From 6c3118e2305326743acb52250bcfd0d52389d9dc Mon Sep 17 00:00:00 2001 From: Vasanthakumar Thiagarajan Date: Wed, 23 Jun 2010 06:49:21 -0700 Subject: ath9k: Fix bug in starting ani There are few places where ANI is started without checking if it is right to start. This might lead to a case where ani timer would be left undeleted and cause improper memory acccess during module unload. This bug is clearly exposed with paprd support where the driver detects tx hang and does a chip reset. During this reset ani is (re)started without checking if it needs to be started. This would leave a timer scheduled even after all the resources are freed and cause a panic. This patch introduces a bit in sc_flags to indicate if ani needs to be started in sw_scan_start() and ath_reset(). This would fix the following panic. This issue is easily seen with ar9003 + paprd. BUG: unable to handle kernel paging request at 0000000000003f38 [] ? __queue_work+0x41/0x50 [] run_timer_softirq+0x17a/0x370 [] ? tick_dev_program_event+0x48/0x110 [] __do_softirq+0xb9/0x1f0 [] ? handle_IRQ_event+0x50/0x160 [] call_softirq+0x1c/0x30 [] do_softirq+0x65/0xa0 [] irq_exit+0x85/0x90 [] do_IRQ+0x75/0xf0 [] ret_from_intr+0x0/0x11 [] ? acpi_idle_enter_simple+0xe4/0x119 [] ? acpi_idle_enter_simple+0xdd/0x119 [] cpuidle_idle_call+0xa7/0x140 [] cpu_idle+0xb3/0x110 [] start_secondary+0x1ee/0x1f5 Signed-off-by: Vasanthakumar Thiagarajan Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath9k/ath9k.h | 1 + drivers/net/wireless/ath/ath9k/main.c | 11 ++++++++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index fbb7dec6ddeb..5ea87736a6ae 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -445,6 +445,7 @@ void ath_deinit_leds(struct ath_softc *sc); #define SC_OP_TSF_RESET BIT(11) #define SC_OP_BT_PRIORITY_DETECTED BIT(12) #define SC_OP_BT_SCAN BIT(13) +#define SC_OP_ANI_RUN BIT(14) /* Powersave flags */ #define PS_WAIT_FOR_BEACON BIT(0) diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index abfa0493236f..1e2a68ea9355 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -336,6 +336,10 @@ set_timer: static void ath_start_ani(struct ath_common *common) { unsigned long timestamp = jiffies_to_msecs(jiffies); + struct ath_softc *sc = (struct ath_softc *) common->priv; + + if (!(sc->sc_flags & SC_OP_ANI_RUN)) + return; common->ani.longcal_timer = timestamp; common->ani.shortcal_timer = timestamp; @@ -872,11 +876,13 @@ static void ath9k_bss_assoc_info(struct ath_softc *sc, /* Reset rssi stats */ sc->sc_ah->stats.avgbrssi = ATH_RSSI_DUMMY_MARKER; + sc->sc_flags |= SC_OP_ANI_RUN; ath_start_ani(common); } else { ath_print(common, ATH_DBG_CONFIG, "Bss Info DISASSOC\n"); common->curaid = 0; /* Stop ANI */ + sc->sc_flags &= ~SC_OP_ANI_RUN; del_timer_sync(&common->ani.timer); } } @@ -1478,8 +1484,10 @@ static int ath9k_add_interface(struct ieee80211_hw *hw, if (vif->type == NL80211_IFTYPE_AP || vif->type == NL80211_IFTYPE_ADHOC || - vif->type == NL80211_IFTYPE_MONITOR) + vif->type == NL80211_IFTYPE_MONITOR) { + sc->sc_flags |= SC_OP_ANI_RUN; ath_start_ani(common); + } out: mutex_unlock(&sc->mutex); @@ -1500,6 +1508,7 @@ static void ath9k_remove_interface(struct ieee80211_hw *hw, mutex_lock(&sc->mutex); /* Stop ANI */ + sc->sc_flags &= ~SC_OP_ANI_RUN; del_timer_sync(&common->ani.timer); /* Reclaim beacon resources */ -- cgit v1.2.3 From d1e89f37de2845db364ef6d67586cd882f86b557 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Jun 2010 03:41:25 -0700 Subject: iwlwifi: fix multicast commit 3474ad635db371b0d8d0ee40086f15d223d5b6a4 Author: Johannes Berg Date: Thu Apr 29 04:43:05 2010 -0700 iwlwifi: apply filter flags directly broke multicast. The reason, it turns out, is that the code previously checked if ALLMULTI _changed_, which the new code no longer did, and normally it _never_ changes. Had somebody changed it manually, the code prior to my patch there would have been broken already. The reason is that we always, unconditionally, ask the device to pass up all multicast frames, but the new code made it depend on ALLMULTI which broke it since now we'd pass up multicast frames depending on the default filter in the device, which isn't necessarily what we want (since we don't program it right now). Fix this by simply not checking allmulti as we have allmulti behaviour enabled already anyway. Reported-by: Maxim Levitsky Tested-by: Maxim Levitsky Signed-off-by: Johannes Berg --- drivers/net/wireless/iwlwifi/iwl-core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index 426e95567de3..5bbc5298ef96 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -1314,7 +1314,6 @@ void iwl_configure_filter(struct ieee80211_hw *hw, changed_flags, *total_flags); CHK(FIF_OTHER_BSS | FIF_PROMISC_IN_BSS, RXON_FILTER_PROMISC_MSK); - CHK(FIF_ALLMULTI, RXON_FILTER_ACCEPT_GRP_MSK); CHK(FIF_CONTROL, RXON_FILTER_CTL2HOST_MSK); CHK(FIF_BCN_PRBRESP_PROMISC, RXON_FILTER_BCON_AWARE_MSK); @@ -1329,6 +1328,12 @@ void iwl_configure_filter(struct ieee80211_hw *hw, mutex_unlock(&priv->mutex); + /* + * Receiving all multicast frames is always enabled by the + * default flags setup in iwl_connection_init_rx_config() + * since we currently do not support programming multicast + * filters into the device. + */ *total_flags &= FIF_OTHER_BSS | FIF_ALLMULTI | FIF_PROMISC_IN_BSS | FIF_BCN_PRBRESP_PROMISC | FIF_CONTROL; } -- cgit v1.2.3 From 062bee448bd539580ef9f64efe50fdfe04eeb103 Mon Sep 17 00:00:00 2001 From: Wey-Yi Guy Date: Fri, 18 Jun 2010 11:33:17 -0700 Subject: iwlwifi: set TX_CMD_FLAG_PROT_REQUIRE_MSK in tx_flag When building tx command, always set TX_CMD_FLAG_PROT_REQUIRE_MSK for 5000 series and up. Without setting this bit the firmware will not examine the RTS/CTS setting and thus not send traffic with the appropriate protection. RTS/CTS is is required for HT traffic in a noisy environment where, without this setting, connections will stall on some hardware as documented in the patch that initially attempted to address this: commit 1152dcc28c66a74b5b3f1a3ede0aa6729bfd48e4 Author: Wey-Yi Guy Date: Fri Jan 15 13:42:58 2010 -0800 iwlwifi: Fix throughput stall issue in HT mode for 5000 Similar to 6000 and 1000 series, RTS/CTS is the recommended protection mechanism for 5000 series in HT mode based on the HW design. Using RTS/CTS will better protect the inner exchange from interference, especially in highly-congested environment, it also prevent uCode encounter TX FIFO underrun and other HT mode related performance issues. For 3945 and 4965, different flags are used for RTS/CTS or CTS-to-Self protection. Signed-off-by: Wey-Yi Guy Signed-off-by: Reinette Chatre --- drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c index 44ef5d93befc..01658cf82d39 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c @@ -212,11 +212,7 @@ static void iwlagn_chain_noise_reset(struct iwl_priv *priv) static void iwlagn_rts_tx_cmd_flag(struct ieee80211_tx_info *info, __le32 *tx_flags) { - if ((info->control.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || - (info->control.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) - *tx_flags |= TX_CMD_FLG_RTS_CTS_MSK; - else - *tx_flags &= ~TX_CMD_FLG_RTS_CTS_MSK; + *tx_flags |= TX_CMD_FLG_RTS_CTS_MSK; } /* Calc max signal level (dBm) among 3 possible receivers */ -- cgit v1.2.3 From d5675bd204efd87a174eeea592de23c4c4e7f908 Mon Sep 17 00:00:00 2001 From: Michael S. Tsirkin Date: Thu, 24 Jun 2010 16:59:59 +0300 Subject: vhost: break out of polling loop on error When ring parsing fails, we currently handle this as ring empty condition. This means that we enable kicks and recheck ring empty: if this not empty, we re-start polling which of course will fail again. Instead, let's return a negative error code and stop polling. Signed-off-by: Michael S. Tsirkin --- drivers/vhost/net.c | 12 ++++++++++-- drivers/vhost/vhost.c | 33 +++++++++++++++++---------------- drivers/vhost/vhost.h | 8 ++++---- 3 files changed, 31 insertions(+), 22 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 0f41c9195e9b..54096eef4840 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -98,7 +98,8 @@ static void tx_poll_start(struct vhost_net *net, struct socket *sock) static void handle_tx(struct vhost_net *net) { struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX]; - unsigned head, out, in, s; + unsigned out, in, s; + int head; struct msghdr msg = { .msg_name = NULL, .msg_namelen = 0, @@ -135,6 +136,9 @@ static void handle_tx(struct vhost_net *net) ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); + /* On error, stop handling until the next kick. */ + if (head < 0) + break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { wmem = atomic_read(&sock->sk->sk_wmem_alloc); @@ -192,7 +196,8 @@ static void handle_tx(struct vhost_net *net) static void handle_rx(struct vhost_net *net) { struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX]; - unsigned head, out, in, log, s; + unsigned out, in, log, s; + int head; struct vhost_log *vq_log; struct msghdr msg = { .msg_name = NULL, @@ -228,6 +233,9 @@ static void handle_rx(struct vhost_net *net) ARRAY_SIZE(vq->iov), &out, &in, vq_log, &log); + /* On error, stop handling until the next kick. */ + if (head < 0) + break; /* OK, now we need to know about added descriptors. */ if (head == vq->num) { if (unlikely(vhost_enable_notify(vq))) { diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 3b83382e06eb..5ccd384ec0be 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -873,12 +873,13 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, * number of output then some number of input descriptors, it's actually two * iovecs, but we pack them into one and note how many of each there were. * - * This function returns the descriptor number found, or vq->num (which - * is never a valid descriptor number) if none was found. */ -unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, - struct iovec iov[], unsigned int iov_size, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num) + * This function returns the descriptor number found, or vq->num (which is + * never a valid descriptor number) if none was found. A negative code is + * returned on error. */ +int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num) { struct vring_desc desc; unsigned int i, head, found = 0; @@ -890,13 +891,13 @@ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, if (get_user(vq->avail_idx, &vq->avail->idx)) { vq_err(vq, "Failed to access avail idx at %p\n", &vq->avail->idx); - return vq->num; + return -EFAULT; } if ((u16)(vq->avail_idx - last_avail_idx) > vq->num) { vq_err(vq, "Guest moved used index from %u to %u", last_avail_idx, vq->avail_idx); - return vq->num; + return -EFAULT; } /* If there's nothing new since last we looked, return invalid. */ @@ -912,14 +913,14 @@ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); - return vq->num; + return -EFAULT; } /* If their number is silly, that's an error. */ if (head >= vq->num) { vq_err(vq, "Guest says index %u > %u is available", head, vq->num); - return vq->num; + return -EINVAL; } /* When we start there are none of either input nor output. */ @@ -933,19 +934,19 @@ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, if (i >= vq->num) { vq_err(vq, "Desc index is %u > %u, head = %u", i, vq->num, head); - return vq->num; + return -EINVAL; } if (++found > vq->num) { vq_err(vq, "Loop detected: last one at %u " "vq size %u head %u\n", i, vq->num, head); - return vq->num; + return -EINVAL; } ret = copy_from_user(&desc, vq->desc + i, sizeof desc); if (ret) { vq_err(vq, "Failed to get descriptor: idx %d addr %p\n", i, vq->desc + i); - return vq->num; + return -EFAULT; } if (desc.flags & VRING_DESC_F_INDIRECT) { ret = get_indirect(dev, vq, iov, iov_size, @@ -954,7 +955,7 @@ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, if (ret < 0) { vq_err(vq, "Failure detected " "in indirect descriptor at idx %d\n", i); - return vq->num; + return ret; } continue; } @@ -964,7 +965,7 @@ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, if (ret < 0) { vq_err(vq, "Translation failure %d descriptor idx %d\n", ret, i); - return vq->num; + return ret; } if (desc.flags & VRING_DESC_F_WRITE) { /* If this is an input descriptor, @@ -981,7 +982,7 @@ unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, if (*in_num) { vq_err(vq, "Descriptor has out after in: " "idx %d\n", i); - return vq->num; + return -EINVAL; } *out_num += ret; } diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 44591ba9b07a..11ee13dba0f7 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -120,10 +120,10 @@ long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, unsigned long arg); int vhost_vq_access_ok(struct vhost_virtqueue *vq); int vhost_log_access_ok(struct vhost_dev *); -unsigned vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *, - struct iovec iov[], unsigned int iov_count, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num); +int vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *, + struct iovec iov[], unsigned int iov_count, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num); void vhost_discard_vq_desc(struct vhost_virtqueue *); int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len); -- cgit v1.2.3 From c22d7ac844f1cb9c6a5fd20f89ebadc2feef891b Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Fri, 25 Jun 2010 09:50:44 +0000 Subject: bonding: prevent netpoll over bonded interfaces Support for netpoll over bonded interfaces was added here: commit f6dc31a85cd46a959bdd987adad14c3b645e03c1 Author: WANG Cong Date: Thu May 6 00:48:51 2010 -0700 bonding: make bonding support netpoll but it is bad enough that we should probably just disable netpoll over bonding until some of the locking logic in the bonding driver is changed or converted completely to RCU. Simple actions like changing the active slave in active-backup mode will hang the box if a high enough printk debugging level is enabled. Keeping the old code around will be good for anyone that wants to work on it (and for after the RCU conversion), so I propose this small patch rather than ripping it all out. Signed-off-by: Andy Gospodarek Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5e12462a9d5e..c3d98dde2f86 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -168,7 +168,7 @@ static int arp_ip_count; static int bond_mode = BOND_MODE_ROUNDROBIN; static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; static int lacp_fast; - +static int disable_netpoll = 1; const struct bond_parm_tbl bond_lacp_tbl[] = { { "slow", AD_LACP_SLOW}, @@ -1742,15 +1742,23 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); #ifdef CONFIG_NET_POLL_CONTROLLER - if (slaves_support_netpoll(bond_dev)) { - bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; - if (bond_dev->npinfo) - slave_dev->npinfo = bond_dev->npinfo; - } else if (!(bond_dev->priv_flags & IFF_DISABLE_NETPOLL)) { + /* + * Netpoll and bonding is broken, make sure it is not initialized + * until it is fixed. + */ + if (disable_netpoll) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - pr_info("New slave device %s does not support netpoll\n", - slave_dev->name); - pr_info("Disabling netpoll support for %s\n", bond_dev->name); + } else { + if (slaves_support_netpoll(bond_dev)) { + bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; + if (bond_dev->npinfo) + slave_dev->npinfo = bond_dev->npinfo; + } else if (!(bond_dev->priv_flags & IFF_DISABLE_NETPOLL)) { + bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; + pr_info("New slave device %s does not support netpoll\n", + slave_dev->name); + pr_info("Disabling netpoll support for %s\n", bond_dev->name); + } } #endif read_unlock(&bond->lock); @@ -1950,8 +1958,11 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) #ifdef CONFIG_NET_POLL_CONTROLLER read_lock_bh(&bond->lock); - if (slaves_support_netpoll(bond_dev)) - bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; + + /* Make sure netpoll over stays disabled until fixed. */ + if (!disable_netpoll) + if (slaves_support_netpoll(bond_dev)) + bond_dev->priv_flags &= ~IFF_DISABLE_NETPOLL; read_unlock_bh(&bond->lock); if (slave_dev->netdev_ops->ndo_netpoll_cleanup) slave_dev->netdev_ops->ndo_netpoll_cleanup(slave_dev); -- cgit v1.2.3 From db048b69037e7fa6a7d9e95a1271a50dc08ae233 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 28 Jun 2010 08:44:07 +0000 Subject: ethtool: Fix potential kernel buffer overflow in ETHTOOL_GRXCLSRLALL On a 32-bit machine, info.rule_cnt >= 0x40000000 leads to integer overflow and the buffer may be smaller than needed. Since ETHTOOL_GRXCLSRLALL is unprivileged, this can presumably be used for at least denial of service. Signed-off-by: Ben Hutchings Cc: stable@kernel.org Signed-off-by: David S. Miller --- net/core/ethtool.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index a0f4964033d2..a3a7e9a48dff 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -347,8 +347,9 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (info.cmd == ETHTOOL_GRXCLSRLALL) { if (info.rule_cnt > 0) { - rule_buf = kmalloc(info.rule_cnt * sizeof(u32), - GFP_USER); + if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32)) + rule_buf = kmalloc(info.rule_cnt * sizeof(u32), + GFP_USER); if (!rule_buf) return -ENOMEM; } -- cgit v1.2.3 From bf988435bd5b53529f4408a8efb1f433f6ddfda9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 28 Jun 2010 08:45:58 +0000 Subject: ethtool: Fix potential user buffer overflow for ETHTOOL_{G, S}RXFH struct ethtool_rxnfc was originally defined in 2.6.27 for the ETHTOOL_{G,S}RXFH command with only the cmd, flow_type and data fields. It was then extended in 2.6.30 to support various additional commands. These commands should have been defined to use a new structure, but it is too late to change that now. Since user-space may still be using the old structure definition for the ETHTOOL_{G,S}RXFH commands, and since they do not need the additional fields, only copy the originally defined fields to and from user-space. Signed-off-by: Ben Hutchings Cc: stable@kernel.org Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 ++ net/core/ethtool.c | 36 +++++++++++++++++++++++++++--------- 2 files changed, 29 insertions(+), 9 deletions(-) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 276b40a16835..b4207ca3ad52 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -379,6 +379,8 @@ struct ethtool_rxnfc { __u32 flow_type; /* The rx flow hash value or the rule DB size */ __u64 data; + /* The following fields are not valid and must not be used for + * the ETHTOOL_{G,X}RXFH commands. */ struct ethtool_rx_flow_spec fs; __u32 rule_cnt; __u32 rule_locs[0]; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index a3a7e9a48dff..75e4ffeb8cc9 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -318,23 +318,33 @@ out: } static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, - void __user *useraddr) + u32 cmd, void __user *useraddr) { - struct ethtool_rxnfc cmd; + struct ethtool_rxnfc info; + size_t info_size = sizeof(info); if (!dev->ethtool_ops->set_rxnfc) return -EOPNOTSUPP; - if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + /* struct ethtool_rxnfc was originally defined for + * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data + * members. User-space might still be using that + * definition. */ + if (cmd == ETHTOOL_SRXFH) + info_size = (offsetof(struct ethtool_rxnfc, data) + + sizeof(info.data)); + + if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; - return dev->ethtool_ops->set_rxnfc(dev, &cmd); + return dev->ethtool_ops->set_rxnfc(dev, &info); } static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, - void __user *useraddr) + u32 cmd, void __user *useraddr) { struct ethtool_rxnfc info; + size_t info_size = sizeof(info); const struct ethtool_ops *ops = dev->ethtool_ops; int ret; void *rule_buf = NULL; @@ -342,7 +352,15 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (!ops->get_rxnfc) return -EOPNOTSUPP; - if (copy_from_user(&info, useraddr, sizeof(info))) + /* struct ethtool_rxnfc was originally defined for + * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data + * members. User-space might still be using that + * definition. */ + if (cmd == ETHTOOL_GRXFH) + info_size = (offsetof(struct ethtool_rxnfc, data) + + sizeof(info.data)); + + if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; if (info.cmd == ETHTOOL_GRXCLSRLALL) { @@ -360,7 +378,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, goto err_out; ret = -EFAULT; - if (copy_to_user(useraddr, &info, sizeof(info))) + if (copy_to_user(useraddr, &info, info_size)) goto err_out; if (rule_buf) { @@ -1517,12 +1535,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: - rc = ethtool_get_rxnfc(dev, useraddr); + rc = ethtool_get_rxnfc(dev, ethcmd, useraddr); break; case ETHTOOL_SRXFH: case ETHTOOL_SRXCLSRLDEL: case ETHTOOL_SRXCLSRLINS: - rc = ethtool_set_rxnfc(dev, useraddr); + rc = ethtool_set_rxnfc(dev, ethcmd, useraddr); break; case ETHTOOL_GGRO: rc = ethtool_get_gro(dev, useraddr); -- cgit v1.2.3 From fa37813401ff52d78591c262d6542e4d5d935584 Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Tue, 29 Jun 2010 18:28:12 +0000 Subject: ixgbe: fix panic when shutting down system with WoL enabled This patch added to 2.6.34: commit 5f6c01819979afbfec7e0b15fe52371b8eed87e8 Author: Jesse Brandeburg Date: Wed Apr 14 16:04:23 2010 -0700 ixgbe: fix bug with vlan strip in promsic mode among other things added a function called ixgbe_vlan_filter_enable. This new function wants to access and set some rx_ring parameters, but adapter->rx_ring has already been freed. This simply moves the free until after the access and makes __ixgbe_shutdown look more like ixgbe_remove. Signed-off-by: Andy Gospodarek Acked-by: Jesse Brandeburg Tested-by: Emil Tantilov Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ixgbe/ixgbe_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index ce30c62a97f7..e237748995c1 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -5195,7 +5195,6 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) ixgbe_free_all_tx_resources(adapter); ixgbe_free_all_rx_resources(adapter); } - ixgbe_clear_interrupt_scheme(adapter); #ifdef CONFIG_PM retval = pci_save_state(pdev); @@ -5230,6 +5229,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) *enable_wake = !!wufc; + ixgbe_clear_interrupt_scheme(adapter); + ixgbe_release_hw_control(adapter); pci_disable_device(pdev); -- cgit v1.2.3 From 9f756f018a6d9f83556f972ce7fcd6870274efae Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 29 Jun 2010 18:28:36 +0000 Subject: ixgbe: disable tx engine before disabling tx laser Disabling the tx laser while receiving DMA requests can hang the device. After this occurs the device is in a bad state. The GPIO bit never clears when PCI master access is disabled and a reboot is required to get the device in a good state again. Signed-off-by: John Fastabend Acked-by: Peter P Waskiewicz Jr Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ixgbe/ixgbe_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index e237748995c1..7ddd60e7d389 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -3684,10 +3684,6 @@ void ixgbe_down(struct ixgbe_adapter *adapter) /* signal that we are down to the interrupt handler */ set_bit(__IXGBE_DOWN, &adapter->state); - /* power down the optics */ - if (hw->phy.multispeed_fiber) - hw->mac.ops.disable_tx_laser(hw); - /* disable receive for all VFs and wait one second */ if (adapter->num_vfs) { /* ping all the active vfs to let them know we are going down */ @@ -3742,6 +3738,10 @@ void ixgbe_down(struct ixgbe_adapter *adapter) (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & ~IXGBE_DMATXCTL_TE)); + /* power down the optics */ + if (hw->phy.multispeed_fiber) + hw->mac.ops.disable_tx_laser(hw); + /* clear n-tuple filters that are cached */ ethtool_ntuple_flush(netdev); -- cgit v1.2.3 From d3ead2413cb99d3e6265577b12537434e229d8c2 Mon Sep 17 00:00:00 2001 From: Guillaume Gaudonville Date: Tue, 29 Jun 2010 18:29:00 +0000 Subject: ixgbe: skip non IPv4 packets in ATR filter In driver ixgbe, ixgbe_atr may cause crashes for non-ipv4 packets. Just add a test to check skb->protocol. It may crash on short packets due to ip_hdr() access. Signed-off-by: Guillaume Gaudonville Acked-by: Peter P Waskiewicz Jr Signed-off-by: Don Skidmore Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ixgbe/ixgbe_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 7ddd60e7d389..a0b33165b989 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -6024,7 +6024,6 @@ static void ixgbe_tx_queue(struct ixgbe_adapter *adapter, static void ixgbe_atr(struct ixgbe_adapter *adapter, struct sk_buff *skb, int queue, u32 tx_flags) { - /* Right now, we support IPv4 only */ struct ixgbe_atr_input atr_input; struct tcphdr *th; struct iphdr *iph = ip_hdr(skb); @@ -6033,6 +6032,9 @@ static void ixgbe_atr(struct ixgbe_adapter *adapter, struct sk_buff *skb, u32 src_ipv4_addr, dst_ipv4_addr; u8 l4type = 0; + /* Right now, we support IPv4 only */ + if (skb->protocol != htons(ETH_P_IP)) + return; /* check if we're UDP or TCP */ if (iph->protocol == IPPROTO_TCP) { th = tcp_hdr(skb); -- cgit v1.2.3 From 4efd7e833591721bec21cc4730a7f6261417840f Mon Sep 17 00:00:00 2001 From: Andreas Steffen Date: Wed, 30 Jun 2010 10:41:15 -0700 Subject: xfrm: fix XFRMA_MARK extraction in xfrm_mark_get Determine the size of the xfrm_mark struct, not of its pointer. Signed-off-by: Andreas Steffen Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 1913af67c43d..fc8f36dd0f5c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1586,7 +1586,7 @@ static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_MARK]) - memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(m)); + memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(struct xfrm_mark)); else m->v = m->m = 0; -- cgit v1.2.3 From 9b2c2ff7a1c04e69842254dd4afe0f8ad4efa439 Mon Sep 17 00:00:00 2001 From: Saeed Bishara Date: Sun, 27 Jun 2010 00:26:43 +0000 Subject: mv643xx_eth: use sw csum for big packets Some controllers (KW, Dove) limits the TX IP/layer4 checksum offloading to a max size. Signed-off-by: Saeed Bishara Acked-by: Lennert Buytenhek Signed-off-by: David S. Miller --- drivers/net/mv643xx_eth.c | 9 +++++++-- include/linux/mv643xx_eth.h | 5 +++++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index e345ec8cb473..73bb8ea6f54a 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -289,6 +289,7 @@ struct mv643xx_eth_shared_private { unsigned int t_clk; int extended_rx_coal_limit; int tx_bw_control; + int tx_csum_limit; }; #define TX_BW_CONTROL_ABSENT 0 @@ -776,13 +777,16 @@ static int txq_submit_skb(struct tx_queue *txq, struct sk_buff *skb) l4i_chk = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { + int hdr_len; int tag_bytes; BUG_ON(skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_8021Q)); - tag_bytes = (void *)ip_hdr(skb) - (void *)skb->data - ETH_HLEN; - if (unlikely(tag_bytes & ~12)) { + hdr_len = (void *)ip_hdr(skb) - (void *)skb->data; + tag_bytes = hdr_len - ETH_HLEN; + if (skb->len - hdr_len > mp->shared->tx_csum_limit || + unlikely(tag_bytes & ~12)) { if (skb_checksum_help(skb) == 0) goto no_csum; kfree_skb(skb); @@ -2666,6 +2670,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) * Detect hardware parameters. */ msp->t_clk = (pd != NULL && pd->t_clk != 0) ? pd->t_clk : 133000000; + msp->tx_csum_limit = pd->tx_csum_limit ? pd->tx_csum_limit : 9 * 1024; infer_hw_params(msp); platform_set_drvdata(pdev, msp); diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index cbbbe9bfecad..30b0c4e78f91 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -19,6 +19,11 @@ struct mv643xx_eth_shared_platform_data { struct mbus_dram_target_info *dram; struct platform_device *shared_smi; unsigned int t_clk; + /* + * Max packet size for Tx IP/Layer 4 checksum, when set to 0, default + * limit of 9KiB will be used. + */ + int tx_csum_limit; }; #define MV643XX_ETH_PHY_ADDR_DEFAULT 0 -- cgit v1.2.3 From dd1589a431e90f9ff587e640c67101a565e52bba Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 30 Jun 2010 13:10:09 -0700 Subject: Bluetooth: Fix abuse of the preincrement operator Fix abuse of the preincrement operator as detected when building with gcc 4.6.0: CC [M] drivers/bluetooth/hci_bcsp.o drivers/bluetooth/hci_bcsp.c: In function 'bcsp_prepare_pkt': drivers/bluetooth/hci_bcsp.c:247:20: warning: operation on 'bcsp->msgq_txseq' may be undefined Reported-by: Justin P. Mattock Signed-off-by: David Howells Acked-by: Gustavo F. Padovan Signed-off-by: David S. Miller --- drivers/bluetooth/hci_bcsp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index 40aec0fb8596..42d69d4de05c 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -244,7 +244,7 @@ static struct sk_buff *bcsp_prepare_pkt(struct bcsp_struct *bcsp, u8 *data, if (rel) { hdr[0] |= 0x80 + bcsp->msgq_txseq; BT_DBG("Sending packet with seqno %u", bcsp->msgq_txseq); - bcsp->msgq_txseq = ++(bcsp->msgq_txseq) & 0x07; + bcsp->msgq_txseq = (bcsp->msgq_txseq + 1) & 0x07; } if (bcsp->use_crc) -- cgit v1.2.3 From 42d782ac1bef7cbcdf05b857731345c6e8149f90 Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Tue, 29 Jun 2010 08:24:39 +0000 Subject: bonding: check if clients MAC addr has changed When two systems using bonding devices in adaptive load balancing (ALB) communicates with each other, an endless ping-pong of ARP replies starts between these two systems. What happens? In the ALB mode, bonding driver keeps track of each client connected in a hash table, so it can do the receive load balancing (RLB). This hash table is updated when an ARP reply is received, then it scans for the client entry, updates its MAC address and flag it to be announced later. Therefore, two seconds later, the alb monitor runs and send for each updated client entry two ARP replies updating this specific client. The same process happens on the receiving system, causing the endless ping-pong of arp replies. See more information including the relevant functions below: System 1 System 2 bond0 bond0 ping ARP request ---------> <--------- ARP reply +->rlb_arp_recv <---------------------+ <--- loop begins | rlb_update_entry_from_arp | | client_info->ntt = 1; | | bond_info->rx_ntt = 1; | | | | | | | | bond_alb_monitor | | rlb_update_rx_clients | | rlb_update_client | | arp_create(ARPOP_REPLY) | | send ARP reply --------------> V | send ARP reply --------------> | rlb_arp_recv | rlb_update_entry_from_arp | client_info->ntt = 1; | bond_info->rx_ntt = 1; | < snipped, same as in system 1> +------- <-------------- send ARP reply <-------------- send ARP reply Besides the unneeded networking traffic, this loop breaks a cluster because a backup system can't take over the IP address. There is always one system sending an ARP reply poisoning the network. This patch fixes the problem adding a check for the MAC address before updating it. Thus, if the MAC address didn't change, there is no need to update neither to announce it later. Signed-off-by: Flavio Leitner Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller --- drivers/net/bonding/bond_alb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 40fdc41446cc..df483076eda6 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -340,7 +340,8 @@ static void rlb_update_entry_from_arp(struct bonding *bond, struct arp_pkt *arp) if ((client_info->assigned) && (client_info->ip_src == arp->ip_dst) && - (client_info->ip_dst == arp->ip_src)) { + (client_info->ip_dst == arp->ip_src) && + (compare_ether_addr_64bits(client_info->mac_dst, arp->mac_src))) { /* update the clients MAC address */ memcpy(client_info->mac_dst, arp->mac_src, ETH_ALEN); client_info->ntt = 1; -- cgit v1.2.3 From 7b3384fc30633738ae4eaf8e1bc6ce70470ced80 Mon Sep 17 00:00:00 2001 From: Michael S. Tsirkin Date: Thu, 1 Jul 2010 18:40:12 +0300 Subject: vhost: add unlikely annotations to error path patch 'break out of polling loop on error' caused a minor performance regression on my machine: recover that performance by adding a bunch of unlikely annotations in the error handling. Signed-off-by: Michael S. Tsirkin --- drivers/vhost/net.c | 4 ++-- drivers/vhost/vhost.c | 53 ++++++++++++++++++++++++++------------------------- 2 files changed, 29 insertions(+), 28 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 54096eef4840..2406377a6e5e 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -137,7 +137,7 @@ static void handle_tx(struct vhost_net *net) &out, &in, NULL, NULL); /* On error, stop handling until the next kick. */ - if (head < 0) + if (unlikely(head < 0)) break; /* Nothing new? Wait for eventfd to tell us they refilled. */ if (head == vq->num) { @@ -234,7 +234,7 @@ static void handle_rx(struct vhost_net *net) &out, &in, vq_log, &log); /* On error, stop handling until the next kick. */ - if (head < 0) + if (unlikely(head < 0)) break; /* OK, now we need to know about added descriptors. */ if (head == vq->num) { diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5ccd384ec0be..0b99783083f6 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -736,12 +736,12 @@ static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len, mem = rcu_dereference(dev->memory); while ((u64)len > s) { u64 size; - if (ret >= iov_size) { + if (unlikely(ret >= iov_size)) { ret = -ENOBUFS; break; } reg = find_region(mem, addr, len); - if (!reg) { + if (unlikely(!reg)) { ret = -EFAULT; break; } @@ -780,18 +780,18 @@ static unsigned next_desc(struct vring_desc *desc) return next; } -static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, - struct iovec iov[], unsigned int iov_size, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num, - struct vring_desc *indirect) +static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num, + struct vring_desc *indirect) { struct vring_desc desc; unsigned int i = 0, count, found = 0; int ret; /* Sanity check */ - if (indirect->len % sizeof desc) { + if (unlikely(indirect->len % sizeof desc)) { vq_err(vq, "Invalid length in indirect descriptor: " "len 0x%llx not multiple of 0x%zx\n", (unsigned long long)indirect->len, @@ -801,7 +801,7 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect, ARRAY_SIZE(vq->indirect)); - if (ret < 0) { + if (unlikely(ret < 0)) { vq_err(vq, "Translation failure %d in indirect.\n", ret); return ret; } @@ -813,7 +813,7 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, count = indirect->len / sizeof desc; /* Buffers are chained via a 16 bit next field, so * we can have at most 2^16 of these. */ - if (count > USHRT_MAX + 1) { + if (unlikely(count > USHRT_MAX + 1)) { vq_err(vq, "Indirect buffer length too big: %d\n", indirect->len); return -E2BIG; @@ -821,19 +821,19 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, do { unsigned iov_count = *in_num + *out_num; - if (++found > count) { + if (unlikely(++found > count)) { vq_err(vq, "Loop detected: last one at %u " "indirect size %u\n", i, count); return -EINVAL; } - if (memcpy_fromiovec((unsigned char *)&desc, vq->indirect, - sizeof desc)) { + if (unlikely(memcpy_fromiovec((unsigned char *)&desc, vq->indirect, + sizeof desc))) { vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n", i, (size_t)indirect->addr + i * sizeof desc); return -EINVAL; } - if (desc.flags & VRING_DESC_F_INDIRECT) { + if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) { vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n", i, (size_t)indirect->addr + i * sizeof desc); return -EINVAL; @@ -841,7 +841,7 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count, iov_size - iov_count); - if (ret < 0) { + if (unlikely(ret < 0)) { vq_err(vq, "Translation failure %d indirect idx %d\n", ret, i); return ret; @@ -857,7 +857,7 @@ static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq, } else { /* If it's an output descriptor, they're all supposed * to come before any input descriptors. */ - if (*in_num) { + if (unlikely(*in_num)) { vq_err(vq, "Indirect descriptor " "has out after in: idx %d\n", i); return -EINVAL; @@ -888,13 +888,13 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, /* Check it isn't doing very strange things with descriptor numbers. */ last_avail_idx = vq->last_avail_idx; - if (get_user(vq->avail_idx, &vq->avail->idx)) { + if (unlikely(get_user(vq->avail_idx, &vq->avail->idx))) { vq_err(vq, "Failed to access avail idx at %p\n", &vq->avail->idx); return -EFAULT; } - if ((u16)(vq->avail_idx - last_avail_idx) > vq->num) { + if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) { vq_err(vq, "Guest moved used index from %u to %u", last_avail_idx, vq->avail_idx); return -EFAULT; @@ -909,7 +909,8 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ - if (get_user(head, &vq->avail->ring[last_avail_idx % vq->num])) { + if (unlikely(get_user(head, + &vq->avail->ring[last_avail_idx % vq->num]))) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); @@ -917,7 +918,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, } /* If their number is silly, that's an error. */ - if (head >= vq->num) { + if (unlikely(head >= vq->num)) { vq_err(vq, "Guest says index %u > %u is available", head, vq->num); return -EINVAL; @@ -931,19 +932,19 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, i = head; do { unsigned iov_count = *in_num + *out_num; - if (i >= vq->num) { + if (unlikely(i >= vq->num)) { vq_err(vq, "Desc index is %u > %u, head = %u", i, vq->num, head); return -EINVAL; } - if (++found > vq->num) { + if (unlikely(++found > vq->num)) { vq_err(vq, "Loop detected: last one at %u " "vq size %u head %u\n", i, vq->num, head); return -EINVAL; } ret = copy_from_user(&desc, vq->desc + i, sizeof desc); - if (ret) { + if (unlikely(ret)) { vq_err(vq, "Failed to get descriptor: idx %d addr %p\n", i, vq->desc + i); return -EFAULT; @@ -952,7 +953,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, ret = get_indirect(dev, vq, iov, iov_size, out_num, in_num, log, log_num, &desc); - if (ret < 0) { + if (unlikely(ret < 0)) { vq_err(vq, "Failure detected " "in indirect descriptor at idx %d\n", i); return ret; @@ -962,7 +963,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count, iov_size - iov_count); - if (ret < 0) { + if (unlikely(ret < 0)) { vq_err(vq, "Translation failure %d descriptor idx %d\n", ret, i); return ret; @@ -979,7 +980,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq, } else { /* If it's an output descriptor, they're all supposed * to come before any input descriptors. */ - if (*in_num) { + if (unlikely(*in_num)) { vq_err(vq, "Descriptor has out after in: " "idx %d\n", i); return -EINVAL; -- cgit v1.2.3 From c89827e0e9346c039aed9b63c14096c2d36796b1 Mon Sep 17 00:00:00 2001 From: Cody Rester Date: Thu, 1 Jul 2010 21:27:44 -0700 Subject: drivers: bluetooth: bluecard_cs.c: Fixed include error, changed to linux/io.h Fixed include error, changed to linux/io.h Signed-off-by: Cody Rester Acked-by: Gustavo F. Padovan Signed-off-by: David S. Miller --- drivers/bluetooth/bluecard_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c index 6f907ebed2d5..6d34f405a2f3 100644 --- a/drivers/bluetooth/bluecard_cs.c +++ b/drivers/bluetooth/bluecard_cs.c @@ -37,7 +37,7 @@ #include #include -#include +#include #include #include -- cgit v1.2.3 From 499031ac8a3df6738f6186ded9da853e8ea18253 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Jul 2010 10:05:01 +0200 Subject: netfilter: ip6t_REJECT: fix a dst leak in ipv6 REJECT We should release dst if dst->error is set. Bug introduced in 2.6.14 by commit e104411b82f5c ([XFRM]: Always release dst_entry on error in xfrm_lookup) Signed-off-by: Eric Dumazet Cc: stable@kernel.org Signed-off-by: Patrick McHardy --- net/ipv6/netfilter/ip6t_REJECT.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 47d227713758..2933396e0281 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -97,9 +97,11 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) fl.fl_ip_dport = otcph.source; security_skb_classify_flow(oldskb, &fl); dst = ip6_route_output(net, NULL, &fl); - if (dst == NULL) + if (dst == NULL || dst->error) { + dst_release(dst); return; - if (dst->error || xfrm_lookup(net, &dst, &fl, NULL, 0)) + } + if (xfrm_lookup(net, &dst, &fl, NULL, 0)) return; hh_len = (dst->dev->hard_header_len + 15)&~15; -- cgit v1.2.3 From 7b00ac51ffcda994ef0839001257be894cc6e5a8 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 2 Jul 2010 21:47:54 -0700 Subject: net: Revert "rndis_host: Poll status channel before control channel" This reverts commit c17b274dc2aa538b68c1f02b01a3c4e124b435ba. That change was reported to break rndis_wlan support for the WUSB54GS. Reported-by: Luís Picciochi Oliveira Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/usb/rndis_host.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index 28d3ee175e7b..dd8a4adf48ca 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -104,10 +104,8 @@ static void rndis_msg_indicate(struct usbnet *dev, struct rndis_indicate *msg, int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) { struct cdc_state *info = (void *) &dev->data; - struct usb_cdc_notification notification; int master_ifnum; int retval; - int partial; unsigned count; __le32 rsp; u32 xid = 0, msg_len, request_id; @@ -135,17 +133,13 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) if (unlikely(retval < 0 || xid == 0)) return retval; - /* Some devices don't respond on the control channel until - * polled on the status channel, so do that first. */ - retval = usb_interrupt_msg( - dev->udev, - usb_rcvintpipe(dev->udev, dev->status->desc.bEndpointAddress), - ¬ification, sizeof(notification), &partial, - RNDIS_CONTROL_TIMEOUT_MS); - if (unlikely(retval < 0)) - return retval; + // FIXME Seems like some devices discard responses when + // we time out and cancel our "get response" requests... + // so, this is fragile. Probably need to poll for status. - /* Poll the control channel; the request probably completed immediately */ + /* ignore status endpoint, just poll the control channel; + * the request probably completed immediately + */ rsp = buf->msg_type | RNDIS_MSG_COMPLETION; for (count = 0; count < 10; count++) { memset(buf, 0, CONTROL_BUFFER_SIZE); -- cgit v1.2.3 From 0dacca73a3ddefa6cb8a7e0282f938e01faa1a64 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 2 Jul 2010 21:49:02 -0700 Subject: usbnet: Set parent device early for netdev_printk() netdev_printk() follows the net_device's parent device pointer, so we must set that earlier than we previously did. Reported-by: Luís Picciochi Oliveira Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index a95c73de5824..81c76ada8e56 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1293,6 +1293,9 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) goto out; } + /* netdev_printk() needs this so do it as early as possible */ + SET_NETDEV_DEV(net, &udev->dev); + dev = netdev_priv(net); dev->udev = xdev; dev->intf = udev; @@ -1377,8 +1380,6 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->rx_urb_size = dev->hard_mtu; dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1); - SET_NETDEV_DEV(net, &udev->dev); - if ((dev->driver_info->flags & FLAG_WLAN) != 0) SET_NETDEV_DEVTYPE(net, &wlan_type); if ((dev->driver_info->flags & FLAG_WWAN) != 0) -- cgit v1.2.3 From 72046d84f0d6e3047f4d5a5173260141983b2b61 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 1 Jul 2010 03:00:17 +0000 Subject: qlge: Replacing add_timer() to mod_timer() Currently qlge driver calls add_timer() instead of mod_timer(). This patch changes add_timer() to mod_timer(), which seems a better solution. Signed-off-by: Breno Leitao Signed-off-by: Ron Mercer Signed-off-by: David S. Miller --- drivers/net/qlge/qlge_main.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c index fa4b24c49f42..509dadcd1c5a 100644 --- a/drivers/net/qlge/qlge_main.c +++ b/drivers/net/qlge/qlge_main.c @@ -4611,8 +4611,7 @@ static void ql_timer(unsigned long data) return; } - qdev->timer.expires = jiffies + (5*HZ); - add_timer(&qdev->timer); + mod_timer(&qdev->timer, jiffies + (5*HZ)); } static int __devinit qlge_probe(struct pci_dev *pdev, @@ -4808,8 +4807,7 @@ static void qlge_io_resume(struct pci_dev *pdev) netif_err(qdev, ifup, qdev->ndev, "Device was not running prior to EEH.\n"); } - qdev->timer.expires = jiffies + (5*HZ); - add_timer(&qdev->timer); + mod_timer(&qdev->timer, jiffies + (5*HZ)); netif_device_attach(ndev); } @@ -4871,8 +4869,7 @@ static int qlge_resume(struct pci_dev *pdev) return err; } - qdev->timer.expires = jiffies + (5*HZ); - add_timer(&qdev->timer); + mod_timer(&qdev->timer, jiffies + (5*HZ)); netif_device_attach(ndev); return 0; -- cgit v1.2.3 From 7ae80abdba0644e12ac17da567a2db1efc1bf8a8 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 1 Jul 2010 03:00:18 +0000 Subject: qlge: fix a eeh handler to not add a pending timer On some ocasions the function qlge_io_resume() tries to add a pending timer, which causes the system to hit the BUG() on add_timer() function. This patch removes the timer during the EEH recovery. Signed-off-by: Breno Leitao Signed-off-by: Ron Mercer Signed-off-by: David S. Miller --- drivers/net/qlge/qlge_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c index 509dadcd1c5a..d10bcefc0e45 100644 --- a/drivers/net/qlge/qlge_main.c +++ b/drivers/net/qlge/qlge_main.c @@ -4712,6 +4712,8 @@ static void ql_eeh_close(struct net_device *ndev) netif_stop_queue(ndev); } + /* Disabling the timer */ + del_timer_sync(&qdev->timer); if (test_bit(QL_ADAPTER_UP, &qdev->flags)) cancel_delayed_work_sync(&qdev->asic_reset_work); cancel_delayed_work_sync(&qdev->mpi_reset_work); -- cgit v1.2.3 From 4ef6acff83222f4496ceef7d1f0ee9e50a5bb403 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 1 Jul 2010 13:21:35 +0000 Subject: sched: qdisc_reset_all_tx is calling qdisc_reset without qdisc_lock When calling qdisc_reset() the qdisc lock needs to be held. In this case there is at least one driver i4l which is using this without holding the lock. Add the locking here. Signed-off-by: John Fastabend Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/net/sch_generic.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 03ca5d826757..ba749be1e354 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -317,8 +317,16 @@ extern void tcf_destroy_chain(struct tcf_proto **fl); static inline void qdisc_reset_all_tx(struct net_device *dev) { unsigned int i; - for (i = 0; i < dev->num_tx_queues; i++) - qdisc_reset(netdev_get_tx_queue(dev, i)->qdisc); + struct Qdisc *qdisc; + + for (i = 0; i < dev->num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + if (qdisc) { + spin_lock_bh(qdisc_lock(qdisc)); + qdisc_reset(qdisc); + spin_unlock_bh(qdisc_lock(qdisc)); + } + } } /* Are all TX queues of the device empty? */ -- cgit v1.2.3 From f0796d5c73e59786d09a1e617689d1d415f2db44 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 1 Jul 2010 13:21:57 +0000 Subject: net: decreasing real_num_tx_queues needs to flush qdisc Reducing real_num_queues needs to flush the qdisc otherwise skbs with queue_mappings greater then real_num_tx_queues can be sent to the underlying driver. The flow for this is, dev_queue_xmit() dev_pick_tx() skb_tx_hash() => hash using real_num_tx_queues skb_set_queue_mapping() ... qdisc_enqueue_root() => enqueue skb on txq from hash ... dev->real_num_tx_queues -= n ... sch_direct_xmit() dev_hard_start_xmit() ndo_start_xmit(skb,dev) => skb queue set with old hash skbs are enqueued on the qdisc with skb->queue_mapping set 0 < queue_mappings < real_num_tx_queues. When the driver decreases real_num_tx_queues skb's may be dequeued from the qdisc with a queue_mapping greater then real_num_tx_queues. This fixes a case in ixgbe where this was occurring with DCB and FCoE. Because the driver is using queue_mapping to map skbs to tx descriptor rings we can potentially map skbs to rings that no longer exist. Signed-off-by: John Fastabend Tested-by: Ross Brattain Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/ixgbe/ixgbe_main.c | 2 +- include/linux/netdevice.h | 3 +++ include/net/sch_generic.h | 12 ++++++++---- net/core/dev.c | 18 ++++++++++++++++++ 4 files changed, 30 insertions(+), 5 deletions(-) diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index a0b33165b989..7b5d9764f317 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -4001,7 +4001,7 @@ static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter) done: /* Notify the stack of the (possibly) reduced Tx Queue count. */ - adapter->netdev->real_num_tx_queues = adapter->num_tx_queues; + netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); } static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 40291f375024..5e6188d9f017 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1656,6 +1656,9 @@ static inline int netif_is_multiqueue(const struct net_device *dev) return (dev->num_tx_queues > 1); } +extern void netif_set_real_num_tx_queues(struct net_device *dev, + unsigned int txq); + /* Use this variant when it is known for sure that it * is executing from hardware interrupt context or with hardware interrupts * disabled. diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ba749be1e354..433604bb3fe8 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -313,13 +313,12 @@ extern void qdisc_calculate_pkt_len(struct sk_buff *skb, extern void tcf_destroy(struct tcf_proto *tp); extern void tcf_destroy_chain(struct tcf_proto **fl); -/* Reset all TX qdiscs of a device. */ -static inline void qdisc_reset_all_tx(struct net_device *dev) +/* Reset all TX qdiscs greater then index of a device. */ +static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { - unsigned int i; struct Qdisc *qdisc; - for (i = 0; i < dev->num_tx_queues; i++) { + for (; i < dev->num_tx_queues; i++) { qdisc = netdev_get_tx_queue(dev, i)->qdisc; if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); @@ -329,6 +328,11 @@ static inline void qdisc_reset_all_tx(struct net_device *dev) } } +static inline void qdisc_reset_all_tx(struct net_device *dev) +{ + qdisc_reset_all_tx_gt(dev, 0); +} + /* Are all TX queues of the device empty? */ static inline bool qdisc_all_tx_empty(const struct net_device *dev) { diff --git a/net/core/dev.c b/net/core/dev.c index 2b3bf53bc687..723a34710ad4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1553,6 +1553,24 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); } +/* + * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues + * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. + */ +void netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) +{ + unsigned int real_num = dev->real_num_tx_queues; + + if (unlikely(txq > dev->num_tx_queues)) + ; + else if (txq > real_num) + dev->real_num_tx_queues = txq; + else if (txq < real_num) { + dev->real_num_tx_queues = txq; + qdisc_reset_all_tx_gt(dev, txq); + } +} +EXPORT_SYMBOL(netif_set_real_num_tx_queues); static inline void __netif_reschedule(struct Qdisc *q) { -- cgit v1.2.3 From e2aec372ff4b7e78e79c308104a860ae0ed20950 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 1 Jul 2010 13:18:58 +0000 Subject: linux/net.h: fix kernel-doc warnings Fix kernel-doc warnings in linux/net.h: Warning(include/linux/net.h:151): No description found for parameter 'wq' Warning(include/linux/net.h:151): Excess struct/union/enum/typedef member 'fasync_list' description in 'socket' Warning(include/linux/net.h:151): Excess struct/union/enum/typedef member 'wait' description in 'socket' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/net.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/linux/net.h b/include/linux/net.h index 2b4deeeb8646..dee0b11a8759 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -129,10 +129,9 @@ struct socket_wq { * @type: socket type (%SOCK_STREAM, etc) * @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc) * @ops: protocol specific socket operations - * @fasync_list: Asynchronous wake up list * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation - * @wait: wait queue for several uses + * @wq: wait queue for several uses */ struct socket { socket_state state; -- cgit v1.2.3 From 4a49043223e5047c8f60a09f7b2927a2e6e8dfc7 Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Fri, 2 Jul 2010 09:13:49 +0000 Subject: s2io: resolve statistics issues This patch resolves a number of issues in the statistics gathering of the s2io driver. On Xframe adapters, the received multicast statistics counter includes pause frames which are not indicated to the driver. This can cause issues where the multicast packet count is higher than what has actually been received, possibly higher than the number of packets received. The driver software counters are replaced with the adapter hardware statistics for rx_packets, rx_bytes, and tx_bytes. It also uses the overflow registers to determine if the statistics wrapped the 32bit register (removing the window of having a statistic value less than the previous call). rx_length_errors statistic now includes undersized packets in addition to oversized packets in its counting. Finally, rx_crc_errors are now being counted. Signed-off-by: Jon Mason Signed-off-by: David S. Miller --- drivers/net/s2io.c | 101 +++++++++++++++++++++++++++++++++-------------------- drivers/net/s2io.h | 4 --- 2 files changed, 64 insertions(+), 41 deletions(-) diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c index 668327ccd8d0..1d37f0c310ca 100644 --- a/drivers/net/s2io.c +++ b/drivers/net/s2io.c @@ -3130,7 +3130,6 @@ static void tx_intr_handler(struct fifo_info *fifo_data) pkt_cnt++; /* Updating the statistics block */ - nic->dev->stats.tx_bytes += skb->len; swstats->mem_freed += skb->truesize; dev_kfree_skb_irq(skb); @@ -4901,48 +4900,81 @@ static void s2io_updt_stats(struct s2io_nic *sp) * Return value: * pointer to the updated net_device_stats structure. */ - static struct net_device_stats *s2io_get_stats(struct net_device *dev) { struct s2io_nic *sp = netdev_priv(dev); - struct config_param *config = &sp->config; struct mac_info *mac_control = &sp->mac_control; struct stat_block *stats = mac_control->stats_info; - int i; + u64 delta; /* Configure Stats for immediate updt */ s2io_updt_stats(sp); - /* Using sp->stats as a staging area, because reset (due to mtu - change, for example) will clear some hardware counters */ - dev->stats.tx_packets += le32_to_cpu(stats->tmac_frms) - - sp->stats.tx_packets; - sp->stats.tx_packets = le32_to_cpu(stats->tmac_frms); - - dev->stats.tx_errors += le32_to_cpu(stats->tmac_any_err_frms) - - sp->stats.tx_errors; - sp->stats.tx_errors = le32_to_cpu(stats->tmac_any_err_frms); - - dev->stats.rx_errors += le64_to_cpu(stats->rmac_drop_frms) - - sp->stats.rx_errors; - sp->stats.rx_errors = le64_to_cpu(stats->rmac_drop_frms); - - dev->stats.multicast = le32_to_cpu(stats->rmac_vld_mcst_frms) - - sp->stats.multicast; - sp->stats.multicast = le32_to_cpu(stats->rmac_vld_mcst_frms); - - dev->stats.rx_length_errors = le64_to_cpu(stats->rmac_long_frms) - - sp->stats.rx_length_errors; - sp->stats.rx_length_errors = le64_to_cpu(stats->rmac_long_frms); + /* A device reset will cause the on-adapter statistics to be zero'ed. + * This can be done while running by changing the MTU. To prevent the + * system from having the stats zero'ed, the driver keeps a copy of the + * last update to the system (which is also zero'ed on reset). This + * enables the driver to accurately know the delta between the last + * update and the current update. + */ + delta = ((u64) le32_to_cpu(stats->rmac_vld_frms_oflow) << 32 | + le32_to_cpu(stats->rmac_vld_frms)) - sp->stats.rx_packets; + sp->stats.rx_packets += delta; + dev->stats.rx_packets += delta; + + delta = ((u64) le32_to_cpu(stats->tmac_frms_oflow) << 32 | + le32_to_cpu(stats->tmac_frms)) - sp->stats.tx_packets; + sp->stats.tx_packets += delta; + dev->stats.tx_packets += delta; + + delta = ((u64) le32_to_cpu(stats->rmac_data_octets_oflow) << 32 | + le32_to_cpu(stats->rmac_data_octets)) - sp->stats.rx_bytes; + sp->stats.rx_bytes += delta; + dev->stats.rx_bytes += delta; + + delta = ((u64) le32_to_cpu(stats->tmac_data_octets_oflow) << 32 | + le32_to_cpu(stats->tmac_data_octets)) - sp->stats.tx_bytes; + sp->stats.tx_bytes += delta; + dev->stats.tx_bytes += delta; + + delta = le64_to_cpu(stats->rmac_drop_frms) - sp->stats.rx_errors; + sp->stats.rx_errors += delta; + dev->stats.rx_errors += delta; + + delta = ((u64) le32_to_cpu(stats->tmac_any_err_frms_oflow) << 32 | + le32_to_cpu(stats->tmac_any_err_frms)) - sp->stats.tx_errors; + sp->stats.tx_errors += delta; + dev->stats.tx_errors += delta; + + delta = le64_to_cpu(stats->rmac_drop_frms) - sp->stats.rx_dropped; + sp->stats.rx_dropped += delta; + dev->stats.rx_dropped += delta; + + delta = le64_to_cpu(stats->tmac_drop_frms) - sp->stats.tx_dropped; + sp->stats.tx_dropped += delta; + dev->stats.tx_dropped += delta; + + /* The adapter MAC interprets pause frames as multicast packets, but + * does not pass them up. This erroneously increases the multicast + * packet count and needs to be deducted when the multicast frame count + * is queried. + */ + delta = (u64) le32_to_cpu(stats->rmac_vld_mcst_frms_oflow) << 32 | + le32_to_cpu(stats->rmac_vld_mcst_frms); + delta -= le64_to_cpu(stats->rmac_pause_ctrl_frms); + delta -= sp->stats.multicast; + sp->stats.multicast += delta; + dev->stats.multicast += delta; - /* collect per-ring rx_packets and rx_bytes */ - dev->stats.rx_packets = dev->stats.rx_bytes = 0; - for (i = 0; i < config->rx_ring_num; i++) { - struct ring_info *ring = &mac_control->rings[i]; + delta = ((u64) le32_to_cpu(stats->rmac_usized_frms_oflow) << 32 | + le32_to_cpu(stats->rmac_usized_frms)) + + le64_to_cpu(stats->rmac_long_frms) - sp->stats.rx_length_errors; + sp->stats.rx_length_errors += delta; + dev->stats.rx_length_errors += delta; - dev->stats.rx_packets += ring->rx_packets; - dev->stats.rx_bytes += ring->rx_bytes; - } + delta = le64_to_cpu(stats->rmac_fcs_err_frms) - sp->stats.rx_crc_errors; + sp->stats.rx_crc_errors += delta; + dev->stats.rx_crc_errors += delta; return &dev->stats; } @@ -7455,15 +7487,11 @@ static int rx_osm_handler(struct ring_info *ring_data, struct RxD_t * rxdp) } } - /* Updating statistics */ - ring_data->rx_packets++; rxdp->Host_Control = 0; if (sp->rxd_mode == RXD_MODE_1) { int len = RXD_GET_BUFFER0_SIZE_1(rxdp->Control_2); - ring_data->rx_bytes += len; skb_put(skb, len); - } else if (sp->rxd_mode == RXD_MODE_3B) { int get_block = ring_data->rx_curr_get_info.block_index; int get_off = ring_data->rx_curr_get_info.offset; @@ -7472,7 +7500,6 @@ static int rx_osm_handler(struct ring_info *ring_data, struct RxD_t * rxdp) unsigned char *buff = skb_push(skb, buf0_len); struct buffAdd *ba = &ring_data->ba[get_block][get_off]; - ring_data->rx_bytes += buf0_len + buf2_len; memcpy(buff, ba->ba_0, buf0_len); skb_put(skb, buf2_len); } diff --git a/drivers/net/s2io.h b/drivers/net/s2io.h index 47c36e0994f5..5e52c75892df 100644 --- a/drivers/net/s2io.h +++ b/drivers/net/s2io.h @@ -745,10 +745,6 @@ struct ring_info { /* Buffer Address store. */ struct buffAdd **ba; - - /* per-Ring statistics */ - unsigned long rx_packets; - unsigned long rx_bytes; } ____cacheline_aligned; /* Fifo specific structure */ -- cgit v1.2.3 From 1788f49548860fa1c861ee3454d47b466c877e43 Mon Sep 17 00:00:00 2001 From: Michael S. Tsirkin Date: Fri, 2 Jul 2010 16:32:55 +0000 Subject: virtio_net: do not reschedule rx refill forever We currently fill all of RX ring, then add_buf returns ENOSPC, which gets mis-detected as an out of memory condition and causes us to reschedule the work, and so on forever. Fix this by oom = err == -ENOMEM; Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell Cc: stable@kernel.org # .34.x Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1edb7a61983c..ee7571195b10 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -415,7 +415,7 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp) static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp) { int err; - bool oom = false; + bool oom; do { if (vi->mergeable_rx_bufs) @@ -425,10 +425,9 @@ static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp) else err = add_recvbuf_small(vi, gfp); - if (err < 0) { - oom = true; + oom = err == -ENOMEM; + if (err < 0) break; - } ++vi->num; } while (err > 0); if (unlikely(vi->num > vi->max)) -- cgit v1.2.3 From 58eba97d0774c69b1cf3e5a8ac74419409d1abbf Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 2 Jul 2010 16:34:01 +0000 Subject: virtio_net: fix oom handling on tx virtio net will never try to overflow the TX ring, so the only reason add_buf may fail is out of memory. Thus, we can not stop the device until some request completes - there's no guarantee anything at all is outstanding. Make the error message clearer as well: error here does not indicate queue full. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell (...and avoid TX_BUSY) Cc: stable@kernel.org # .34.x (s/virtqueue_/vi->svq->vq_ops->/) Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ee7571195b10..bb6b67f6b0cc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -562,7 +562,6 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) struct virtnet_info *vi = netdev_priv(dev); int capacity; -again: /* Free up any pending old buffers before queueing new ones. */ free_old_xmit_skbs(vi); @@ -571,14 +570,20 @@ again: /* This can happen with OOM and indirect buffers. */ if (unlikely(capacity < 0)) { - netif_stop_queue(dev); - dev_warn(&dev->dev, "Unexpected full queue\n"); - if (unlikely(!virtqueue_enable_cb(vi->svq))) { - virtqueue_disable_cb(vi->svq); - netif_start_queue(dev); - goto again; + if (net_ratelimit()) { + if (likely(capacity == -ENOMEM)) { + dev_warn(&dev->dev, + "TX queue failure: out of memory\n"); + } else { + dev->stats.tx_fifo_errors++; + dev_warn(&dev->dev, + "Unexpected TX queue failure: %d\n", + capacity); + } } - return NETDEV_TX_BUSY; + dev->stats.tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; } virtqueue_kick(vi->svq); -- cgit v1.2.3 From 44b451f1633896de15d2d52e1a2bd462e80b7814 Mon Sep 17 00:00:00 2001 From: Peter Kosyh Date: Fri, 2 Jul 2010 07:47:55 +0000 Subject: xfrm: fix xfrm by MARK logic While using xfrm by MARK feature in 2.6.34 - 2.6.35 kernels, the mark is always cleared in flowi structure via memset in _decode_session4 (net/ipv4/xfrm4_policy.c), so the policy lookup fails. IPv6 code is affected by this bug too. Signed-off-by: Peter Kosyh Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/xfrm4_policy.c | 2 ++ net/ipv6/xfrm6_policy.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1705476670ef..23883a48ebfb 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -108,6 +108,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) u8 *xprth = skb_network_header(skb) + iph->ihl * 4; memset(fl, 0, sizeof(struct flowi)); + fl->mark = skb->mark; + if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) { switch (iph->protocol) { case IPPROTO_UDP: diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 4a0e77e14468..6baeabbbca82 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -124,6 +124,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) u8 nexthdr = nh[IP6CB(skb)->nhoff]; memset(fl, 0, sizeof(struct flowi)); + fl->mark = skb->mark; + ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr); ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr); -- cgit v1.2.3 From 3390712a474abdcd3de10024dd1062e5928d381c Mon Sep 17 00:00:00 2001 From: Kulikov Vasiliy Date: Sat, 3 Jul 2010 05:20:42 +0000 Subject: net/ne: fix memory leak in ne_drv_probe() net_device allocated with alloc_eip_netdev() must be freed. Signed-off-by: Kulikov Vasiliy Signed-off-by: David S. Miller --- drivers/net/ne.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ne.c b/drivers/net/ne.c index b8e2923a1d69..1063093b3afc 100644 --- a/drivers/net/ne.c +++ b/drivers/net/ne.c @@ -806,8 +806,10 @@ static int __init ne_drv_probe(struct platform_device *pdev) dev->base_addr = res->start; dev->irq = platform_get_irq(pdev, 0); } else { - if (this_dev < 0 || this_dev >= MAX_NE_CARDS) + if (this_dev < 0 || this_dev >= MAX_NE_CARDS) { + free_netdev(dev); return -EINVAL; + } dev->base_addr = io[this_dev]; dev->irq = irq[this_dev]; dev->mem_end = bad[this_dev]; -- cgit v1.2.3 From bcfcc450baaaa44afc1d3c51ef96a53338ff0eb2 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 2 Jul 2010 07:08:44 +0000 Subject: net: Fix definition of netif_vdbg() when VERBOSE_DEBUG is defined netif_vdbg() was originally defined as entirely equivalent to netdev_vdbg(), but I assume that it was intended to take the same parameters as netif_dbg() etc. (Currently it is only used by the sfc driver, in which I worked on that assumption.) In commit a4ed89c I changed the definition used when VERBOSE_DEBUG is not defined, but I failed to notice that the definition used when VERBOSE_DEBUG is defined was also not as I expected. Change that to match netif_dbg() as well. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e6188d9f017..b21e4054c12c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2332,7 +2332,7 @@ do { \ #endif #if defined(VERBOSE_DEBUG) -#define netif_vdbg netdev_dbg +#define netif_vdbg netif_dbg #else #define netif_vdbg(priv, type, dev, format, args...) \ ({ \ -- cgit v1.2.3 From 7f285fa78d4b81b8458f05e77fb6b46245121b4e Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 5 Jul 2010 14:50:08 +0000 Subject: bridge br_multicast: BUG: unable to handle kernel NULL pointer dereference On Tue, Jul 06, 2010 at 08:48:35AM +0800, Herbert Xu wrote: > > bridge: Restore NULL check in br_mdb_ip_get Resend with proper attribution. bridge: Restore NULL check in br_mdb_ip_get Somewhere along the line the NULL check in br_mdb_ip_get went AWOL, causing crashes when we receive an IGMP packet with no multicast table allocated. This patch restores it and ensures all br_mdb_*_get functions use it. Reported-by: Frank Arnold Signed-off-by: Herbert Xu Thanks, Signed-off-by: David S. Miller --- net/bridge/br_multicast.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 9d21d98ae5fa..27ae946363f1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -99,6 +99,15 @@ static struct net_bridge_mdb_entry *__br_mdb_ip_get( return NULL; } +static struct net_bridge_mdb_entry *br_mdb_ip_get( + struct net_bridge_mdb_htable *mdb, struct br_ip *dst) +{ + if (!mdb) + return NULL; + + return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst)); +} + static struct net_bridge_mdb_entry *br_mdb_ip4_get( struct net_bridge_mdb_htable *mdb, __be32 dst) { @@ -107,7 +116,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get( br_dst.u.ip4 = dst; br_dst.proto = htons(ETH_P_IP); - return __br_mdb_ip_get(mdb, &br_dst, __br_ip4_hash(mdb, dst)); + return br_mdb_ip_get(mdb, &br_dst); } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) @@ -119,23 +128,17 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get( ipv6_addr_copy(&br_dst.u.ip6, dst); br_dst.proto = htons(ETH_P_IPV6); - return __br_mdb_ip_get(mdb, &br_dst, __br_ip6_hash(mdb, dst)); + return br_mdb_ip_get(mdb, &br_dst); } #endif -static struct net_bridge_mdb_entry *br_mdb_ip_get( - struct net_bridge_mdb_htable *mdb, struct br_ip *dst) -{ - return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst)); -} - struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, struct sk_buff *skb) { struct net_bridge_mdb_htable *mdb = br->mdb; struct br_ip ip; - if (!mdb || br->multicast_disabled) + if (br->multicast_disabled) return NULL; if (BR_INPUT_SKB_CB(skb)->igmp) -- cgit v1.2.3 From 17762060c25590bfddd68cc1131f28ec720f405f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 5 Jul 2010 21:29:28 +0000 Subject: bridge: Clear IPCB before possible entry into IP stack The bridge protocol lives dangerously by having incestuous relations with the IP stack. In this instance an abomination has been created where a bogus IPCB area from a bridged packet leads to a crash in the IP stack because it's interpreted as IP options. This patch papers over the problem by clearing the IPCB area in that particular spot. To fix this properly we'd also need to parse any IP options if present but I'm way too lazy for that. Signed-off-by: Herbert Xu Cheers, Signed-off-by: David S. Miller --- net/bridge/br_netfilter.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 44420992f72f..8fb75f89c4aa 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -591,6 +591,9 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, pskb_trim_rcsum(skb, len); + /* BUG: Should really parse the IP options here. */ + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + nf_bridge_put(skb->nf_bridge); if (!nf_bridge_alloc(skb)) return NF_DROP; -- cgit v1.2.3 From dfe1e8eddcd73fc58124933c14c2efe93fab0b8f Mon Sep 17 00:00:00 2001 From: Denis Kirjanov Date: Mon, 5 Jul 2010 21:44:20 +0000 Subject: ll_temac: Fix missing iounmaps Fix missing iounmaps. Signed-off-by: Denis Kirjanov Signed-off-by: David S. Miller --- drivers/net/ll_temac_main.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/ll_temac_main.c b/drivers/net/ll_temac_main.c index 52dcc8495647..6474c4973d3a 100644 --- a/drivers/net/ll_temac_main.c +++ b/drivers/net/ll_temac_main.c @@ -964,7 +964,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match) np = of_parse_phandle(op->dev.of_node, "llink-connected", 0); if (!np) { dev_err(&op->dev, "could not find DMA node\n"); - goto nodev; + goto err_iounmap; } /* Setup the DMA register accesses, could be DCR or memory mapped */ @@ -978,7 +978,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match) dev_dbg(&op->dev, "MEM base: %p\n", lp->sdma_regs); } else { dev_err(&op->dev, "unable to map DMA registers\n"); - goto nodev; + goto err_iounmap; } } @@ -987,7 +987,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match) if ((lp->rx_irq == NO_IRQ) || (lp->tx_irq == NO_IRQ)) { dev_err(&op->dev, "could not determine irqs\n"); rc = -ENOMEM; - goto nodev; + goto err_iounmap_2; } of_node_put(np); /* Finished with the DMA node; drop the reference */ @@ -997,7 +997,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match) if ((!addr) || (size != 6)) { dev_err(&op->dev, "could not find MAC address\n"); rc = -ENODEV; - goto nodev; + goto err_iounmap_2; } temac_set_mac_address(ndev, (void *)addr); @@ -1013,7 +1013,7 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match) rc = sysfs_create_group(&lp->dev->kobj, &temac_attr_group); if (rc) { dev_err(lp->dev, "Error creating sysfs files\n"); - goto nodev; + goto err_iounmap_2; } rc = register_netdev(lp->ndev); @@ -1026,6 +1026,11 @@ temac_of_probe(struct of_device *op, const struct of_device_id *match) err_register_ndev: sysfs_remove_group(&lp->dev->kobj, &temac_attr_group); + err_iounmap_2: + if (lp->sdma_regs) + iounmap(lp->sdma_regs); + err_iounmap: + iounmap(lp->regs); nodev: free_netdev(ndev); ndev = NULL; @@ -1044,6 +1049,9 @@ static int __devexit temac_of_remove(struct of_device *op) of_node_put(lp->phy_node); lp->phy_node = NULL; dev_set_drvdata(&op->dev, NULL); + iounmap(lp->regs); + if (lp->sdma_regs) + iounmap(lp->sdma_regs); free_netdev(ndev); return 0; } -- cgit v1.2.3 From 7074b16cc6bd27b1962e8f592b3733ebe92f4897 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Tue, 6 Jul 2010 03:02:03 +0000 Subject: vxge: show startup message with KERN_INFO The original KERN_CRIT will mess up terminals. CC: Sreenivasa Honnur Signed-off-by: Wu Fengguang Signed-off-by: David S. Miller --- drivers/net/vxge/vxge-main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index d14e207de1df..fc8b2d7a0919 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -4517,9 +4517,9 @@ vxge_starter(void) char version[32]; snprintf(version, 32, "%s", DRV_VERSION); - printk(KERN_CRIT "%s: Copyright(c) 2002-2009 Neterion Inc\n", + printk(KERN_INFO "%s: Copyright(c) 2002-2009 Neterion Inc\n", VXGE_DRIVER_NAME); - printk(KERN_CRIT "%s: Driver version: %s\n", + printk(KERN_INFO "%s: Driver version: %s\n", VXGE_DRIVER_NAME, version); verify_bandwidth(); -- cgit v1.2.3 From 33b665eeeb85956ccbdf31c4c31a4e2a31133c44 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Tue, 6 Jul 2010 05:18:11 +0000 Subject: NET: SB1250: Initialize .owner Signed-off-by: Ralf Baechle drivers/net/sb1250-mac.c | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) Signed-off-by: David S. Miller --- drivers/net/sb1250-mac.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/sb1250-mac.c b/drivers/net/sb1250-mac.c index 1f3acc3a5dfd..79eee3062083 100644 --- a/drivers/net/sb1250-mac.c +++ b/drivers/net/sb1250-mac.c @@ -2671,6 +2671,7 @@ static struct platform_driver sbmac_driver = { .remove = __exit_p(sbmac_remove), .driver = { .name = sbmac_string, + .owner = THIS_MODULE, }, }; -- cgit v1.2.3