMAURGENTTHRESH_VALUE, RX_DMA_URGENT_THRESH); - ipg_w8(IPG_RXDMABURSTTHRESH_VALUE, RX_DMA_BURST_THRESH); - ipg_w8(IPG_TXDMAPOLLPERIOD_VALUE, TX_DMA_POLL_PERIOD); - ipg_w8(IPG_TXDMAURGENTTHRESH_VALUE, TX_DMA_URGENT_THRESH); - ipg_w8(IPG_TXDMABURSTTHRESH_VALUE, TX_DMA_BURST_THRESH); - ipg_w16((IPG_IE_HOST_ERROR | IPG_IE_TX_DMA_COMPLETE | - IPG_IE_TX_COMPLETE | IPG_IE_INT_REQUESTED | - IPG_IE_UPDATE_STATS | IPG_IE_LINK_EVENT | - IPG_IE_RX_DMA_COMPLETE | IPG_IE_RX_DMA_PRIORITY), INT_ENABLE); - ipg_w16(IPG_FLOWONTHRESH_VALUE, FLOW_ON_THRESH); - ipg_w16(IPG_FLOWOFFTHRESH_VALUE, FLOW_OFF_THRESH); - - /* IPG multi-frag frame bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0200, DEBUG_CTRL); - - /* IPG TX poll now bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0010, DEBUG_CTRL); - - /* IPG RX poll now bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0020, DEBUG_CTRL); - - /* Now restore MACCTRL to original setting. */ - ipg_w32(IPG_MC_RSVD_MASK & restoremacctrl, MAC_CTRL); - - /* Disable unused RMON statistics. */ - ipg_w32(IPG_RZ_ALL, RMON_STATISTICS_MASK); - - /* Disable unused MIB statistics. */ - ipg_w32(IPG_SM_MACCONTROLFRAMESXMTD | IPG_SM_MACCONTROLFRAMESRCVD | - IPG_SM_BCSTOCTETXMTOK_BCSTFRAMESXMTDOK | IPG_SM_TXJUMBOFRAMES | - IPG_SM_MCSTOCTETXMTOK_MCSTFRAMESXMTDOK | IPG_SM_RXJUMBOFRAMES | - IPG_SM_BCSTOCTETRCVDOK_BCSTFRAMESRCVDOK | - IPG_SM_UDPCHECKSUMERRORS | IPG_SM_TCPCHECKSUMERRORS | - IPG_SM_IPCHECKSUMERRORS, STATISTICS_MASK); - - return 0; -} - -/* - * Create a receive buffer within system memory and update - * NIC private structure appropriately. - */ -static int ipg_get_rxbuff(struct net_device *dev, int entry) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct ipg_rx *rxfd = sp->rxd + entry; - struct sk_buff *skb; - u64 rxfragsize; - - IPG_DEBUG_MSG("_get_rxbuff\n"); - - skb = netdev_alloc_skb_ip_align(dev, sp->rxsupport_size); - if (!skb) { - sp->rx_buff[entry] = NULL; - return -ENOMEM; - } - - /* Save the address of the sk_buff structure. */ - sp->rx_buff[entry] = skb; - - rxfd->frag_info = cpu_to_le64(pci_map_single(sp->pdev, skb->data, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE)); - - /* Set the RFD fragment length. */ - rxfragsize = sp->rxfrag_size; - rxfd->frag_info |= cpu_to_le64((rxfragsize << 48) & IPG_RFI_FRAGLEN); - - return 0; -} - -static int init_rfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_init_rfdlist\n"); - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - struct ipg_rx *rxfd = sp->rxd + i; - - if (sp->rx_buff[i]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[i]); - sp->rx_buff[i] = NULL; - } - - /* Clear out the RFS field. */ - rxfd->rfs = 0x0000000000000000; - - if (ipg_get_rxbuff(dev, i) < 0) { - /* - * A receive buffer was not ready, break the - * RFD list here. - */ - IPG_DEBUG_MSG("Cannot allocate Rx buffer\n"); - - /* Just in case we cannot allocate a single RFD. - * Should not occur. - */ - if (i == 0) { - netdev_err(dev, "No memory available for RFD list\n"); - return -ENOMEM; - } - } - - rxfd->next_desc = cpu_to_le64(sp->rxd_map + - sizeof(struct ipg_rx)*(i + 1)); - } - sp->rxd[i - 1].next_desc = cpu_to_le64(sp->rxd_map); - - sp->rx_current = 0; - sp->rx_dirty = 0; - - /* Write the location of the RFDList to the IPG. */ - ipg_w32((u32) sp->rxd_map, RFD_LIST_PTR_0); - ipg_w32(0x00000000, RFD_LIST_PTR_1); - - return 0; -} - -static void init_tfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_init_tfdlist\n"); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - struct ipg_tx *txfd = sp->txd + i; - - txfd->tfc = cpu_to_le64(IPG_TFC_TFDDONE); - - if (sp->tx_buff[i]) { - dev_kfree_skb_irq(sp->tx_buff[i]); - sp->tx_buff[i] = NULL; - } - - txfd->next_desc = cpu_to_le64(sp->txd_map + - sizeof(struct ipg_tx)*(i + 1)); - } - sp->txd[i - 1].next_desc = cpu_to_le64(sp->txd_map); - - sp->tx_current = 0; - sp->tx_dirty = 0; - - /* Write the location of the TFDList to the IPG. */ - IPG_DDEBUG_MSG("Starting TFDListPtr = %08x\n", - (u32) sp->txd_map); - ipg_w32((u32) sp->txd_map, TFD_LIST_PTR_0); - ipg_w32(0x00000000, TFD_LIST_PTR_1); - - sp->reset_current_tfd = 1; -} - -/* - * Free all transmit buffers which have already been transferred - * via DMA to the IPG. - */ -static void ipg_nic_txfree(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int released, pending, dirty; - - IPG_DEBUG_MSG("_nic_txfree\n"); - - pending = sp->tx_current - sp->tx_dirty; - dirty = sp->tx_dirty % IPG_TFDLIST_LENGTH; - - for (released = 0; released < pending; released++) { - struct sk_buff *skb = sp->tx_buff[dirty]; - struct ipg_tx *txfd = sp->txd + dirty; - - IPG_DEBUG_MSG("TFC = %016lx\n", (unsigned long) txfd->tfc); - - /* Look at each TFD's TFC field beginning - * at the last freed TFD up to the current TFD. - * If the TFDDone bit is set, free the associated - * buffer. - */ - if (!(txfd->tfc & cpu_to_le64(IPG_TFC_TFDDONE))) - break; - - /* Free the transmit buffer. */ - if (skb) { - pci_unmap_single(sp->pdev, - le64_to_cpu(txfd->frag_info) & ~IPG_TFI_FRAGLEN, - skb->len, PCI_DMA_TODEVICE); - - dev_kfree_skb_irq(skb); - - sp->tx_buff[dirty] = NULL; - } - dirty = (dirty + 1) % IPG_TFDLIST_LENGTH; - } - - sp->tx_dirty += released; - - if (netif_queue_stopped(dev) && - (sp->tx_current != (sp->tx_dirty + IPG_TFDLIST_LENGTH))) { - netif_wake_queue(dev); - } -} - -static void ipg_tx_timeout(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - - ipg_reset(dev, IPG_AC_TX_RESET | IPG_AC_DMA | IPG_AC_NETWORK | - IPG_AC_FIFO); - - spin_lock_irq(&sp->lock); - - /* Re-configure after DMA reset. */ - if (ipg_io_config(dev) < 0) - netdev_info(dev, "Error during re-configuration\n"); - - init_tfdlist(dev); - - spin_unlock_irq(&sp->lock); - - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & IPG_MC_RSVD_MASK, - MAC_CTRL); -} - -/* - * For TxComplete interrupts, free all transmit - * buffers which have already been transferred via DMA - * to the IPG. - */ -static void ipg_nic_txcleanup(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_nic_txcleanup\n"); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - /* Reading the TXSTATUS register clears the - * TX_COMPLETE interrupt. - */ - u32 txstatusdword = ipg_r32(TX_STATUS); - - IPG_DEBUG_MSG("TxStatus = %08x\n", txstatusdword); - - /* Check for Transmit errors. Error bits only valid if - * TX_COMPLETE bit in the TXSTATUS register is a 1. - */ - if (!(txstatusdword & IPG_TS_TX_COMPLETE)) - break; - - /* If in 10Mbps mode, indicate transmit is ready. */ - if (sp->tenmbpsmode) { - netif_wake_queue(dev); - } - - /* Transmit error, increment stat counters. */ - if (txstatusdword & IPG_TS_TX_ERROR) { - IPG_DEBUG_MSG("Transmit error\n"); - sp->stats.tx_errors++; - } - - /* Late collision, re-enable transmitter. */ - if (txstatusdword & IPG_TS_LATE_COLLISION) { - IPG_DEBUG_MSG("Late collision on transmit\n"); - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - - /* Maximum collisions, re-enable transmitter. */ - if (txstatusdword & IPG_TS_TX_MAX_COLL) { - IPG_DEBUG_MSG("Maximum collisions on transmit\n"); - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - - /* Transmit underrun, reset and re-enable - * transmitter. - */ - if (txstatusdword & IPG_TS_TX_UNDERRUN) { - IPG_DEBUG_MSG("Transmitter underrun\n"); - sp->stats.tx_fifo_errors++; - ipg_reset(dev, IPG_AC_TX_RESET | IPG_AC_DMA | - IPG_AC_NETWORK | IPG_AC_FIFO); - - /* Re-configure after DMA reset. */ - if (ipg_io_config(dev) < 0) { - netdev_info(dev, "Error during re-configuration\n"); - } - init_tfdlist(dev); - - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - } - - ipg_nic_txfree(dev); -} - -/* Provides statistical information about the IPG NIC. */ -static struct net_device_stats *ipg_nic_get_stats(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - u16 temp1; - u16 temp2; - - IPG_DEBUG_MSG("_nic_get_stats\n"); - - /* Check to see if the NIC has been initialized via nic_open, - * before trying to read statistic registers. - */ - if (!netif_running(dev)) - return &sp->stats; - - sp->stats.rx_packets += ipg_r32(IPG_FRAMESRCVDOK); - sp->stats.tx_packets += ipg_r32(IPG_FRAMESXMTDOK); - sp->stats.rx_bytes += ipg_r32(IPG_OCTETRCVOK); - sp->stats.tx_bytes += ipg_r32(IPG_OCTETXMTOK); - temp1 = ipg_r16(IPG_FRAMESLOSTRXERRORS); - sp->stats.rx_errors += temp1; - sp->stats.rx_missed_errors += temp1; - temp1 = ipg_r32(IPG_SINGLECOLFRAMES) + ipg_r32(IPG_MULTICOLFRAMES) + - ipg_r32(IPG_LATECOLLISIONS); - temp2 = ipg_r16(IPG_CARRIERSENSEERRORS); - sp->stats.collisions += temp1; - sp->stats.tx_dropped += ipg_r16(IPG_FRAMESABORTXSCOLLS); - sp->stats.tx_errors += ipg_r16(IPG_FRAMESWEXDEFERRAL) + - ipg_r32(IPG_FRAMESWDEFERREDXMT) + temp1 + temp2; - sp->stats.multicast += ipg_r32(IPG_MCSTOCTETRCVDOK); - - /* detailed tx_errors */ - sp->stats.tx_carrier_errors += temp2; - - /* detailed rx_errors */ - sp->stats.rx_length_errors += ipg_r16(IPG_INRANGELENGTHERRORS) + - ipg_r16(IPG_FRAMETOOLONGERRORS); - sp->stats.rx_crc_errors += ipg_r16(IPG_FRAMECHECKSEQERRORS); - - /* Unutilized IPG statistic registers. */ - ipg_r32(IPG_MCSTFRAMESRCVDOK); - - return &sp->stats; -} - -/* Restore used receive buffers. */ -static int ipg_nic_rxrestore(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - const unsigned int curr = sp->rx_current; - unsigned int dirty = sp->rx_dirty; - - IPG_DEBUG_MSG("_nic_rxrestore\n"); - - for (dirty = sp->rx_dirty; curr - dirty > 0; dirty++) { - unsigned int entry = dirty % IPG_RFDLIST_LENGTH; - - /* rx_copybreak may poke hole here and there. */ - if (sp->rx_buff[entry]) - continue; - - /* Generate a new receive buffer to replace the - * current buffer (which will be released by the - * Linux system). - */ - if (ipg_get_rxbuff(dev, entry) < 0) { - IPG_DEBUG_MSG("Cannot allocate new Rx buffer\n"); - - break; - } - - /* Reset the RFS field. */ - sp->rxd[entry].rfs = 0x0000000000000000; - } - sp->rx_dirty = dirty; - - return 0; -} - -/* use jumboindex and jumbosize to control jumbo frame status - * initial status is jumboindex=-1 and jumbosize=0 - * 1. jumboindex = -1 and jumbosize=0 : previous jumbo frame has been done. - * 2. jumboindex != -1 and jumbosize != 0 : jumbo frame is not over size and receiving - * 3. jumboindex = -1 and jumbosize != 0 : jumbo frame is over size, already dump - * previous receiving and need to continue dumping the current one - */ -enum { - NORMAL_PACKET, - ERROR_PACKET -}; - -enum { - FRAME_NO_START_NO_END = 0, - FRAME_WITH_START = 1, - FRAME_WITH_END = 10, - FRAME_WITH_START_WITH_END = 11 -}; - -static void ipg_nic_rx_free_skb(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; - - if (sp->rx_buff[entry]) { - struct ipg_rx *rxfd = sp->rxd + entry; - - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[entry]); - sp->rx_buff[entry] = NULL; - } -} - -static int ipg_nic_rx_check_frame_type(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct ipg_rx *rxfd = sp->rxd + (sp->rx_current % IPG_RFDLIST_LENGTH); - int type = FRAME_NO_START_NO_END; - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMESTART) - type += FRAME_WITH_START; - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMEEND) - type += FRAME_WITH_END; - return type; -} - -static int ipg_nic_rx_check_error(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; - struct ipg_rx *rxfd = sp->rxd + entry; - - if (IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & - (IPG_RFS_RXFIFOOVERRUN | IPG_RFS_RXRUNTFRAME | - IPG_RFS_RXALIGNMENTERROR | IPG_RFS_RXFCSERROR | - IPG_RFS_RXOVERSIZEDFRAME | IPG_RFS_RXLENGTHERROR))) { - IPG_DEBUG_MSG("Rx error, RFS = %016lx\n", - (unsigned long) rxfd->rfs); - - /* Increment general receive error statistic. */ - sp->stats.rx_errors++; - - /* Increment detailed receive error statistics. */ - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFIFOOVERRUN) { - IPG_DEBUG_MSG("RX FIFO overrun occurred\n"); - - sp->stats.rx_fifo_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXRUNTFRAME) { - IPG_DEBUG_MSG("RX runt occurred\n"); - sp->stats.rx_length_errors++; - } - - /* Do nothing for IPG_RFS_RXOVERSIZEDFRAME, - * error count handled by a IPG statistic register. - */ - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXALIGNMENTERROR) { - IPG_DEBUG_MSG("RX alignment error occurred\n"); - sp->stats.rx_frame_errors++; - } - - /* Do nothing for IPG_RFS_RXFCSERROR, error count - * handled by a IPG statistic register. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (sp->rx_buff[entry]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - dev_kfree_skb_irq(sp->rx_buff[entry]); - sp->rx_buff[entry] = NULL; - } - return ERROR_PACKET; - } - return NORMAL_PACKET; -} - -static void ipg_nic_rx_with_start_and_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - struct sk_buff *skb; - int framelen; - - if (jumbo->found_start) { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) != NORMAL_PACKET) - return; - - skb = sp->rx_buff[entry]; - if (!skb) - return; - - /* accept this frame and send to upper layer */ - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - if (framelen > sp->rxfrag_size) - framelen = sp->rxfrag_size; - - skb_put(skb, framelen); - skb->protocol = eth_type_trans(skb, dev); - skb_checksum_none_assert(skb); - netif_rx(skb); - sp->rx_buff[entry] = NULL; -} - -static void ipg_nic_rx_with_start(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - struct pci_dev *pdev = sp->pdev; - struct sk_buff *skb; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) != NORMAL_PACKET) - return; - - /* accept this frame and send to upper layer */ - skb = sp->rx_buff[entry]; - if (!skb) - return; - - if (jumbo->found_start) - dev_kfree_skb_irq(jumbo->skb); - - pci_unmap_single(pdev, le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - skb_put(skb, sp->rxfrag_size); - - jumbo->found_start = 1; - jumbo->current_size = sp->rxfrag_size; - jumbo->skb = skb; - - sp->rx_buff[entry] = NULL; -} - -static void ipg_nic_rx_with_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) == NORMAL_PACKET) { - struct sk_buff *skb = sp->rx_buff[entry]; - - if (!skb) - return; - - if (jumbo->found_start) { - int framelen, endframelen; - - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - - endframelen = framelen - jumbo->current_size; - if (framelen > sp->rxsupport_size) - dev_kfree_skb_irq(jumbo->skb); - else { - memcpy(skb_put(jumbo->skb, endframelen), - skb->data, endframelen); - - jumbo->skb->protocol = - eth_type_trans(jumbo->skb, dev); - - skb_checksum_none_assert(jumbo->skb); - netif_rx(jumbo->skb); - } - } - - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - - ipg_nic_rx_free_skb(dev); - } else { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } -} - -static void ipg_nic_rx_no_start_no_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) == NORMAL_PACKET) { - struct sk_buff *skb = sp->rx_buff[entry]; - - if (skb) { - if (jumbo->found_start) { - jumbo->current_size += sp->rxfrag_size; - if (jumbo->current_size <= sp->rxsupport_size) { - memcpy(skb_put(jumbo->skb, - sp->rxfrag_size), - skb->data, sp->rxfrag_size); - } - } - ipg_nic_rx_free_skb(dev); - } - } else { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } -} - -static int ipg_nic_rx_jumbo(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int curr = sp->rx_current; - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_nic_rx\n"); - - for (i = 0; i < IPG_MAXRFDPROCESS_COUNT; i++, curr++) { - unsigned int entry = curr % IPG_RFDLIST_LENGTH; - struct ipg_rx *rxfd = sp->rxd + entry; - - if (!(rxfd->rfs & cpu_to_le64(IPG_RFS_RFDDONE))) - break; - - switch (ipg_nic_rx_check_frame_type(dev)) { - case FRAME_WITH_START_WITH_END: - ipg_nic_rx_with_start_and_end(dev, sp, rxfd, entry); - break; - case FRAME_WITH_START: - ipg_nic_rx_with_start(dev, sp, rxfd, entry); - break; - case FRAME_WITH_END: - ipg_nic_rx_with_end(dev, sp, rxfd, entry); - break; - case FRAME_NO_START_NO_END: - ipg_nic_rx_no_start_no_end(dev, sp, rxfd, entry); - break; - } - } - - sp->rx_current = curr; - - if (i == IPG_MAXRFDPROCESS_COUNT) { - /* There are more RFDs to process, however the - * allocated amount of RFD processing time has - * expired. Assert Interrupt Requested to make - * sure we come back to process the remaining RFDs. - */ - ipg_w32(ipg_r32(ASIC_CTRL) | IPG_AC_INT_REQUEST, ASIC_CTRL); - } - - ipg_nic_rxrestore(dev); - - return 0; -} - -static int ipg_nic_rx(struct net_device *dev) -{ - /* Transfer received Ethernet frames to higher network layers. */ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int curr = sp->rx_current; - void __iomem *ioaddr = sp->ioaddr; - struct ipg_rx *rxfd; - unsigned int i; - - IPG_DEBUG_MSG("_nic_rx\n"); - -#define __RFS_MASK \ - cpu_to_le64(IPG_RFS_RFDDONE | IPG_RFS_FRAMESTART | IPG_RFS_FRAMEEND) - - for (i = 0; i < IPG_MAXRFDPROCESS_COUNT; i++, curr++) { - unsigned int entry = curr % IPG_RFDLIST_LENGTH; - struct sk_buff *skb = sp->rx_buff[entry]; - unsigned int framelen; - - rxfd = sp->rxd + entry; - - if (((rxfd->rfs & __RFS_MASK) != __RFS_MASK) || !skb) - break; - - /* Get received frame length. */ - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - - /* Check for jumbo frame arrival with too small - * RXFRAG_SIZE. - */ - if (framelen > sp->rxfrag_size) { - IPG_DEBUG_MSG - ("RFS FrameLen > allocated fragment size\n"); - - framelen = sp->rxfrag_size; - } - - if ((IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & - (IPG_RFS_RXFIFOOVERRUN | IPG_RFS_RXRUNTFRAME | - IPG_RFS_RXALIGNMENTERROR | IPG_RFS_RXFCSERROR | - IPG_RFS_RXOVERSIZEDFRAME | IPG_RFS_RXLENGTHERROR)))) { - - IPG_DEBUG_MSG("Rx error, RFS = %016lx\n", - (unsigned long int) rxfd->rfs); - - /* Increment general receive error statistic. */ - sp->stats.rx_errors++; - - /* Increment detailed receive error statistics. */ - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFIFOOVERRUN) { - IPG_DEBUG_MSG("RX FIFO overrun occurred\n"); - sp->stats.rx_fifo_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXRUNTFRAME) { - IPG_DEBUG_MSG("RX runt occurred\n"); - sp->stats.rx_length_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXOVERSIZEDFRAME) ; - /* Do nothing, error count handled by a IPG - * statistic register. - */ - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXALIGNMENTERROR) { - IPG_DEBUG_MSG("RX alignment error occurred\n"); - sp->stats.rx_frame_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFCSERROR) ; - /* Do nothing, error count handled by a IPG - * statistic register. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (skb) { - __le64 info = rxfd->frag_info; - - pci_unmap_single(sp->pdev, - le64_to_cpu(info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - dev_kfree_skb_irq(skb); - } - } else { - - /* Adjust the new buffer length to accommodate the size - * of the received frame. - */ - skb_put(skb, framelen); - - /* Set the buffer's protocol field to Ethernet. */ - skb->protocol = eth_type_trans(skb, dev); - - /* The IPG encountered an error with (or - * there were no) IP/TCP/UDP checksums. - * This may or may not indicate an invalid - * IP/TCP/UDP frame was received. Let the - * upper layer decide. - */ - skb_checksum_none_assert(skb); - - /* Hand off frame for higher layer processing. - * The function netif_rx() releases the sk_buff - * when processing completes. - */ - netif_rx(skb); - } - - /* Assure RX buffer is not reused by IPG. */ - sp->rx_buff[entry] = NULL; - } - - /* - * If there are more RFDs to process and the allocated amount of RFD - * processing time has expired, assert Interrupt Requested to make - * sure we come back to process the remaining RFDs. - */ - if (i == IPG_MAXRFDPROCESS_COUNT) - ipg_w32(ipg_r32(ASIC_CTRL) | IPG_AC_INT_REQUEST, ASIC_CTRL); - -#ifdef IPG_DEBUG - /* Check if the RFD list contained no receive frame data. */ - if (!i) - sp->EmptyRFDListCount++; -#endif - while ((le64_to_cpu(rxfd->rfs) & IPG_RFS_RFDDONE) && - !((le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMESTART) && - (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMEEND))) { - unsigned int entry = curr++ % IPG_RFDLIST_LENGTH; - - rxfd = sp->rxd + entry; - - IPG_DEBUG_MSG("Frame requires multiple RFDs\n"); - - /* An unexpected event, additional code needed to handle - * properly. So for the time being, just disregard the - * frame. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (sp->rx_buff[entry]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[entry]); - } - - /* Assure RX buffer is not reused by IPG. */ - sp->rx_buff[entry] = NULL; - } - - sp->rx_current = curr; - - /* Check to see if there are a minimum number of used - * RFDs before restoring any (should improve performance.) - */ - if ((curr - sp->rx_dirty) >= IPG_MINUSEDRFDSTOFREE) - ipg_nic_rxrestore(dev); - - return 0; -} - -static void ipg_reset_after_host_error(struct work_struct *work) -{ - struct ipg_nic_private *sp = - container_of(work, struct ipg_nic_private, task.work); - struct net_device *dev = sp->dev; - - /* - * Acknowledge HostError interrupt by resetting - * IPG DMA and HOST. - */ - ipg_reset(dev, IPG_AC_GLOBAL_RESET | IPG_AC_HOST | IPG_AC_DMA); - - init_rfdlist(dev); - init_tfdlist(dev); - - if (ipg_io_config(dev) < 0) { - netdev_info(dev, "Cannot recover from PCI error\n"); - schedule_delayed_work(&sp->task, HZ); - } -} - -static irqreturn_t ipg_interrupt_handler(int irq, void *dev_inst) -{ - struct net_device *dev = dev_inst; - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int handled = 0; - u16 status; - - IPG_DEBUG_MSG("_interrupt_handler\n"); - - if (sp->is_jumbo) - ipg_nic_rxrestore(dev); - - spin_lock(&sp->lock); - - /* Get interrupt source information, and acknowledge - * some (i.e. TxDMAComplete, RxDMAComplete, RxEarly, - * IntRequested, MacControlFrame, LinkEvent) interrupts - * if issued. Also, all IPG interrupts are disabled by - * reading IntStatusAck. - */ - status = ipg_r16(INT_STATUS_ACK); - - IPG_DEBUG_MSG("IntStatusAck = %04x\n", status); - - /* Shared IRQ of remove event. */ - if (!(status & IPG_IS_RSVD_MASK)) - goto out_enable; - - handled = 1; - - if (unlikely(!netif_running(dev))) - goto out_unlock; - - /* If RFDListEnd interrupt, restore all used RFDs. */ - if (status & IPG_IS_RFD_LIST_END) { - IPG_DEBUG_MSG("RFDListEnd Interrupt\n"); - - /* The RFD list end indicates an RFD was encountered - * with a 0 NextPtr, or with an RFDDone bit set to 1 - * (indicating the RFD is not read for use by the - * IPG.) Try to restore all RFDs. - */ - ipg_nic_rxrestore(dev); - -#ifdef IPG_DEBUG - /* Increment the RFDlistendCount counter. */ - sp->RFDlistendCount++; -#endif - } - - /* If RFDListEnd, RxDMAPriority, RxDMAComplete, or - * IntRequested interrupt, process received frames. */ - if ((status & IPG_IS_RX_DMA_PRIORITY) || - (status & IPG_IS_RFD_LIST_END) || - (status & IPG_IS_RX_DMA_COMPLETE) || - (status & IPG_IS_INT_REQUESTED)) { -#ifdef IPG_DEBUG - /* Increment the RFD list checked counter if interrupted - * only to check the RFD list. */ - if (status & (~(IPG_IS_RX_DMA_PRIORITY | IPG_IS_RFD_LIST_END | - IPG_IS_RX_DMA_COMPLETE | IPG_IS_INT_REQUESTED) & - (IPG_IS_HOST_ERROR | IPG_IS_TX_DMA_COMPLETE | - IPG_IS_LINK_EVENT | IPG_IS_TX_COMPLETE | - IPG_IS_UPDATE_STATS))) - sp->RFDListCheckedCount++; -#endif - - if (sp->is_jumbo) - ipg_nic_rx_jumbo(dev); - else - ipg_nic_rx(dev); - } - - /* If TxDMAComplete interrupt, free used TFDs. */ - if (status & IPG_IS_TX_DMA_COMPLETE) - ipg_nic_txfree(dev); - - /* TxComplete interrupts indicate one of numerous actions. - * Determine what action to take based on TXSTATUS register. - */ - if (status & IPG_IS_TX_COMPLETE) - ipg_nic_txcleanup(dev); - - /* If UpdateStats interrupt, update Linux Ethernet statistics */ - if (status & IPG_IS_UPDATE_STATS) - ipg_nic_get_stats(dev); - - /* If HostError interrupt, reset IPG. */ - if (status & IPG_IS_HOST_ERROR) { - IPG_DDEBUG_MSG("HostError Interrupt\n"); - - schedule_delayed_work(&sp->task, 0); - } - - /* If LinkEvent interrupt, resolve autonegotiation. */ - if (status & IPG_IS_LINK_EVENT) { - if (ipg_config_autoneg(dev) < 0) - netdev_info(dev, "Auto-negotiation error\n"); - } - - /* If MACCtrlFrame interrupt, do nothing. */ - if (status & IPG_IS_MAC_CTRL_FRAME) - IPG_DEBUG_MSG("MACCtrlFrame interrupt\n"); - - /* If RxComplete interrupt, do nothing. */ - if (status & IPG_IS_RX_COMPLETE) - IPG_DEBUG_MSG("RxComplete interrupt\n"); - - /* If RxEarly interrupt, do nothing. */ - if (status & IPG_IS_RX_EARLY) - IPG_DEBUG_MSG("RxEarly interrupt\n"); - -out_enable: - /* Re-enable IPG interrupts. */ - ipg_w16(IPG_IE_TX_DMA_COMPLETE | IPG_IE_RX_DMA_COMPLETE | - IPG_IE_HOST_ERROR | IPG_IE_INT_REQUESTED | IPG_IE_TX_COMPLETE | - IPG_IE_LINK_EVENT | IPG_IE_UPDATE_STATS, INT_ENABLE); -out_unlock: - spin_unlock(&sp->lock); - - return IRQ_RETVAL(handled); -} - -static void ipg_rx_clear(struct ipg_nic_private *sp) -{ - unsigned int i; - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - if (sp->rx_buff[i]) { - struct ipg_rx *rxfd = sp->rxd + i; - - dev_kfree_skb_irq(sp->rx_buff[i]); - sp->rx_buff[i] = NULL; - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - } - } -} - -static void ipg_tx_clear(struct ipg_nic_private *sp) -{ - unsigned int i; - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - if (sp->tx_buff[i]) { - struct ipg_tx *txfd = sp->txd + i; - - pci_unmap_single(sp->pdev, - le64_to_cpu(txfd->frag_info) & ~IPG_TFI_FRAGLEN, - sp->tx_buff[i]->len, PCI_DMA_TODEVICE); - - dev_kfree_skb_irq(sp->tx_buff[i]); - - sp->tx_buff[i] = NULL; - } - } -} - -static int ipg_nic_open(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - struct pci_dev *pdev = sp->pdev; - int rc; - - IPG_DEBUG_MSG("_nic_open\n"); - - sp->rx_buf_sz = sp->rxsupport_size; - - /* Check for interrupt line conflicts, and request interrupt - * line for IPG. - * - * IMPORTANT: Disable IPG interrupts prior to registering - * IRQ. - */ - ipg_w16(0x0000, INT_ENABLE); - - /* Register the interrupt line to be used by the IPG within - * the Linux system. - */ - rc = request_irq(pdev->irq, ipg_interrupt_handler, IRQF_SHARED, - dev->name, dev); - if (rc < 0) { - netdev_info(dev, "Error when requesting interrupt\n"); - goto out; - } - - dev->irq = pdev->irq; - - rc = -ENOMEM; - - sp->rxd = dma_alloc_coherent(&pdev->dev, IPG_RX_RING_BYTES, - &sp->rxd_map, GFP_KERNEL); - if (!sp->rxd) - goto err_free_irq_0; - - sp->txd = dma_alloc_coherent(&pdev->dev, IPG_TX_RING_BYTES, - &sp->txd_map, GFP_KERNEL); - if (!sp->txd) - goto err_free_rx_1; - - rc = init_rfdlist(dev); - if (rc < 0) { - netdev_info(dev, "Error during configuration\n"); - goto err_free_tx_2; - } - - init_tfdlist(dev); - - rc = ipg_io_config(dev); - if (rc < 0) { - netdev_info(dev, "Error during configuration\n"); - goto err_release_tfdlist_3; - } - - /* Resolve autonegotiation. */ - if (ipg_config_autoneg(dev) < 0) - netdev_info(dev, "Auto-negotiation error\n"); - - /* initialize JUMBO Frame control variable */ - sp->jumbo.found_start = 0; - sp->jumbo.current_size = 0; - sp->jumbo.skb = NULL; - - /* Enable transmit and receive operation of the IPG. */ - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_RX_ENABLE | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - - netif_start_queue(dev); -out: - return rc; - -err_release_tfdlist_3: - ipg_tx_clear(sp); - ipg_rx_clear(sp); -err_free_tx_2: - dma_free_coherent(&pdev->dev, IPG_TX_RING_BYTES, sp->txd, sp->txd_map); -err_free_rx_1: - dma_free_coherent(&pdev->dev, IPG_RX_RING_BYTES, sp->rxd, sp->rxd_map); -err_free_irq_0: - free_irq(pdev->irq, dev); - goto out; -} - -static int ipg_nic_stop(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - struct pci_dev *pdev = sp->pdev; - - IPG_DEBUG_MSG("_nic_stop\n"); - - netif_stop_queue(dev); - - IPG_DUMPTFDLIST(dev); - - do { - (void) ipg_r16(INT_STATUS_ACK); - - ipg_reset(dev, IPG_AC_GLOBAL_RESET | IPG_AC_HOST | IPG_AC_DMA); - - synchronize_irq(pdev->irq); - } while (ipg_r16(INT_ENABLE) & IPG_IE_RSVD_MASK); - - ipg_rx_clear(sp); - - ipg_tx_clear(sp); - - pci_free_consistent(pdev, IPG_RX_RING_BYTES, sp->rxd, sp->rxd_map); - pci_free_consistent(pdev, IPG_TX_RING_BYTES, sp->txd, sp->txd_map); - - free_irq(pdev->irq, dev); - - return 0; -} - -static netdev_tx_t ipg_nic_hard_start_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int entry = sp->tx_current % IPG_TFDLIST_LENGTH; - unsigned long flags; - struct ipg_tx *txfd; - - IPG_DDEBUG_MSG("_nic_hard_start_xmit\n"); - - /* If in 10Mbps mode, stop the transmit queue so - * no more transmit frames are accepted. - */ - if (sp->tenmbpsmode) - netif_stop_queue(dev); - - if (sp->reset_current_tfd) { - sp->reset_current_tfd = 0; - entry = 0; - } - - txfd = sp->txd + entry; - - sp->tx_buff[entry] = skb; - - /* Clear all TFC fields, except TFDDONE. */ - txfd->tfc = cpu_to_le64(IPG_TFC_TFDDONE); - - /* Specify the TFC field within the TFD. */ - txfd->tfc |= cpu_to_le64(IPG_TFC_WORDALIGNDISABLED | - (IPG_TFC_FRAMEID & sp->tx_current) | - (IPG_TFC_FRAGCOUNT & (1 << 24))); - /* - * 16--17 (WordAlign) <- 3 (disable), - * 0--15 (FrameId) <- sp->tx_current, - * 24--27 (FragCount) <- 1 - */ - - /* Request TxComplete interrupts at an interval defined - * by the constant IPG_FRAMESBETWEENTXCOMPLETES. - * Request TxComplete interrupt for every frame - * if in 10Mbps mode to accommodate problem with 10Mbps - * processing. - */ - if (sp->tenmbpsmode) - txfd->tfc |= cpu_to_le64(IPG_TFC_TXINDICATE); - txfd->tfc |= cpu_to_le64(IPG_TFC_TXDMAINDICATE); - /* Based on compilation option, determine if FCS is to be - * appended to transmit frame by IPG. - */ - if (!(IPG_APPEND_FCS_ON_TX)) - txfd->tfc |= cpu_to_le64(IPG_TFC_FCSAPPENDDISABLE); - - /* Based on compilation option, determine if IP, TCP and/or - * UDP checksums are to be added to transmit frame by IPG. - */ - if (IPG_ADD_IPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_IPCHECKSUMENABLE); - - if (IPG_ADD_TCPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_TCPCHECKSUMENABLE); - - if (IPG_ADD_UDPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_UDPCHECKSUMENABLE); - - /* Based on compilation option, determine if VLAN tag info is to be - * inserted into transmit frame by IPG. - */ - if (IPG_INSERT_MANUAL_VLAN_TAG) { - txfd->tfc |= cpu_to_le64(IPG_TFC_VLANTAGINSERT | - ((u64) IPG_MANUAL_VLAN_VID << 32) | - ((u64) IPG_MANUAL_VLAN_CFI << 44) | - ((u64) IPG_MANUAL_VLAN_USERPRIORITY << 45)); - } - - /* The fragment start location within system memory is defined - * by the sk_buff structure's data field. The physical address - * of this location within the system's virtual memory space - * is determined using the IPG_HOST2BUS_MAP function. - */ - txfd->frag_info = cpu_to_le64(pci_map_single(sp->pdev, skb->data, - skb->len, PCI_DMA_TODEVICE)); - - /* The length of the fragment within system memory is defined by - * the sk_buff structure's len field. - */ - txfd->frag_info |= cpu_to_le64(IPG_TFI_FRAGLEN & - ((u64) (skb->len & 0xffff) << 48)); - - /* Clear the TFDDone bit last to indicate the TFD is ready - * for transfer to the IPG. - */ - txfd->tfc &= cpu_to_le64(~IPG_TFC_TFDDONE); - - spin_lock_irqsave(&sp->lock, flags); - - sp->tx_current++; - - mmiowb(); - - ipg_w32(IPG_DC_TX_DMA_POLL_NOW, DMA_CTRL); - - if (sp->tx_current == (sp->tx_dirty + IPG_TFDLIST_LENGTH)) - netif_stop_queue(dev); - - spin_unlock_irqrestore(&sp->lock, flags); - - return NETDEV_TX_OK; -} - -static void ipg_set_phy_default_param(unsigned char rev, - struct net_device *dev, int phy_address) -{ - unsigned short length; - unsigned char revision; - const unsigned short *phy_param; - unsigned short address, value; - - phy_param = &DefaultPhyParam[0]; - length = *phy_param & 0x00FF; - revision = (unsigned char)((*phy_param) >> 8); - phy_param++; - while (length != 0) { - if (rev == revision) { - while (length > 1) { - address = *phy_param; - value = *(phy_param + 1); - phy_param += 2; - mdio_write(dev, phy_address, address, value); - length -= 4; - } - break; - } else { - phy_param += length / 2; - length = *phy_param & 0x00FF; - revision = (unsigned char)((*phy_param) >> 8); - phy_param++; - } - } -} - -static int read_eeprom(struct net_device *dev, int eep_addr) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - unsigned int i; - int ret = 0; - u16 value; - - value = IPG_EC_EEPROM_READOPCODE | (eep_addr & 0xff); - ipg_w16(value, EEPROM_CTRL); - - for (i = 0; i < 1000; i++) { - u16 data; - - mdelay(10); - data = ipg_r16(EEPROM_CTRL); - if (!(data & IPG_EC_EEPROM_BUSY)) { - ret = ipg_r16(EEPROM_DATA); - break; - } - } - return ret; -} - -static void ipg_init_mii(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct mii_if_info *mii_if = &sp->mii_if; - int phyaddr; - - mii_if->dev = dev; - mii_if->mdio_read = mdio_read; - mii_if->mdio_write = mdio_write; - mii_if->phy_id_mask = 0x1f; - mii_if->reg_num_mask = 0x1f; - - mii_if->phy_id = phyaddr = ipg_find_phyaddr(dev); - - if (phyaddr != 0x1f) { - u16 mii_phyctrl, mii_1000cr; - - mii_1000cr = mdio_read(dev, phyaddr, MII_CTRL1000); - mii_1000cr |= ADVERTISE_1000FULL | ADVERTISE_1000HALF | - GMII_PHY_1000BASETCONTROL_PreferMaster; - mdio_write(dev, phyaddr, MII_CTRL1000, mii_1000cr); - - mii_phyctrl = mdio_read(dev, phyaddr, MII_BMCR); - - /* Set default phyparam */ - ipg_set_phy_default_param(sp->pdev->revision, dev, phyaddr); - - /* Reset PHY */ - mii_phyctrl |= BMCR_RESET | BMCR_ANRESTART; - mdio_write(dev, phyaddr, MII_BMCR, mii_phyctrl); - - } -} - -static int ipg_hw_init(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - int rc; - - /* Read/Write and Reset EEPROM Value */ - /* Read LED Mode Configuration from EEPROM */ - sp->led_mode = read_eeprom(dev, 6); - - /* Reset all functions within the IPG. Do not assert - * RST_OUT as not compatible with some PHYs. - */ - rc = ipg_reset(dev, IPG_RESET_MASK); - if (rc < 0) - goto out; - - ipg_init_mii(dev); - - /* Read MAC Address from EEPROM */ - for (i = 0; i < 3; i++) - sp->station_addr[i] = read_eeprom(dev, 16 + i); - - for (i = 0; i < 3; i++) - ipg_w16(sp->station_addr[i], STATION_ADDRESS_0 + 2*i); - - /* Set station address in ethernet_device structure. */ - dev->dev_addr[0] = ipg_r16(STATION_ADDRESS_0) & 0x00ff; - dev->dev_addr[1] = (ipg_r16(STATION_ADDRESS_0) & 0xff00) >> 8; - dev->dev_addr[2] = ipg_r16(STATION_ADDRESS_1) & 0x00ff; - dev->dev_addr[3] = (ipg_r16(STATION_ADDRESS_1) & 0xff00) >> 8; - dev->dev_addr[4] = ipg_r16(STATION_ADDRESS_2) & 0x00ff; - dev->dev_addr[5] = (ipg_r16(STATION_ADDRESS_2) & 0xff00) >> 8; -out: - return rc; -} - -static int ipg_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = generic_mii_ioctl(&sp->mii_if, if_mii(ifr), cmd, NULL); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_nic_change_mtu(struct net_device *dev, int new_mtu) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int err; - - /* Function to accommodate changes to Maximum Transfer Unit - * (or MTU) of IPG NIC. Cannot use default function since - * the default will not allow for MTU > 1500 bytes. - */ - - IPG_DEBUG_MSG("_nic_change_mtu\n"); - - /* - * Check that the new MTU value is between 68 (14 byte header, 46 byte - * payload, 4 byte FCS) and 10 KB, which is the largest supported MTU. - */ - if (new_mtu < 68 || new_mtu > 10240) - return -EINVAL; - - err = ipg_nic_stop(dev); - if (err) - return err; - - dev->mtu = new_mtu; - - sp->max_rxframe_size = new_mtu; - - sp->rxfrag_size = new_mtu; - if (sp->rxfrag_size > 4088) - sp->rxfrag_size = 4088; - - sp->rxsupport_size = sp->max_rxframe_size; - - if (new_mtu > 0x0600) - sp->is_jumbo = true; - else - sp->is_jumbo = false; - - return ipg_nic_open(dev); -} - -static int ipg_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_ethtool_gset(&sp->mii_if, cmd); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_ethtool_sset(&sp->mii_if, cmd); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_nway_reset(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_nway_restart(&sp->mii_if); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static const struct ethtool_ops ipg_ethtool_ops = { - .get_settings = ipg_get_settings, - .set_settings = ipg_set_settings, - .nway_reset = ipg_nway_reset, -}; - -static void ipg_remove(struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata(pdev); - struct ipg_nic_private *sp = netdev_priv(dev); - - IPG_DEBUG_MSG("_remove\n"); - - /* Un-register Ethernet device. */ - unregister_netdev(dev); - - pci_iounmap(pdev, sp->ioaddr); - - pci_release_regions(pdev); - - free_netdev(dev); - pci_disable_device(pdev); -} - -static const struct net_device_ops ipg_netdev_ops = { - .ndo_open = ipg_nic_open, - .ndo_stop = ipg_nic_stop, - .ndo_start_xmit = ipg_nic_hard_start_xmit, - .ndo_get_stats = ipg_nic_get_stats, - .ndo_set_rx_mode = ipg_nic_set_multicast_list, - .ndo_do_ioctl = ipg_ioctl, - .ndo_tx_timeout = ipg_tx_timeout, - .ndo_change_mtu = ipg_nic_change_mtu, - .ndo_set_mac_address = eth_mac_addr, - .ndo_validate_addr = eth_validate_addr, -}; - -static int ipg_probe(struct pci_dev *pdev, const struct pci_device_id *id) -{ - unsigned int i = id->driver_data; - struct ipg_nic_private *sp; - struct net_device *dev; - void __iomem *ioaddr; - int rc; - - rc = pci_enable_device(pdev); - if (rc < 0) - goto out; - - pr_info("%s: %s\n", pci_name(pdev), ipg_brand_name[i]); - - pci_set_master(pdev); - - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(40)); - if (rc < 0) { - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc < 0) { - pr_err("%s: DMA config failed\n", pci_name(pdev)); - goto err_disable_0; - } - } - - /* - * Initialize net device. - */ - dev = alloc_etherdev(sizeof(struct ipg_nic_private)); - if (!dev) { - rc = -ENOMEM; - goto err_disable_0; - } - - sp = netdev_priv(dev); - spin_lock_init(&sp->lock); - mutex_init(&sp->mii_mutex); - - sp->is_jumbo = IPG_IS_JUMBO; - sp->rxfrag_size = IPG_RXFRAG_SIZE; - sp->rxsupport_size = IPG_RXSUPPORT_SIZE; - sp->max_rxframe_size = IPG_MAX_RXFRAME_SIZE; - - /* Declare IPG NIC functions for Ethernet device methods. - */ - dev->netdev_ops = &ipg_netdev_ops; - SET_NETDEV_DEV(dev, &pdev->dev); - dev->ethtool_ops = &ipg_ethtool_ops; - - rc = pci_request_regions(pdev, DRV_NAME); - if (rc) - goto err_free_dev_1; - - ioaddr = pci_iomap(pdev, 1, pci_resource_len(pdev, 1)); - if (!ioaddr) { - pr_err("%s: cannot map MMIO\n", pci_name(pdev)); - rc = -EIO; - goto err_release_regions_2; - } - - /* Save the pointer to the PCI device information. */ - sp->ioaddr = ioaddr; - sp->pdev = pdev; - sp->dev = dev; - - INIT_DELAYED_WORK(&sp->task, ipg_reset_after_host_error); - - pci_set_drvdata(pdev, dev); - - rc = ipg_hw_init(dev); - if (rc < 0) - goto err_unmap_3; - - rc = register_netdev(dev); - if (rc < 0) - goto err_unmap_3; - - netdev_info(dev, "Ethernet device registered\n"); -out: - return rc; - -err_unmap_3: - pci_iounmap(pdev, ioaddr); -err_release_regions_2: - pci_release_regions(pdev); -err_free_dev_1: - free_netdev(dev); -err_disable_0: - pci_disable_device(pdev); - goto out; -} - -static struct pci_driver ipg_pci_driver = { - .name = IPG_DRIVER_NAME, - .id_table = ipg_pci_tbl, - .probe = ipg_probe, - .remove = ipg_remove, -}; - -module_pci_driver(ipg_pci_driver); diff --git a/drivers/net/ethernet/icplus/ipg.h b/drivers/net/ethernet/icplus/ipg.h deleted file mode 100644 index de60628..0000000 --- a/drivers/net/ethernet/icplus/ipg.h +++ /dev/null @@ -1,748 +0,0 @@ -/* - * Include file for Gigabit Ethernet device driver for Network - * Interface Cards (NICs) utilizing the Tamarack Microelectronics - * Inc. IPG Gigabit or Triple Speed Ethernet Media Access - * Controller. - */ -#ifndef __LINUX_IPG_H -#define __LINUX_IPG_H - -#include <linux/module.h> - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/ioport.h> -#include <linux/errno.h> -#include <asm/io.h> -#include <linux/delay.h> -#include <linux/types.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <asm/bitops.h> - -/* - * Constants - */ - -/* GMII based PHY IDs */ -#define NS 0x2000 -#define MARVELL 0x0141 -#define ICPLUS_PHY 0x243 - -/* NIC Physical Layer Device MII register fields. */ -#define MII_PHY_SELECTOR_IEEE8023 0x0001 -#define MII_PHY_TECHABILITYFIELD 0x1FE0 - -/* GMII_PHY_1000 need to set to prefer master */ -#define GMII_PHY_1000BASETCONTROL_PreferMaster 0x0400 - -/* NIC Physical Layer Device GMII constants. */ -#define GMII_PREAMBLE 0xFFFFFFFF -#define GMII_ST 0x1 -#define GMII_READ 0x2 -#define GMII_WRITE 0x1 -#define GMII_TA_READ_MASK 0x1 -#define GMII_TA_WRITE 0x2 - -/* I/O register offsets. */ -enum ipg_regs { - DMA_CTRL = 0x00, - RX_DMA_STATUS = 0x08, /* Unused + reserved */ - TFD_LIST_PTR_0 = 0x10, - TFD_LIST_PTR_1 = 0x14, - TX_DMA_BURST_THRESH = 0x18, - TX_DMA_URGENT_THRESH = 0x19, - TX_DMA_POLL_PERIOD = 0x1a, - RFD_LIST_PTR_0 = 0x1c, - RFD_LIST_PTR_1 = 0x20, - RX_DMA_BURST_THRESH = 0x24, - RX_DMA_URGENT_THRESH = 0x25, - RX_DMA_POLL_PERIOD = 0x26, - DEBUG_CTRL = 0x2c, - ASIC_CTRL = 0x30, - FIFO_CTRL = 0x38, /* Unused */ - FLOW_OFF_THRESH = 0x3c, - FLOW_ON_THRESH = 0x3e, - EEPROM_DATA = 0x48, - EEPROM_CTRL = 0x4a, - EXPROM_ADDR = 0x4c, /* Unused */ - EXPROM_DATA = 0x50, /* Unused */ - WAKE_EVENT = 0x51, /* Unused */ - COUNTDOWN = 0x54, /* Unused */ - INT_STATUS_ACK = 0x5a, - INT_ENABLE = 0x5c, - INT_STATUS = 0x5e, /* Unused */ - TX_STATUS = 0x60, - MAC_CTRL = 0x6c, - VLAN_TAG = 0x70, /* Unused */ - PHY_SET = 0x75, - PHY_CTRL = 0x76, - STATION_ADDRESS_0 = 0x78, - STATION_ADDRESS_1 = 0x7a, - STATION_ADDRESS_2 = 0x7c, - MAX_FRAME_SIZE = 0x86, - RECEIVE_MODE = 0x88, - HASHTABLE_0 = 0x8c, - HASHTABLE_1 = 0x90, - RMON_STATISTICS_MASK = 0x98, - STATISTICS_MASK = 0x9c, - RX_JUMBO_FRAMES = 0xbc, /* Unused */ - TCP_CHECKSUM_ERRORS = 0xc0, /* Unused */ - IP_CHECKSUM_ERRORS = 0xc2, /* Unused */ - UDP_CHECKSUM_ERRORS = 0xc4, /* Unused */ - TX_JUMBO_FRAMES = 0xf4 /* Unused */ -}; - -/* Ethernet MIB statistic register offsets. */ -#define IPG_OCTETRCVOK 0xA8 -#define IPG_MCSTOCTETRCVDOK 0xAC -#define IPG_BCSTOCTETRCVOK 0xB0 -#define IPG_FRAMESRCVDOK 0xB4 -#define IPG_MCSTFRAMESRCVDOK 0xB8 -#define IPG_BCSTFRAMESRCVDOK 0xBE -#define IPG_MACCONTROLFRAMESRCVD 0xC6 -#define IPG_FRAMETOOLONGERRORS 0xC8 -#define IPG_INRANGELENGTHERRORS 0xCA -#define IPG_FRAMECHECKSEQERRORS 0xCC -#define IPG_FRAMESLOSTRXERRORS 0xCE -#define IPG_OCTETXMTOK 0xD0 -#define IPG_MCSTOCTETXMTOK 0xD4 -#define IPG_BCSTOCTETXMTOK 0xD8 -#define IPG_FRAMESXMTDOK 0xDC -#define IPG_MCSTFRAMESXMTDOK 0xE0 -#define IPG_FRAMESWDEFERREDXMT 0xE4 -#define IPG_LATECOLLISIONS 0xE8 -#define IPG_MULTICOLFRAMES 0xEC -#define IPG_SINGLECOLFRAMES 0xF0 -#define IPG_BCSTFRAMESXMTDOK 0xF6 -#define IPG_CARRIERSENSEERRORS 0xF8 -#define IPG_MACCONTROLFRAMESXMTDOK 0xFA -#define IPG_FRAMESABORTXSCOLLS 0xFC -#define IPG_FRAMESWEXDEFERRAL 0xFE - -/* RMON statistic register offsets. */ -#define IPG_ETHERSTATSCOLLISIONS 0x100 -#define IPG_ETHERSTATSOCTETSTRANSMIT 0x104 -#define IPG_ETHERSTATSPKTSTRANSMIT 0x108 -#define IPG_ETHERSTATSPKTS64OCTESTSTRANSMIT 0x10C -#define IPG_ETHERSTATSPKTS65TO127OCTESTSTRANSMIT 0x110 -#define IPG_ETHERSTATSPKTS128TO255OCTESTSTRANSMIT 0x114 -#define IPG_ETHERSTATSPKTS256TO511OCTESTSTRANSMIT 0x118 -#define IPG_ETHERSTATSPKTS512TO1023OCTESTSTRANSMIT 0x11C -#define IPG_ETHERSTATSPKTS1024TO1518OCTESTSTRANSMIT 0x120 -#define IPG_ETHERSTATSCRCALIGNERRORS 0x124 -#define IPG_ETHERSTATSUNDERSIZEPKTS 0x128 -#define IPG_ETHERSTATSFRAGMENTS 0x12C -#define IPG_ETHERSTATSJABBERS 0x130 -#define IPG_ETHERSTATSOCTETS 0x134 -#define IPG_ETHERSTATSPKTS 0x138 -#define IPG_ETHERSTATSPKTS64OCTESTS 0x13C -#define IPG_ETHERSTATSPKTS65TO127OCTESTS 0x140 -#define IPG_ETHERSTATSPKTS128TO255OCTESTS 0x144 -#define IPG_ETHERSTATSPKTS256TO511OCTESTS 0x148 -#define IPG_ETHERSTATSPKTS512TO1023OCTESTS 0x14C -#define IPG_ETHERSTATSPKTS1024TO1518OCTESTS 0x150 - -/* RMON statistic register equivalents. */ -#define IPG_ETHERSTATSMULTICASTPKTSTRANSMIT 0xE0 -#define IPG_ETHERSTATSBROADCASTPKTSTRANSMIT 0xF6 -#define IPG_ETHERSTATSMULTICASTPKTS 0xB8 -#define IPG_ETHERSTATSBROADCASTPKTS 0xBE -#define IPG_ETHERSTATSOVERSIZEPKTS 0xC8 -#define IPG_ETHERSTATSDROPEVENTS 0xCE - -/* Serial EEPROM offsets */ -#define IPG_EEPROM_CONFIGPARAM 0x00 -#define IPG_EEPROM_ASICCTRL 0x01 -#define IPG_EEPROM_SUBSYSTEMVENDORID 0x02 -#define IPG_EEPROM_SUBSYSTEMID 0x03 -#define IPG_EEPROM_STATIONADDRESS0 0x10 -#define IPG_EEPROM_STATIONADDRESS1 0x11 -#define IPG_EEPROM_STATIONADDRESS2 0x12 - -/* Register & data structure bit masks */ - -/* PCI register masks. */ - -/* IOBaseAddress */ -#define IPG_PIB_RSVD_MASK 0xFFFFFE01 -#define IPG_PIB_IOBASEADDRESS 0xFFFFFF00 -#define IPG_PIB_IOBASEADDRIND 0x00000001 - -/* MemBaseAddress */ -#define IPG_PMB_RSVD_MASK 0xFFFFFE07 -#define IPG_PMB_MEMBASEADDRIND 0x00000001 -#define IPG_PMB_MEMMAPTYPE 0x00000006 -#define IPG_PMB_MEMMAPTYPE0 0x00000002 -#define IPG_PMB_MEMMAPTYPE1 0x00000004 -#define IPG_PMB_MEMBASEADDRESS 0xFFFFFE00 - -/* ConfigStatus */ -#define IPG_CS_RSVD_MASK 0xFFB0 -#define IPG_CS_CAPABILITIES 0x0010 -#define IPG_CS_66MHZCAPABLE 0x0020 -#define IPG_CS_FASTBACK2BACK 0x0080 -#define IPG_CS_DATAPARITYREPORTED 0x0100 -#define IPG_CS_DEVSELTIMING 0x0600 -#define IPG_CS_SIGNALEDTARGETABORT 0x0800 -#define IPG_CS_RECEIVEDTARGETABORT 0x1000 -#define IPG_CS_RECEIVEDMASTERABORT 0x2000 -#define IPG_CS_SIGNALEDSYSTEMERROR 0x4000 -#define IPG_CS_DETECTEDPARITYERROR 0x8000 - -/* TFD data structure masks. */ - -/* TFDList, TFC */ -#define IPG_TFC_RSVD_MASK 0x0000FFFF9FFFFFFFULL -#define IPG_TFC_FRAMEID 0x000000000000FFFFULL -#define IPG_TFC_WORDALIGN 0x0000000000030000ULL -#define IPG_TFC_WORDALIGNTODWORD 0x0000000000000000ULL -#define IPG_TFC_WORDALIGNTOWORD 0x0000000000020000ULL -#define IPG_TFC_WORDALIGNDISABLED 0x0000000000030000ULL -#define IPG_TFC_TCPCHECKSUMENABLE 0x0000000000040000ULL -#define IPG_TFC_UDPCHECKSUMENABLE 0x0000000000080000ULL -#define IPG_TFC_IPCHECKSUMENABLE 0x0000000000100000ULL -#define IPG_TFC_FCSAPPENDDISABLE 0x0000000000200000ULL -#define IPG_TFC_TXINDICATE 0x0000000000400000ULL -#define IPG_TFC_TXDMAINDICATE 0x0000000000800000ULL -#define IPG_TFC_FRAGCOUNT 0x000000000F000000ULL -#define IPG_TFC_VLANTAGINSERT 0x0000000010000000ULL -#define IPG_TFC_TFDDONE 0x0000000080000000ULL -#define IPG_TFC_VID 0x00000FFF00000000ULL -#define IPG_TFC_CFI 0x0000100000000000ULL -#define IPG_TFC_USERPRIORITY 0x0000E00000000000ULL - -/* TFDList, FragInfo */ -#define IPG_TFI_RSVD_MASK 0xFFFF00FFFFFFFFFFULL -#define IPG_TFI_FRAGADDR 0x000000FFFFFFFFFFULL -#define IPG_TFI_FRAGLEN 0xFFFF000000000000ULL - -/* RFD data structure masks. */ - -/* RFDList, RFS */ -#define IPG_RFS_RSVD_MASK 0x0000FFFFFFFFFFFFULL -#define IPG_RFS_RXFRAMELEN 0x000000000000FFFFULL -#define IPG_RFS_RXFIFOOVERRUN 0x0000000000010000ULL -#define IPG_RFS_RXRUNTFRAME 0x0000000000020000ULL -#define IPG_RFS_RXALIGNMENTERROR 0x0000000000040000ULL -#define IPG_RFS_RXFCSERROR 0x0000000000080000ULL -#define IPG_RFS_RXOVERSIZEDFRAME 0x0000000000100000ULL -#define IPG_RFS_RXLENGTHERROR 0x0000000000200000ULL -#define IPG_RFS_VLANDETECTED 0x0000000000400000ULL -#define IPG_RFS_TCPDETECTED 0x0000000000800000ULL -#define IPG_RFS_TCPERROR 0x0000000001000000ULL -#define IPG_RFS_UDPDETECTED 0x0000000002000000ULL -#define IPG_RFS_UDPERROR 0x0000000004000000ULL -#define IPG_RFS_IPDETECTED 0x0000000008000000ULL -#define IPG_RFS_IPERROR 0x0000000010000000ULL -#define IPG_RFS_FRAMESTART 0x0000000020000000ULL -#define IPG_RFS_FRAMEEND 0x0000000040000000ULL -#define IPG_RFS_RFDDONE 0x0000000080000000ULL -#define IPG_RFS_TCI 0x0000FFFF00000000ULL - -/* RFDList, FragInfo */ -#define IPG_RFI_RSVD_MASK 0xFFFF00FFFFFFFFFFULL -#define IPG_RFI_FRAGADDR 0x000000FFFFFFFFFFULL -#define IPG_RFI_FRAGLEN 0xFFFF000000000000ULL - -/* I/O Register masks. */ - -/* RMON Statistics Mask */ -#define IPG_RZ_ALL 0x0FFFFFFF - -/* Statistics Mask */ -#define IPG_SM_ALL 0x0FFFFFFF -#define IPG_SM_OCTETRCVOK_FRAMESRCVDOK 0x00000001 -#define IPG_SM_MCSTOCTETRCVDOK_MCSTFRAMESRCVDOK 0x00000002 -#define IPG_SM_BCSTOCTETRCVDOK_BCSTFRAMESRCVDOK 0x00000004 -#define IPG_SM_RXJUMBOFRAMES 0x00000008 -#define IPG_SM_TCPCHECKSUMERRORS 0x00000010 -#define IPG_SM_IPCHECKSUMERRORS 0x00000020 -#define IPG_SM_UDPCHECKSUMERRORS 0x00000040 -#define IPG_SM_MACCONTROLFRAMESRCVD 0x00000080 -#define IPG_SM_FRAMESTOOLONGERRORS 0x00000100 -#define IPG_SM_INRANGELENGTHERRORS 0x00000200 -#define IPG_SM_FRAMECHECKSEQERRORS 0x00000400 -#define IPG_SM_FRAMESLOSTRXERRORS 0x00000800 -#define IPG_SM_OCTETXMTOK_FRAMESXMTOK 0x00001000 -#define IPG_SM_MCSTOCTETXMTOK_MCSTFRAMESXMTDOK 0x00002000 -#define IPG_SM_BCSTOCTETXMTOK_BCSTFRAMESXMTDOK 0x00004000 -#define IPG_SM_FRAMESWDEFERREDXMT 0x00008000 -#define IPG_SM_LATECOLLISIONS 0x00010000 -#define IPG_SM_MULTICOLFRAMES 0x00020000 -#define IPG_SM_SINGLECOLFRAMES 0x00040000 -#define IPG_SM_TXJUMBOFRAMES 0x00080000 -#define IPG_SM_CARRIERSENSEERRORS 0x00100000 -#define IPG_SM_MACCONTROLFRAMESXMTD 0x00200000 -#define IPG_SM_FRAMESABORTXSCOLLS 0x00400000 -#define IPG_SM_FRAMESWEXDEFERAL 0x00800000 - -/* Countdown */ -#define IPG_CD_RSVD_MASK 0x0700FFFF -#define IPG_CD_COUNT 0x0000FFFF -#define IPG_CD_COUNTDOWNSPEED 0x01000000 -#define IPG_CD_COUNTDOWNMODE 0x02000000 -#define IPG_CD_COUNTINTENABLED 0x04000000 - -/* TxDMABurstThresh */ -#define IPG_TB_RSVD_MASK 0xFF - -/* TxDMAUrgentThresh */ -#define IPG_TU_RSVD_MASK 0xFF - -/* TxDMAPollPeriod */ -#define IPG_TP_RSVD_MASK 0xFF - -/* RxDMAUrgentThresh */ -#define IPG_RU_RSVD_MASK 0xFF - -/* RxDMAPollPeriod */ -#define IPG_RP_RSVD_MASK 0xFF - -/* ReceiveMode */ -#define IPG_RM_RSVD_MASK 0x3F -#define IPG_RM_RECEIVEUNICAST 0x01 -#define IPG_RM_RECEIVEMULTICAST 0x02 -#define IPG_RM_RECEIVEBROADCAST 0x04 -#define IPG_RM_RECEIVEALLFRAMES 0x08 -#define IPG_RM_RECEIVEMULTICASTHASH 0x10 -#define IPG_RM_RECEIVEIPMULTICAST 0x20 - -/* PhySet */ -#define IPG_PS_MEM_LENB9B 0x01 -#define IPG_PS_MEM_LEN9 0x02 -#define IPG_PS_NON_COMPDET 0x04 - -/* PhyCtrl */ -#define IPG_PC_RSVD_MASK 0xFF -#define IPG_PC_MGMTCLK_LO 0x00 -#define IPG_PC_MGMTCLK_HI 0x01 -#define IPG_PC_MGMTCLK 0x01 -#define IPG_PC_MGMTDATA 0x02 -#define IPG_PC_MGMTDIR 0x04 -#define IPG_PC_DUPLEX_POLARITY 0x08 -#define IPG_PC_DUPLEX_STATUS 0x10 -#define IPG_PC_LINK_POLARITY 0x20 -#define IPG_PC_LINK_SPEED 0xC0 -#define IPG_PC_LINK_SPEED_10MBPS 0x40 -#define IPG_PC_LINK_SPEED_100MBPS 0x80 -#define IPG_PC_LINK_SPEED_1000MBPS 0xC0 - -/* DMACtrl */ -#define IPG_DC_RSVD_MASK 0xC07D9818 -#define IPG_DC_RX_DMA_COMPLETE 0x00000008 -#define IPG_DC_RX_DMA_POLL_NOW 0x00000010 -#define IPG_DC_TX_DMA_COMPLETE 0x00000800 -#define IPG_DC_TX_DMA_POLL_NOW 0x00001000 -#define IPG_DC_TX_DMA_IN_PROG 0x00008000 -#define IPG_DC_RX_EARLY_DISABLE 0x00010000 -#define IPG_DC_MWI_DISABLE 0x00040000 -#define IPG_DC_TX_WRITE_BACK_DISABLE 0x00080000 -#define IPG_DC_TX_BURST_LIMIT 0x00700000 -#define IPG_DC_TARGET_ABORT 0x40000000 -#define IPG_DC_MASTER_ABORT 0x80000000 - -/* ASICCtrl */ -#define IPG_AC_RSVD_MASK 0x07FFEFF2 -#define IPG_AC_EXP_ROM_SIZE 0x00000002 -#define IPG_AC_PHY_SPEED10 0x00000010 -#define IPG_AC_PHY_SPEED100 0x00000020 -#define IPG_AC_PHY_SPEED1000 0x00000040 -#define IPG_AC_PHY_MEDIA 0x00000080 -#define IPG_AC_FORCED_CFG 0x00000700 -#define IPG_AC_D3RESETDISABLE 0x00000800 -#define IPG_AC_SPEED_UP_MODE 0x00002000 -#define IPG_AC_LED_MODE 0x00004000 -#define IPG_AC_RST_OUT_POLARITY 0x00008000 -#define IPG_AC_GLOBAL_RESET 0x00010000 -#define IPG_AC_RX_RESET 0x00020000 -#define IPG_AC_TX_RESET 0x00040000 -#define IPG_AC_DMA 0x00080000 -#define IPG_AC_FIFO 0x00100000 -#define IPG_AC_NETWORK 0x00200000 -#define IPG_AC_HOST 0x00400000 -#define IPG_AC_AUTO_INIT 0x00800000 -#define IPG_AC_RST_OUT 0x01000000 -#define IPG_AC_INT_REQUEST 0x02000000 -#define IPG_AC_RESET_BUSY 0x04000000 -#define IPG_AC_LED_SPEED 0x08000000 -#define IPG_AC_LED_MODE_BIT_1 0x20000000 - -/* EepromCtrl */ -#define IPG_EC_RSVD_MASK 0x83FF -#define IPG_EC_EEPROM_ADDR 0x00FF -#define IPG_EC_EEPROM_OPCODE 0x0300 -#define IPG_EC_EEPROM_SUBCOMMAD 0x0000 -#define IPG_EC_EEPROM_WRITEOPCODE 0x0100 -#define IPG_EC_EEPROM_READOPCODE 0x0200 -#define IPG_EC_EEPROM_ERASEOPCODE 0x0300 -#define IPG_EC_EEPROM_BUSY 0x8000 - -/* FIFOCtrl */ -#define IPG_FC_RSVD_MASK 0xC001 -#define IPG_FC_RAM_TEST_MODE 0x0001 -#define IPG_FC_TRANSMITTING 0x4000 -#define IPG_FC_RECEIVING 0x8000 - -/* TxStatus */ -#define IPG_TS_RSVD_MASK 0xFFFF00DD -#define IPG_TS_TX_ERROR 0x00000001 -#define IPG_TS_LATE_COLLISION 0x00000004 -#define IPG_TS_TX_MAX_COLL 0x00000008 -#define IPG_TS_TX_UNDERRUN 0x00000010 -#define IPG_TS_TX_IND_REQD 0x00000040 -#define IPG_TS_TX_COMPLETE 0x00000080 -#define IPG_TS_TX_FRAMEID 0xFFFF0000 - -/* WakeEvent */ -#define IPG_WE_WAKE_PKT_ENABLE 0x01 -#define IPG_WE_MAGIC_PKT_ENABLE 0x02 -#define IPG_WE_LINK_EVT_ENABLE 0x04 -#define IPG_WE_WAKE_POLARITY 0x08 -#define IPG_WE_WAKE_PKT_EVT 0x10 -#define IPG_WE_MAGIC_PKT_EVT 0x20 -#define IPG_WE_LINK_EVT 0x40 -#define IPG_WE_WOL_ENABLE 0x80 - -/* IntEnable */ -#define IPG_IE_RSVD_MASK 0x1FFE -#define IPG_IE_HOST_ERROR 0x0002 -#define IPG_IE_TX_COMPLETE 0x0004 -#define IPG_IE_MAC_CTRL_FRAME 0x0008 -#define IPG_IE_RX_COMPLETE 0x0010 -#define IPG_IE_RX_EARLY 0x0020 -#define IPG_IE_INT_REQUESTED 0x0040 -#define IPG_IE_UPDATE_STATS 0x0080 -#define IPG_IE_LINK_EVENT 0x0100 -#define IPG_IE_TX_DMA_COMPLETE 0x0200 -#define IPG_IE_RX_DMA_COMPLETE 0x0400 -#define IPG_IE_RFD_LIST_END 0x0800 -#define IPG_IE_RX_DMA_PRIORITY 0x1000 - -/* IntStatus */ -#define IPG_IS_RSVD_MASK 0x1FFF -#define IPG_IS_INTERRUPT_STATUS 0x0001 -#define IPG_IS_HOST_ERROR 0x0002 -#define IPG_IS_TX_COMPLETE 0x0004 -#define IPG_IS_MAC_CTRL_FRAME 0x0008 -#define IPG_IS_RX_COMPLETE 0x0010 -#define IPG_IS_RX_EARLY 0x0020 -#define IPG_IS_INT_REQUESTED 0x0040 -#define IPG_IS_UPDATE_STATS 0x0080 -#define IPG_IS_LINK_EVENT 0x0100 -#define IPG_IS_TX_DMA_COMPLETE 0x0200 -#define IPG_IS_RX_DMA_COMPLETE 0x0400 -#define IPG_IS_RFD_LIST_END 0x0800 -#define IPG_IS_RX_DMA_PRIORITY 0x1000 - -/* MACCtrl */ -#define IPG_MC_RSVD_MASK 0x7FE33FA3 -#define IPG_MC_IFS_SELECT 0x00000003 -#define IPG_MC_IFS_4352BIT 0x00000003 -#define IPG_MC_IFS_1792BIT 0x00000002 -#define IPG_MC_IFS_1024BIT 0x00000001 -#define IPG_MC_IFS_96BIT 0x00000000 -#define IPG_MC_DUPLEX_SELECT 0x00000020 -#define IPG_MC_DUPLEX_SELECT_FD 0x00000020 -#define IPG_MC_DUPLEX_SELECT_HD 0x00000000 -#define IPG_MC_TX_FLOW_CONTROL_ENABLE 0x00000080 -#define IPG_MC_RX_FLOW_CONTROL_ENABLE 0x00000100 -#define IPG_MC_RCV_FCS 0x00000200 -#define IPG_MC_FIFO_LOOPBACK 0x00000400 -#define IPG_MC_MAC_LOOPBACK 0x00000800 -#define IPG_MC_AUTO_VLAN_TAGGING 0x00001000 -#define IPG_MC_AUTO_VLAN_UNTAGGING 0x00002000 -#define IPG_MC_COLLISION_DETECT 0x00010000 -#define IPG_MC_CARRIER_SENSE 0x00020000 -#define IPG_MC_STATISTICS_ENABLE 0x00200000 -#define IPG_MC_STATISTICS_DISABLE 0x00400000 -#define IPG_MC_STATISTICS_ENABLED 0x00800000 -#define IPG_MC_TX_ENABLE 0x01000000 -#define IPG_MC_TX_DISABLE 0x02000000 -#define IPG_MC_TX_ENABLED 0x04000000 -#define IPG_MC_RX_ENABLE 0x08000000 -#define IPG_MC_RX_DISABLE 0x10000000 -#define IPG_MC_RX_ENABLED 0x20000000 -#define IPG_MC_PAUSED 0x40000000 - -/* - * Tune - */ - -/* Assign IPG_APPEND_FCS_ON_TX > 0 for auto FCS append on TX. */ -#define IPG_APPEND_FCS_ON_TX 1 - -/* Assign IPG_APPEND_FCS_ON_TX > 0 for auto FCS strip on RX. */ -#define IPG_STRIP_FCS_ON_RX 1 - -/* Assign IPG_DROP_ON_RX_ETH_ERRORS > 0 to drop RX frames with - * Ethernet errors. - */ -#define IPG_DROP_ON_RX_ETH_ERRORS 1 - -/* Assign IPG_INSERT_MANUAL_VLAN_TAG > 0 to insert VLAN tags manually - * (via TFC). - */ -#define IPG_INSERT_MANUAL_VLAN_TAG 0 - -/* Assign IPG_ADD_IPCHECKSUM_ON_TX > 0 for auto IP checksum on TX. */ -#define IPG_ADD_IPCHECKSUM_ON_TX 0 - -/* Assign IPG_ADD_TCPCHECKSUM_ON_TX > 0 for auto TCP checksum on TX. - * DO NOT USE FOR SILICON REVISIONS B3 AND EARLIER. - */ -#define IPG_ADD_TCPCHECKSUM_ON_TX 0 - -/* Assign IPG_ADD_UDPCHECKSUM_ON_TX > 0 for auto UDP checksum on TX. - * DO NOT USE FOR SILICON REVISIONS B3 AND EARLIER. - */ -#define IPG_ADD_UDPCHECKSUM_ON_TX 0 - -/* If inserting VLAN tags manually, assign the IPG_MANUAL_VLAN_xx - * constants as desired. - */ -#define IPG_MANUAL_VLAN_VID 0xABC -#define IPG_MANUAL_VLAN_CFI 0x1 -#define IPG_MANUAL_VLAN_USERPRIORITY 0x5 - -#define IPG_IO_REG_RANGE 0xFF -#define IPG_MEM_REG_RANGE 0x154 -#define IPG_DRIVER_NAME "Sundance Technology IPG Triple-Speed Ethernet" -#define IPG_NIC_PHY_ADDRESS 0x01 -#define IPG_DMALIST_ALIGN_PAD 0x07 -#define IPG_MULTICAST_HASHTABLE_SIZE 0x40 - -/* Number of milliseconds to wait after issuing a software reset. - * 0x05 <= IPG_AC_RESETWAIT to account for proper 10Mbps operation. - */ -#define IPG_AC_RESETWAIT 0x05 - -/* Number of IPG_AC_RESETWAIT timeperiods before declaring timeout. */ -#define IPG_AC_RESET_TIMEOUT 0x0A - -/* Minimum number of nanoseconds used to toggle MDC clock during - * MII/GMII register access. - */ -#define IPG_PC_PHYCTRLWAIT_NS 200 - -#define IPG_TFDLIST_LENGTH 0x100 - -/* Number of frames between TxDMAComplete interrupt. - * 0 < IPG_FRAMESBETWEENTXDMACOMPLETES <= IPG_TFDLIST_LENGTH - */ -#define IPG_FRAMESBETWEENTXDMACOMPLETES 0x1 - -#define IPG_RFDLIST_LENGTH 0x100 - -/* Maximum number of RFDs to process per interrupt. - * 1 < IPG_MAXRFDPROCESS_COUNT < IPG_RFDLIST_LENGTH - */ -#define IPG_MAXRFDPROCESS_COUNT 0x80 - -/* Minimum margin between last freed RFD, and current RFD. - * 1 < IPG_MINUSEDRFDSTOFREE < IPG_RFDLIST_LENGTH - */ -#define IPG_MINUSEDRFDSTOFREE 0x80 - -/* specify the jumbo frame maximum size - * per unit is 0x600 (the rx_buffer size that one RFD can carry) - */ -#define MAX_JUMBOSIZE 0x8 /* max is 12K */ - -/* Key register values loaded at driver start up. */ - -/* TXDMAPollPeriod is specified in 320ns increments. - * - * Value Time - * --------------------- - * 0x00-0x01 320ns - * 0x03 ~1us - * 0x1F ~10us - * 0xFF ~82us - */ -#define IPG_TXDMAPOLLPERIOD_VALUE 0x26 - -/* TxDMAUrgentThresh specifies the minimum amount of - * data in the transmit FIFO before asserting an - * urgent transmit DMA request. - * - * Value Min TxFIFO occupied space before urgent TX request - * --------------------------------------------------------------- - * 0x00-0x04 128 bytes (1024 bits) - * 0x27 1248 bytes (~10000 bits) - * 0x30 1536 bytes (12288 bits) - * 0xFF 8192 bytes (65535 bits) - */ -#define IPG_TXDMAURGENTTHRESH_VALUE 0x04 - -/* TxDMABurstThresh specifies the minimum amount of - * free space in the transmit FIFO before asserting an - * transmit DMA request. - * - * Value Min TxFIFO free space before TX request - * ---------------------------------------------------- - * 0x00-0x08 256 bytes - * 0x30 1536 bytes - * 0xFF 8192 bytes - */ -#define IPG_TXDMABURSTTHRESH_VALUE 0x30 - -/* RXDMAPollPeriod is specified in 320ns increments. - * - * Value Time - * --------------------- - * 0x00-0x01 320ns - * 0x03 ~1us - * 0x1F ~10us - * 0xFF ~82us - */ -#define IPG_RXDMAPOLLPERIOD_VALUE 0x01 - -/* RxDMAUrgentThresh specifies the minimum amount of - * free space within the receive FIFO before asserting - * a urgent receive DMA request. - * - * Value Min RxFIFO free space before urgent RX request - * --------------------------------------------------------------- - * 0x00-0x04 128 bytes (1024 bits) - * 0x27 1248 bytes (~10000 bits) - * 0x30 1536 bytes (12288 bits) - * 0xFF 8192 bytes (65535 bits) - */ -#define IPG_RXDMAURGENTTHRESH_VALUE 0x30 - -/* RxDMABurstThresh specifies the minimum amount of - * occupied space within the receive FIFO before asserting - * a receive DMA request. - * - * Value Min TxFIFO free space before TX request - * ---------------------------------------------------- - * 0x00-0x08 256 bytes - * 0x30 1536 bytes - * 0xFF 8192 bytes - */ -#define IPG_RXDMABURSTTHRESH_VALUE 0x30 - -/* FlowOnThresh specifies the maximum amount of occupied - * space in the receive FIFO before a PAUSE frame with - * maximum pause time transmitted. - * - * Value Max RxFIFO occupied space before PAUSE - * --------------------------------------------------- - * 0x0000 0 bytes - * 0x0740 29,696 bytes - * 0x07FF 32,752 bytes - */ -#define IPG_FLOWONTHRESH_VALUE 0x0740 - -/* FlowOffThresh specifies the minimum amount of occupied - * space in the receive FIFO before a PAUSE frame with - * zero pause time is transmitted. - * - * Value Max RxFIFO occupied space before PAUSE - * --------------------------------------------------- - * 0x0000 0 bytes - * 0x00BF 3056 bytes - * 0x07FF 32,752 bytes - */ -#define IPG_FLOWOFFTHRESH_VALUE 0x00BF - -/* - * Miscellaneous macros. - */ - -/* Macros for printing debug statements. */ -#ifdef IPG_DEBUG -# define IPG_DEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DDEBUG_MSG(fmt, args...) \ - printk(KERN_DEBUG "IPG: " fmt, ##args) -# define IPG_DUMPRFDLIST(args) ipg_dump_rfdlist(args) -# define IPG_DUMPTFDLIST(args) ipg_dump_tfdlist(args) -#else -# define IPG_DEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DDEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DUMPRFDLIST(args) -# define IPG_DUMPTFDLIST(args) -#endif - -/* - * End miscellaneous macros. - */ - -/* Transmit Frame Descriptor. The IPG supports 15 fragments, - * however Linux requires only a single fragment. Note, each - * TFD field is 64 bits wide. - */ -struct ipg_tx { - __le64 next_desc; - __le64 tfc; - __le64 frag_info; -}; - -/* Receive Frame Descriptor. Note, each RFD field is 64 bits wide. - */ -struct ipg_rx { - __le64 next_desc; - __le64 rfs; - __le64 frag_info; -}; - -struct ipg_jumbo { - int found_start; - int current_size; - struct sk_buff *skb; -}; - -/* Structure of IPG NIC specific data. */ -struct ipg_nic_private { - void __iomem *ioaddr; - struct ipg_tx *txd; - struct ipg_rx *rxd; - dma_addr_t txd_map; - dma_addr_t rxd_map; - struct sk_buff *tx_buff[IPG_TFDLIST_LENGTH]; - struct sk_buff *rx_buff[IPG_RFDLIST_LENGTH]; - unsigned int tx_current; - unsigned int tx_dirty; - unsigned int rx_current; - unsigned int rx_dirty; - bool is_jumbo; - struct ipg_jumbo jumbo; - unsigned long rxfrag_size; - unsigned long rxsupport_size; - unsigned long max_rxframe_size; - unsigned int rx_buf_sz; - struct pci_dev *pdev; - struct net_device *dev; - struct net_device_stats stats; - spinlock_t lock; - int tenmbpsmode; - - u16 led_mode; - u16 station_addr[3]; /* Station Address in EEPROM Reg 0x10..0x12 */ - - struct mutex mii_mutex; - struct mii_if_info mii_if; - int reset_current_tfd; -#ifdef IPG_DEBUG - int RFDlistendCount; - int RFDListCheckedCount; - int EmptyRFDListCount; -#endif - struct delayed_work task; -}; - -#endif /* __LINUX_IPG_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 85f1b1e..31c491e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -892,9 +892,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn; dev->caps.port_mask[i] = dev->caps.port_type[i]; dev->caps.phys_port_id[i] = func_cap.phys_port_id; - if (mlx4_get_slave_pkey_gid_tbl_len(dev, i, - &dev->caps.gid_table_len[i], - &dev->caps.pkey_table_len[i])) + err = mlx4_get_slave_pkey_gid_tbl_len(dev, i, + &dev->caps.gid_table_len[i], + &dev->caps.pkey_table_len[i]); + if (err) goto err_mem; } @@ -906,6 +907,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.uar_page_size * dev->caps.num_uars, (unsigned long long) pci_resource_len(dev->persist->pdev, 2)); + err = -ENOMEM; goto err_mem; } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 9813d34..6fec3e9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4952,26 +4952,41 @@ static void rem_slave_counters(struct mlx4_dev *dev, int slave) struct res_counter *counter; struct res_counter *tmp; int err; - int index; + int *counters_arr = NULL; + int i, j; err = move_all_busy(dev, slave, RES_COUNTER); if (err) mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n", slave); - spin_lock_irq(mlx4_tlock(dev)); - list_for_each_entry_safe(counter, tmp, counter_list, com.list) { - if (counter->com.owner == slave) { - index = counter->com.res_id; - rb_erase(&counter->com.node, - &tracker->res_tree[RES_COUNTER]); - list_del(&counter->com.list); - kfree(counter); - __mlx4_counter_free(dev, index); + counters_arr = kmalloc_array(dev->caps.max_counters, + sizeof(*counters_arr), GFP_KERNEL); + if (!counters_arr) + return; + + do { + i = 0; + j = 0; + spin_lock_irq(mlx4_tlock(dev)); + list_for_each_entry_safe(counter, tmp, counter_list, com.list) { + if (counter->com.owner == slave) { + counters_arr[i++] = counter->com.res_id; + rb_erase(&counter->com.node, + &tracker->res_tree[RES_COUNTER]); + list_del(&counter->com.list); + kfree(counter); + } + } + spin_unlock_irq(mlx4_tlock(dev)); + + while (j < i) { + __mlx4_counter_free(dev, counters_arr[j++]); mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0); } - } - spin_unlock_irq(mlx4_tlock(dev)); + } while (i); + + kfree(counters_arr); } static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f2ae62d..22e72bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -334,9 +334,15 @@ struct mlx5e_tx_skb_cb { #define MLX5E_TX_SKB_CB(__skb) ((struct mlx5e_tx_skb_cb *)__skb->cb) +enum mlx5e_dma_map_type { + MLX5E_DMA_MAP_SINGLE, + MLX5E_DMA_MAP_PAGE +}; + struct mlx5e_sq_dma { - dma_addr_t addr; - u32 size; + dma_addr_t addr; + u32 size; + enum mlx5e_dma_map_type type; }; enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5fc4d2d..1e52db3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1332,6 +1332,42 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) return err; } +static int mlx5e_refresh_tir_self_loopback_enable(struct mlx5_core_dev *mdev, + u32 tirn) +{ + void *in; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); + + err = mlx5_core_modify_tir(mdev, tirn, in, inlen); + + kvfree(in); + + return err; +} + +static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv) +{ + int err; + int i; + + for (i = 0; i < MLX5E_NUM_TT; i++) { + err = mlx5e_refresh_tir_self_loopback_enable(priv->mdev, + priv->tirn[i]); + if (err) + return err; + } + + return 0; +} + static int mlx5e_set_dev_port_mtu(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -1376,6 +1412,13 @@ int mlx5e_open_locked(struct net_device *netdev) goto err_clear_state_opened_flag; } + err = mlx5e_refresh_tirs_self_loopback_enable(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n", + __func__, err); + goto err_close_channels; + } + mlx5e_update_carrier(priv); mlx5e_redirect_rqts(priv); @@ -1383,6 +1426,8 @@ int mlx5e_open_locked(struct net_device *netdev) return 0; +err_close_channels: + mlx5e_close_channels(priv); err_clear_state_opened_flag: clear_bit(MLX5E_STATE_OPENED, &priv->state); return err; @@ -1856,6 +1901,8 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + max_mtu = MLX5E_HW2SW_MTU(max_mtu); + if (new_mtu > max_mtu) { netdev_err(netdev, "%s: Bad MTU (%d) > (%d) Max\n", @@ -1909,6 +1956,9 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) "Not creating net device, some required device capabilities are missing\n"); return -ENOTSUPP; } + if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) + mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index cd8f85a..1341b1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -61,39 +61,47 @@ void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw) } } -static void mlx5e_dma_pop_last_pushed(struct mlx5e_sq *sq, dma_addr_t *addr, - u32 *size) +static inline void mlx5e_tx_dma_unmap(struct device *pdev, + struct mlx5e_sq_dma *dma) { - sq->dma_fifo_pc--; - *addr = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr; - *size = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size; -} - -static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) -{ - dma_addr_t addr; - u32 size; - int i; - - for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { - mlx5e_dma_pop_last_pushed(sq, &addr, &size); - dma_unmap_single(sq->pdev, addr, size, DMA_TO_DEVICE); + switch (dma->type) { + case MLX5E_DMA_MAP_SINGLE: + dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + break; + case MLX5E_DMA_MAP_PAGE: + dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + break; + default: + WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n"); } } -static inline void mlx5e_dma_push(struct mlx5e_sq *sq, dma_addr_t addr, - u32 size) +static inline void mlx5e_dma_push(struct mlx5e_sq *sq, + dma_addr_t addr, + u32 size, + enum mlx5e_dma_map_type map_type) { sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr = addr; sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size = size; + sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].type = map_type; sq->dma_fifo_pc++; } -static inline void mlx5e_dma_get(struct mlx5e_sq *sq, u32 i, dma_addr_t *addr, - u32 *size) +static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i) { - *addr = sq->dma_fifo[i & sq->dma_fifo_mask].addr; - *size = sq->dma_fifo[i & sq->dma_fifo_mask].size; + return &sq->dma_fifo[i & sq->dma_fifo_mask]; +} + +static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) +{ + int i; + + for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { + struct mlx5e_sq_dma *last_pushed_dma = + mlx5e_dma_get(sq, --sq->dma_fifo_pc); + + mlx5e_tx_dma_unmap(sq->pdev, last_pushed_dma); + } } u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, @@ -118,8 +126,15 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, */ #define MLX5E_MIN_INLINE ETH_HLEN - if (bf && (skb_headlen(skb) <= sq->max_inline)) - return skb_headlen(skb); + if (bf) { + u16 ihs = skb_headlen(skb); + + if (skb_vlan_tag_present(skb)) + ihs += VLAN_HLEN; + + if (ihs <= sq->max_inline) + return skb_headlen(skb); + } return MLX5E_MIN_INLINE; } @@ -218,7 +233,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(headlen); - mlx5e_dma_push(sq, dma_addr, headlen); + mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE); MLX5E_TX_SKB_CB(skb)->num_dma++; dseg++; @@ -237,7 +252,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(fsz); - mlx5e_dma_push(sq, dma_addr, fsz); + mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); MLX5E_TX_SKB_CB(skb)->num_dma++; dseg++; @@ -353,13 +368,10 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) } for (j = 0; j < MLX5E_TX_SKB_CB(skb)->num_dma; j++) { - dma_addr_t addr; - u32 size; + struct mlx5e_sq_dma *dma = + mlx5e_dma_get(sq, dma_fifo_cc++); - mlx5e_dma_get(sq, dma_fifo_cc, &addr, &size); - dma_fifo_cc++; - dma_unmap_single(sq->pdev, addr, size, - DMA_TO_DEVICE); + mlx5e_tx_dma_unmap(sq->pdev, dma); } npkts++; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b4f2123..79ef799 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7429,15 +7429,15 @@ process_pkt: rtl8169_rx_vlan_tag(desc, skb); + if (skb->pkt_type == PACKET_MULTICAST) + dev->stats.multicast++; + napi_gro_receive(&tp->napi, skb); u64_stats_update_begin(&tp->rx_stats.syncp); tp->rx_stats.packets++; tp->rx_stats.bytes += pkt_size; u64_stats_update_end(&tp->rx_stats.syncp); - - if (skb->pkt_type == PACKET_MULTICAST) - dev->stats.multicast++; } release_descriptor: desc->opts2 = 0; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index aa7b208..ee8d1ec 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -408,8 +408,6 @@ static int ravb_dmac_init(struct net_device *ndev) /* Interrupt enable: */ /* Frame receive */ ravb_write(ndev, RIC0_FRE0 | RIC0_FRE1, RIC0); - /* Receive FIFO full warning */ - ravb_write(ndev, RIC1_RFWE, RIC1); /* Receive FIFO full error, descriptor empty */ ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2); /* Frame transmitted, timestamp FIFO updated */ @@ -733,8 +731,10 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id) ((tis & tic) & BIT(q))) { if (napi_schedule_prep(&priv->napi[q])) { /* Mask RX and TX interrupts */ - ravb_write(ndev, ric0 & ~BIT(q), RIC0); - ravb_write(ndev, tic & ~BIT(q), TIC); + ric0 &= ~BIT(q); + tic &= ~BIT(q); + ravb_write(ndev, ric0, RIC0); + ravb_write(ndev, tic, TIC); __napi_schedule(&priv->napi[q]); } else { netdev_warn(ndev, diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index d288f1c..a3c42a3 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -3422,7 +3422,7 @@ out: * with our request for slot reset the mmio_enabled callback will never be * called, and the link_reset callback is not used by AER or EEH mechanisms. */ -static struct pci_error_handlers efx_err_handlers = { +static const struct pci_error_handlers efx_err_handlers = { .error_detected = efx_io_error_detected, .slot_reset = efx_io_slot_reset, .resume = efx_io_resume, diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index c860c90..219a99b 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -809,22 +809,17 @@ static int smsc911x_phy_check_loopbackpkt(struct smsc911x_data *pdata) static int smsc911x_phy_reset(struct smsc911x_data *pdata) { - struct phy_device *phy_dev = pdata->phy_dev; unsigned int temp; unsigned int i = 100000; - BUG_ON(!phy_dev); - BUG_ON(!phy_dev->bus); - - SMSC_TRACE(pdata, hw, "Performing PHY BCR Reset"); - smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, BMCR_RESET); + temp = smsc911x_reg_read(pdata, PMT_CTRL); + smsc911x_reg_write(pdata, PMT_CTRL, temp | PMT_CTRL_PHY_RST_); do { msleep(1); - temp = smsc911x_mii_read(phy_dev->bus, phy_dev->addr, - MII_BMCR); - } while ((i--) && (temp & BMCR_RESET)); + temp = smsc911x_reg_read(pdata, PMT_CTRL); + } while ((i--) && (temp & PMT_CTRL_PHY_RST_)); - if (temp & BMCR_RESET) { + if (unlikely(temp & PMT_CTRL_PHY_RST_)) { SMSC_WARN(pdata, hw, "PHY reset failed to complete"); return -EIO; } @@ -2296,7 +2291,7 @@ static int smsc911x_init(struct net_device *dev) } /* Reset the LAN911x */ - if (smsc911x_soft_reset(pdata)) + if (smsc911x_phy_reset(pdata) || smsc911x_soft_reset(pdata)) return -ENODEV; dev->flags |= IFF_MULTICAST; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 9d89bdb..82de68b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -337,11 +337,11 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) QSGMII_PHY_RX_SIGNAL_DETECT_EN | QSGMII_PHY_TX_DRIVER_EN | QSGMII_PHY_QSGMII_EN | - 0x4 << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | - 0x3 << QSGMII_PHY_RX_DC_BIAS_OFFSET | - 0x1 << QSGMII_PHY_RX_INPUT_EQU_OFFSET | - 0x2 << QSGMII_PHY_CDR_PI_SLEW_OFFSET | - 0xC << QSGMII_PHY_TX_DRV_AMP_OFFSET); + 0x4ul << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | + 0x3ul << QSGMII_PHY_RX_DC_BIAS_OFFSET | + 0x1ul << QSGMII_PHY_RX_INPUT_EQU_OFFSET | + 0x2ul << QSGMII_PHY_CDR_PI_SLEW_OFFSET | + 0xCul << QSGMII_PHY_TX_DRV_AMP_OFFSET); } plat_dat->has_gmac = true; diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index ae68afd..f38696c 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -345,13 +345,6 @@ VELOCITY_PARAM(flow_control, "Enable flow control ability"); */ VELOCITY_PARAM(speed_duplex, "Setting the speed and duplex mode"); -#define VAL_PKT_LEN_DEF 0 -/* ValPktLen[] is used for setting the checksum offload ability of NIC. - 0: Receive frame with invalid layer 2 length (Default) - 1: Drop frame with invalid layer 2 length -*/ -VELOCITY_PARAM(ValPktLen, "Receiving or Drop invalid 802.3 frame"); - #define WOL_OPT_DEF 0 #define WOL_OPT_MIN 0 #define WOL_OPT_MAX 7 @@ -494,7 +487,6 @@ static void velocity_get_options(struct velocity_opt *opts, int index, velocity_set_int_opt(&opts->flow_cntl, flow_control[index], FLOW_CNTL_MIN, FLOW_CNTL_MAX, FLOW_CNTL_DEF, "flow_control", devname); velocity_set_bool_opt(&opts->flags, IP_byte_align[index], IP_ALIG_DEF, VELOCITY_FLAGS_IP_ALIGN, "IP_byte_align", devname); - velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname); velocity_set_int_opt((int *) &opts->spd_dpx, speed_duplex[index], MED_LNK_MIN, MED_LNK_MAX, MED_LNK_DEF, "Media link mode", devname); velocity_set_int_opt(&opts->wol_opts, wol_opts[index], WOL_OPT_MIN, WOL_OPT_MAX, WOL_OPT_DEF, "Wake On Lan options", devname); opts->numrx = (opts->numrx & ~3); @@ -2055,8 +2047,9 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) int pkt_len = le16_to_cpu(rd->rdesc0.len) & 0x3fff; struct sk_buff *skb; - if (rd->rdesc0.RSR & (RSR_STP | RSR_EDP)) { - VELOCITY_PRT(MSG_LEVEL_VERBOSE, KERN_ERR " %s : the received frame spans multiple RDs.\n", vptr->netdev->name); + if (unlikely(rd->rdesc0.RSR & (RSR_STP | RSR_EDP | RSR_RL))) { + if (rd->rdesc0.RSR & (RSR_STP | RSR_EDP)) + VELOCITY_PRT(MSG_LEVEL_VERBOSE, KERN_ERR " %s : the received frame spans multiple RDs.\n", vptr->netdev->name); stats->rx_length_errors++; return -EINVAL; } @@ -2069,17 +2062,6 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) dma_sync_single_for_cpu(vptr->dev, rd_info->skb_dma, vptr->rx.buf_sz, DMA_FROM_DEVICE); - /* - * Drop frame not meeting IEEE 802.3 - */ - - if (vptr->flags & VELOCITY_FLAGS_VAL_PKT_LEN) { - if (rd->rdesc0.RSR & RSR_RL) { - stats->rx_length_errors++; - return -EINVAL; - } - } - velocity_rx_csum(rd, skb); if (velocity_rx_copy(&skb, pkt_len, vptr) < 0) { diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index bb8b530..b103adb 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -599,7 +599,7 @@ int fjes_hw_unregister_buff_addr(struct fjes_hw *hw, int dest_epid) FJES_CMD_REQ_RES_CODE_BUSY) && (timeout > 0)) { msleep(200 + hw->my_epid * 20); - timeout -= (200 + hw->my_epid * 20); + timeout -= (200 + hw->my_epid * 20); res_buf->unshare_buffer.length = 0; res_buf->unshare_buffer.code = 0; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index d50887e..8c48bb2 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -254,7 +254,7 @@ acct: } } -static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, +static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb, bool local) { struct ipvl_dev *ipvlan = addr->master; @@ -262,6 +262,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, unsigned int len; rx_handler_result_t ret = RX_HANDLER_CONSUMED; bool success = false; + struct sk_buff *skb = *pskb; len = skb->len + ETH_HLEN; if (unlikely(!(dev->flags & IFF_UP))) { @@ -273,6 +274,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, if (!skb) goto out; + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; @@ -486,7 +488,7 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) - return ipvlan_rcv_frame(addr, skb, true); + return ipvlan_rcv_frame(addr, &skb, true); out: skb->dev = ipvlan->phy_dev; @@ -506,7 +508,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) - return ipvlan_rcv_frame(addr, skb, true); + return ipvlan_rcv_frame(addr, &skb, true); } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) @@ -589,7 +591,7 @@ static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb, addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) - ret = ipvlan_rcv_frame(addr, skb, false); + ret = ipvlan_rcv_frame(addr, pskb, false); out: return ret; @@ -626,7 +628,7 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) - ret = ipvlan_rcv_frame(addr, skb, false); + ret = ipvlan_rcv_frame(addr, pskb, false); } return ret; @@ -651,5 +653,5 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n", port->mode); kfree_skb(skb); - return NET_RX_DROP; + return RX_HANDLER_CONSUMED; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 86f6c62..06c8bfe 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -415,6 +415,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; + *pskb = skb; eth = eth_hdr(skb); macvlan_forward_source(skb, port, eth->h_source); src = macvlan_hash_lookup(port, eth->h_source); @@ -456,6 +457,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) goto out; } + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index fabf11d..2d020a3 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -308,6 +308,8 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_HAS_INTERRUPT, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, .driver = { .owner = THIS_MODULE, }, @@ -327,6 +329,8 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_HAS_INTERRUPT, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, .driver = { .owner = THIS_MODULE, }, diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 5de8d58..0240552 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1154,6 +1154,21 @@ static struct phy_driver marvell_drivers[] = { .driver = { .owner = THIS_MODULE }, }, { + .phy_id = MARVELL_PHY_ID_88E1540, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "Marvell 88E1540", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_aneg = &m88e1510_config_aneg, + .read_status = &marvell_read_status, + .ack_interrupt = &marvell_ack_interrupt, + .config_intr = &marvell_config_intr, + .did_interrupt = &m88e1121_did_interrupt, + .resume = &genphy_resume, + .suspend = &genphy_suspend, + .driver = { .owner = THIS_MODULE }, + }, + { .phy_id = MARVELL_PHY_ID_88E3016, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E3016", @@ -1186,6 +1201,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1318S, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1116R, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1510, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1540, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index adb48ab..48ce6ef 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -863,6 +863,9 @@ void phy_state_machine(struct work_struct *work) needs_aneg = true; break; case PHY_NOLINK: + if (phy_interrupt_is_valid(phydev)) + break; + err = phy_read_status(phydev); if (err) break; diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 76cad71..dd295db 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -66,6 +66,7 @@ #define PHY_ID_VSC8244 0x000fc6c0 #define PHY_ID_VSC8514 0x00070670 #define PHY_ID_VSC8574 0x000704a0 +#define PHY_ID_VSC8601 0x00070420 #define PHY_ID_VSC8662 0x00070660 #define PHY_ID_VSC8221 0x000fc550 #define PHY_ID_VSC8211 0x000fc4b0 @@ -133,7 +134,8 @@ static int vsc82xx_config_intr(struct phy_device *phydev) (phydev->drv->phy_id == PHY_ID_VSC8234 || phydev->drv->phy_id == PHY_ID_VSC8244 || phydev->drv->phy_id == PHY_ID_VSC8514 || - phydev->drv->phy_id == PHY_ID_VSC8574) ? + phydev->drv->phy_id == PHY_ID_VSC8574 || + phydev->drv->phy_id == PHY_ID_VSC8601) ? MII_VSC8244_IMASK_MASK : MII_VSC8221_IMASK_MASK); else { @@ -272,6 +274,18 @@ static struct phy_driver vsc82xx_driver[] = { .config_intr = &vsc82xx_config_intr, .driver = { .owner = THIS_MODULE,}, }, { + .phy_id = PHY_ID_VSC8601, + .name = "Vitesse VSC8601", + .phy_id_mask = 0x000ffff0, + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = &genphy_config_init, + .config_aneg = &genphy_config_aneg, + .read_status = &genphy_read_status, + .ack_interrupt = &vsc824x_ack_interrupt, + .config_intr = &vsc82xx_config_intr, + .driver = { .owner = THIS_MODULE,}, +}, { .phy_id = PHY_ID_VSC8662, .name = "Vitesse VSC8662", .phy_id_mask = 0x000ffff0, diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c78d3cb..3da70bf 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -696,6 +696,11 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (kernel_ulong_t) &wwan_info, }, { + /* Dell DW5580 modules */ + USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, 0x81ba, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = (kernel_ulong_t)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 46f4cad..899ea42 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2157,12 +2157,13 @@ vmxnet3_set_mc(struct net_device *netdev) if (!netdev_mc_empty(netdev)) { new_table = vmxnet3_copy_mc(netdev); if (new_table) { - rxConf->mfTableLen = cpu_to_le16( - netdev_mc_count(netdev) * ETH_ALEN); + size_t sz = netdev_mc_count(netdev) * ETH_ALEN; + + rxConf->mfTableLen = cpu_to_le16(sz); new_table_pa = dma_map_single( &adapter->pdev->dev, new_table, - rxConf->mfTableLen, + sz, PCI_DMA_TODEVICE); } diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 3f859a5..4c58c83 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.3.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.4.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040300 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040400 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index e6982ac..a57f0df 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -16,6 +16,7 @@ #define MARVELL_PHY_ID_88E1318S 0x01410e90 #define MARVELL_PHY_ID_88E1116R 0x01410e40 #define MARVELL_PHY_ID_88E1510 0x01410dd0 +#define MARVELL_PHY_ID_88E1540 0x01410eb0 #define MARVELL_PHY_ID_88E3016 0x01410e60 /* struct phy_device dev_flags definitions */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dd20974..1565324 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -453,26 +453,28 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 lro_cap[0x1]; u8 lro_psh_flag[0x1]; u8 lro_time_stamp[0x1]; - u8 reserved_0[0x6]; + u8 reserved_0[0x3]; + u8 self_lb_en_modifiable[0x1]; + u8 reserved_1[0x2]; u8 max_lso_cap[0x5]; - u8 reserved_1[0x4]; + u8 reserved_2[0x4]; u8 rss_ind_tbl_cap[0x4]; - u8 reserved_2[0x3]; + u8 reserved_3[0x3]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_3[0x2]; + u8 reserved_4[0x2]; u8 tunnel_statless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; - u8 reserved_4[0x20]; + u8 reserved_5[0x20]; - u8 reserved_5[0x10]; + u8 reserved_6[0x10]; u8 lro_min_mss_size[0x10]; - u8 reserved_6[0x120]; + u8 reserved_7[0x120]; u8 lro_timer_supported_periods[4][0x20]; - u8 reserved_7[0x600]; + u8 reserved_8[0x600]; }; struct mlx5_ifc_roce_cap_bits { @@ -4051,9 +4053,11 @@ struct mlx5_ifc_modify_tis_in_bits { }; struct mlx5_ifc_modify_tir_bitmask_bits { - u8 reserved[0x20]; + u8 reserved_0[0x20]; - u8 reserved1[0x1f]; + u8 reserved_1[0x1b]; + u8 self_lb_en[0x1]; + u8 reserved_2[0x3]; u8 lro[0x1]; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d208914..67bfac1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2068,20 +2068,23 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; -#define netdev_alloc_pcpu_stats(type) \ -({ \ - typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ - if (pcpu_stats) { \ - int __cpu; \ - for_each_possible_cpu(__cpu) { \ - typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, __cpu); \ - u64_stats_init(&stat->syncp); \ - } \ - } \ - pcpu_stats; \ +#define __netdev_alloc_pcpu_stats(type, gfp) \ +({ \ + typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ + if (pcpu_stats) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ }) +#define netdev_alloc_pcpu_stats(type) \ + __netdev_alloc_pcpu_stats(type, GFP_KERNEL); + #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update the rtnetlink @@ -3854,6 +3857,11 @@ static inline bool netif_is_bridge_master(const struct net_device *dev) return dev->priv_flags & IFF_EBRIDGE; } +static inline bool netif_is_bridge_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_BRIDGE_PORT; +} + static inline bool netif_is_ovs_master(const struct net_device *dev) { return dev->priv_flags & IFF_OPENVSWITCH; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 48bb01e..0e1f433 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -421,7 +421,7 @@ extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], - size_t len); + size_t len, size_t align); extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext *ext); diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 187feab..5fcd375 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -5,10 +5,13 @@ #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS -static inline int nf_hook_ingress_active(struct sk_buff *skb) +static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { - return nf_hook_list_active(&skb->dev->nf_hooks_ingress, - NFPROTO_NETDEV, NF_NETDEV_INGRESS); +#ifdef HAVE_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) + return false; +#endif + return !list_empty(&skb->dev->nf_hooks_ingress); } static inline int nf_hook_ingress(struct sk_buff *skb) @@ -16,8 +19,8 @@ static inline int nf_hook_ingress(struct sk_buff *skb) struct nf_hook_state state; nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, - NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL, - skb->dev, NULL, dev_net(skb->dev), NULL); + NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, + skb->dev, NULL, NULL, dev_net(skb->dev), NULL); return nf_hook_slow(skb, &state); } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index aaf9700..fb961a5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -167,7 +167,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) static inline u32 rt6_get_cookie(const struct rt6_info *rt) { - if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE)) + if (rt->rt6i_flags & RTF_PCPU || + (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index aaee6fa..ff788b6 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else { stats->tx_errors++; stats->tx_aborted_errors++; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f6dafec..62a750a 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err, struct pcpu_sw_netstats __percpu *stats) { if (err > 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += err; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else if (err < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c9149cc..4bd7508 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -618,6 +618,8 @@ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); + int (*clone)(struct nft_expr *dst, + const struct nft_expr *src); unsigned int size; int (*init)(const struct nft_ctx *ctx, @@ -660,10 +662,20 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); -static inline void nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { + int err; + __module_get(src->ops->type->owner); - memcpy(dst, src, src->ops->size); + if (src->ops->clone) { + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; + } else { + memcpy(dst, src, src->ops->size); + } + return 0; } /** diff --git a/include/net/sock.h b/include/net/sock.h index bbf7c2c..7f89e4b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2226,6 +2226,31 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/** + * sk_state_load - read sk->sk_state for lockless contexts + * @sk: socket pointer + * + * Paired with sk_state_store(). Used in places we do not hold socket lock : + * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... + */ +static inline int sk_state_load(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_state); +} + +/** + * sk_state_store - update sk->sk_state + * @sk: socket pointer + * @newstate: new state + * + * Paired with sk_state_load(). Should be used in contexts where + * state change might impact lockless readers. + */ +static inline void sk_state_store(struct sock *sk, int newstate) +{ + smp_store_release(&sk->sk_state, newstate); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bc865e2..1d22ce9 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -323,7 +323,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb, struct net_device *filter_dev, int idx) { - return -EOPNOTSUPP; + return idx; } static inline void switchdev_port_fwd_mark_set(struct net_device *dev, diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 496b275..e2ed698 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -30,7 +30,9 @@ bool vlan_do_receive(struct sk_buff **skbp) skb->pkt_type = PACKET_HOST; } - if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) { + if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR) && + !netif_is_macvlan_port(vlan_dev) && + !netif_is_bridge_port(vlan_dev)) { unsigned int offset = skb->data - skb_mac_header(skb); /* diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index f7e8dee..5f3f645 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -48,7 +48,7 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) p->state = state; err = switchdev_port_attr_set(p->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index fa53d7a..5396ff08 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -50,7 +50,7 @@ void br_init_port(struct net_bridge_port *p) p->config_pending = 0; err = switchdev_port_attr_set(p->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) netdev_err(p->dev, "failed to set HW ageing time\n"); } diff --git a/net/core/dev.c b/net/core/dev.c index ab9b8d0..ae00b89 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2403,17 +2403,20 @@ static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features = 0; struct net_device *dev = skb->dev; - const char *driver = ""; + const char *name = ""; if (!net_ratelimit()) return; - if (dev && dev->dev.parent) - driver = dev_driver_string(dev->dev.parent); - + if (dev) { + if (dev->dev.parent) + name = dev_driver_string(dev->dev.parent); + else + name = netdev_name(dev); + } WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " "gso_type=%d ip_summed=%d\n", - driver, dev ? &dev->features : &null_features, + name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features, skb->len, skb->data_len, skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type, skb->ip_summed); @@ -6426,11 +6429,16 @@ int __netdev_update_features(struct net_device *dev) if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); + else + err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); + /* return non-0 since some features might have changed and + * it's better to fire a spurious notification than miss it + */ return -1; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 1aa8437..e6af42d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -857,7 +857,7 @@ static void neigh_probe(struct neighbour *neigh) struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) - skb = skb_copy(skb, GFP_ATOMIC); + skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 504bd17..34ba7a0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1045,15 +1045,156 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb, + struct net_device *dev) +{ + const struct rtnl_link_stats64 *stats; + struct rtnl_link_stats64 temp; + struct nlattr *attr; + + stats = dev_get_stats(dev, &temp); + + attr = nla_reserve(skb, IFLA_STATS, + sizeof(struct rtnl_link_stats)); + if (!attr) + return -EMSGSIZE; + + copy_rtnl_link_stats(nla_data(attr), stats); + + attr = nla_reserve(skb, IFLA_STATS64, + sizeof(struct rtnl_link_stats64)); + if (!attr) + return -EMSGSIZE; + + copy_rtnl_link_stats64(nla_data(attr), stats); + + return 0; +} + +static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, + struct net_device *dev, + int vfs_num, + struct nlattr *vfinfo) +{ + struct ifla_vf_rss_query_en vf_rss_query_en; + struct ifla_vf_link_state vf_linkstate; + struct ifla_vf_spoofchk vf_spoofchk; + struct ifla_vf_tx_rate vf_tx_rate; + struct ifla_vf_stats vf_stats; + struct ifla_vf_trust vf_trust; + struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; + struct nlattr *vf, *vfstats; + struct ifla_vf_mac vf_mac; + struct ifla_vf_info ivi; + + /* Not all SR-IOV capable drivers support the + * spoofcheck and "RSS query enable" query. Preset to + * -1 so the user space tool can detect that the driver + * didn't report anything. + */ + ivi.spoofchk = -1; + ivi.rss_query_en = -1; + ivi.trusted = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); + /* The default value for VF link state is "auto" + * IFLA_VF_LINK_STATE_AUTO which equals zero + */ + ivi.linkstate = 0; + if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi)) + return 0; + + vf_mac.vf = + vf_vlan.vf = + vf_rate.vf = + vf_tx_rate.vf = + vf_spoofchk.vf = + vf_linkstate.vf = + vf_rss_query_en.vf = + vf_trust.vf = ivi.vf; + + memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); + vf_vlan.vlan = ivi.vlan; + vf_vlan.qos = ivi.qos; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; + vf_spoofchk.setting = ivi.spoofchk; + vf_linkstate.link_state = ivi.linkstate; + vf_rss_query_en.setting = ivi.rss_query_en; + vf_trust.setting = ivi.trusted; + vf = nla_nest_start(skb, IFLA_VF_INFO); + if (!vf) { + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; + } + if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || + nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || + nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), + &vf_tx_rate) || + nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), + &vf_spoofchk) || + nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), + &vf_linkstate) || + nla_put(skb, IFLA_VF_RSS_QUERY_EN, + sizeof(vf_rss_query_en), + &vf_rss_query_en) || + nla_put(skb, IFLA_VF_TRUST, + sizeof(vf_trust), &vf_trust)) + return -EMSGSIZE; + memset(&vf_stats, 0, sizeof(vf_stats)); + if (dev->netdev_ops->ndo_get_vf_stats) + dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, + &vf_stats); + vfstats = nla_nest_start(skb, IFLA_VF_STATS); + if (!vfstats) { + nla_nest_cancel(skb, vf); + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; + } + if (nla_put_u64(skb, IFLA_VF_STATS_RX_PACKETS, + vf_stats.rx_packets) || + nla_put_u64(skb, IFLA_VF_STATS_TX_PACKETS, + vf_stats.tx_packets) || + nla_put_u64(skb, IFLA_VF_STATS_RX_BYTES, + vf_stats.rx_bytes) || + nla_put_u64(skb, IFLA_VF_STATS_TX_BYTES, + vf_stats.tx_bytes) || + nla_put_u64(skb, IFLA_VF_STATS_BROADCAST, + vf_stats.broadcast) || + nla_put_u64(skb, IFLA_VF_STATS_MULTICAST, + vf_stats.multicast)) + return -EMSGSIZE; + nla_nest_end(skb, vfstats); + nla_nest_end(skb, vf); + return 0; +} + +static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) +{ + struct rtnl_link_ifmap map = { + .mem_start = dev->mem_start, + .mem_end = dev->mem_end, + .base_addr = dev->base_addr, + .irq = dev->irq, + .dma = dev->dma, + .port = dev->if_port, + }; + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - struct rtnl_link_stats64 temp; - const struct rtnl_link_stats64 *stats; - struct nlattr *attr, *af_spec; + struct nlattr *af_spec; struct rtnl_af_ops *af_ops; struct net_device *upper_dev = netdev_master_upper_dev_get(dev); @@ -1096,18 +1237,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; - if (1) { - struct rtnl_link_ifmap map = { - .mem_start = dev->mem_start, - .mem_end = dev->mem_end, - .base_addr = dev->base_addr, - .irq = dev->irq, - .dma = dev->dma, - .port = dev->if_port, - }; - if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) - goto nla_put_failure; - } + if (rtnl_fill_link_ifmap(skb, dev)) + goto nla_put_failure; if (dev->addr_len) { if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) || @@ -1124,128 +1255,27 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_phys_switch_id_fill(skb, dev)) goto nla_put_failure; - attr = nla_reserve(skb, IFLA_STATS, - sizeof(struct rtnl_link_stats)); - if (attr == NULL) - goto nla_put_failure; - - stats = dev_get_stats(dev, &temp); - copy_rtnl_link_stats(nla_data(attr), stats); - - attr = nla_reserve(skb, IFLA_STATS64, - sizeof(struct rtnl_link_stats64)); - if (attr == NULL) + if (rtnl_fill_stats(skb, dev)) goto nla_put_failure; - copy_rtnl_link_stats64(nla_data(attr), stats); if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) goto nla_put_failure; - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent - && (ext_filter_mask & RTEXT_FILTER_VF)) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent && + ext_filter_mask & RTEXT_FILTER_VF) { int i; - - struct nlattr *vfinfo, *vf, *vfstats; + struct nlattr *vfinfo; int num_vfs = dev_num_vf(dev->dev.parent); vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); if (!vfinfo) goto nla_put_failure; for (i = 0; i < num_vfs; i++) { - struct ifla_vf_info ivi; - struct ifla_vf_mac vf_mac; - struct ifla_vf_vlan vf_vlan; - struct ifla_vf_rate vf_rate; - struct ifla_vf_tx_rate vf_tx_rate; - struct ifla_vf_spoofchk vf_spoofchk; - struct ifla_vf_link_state vf_linkstate; - struct ifla_vf_rss_query_en vf_rss_query_en; - struct ifla_vf_stats vf_stats; - struct ifla_vf_trust vf_trust; - - /* - * Not all SR-IOV capable drivers support the - * spoofcheck and "RSS query enable" query. Preset to - * -1 so the user space tool can detect that the driver - * didn't report anything. - */ - ivi.spoofchk = -1; - ivi.rss_query_en = -1; - ivi.trusted = -1; - memset(ivi.mac, 0, sizeof(ivi.mac)); - /* The default value for VF link state is "auto" - * IFLA_VF_LINK_STATE_AUTO which equals zero - */ - ivi.linkstate = 0; - if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) - break; - vf_mac.vf = - vf_vlan.vf = - vf_rate.vf = - vf_tx_rate.vf = - vf_spoofchk.vf = - vf_linkstate.vf = - vf_rss_query_en.vf = - vf_trust.vf = ivi.vf; - - memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); - vf_vlan.vlan = ivi.vlan; - vf_vlan.qos = ivi.qos; - vf_tx_rate.rate = ivi.max_tx_rate; - vf_rate.min_tx_rate = ivi.min_tx_rate; - vf_rate.max_tx_rate = ivi.max_tx_rate; - vf_spoofchk.setting = ivi.spoofchk; - vf_linkstate.link_state = ivi.linkstate; - vf_rss_query_en.setting = ivi.rss_query_en; - vf_trust.setting = ivi.trusted; - vf = nla_nest_start(skb, IFLA_VF_INFO); - if (!vf) { - nla_nest_cancel(skb, vfinfo); - goto nla_put_failure; - } - if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || - nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || - nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), - &vf_rate) || - nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), - &vf_tx_rate) || - nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), - &vf_spoofchk) || - nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), - &vf_linkstate) || - nla_put(skb, IFLA_VF_RSS_QUERY_EN, - sizeof(vf_rss_query_en), - &vf_rss_query_en) || - nla_put(skb, IFLA_VF_TRUST, - sizeof(vf_trust), &vf_trust)) + if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) goto nla_put_failure; - memset(&vf_stats, 0, sizeof(vf_stats)); - if (dev->netdev_ops->ndo_get_vf_stats) - dev->netdev_ops->ndo_get_vf_stats(dev, i, - &vf_stats); - vfstats = nla_nest_start(skb, IFLA_VF_STATS); - if (!vfstats) { - nla_nest_cancel(skb, vf); - nla_nest_cancel(skb, vfinfo); - goto nla_put_failure; - } - if (nla_put_u64(skb, IFLA_VF_STATS_RX_PACKETS, - vf_stats.rx_packets) || - nla_put_u64(skb, IFLA_VF_STATS_TX_PACKETS, - vf_stats.tx_packets) || - nla_put_u64(skb, IFLA_VF_STATS_RX_BYTES, - vf_stats.rx_bytes) || - nla_put_u64(skb, IFLA_VF_STATS_TX_BYTES, - vf_stats.tx_bytes) || - nla_put_u64(skb, IFLA_VF_STATS_BROADCAST, - vf_stats.broadcast) || - nla_put_u64(skb, IFLA_VF_STATS_MULTICAST, - vf_stats.multicast)) - goto nla_put_failure; - nla_nest_end(skb, vfstats); - nla_nest_end(skb, vf); } + nla_nest_end(skb, vfinfo); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index aa41e6d..152b9c7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4268,7 +4268,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len, + 2 * ETH_ALEN); skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 1feb15f..46b9c88 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -563,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data) int max_retries, thresh; u8 defer_accept; - if (sk_listener->sk_state != TCP_LISTEN) + if (sk_state_load(sk_listener) != TCP_LISTEN) goto drop; max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; @@ -749,7 +749,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog) * It is OK, because this socket enters to hash table only * after validation is complete. */ - sk->sk_state = TCP_LISTEN; + sk_state_store(sk, TCP_LISTEN); if (!sk->sk_prot->get_port(sk, inet->inet_num)) { inet->inet_sport = htons(inet->inet_num); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 657d230..b3ca21b 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -45,7 +45,7 @@ static void pptp_nat_expected(struct nf_conn *ct, struct net *net = nf_ct_net(ct); const struct nf_conn *master = ct->master; struct nf_conntrack_expect *other_exp; - struct nf_conntrack_tuple t; + struct nf_conntrack_tuple t = {}; const struct nf_ct_pptp_master *ct_pptp_info; const struct nf_nat_pptp *nat_pptp_info; struct nf_nat_range range; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8c0d0bd..63e5be0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -406,10 +406,12 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, ip_select_ident(net, skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + skb->transport_header += iphlen; + if (iph->protocol == IPPROTO_ICMP && + length >= iphlen + sizeof(struct icmphdr)) + icmp_out_count(net, ((struct icmphdr *) + skb_transport_header(skb))->type); } - if (iph->protocol == IPPROTO_ICMP) - icmp_out_count(net, ((struct icmphdr *) - skb_transport_header(skb))->type); err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0cfa7c0..c172877 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -451,11 +451,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + int state; sock_rps_record_flow(sk); sock_poll_wait(file, sk_sleep(sk), wait); - if (sk->sk_state == TCP_LISTEN) + + state = sk_state_load(sk); + if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -492,14 +495,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) + if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= POLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLIN | POLLRDNORM | POLLRDHUP; /* Connected or passive Fast Open socket? */ - if (sk->sk_state != TCP_SYN_SENT && - (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) { + if (state != TCP_SYN_SENT && + (state != TCP_SYN_RECV || tp->fastopen_rsk)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -507,9 +510,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) tp->urg_data) target++; - /* Potential race condition. If read of tp below will - * escape above sk->sk_state, we can be illegally awaken - * in SYN_* states. */ if (tp->rcv_nxt - tp->copied_seq >= target) mask |= POLLIN | POLLRDNORM; @@ -1934,7 +1934,7 @@ void tcp_set_state(struct sock *sk, int state) /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ - sk->sk_state = state; + sk_state_store(sk, state); #ifdef STATE_TRACE SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]); @@ -2644,7 +2644,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) if (sk->sk_type != SOCK_STREAM) return; - info->tcpi_state = sk->sk_state; + info->tcpi_state = sk_state_load(sk); + info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; @@ -2672,7 +2673,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; - if (sk->sk_state == TCP_LISTEN) { + if (info->tcpi_state == TCP_LISTEN) { info->tcpi_unacked = sk->sk_ack_backlog; info->tcpi_sacked = sk->sk_max_ack_backlog; } else { diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 479f349..b316040 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -21,7 +21,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, { struct tcp_info *info = _info; - if (sk->sk_state == TCP_LISTEN) { + if (sk_state_load(sk) == TCP_LISTEN) { r->idiag_rqueue = sk->sk_ack_backlog; r->idiag_wqueue = sk->sk_max_ack_backlog; } else if (sk->sk_type == SOCK_STREAM) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 950e28c..ba09016 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2158,6 +2158,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); int rx_queue; + int state; if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || @@ -2175,17 +2176,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) timer_expires = jiffies; } - if (sk->sk_state == TCP_LISTEN) + state = sk_state_load(sk); + if (state == TCP_LISTEN) rx_queue = sk->sk_ack_backlog; else - /* - * because we dont lock socket, we might find a transient negative value + /* Because we don't lock the socket, + * we might find a transient negative value. */ rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", - i, src, srcp, dest, destp, sk->sk_state, + i, src, srcp, dest, destp, state, tp->write_seq - tp->snd_una, rx_queue, timer_active, @@ -2199,8 +2201,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - sk->sk_state == TCP_LISTEN ? - (fastopenq ? fastopenq->max_qlen : 0) : + state == TCP_LISTEN ? + fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 124338a..5ee56d0 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1651,7 +1651,6 @@ out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } @@ -2015,7 +2014,6 @@ out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c8bc9b4..6f01fe1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -404,6 +404,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, } } +static bool __rt6_check_expired(const struct rt6_info *rt) +{ + if (rt->rt6i_flags & RTF_EXPIRES) + return time_after(jiffies, rt->dst.expires); + else + return false; +} + static bool rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) { @@ -1252,7 +1260,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) { - if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + if (!__rt6_check_expired(rt) && + rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && rt6_check((struct rt6_info *)(rt->dst.from), cookie)) return &rt->dst; else @@ -1272,7 +1281,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt6_dst_from_metrics_check(rt); - if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE)) + if (rt->rt6i_flags & RTF_PCPU || + (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from)) return rt6_dst_from_check(rt, cookie); else return rt6_check(rt, cookie); @@ -1322,6 +1332,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } +static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) +{ + return !(rt->rt6i_flags & RTF_CACHE) && + (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node); +} + static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu) { @@ -1335,7 +1351,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (mtu >= dst_mtu(dst)) return; - if (rt6->rt6i_flags & RTF_CACHE) { + if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); } else { const struct in6_addr *daddr, *saddr; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5baa8e7..c5429a6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1690,6 +1690,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; + int rx_queue; + int state; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; @@ -1710,6 +1712,15 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) timer_expires = jiffies; } + state = sk_state_load(sp); + if (state == TCP_LISTEN) + rx_queue = sp->sk_ack_backlog; + else + /* Because we don't lock the socket, + * we might find a transient negative value. + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", @@ -1718,9 +1729,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - tp->write_seq-tp->snd_una, - (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), + state, + tp->write_seq - tp->snd_una, + rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, @@ -1732,7 +1743,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - sp->sk_state == TCP_LISTEN ? + state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e22349e..4692782 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -869,7 +869,7 @@ config NETFILTER_XT_TARGET_TEE depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 - select NF_DUP_IPV6 if IP6_NF_IPTABLES + select NF_DUP_IPV6 if IP6_NF_IPTABLES != n ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. @@ -882,7 +882,7 @@ config NETFILTER_XT_TARGET_TPROXY depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 - select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n help This option adds a `TPROXY' target, which is somewhat similar to REDIRECT. It can only be used in the mangle table and is useful @@ -1375,7 +1375,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on IPV6 || IPV6=n depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n select NF_DEFRAG_IPV4 - select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n help This option adds a `socket' match, which can be used to match packets for which a TCP or UDP socket lookup finds a valid socket. diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index d05e759..b0bc475 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -33,7 +33,7 @@ #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype MTYPE -#define get_ext(set, map, id) ((map)->extensions + (set)->dsize * (id)) +#define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) static void mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) @@ -67,12 +67,9 @@ mtype_destroy(struct ip_set *set) del_timer_sync(&map->gc); ip_set_free(map->members); - if (set->dsize) { - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set); - ip_set_free(map->extensions); - } - kfree(map); + if (set->dsize && set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set); + ip_set_free(map); set->data = NULL; } @@ -92,16 +89,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) { const struct mtype *map = set->data; struct nlattr *nested; + size_t memsize = sizeof(*map) + map->memsize; nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (mtype_do_head(skb, map) || nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || - nla_put_net32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) + - map->memsize + - set->dsize * map->elements))) + nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 64a5643..4783eff 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -41,7 +41,6 @@ MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ struct bitmap_ip { void *members; /* the set members */ - void *extensions; /* data extensions */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -49,6 +48,8 @@ struct bitmap_ip { size_t memsize; /* members size */ u8 netmask; /* subnet netmask */ struct timer_list gc; /* garbage collection */ + unsigned char extensions[0] /* data extensions */ + __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ @@ -224,13 +225,6 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, map->members = ip_set_alloc(map->memsize); if (!map->members) return false; - if (set->dsize) { - map->extensions = ip_set_alloc(set->dsize * elements); - if (!map->extensions) { - kfree(map->members); - return false; - } - } map->first_ip = first_ip; map->last_ip = last_ip; map->elements = elements; @@ -316,13 +310,13 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], pr_debug("hosts %u, elements %llu\n", hosts, (unsigned long long)elements); - map = kzalloc(sizeof(*map), GFP_KERNEL); + set->dsize = ip_set_elem_len(set, tb, 0, 0); + map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; map->memsize = bitmap_bytes(0, elements - 1); set->variant = &bitmap_ip; - set->dsize = ip_set_elem_len(set, tb, 0); if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { kfree(map); diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 1430535..29dde20 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -47,24 +47,26 @@ enum { /* Type structure */ struct bitmap_ipmac { void *members; /* the set members */ - void *extensions; /* MAC + data extensions */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collector */ + unsigned char extensions[0] /* MAC + data extensions */ + __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ struct bitmap_ipmac_adt_elem { + unsigned char ether[ETH_ALEN] __aligned(2); u16 id; - unsigned char *ether; + u16 add_mac; }; struct bitmap_ipmac_elem { unsigned char ether[ETH_ALEN]; unsigned char filled; -} __attribute__ ((aligned)); +} __aligned(__alignof__(u64)); static inline u32 ip_to_id(const struct bitmap_ipmac *m, u32 ip) @@ -72,11 +74,11 @@ ip_to_id(const struct bitmap_ipmac *m, u32 ip) return ip - m->first_ip; } -static inline struct bitmap_ipmac_elem * -get_elem(void *extensions, u16 id, size_t dsize) -{ - return (struct bitmap_ipmac_elem *)(extensions + id * dsize); -} +#define get_elem(extensions, id, dsize) \ + (struct bitmap_ipmac_elem *)(extensions + (id) * (dsize)) + +#define get_const_elem(extensions, id, dsize) \ + (const struct bitmap_ipmac_elem *)(extensions + (id) * (dsize)) /* Common functions */ @@ -88,10 +90,9 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e, if (!test_bit(e->id, map->members)) return 0; - elem = get_elem(map->extensions, e->id, dsize); - if (elem->filled == MAC_FILLED) - return !e->ether || - ether_addr_equal(e->ether, elem->ether); + elem = get_const_elem(map->extensions, e->id, dsize); + if (e->add_mac && elem->filled == MAC_FILLED) + return ether_addr_equal(e->ether, elem->ether); /* Trigger kernel to fill out the ethernet address */ return -EAGAIN; } @@ -103,7 +104,7 @@ bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize) if (!test_bit(id, map->members)) return 0; - elem = get_elem(map->extensions, id, dsize); + elem = get_const_elem(map->extensions, id, dsize); /* Timer not started for the incomplete elements */ return elem->filled == MAC_FILLED; } @@ -133,7 +134,7 @@ bitmap_ipmac_add_timeout(unsigned long *timeout, * and we can reuse it later when MAC is filled out, * possibly by the kernel */ - if (e->ether) + if (e->add_mac) ip_set_timeout_set(timeout, t); else *timeout = t; @@ -150,7 +151,7 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, elem = get_elem(map->extensions, e->id, dsize); if (test_bit(e->id, map->members)) { if (elem->filled == MAC_FILLED) { - if (e->ether && + if (e->add_mac && (flags & IPSET_FLAG_EXIST) && !ether_addr_equal(e->ether, elem->ether)) { /* memcpy isn't atomic */ @@ -159,7 +160,7 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, ether_addr_copy(elem->ether, e->ether); } return IPSET_ADD_FAILED; - } else if (!e->ether) + } else if (!e->add_mac) /* Already added without ethernet address */ return IPSET_ADD_FAILED; /* Fill the MAC address and trigger the timer activation */ @@ -168,7 +169,7 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, ether_addr_copy(elem->ether, e->ether); elem->filled = MAC_FILLED; return IPSET_ADD_START_STORED_TIMEOUT; - } else if (e->ether) { + } else if (e->add_mac) { /* We can store MAC too */ ether_addr_copy(elem->ether, e->ether); elem->filled = MAC_FILLED; @@ -191,7 +192,7 @@ bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map, u32 id, size_t dsize) { const struct bitmap_ipmac_elem *elem = - get_elem(map->extensions, id, dsize); + get_const_elem(map->extensions, id, dsize); return nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip + id)) || @@ -213,7 +214,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, { struct bitmap_ipmac *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct bitmap_ipmac_adt_elem e = { .id = 0 }; + struct bitmap_ipmac_adt_elem e = { .id = 0, .add_mac = 1 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); u32 ip; @@ -231,7 +232,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, return -EINVAL; e.id = ip_to_id(map, ip); - e.ether = eth_hdr(skb)->h_source; + memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -265,11 +266,10 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_BITMAP_RANGE; e.id = ip_to_id(map, ip); - if (tb[IPSET_ATTR_ETHER]) - e.ether = nla_data(tb[IPSET_ATTR_ETHER]); - else - e.ether = NULL; - + if (tb[IPSET_ATTR_ETHER]) { + memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN); + e.add_mac = 1; + } ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; @@ -300,13 +300,6 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, map->members = ip_set_alloc(map->memsize); if (!map->members) return false; - if (set->dsize) { - map->extensions = ip_set_alloc(set->dsize * elements); - if (!map->extensions) { - kfree(map->members); - return false; - } - } map->first_ip = first_ip; map->last_ip = last_ip; map->elements = elements; @@ -361,14 +354,15 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; - map = kzalloc(sizeof(*map), GFP_KERNEL); + set->dsize = ip_set_elem_len(set, tb, + sizeof(struct bitmap_ipmac_elem), + __alignof__(struct bitmap_ipmac_elem)); + map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; map->memsize = bitmap_bytes(0, elements - 1); set->variant = &bitmap_ipmac; - set->dsize = ip_set_elem_len(set, tb, - sizeof(struct bitmap_ipmac_elem)); if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { kfree(map); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 5338ccd..7f0c733 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -35,12 +35,13 @@ MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ struct bitmap_port { void *members; /* the set members */ - void *extensions; /* data extensions */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collection */ + unsigned char extensions[0] /* data extensions */ + __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ @@ -209,13 +210,6 @@ init_map_port(struct ip_set *set, struct bitmap_port *map, map->members = ip_set_alloc(map->memsize); if (!map->members) return false; - if (set->dsize) { - map->extensions = ip_set_alloc(set->dsize * map->elements); - if (!map->extensions) { - kfree(map->members); - return false; - } - } map->first_port = first_port; map->last_port = last_port; set->timeout = IPSET_NO_TIMEOUT; @@ -232,6 +226,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], { struct bitmap_port *map; u16 first_port, last_port; + u32 elements; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) || @@ -248,14 +243,15 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], last_port = tmp; } - map = kzalloc(sizeof(*map), GFP_KERNEL); + elements = last_port - first_port + 1; + set->dsize = ip_set_elem_len(set, tb, 0, 0); + map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; - map->elements = last_port - first_port + 1; + map->elements = elements; map->memsize = bitmap_bytes(0, map->elements); set->variant = &bitmap_port; - set->dsize = ip_set_elem_len(set, tb, 0); if (!init_map_port(set, map, first_port, last_port)) { kfree(map); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69ab9c26..54f3d7c 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -364,25 +364,27 @@ add_extension(enum ip_set_ext_id id, u32 flags, struct nlattr *tb[]) } size_t -ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) +ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, + size_t align) { enum ip_set_ext_id id; - size_t offset = len; u32 cadt_flags = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_WITH_FORCEADD) set->flags |= IPSET_CREATE_FLAG_FORCEADD; + if (!align) + align = 1; for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; - offset = ALIGN(offset, ip_set_extensions[id].align); - set->offset[id] = offset; + len = ALIGN(len, ip_set_extensions[id].align); + set->offset[id] = len; set->extensions |= ip_set_extensions[id].type; - offset += ip_set_extensions[id].len; + len += ip_set_extensions[id].len; } - return offset; + return ALIGN(len, align); } EXPORT_SYMBOL_GPL(ip_set_elem_len); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 691b54f..e5336ab 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -72,8 +72,9 @@ struct hbucket { DECLARE_BITMAP(used, AHASH_MAX_TUNED); u8 size; /* size of the array */ u8 pos; /* position of the first free entry */ - unsigned char value[0]; /* the array of the values */ -} __attribute__ ((aligned)); + unsigned char value[0] /* the array of the values */ + __aligned(__alignof__(u64)); +}; /* The hash table: the table size stored here in order to make resizing easy */ struct htable { @@ -475,7 +476,7 @@ static void mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) { struct htable *t; - struct hbucket *n; + struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; #ifdef IP_SET_HASH_WITH_NETS @@ -510,9 +511,14 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) } } if (d >= AHASH_INIT_SIZE) { - struct hbucket *tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + if (d >= n->size) { + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + continue; + } + tmp = kzalloc(sizeof(*tmp) + + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) /* Still try to delete expired elements */ continue; @@ -522,7 +528,7 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) continue; data = ahash_data(n, j, dsize); memcpy(tmp->value + d * dsize, data, dsize); - set_bit(j, tmp->used); + set_bit(d, tmp->used); d++; } tmp->pos = d; @@ -1323,12 +1329,14 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif set->variant = &IPSET_TOKEN(HTYPE, 4_variant); set->dsize = ip_set_elem_len(set, tb, - sizeof(struct IPSET_TOKEN(HTYPE, 4_elem))); + sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)), + __alignof__(struct IPSET_TOKEN(HTYPE, 4_elem))); #ifndef IP_SET_PROTO_UNDEF } else { set->variant = &IPSET_TOKEN(HTYPE, 6_variant); set->dsize = ip_set_elem_len(set, tb, - sizeof(struct IPSET_TOKEN(HTYPE, 6_elem))); + sizeof(struct IPSET_TOKEN(HTYPE, 6_elem)), + __alignof__(struct IPSET_TOKEN(HTYPE, 6_elem))); } #endif if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a30ce6..bbede95 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -31,7 +31,7 @@ struct set_elem { struct rcu_head rcu; struct list_head list; ip_set_id_t id; -}; +} __aligned(__alignof__(u64)); struct set_adt_elem { ip_set_id_t id; @@ -618,7 +618,8 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], size = IP_SET_LIST_MIN_SIZE; set->variant = &set_variant; - set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem)); + set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), + __alignof__(struct set_elem)); if (!init_list_set(net, set, size)) return -ENOMEM; if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 1e24fff..f57b4dc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1176,6 +1176,7 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + struct sock *sk; EnterFunction(11); @@ -1183,13 +1184,12 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in if (skb->ipvs_property) return NF_ACCEPT; + sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ - if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && + if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - struct sock *sk = skb->sk; - struct inet_sock *inet = inet_sk(skb->sk); - if (inet && sk->sk_family == PF_INET && inet->nodefrag) + if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } @@ -1681,6 +1681,7 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int struct ip_vs_conn *cp; int ret, pkts; int conn_reuse_mode; + struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -1708,12 +1709,11 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ - if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && + sk = skb_to_full_sk(skb); + if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - struct sock *sk = skb->sk; - struct inet_sock *inet = inet_sk(skb->sk); - if (inet && sk->sk_family == PF_INET && inet->nodefrag) + if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 06eb48f..740cce4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -825,7 +825,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, struct net *net = sock_net(ctnl); struct nfnl_log_net *log = nfnl_log_pernet(net); int ret = 0; - u16 flags; + u16 flags = 0; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = nfmsg->nfgen_family; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 1067fb4..c7808fc 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -47,27 +47,34 @@ static void nft_counter_eval(const struct nft_expr *expr, local_bh_enable(); } -static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +static void nft_counter_fetch(const struct nft_counter_percpu __percpu *counter, + struct nft_counter *total) { - struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - struct nft_counter_percpu *cpu_stats; - struct nft_counter total; + const struct nft_counter_percpu *cpu_stats; u64 bytes, packets; unsigned int seq; int cpu; - memset(&total, 0, sizeof(total)); + memset(total, 0, sizeof(*total)); for_each_possible_cpu(cpu) { - cpu_stats = per_cpu_ptr(priv->counter, cpu); + cpu_stats = per_cpu_ptr(counter, cpu); do { seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); bytes = cpu_stats->counter.bytes; packets = cpu_stats->counter.packets; } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); - total.packets += packets; - total.bytes += bytes; + total->packets += packets; + total->bytes += bytes; } +} + +static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct nft_counter total; + + nft_counter_fetch(priv->counter, &total); if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes)) || nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.packets))) @@ -118,6 +125,31 @@ static void nft_counter_destroy(const struct nft_ctx *ctx, free_percpu(priv->counter); } +static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(src); + struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); + struct nft_counter_percpu __percpu *cpu_stats; + struct nft_counter_percpu *this_cpu; + struct nft_counter total; + + nft_counter_fetch(priv->counter, &total); + + cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu, + GFP_ATOMIC); + if (cpu_stats == NULL) + return ENOMEM; + + preempt_disable(); + this_cpu = this_cpu_ptr(cpu_stats); + this_cpu->counter.packets = total.packets; + this_cpu->counter.bytes = total.bytes; + preempt_enable(); + + priv_clone->counter = cpu_stats; + return 0; +} + static struct nft_expr_type nft_counter_type; static const struct nft_expr_ops nft_counter_ops = { .type = &nft_counter_type, @@ -126,6 +158,7 @@ static const struct nft_expr_ops nft_counter_ops = { .init = nft_counter_init, .destroy = nft_counter_destroy, .dump = nft_counter_dump, + .clone = nft_counter_clone, }; static struct nft_expr_type nft_counter_type __read_mostly = { diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 513a8ef..9dec3bd 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -50,8 +50,9 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, } ext = nft_set_elem_ext(set, elem); - if (priv->expr != NULL) - nft_expr_clone(nft_set_ext_expr(ext), priv->expr); + if (priv->expr != NULL && + nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0) + return NULL; return elem; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index af399ca..1cf928f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1741,6 +1741,20 @@ static void fanout_release(struct sock *sk) kfree_rcu(po->rollover, rcu); } +static bool packet_extra_vlan_len_allowed(const struct net_device *dev, + struct sk_buff *skb) +{ + /* Earlier code assumed this would be a VLAN pkt, double-check + * this now that we have the actual packet in hand. We can only + * do this check on Ethernet devices. + */ + if (unlikely(dev->type != ARPHRD_ETHER)) + return false; + + skb_reset_mac_header(skb); + return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); +} + static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; @@ -1902,18 +1916,10 @@ retry: goto retry; } - if (len > (dev->mtu + dev->hard_header_len + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_unlock; - } + if (len > (dev->mtu + dev->hard_header_len + extra_len) && + !packet_extra_vlan_len_allowed(dev, skb)) { + err = -EMSGSIZE; + goto out_unlock; } skb->protocol = proto; @@ -2332,6 +2338,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len) return false; } +static void tpacket_set_protocol(const struct net_device *dev, + struct sk_buff *skb) +{ + if (dev->type == ARPHRD_ETHER) { + skb_reset_mac_header(skb); + skb->protocol = eth_hdr(skb)->h_proto; + } +} + static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, int size_max, __be16 proto, unsigned char *addr, int hlen) @@ -2368,8 +2383,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb_reserve(skb, hlen); skb_reset_network_header(skb); - if (!packet_use_direct_xmit(po)) - skb_probe_transport_header(skb, 0); if (unlikely(po->tp_tx_has_off)) { int off_min, off_max, off; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); @@ -2415,6 +2428,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, dev->hard_header_len); if (unlikely(err)) return err; + if (!skb->protocol) + tpacket_set_protocol(dev, skb); data += dev->hard_header_len; to_write -= dev->hard_header_len; @@ -2449,6 +2464,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, len = ((to_write > len_max) ? len_max : to_write); } + skb_probe_transport_header(skb, 0); + return tp_len; } @@ -2493,12 +2510,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - reserve = dev->hard_header_len + VLAN_HLEN; + if (po->sk.sk_socket->type == SOCK_RAW) + reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); - if (size_max > dev->mtu + reserve) - size_max = dev->mtu + reserve; + if (size_max > dev->mtu + reserve + VLAN_HLEN) + size_max = dev->mtu + reserve + VLAN_HLEN; do { ph = packet_current_frame(po, &po->tx_ring, @@ -2525,18 +2543,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); if (likely(tp_len >= 0) && - tp_len > dev->mtu + dev->hard_header_len) { - struct ethhdr *ehdr; - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ + tp_len > dev->mtu + reserve && + !packet_extra_vlan_len_allowed(dev, skb)) + tp_len = -EMSGSIZE; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) - tp_len = -EMSGSIZE; - } if (unlikely(tp_len < 0)) { if (po->tp_loss) { __packet_set_status(po, ph, @@ -2765,18 +2775,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); - if (!gso_type && (len > dev->mtu + reserve + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_free; - } + if (!gso_type && (len > dev->mtu + reserve + extra_len) && + !packet_extra_vlan_len_allowed(dev, skb)) { + err = -EMSGSIZE; + goto out_free; } skb->protocol = proto; @@ -2807,8 +2809,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) len += vnet_hdr_len; } - if (!packet_use_direct_xmit(po)) - skb_probe_transport_header(skb, reserve); + skb_probe_transport_header(skb, reserve); + if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -4107,7 +4109,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; - if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) + if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; if (po->tp_version >= TPACKET_V3 && (int)(req->tp_block_size - @@ -4119,8 +4121,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; - rb->frames_per_block = req->tp_block_size/req->tp_frame_size; - if (unlikely(rb->frames_per_block <= 0)) + rb->frames_per_block = req->tp_block_size / req->tp_frame_size; + if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 4f15b7d..1543e39 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, if (!has_sha1) return -EINVAL; - memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0], - hmacs->shmac_num_idents * sizeof(__u16)); + for (i = 0; i < hmacs->shmac_num_idents; i++) + ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]); ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) + hmacs->shmac_num_idents * sizeof(__u16)); return 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index aaa0b58..955ec15 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -441,6 +441,7 @@ static void unix_release_sock(struct sock *sk, int embrion) if (state == TCP_LISTEN) unix_release_sock(skb->sk, 1); /* passed fds are erased in the kfree_skb hook */ + UNIXCB(skb).consumed = skb->len; kfree_skb(skb); } @@ -1799,6 +1800,7 @@ alloc_skb: * this - does no harm */ consume_skb(newskb); + newskb = NULL; } if (skb_append_pagefrags(skb, page, offset, size)) { @@ -1811,8 +1813,11 @@ alloc_skb: skb->truesize += size; atomic_add(size, &sk->sk_wmem_alloc); - if (newskb) + if (newskb) { + spin_lock(&other->sk_receive_queue.lock); __skb_queue_tail(&other->sk_receive_queue, newskb); + spin_unlock(&other->sk_receive_queue.lock); + } unix_state_unlock(other); mutex_unlock(&unix_sk(other)->readlock); @@ -2072,6 +2077,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) do { int chunk; + bool drop_skb; struct sk_buff *skb, *last; unix_state_lock(sk); @@ -2152,7 +2158,11 @@ unlock: } chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size); + skb_get(skb); chunk = state->recv_actor(skb, skip, chunk, state); + drop_skb = !unix_skb_len(skb); + /* skb is only safe to use if !drop_skb */ + consume_skb(skb); if (chunk < 0) { if (copied == 0) copied = -EFAULT; @@ -2161,6 +2171,18 @@ unlock: copied += chunk; size -= chunk; + if (drop_skb) { + /* the skb was touched by a concurrent reader; + * we should not expect anything from this skb + * anymore and assume it invalid - we can be + * sure it was dropped from the socket queue + * + * let's report a short read + */ + err = 0; + break; + } + /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { UNIXCB(skb).consumed += chunk; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 79b4596..edd638b 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -67,10 +67,13 @@ HOSTLOADLIBES_lathist += -lelf # point this to your LLVM backend with bpf support LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc +# asm/sysreg.h inline assmbly used by it is incompatible with llvm. +# But, ehere is not easy way to fix it, so just exclude it since it is +# useless for BPF samples. $(obj)/%.o: $(src)/%.c clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ - -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ + -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ - -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ + -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=asm -o $@.s diff --git a/tools/net/Makefile b/tools/net/Makefile index ee577ea..ddf8880 100644 --- a/tools/net/Makefile +++ b/tools/net/Makefile @@ -4,6 +4,9 @@ CC = gcc LEX = flex YACC = bison +CFLAGS += -Wall -O2 +CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include + %.yacc.c: %.y $(YACC) -o $@ -d $< @@ -12,15 +15,13 @@ YACC = bison all : bpf_jit_disasm bpf_dbg bpf_asm -bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm' +bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm' bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl bpf_jit_disasm : bpf_jit_disasm.o -bpf_dbg : CFLAGS = -Wall -O2 bpf_dbg : LDLIBS = -lreadline bpf_dbg : bpf_dbg.o -bpf_asm : CFLAGS = -Wall -O2 -I. bpf_asm : LDLIBS = bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o bpf_exp.lex.o : bpf_exp.yacc.c |