From 06ee1c261360545c97fd836fff9dbd10ebd9301b Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Mon, 19 Jul 2010 11:52:59 -0400 Subject: wireless: use netif_rx_ni in ieee80211_send_layer2_update These synthetic frames are all triggered from userland requests in process context. https://bugzilla.kernel.org/show_bug.cgi?id=16412 Signed-off-by: John W. Linville diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c7000a6..67ee34f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -632,7 +632,7 @@ static void ieee80211_send_layer2_update(struct sta_info *sta) skb->dev = sta->sdata->dev; skb->protocol = eth_type_trans(skb, sta->sdata->dev); memset(skb->cb, 0, sizeof(skb->cb)); - netif_rx(skb); + netif_rx_ni(skb); } static void sta_apply_parameters(struct ieee80211_local *local, -- cgit v0.10.2 From a13773a53faa28cf79982601b6fc9ddb0ca45f36 Mon Sep 17 00:00:00 2001 From: Vladislav Zolotarov Date: Wed, 21 Jul 2010 05:59:01 +0000 Subject: bnx2x: Protect a SM state change Bug fix: Protect the statistics state machine state update with a spinlock. Otherwise there was a race condition that would cause the statistics to stay enabled despite the fact that they were disabled in the LINK_DOWN event handler. Signed-off-by: Vladislav Zolotarov Signed-off-by: Dmitry Kravkov Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h index 8bd2368..bb0872a 100644 --- a/drivers/net/bnx2x.h +++ b/drivers/net/bnx2x.h @@ -1062,6 +1062,10 @@ struct bnx2x { /* used to synchronize stats collecting */ int stats_state; + + /* used for synchronization of concurrent threads statistics handling */ + spinlock_t stats_lock; + /* used by dmae command loader */ struct dmae_command stats_dmae; int executer_idx; diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c index 57ff5b3..3dc876c 100644 --- a/drivers/net/bnx2x_main.c +++ b/drivers/net/bnx2x_main.c @@ -4849,16 +4849,18 @@ static const struct { static void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event) { - enum bnx2x_stats_state state = bp->stats_state; + enum bnx2x_stats_state state; if (unlikely(bp->panic)) return; - bnx2x_stats_stm[state][event].action(bp); + /* Protect a state change flow */ + spin_lock_bh(&bp->stats_lock); + state = bp->stats_state; bp->stats_state = bnx2x_stats_stm[state][event].next_state; + spin_unlock_bh(&bp->stats_lock); - /* Make sure the state has been "changed" */ - smp_wmb(); + bnx2x_stats_stm[state][event].action(bp); if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp)) DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n", @@ -9908,6 +9910,7 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp) mutex_init(&bp->port.phy_mutex); mutex_init(&bp->fw_mb_mutex); + spin_lock_init(&bp->stats_lock); #ifdef BCM_CNIC mutex_init(&bp->cnic_mutex); #endif -- cgit v0.10.2 From d0996faeec8b3ab5bda65074c274bc67baf13501 Mon Sep 17 00:00:00 2001 From: Vladislav Zolotarov Date: Wed, 21 Jul 2010 05:59:14 +0000 Subject: bnx2x: Protect statistics ramrod and sequence number Bug fix: Protect statistics ramrod sending code and a statistics counter update with a spinlock. Otherwise there was a race condition that would allow sending a statistics ramrods with the same sequence number or with sequence numbers not in a natural order, which would cause a FW assert. Signed-off-by: Vladislav Zolotarov Signed-off-by: Dmitry Kravkov Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c index 3dc876c..b86e47b 100644 --- a/drivers/net/bnx2x_main.c +++ b/drivers/net/bnx2x_main.c @@ -3789,6 +3789,8 @@ static void bnx2x_storm_stats_post(struct bnx2x *bp) struct eth_query_ramrod_data ramrod_data = {0}; int i, rc; + spin_lock_bh(&bp->stats_lock); + ramrod_data.drv_counter = bp->stats_counter++; ramrod_data.collect_port = bp->port.pmf ? 1 : 0; for_each_queue(bp, i) @@ -3802,6 +3804,8 @@ static void bnx2x_storm_stats_post(struct bnx2x *bp) bp->spq_left++; bp->stats_pending = 1; } + + spin_unlock_bh(&bp->stats_lock); } } @@ -4367,6 +4371,14 @@ static int bnx2x_storm_stats_update(struct bnx2x *bp) struct host_func_stats *fstats = bnx2x_sp(bp, func_stats); struct bnx2x_eth_stats *estats = &bp->eth_stats; int i; + u16 cur_stats_counter; + + /* Make sure we use the value of the counter + * used for sending the last stats ramrod. + */ + spin_lock_bh(&bp->stats_lock); + cur_stats_counter = bp->stats_counter - 1; + spin_unlock_bh(&bp->stats_lock); memcpy(&(fstats->total_bytes_received_hi), &(bnx2x_sp(bp, func_stats_base)->total_bytes_received_hi), @@ -4394,25 +4406,22 @@ static int bnx2x_storm_stats_update(struct bnx2x *bp) u32 diff; /* are storm stats valid? */ - if ((u16)(le16_to_cpu(xclient->stats_counter) + 1) != - bp->stats_counter) { + if (le16_to_cpu(xclient->stats_counter) != cur_stats_counter) { DP(BNX2X_MSG_STATS, "[%d] stats not updated by xstorm" " xstorm counter (0x%x) != stats_counter (0x%x)\n", - i, xclient->stats_counter, bp->stats_counter); + i, xclient->stats_counter, cur_stats_counter + 1); return -1; } - if ((u16)(le16_to_cpu(tclient->stats_counter) + 1) != - bp->stats_counter) { + if (le16_to_cpu(tclient->stats_counter) != cur_stats_counter) { DP(BNX2X_MSG_STATS, "[%d] stats not updated by tstorm" " tstorm counter (0x%x) != stats_counter (0x%x)\n", - i, tclient->stats_counter, bp->stats_counter); + i, tclient->stats_counter, cur_stats_counter + 1); return -2; } - if ((u16)(le16_to_cpu(uclient->stats_counter) + 1) != - bp->stats_counter) { + if (le16_to_cpu(uclient->stats_counter) != cur_stats_counter) { DP(BNX2X_MSG_STATS, "[%d] stats not updated by ustorm" " ustorm counter (0x%x) != stats_counter (0x%x)\n", - i, uclient->stats_counter, bp->stats_counter); + i, uclient->stats_counter, cur_stats_counter + 1); return -4; } -- cgit v0.10.2 From 0577589cc1d99700c2789b2fa075cc522d0de30b Mon Sep 17 00:00:00 2001 From: Vladislav Zolotarov Date: Wed, 21 Jul 2010 05:59:17 +0000 Subject: bnx2x: Advance a module version Advance a module version to 1.52.53-2. Signed-off-by: Vladislav Zolotarov Signed-off-by: Dmitry Kravkov Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c index b86e47b..46167c0 100644 --- a/drivers/net/bnx2x_main.c +++ b/drivers/net/bnx2x_main.c @@ -57,8 +57,8 @@ #include "bnx2x_init_ops.h" #include "bnx2x_dump.h" -#define DRV_MODULE_VERSION "1.52.53-1" -#define DRV_MODULE_RELDATE "2010/18/04" +#define DRV_MODULE_VERSION "1.52.53-2" +#define DRV_MODULE_RELDATE "2010/21/07" #define BNX2X_BC_VER 0x040200 #include -- cgit v0.10.2 From bded64a7ff82f6af56426a4ff2483888e5ad5fe9 Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Wed, 21 Jul 2010 06:40:31 +0000 Subject: ixgbe/igb: catch invalid VF settings Some ixgbe cards put an invalid VF device ID in the PCIe SR-IOV capability. The ixgbe driver is only valid for PFs or non SR-IOV hardware. It seems that the same problem could occur on igb hardware as well, so if we discover we are trying to initialize a VF in ixbge_probe or igb_probe, print an error and exit. Based on a patch for ixgbe from Chris Wright . Signed-off-by: Andy Gospodarek Cc: Chris Wright Acked-by: Chris Wright Acked-by: Greg Rose Signed-off-by: David S. Miller diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 3881918..cea37e0 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -1722,6 +1722,15 @@ static int __devinit igb_probe(struct pci_dev *pdev, u16 eeprom_apme_mask = IGB_EEPROM_APME; u32 part_num; + /* Catch broken hardware that put the wrong VF device ID in + * the PCIe SR-IOV capability. + */ + if (pdev->is_virtfn) { + WARN(1, KERN_ERR "%s (%hx:%hx) should not be a VF!\n", + pci_name(pdev), pdev->vendor, pdev->device); + return -EINVAL; + } + err = pci_enable_device_mem(pdev); if (err) return err; diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 7b5d976..74d9b6d 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -6492,6 +6492,15 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, #endif u32 part_num, eec; + /* Catch broken hardware that put the wrong VF device ID in + * the PCIe SR-IOV capability. + */ + if (pdev->is_virtfn) { + WARN(1, KERN_ERR "%s (%hx:%hx) should not be a VF!\n", + pci_name(pdev), pdev->vendor, pdev->device); + return -EINVAL; + } + err = pci_enable_device_mem(pdev); if (err) return err; -- cgit v0.10.2 From 8a35747a5d13b99e076b0222729e0caa48cb69b6 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 21 Jul 2010 21:44:31 +0000 Subject: macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner Signed-off-by: Herbert Xu Acked-by: Chris Wright Acked-by: Arnd Bergmann Signed-off-by: David S. Miller diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 87e8d4c..f15fe2c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -499,7 +499,7 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_validate_addr = eth_validate_addr, }; -static void macvlan_setup(struct net_device *dev) +void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); @@ -508,6 +508,12 @@ static void macvlan_setup(struct net_device *dev) dev->destructor = free_netdev; dev->header_ops = &macvlan_hard_header_ops, dev->ethtool_ops = &macvlan_ethtool_ops; +} +EXPORT_SYMBOL_GPL(macvlan_common_setup); + +static void macvlan_setup(struct net_device *dev) +{ + macvlan_common_setup(dev); dev->tx_queue_len = 0; } @@ -705,7 +711,6 @@ int macvlan_link_register(struct rtnl_link_ops *ops) /* common fields */ ops->priv_size = sizeof(struct macvlan_dev); ops->get_tx_queues = macvlan_get_tx_queues; - ops->setup = macvlan_setup; ops->validate = macvlan_validate; ops->maxtype = IFLA_MACVLAN_MAX; ops->policy = macvlan_policy; @@ -719,6 +724,7 @@ EXPORT_SYMBOL_GPL(macvlan_link_register); static struct rtnl_link_ops macvlan_link_ops = { .kind = "macvlan", + .setup = macvlan_setup, .newlink = macvlan_newlink, .dellink = macvlan_dellink, }; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index a8a94e2..ff02b83 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -180,11 +180,18 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb) { struct macvtap_queue *q = macvtap_get_queue(dev, skb); if (!q) - return -ENOLINK; + goto drop; + + if (skb_queue_len(&q->sk.sk_receive_queue) >= dev->tx_queue_len) + goto drop; skb_queue_tail(&q->sk.sk_receive_queue, skb); wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND); - return 0; + return NET_RX_SUCCESS; + +drop: + kfree_skb(skb); + return NET_RX_DROP; } /* @@ -235,8 +242,15 @@ static void macvtap_dellink(struct net_device *dev, macvlan_dellink(dev, head); } +static void macvtap_setup(struct net_device *dev) +{ + macvlan_common_setup(dev); + dev->tx_queue_len = TUN_READQ_SIZE; +} + static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", + .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, }; diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 9ea047a..1ffaeff 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -67,6 +67,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, } } +extern void macvlan_common_setup(struct net_device *dev); + extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], int (*receive)(struct sk_buff *skb), -- cgit v0.10.2 From 00c5a9834b476a138158fb17d576da751727a9f1 Mon Sep 17 00:00:00 2001 From: Andrea Shepard Date: Thu, 22 Jul 2010 09:12:35 +0000 Subject: net: Fix corruption of skb csum field in pskb_expand_head() of net/core/skbuff.c Make pskb_expand_head() check ip_summed to make sure csum_start is really csum_start and not csum before adjusting it. This fixes a bug I encountered using a Sun Quad-Fast Ethernet card and VLANs. On my configuration, the sunhme driver produces skbs with differing amounts of headroom on receive depending on the packet size. See line 2030 of drivers/net/sunhme.c; packets smaller than RX_COPY_THRESHOLD have 52 bytes of headroom but packets larger than that cutoff have only 20 bytes. When these packets reach the VLAN driver, vlan_check_reorder_header() calls skb_cow(), which, if the packet has less than NET_SKB_PAD (== 32) bytes of headroom, uses pskb_expand_head() to make more. Then, pskb_expand_head() needs to adjust a lot of offsets into the skb, including csum_start. Since csum_start is a union with csum, if the packet has a valid csum value this will corrupt it, which was the effect I observed. The sunhme hardware computes receive checksums, so the skbs would be created by the driver with ip_summed == CHECKSUM_COMPLETE and a valid csum field, and then pskb_expand_head() would corrupt the csum field, leading to an "hw csum error" message later on, for example in icmp_rcv() for pings larger than the sunhme RX_COPY_THRESHOLD. On the basis of the comment at the beginning of include/linux/skbuff.h, I believe that the csum_start skb field is only meaningful if ip_csummed is CSUM_PARTIAL, so this patch makes pskb_expand_head() adjust it only in that case to avoid corrupting a valid csum value. Please see my more in-depth disucssion of tracking down this bug for more details if you like: http://puellavulnerata.livejournal.com/112186.html http://puellavulnerata.livejournal.com/112567.html http://puellavulnerata.livejournal.com/112891.html http://puellavulnerata.livejournal.com/113096.html http://puellavulnerata.livejournal.com/113591.html I am not subscribed to this list, so please CC me on replies. Signed-off-by: Andrea Shepard Signed-off-by: David S. Miller diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 34432b4..c699159 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -843,7 +843,9 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; - skb->csum_start += nhead; + /* Only adjust this if it actually is csum_start rather than csum */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb->csum_start += nhead; skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; -- cgit v0.10.2 From be2b6e62357dd7ee56bdcb05e54002afb4830292 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 22 Jul 2010 13:27:09 -0700 Subject: net: Fix skb_copy_expand() handling of ->csum_start It should only be adjusted if ip_summed == CHECKSUM_PARTIAL. Signed-off-by: David S. Miller diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c699159..ce88293 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -932,7 +932,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, copy_skb_header(n, skb); off = newheadroom - oldheadroom; - n->csum_start += off; + if (n->ip_summed == CHECKSUM_PARTIAL) + n->csum_start += off; #ifdef NET_SKBUFF_DATA_USES_OFFSET n->transport_header += off; n->network_header += off; -- cgit v0.10.2 From 64e724f62ab743d55229cd5e27ec8b068b68eb16 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Tue, 20 Jul 2010 10:34:30 +0000 Subject: ipv6: Don't add routes to ipv6 disabled interfaces. If the interface has IPv6 disabled, don't add a multicast or link-local route since we won't be adding a link-local address. Reported-by: Mahesh Kelkar Signed-off-by: Brian Haley Signed-off-by: David S. Miller diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e1a698d..784f34d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1760,7 +1760,10 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) idev = ipv6_find_idev(dev); if (!idev) - return NULL; + return ERR_PTR(-ENOBUFS); + + if (idev->cnf.disable_ipv6) + return ERR_PTR(-EACCES); /* Add default multicast route */ addrconf_add_mroute(dev); @@ -2129,8 +2132,9 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, if (!dev) return -ENODEV; - if ((idev = addrconf_add_dev(dev)) == NULL) - return -ENOBUFS; + idev = addrconf_add_dev(dev); + if (IS_ERR(idev)) + return PTR_ERR(idev); scope = ipv6_addr_scope(pfx); @@ -2377,7 +2381,7 @@ static void addrconf_dev_config(struct net_device *dev) } idev = addrconf_add_dev(dev); - if (idev == NULL) + if (IS_ERR(idev)) return; memset(&addr, 0, sizeof(struct in6_addr)); @@ -2468,7 +2472,7 @@ static void addrconf_ip6_tnl_config(struct net_device *dev) ASSERT_RTNL(); idev = addrconf_add_dev(dev); - if (!idev) { + if (IS_ERR(idev)) { printk(KERN_DEBUG "init ip6-ip6: add_dev failed\n"); return; } -- cgit v0.10.2 From 41a8730c23aba4b77a13e5e151d2b69cd10ef6cb Mon Sep 17 00:00:00 2001 From: Alexey Shvetsov Date: Fri, 23 Jul 2010 00:35:16 +0400 Subject: wimax/i2400m: Add PID & VID for Intel WiMAX 6250 This version of intel wimax device was found in my IBM ThinkPad x201 Signed-off-by: Alexey Shvetsov diff --git a/drivers/net/wimax/i2400m/i2400m-usb.h b/drivers/net/wimax/i2400m/i2400m-usb.h index 2d7c96d..eb80243 100644 --- a/drivers/net/wimax/i2400m/i2400m-usb.h +++ b/drivers/net/wimax/i2400m/i2400m-usb.h @@ -152,6 +152,7 @@ enum { /* Device IDs */ USB_DEVICE_ID_I6050 = 0x0186, USB_DEVICE_ID_I6050_2 = 0x0188, + USB_DEVICE_ID_I6250 = 0x0187, }; diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index 16341ff..0f88702 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -491,6 +491,7 @@ int i2400mu_probe(struct usb_interface *iface, switch (id->idProduct) { case USB_DEVICE_ID_I6050: case USB_DEVICE_ID_I6050_2: + case USB_DEVICE_ID_I6250: i2400mu->i6050 = 1; break; default: @@ -739,6 +740,7 @@ static struct usb_device_id i2400mu_id_table[] = { { USB_DEVICE(0x8086, USB_DEVICE_ID_I6050) }, { USB_DEVICE(0x8086, USB_DEVICE_ID_I6050_2) }, + { USB_DEVICE(0x8086, USB_DEVICE_ID_I6250) }, { USB_DEVICE(0x8086, 0x0181) }, { USB_DEVICE(0x8086, 0x1403) }, { USB_DEVICE(0x8086, 0x1405) }, -- cgit v0.10.2 From d8190dff018ffe932d17cae047c6b3d1c5fc7574 Mon Sep 17 00:00:00 2001 From: Greg Edwards Date: Fri, 23 Jul 2010 10:02:04 +0000 Subject: bonding: set device in RLB ARP packet handler After: commit 6146b1a4da98377e4abddc91ba5856bef8f23f1e Author: Jay Vosburgh Date: Tue Nov 4 17:51:15 2008 -0800 bonding: Fix ALB mode to balance traffic on VLANs the dev field in the RLB ARP packet handler was set to NULL to wildcard and accommodate balancing VLANs on top of bonds. This has the side-effect of the packet handler being called against other, non RLB-enabled bonds, and a kernel oops results when it tries to dereference rx_hashtbl in rlb_update_entry_from_arp(), which won't be set for those bonds, e.g. active-backup. With the __netif_receive_skb() changes from: commit 1f3c8804acba841b5573b953f5560d2683d2db0d Author: Andy Gospodarek Date: Mon Dec 14 10:48:58 2009 +0000 bonding: allow arp_ip_targets on separate vlans to use arp validation frames received on VLANs correctly make their way to the bond's handler, so we no longer need to wildcard the device. The oops can be reproduced by: modprobe bonding echo active-backup > /sys/class/net/bond0/bonding/mode echo 100 > /sys/class/net/bond0/bonding/miimon ifconfig bond0 xxx.xxx.xxx.xxx netmask xxx.xxx.xxx.xxx echo +eth0 > /sys/class/net/bond0/bonding/slaves echo +eth1 > /sys/class/net/bond0/bonding/slaves echo +bond1 > /sys/class/net/bonding_masters echo balance-alb > /sys/class/net/bond1/bonding/mode echo 100 > /sys/class/net/bond1/bonding/miimon ifconfig bond1 xxx.xxx.xxx.xxx netmask xxx.xxx.xxx.xxx echo +eth2 > /sys/class/net/bond1/bonding/slaves echo +eth3 > /sys/class/net/bond1/bonding/slaves Pass some traffic on bond0. Boom. [ Tested, behaves as advertised. I do not believe a test of the bonding mode is necessary, as there is no race between the packet handler and the bonding mode changing (the mode can only change when the device is closed). Also updated the log message to include the reproduction and full commit ids. -J ] Signed-off-by: Greg Edwards Signed-off-by: Jay Vosburgh Acked-by: Andy Gospodarek Signed-off-by: David S. Miller diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index df48307..8d7dfd2 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -822,7 +822,7 @@ static int rlb_initialize(struct bonding *bond) /*initialize packet type*/ pk_type->type = cpu_to_be16(ETH_P_ARP); - pk_type->dev = NULL; + pk_type->dev = bond->dev; pk_type->func = rlb_arp_recv; /* register to receive ARPs */ -- cgit v0.10.2 From ef3db4a5954281bc1ea49a4739c88eaea091dc71 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 21 Jul 2010 04:32:45 +0000 Subject: tun: avoid BUG, dump packet on GSO errors There are still some LRO cards that cause GSO errors in tun, and BUG on this is an unfriendly way to tell the admin to disable LRO. Further, experience shows we might have more GSO bugs lurking. See https://bugzilla.kernel.org/show_bug.cgi?id=16413 as a recent example. dumping a packet will make it easier to figure it out. Replace BUG with warning+dump+drop the packet to make GSO errors in tun less critical and easier to debug. Signed-off-by: Michael S. Tsirkin Tested-by: Alex Unigovsky Acked-by: Herbert Xu Signed-off-by: David S. Miller diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 6ad6fe7..6304259 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -736,8 +736,18 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else if (sinfo->gso_type & SKB_GSO_UDP) gso.gso_type = VIRTIO_NET_HDR_GSO_UDP; - else - BUG(); + else { + printk(KERN_ERR "tun: unexpected GSO type: " + "0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, gso.gso_size, + gso.hdr_len); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)gso.hdr_len, 64), true); + WARN_ON_ONCE(1); + return -EINVAL; + } if (sinfo->gso_type & SKB_GSO_TCP_ECN) gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else -- cgit v0.10.2 From 3b87956ea645fb4de7e59c7d0aa94de04be72615 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 22 Jul 2010 18:45:04 +0000 Subject: net sched: fix race in mirred device removal This fixes hang when target device of mirred packet classifier action is removed. If a mirror or redirection action is configured to cause packets to go to another device, the classifier holds a ref count, but was assuming the adminstrator cleaned up all redirections before removing. The fix is to add a notifier and cleanup during unregister. The new list is implicitly protected by RTNL mutex because it is held during filter add/delete as well as notifier. Signed-off-by: Stephen Hemminger Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index ceac661..cfe2943 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -9,6 +9,7 @@ struct tcf_mirred { int tcfm_ifindex; int tcfm_ok_push; struct net_device *tcfm_dev; + struct list_head tcfm_list; }; #define to_mirred(pc) \ container_of(pc, struct tcf_mirred, common) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index c0b6863..1980b71 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -33,6 +33,7 @@ static struct tcf_common *tcf_mirred_ht[MIRRED_TAB_MASK + 1]; static u32 mirred_idx_gen; static DEFINE_RWLOCK(mirred_lock); +static LIST_HEAD(mirred_list); static struct tcf_hashinfo mirred_hash_info = { .htab = tcf_mirred_ht, @@ -47,7 +48,9 @@ static inline int tcf_mirred_release(struct tcf_mirred *m, int bind) m->tcf_bindcnt--; m->tcf_refcnt--; if(!m->tcf_bindcnt && m->tcf_refcnt <= 0) { - dev_put(m->tcfm_dev); + list_del(&m->tcfm_list); + if (m->tcfm_dev) + dev_put(m->tcfm_dev); tcf_hash_destroy(&m->common, &mirred_hash_info); return 1; } @@ -134,8 +137,10 @@ static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est, m->tcfm_ok_push = ok_push; } spin_unlock_bh(&m->tcf_lock); - if (ret == ACT_P_CREATED) + if (ret == ACT_P_CREATED) { + list_add(&m->tcfm_list, &mirred_list); tcf_hash_insert(pc, &mirred_hash_info); + } return ret; } @@ -162,9 +167,14 @@ static int tcf_mirred(struct sk_buff *skb, struct tc_action *a, m->tcf_tm.lastuse = jiffies; dev = m->tcfm_dev; + if (!dev) { + printk_once(KERN_NOTICE "tc mirred: target device is gone\n"); + goto out; + } + if (!(dev->flags & IFF_UP)) { if (net_ratelimit()) - pr_notice("tc mirred to Houston: device %s is gone!\n", + pr_notice("tc mirred to Houston: device %s is down\n", dev->name); goto out; } @@ -232,6 +242,28 @@ nla_put_failure: return -1; } +static int mirred_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct tcf_mirred *m; + + if (event == NETDEV_UNREGISTER) + list_for_each_entry(m, &mirred_list, tcfm_list) { + if (m->tcfm_dev == dev) { + dev_put(dev); + m->tcfm_dev = NULL; + } + } + + return NOTIFY_DONE; +} + +static struct notifier_block mirred_device_notifier = { + .notifier_call = mirred_device_event, +}; + + static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .hinfo = &mirred_hash_info, @@ -252,12 +284,17 @@ MODULE_LICENSE("GPL"); static int __init mirred_init_module(void) { + int err = register_netdevice_notifier(&mirred_device_notifier); + if (err) + return err; + pr_info("Mirror/redirect action on\n"); return tcf_register_action(&act_mirred_ops); } static void __exit mirred_cleanup_module(void) { + unregister_netdevice_notifier(&mirred_device_notifier); tcf_unregister_action(&act_mirred_ops); } -- cgit v0.10.2 From c736eefadb71a01a5e61e0de700f28f6952b4444 Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Thu, 22 Jul 2010 09:54:47 +0000 Subject: net: dev_forward_skb should call nf_reset With conn-track zones and probably with different network namespaces, the netfilter logic needs to be re-calculated on packet receive. If the netfilter logic is not reset, it will not be recalculated properly. This patch adds the nf_reset logic to dev_forward_skb. Signed-off-by: Ben Greear Signed-off-by: David S. Miller diff --git a/net/core/dev.c b/net/core/dev.c index 0ea10f8..1f466e8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1488,6 +1488,7 @@ static inline void net_timestamp_check(struct sk_buff *skb) int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { skb_orphan(skb); + nf_reset(skb); if (!(dev->flags & IFF_UP) || (skb->len > (dev->mtu + dev->hard_header_len))) { -- cgit v0.10.2 From f792af250de54309e4bc9f238db3623ead0a4507 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 14 May 2010 21:15:38 +0800 Subject: ath9k: fix dma direction for map/unmap in ath_rx_tasklet For edma, we should use DMA_BIDIRECTIONAL, or else use DMA_FROM_DEVICE. This is found to address "BUG at arch/x86/mm/physaddr.c:5" as described here: http://lkml.org/lkml/2010/7/14/21 Signed-off-by: Ming Lei Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index ca6065b..e3e5291 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -844,9 +844,9 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) int dma_type; if (edma) - dma_type = DMA_FROM_DEVICE; - else dma_type = DMA_BIDIRECTIONAL; + else + dma_type = DMA_FROM_DEVICE; qtype = hp ? ATH9K_RX_QUEUE_HP : ATH9K_RX_QUEUE_LP; spin_lock_bh(&sc->rx.rxbuflock); -- cgit v0.10.2 From 5447080cfa3c77154498dfbf225367ac85b4c2b5 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 26 Jul 2010 15:37:30 -0700 Subject: s2io: fixing DBG_PRINT() macro Patch 9e39f7c5b311a306977c5471f9e2ce4c456aa038 changed the DBG_PRINT() macro and the if clause was wrongly changed. It means that currently all the DBG_PRINT are being printed, flooding the kernel log buffer with things like: s2io: eth6: Next block at: c0000000b9c90000 s2io: eth6: In Neterion Tx routine Signed-off-by: Breno Leitao Acked-by: Sreenivasa Honnur Signed-off-by: David S. Miller diff --git a/drivers/net/s2io.h b/drivers/net/s2io.h index 5e52c75..7f3a53d 100644 --- a/drivers/net/s2io.h +++ b/drivers/net/s2io.h @@ -65,7 +65,7 @@ static int debug_level = ERR_DBG; /* DEBUG message print. */ #define DBG_PRINT(dbg_level, fmt, args...) do { \ - if (dbg_level >= debug_level) \ + if (dbg_level <= debug_level) \ pr_info(fmt, ##args); \ } while (0) -- cgit v0.10.2