diff options
67 files changed, 469 insertions, 333 deletions
diff --git a/Documentation/networking/LICENSE.qlcnic b/Documentation/networking/LICENSE.qlcnic index e7fb2c6023bc..2ae3b64983ab 100644 --- a/Documentation/networking/LICENSE.qlcnic +++ b/Documentation/networking/LICENSE.qlcnic @@ -1,4 +1,4 @@ -Copyright (c) 2009-2011 QLogic Corporation +Copyright (c) 2009-2013 QLogic Corporation QLogic Linux qlcnic NIC Driver You may modify and redistribute the device driver code under the diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 19ac1802bfd4..dc2dc87d2557 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -130,17 +130,6 @@ somaxconn - INTEGER Defaults to 128. See also tcp_max_syn_backlog for additional tuning for TCP sockets. -tcp_abc - INTEGER - Controls Appropriate Byte Count (ABC) defined in RFC3465. - ABC is a way of increasing congestion window (cwnd) more slowly - in response to partial acknowledgments. - Possible values are: - 0 increase cwnd once per acknowledgment (no ABC) - 1 increase cwnd once per acknowledgment of full sized segment - 2 allow increase cwnd by two if acknowledgment is - of two segments to compensate for delayed acknowledgments. - Default: 0 (off) - tcp_abort_on_overflow - BOOLEAN If listening service is too slow to accept new connections, reset them. Default state is FALSE. It means that if overflow diff --git a/drivers/bcma/driver_chipcommon_nflash.c b/drivers/bcma/driver_chipcommon_nflash.c index dbda91e4dff5..1f0b83e18f68 100644 --- a/drivers/bcma/driver_chipcommon_nflash.c +++ b/drivers/bcma/driver_chipcommon_nflash.c @@ -21,7 +21,7 @@ int bcma_nflash_init(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; if (bus->chipinfo.id != BCMA_CHIP_ID_BCM4706 && - cc->core->id.rev != 0x38) { + cc->core->id.rev != 38) { bcma_err(bus, "NAND flash on unsupported board!\n"); return -ENOTSUPP; } diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 1877ed7ca086..1c9e09fbdff8 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1053,6 +1053,7 @@ static ssize_t bonding_store_primary(struct device *d, pr_info("%s: Setting primary slave to None.\n", bond->dev->name); bond->primary_slave = NULL; + memset(bond->params.primary, 0, sizeof(bond->params.primary)); bond_select_active_slave(bond); goto out; } diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 285f763e3cd1..a668cd491cb3 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -491,8 +491,12 @@ static void c_can_setup_receive_object(struct net_device *dev, int iface, priv->write_reg(priv, C_CAN_IFACE(MASK1_REG, iface), IFX_WRITE_LOW_16BIT(mask)); + + /* According to C_CAN documentation, the reserved bit + * in IFx_MASK2 register is fixed 1 + */ priv->write_reg(priv, C_CAN_IFACE(MASK2_REG, iface), - IFX_WRITE_HIGH_16BIT(mask)); + IFX_WRITE_HIGH_16BIT(mask) | BIT(13)); priv->write_reg(priv, C_CAN_IFACE(ARB1_REG, iface), IFX_WRITE_LOW_16BIT(id)); diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 4010cb71bddb..28ceb8414185 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -36,13 +36,13 @@ #define DRV_VER "4.6.62.0u" #define DRV_NAME "be2net" -#define BE_NAME "ServerEngines BladeEngine2 10Gbps NIC" -#define BE3_NAME "ServerEngines BladeEngine3 10Gbps NIC" -#define OC_NAME "Emulex OneConnect 10Gbps NIC" +#define BE_NAME "Emulex BladeEngine2" +#define BE3_NAME "Emulex BladeEngine3" +#define OC_NAME "Emulex OneConnect" #define OC_NAME_BE OC_NAME "(be3)" #define OC_NAME_LANCER OC_NAME "(Lancer)" #define OC_NAME_SH OC_NAME "(Skyhawk)" -#define DRV_DESC "ServerEngines BladeEngine 10Gbps NIC Driver" +#define DRV_DESC "Emulex OneConnect 10Gbps NIC Driver" #define BE_VENDOR_ID 0x19a2 #define EMULEX_VENDOR_ID 0x10df diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7d534818d2fb..3860888ac711 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -25,7 +25,7 @@ MODULE_VERSION(DRV_VER); MODULE_DEVICE_TABLE(pci, be_dev_ids); MODULE_DESCRIPTION(DRV_DESC " " DRV_VER); -MODULE_AUTHOR("ServerEngines Corporation"); +MODULE_AUTHOR("Emulex Corporation"); MODULE_LICENSE("GPL"); static unsigned int num_vfs; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 19c54a0acb56..75734bfed10f 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -580,19 +580,11 @@ static int gfar_parse_group(struct device_node *np, u32 *queue_mask; int i; - if (priv->mode == MQ_MG_MODE) { - for (i = 0; i < GFAR_NUM_IRQS; i++) { - grp->irqinfo[i] = kzalloc(sizeof(struct gfar_irqinfo), - GFP_KERNEL); - if (!grp->irqinfo[i]) - return -ENOMEM; - } - } else { - grp->irqinfo[GFAR_TX] = kzalloc(sizeof(struct gfar_irqinfo), - GFP_KERNEL); - if (!grp->irqinfo[GFAR_TX]) + for (i = 0; i < GFAR_NUM_IRQS; i++) { + grp->irqinfo[i] = kzalloc(sizeof(struct gfar_irqinfo), + GFP_KERNEL); + if (!grp->irqinfo[i]) return -ENOMEM; - grp->irqinfo[GFAR_RX] = grp->irqinfo[GFAR_ER] = NULL; } grp->regs = of_iomap(np, 0); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 457ca8ec9e73..3a840e741982 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 65233c846537..cdcbbb0e40cb 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #include "qlcnic.h" #include <linux/if_vlan.h> #include <linux/ipv6.h> diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index 2b44eb14d525..b62017bae368 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #ifndef __QLCNIC_83XX_HW_H #define __QLCNIC_83XX_HW_H diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 8163e5b338e4..f6470027d0fc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #include "qlcnic.h" #include "qlcnic_hw.h" diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c index b3ef33a67229..b0c3de9ede03 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #include "qlcnic.h" #include "qlcnic_hw.h" diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index 7372964d3a76..4a3bd64b7fb0 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index f65fd7b6f9ae..6320d551c63d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hdr.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hdr.h index 74f771122985..44197ca1456c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hdr.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hdr.h @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index 4ee92b254fc0..51716ab8739a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 9673e2bcff06..ed52b9cfa15d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #ifndef __QLCNIC_HW_H #define __QLCNIC_HW_H diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c index 10ad25d7aa0e..d28336fc65ab 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index d00f62832742..bb4311e9aea9 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <net/ip.h> diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index fb0255a90ce4..d0aef32d0390 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -1,6 +1,6 @@ /* * QLogic qlcnic NIC Driver - * Copyright (c) 2009-2010 QLogic Corporation + * Copyright (c) 2009-2013 QLogic Corporation * * See LICENSE.qlcnic for copyright and licensing details. */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index 8dbc8e76bc74..abbd22c814a6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1,3 +1,9 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ #include "qlcnic.h" #include "qlcnic_hdr.h" diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 504506349ac1..987fb6f8adc3 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -1,3 +1,10 @@ +/* + * QLogic qlcnic NIC Driver + * Copyright (c) 2009-2013 QLogic Corporation + * + * See LICENSE.qlcnic for copyright and licensing details. + */ + #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/interrupt.h> diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index ec4a5e1c6fb2..185c721c52d7 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1812,7 +1812,7 @@ static void rhine_tx(struct net_device *dev) rp->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); } - dev_kfree_skb_irq(rp->tx_skbuff[entry]); + dev_kfree_skb(rp->tx_skbuff[entry]); rp->tx_skbuff[entry] = NULL; entry = (++rp->dirty_tx) % TX_RING_SIZE; } @@ -2024,11 +2024,7 @@ static void rhine_slow_event_task(struct work_struct *work) if (intr_status & IntrPCIErr) netif_warn(rp, hw, dev, "PCI error\n"); - napi_disable(&rp->napi); - rhine_irq_disable(rp); - /* Slow and safe. Consider __napi_schedule as a replacement ? */ - napi_enable(&rp->napi); - napi_schedule(&rp->napi); + iowrite16(RHINE_EVENT & 0xffff, rp->base + IntrEnable); out_unlock: mutex_unlock(&rp->task_lock); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8d208dd92963..b1038c0e2240 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -298,11 +298,12 @@ static void tun_flow_cleanup(unsigned long data) } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, - u16 queue_index) + struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; + u16 queue_index = tfile->queue_index; if (!rxhash) return; @@ -311,7 +312,9 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, rcu_read_lock(); - if (tun->numqueues == 1) + /* We may get a very small possibility of OOO during switching, not + * worth to optimize.*/ + if (tun->numqueues == 1 || tfile->detached) goto unlock; e = tun_flow_find(head, rxhash); @@ -411,21 +414,21 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun = rtnl_dereference(tfile->tun); - if (tun) { + if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); dev = tun->dev; rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); - rcu_assign_pointer(tfile->tun, NULL); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; --tun->numqueues; - if (clean) + if (clean) { + rcu_assign_pointer(tfile->tun, NULL); sock_put(&tfile->sk); - else + } else tun_disable_queue(tun, tfile); synchronize_net(); @@ -439,10 +442,13 @@ static void __tun_detach(struct tun_file *tfile, bool clean) } if (clean) { - if (tun && tun->numqueues == 0 && tun->numdisabled == 0 && - !(tun->flags & TUN_PERSIST)) - if (tun->dev->reg_state == NETREG_REGISTERED) + if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { + netif_carrier_off(tun->dev); + + if (!(tun->flags & TUN_PERSIST) && + tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); + } BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags)); @@ -470,6 +476,10 @@ static void tun_detach_all(struct net_device *dev) rcu_assign_pointer(tfile->tun, NULL); --tun->numqueues; } + list_for_each_entry(tfile, &tun->disabled, next) { + wake_up_all(&tfile->wq.wait); + rcu_assign_pointer(tfile->tun, NULL); + } BUG_ON(tun->numqueues != 0); synchronize_net(); @@ -500,7 +510,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file) goto out; err = -EINVAL; - if (rtnl_dereference(tfile->tun)) + if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; @@ -1203,7 +1213,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, tun->dev->stats.rx_packets++; tun->dev->stats.rx_bytes += len; - tun_flow_update(tun, rxhash, tfile->queue_index); + tun_flow_update(tun, rxhash, tfile); return total_len; } @@ -1662,10 +1672,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) device_create_file(&tun->dev->dev, &dev_attr_owner) || device_create_file(&tun->dev->dev, &dev_attr_group)) pr_err("Failed to create tun sysfs files\n"); - - netif_carrier_on(tun->dev); } + netif_carrier_on(tun->dev); + tun_debug(KERN_INFO, tun, "tun_set_iff\n"); if (ifr->ifr_flags & IFF_NO_PI) @@ -1817,7 +1827,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) ret = tun_attach(tun, file); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); - if (!tun || !(tun->flags & TUN_TAP_MQ)) + if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 575a5839ee34..2ca7f8ea2dca 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -461,6 +461,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ + {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 30c1b330e983..51f3192f3931 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -380,6 +380,12 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) unsigned long lockflags; size_t size = dev->rx_urb_size; + /* prevent rx skb allocation when error ratio is high */ + if (test_bit(EVENT_RX_KILL, &dev->flags)) { + usb_free_urb(urb); + return -ENOLINK; + } + skb = __netdev_alloc_skb_ip_align(dev->net, size, flags); if (!skb) { netif_dbg(dev, rx_err, dev->net, "no rx skb\n"); @@ -539,6 +545,17 @@ block: break; } + /* stop rx if packet error rate is high */ + if (++dev->pkt_cnt > 30) { + dev->pkt_cnt = 0; + dev->pkt_err = 0; + } else { + if (state == rx_cleanup) + dev->pkt_err++; + if (dev->pkt_err > 20) + set_bit(EVENT_RX_KILL, &dev->flags); + } + state = defer_bh(dev, skb, &dev->rxq, state); if (urb) { @@ -791,6 +808,11 @@ int usbnet_open (struct net_device *net) (dev->driver_info->flags & FLAG_FRAMING_AX) ? "ASIX" : "simple"); + /* reset rx error state */ + dev->pkt_cnt = 0; + dev->pkt_err = 0; + clear_bit(EVENT_RX_KILL, &dev->flags); + // delay posting reads until we're fully open tasklet_schedule (&dev->bh); if (info->manage_power) { @@ -1103,13 +1125,11 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, if (info->tx_fixup) { skb = info->tx_fixup (dev, skb, GFP_ATOMIC); if (!skb) { - if (netif_msg_tx_err(dev)) { - netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); - goto drop; - } else { - /* cdc_ncm collected packet; waits for more */ + /* packet collected; minidriver waiting for more */ + if (info->flags & FLAG_MULTI_PACKET) goto not_drop; - } + netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); + goto drop; } } length = skb->len; @@ -1254,6 +1274,9 @@ static void usbnet_bh (unsigned long param) } } + /* restart RX again after disabling due to high error rate */ + clear_bit(EVENT_RX_KILL, &dev->flags); + // waiting for all pending urbs to complete? if (dev->wait) { if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) { diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index b1c90f8ccd3d..ffb97b2a15a0 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -150,8 +150,7 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue) if (ret & 1) { /* Link is up. */ netdev_info(adapter->netdev, "NIC Link is Up %d Mbps\n", adapter->link_speed); - if (!netif_carrier_ok(adapter->netdev)) - netif_carrier_on(adapter->netdev); + netif_carrier_on(adapter->netdev); if (affectTxQueue) { for (i = 0; i < adapter->num_tx_queues; i++) @@ -160,8 +159,7 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue) } } else { netdev_info(adapter->netdev, "NIC Link is Down\n"); - if (netif_carrier_ok(adapter->netdev)) - netif_carrier_off(adapter->netdev); + netif_carrier_off(adapter->netdev); if (affectTxQueue) { for (i = 0; i < adapter->num_tx_queues; i++) @@ -3060,6 +3058,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); netif_set_real_num_rx_queues(adapter->netdev, adapter->num_rx_queues); + netif_carrier_off(netdev); err = register_netdev(netdev); if (err) { diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c index c26992a60e6c..8d560b64516d 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/main.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c @@ -1027,7 +1027,6 @@ brcms_c_dotxstatus(struct brcms_c_info *wlc, struct tx_status *txs) static bool brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal) { - bool morepending = false; struct bcma_device *core; struct tx_status txstatus, *txs; u32 s1, s2; @@ -1041,23 +1040,20 @@ brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal) txs = &txstatus; core = wlc_hw->d11core; *fatal = false; - s1 = bcma_read32(core, D11REGOFFS(frmtxstatus)); - while (!(*fatal) - && (s1 & TXS_V)) { - /* !give others some time to run! */ - if (n >= max_tx_num) { - morepending = true; - break; - } + while (n < max_tx_num) { + s1 = bcma_read32(core, D11REGOFFS(frmtxstatus)); if (s1 == 0xffffffff) { brcms_err(core, "wl%d: %s: dead chip\n", wlc_hw->unit, __func__); *fatal = true; return false; } - s2 = bcma_read32(core, D11REGOFFS(frmtxstatus2)); + /* only process when valid */ + if (!(s1 & TXS_V)) + break; + s2 = bcma_read32(core, D11REGOFFS(frmtxstatus2)); txs->status = s1 & TXS_STATUS_MASK; txs->frameid = (s1 & TXS_FID_MASK) >> TXS_FID_SHIFT; txs->sequence = s2 & TXS_SEQ_MASK; @@ -1065,15 +1061,12 @@ brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal) txs->lasttxtime = 0; *fatal = brcms_c_dotxstatus(wlc_hw->wlc, txs); - - s1 = bcma_read32(core, D11REGOFFS(frmtxstatus)); + if (*fatal == true) + return false; n++; } - if (*fatal) - return false; - - return morepending; + return n >= max_tx_num; } static void brcms_c_tbtt(struct brcms_c_info *wlc) diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c index 6b01fc195940..191b9d4bee47 100644 --- a/drivers/net/wireless/iwlwifi/dvm/tx.c +++ b/drivers/net/wireless/iwlwifi/dvm/tx.c @@ -1145,6 +1145,13 @@ int iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb, next_reclaimed = ssn; } + if (tid != IWL_TID_NON_QOS) { + priv->tid_data[sta_id][tid].next_reclaimed = + next_reclaimed; + IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n", + next_reclaimed); + } + iwl_trans_reclaim(priv->trans, txq_id, ssn, &skbs); iwlagn_check_ratid_empty(priv, sta_id, tid); @@ -1195,30 +1202,12 @@ int iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb, if (!is_agg) iwlagn_non_agg_tx_status(priv, ctx, hdr->addr1); - /* - * W/A for FW bug - the seq_ctl isn't updated when the - * queues are flushed. Fetch it from the packet itself - */ - if (!is_agg && status == TX_STATUS_FAIL_FIFO_FLUSHED) { - next_reclaimed = le16_to_cpu(hdr->seq_ctrl); - next_reclaimed = - SEQ_TO_SN(next_reclaimed + 0x10); - } - is_offchannel_skb = (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN); freed++; } - if (tid != IWL_TID_NON_QOS) { - priv->tid_data[sta_id][tid].next_reclaimed = - next_reclaimed; - IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n", - next_reclaimed); - } - - if (!is_agg && freed != 1) - IWL_ERR(priv, "Q: %d, freed %d\n", txq_id, freed); + WARN_ON(!is_agg && freed != 1); /* * An offchannel frame can be send only on the AUX queue, where diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c index f0de40166dc3..d41f0e647280 100644 --- a/drivers/net/wireless/mwifiex/scan.c +++ b/drivers/net/wireless/mwifiex/scan.c @@ -1557,7 +1557,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, dev_err(adapter->dev, "SCAN_RESP: too many AP returned (%d)\n", scan_rsp->number_of_sets); ret = -1; - goto done; + goto check_next_scan; } bytes_left = le16_to_cpu(scan_rsp->bss_descript_size); @@ -1628,7 +1628,8 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, if (!beacon_size || beacon_size > bytes_left) { bss_info += bytes_left; bytes_left = 0; - return -1; + ret = -1; + goto check_next_scan; } /* Initialize the current working beacon pointer for this BSS @@ -1684,7 +1685,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, dev_err(priv->adapter->dev, "%s: bytes left < IE length\n", __func__); - goto done; + goto check_next_scan; } if (element_id == WLAN_EID_DS_PARAMS) { channel = *(current_ptr + sizeof(struct ieee_types_header)); @@ -1747,6 +1748,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, } } +check_next_scan: spin_lock_irqsave(&adapter->scan_pending_q_lock, flags); if (list_empty(&adapter->scan_pending_q)) { spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags); @@ -1807,7 +1809,6 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, } } -done: return ret; } diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c index f2ecdeb3a90d..1535efda3d52 100644 --- a/drivers/net/wireless/rtlwifi/usb.c +++ b/drivers/net/wireless/rtlwifi/usb.c @@ -542,8 +542,8 @@ static void _rtl_rx_pre_process(struct ieee80211_hw *hw, struct sk_buff *skb) WARN_ON(skb_queue_empty(&rx_queue)); while (!skb_queue_empty(&rx_queue)) { _skb = skb_dequeue(&rx_queue); - _rtl_usb_rx_process_agg(hw, skb); - ieee80211_rx_irqsafe(hw, skb); + _rtl_usb_rx_process_agg(hw, _skb); + ieee80211_rx_irqsafe(hw, _skb); } } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index ebd08b21b234..959b1cd89e6a 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -165,12 +165,16 @@ static void tx_poll_stop(struct vhost_net *net) } /* Caller must have TX VQ lock */ -static void tx_poll_start(struct vhost_net *net, struct socket *sock) +static int tx_poll_start(struct vhost_net *net, struct socket *sock) { + int ret; + if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED)) - return; - vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file); - net->tx_poll_state = VHOST_NET_POLL_STARTED; + return 0; + ret = vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file); + if (!ret) + net->tx_poll_state = VHOST_NET_POLL_STARTED; + return ret; } /* In case of DMA done not in order in lower device driver for some reason. @@ -642,20 +646,23 @@ static void vhost_net_disable_vq(struct vhost_net *n, vhost_poll_stop(n->poll + VHOST_NET_VQ_RX); } -static void vhost_net_enable_vq(struct vhost_net *n, +static int vhost_net_enable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct socket *sock; + int ret; sock = rcu_dereference_protected(vq->private_data, lockdep_is_held(&vq->mutex)); if (!sock) - return; + return 0; if (vq == n->vqs + VHOST_NET_VQ_TX) { n->tx_poll_state = VHOST_NET_POLL_STOPPED; - tx_poll_start(n, sock); + ret = tx_poll_start(n, sock); } else - vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file); + ret = vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file); + + return ret; } static struct socket *vhost_net_stop_vq(struct vhost_net *n, @@ -827,15 +834,18 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = PTR_ERR(ubufs); goto err_ubufs; } - oldubufs = vq->ubufs; - vq->ubufs = ubufs; + vhost_net_disable_vq(n, vq); rcu_assign_pointer(vq->private_data, sock); - vhost_net_enable_vq(n, vq); - r = vhost_init_used(vq); if (r) - goto err_vq; + goto err_used; + r = vhost_net_enable_vq(n, vq); + if (r) + goto err_used; + + oldubufs = vq->ubufs; + vq->ubufs = ubufs; n->tx_packets = 0; n->tx_zcopy_err = 0; @@ -859,6 +869,11 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) mutex_unlock(&n->dev.mutex); return 0; +err_used: + rcu_assign_pointer(vq->private_data, oldsock); + vhost_net_enable_vq(n, vq); + if (ubufs) + vhost_ubuf_put_and_wait(ubufs); err_ubufs: fput(sock->file); err_vq: diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 34389f75fe65..9759249e6d90 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -77,26 +77,38 @@ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, init_poll_funcptr(&poll->table, vhost_poll_func); poll->mask = mask; poll->dev = dev; + poll->wqh = NULL; vhost_work_init(&poll->work, fn); } /* Start polling a file. We add ourselves to file's wait queue. The caller must * keep a reference to a file until after vhost_poll_stop is called. */ -void vhost_poll_start(struct vhost_poll *poll, struct file *file) +int vhost_poll_start(struct vhost_poll *poll, struct file *file) { unsigned long mask; + int ret = 0; mask = file->f_op->poll(file, &poll->table); if (mask) vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask); + if (mask & POLLERR) { + if (poll->wqh) + remove_wait_queue(poll->wqh, &poll->wait); + ret = -EINVAL; + } + + return ret; } /* Stop polling a file. After this function returns, it becomes safe to drop the * file reference. You must also flush afterwards. */ void vhost_poll_stop(struct vhost_poll *poll) { - remove_wait_queue(poll->wqh, &poll->wait); + if (poll->wqh) { + remove_wait_queue(poll->wqh, &poll->wait); + poll->wqh = NULL; + } } static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work, @@ -792,7 +804,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) fput(filep); if (pollstart && vq->handle_kick) - vhost_poll_start(&vq->poll, vq->kick); + r = vhost_poll_start(&vq->poll, vq->kick); mutex_unlock(&vq->mutex); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 2639c58b23ab..17261e277c02 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -42,7 +42,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work); void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, unsigned long mask, struct vhost_dev *dev); -void vhost_poll_start(struct vhost_poll *poll, struct file *file); +int vhost_poll_start(struct vhost_poll *poll, struct file *file); void vhost_poll_stop(struct vhost_poll *poll); void vhost_poll_flush(struct vhost_poll *poll); void vhost_poll_queue(struct vhost_poll *poll); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4e1d2283e3cc..6d0d46138ae8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -246,7 +246,6 @@ struct tcp_sock { u32 sacked_out; /* SACK'd packets */ u32 fackets_out; /* FACK'd packets */ u32 tso_deferred; - u32 bytes_acked; /* Appropriate Byte Counting - RFC3465 */ /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 5de7a220e986..0de078d4cdb9 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -33,6 +33,7 @@ struct usbnet { wait_queue_head_t *wait; struct mutex phy_mutex; unsigned char suspend_count; + unsigned char pkt_cnt, pkt_err; /* i/o info: pipes etc */ unsigned in, out; @@ -70,6 +71,7 @@ struct usbnet { # define EVENT_DEV_OPEN 7 # define EVENT_DEVICE_REPORT_IDLE 8 # define EVENT_NO_RUNTIME_PM 9 +# define EVENT_RX_KILL 10 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) diff --git a/include/net/tcp.h b/include/net/tcp.h index 614af8b7758e..23f2e98d4b65 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -279,7 +279,6 @@ extern int sysctl_tcp_dma_copybreak; extern int sysctl_tcp_nometrics_save; extern int sysctl_tcp_moderate_rcvbuf; extern int sysctl_tcp_tso_win_divisor; -extern int sysctl_tcp_abc; extern int sysctl_tcp_mtu_probing; extern int sysctl_tcp_base_mss; extern int sysctl_tcp_workaround_signed_windows; diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 498433dd067d..938b7fd11204 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -34,17 +34,17 @@ extern int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); -extern int datagram_recv_ctl(struct sock *sk, - struct msghdr *msg, - struct sk_buff *skb); - -extern int datagram_send_ctl(struct net *net, - struct sock *sk, - struct msghdr *msg, - struct flowi6 *fl6, - struct ipv6_txoptions *opt, - int *hlimit, int *tclass, - int *dontfrag); +extern int ip6_datagram_recv_ctl(struct sock *sk, + struct msghdr *msg, + struct sk_buff *skb); + +extern int ip6_datagram_send_ctl(struct net *net, + struct sock *sk, + struct msghdr *msg, + struct flowi6 *fl6, + struct ipv6_txoptions *opt, + int *hlimit, int *tclass, + int *dontfrag); #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006) diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 5a6384450501..b669ca1fa103 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -387,7 +387,6 @@ static const struct bin_table bin_net_ipv4_table[] = { { CTL_INT, NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, { CTL_INT, NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, { CTL_STR, NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, - { CTL_INT, NET_TCP_ABC, "tcp_abc" }, { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" }, { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 797769551b91..2201e699ad67 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1790,10 +1790,13 @@ static ssize_t pktgen_thread_write(struct file *file, return -EFAULT; i += len; mutex_lock(&pktgen_thread_lock); - pktgen_add_device(t, f); + ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bddc1dd2e7f2..55f7ef6ada6d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -686,7 +686,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->network_header = old->network_header; new->mac_header = old->mac_header; new->inner_transport_header = old->inner_transport_header; - new->inner_network_header = old->inner_transport_header; + new->inner_network_header = old->inner_network_header; skb_dst_copy(new, old); new->rxhash = old->rxhash; new->ooo_okay = old->ooo_okay; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 49ddca31c4da..1aec92bf8018 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -263,21 +263,6 @@ void build_ehash_secret(void) } EXPORT_SYMBOL(build_ehash_secret); -static inline int inet_netns_ok(struct net *net, __u8 protocol) -{ - const struct net_protocol *ipprot; - - if (net_eq(net, &init_net)) - return 1; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot == NULL) { - /* raw IP is OK */ - return 1; - } - return ipprot->netns_ok; -} - /* * Create an inet socket. */ @@ -350,10 +335,6 @@ lookup_protocol: !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; - err = -EAFNOSUPPORT; - if (!inet_netns_ok(net, protocol)) - goto out_rcu_unlock; - sock->ops = answer->ops; answer_prot = answer->prot; answer_no_check = answer->no_check; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f1395a6fb35f..87abd3e2bd32 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -208,13 +208,6 @@ static int ip_local_deliver_finish(struct sk_buff *skb) if (ipprot != NULL) { int ret; - if (!net_eq(net, &init_net) && !ipprot->netns_ok) { - net_info_ratelimited("%s: proto %d isn't netns-ready\n", - __func__, protocol); - kfree_skb(skb); - goto out; - } - if (!ipprot->no_policy) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { kfree_skb(skb); diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 0f9d09f54bd9..ce848461acbb 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -37,6 +37,12 @@ const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { + if (!prot->netns_ok) { + pr_err("Protocol %u is not namespace aware, cannot register.\n", + protocol); + return -EINVAL; + } + return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], NULL, prot) ? 0 : -1; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 2622707602d1..960fd29d9b8e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -633,13 +633,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_tcp_congestion_control, }, { - .procname = "tcp_abc", - .data = &sysctl_tcp_abc, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { .procname = "tcp_mtu_probing", .data = &sysctl_tcp_mtu_probing, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3ec1f69c5ceb..2c7e5963c2ea 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2289,7 +2289,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->packets_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 291f2ed7cc31..019c2389a341 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -310,35 +310,24 @@ void tcp_slow_start(struct tcp_sock *tp) { int cnt; /* increase in packets */ unsigned int delta = 0; + u32 snd_cwnd = tp->snd_cwnd; - /* RFC3465: ABC Slow start - * Increase only after a full MSS of bytes is acked - * - * TCP sender SHOULD increase cwnd by the number of - * previously unacknowledged bytes ACKed by each incoming - * acknowledgment, provided the increase is not more than L - */ - if (sysctl_tcp_abc && tp->bytes_acked < tp->mss_cache) - return; + if (unlikely(!snd_cwnd)) { + pr_err_once("snd_cwnd is nul, please report this bug.\n"); + snd_cwnd = 1U; + } if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh) cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */ else - cnt = tp->snd_cwnd; /* exponential increase */ - - /* RFC3465: ABC - * We MAY increase by 2 if discovered delayed ack - */ - if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache) - cnt <<= 1; - tp->bytes_acked = 0; + cnt = snd_cwnd; /* exponential increase */ tp->snd_cwnd_cnt += cnt; - while (tp->snd_cwnd_cnt >= tp->snd_cwnd) { - tp->snd_cwnd_cnt -= tp->snd_cwnd; + while (tp->snd_cwnd_cnt >= snd_cwnd) { + tp->snd_cwnd_cnt -= snd_cwnd; delta++; } - tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp); + tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_slow_start); @@ -372,20 +361,9 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) /* In "safe" area, increase. */ if (tp->snd_cwnd <= tp->snd_ssthresh) tcp_slow_start(tp); - /* In dangerous area, increase slowly. */ - else if (sysctl_tcp_abc) { - /* RFC3465: Appropriate Byte Count - * increase once for each full cwnd acked - */ - if (tp->bytes_acked >= tp->snd_cwnd*tp->mss_cache) { - tp->bytes_acked -= tp->snd_cwnd*tp->mss_cache; - if (tp->snd_cwnd < tp->snd_cwnd_clamp) - tp->snd_cwnd++; - } - } else { + else tcp_cong_avoid_ai(tp, tp->snd_cwnd); - } } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 492c7cfe1453..f56bd1082f54 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -98,7 +98,6 @@ int sysctl_tcp_frto_response __read_mostly; int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; -int sysctl_tcp_abc __read_mostly; int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ @@ -2007,7 +2006,6 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; tp->frto_counter = 0; - tp->bytes_acked = 0; tp->reordering = min_t(unsigned int, tp->reordering, sysctl_tcp_reordering); @@ -2056,7 +2054,6 @@ void tcp_enter_loss(struct sock *sk, int how) tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; - tp->bytes_acked = 0; tcp_clear_retrans_partial(tp); if (tcp_is_reno(tp)) @@ -2684,7 +2681,6 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) struct tcp_sock *tp = tcp_sk(sk); tp->high_seq = tp->snd_nxt; - tp->bytes_acked = 0; tp->snd_cwnd_cnt = 0; tp->prior_cwnd = tp->snd_cwnd; tp->prr_delivered = 0; @@ -2735,7 +2731,6 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) struct tcp_sock *tp = tcp_sk(sk); tp->prior_ssthresh = 0; - tp->bytes_acked = 0; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { tp->undo_marker = 0; tcp_init_cwnd_reduction(sk, set_ssthresh); @@ -3417,7 +3412,6 @@ static void tcp_conservative_spur_to_response(struct tcp_sock *tp) { tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; TCP_ECN_queue_cwr(tp); tcp_moderate_cwnd(tp); } @@ -3482,7 +3476,8 @@ static bool tcp_process_frto(struct sock *sk, int flag) ((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED))) tp->undo_marker = 0; - if (!before(tp->snd_una, tp->frto_highmark)) { + if (!before(tp->snd_una, tp->frto_highmark) || + !tcp_packets_in_flight(tp)) { tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag); return true; } @@ -3608,15 +3603,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, prior_snd_una)) flag |= FLAG_SND_UNA_ADVANCED; - if (sysctl_tcp_abc) { - if (icsk->icsk_ca_state < TCP_CA_CWR) - tp->bytes_acked += ack - prior_snd_una; - else if (icsk->icsk_ca_state == TCP_CA_Loss) - /* we assume just one segment left network */ - tp->bytes_acked += min(ack - prior_snd_una, - tp->mss_cache); - } - prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); @@ -5647,8 +5633,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, * the remote receives only the retransmitted (regular) SYNs: either * the original SYN-data or the corresponding SYN-ACK is lost. */ - syn_drop = (cookie->len <= 0 && data && - inet_csk(sk)->icsk_retransmits); + syn_drop = (cookie->len <= 0 && data && tp->total_retrans); tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5a1cfc692df0..0eaf685bddc9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -496,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -1501,8 +1502,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * clogging syn queue with openreqs with exponentially increasing * timeout. */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) @@ -1667,6 +1670,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f35f2dfb6401..f0409287b5f4 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -446,7 +446,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, */ newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; - newtp->bytes_acked = 0; newtp->frto_counter = 0; newtp->frto_highmark = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7f7332b44699..bd9f9360f769 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1656,6 +1656,7 @@ static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) if (dev->addr_len != IEEE802154_ADDR_LEN) return -1; memcpy(eui, dev->dev_addr, 8); + eui[0] ^= 2; return 0; } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 33be36398a78..f5a54782a340 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -380,7 +380,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { @@ -468,7 +468,8 @@ out: } -int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) +int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_skb_parm *opt = IP6CB(skb); @@ -598,11 +599,12 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } return 0; } +EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); -int datagram_send_ctl(struct net *net, struct sock *sk, - struct msghdr *msg, struct flowi6 *fl6, - struct ipv6_txoptions *opt, - int *hlimit, int *tclass, int *dontfrag) +int ip6_datagram_send_ctl(struct net *net, struct sock *sk, + struct msghdr *msg, struct flowi6 *fl6, + struct ipv6_txoptions *opt, + int *hlimit, int *tclass, int *dontfrag) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -872,4 +874,4 @@ int datagram_send_ctl(struct net *net, struct sock *sk, exit_f: return err; } -EXPORT_SYMBOL_GPL(datagram_send_ctl); +EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 22494afd981c..ea42bf40a997 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -390,8 +390,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, msg.msg_control = (void*)(fl->opt+1); memset(&flowi6, 0, sizeof(flowi6)); - err = datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, &junk, - &junk, &junk); + err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, + &junk, &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ee94d31c9d4d..d1e2e8ef29c5 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -476,8 +476,8 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, &junk, - &junk); + retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, + &junk, &junk); if (retv) goto done; update: @@ -1002,7 +1002,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, release_sock(sk); if (skb) { - int err = datagram_recv_ctl(sk, &msg, skb); + int err = ip6_datagram_recv_ctl(sk, &msg, skb); kfree_skb(skb); if (err) return err; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 6cd29b1e8b92..70fa81449997 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -507,7 +507,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) @@ -822,8 +822,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 06087e58738a..bbb28ae7e5f3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -423,6 +423,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -959,8 +960,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop; } - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) @@ -1109,6 +1112,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index cb5bf497c09c..599e1ba6d1ce 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -467,7 +467,7 @@ try_again: ip_cmsg_recv(msg, skb); } else { if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); } err = copied; @@ -1143,8 +1143,8 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 1a9f3723c13c..b6ba65fa3c50 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -101,6 +101,7 @@ struct l2tp_skb_cb { static atomic_t l2tp_tunnel_count; static atomic_t l2tp_session_count; +static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; @@ -122,7 +123,6 @@ static inline struct l2tp_net *l2tp_pernet(struct net *net) return net_generic(net, l2tp_net_id); } - /* Tunnel reference counts. Incremented per session that is added to * the tunnel. */ @@ -168,6 +168,51 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } +/* Lookup the tunnel socket, possibly involving the fs code if the socket is + * owned by userspace. A struct sock returned from this function must be + * released using l2tp_tunnel_sock_put once you're done with it. + */ +struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) +{ + int err = 0; + struct socket *sock = NULL; + struct sock *sk = NULL; + + if (!tunnel) + goto out; + + if (tunnel->fd >= 0) { + /* Socket is owned by userspace, who might be in the process + * of closing it. Look the socket up using the fd to ensure + * consistency. + */ + sock = sockfd_lookup(tunnel->fd, &err); + if (sock) + sk = sock->sk; + } else { + /* Socket is owned by kernelspace */ + sk = tunnel->sock; + } + +out: + return sk; +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup); + +/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ +void l2tp_tunnel_sock_put(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + if (tunnel) { + if (tunnel->fd >= 0) { + /* Socket is owned by userspace */ + sockfd_put(sk->sk_socket); + } + sock_put(sk); + } +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); + /* Lookup a session by id in the global session list */ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id) @@ -1232,6 +1277,7 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel; + struct l2tp_net *pn; tunnel = sk->sk_user_data; if (tunnel == NULL) @@ -1239,9 +1285,8 @@ static void l2tp_tunnel_destruct(struct sock *sk) l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Close all sessions */ - l2tp_tunnel_closeall(tunnel); + /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ @@ -1253,17 +1298,23 @@ static void l2tp_tunnel_destruct(struct sock *sk) } /* Remove hooks into tunnel socket */ - tunnel->sock = NULL; sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; + tunnel->sock = NULL; - /* Call the original destructor */ - if (sk->sk_destruct) - (*sk->sk_destruct)(sk); + /* Remove the tunnel struct from the tunnel list */ + pn = l2tp_pernet(tunnel->l2tp_net); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_del_rcu(&tunnel->list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + atomic_dec(&l2tp_tunnel_count); - /* We're finished with the socket */ + l2tp_tunnel_closeall(tunnel); l2tp_tunnel_dec_refcount(tunnel); + /* Call the original destructor */ + if (sk->sk_destruct) + (*sk->sk_destruct)(sk); end: return; } @@ -1337,48 +1388,77 @@ again: */ static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - BUG_ON(atomic_read(&tunnel->ref_count) != 0); BUG_ON(tunnel->sock != NULL); - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: free...\n", tunnel->name); - - /* Remove from tunnel list */ - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); kfree_rcu(tunnel, rcu); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); +} - atomic_dec(&l2tp_tunnel_count); +/* Workqueue tunnel deletion function */ +static void l2tp_tunnel_del_work(struct work_struct *work) +{ + struct l2tp_tunnel *tunnel = NULL; + struct socket *sock = NULL; + struct sock *sk = NULL; + + tunnel = container_of(work, struct l2tp_tunnel, del_work); + sk = l2tp_tunnel_sock_lookup(tunnel); + if (!sk) + return; + + sock = sk->sk_socket; + BUG_ON(!sock); + + /* If the tunnel socket was created directly by the kernel, use the + * sk_* API to release the socket now. Otherwise go through the + * inet_* layer to shut the socket down, and let userspace close it. + * In either case the tunnel resources are freed in the socket + * destructor when the tunnel socket goes away. + */ + if (sock->file == NULL) { + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sk); + } else { + inet_shutdown(sock, 2); + } + + l2tp_tunnel_sock_put(sk); } /* Create a socket for the tunnel, if one isn't set up by * userspace. This is used for static tunnels where there is no * managing L2TP daemon. + * + * Since we don't want these sockets to keep a namespace alive by + * themselves, we drop the socket's namespace refcount after creation. + * These sockets are freed when the namespace exits using the pernet + * exit hook. */ -static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp) +static int l2tp_tunnel_sock_create(struct net *net, + u32 tunnel_id, + u32 peer_tunnel_id, + struct l2tp_tunnel_cfg *cfg, + struct socket **sockp) { int err = -EINVAL; - struct sockaddr_in udp_addr; + struct socket *sock = NULL; + struct sockaddr_in udp_addr = {0}; + struct sockaddr_l2tpip ip_addr = {0}; #if IS_ENABLED(CONFIG_IPV6) - struct sockaddr_in6 udp6_addr; - struct sockaddr_l2tpip6 ip6_addr; + struct sockaddr_in6 udp6_addr = {0}; + struct sockaddr_l2tpip6 ip6_addr = {0}; #endif - struct sockaddr_l2tpip ip_addr; - struct socket *sock = NULL; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { - err = sock_create(AF_INET6, SOCK_DGRAM, 0, sockp); + err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); @@ -1400,13 +1480,12 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t } else #endif { - err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp); + err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&udp_addr, 0, sizeof(udp_addr)); udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = htons(cfg->local_udp_port); @@ -1433,14 +1512,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { - err = sock_create(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, - sockp); + err = sock_create_kern(AF_INET6, SOCK_DGRAM, + IPPROTO_L2TP, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&ip6_addr, 0, sizeof(ip6_addr)); ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); @@ -1462,14 +1540,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t } else #endif { - err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, - sockp); + err = sock_create_kern(AF_INET, SOCK_DGRAM, + IPPROTO_L2TP, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&ip_addr, 0, sizeof(ip_addr)); ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; @@ -1493,8 +1570,10 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t } out: + *sockp = sock; if ((err < 0) && sock) { - sock_release(sock); + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sock->sk); *sockp = NULL; } @@ -1517,15 +1596,23 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 * kernel socket. */ if (fd < 0) { - err = l2tp_tunnel_sock_create(tunnel_id, peer_tunnel_id, cfg, &sock); + err = l2tp_tunnel_sock_create(net, tunnel_id, peer_tunnel_id, + cfg, &sock); if (err < 0) goto err; } else { - err = -EBADF; sock = sockfd_lookup(fd, &err); if (!sock) { - pr_err("tunl %hu: sockfd_lookup(fd=%d) returned %d\n", + pr_err("tunl %u: sockfd_lookup(fd=%d) returned %d\n", tunnel_id, fd, err); + err = -EBADF; + goto err; + } + + /* Reject namespace mismatches */ + if (!net_eq(sock_net(sock->sk), net)) { + pr_err("tunl %u: netns mismatch\n", tunnel_id); + err = -EINVAL; goto err; } } @@ -1607,10 +1694,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; tunnel->sock = sk; + tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + /* Init delete workqueue struct */ + INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); + /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); atomic_inc(&l2tp_tunnel_count); @@ -1642,25 +1733,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); */ int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { - int err = 0; - struct socket *sock = tunnel->sock ? tunnel->sock->sk_socket : NULL; - - /* Force the tunnel socket to close. This will eventually - * cause the tunnel to be deleted via the normal socket close - * mechanisms when userspace closes the tunnel socket. - */ - if (sock != NULL) { - err = inet_shutdown(sock, 2); - - /* If the tunnel's socket was created by the kernel, - * close the socket here since the socket was not - * created by userspace. - */ - if (sock->file == NULL) - err = inet_release(sock); - } - - return err; + return (false == queue_work(l2tp_wq, &tunnel->del_work)); } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); @@ -1844,8 +1917,21 @@ static __net_init int l2tp_init_net(struct net *net) return 0; } +static __net_exit void l2tp_exit_net(struct net *net) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_tunnel *tunnel = NULL; + + rcu_read_lock_bh(); + list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { + (void)l2tp_tunnel_delete(tunnel); + } + rcu_read_unlock_bh(); +} + static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, + .exit = l2tp_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; @@ -1858,6 +1944,13 @@ static int __init l2tp_init(void) if (rc) goto out; + l2tp_wq = alloc_workqueue("l2tp", WQ_NON_REENTRANT | WQ_UNBOUND, 0); + if (!l2tp_wq) { + pr_err("alloc_workqueue failed\n"); + rc = -ENOMEM; + goto out; + } + pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: @@ -1867,6 +1960,10 @@ out: static void __exit l2tp_exit(void) { unregister_pernet_device(&l2tp_net_ops); + if (l2tp_wq) { + destroy_workqueue(l2tp_wq); + l2tp_wq = NULL; + } } module_init(l2tp_init); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 56d583e083a7..8eb8f1d47f3a 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -188,7 +188,10 @@ struct l2tp_tunnel { int (*recv_payload_hook)(struct sk_buff *skb); void (*old_sk_destruct)(struct sock *); struct sock *sock; /* Parent socket */ - int fd; + int fd; /* Parent fd, if tunnel socket + * was created by userspace */ + + struct work_struct del_work; uint8_t priv[0]; /* private data */ }; @@ -228,6 +231,8 @@ out: return tunnel; } +extern struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel); +extern void l2tp_tunnel_sock_put(struct sock *sk); extern struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth); extern struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 61d8b75d2686..f7ac8f42fee2 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -115,6 +115,7 @@ static inline struct sock *l2tp_ip_bind_lookup(struct net *net, __be32 laddr, in */ static int l2tp_ip_recv(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); struct sock *sk; u32 session_id; u32 tunnel_id; @@ -142,7 +143,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_find(&init_net, NULL, session_id); + session = l2tp_session_find(net, NULL, session_id); if (session == NULL) goto discard; @@ -173,14 +174,14 @@ pass_up: goto discard; tunnel_id = ntohl(*(__be32 *) &skb->data[4]); - tunnel = l2tp_tunnel_find(&init_net, tunnel_id); + tunnel = l2tp_tunnel_find(net, tunnel_id); if (tunnel != NULL) sk = tunnel->sock; else { struct iphdr *iph = (struct iphdr *) skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); - sk = __l2tp_ip_bind_lookup(&init_net, iph->daddr, 0, tunnel_id); + sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id); read_unlock_bh(&l2tp_ip_lock); } @@ -239,6 +240,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *) uaddr; + struct net *net = sock_net(sk); int ret; int chk_addr_ret; @@ -251,7 +253,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) ret = -EADDRINUSE; read_lock_bh(&l2tp_ip_lock); - if (__l2tp_ip_bind_lookup(&init_net, addr->l2tp_addr.s_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id)) + if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, + sk->sk_bound_dev_if, addr->l2tp_conn_id)) goto out_in_use; read_unlock_bh(&l2tp_ip_lock); @@ -260,7 +263,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip)) goto out; - chk_addr_ret = inet_addr_type(&init_net, addr->l2tp_addr.s_addr); + chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) @@ -369,7 +372,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) return 0; drop: - IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return -1; } @@ -605,6 +608,7 @@ static struct inet_protosw l2tp_ip_protosw = { static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, + .netns_ok = 1, }; static int __init l2tp_ip_init(void) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 927547171bc7..8ee4a86ae996 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -554,8 +554,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -646,7 +646,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { - struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name; size_t copied = 0; int err = -EOPNOTSUPP; @@ -688,8 +688,8 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, lsa->l2tp_scope_id = IP6CB(skb)->iif; } - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + if (np->rxopt.all) + ip6_datagram_recv_ctl(sk, msg, skb); if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index bbba3a19e944..c1bab22db85e 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -37,6 +37,7 @@ static struct genl_family l2tp_nl_family = { .version = L2TP_GENL_VERSION, .hdrsize = 0, .maxattr = L2TP_ATTR_MAX, + .netnsok = true, }; /* Accessed under genl lock */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e639645e8fec..c111bd0e083a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2361,13 +2361,15 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); - memset(&req_u, 0, sizeof(req_u)); - - if (po->rx_ring.pg_vec) + if (po->rx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); + } - if (po->tx_ring.pg_vec) + if (po->tx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); + } fanout_release(sk); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 298c0ddfb57e..3d2acc7a9c80 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -438,18 +438,18 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (q->rate) { struct sk_buff_head *list = &sch->q; - delay += packet_len_2_sched_time(skb->len, q); - if (!skb_queue_empty(list)) { /* - * Last packet in queue is reference point (now). - * First packet in queue is already in flight, - * calculate this time bonus and substract + * Last packet in queue is reference point (now), + * calculate this time bonus and subtract * from delay. */ - delay -= now - netem_skb_cb(skb_peek(list))->time_to_send; + delay -= netem_skb_cb(skb_peek_tail(list))->time_to_send - now; + delay = max_t(psched_tdiff_t, 0, delay); now = netem_skb_cb(skb_peek_tail(list))->time_to_send; } + + delay += packet_len_2_sched_time(skb->len, q); } cb->time_to_send = now + delay; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 0a148c9d2a5c..0f679df7d072 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -465,7 +465,7 @@ static int svc_udp_get_dest_address4(struct svc_rqst *rqstp, } /* - * See net/ipv6/datagram.c : datagram_recv_ctl + * See net/ipv6/datagram.c : ip6_datagram_recv_ctl */ static int svc_udp_get_dest_address6(struct svc_rqst *rqstp, struct cmsghdr *cmh) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 01592d7d4789..45f1618c8e23 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1358,7 +1358,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, &iwe, IW_EV_UINT_LEN); } - buf = kmalloc(30, GFP_ATOMIC); + buf = kmalloc(31, GFP_ATOMIC); if (buf) { memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVCUSTOM; |