diff options
53 files changed, 527 insertions, 317 deletions
diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt index 639ddf0ece9b..9ed15f86c17c 100644 --- a/Documentation/networking/mpls-sysctl.txt +++ b/Documentation/networking/mpls-sysctl.txt @@ -18,3 +18,12 @@ platform_labels - INTEGER Possible values: 0 - 1048575 Default: 0 + +conf/<interface>/input - BOOL + Control whether packets can be input on this interface. + + If disabled, packets will be discarded without further + processing. + + 0 - disabled (default) + not 0 - enabled diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index cbfac0949635..59f4db2a0c85 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt @@ -282,7 +282,7 @@ following is true: - The current CPU's queue head counter >= the recorded tail counter value in rps_dev_flow[i] -- The current CPU is unset (equal to RPS_NO_CPU) +- The current CPU is unset (>= nr_cpu_ids) - The current CPU is offline After this check, the packet is sent to the (possibly updated) current diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 78dde56ae6e6..3a10551d64cf 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -82,6 +82,8 @@ #include <net/bond_3ad.h> #include <net/bond_alb.h> +#include "bonding_priv.h" + /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 62694cfc05b6..b20b35acb47d 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -4,6 +4,7 @@ #include <net/netns/generic.h> #include <net/bonding.h> +#include "bonding_priv.h" static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h new file mode 100644 index 000000000000..5a4d81a9437c --- /dev/null +++ b/drivers/net/bonding/bonding_priv.h @@ -0,0 +1,25 @@ +/* + * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. + * + * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes + * NCM: Network and Communications Management, Inc. + * + * BUT, I'm the one who modified it for ethernet, so: + * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov + * + * This software may be used and distributed according to the terms + * of the GNU Public License, incorporated herein by reference. + * + */ + +#ifndef _BONDING_PRIV_H +#define _BONDING_PRIV_H + +#define DRV_VERSION "3.7.1" +#define DRV_RELDATE "April 27, 2011" +#define DRV_NAME "bonding" +#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" + +#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" + +#endif diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 58808f651452..e8c96b8e86f4 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -112,7 +112,7 @@ config PCH_CAN config CAN_GRCAN tristate "Aeroflex Gaisler GRCAN and GRHCAN CAN devices" - depends on OF + depends on OF && HAS_DMA ---help--- Say Y here if you want to use Aeroflex Gaisler GRCAN or GRHCAN. Note that the driver supports little endian, even though little diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 4643914859b2..8b17a9065b0b 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -1102,7 +1102,7 @@ static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | MSG_FLAG_NERR)) { - netdev_err(priv->netdev, "Unknow error (flags: 0x%02x)\n", + netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n", msg->u.rx_can_header.flag); stats->rx_errors++; diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index b36ee9e0d220..d686b9cac29f 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -523,7 +523,7 @@ static int etherh_addr(char *addr, struct expansion_card *ec) char *s; if (!ecard_readchunk(&cd, ec, 0xf5, 0)) { - printk(KERN_ERR "%s: unable to read podule description string\n", + printk(KERN_ERR "%s: unable to read module description string\n", dev_name(&ec->dev)); goto no_addr; } diff --git a/drivers/net/ethernet/altera/altera_msgdmahw.h b/drivers/net/ethernet/altera/altera_msgdmahw.h index eba070f16782..89cd11d86642 100644 --- a/drivers/net/ethernet/altera/altera_msgdmahw.h +++ b/drivers/net/ethernet/altera/altera_msgdmahw.h @@ -58,15 +58,12 @@ struct msgdma_extended_desc { /* Tx buffer control flags */ #define MSGDMA_DESC_CTL_TX_FIRST (MSGDMA_DESC_CTL_GEN_SOP | \ - MSGDMA_DESC_CTL_TR_ERR_IRQ | \ MSGDMA_DESC_CTL_GO) -#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_TR_ERR_IRQ | \ - MSGDMA_DESC_CTL_GO) +#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_GO) #define MSGDMA_DESC_CTL_TX_LAST (MSGDMA_DESC_CTL_GEN_EOP | \ MSGDMA_DESC_CTL_TR_COMP_IRQ | \ - MSGDMA_DESC_CTL_TR_ERR_IRQ | \ MSGDMA_DESC_CTL_GO) #define MSGDMA_DESC_CTL_TX_SINGLE (MSGDMA_DESC_CTL_GEN_SOP | \ diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 90a76306ad0f..0533c051a3e5 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -777,6 +777,8 @@ static int init_phy(struct net_device *dev) struct altera_tse_private *priv = netdev_priv(dev); struct phy_device *phydev; struct device_node *phynode; + bool fixed_link = false; + int rc = 0; /* Avoid init phy in case of no phy present */ if (!priv->phy_iface) @@ -789,13 +791,32 @@ static int init_phy(struct net_device *dev) phynode = of_parse_phandle(priv->device->of_node, "phy-handle", 0); if (!phynode) { - netdev_dbg(dev, "no phy-handle found\n"); - if (!priv->mdio) { - netdev_err(dev, - "No phy-handle nor local mdio specified\n"); - return -ENODEV; + /* check if a fixed-link is defined in device-tree */ + if (of_phy_is_fixed_link(priv->device->of_node)) { + rc = of_phy_register_fixed_link(priv->device->of_node); + if (rc < 0) { + netdev_err(dev, "cannot register fixed PHY\n"); + return rc; + } + + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ + phynode = of_node_get(priv->device->of_node); + fixed_link = true; + + netdev_dbg(dev, "fixed-link detected\n"); + phydev = of_phy_connect(dev, phynode, + &altera_tse_adjust_link, + 0, priv->phy_iface); + } else { + netdev_dbg(dev, "no phy-handle found\n"); + if (!priv->mdio) { + netdev_err(dev, "No phy-handle nor local mdio specified\n"); + return -ENODEV; + } + phydev = connect_local_phy(dev); } - phydev = connect_local_phy(dev); } else { netdev_dbg(dev, "phy-handle found\n"); phydev = of_phy_connect(dev, phynode, @@ -819,10 +840,10 @@ static int init_phy(struct net_device *dev) /* Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning * 0 rather than 0xffff. Catch this here and treat 0 as a non-existent - * device as well. + * device as well. If a fixed-link is used the phy_id is always 0. * Note: phydev->phy_id is the result of reading the UID PHY registers. */ - if (phydev->phy_id == 0) { + if ((phydev->phy_id == 0) && !fixed_link) { netdev_err(dev, "Bad PHY UID 0x%08x\n", phydev->phy_id); phy_disconnect(phydev); return -ENODEV; diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index c638c85f3954..089c269637b7 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -179,7 +179,7 @@ config SUNLANCE config AMD_XGBE tristate "AMD 10GbE Ethernet driver" - depends on (OF_NET || ACPI) && HAS_IOMEM + depends on (OF_NET || ACPI) && HAS_IOMEM && HAS_DMA select PHYLIB select AMD_XGBE_PHY select BITREVERSE diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index 8e262e2b39b6..dea29ee24da4 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -25,8 +25,7 @@ config ARC_EMAC_CORE config ARC_EMAC tristate "ARC EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ - depends on OF_NET + depends on OF_IRQ && OF_NET && HAS_DMA ---help--- On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x non-standard on-chip ethernet device ARC EMAC 10/100 is used. @@ -35,7 +34,7 @@ config ARC_EMAC config EMAC_ROCKCHIP tristate "Rockchip EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ && OF_NET && REGULATOR + depends on OF_IRQ && OF_NET && REGULATOR && HAS_DMA ---help--- Support for Rockchip RK3066/RK3188 EMAC ethernet controllers. This selects Rockchip SoC glue layer support for the diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index de77d3a74abc..21e3c38c7c75 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1260,7 +1260,7 @@ static int bgmac_poll(struct napi_struct *napi, int weight) /* Poll again if more events arrived in the meantime */ if (bgmac_read(bgmac, BGMAC_INT_STATUS) & (BGMAC_IS_TX0 | BGMAC_IS_RX)) - return handled; + return weight; if (handled < weight) { napi_complete(napi); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 2f63467bce46..3558a36b1c2d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2485,8 +2485,10 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index) else if (bp->flags & GRO_ENABLE_FLAG) fp->mode = TPA_MODE_GRO; - /* We don't want TPA on an FCoE L2 ring */ - if (IS_FCOE_FP(fp)) + /* We don't want TPA if it's disabled in bp + * or if this is an FCoE L2 ring. + */ + if (bp->disable_tpa || IS_FCOE_FP(fp)) fp->disable_tpa = 1; } @@ -4809,6 +4811,23 @@ netdev_features_t bnx2x_fix_features(struct net_device *dev, { struct bnx2x *bp = netdev_priv(dev); + if (pci_num_vf(bp->pdev)) { + netdev_features_t changed = dev->features ^ features; + + /* Revert the requested changes in features if they + * would require internal reload of PF in bnx2x_set_features(). + */ + if (!(features & NETIF_F_RXCSUM) && !bp->disable_tpa) { + features &= ~NETIF_F_RXCSUM; + features |= dev->features & NETIF_F_RXCSUM; + } + + if (changed & NETIF_F_LOOPBACK) { + features &= ~NETIF_F_LOOPBACK; + features |= dev->features & NETIF_F_LOOPBACK; + } + } + /* TPA requires Rx CSUM offloading */ if (!(features & NETIF_F_RXCSUM)) { features &= ~NETIF_F_LRO; @@ -4839,15 +4858,18 @@ int bnx2x_set_features(struct net_device *dev, netdev_features_t features) else flags &= ~GRO_ENABLE_FLAG; - if (features & NETIF_F_LOOPBACK) { - if (bp->link_params.loopback_mode != LOOPBACK_BMAC) { - bp->link_params.loopback_mode = LOOPBACK_BMAC; - bnx2x_reload = true; - } - } else { - if (bp->link_params.loopback_mode != LOOPBACK_NONE) { - bp->link_params.loopback_mode = LOOPBACK_NONE; - bnx2x_reload = true; + /* VFs or non SRIOV PFs should be able to change loopback feature */ + if (!pci_num_vf(bp->pdev)) { + if (features & NETIF_F_LOOPBACK) { + if (bp->link_params.loopback_mode != LOOPBACK_BMAC) { + bp->link_params.loopback_mode = LOOPBACK_BMAC; + bnx2x_reload = true; + } + } else { + if (bp->link_params.loopback_mode != LOOPBACK_NONE) { + bp->link_params.loopback_mode = LOOPBACK_NONE; + bnx2x_reload = true; + } } } @@ -4931,6 +4953,11 @@ int bnx2x_resume(struct pci_dev *pdev) } bp = netdev_priv(dev); + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, "VFs are enabled, can not change MTU\n"); + return -EPERM; + } + if (bp->recovery_state != BNX2X_RECOVERY_DONE) { BNX2X_ERR("Handling parity error recovery. Try again later\n"); return -EAGAIN; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index e3d853cab7c9..48ed005ba73f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1843,6 +1843,12 @@ static int bnx2x_set_ringparam(struct net_device *dev, "set ring params command parameters: rx_pending = %d, tx_pending = %d\n", ering->rx_pending, ering->tx_pending); + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, + "VFs are enabled, can not change ring parameters\n"); + return -EPERM; + } + if (bp->recovery_state != BNX2X_RECOVERY_DONE) { DP(BNX2X_MSG_ETHTOOL, "Handling parity error recovery. Try again later\n"); @@ -2899,6 +2905,12 @@ static void bnx2x_self_test(struct net_device *dev, u8 is_serdes, link_up; int rc, cnt = 0; + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, + "VFs are enabled, can not perform self test\n"); + return; + } + if (bp->recovery_state != BNX2X_RECOVERY_DONE) { netdev_err(bp->dev, "Handling parity error recovery. Try again later\n"); @@ -3468,6 +3480,11 @@ static int bnx2x_set_channels(struct net_device *dev, channels->rx_count, channels->tx_count, channels->other_count, channels->combined_count); + if (pci_num_vf(bp->pdev)) { + DP(BNX2X_MSG_IOV, "VFs are enabled, can not set channels\n"); + return -EPERM; + } + /* We don't support separate rx / tx channels. * We don't allow setting 'other' channels. */ diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 1270b189a9a2..069952fa5d64 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18129,7 +18129,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, rtnl_lock(); - tp->pcierr_recovery = true; + /* We needn't recover from permanent error */ + if (state == pci_channel_io_frozen) + tp->pcierr_recovery = true; /* We probably don't have netdev yet */ if (!netdev || !netif_running(netdev)) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 9f5387249f24..665c29098e3c 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -1473,9 +1473,9 @@ static void macb_init_rings(struct macb *bp) for (i = 0; i < TX_RING_SIZE; i++) { bp->queues[0].tx_ring[i].addr = 0; bp->queues[0].tx_ring[i].ctrl = MACB_BIT(TX_USED); - bp->queues[0].tx_head = 0; - bp->queues[0].tx_tail = 0; } + bp->queues[0].tx_head = 0; + bp->queues[0].tx_tail = 0; bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP); bp->rx_tail = 0; diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 291c87036e17..2a0dc127df3f 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3347,7 +3347,7 @@ static int ehea_register_memory_hooks(void) { int ret = 0; - if (atomic_inc_and_test(&ehea_memory_hooks_registered)) + if (atomic_inc_return(&ehea_memory_hooks_registered) > 1) return 0; ret = ehea_create_busmap(); @@ -3381,12 +3381,14 @@ out3: out2: unregister_reboot_notifier(&ehea_reboot_nb); out: + atomic_dec(&ehea_memory_hooks_registered); return ret; } static void ehea_unregister_memory_hooks(void) { - if (atomic_read(&ehea_memory_hooks_registered)) + /* Only remove the hooks if we've registered them */ + if (atomic_read(&ehea_memory_hooks_registered) == 0) return; unregister_reboot_notifier(&ehea_reboot_nb); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index cd7675ac5bf9..18134766a114 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1238,7 +1238,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) - if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) + if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) break; if (i == IBMVETH_NUM_BUFF_POOLS) @@ -1257,7 +1257,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { adapter->rx_buff_pool[i].active = 1; - if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) { + if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) { dev->mtu = new_mtu; vio_cmo_set_dev_desired(viodev, ibmveth_get_desired_dma diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index af829c578400..7ace07dad6a3 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1508,7 +1508,8 @@ static int pxa168_eth_probe(struct platform_device *pdev) np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!np) { dev_err(&pdev->dev, "missing phy-handle\n"); - return -EINVAL; + err = -EINVAL; + goto err_netdev; } of_property_read_u32(np, "reg", &pep->phy_addr); pep->phy_intf = of_get_phy_mode(pdev->dev.of_node); @@ -1526,7 +1527,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) pep->smi_bus = mdiobus_alloc(); if (pep->smi_bus == NULL) { err = -ENOMEM; - goto err_base; + goto err_netdev; } pep->smi_bus->priv = pep; pep->smi_bus->name = "pxa168_eth smi"; @@ -1551,13 +1552,10 @@ err_mdiobus: mdiobus_unregister(pep->smi_bus); err_free_mdio: mdiobus_free(pep->smi_bus); -err_base: - iounmap(pep->base); err_netdev: free_netdev(dev); err_clk: - clk_disable(clk); - clk_put(clk); + clk_disable_unprepare(clk); return err; } @@ -1574,13 +1572,9 @@ static int pxa168_eth_remove(struct platform_device *pdev) if (pep->phy) phy_disconnect(pep->phy); if (pep->clk) { - clk_disable(pep->clk); - clk_put(pep->clk); - pep->clk = NULL; + clk_disable_unprepare(pep->clk); } - iounmap(pep->base); - pep->base = NULL; mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); unregister_netdev(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3f44e2bbb982..a2ddf3d75ff8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1102,20 +1102,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc) struct mlx4_en_priv *priv = netdev_priv(dev); /* check if requested function is supported by the device */ - if ((hfunc == ETH_RSS_HASH_TOP && - !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) || - (hfunc == ETH_RSS_HASH_XOR && - !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))) - return -EINVAL; + if (hfunc == ETH_RSS_HASH_TOP) { + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) + return -EINVAL; + if (!(dev->features & NETIF_F_RXHASH)) + en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); + return 0; + } else if (hfunc == ETH_RSS_HASH_XOR) { + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)) + return -EINVAL; + if (dev->features & NETIF_F_RXHASH) + en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); + return 0; + } - priv->rss_hash_fn = hfunc; - if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH)) - en_warn(priv, - "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); - if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH)) - en_warn(priv, - "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); - return 0; + return -EINVAL; } static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key, @@ -1189,6 +1190,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index, priv->prof->rss_rings = rss_rings; if (key) memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE); + if (hfunc != ETH_RSS_HASH_NO_CHANGE) + priv->rss_hash_fn = hfunc; if (port_up) { err = mlx4_en_start_port(dev); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 1412f5af05ec..2bae50292dcd 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -69,11 +69,7 @@ #include <net/ip.h> #include <net/tcp.h> #include <asm/byteorder.h> -#include <asm/io.h> #include <asm/processor.h> -#ifdef CONFIG_MTRR -#include <asm/mtrr.h> -#endif #include <net/busy_poll.h> #include "myri10ge_mcp.h" @@ -242,8 +238,7 @@ struct myri10ge_priv { unsigned int rdma_tags_available; int intr_coal_delay; __be32 __iomem *intr_coal_delay_ptr; - int mtrr; - int wc_enabled; + int wc_cookie; int down_cnt; wait_queue_head_t down_wq; struct work_struct watchdog_work; @@ -1905,7 +1900,7 @@ static const char myri10ge_gstrings_main_stats[][ETH_GSTRING_LEN] = { "tx_aborted_errors", "tx_carrier_errors", "tx_fifo_errors", "tx_heartbeat_errors", "tx_window_errors", /* device-specific stats */ - "tx_boundary", "WC", "irq", "MSI", "MSIX", + "tx_boundary", "irq", "MSI", "MSIX", "read_dma_bw_MBs", "write_dma_bw_MBs", "read_write_dma_bw_MBs", "serial_number", "watchdog_resets", #ifdef CONFIG_MYRI10GE_DCA @@ -1984,7 +1979,6 @@ myri10ge_get_ethtool_stats(struct net_device *netdev, data[i] = ((u64 *)&link_stats)[i]; data[i++] = (unsigned int)mgp->tx_boundary; - data[i++] = (unsigned int)mgp->wc_enabled; data[i++] = (unsigned int)mgp->pdev->irq; data[i++] = (unsigned int)mgp->msi_enabled; data[i++] = (unsigned int)mgp->msix_enabled; @@ -4040,14 +4034,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mgp->board_span = pci_resource_len(pdev, 0); mgp->iomem_base = pci_resource_start(pdev, 0); - mgp->mtrr = -1; - mgp->wc_enabled = 0; -#ifdef CONFIG_MTRR - mgp->mtrr = mtrr_add(mgp->iomem_base, mgp->board_span, - MTRR_TYPE_WRCOMB, 1); - if (mgp->mtrr >= 0) - mgp->wc_enabled = 1; -#endif + mgp->wc_cookie = arch_phys_wc_add(mgp->iomem_base, mgp->board_span); mgp->sram = ioremap_wc(mgp->iomem_base, mgp->board_span); if (mgp->sram == NULL) { dev_err(&pdev->dev, "ioremap failed for %ld bytes at 0x%lx\n", @@ -4146,14 +4133,14 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto abort_with_state; } if (mgp->msix_enabled) - dev_info(dev, "%d MSI-X IRQs, tx bndry %d, fw %s, WC %s\n", + dev_info(dev, "%d MSI-X IRQs, tx bndry %d, fw %s, MTRR %s, WC Enabled\n", mgp->num_slices, mgp->tx_boundary, mgp->fw_name, - (mgp->wc_enabled ? "Enabled" : "Disabled")); + (mgp->wc_cookie > 0 ? "Enabled" : "Disabled")); else - dev_info(dev, "%s IRQ %d, tx bndry %d, fw %s, WC %s\n", + dev_info(dev, "%s IRQ %d, tx bndry %d, fw %s, MTRR %s, WC Enabled\n", mgp->msi_enabled ? "MSI" : "xPIC", pdev->irq, mgp->tx_boundary, mgp->fw_name, - (mgp->wc_enabled ? "Enabled" : "Disabled")); + (mgp->wc_cookie > 0 ? "Enabled" : "Disabled")); board_number++; return 0; @@ -4175,10 +4162,7 @@ abort_with_ioremap: iounmap(mgp->sram); abort_with_mtrr: -#ifdef CONFIG_MTRR - if (mgp->mtrr >= 0) - mtrr_del(mgp->mtrr, mgp->iomem_base, mgp->board_span); -#endif + arch_phys_wc_del(mgp->wc_cookie); dma_free_coherent(&pdev->dev, sizeof(*mgp->cmd), mgp->cmd, mgp->cmd_bus); @@ -4220,11 +4204,7 @@ static void myri10ge_remove(struct pci_dev *pdev) pci_restore_state(pdev); iounmap(mgp->sram); - -#ifdef CONFIG_MTRR - if (mgp->mtrr >= 0) - mtrr_del(mgp->mtrr, mgp->iomem_base, mgp->board_span); -#endif + arch_phys_wc_del(mgp->wc_cookie); myri10ge_free_slices(mgp); kfree(mgp->msix_vectors); dma_free_coherent(&pdev->dev, sizeof(*mgp->cmd), diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 49ce7ece5af3..c9cb486c753d 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -80,7 +80,8 @@ static void mdio_dir(struct mdiobb_ctrl *ctrl, int dir) * assume the pin serves as pull-up. If direction is * output, the default value is high. */ - gpio_set_value(bitbang->mdo, 1 ^ bitbang->mdo_active_low); + gpio_set_value_cansleep(bitbang->mdo, + 1 ^ bitbang->mdo_active_low); return; } @@ -96,7 +97,8 @@ static int mdio_get(struct mdiobb_ctrl *ctrl) struct mdio_gpio_info *bitbang = container_of(ctrl, struct mdio_gpio_info, ctrl); - return gpio_get_value(bitbang->mdio) ^ bitbang->mdio_active_low; + return gpio_get_value_cansleep(bitbang->mdio) ^ + bitbang->mdio_active_low; } static void mdio_set(struct mdiobb_ctrl *ctrl, int what) @@ -105,9 +107,11 @@ static void mdio_set(struct mdiobb_ctrl *ctrl, int what) container_of(ctrl, struct mdio_gpio_info, ctrl); if (bitbang->mdo) - gpio_set_value(bitbang->mdo, what ^ bitbang->mdo_active_low); + gpio_set_value_cansleep(bitbang->mdo, + what ^ bitbang->mdo_active_low); else - gpio_set_value(bitbang->mdio, what ^ bitbang->mdio_active_low); + gpio_set_value_cansleep(bitbang->mdio, + what ^ bitbang->mdio_active_low); } static void mdc_set(struct mdiobb_ctrl *ctrl, int what) @@ -115,7 +119,7 @@ static void mdc_set(struct mdiobb_ctrl *ctrl, int what) struct mdio_gpio_info *bitbang = container_of(ctrl, struct mdio_gpio_info, ctrl); - gpio_set_value(bitbang->mdc, what ^ bitbang->mdc_active_low); + gpio_set_value_cansleep(bitbang->mdc, what ^ bitbang->mdc_active_low); } static struct mdiobb_ops mdio_gpio_ops = { diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c index 1a87a585e74d..66edd99bc302 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/phy/mdio-mux-gpio.c @@ -12,33 +12,30 @@ #include <linux/module.h> #include <linux/phy.h> #include <linux/mdio-mux.h> -#include <linux/of_gpio.h> +#include <linux/gpio/consumer.h> #define DRV_VERSION "1.1" #define DRV_DESCRIPTION "GPIO controlled MDIO bus multiplexer driver" -#define MDIO_MUX_GPIO_MAX_BITS 8 - struct mdio_mux_gpio_state { - struct gpio_desc *gpio[MDIO_MUX_GPIO_MAX_BITS]; - unsigned int num_gpios; + struct gpio_descs *gpios; void *mux_handle; }; static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, void *data) { - int values[MDIO_MUX_GPIO_MAX_BITS]; - unsigned int n; struct mdio_mux_gpio_state *s = data; + int values[s->gpios->ndescs]; + unsigned int n; if (current_child == desired_child) return 0; - for (n = 0; n < s->num_gpios; n++) { + for (n = 0; n < s->gpios->ndescs; n++) values[n] = (desired_child >> n) & 1; - } - gpiod_set_array_cansleep(s->num_gpios, s->gpio, values); + + gpiod_set_array_cansleep(s->gpios->ndescs, s->gpios->desc, values); return 0; } @@ -46,56 +43,33 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, static int mdio_mux_gpio_probe(struct platform_device *pdev) { struct mdio_mux_gpio_state *s; - int num_gpios; - unsigned int n; int r; - if (!pdev->dev.of_node) - return -ENODEV; - - num_gpios = of_gpio_count(pdev->dev.of_node); - if (num_gpios <= 0 || num_gpios > MDIO_MUX_GPIO_MAX_BITS) - return -ENODEV; - s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; - s->num_gpios = num_gpios; - - for (n = 0; n < num_gpios; ) { - struct gpio_desc *gpio = gpiod_get_index(&pdev->dev, NULL, n, - GPIOD_OUT_LOW); - if (IS_ERR(gpio)) { - r = PTR_ERR(gpio); - goto err; - } - s->gpio[n] = gpio; - n++; - } + s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW); + if (IS_ERR(s->gpios)) + return PTR_ERR(s->gpios); r = mdio_mux_init(&pdev->dev, mdio_mux_gpio_switch_fn, &s->mux_handle, s); - if (r == 0) { - pdev->dev.platform_data = s; - return 0; - } -err: - while (n) { - n--; - gpiod_put(s->gpio[n]); + if (r != 0) { + gpiod_put_array(s->gpios); + return r; } - return r; + + pdev->dev.platform_data = s; + return 0; } static int mdio_mux_gpio_remove(struct platform_device *pdev) { - unsigned int n; struct mdio_mux_gpio_state *s = dev_get_platdata(&pdev->dev); mdio_mux_uninit(s->mux_handle); - for (n = 0; n < s->num_gpios; n++) - gpiod_put(s->gpio[n]); + gpiod_put_array(s->gpios); return 0; } diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c index 911b21602ff2..05005c660d4d 100644 --- a/drivers/net/ppp/ppp_mppe.c +++ b/drivers/net/ppp/ppp_mppe.c @@ -478,7 +478,6 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, struct blkcipher_desc desc = { .tfm = state->arc4 }; unsigned ccount; int flushed = MPPE_BITS(ibuf) & MPPE_BIT_FLUSHED; - int sanity = 0; struct scatterlist sg_in[1], sg_out[1]; if (isize <= PPP_HDRLEN + MPPE_OVHD) { @@ -514,31 +513,19 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, "mppe_decompress[%d]: ENCRYPTED bit not set!\n", state->unit); state->sanity_errors += 100; - sanity = 1; + goto sanity_error; } if (!state->stateful && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set in " "stateless mode!\n", state->unit); state->sanity_errors += 100; - sanity = 1; + goto sanity_error; } if (state->stateful && ((ccount & 0xff) == 0xff) && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set on " "flag packet!\n", state->unit); state->sanity_errors += 100; - sanity = 1; - } - - if (sanity) { - if (state->sanity_errors < SANITY_MAX) - return DECOMP_ERROR; - else - /* - * Take LCP down if the peer is sending too many bogons. - * We don't want to do this for a single or just a few - * instances since it could just be due to packet corruption. - */ - return DECOMP_FATALERROR; + goto sanity_error; } /* @@ -546,6 +533,13 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, */ if (!state->stateful) { + /* Discard late packet */ + if ((ccount - state->ccount) % MPPE_CCOUNT_SPACE + > MPPE_CCOUNT_SPACE / 2) { + state->sanity_errors++; + goto sanity_error; + } + /* RFC 3078, sec 8.1. Rekey for every packet. */ while (state->ccount != ccount) { mppe_rekey(state, 0); @@ -649,6 +643,16 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, state->sanity_errors >>= 1; return osize; + +sanity_error: + if (state->sanity_errors < SANITY_MAX) + return DECOMP_ERROR; + else + /* Take LCP down if the peer is sending too many bogons. + * We don't want to do this for a single or just a few + * instances since it could just be due to packet corruption. + */ + return DECOMP_FATALERROR; } /* diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 154116aafd0d..27a5f954f8e9 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -730,12 +730,8 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { - int rc = vxlan_fdb_replace(f, ip, port, vni, + notify |= vxlan_fdb_replace(f, ip, port, vni, ifindex); - - if (rc < 0) - return rc; - notify |= rc; } else return -EOPNOTSUPP; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bcbde799ec69..dbad4d728b4b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -60,6 +60,7 @@ struct phy_device; struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; +struct mpls_dev; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -1627,6 +1628,9 @@ struct net_device { void *ax25_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; +#if IS_ENABLED(CONFIG_MPLS_ROUTING) + struct mpls_dev __rcu *mpls_ptr; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) @@ -2021,10 +2025,10 @@ struct pcpu_sw_netstats { ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ if (pcpu_stats) { \ - int i; \ - for_each_possible_cpu(i) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, i); \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e23d242d1230..dbcbcc59aa92 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -282,7 +282,8 @@ static inline bool rht_shrink_below_30(const struct rhashtable *ht, static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { - return atomic_read(&ht->nelems) > tbl->size; + return atomic_read(&ht->nelems) > tbl->size && + (!ht->p.max_size || tbl->size < ht->p.max_size); } /* The bucket lock is selected based on the hash and protects mutations diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 06793b598f44..66e374d62f64 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -773,6 +773,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); +struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) diff --git a/include/net/bonding.h b/include/net/bonding.h index fda6feeb6c1f..78ed135e9dea 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -30,13 +30,6 @@ #include <net/bond_alb.h> #include <net/bond_options.h> -#define DRV_VERSION "3.7.1" -#define DRV_RELDATE "April 27, 2011" -#define DRV_NAME "bonding" -#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" - -#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" - #define BOND_MAX_ARP_TARGETS 16 #define BOND_DEFAULT_MIIMON 100 diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 7b5887cd1172..48a815823587 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -279,12 +279,6 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); -static inline void inet_csk_reqsk_queue_removed(struct sock *sk, - struct request_sock *req) -{ - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); -} - static inline void inet_csk_reqsk_queue_added(struct sock *sk, const unsigned long timeout) { @@ -306,19 +300,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue); } -static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req) -{ - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); -} - -static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req) -{ - inet_csk_reqsk_queue_unlink(sk, req); - inet_csk_reqsk_queue_removed(sk, req); - reqsk_put(req); -} +void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index fe41f3ceb008..9f4265ce8892 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -212,24 +212,6 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) return queue->rskq_accept_head == NULL; } -static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req) -{ - struct listen_sock *lopt = queue->listen_opt; - struct request_sock **prev; - - spin_lock(&queue->syn_wait_lock); - - prev = &lopt->syn_table[req->rsk_hash]; - while (*prev != req) - prev = &(*prev)->dl_next; - *prev = req->dl_next; - - spin_unlock(&queue->syn_wait_lock); - if (del_timer(&req->rsk_timer)) - reqsk_put(req); -} - static inline void reqsk_queue_add(struct request_sock_queue *queue, struct request_sock *req, struct sock *parent, diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 4898442b837f..b28df4019ade 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -405,13 +405,18 @@ int rhashtable_insert_rehash(struct rhashtable *ht) if (rht_grow_above_75(ht, tbl)) size *= 2; - /* More than two rehashes (not resizes) detected. */ - else if (WARN_ON(old_tbl != tbl && old_tbl->size == size)) + /* Do not schedule more than one rehash */ + else if (old_tbl != tbl) return -EBUSY; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); - if (new_tbl == NULL) + if (new_tbl == NULL) { + /* Schedule async resize/rehash to try allocation + * non-atomic context. + */ + schedule_work(&ht->run_work); return -ENOMEM; + } err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { diff --git a/net/core/dev.c b/net/core/dev.c index 1796cef55ab5..c7ba0388f1be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3079,7 +3079,7 @@ static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { - if (next_cpu != RPS_NO_CPU) { + if (next_cpu < nr_cpu_ids) { #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; @@ -3184,7 +3184,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: - * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. @@ -3192,14 +3192,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && - (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } - if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; @@ -3240,14 +3240,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; - int cpu; + unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = ACCESS_ONCE(rflow->cpu); - if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < (int)(10 * flow_table->mask))) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d1967dab9cc6..3cfff2a3d651 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -280,13 +280,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -328,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { @@ -348,7 +365,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, gfp_t gfp = gfp_mask; if (order) { - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC; page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); nc->frag.size = PAGE_SIZE << (page ? order : 0); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 2b4f21d34df6..ccf4c5629b3c 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -453,7 +453,8 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) iph->saddr, iph->daddr); if (req) { nsk = dccp_check_req(sk, skb, req); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9d0551092c6c..5165571f397a 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -301,7 +301,8 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &iph->daddr, inet6_iif(skb)); if (req) { nsk = dccp_check_req(sk, skb, req); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 5f566663e47f..30addee2dd03 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -186,8 +186,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req); - inet_csk_reqsk_queue_removed(sk, req); + inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); out: return child; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5c3dd6267ed3..8976ca423a07 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -564,6 +564,40 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); +/* return true if req was found in the syn_table[] */ +static bool reqsk_queue_unlink(struct request_sock_queue *queue, + struct request_sock *req) +{ + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + bool found = false; + + spin_lock(&queue->syn_wait_lock); + + for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL; + prev = &(*prev)->dl_next) { + if (*prev == req) { + *prev = req->dl_next; + found = true; + break; + } + } + + spin_unlock(&queue->syn_wait_lock); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); + return found; +} + +void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +{ + if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) { + reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); + reqsk_put(req); + } +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); + static void reqsk_timer_handler(unsigned long data) { struct request_sock *req = (struct request_sock *)data; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3571f2be4470..fc1c658ec6c1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1348,7 +1348,8 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); if (req) { nsk = tcp_check_req(sk, skb, req, false); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 63d6311b5365..e5d7649136fc 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -755,10 +755,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req); - inet_csk_reqsk_queue_removed(sk, req); - + inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); + /* Warning: caller must not call reqsk_put(req); + * child stole last reference on it. + */ return child; listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8c8d7e06b72f..a369e8a70b2c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2812,39 +2812,65 @@ begin_fwd: } } -/* Send a fin. The caller locks the socket for us. This cannot be - * allowed to fail queueing a FIN frame under any circumstances. +/* We allow to exceed memory limits for FIN packets to expedite + * connection tear down and (memory) recovery. + * Otherwise tcp_send_fin() could be tempted to either delay FIN + * or even be forced to close flow without any FIN. + */ +static void sk_forced_wmem_schedule(struct sock *sk, int size) +{ + int amt, status; + + if (size <= sk->sk_forward_alloc) + return; + amt = sk_mem_pages(size); + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk_memory_allocated_add(sk, amt, &status); +} + +/* Send a FIN. The caller locks the socket for us. + * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { + struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_write_queue_tail(sk); - int mss_now; - /* Optimization, tack on the FIN if we have a queue of - * unsent frames. But be careful about outgoing SACKS - * and IP options. + /* Optimization, tack on the FIN if we have one skb in write queue and + * this skb was not yet sent, or we are under memory pressure. + * Note: in the latter case, FIN packet will be sent after a timeout, + * as TCP stack thinks it has already been transmitted. */ - mss_now = tcp_current_mss(sk); - - if (tcp_send_head(sk)) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; - TCP_SKB_CB(skb)->end_seq++; + if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { +coalesce: + TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; + TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; + if (!tcp_send_head(sk)) { + /* This means tskb was already sent. + * Pretend we included the FIN on previous transmit. + * We need to set tp->snd_nxt to the value it would have + * if FIN had been sent. This is because retransmit path + * does not change tp->snd_nxt. + */ + tp->snd_nxt++; + return; + } } else { - /* Socket is locked, keep trying until memory is available. */ - for (;;) { - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); - if (skb) - break; - yield(); + skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + if (unlikely(!skb)) { + if (tskb) + goto coalesce; + return; } + skb_reserve(skb, MAX_TCP_HEADER); + sk_forced_wmem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); + __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b5e6cc1d4a73..a38d3ac0f18f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1246,7 +1246,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static int ip6gre_tunnel_init(struct net_device *dev) { struct ip6_tnl *tunnel; - int i; tunnel = netdev_priv(dev); @@ -1260,16 +1259,10 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6gre_tunnel_stats; - ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6gre_tunnel_stats->syncp); - } - return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ad51df85aa00..b6575d665568 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -946,7 +946,8 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); if (req) { nsk = tcp_check_req(sk, skb, req, false); - reqsk_put(req); + if (!nsk) + reqsk_put(req); return nsk; } nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index db8a2ea6d4de..954810c76a86 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -53,6 +53,11 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) return rt; } +static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->mpls_ptr); +} + static bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); @@ -136,6 +141,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct mpls_route *rt; struct mpls_entry_decoded dec; struct net_device *out_dev; + struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; unsigned int mtu; @@ -143,6 +149,10 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, /* Careful this entire function runs inside of an rcu critical section */ + mdev = mpls_dev_get(dev); + if (!mdev || !mdev->input_enabled) + goto drop; + if (skb->pkt_type != PACKET_HOST) goto drop; @@ -352,9 +362,9 @@ static int mpls_route_add(struct mpls_route_config *cfg) if (!dev) goto errout; - /* For now just support ethernet devices */ + /* Ensure this is a supported device */ err = -EINVAL; - if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) + if (!mpls_dev_get(dev)) goto errout; err = -EINVAL; @@ -428,10 +438,89 @@ errout: return err; } +#define MPLS_PERDEV_SYSCTL_OFFSET(field) \ + (&((struct mpls_dev *)0)->field) + +static const struct ctl_table mpls_dev_table[] = { + { + .procname = "input", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), + }, + { } +}; + +static int mpls_dev_sysctl_register(struct net_device *dev, + struct mpls_dev *mdev) +{ + char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; + struct ctl_table *table; + int i; + + table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL); + if (!table) + goto out; + + /* Table data contains only offsets relative to the base of + * the mdev at this point, so make them absolute. + */ + for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++) + table[i].data = (char *)mdev + (uintptr_t)table[i].data; + + snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); + + mdev->sysctl = register_net_sysctl(dev_net(dev), path, table); + if (!mdev->sysctl) + goto free; + + return 0; + +free: + kfree(table); +out: + return -ENOBUFS; +} + +static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev) +{ + struct ctl_table *table; + + table = mdev->sysctl->ctl_table_arg; + unregister_net_sysctl_table(mdev->sysctl); + kfree(table); +} + +static struct mpls_dev *mpls_add_dev(struct net_device *dev) +{ + struct mpls_dev *mdev; + int err = -ENOMEM; + + ASSERT_RTNL(); + + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); + if (!mdev) + return ERR_PTR(err); + + err = mpls_dev_sysctl_register(dev, mdev); + if (err) + goto free; + + rcu_assign_pointer(dev->mpls_ptr, mdev); + + return mdev; + +free: + kfree(mdev); + return ERR_PTR(err); +} + static void mpls_ifdown(struct net_device *dev) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); + struct mpls_dev *mdev; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); @@ -443,14 +532,35 @@ static void mpls_ifdown(struct net_device *dev) continue; rt->rt_dev = NULL; } + + mdev = mpls_dev_get(dev); + if (!mdev) + return; + + mpls_dev_sysctl_unregister(mdev); + + RCU_INIT_POINTER(dev->mpls_ptr, NULL); + + kfree(mdev); } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mpls_dev *mdev; switch(event) { + case NETDEV_REGISTER: + /* For now just support ethernet devices */ + if ((dev->type == ARPHRD_ETHER) || + (dev->type == ARPHRD_LOOPBACK)) { + mdev = mpls_add_dev(dev); + if (IS_ERR(mdev)) + return notifier_from_errno(PTR_ERR(mdev)); + } + break; + case NETDEV_UNREGISTER: mpls_ifdown(dev); break; @@ -536,6 +646,15 @@ int nla_get_labels(const struct nlattr *nla, if ((dec.bos != bos) || dec.ttl || dec.tc) return -EINVAL; + switch (dec.label) { + case LABEL_IMPLICIT_NULL: + /* RFC3032: This is a label that an LSR may + * assign and distribute, but which never + * actually appears in the encapsulation. + */ + return -EINVAL; + } + label[i] = dec.label; } *labels = nla_labels; @@ -912,7 +1031,7 @@ static int mpls_platform_labels(struct ctl_table *table, int write, return ret; } -static struct ctl_table mpls_table[] = { +static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", .data = NULL, diff --git a/net/mpls/internal.h b/net/mpls/internal.h index fb6de92052c4..693877d69606 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -22,6 +22,12 @@ struct mpls_entry_decoded { u8 bos; }; +struct mpls_dev { + int input_enabled; + + struct ctl_table_header *sysctl; +}; + struct sk_buff; static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb) diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 57d3e1af5630..0522fc9bfb0a 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -63,6 +63,8 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 62cabee42fbe..635dbba93d01 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -108,6 +108,8 @@ static int nft_reject_inet_dump(struct sk_buff *skb, if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 19909d0786a2..ec4adbdcb9b4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1629,13 +1629,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } diff --git a/net/tipc/link.c b/net/tipc/link.c index a6b30df6ec02..57be6e6aff99 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2143,7 +2143,6 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) err = __tipc_nl_add_node_links(net, &msg, node, &prev_link); tipc_node_unlock(node); - tipc_node_put(node); if (err) goto out; diff --git a/net/tipc/server.c b/net/tipc/server.c index ab6183cdb121..77ff03ed1e18 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -102,7 +102,7 @@ static void tipc_conn_kref_release(struct kref *kref) } saddr->scope = -TIPC_NODE_SCOPE; kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); - sk_release_kernel(sk); + sock_release(sock); con->sock = NULL; } @@ -321,12 +321,9 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) struct socket *sock = NULL; int ret; - ret = sock_create_kern(AF_TIPC, SOCK_SEQPACKET, 0, &sock); + ret = __sock_create(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock, 1); if (ret < 0) return NULL; - - sk_change_net(sock->sk, s->net); - ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, (char *)&s->imp, sizeof(s->imp)); if (ret < 0) @@ -376,7 +373,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) create_err: kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sock->sk); + sock_release(sock); return NULL; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ee90d74d7516..9074b5cede38 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1764,13 +1764,14 @@ static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { u32 dnode, dport = 0; - int err = -TIPC_ERR_NO_PORT; + int err; struct sk_buff *skb; struct tipc_sock *tsk; struct tipc_net *tn; struct sock *sk; while (skb_queue_len(inputq)) { + err = -TIPC_ERR_NO_PORT; skb = NULL; dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 99f7012b23b9..a73a226f2d33 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -95,39 +95,36 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; - struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = file_inode(filp); - /* - * Socket ? - */ + /* Socket ? */ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); struct sock *s = sock->sk; - /* - * PF_UNIX ? - */ + /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; } return u_sock; } -/* - * Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. */ void unix_inflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + if (s) { struct unix_sock *u = unix_sk(s); + spin_lock(&unix_gc_lock); + if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -142,10 +139,13 @@ void unix_inflight(struct file *fp) void unix_notinflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + if (s) { struct unix_sock *u = unix_sk(s); + spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); + if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; @@ -161,32 +161,27 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), spin_lock(&x->sk_receive_queue.lock); skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* - * Do we have file descriptors ? - */ + /* Do we have file descriptors ? */ if (UNIXCB(skb).fp) { bool hit = false; - /* - * Process the descriptors of this socket - */ + /* Process the descriptors of this socket */ int nfd = UNIXCB(skb).fp->count; struct file **fp = UNIXCB(skb).fp->fp; + while (nfd--) { - /* - * Get the socket the fd matches - * if it indeed does so - */ + /* Get the socket the fd matches if it indeed does so */ struct sock *sk = unix_get_socket(*fp++); + if (sk) { struct unix_sock *u = unix_sk(sk); - /* - * Ignore non-candidates, they could + /* Ignore non-candidates, they could * have been added to the queues after * starting the garbage collection */ if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { hit = true; + func(u); } } @@ -203,24 +198,22 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), static void scan_children(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { - if (x->sk_state != TCP_LISTEN) + if (x->sk_state != TCP_LISTEN) { scan_inflight(x, func, hitlist); - else { + } else { struct sk_buff *skb; struct sk_buff *next; struct unix_sock *u; LIST_HEAD(embryos); - /* - * For a listening socket collect the queued embryos + /* For a listening socket collect the queued embryos * and perform a scan on them as well. */ spin_lock(&x->sk_receive_queue.lock); skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { u = unix_sk(skb->sk); - /* - * An embryo cannot be in-flight, so it's safe + /* An embryo cannot be in-flight, so it's safe * to use the list link. */ BUG_ON(!list_empty(&u->link)); @@ -249,8 +242,7 @@ static void inc_inflight(struct unix_sock *usk) static void inc_inflight_move_tail(struct unix_sock *u) { atomic_long_inc(&u->inflight); - /* - * If this still might be part of a cycle, move it to the end + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over */ @@ -263,8 +255,7 @@ static bool gc_in_progress; void wait_for_unix_gc(void) { - /* - * If number of inflight sockets is insane, + /* If number of inflight sockets is insane, * force a garbage collect right now. */ if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) @@ -288,8 +279,7 @@ void unix_gc(void) goto out; gc_in_progress = true; - /* - * First, select candidates for garbage collection. Only + /* First, select candidates for garbage collection. Only * in-flight sockets are considered, and from those only ones * which don't have any external reference. * @@ -320,15 +310,13 @@ void unix_gc(void) } } - /* - * Now remove all internal in-flight reference to children of + /* Now remove all internal in-flight reference to children of * the candidates. */ list_for_each_entry(u, &gc_candidates, link) scan_children(&u->sk, dec_inflight, NULL); - /* - * Restore the references for children of all candidates, + /* Restore the references for children of all candidates, * which have remaining references. Do this recursively, so * only those remain, which form cyclic references. * @@ -350,8 +338,7 @@ void unix_gc(void) } list_del(&cursor); - /* - * not_cycle_list contains those sockets which do not make up a + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ while (!list_empty(¬_cycle_list)) { @@ -360,8 +347,7 @@ void unix_gc(void) list_move_tail(&u->link, &gc_inflight_list); } - /* - * Now gc_candidates contains only garbage. Restore original + /* Now gc_candidates contains only garbage. Restore original * inflight counters for these as well, and remove the skbuffs * which are creating the cycle(s). */ |