From 33766368f6532313571534f9112b1796d6651bbe Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sun, 30 Sep 2012 19:47:40 +0300 Subject: mac80211: Fix FC masking in BIP AAD generation The bits used in the mask were off-by-one and ended up masking PwrMgt, MoreData, Protected fields instead of Retry, PwrMgt, MoreData. Fix this and to mask the correct fields. While doing so, convert the code to mask the full FC using IEEE80211_FCTL_* defines similarly to how CCMP AAD is built. Since BIP is used only with broadcast/multicast management frames, the Retry field is always 0 in these frames. The Protected field is also zero to maintain backwards compatibility. As such, the incorrect mask here does not really cause any problems for valid frames. In theory, an invalid BIP frame with Retry or Protected field set to 1 could be rejected because of BIP validation. However, no such frame should show up with standard compliant implementations, so this does not cause problems in normal BIP use. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- net/mac80211/wpa.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index bdb53aba888e..e58bf3fe3ed9 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -545,14 +545,19 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) static void bip_aad(struct sk_buff *skb, u8 *aad) { + __le16 mask_fc; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + /* BIP AAD: FC(masked) || A1 || A2 || A3 */ /* FC type/subtype */ - aad[0] = skb->data[0]; /* Mask FC Retry, PwrMgt, MoreData flags to zero */ - aad[1] = skb->data[1] & ~(BIT(4) | BIT(5) | BIT(6)); + mask_fc = hdr->frame_control; + mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_RETRY | IEEE80211_FCTL_PM | + IEEE80211_FCTL_MOREDATA); + put_unaligned(mask_fc, (__le16 *) &aad[0]); /* A1 || A2 || A3 */ - memcpy(aad + 2, skb->data + 4, 3 * ETH_ALEN); + memcpy(aad + 2, &hdr->addr1, 3 * ETH_ALEN); } -- cgit v1.2.3 From 6f5601251d7e306b8a7bf5e674c5307d865c0fa1 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 4 Oct 2012 20:01:21 -0400 Subject: net, TTY: initialize tty->driver_data before usage Commit 9c650ffc ("TTY: ircomm_tty, add tty install") split _open() to _install() and _open(). It also moved the initialization of driver_data out of open(), but never added it to install() - causing a NULL ptr deref whenever the driver was used. Signed-off-by: Sasha Levin Acked-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- net/irda/ircomm/ircomm_tty.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 95a3a7a336ba..496ce2cebcd7 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -421,6 +421,8 @@ static int ircomm_tty_install(struct tty_driver *driver, struct tty_struct *tty) hashbin_insert(ircomm_tty, (irda_queue_t *) self, line, NULL); } + tty->driver_data = self; + return tty_port_install(&self->port, driver, tty); } -- cgit v1.2.3 From b61a602ee6730150f4d0df730d9312ac4d820ceb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 9 Oct 2012 13:04:34 +0900 Subject: ipvs: initialize returned data in do_ip_vs_get_ctl As reported by a gcc warning, the do_ip_vs_get_ctl does not initalize all the members of the ip_vs_timeout_user structure it returns if at least one of the TCP or UDP protocols is disabled for ipvs. This makes sure that the data is always initialized, before it is returned as a response to IPVS_CMD_GET_CONFIG or printed as a debug message in IPVS_CMD_SET_CONFIG. Without this patch, building ARM ixp4xx_defconfig results in: net/netfilter/ipvs/ip_vs_ctl.c: In function 'ip_vs_genl_set_cmd': net/netfilter/ipvs/ip_vs_ctl.c:2238:47: warning: 't.udp_timeout' may be used uninitialized in this function [-Wuninitialized] net/netfilter/ipvs/ip_vs_ctl.c:3322:28: note: 't.udp_timeout' was declared here net/netfilter/ipvs/ip_vs_ctl.c:2238:47: warning: 't.tcp_fin_timeout' may be used uninitialized in this function [-Wuninitialized] net/netfilter/ipvs/ip_vs_ctl.c:3322:28: note: 't.tcp_fin_timeout' was declared here net/netfilter/ipvs/ip_vs_ctl.c:2238:47: warning: 't.tcp_timeout' may be used uninitialized in this function [-Wuninitialized] net/netfilter/ipvs/ip_vs_ctl.c:3322:28: note: 't.tcp_timeout' was declared here Signed-off-by: Arnd Bergmann Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_ctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7e7198b51c06..c4ee43710aab 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2589,6 +2589,8 @@ __ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) struct ip_vs_proto_data *pd; #endif + memset(u, 0, sizeof (*u)); + #ifdef CONFIG_IP_VS_PROTO_TCP pd = ip_vs_proto_data_get(net, IPPROTO_TCP); u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; @@ -2766,7 +2768,6 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; - memset(&t, 0, sizeof(t)); __ip_vs_get_timeouts(net, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; -- cgit v1.2.3 From 588377d6199034c36d335e7df5818b731fea072c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 8 Oct 2012 20:37:30 -0700 Subject: rbd: reset BACKOFF if unable to re-queue If ceph_fault() is unable to queue work after a delay, it sets the BACKOFF connection flag so con_work() will attempt to do so. In con_work(), when BACKOFF is set, if queue_delayed_work() doesn't result in newly-queued work, it simply ignores this condition and proceeds as if no backoff delay were desired. There are two problems with this--one of which is a bug. The first problem is simply that the intended behavior is to back off, and if we aren't able queue the work item to run after a delay we're not doing that. The only reason queue_delayed_work() won't queue work is if the provided work item is already queued. In the messenger, this means that con_work() is already scheduled to be run again. So if we simply set the BACKOFF flag again when this occurs, we know the next con_work() call will again attempt to hold off activity on the connection until after the delay. The second problem--the bug--is a leak of a reference count. If queue_delayed_work() returns 0 in con_work(), con->ops->put() drops the connection reference held on entry to con_work(). However, processing is (was) allowed to continue, and at the end of the function a second con->ops->put() is called. This patch fixes both problems. Signed-off-by: Alex Elder Reviewed-by: Sage Weil --- net/ceph/messenger.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 159aa8bef9e7..cad0d17ec45e 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2300,10 +2300,11 @@ restart: mutex_unlock(&con->mutex); return; } else { - con->ops->put(con); dout("con_work %p FAILED to back off %lu\n", con, con->delay); + set_bit(CON_FLAG_BACKOFF, &con->flags); } + goto done; } if (con->state == CON_STATE_STANDBY) { -- cgit v1.2.3 From 065a13e2cc665f6547dc7e8a9d6b6565badf940a Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 11 Oct 2012 16:26:06 +0200 Subject: Bluetooth: SMP: Fix setting unknown auth_req bits When sending a pairing request or response we should not just blindly copy the value that the remote device sent. Instead we should at least make sure to mask out any unknown bits. This is particularly critical from the upcoming LE Secure Connections feature perspective as incorrectly indicating support for it (by copying the remote value) would cause a failure to pair with devices that support it. Signed-off-by: Johan Hedberg Cc: stable@kernel.org Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- net/bluetooth/smp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 8c225ef349cd..2ac8d50861e0 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -32,6 +32,8 @@ #define SMP_TIMEOUT msecs_to_jiffies(30000) +#define AUTH_REQ_MASK 0x07 + static inline void swap128(u8 src[16], u8 dst[16]) { int i; @@ -230,7 +232,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, req->max_key_size = SMP_MAX_ENC_KEY_SIZE; req->init_key_dist = 0; req->resp_key_dist = dist_keys; - req->auth_req = authreq; + req->auth_req = (authreq & AUTH_REQ_MASK); return; } @@ -239,7 +241,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, rsp->max_key_size = SMP_MAX_ENC_KEY_SIZE; rsp->init_key_dist = 0; rsp->resp_key_dist = req->resp_key_dist & dist_keys; - rsp->auth_req = authreq; + rsp->auth_req = (authreq & AUTH_REQ_MASK); } static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) -- cgit v1.2.3 From 0153d5a810ab335aae86acfe69722a7efc1db536 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 11 Oct 2012 10:49:12 +0200 Subject: netfilter: xt_CT: fix timeout setting with IPv6 This patch fixes ip6tables and the CT target if it is used to set some custom conntrack timeout policy for IPv6. Use xt_ct_find_proto which already handles the ip6tables case for us. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_CT.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 16c712563860..ae7f5daeee43 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -180,9 +180,9 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, typeof(nf_ct_timeout_find_get_hook) timeout_find_get; struct ctnl_timeout *timeout; struct nf_conn_timeout *timeout_ext; - const struct ipt_entry *e = par->entryinfo; struct nf_conntrack_l4proto *l4proto; int ret = 0; + u8 proto; rcu_read_lock(); timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook); @@ -192,9 +192,11 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, goto out; } - if (e->ip.invflags & IPT_INV_PROTO) { + proto = xt_ct_find_proto(par); + if (!proto) { ret = -EINVAL; - pr_info("You cannot use inversion on L4 protocol\n"); + pr_info("You must specify a L4 protocol, and not use " + "inversions on it.\n"); goto out; } @@ -214,7 +216,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, /* Make sure the timeout policy matches any existing protocol tracker, * otherwise default to generic. */ - l4proto = __nf_ct_l4proto_find(par->family, e->ip.proto); + l4proto = __nf_ct_l4proto_find(par->family, proto); if (timeout->l4proto->l4proto != l4proto->l4proto) { ret = -EINVAL; pr_info("Timeout policy `%s' can only be used by L4 protocol " -- cgit v1.2.3 From 939ccba437da1726a5c8a5b702a47d473da927ae Mon Sep 17 00:00:00 2001 From: Elison Niven Date: Mon, 15 Oct 2012 00:44:48 +0000 Subject: netfilter: xt_nat: fix incorrect hooks for SNAT and DNAT targets In (c7232c9 netfilter: add protocol independent NAT core), the hooks were accidentally modified: SNAT hooks are POST_ROUTING and LOCAL_IN (before it was LOCAL_OUT). DNAT hooks are PRE_ROUTING and LOCAL_OUT (before it was LOCAL_IN). Signed-off-by: Elison Niven Signed-off-by: Sanket Shah Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_nat.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index 81aafa8e4fef..bea7464cc43f 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -111,7 +111,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .family = NFPROTO_IPV4, .table = "nat", .hooks = (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT), + (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { @@ -123,7 +123,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .family = NFPROTO_IPV4, .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_LOCAL_IN), + (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, { @@ -133,7 +133,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .targetsize = sizeof(struct nf_nat_range), .table = "nat", .hooks = (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT), + (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { @@ -143,7 +143,7 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { .targetsize = sizeof(struct nf_nat_range), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_LOCAL_IN), + (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, }; -- cgit v1.2.3 From 6863255bd0e48bc41ae5a066d5c771801e92735a Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Mon, 15 Oct 2012 14:52:41 +0200 Subject: cfg80211/mac80211: avoid state mishmash on deauth Avoid situation when we are on associate state in mac80211 and on disassociate state in cfg80211. This can results on crash during modules unload (like showed on this thread: http://marc.info/?t=134373976300001&r=1&w=2) and possibly other problems. Reported-by: Pedro Francisco Cc: stable@vger.kernel.org Signed-off-by: Stanislaw Gruszka Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 1 + net/mac80211/mlme.c | 5 +++-- net/wireless/mlme.c | 12 +++--------- 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1b4989082244..f8cd4cf3fad8 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1218,6 +1218,7 @@ struct cfg80211_deauth_request { const u8 *ie; size_t ie_len; u16 reason_code; + bool local_state_change; }; /** diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e714ed8bb198..e510a33fec76 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3549,6 +3549,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + bool tx = !req->local_state_change; mutex_lock(&ifmgd->mtx); @@ -3565,12 +3566,12 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, if (ifmgd->associated && ether_addr_equal(ifmgd->associated->bssid, req->bssid)) { ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, - req->reason_code, true, frame_buf); + req->reason_code, tx, frame_buf); } else { drv_mgd_prepare_tx(sdata->local, sdata); ieee80211_send_deauth_disassoc(sdata, req->bssid, IEEE80211_STYPE_DEAUTH, - req->reason_code, true, + req->reason_code, tx, frame_buf); } diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 8016fee0752b..904a7f368325 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -457,20 +457,14 @@ int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, .reason_code = reason, .ie = ie, .ie_len = ie_len, + .local_state_change = local_state_change, }; ASSERT_WDEV_LOCK(wdev); - if (local_state_change) { - if (wdev->current_bss && - ether_addr_equal(wdev->current_bss->pub.bssid, bssid)) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(&wdev->current_bss->pub); - wdev->current_bss = NULL; - } - + if (local_state_change && (!wdev->current_bss || + !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) return 0; - } return rdev->ops->deauth(&rdev->wiphy, dev, &req); } -- cgit v1.2.3 From 4045f72bcf3c293c7c5932ef001742d8bb5ded76 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Tue, 2 Oct 2012 21:34:23 +0200 Subject: mac80211: check if key has TKIP type before updating IV This patch fix corruption which can manifest itself by following crash when switching on rfkill switch with rt2x00 driver: https://bugzilla.redhat.com/attachment.cgi?id=615362 Pointer key->u.ccmp.tfm of group key get corrupted in: ieee80211_rx_h_michael_mic_verify(): /* update IV in key information to be able to detect replays */ rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32; rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16; because rt2x00 always set RX_FLAG_MMIC_STRIPPED, even if key is not TKIP. We already check type of the key in different path in ieee80211_rx_h_michael_mic_verify() function, so adding additional check here is reasonable. Cc: stable@vger.kernel.org # 3.0+ Signed-off-by: Stanislaw Gruszka Signed-off-by: John W. Linville --- net/mac80211/wpa.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index bdb53aba888e..e72562a18bad 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -106,7 +106,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) if (status->flag & RX_FLAG_MMIC_ERROR) goto mic_fail; - if (!(status->flag & RX_FLAG_IV_STRIPPED) && rx->key) + if (!(status->flag & RX_FLAG_IV_STRIPPED) && rx->key && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) goto update_iv; return RX_CONTINUE; -- cgit v1.2.3 From d4fa14cd62bd078c8e3ef39283b9f237e5b2ff0f Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 10 Oct 2012 22:40:23 +0200 Subject: mac80211: use ieee80211_free_txskb in a few more places Free tx status skbs when draining power save buffers, pending frames, or when tearing down a vif. Fixes remaining conditions that can lead to hostapd/wpa_supplicant hangs when running out of socket write memory. Signed-off-by: Felix Fietkau Cc: stable@vger.kernel.org Signed-off-by: John W. Linville --- net/mac80211/iface.c | 2 +- net/mac80211/sta_info.c | 4 ++-- net/mac80211/util.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 6f8a73c64fb3..7de7717ad67d 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -853,7 +853,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (info->control.vif == &sdata->vif) { __skb_unlink(skb, &local->pending[i]); - dev_kfree_skb_irq(skb); + ieee80211_free_txskb(&local->hw, skb); } } } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 797dd36a220d..0a4e4c04db89 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -650,7 +650,7 @@ static bool sta_info_cleanup_expire_buffered_ac(struct ieee80211_local *local, */ if (!skb) break; - dev_kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); } /* @@ -679,7 +679,7 @@ static bool sta_info_cleanup_expire_buffered_ac(struct ieee80211_local *local, local->total_ps_buffered--; ps_dbg(sta->sdata, "Buffered frame expired (STA %pM)\n", sta->sta.addr); - dev_kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); } /* diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 22ca35054dd0..94e586873979 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -406,7 +406,7 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, int queue = info->hw_queue; if (WARN_ON(!info->control.vif)) { - kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); return; } @@ -431,7 +431,7 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (WARN_ON(!info->control.vif)) { - kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); continue; } -- cgit v1.2.3 From 55462cf30ad9768fff6a6d36db21879146a39bdf Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 14 Oct 2012 04:30:56 +0000 Subject: vlan: fix bond/team enslave of vlan challenged slave/port In vlan_uses_dev() check for number of vlan devs rather than existence of vlan_info. The reason is that vlan id 0 is there without appropriate vlan dev on it by default which prevented from enslaving vlan challenged dev. Reported-by: Jon Stanley Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- net/8021q/vlan_core.c | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b721902bb6b4..b2530b002125 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1519,7 +1519,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); - if (bond_vlan_used(bond)) { + if (vlan_uses_dev(bond_dev)) { pr_err("%s: Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n", bond_dev->name, slave_dev->name, bond_dev->name); return -EPERM; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index fbbf1fa00940..65e06abe023f 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -366,6 +366,13 @@ EXPORT_SYMBOL(vlan_vids_del_by_dev); bool vlan_uses_dev(const struct net_device *dev) { - return rtnl_dereference(dev->vlan_info) ? true : false; + struct vlan_info *vlan_info; + + ASSERT_RTNL(); + + vlan_info = rtnl_dereference(dev->vlan_info); + if (!vlan_info) + return false; + return vlan_info->grp.nr_vlan_devs ? true : false; } EXPORT_SYMBOL(vlan_uses_dev); -- cgit v1.2.3 From f6e80abeab928b7c47cc1fbf53df13b4398a2bec Mon Sep 17 00:00:00 2001 From: Zijie Pan Date: Mon, 15 Oct 2012 03:56:39 +0000 Subject: sctp: fix call to SCTP_CMD_PROCESS_SACK in sctp_cmd_interpreter() Bug introduced by commit edfee0339e681a784ebacec7e8c2dc97dc6d2839 (sctp: check src addr when processing SACK to update transport state) Signed-off-by: Zijie Pan Signed-off-by: Nicolas Dichtel Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/sm_sideeffect.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 57f7de839b03..6773d7803627 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1642,8 +1642,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, asoc->outqueue.outstanding_bytes; sackh.num_gap_ack_blocks = 0; sackh.num_dup_tsns = 0; + chunk->subh.sack_hdr = &sackh; sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK, - SCTP_SACKH(&sackh)); + SCTP_CHUNK(chunk)); break; case SCTP_CMD_DISCARD_PACKET: -- cgit v1.2.3 From 9f0d3c2781baa1102108e16efbe640dd74564a7c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Oct 2012 07:37:27 +0000 Subject: ipv6: addrconf: fix /proc/net/if_inet6 Commit 1d5783030a1 (ipv6/addrconf: speedup /proc/net/if_inet6 filling) added bugs hiding some devices from if_inet6 and breaking applications. "ip -6 addr" could still display all IPv6 addresses, while "ifconfig -a" couldnt. One way to reproduce the bug is by starting in a shell : unshare -n /bin/bash ifconfig lo up And in original net namespace, lo device disappeared from if_inet6 Reported-by: Jan Hinnerk Stosch Tested-by: Jan Hinnerk Stosch Signed-off-by: Eric Dumazet Cc: Mihai Maruseac Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d7c56f8a5b4e..0424e4e27414 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3064,14 +3064,15 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) struct hlist_node *n; hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; /* sync with offset */ if (p < state->offset) { p++; continue; } state->offset++; - if (net_eq(dev_net(ifa->idev->dev), net)) - return ifa; + return ifa; } /* prepare for next bucket */ @@ -3089,18 +3090,20 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct hlist_node *n = &ifa->addr_lst; hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; state->offset++; - if (net_eq(dev_net(ifa->idev->dev), net)) - return ifa; + return ifa; } while (++state->bucket < IN6_ADDR_HSIZE) { state->offset = 0; hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; state->offset++; - if (net_eq(dev_net(ifa->idev->dev), net)) - return ifa; + return ifa; } } -- cgit v1.2.3 From 2ad5b9e4bd314fc685086b99e90e5de3bc59e26b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Oct 2012 22:33:29 +0000 Subject: netfilter: xt_TEE: don't use destination address found in header Torsten Luettgert bisected TEE regression starting with commit f8126f1d5136be1 (ipv4: Adjust semantics of rt->rt_gateway.) The problem is that it tries to ARP-lookup the original destination address of the forwarded packet, not the address of the gateway. Fix this using FLOWI_FLAG_KNOWN_NH Julian added in commit c92b96553a80c1 (ipv4: Add FLOWI_FLAG_KNOWN_NH), so that known nexthop (info->gw.ip) has preference on resolving. Reported-by: Torsten Luettgert Bisected-by: Torsten Luettgert Tested-by: Torsten Luettgert Cc: Julian Anastasov Signed-off-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_TEE.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index ee2e5bc5a8c7..bd93e51d30ac 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -70,6 +70,7 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl4.daddr = info->gw.ip; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return false; -- cgit v1.2.3 From 3a40414f826a8f1096d9b94c4a53ef91b25ba28d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 1 Oct 2012 15:52:00 +0200 Subject: mac80211: connect with HT20 if HT40 is not permitted Some changes to fix issues with HT40 APs in Korea and follow-up changes to allow using HT40 even if the local regulatory database disallows it caused issues with iwlwifi (and could cause issues with other devices); iwlwifi firmware would assert if you tried to connect to an AP that has an invalid configuration (e.g. using HT40- on channel 140.) Fix this, while avoiding the "Korean AP" issue by disabling HT40 and advertising HT20 to the AP when connecting. Cc: stable@vger.kernel.org [3.6] Reported-by: Florian Reitmeir Tested-by: Florian Reitmeir Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e510a33fec76..1b7eed252fe9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3099,22 +3099,32 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ht_cfreq, ht_oper->primary_chan, cbss->channel->band); ht_oper = NULL; + } else { + channel_type = NL80211_CHAN_HT20; } } - if (ht_oper) { - channel_type = NL80211_CHAN_HT20; + if (ht_oper && sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { + /* + * cfg80211 already verified that the channel itself can + * be used, but it didn't check that we can do the right + * HT type, so do that here as well. If HT40 isn't allowed + * on this channel, disable 40 MHz operation. + */ - if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { - switch (ht_oper->ht_param & - IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { - case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: + switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: + if (cbss->channel->flags & IEEE80211_CHAN_NO_HT40PLUS) + ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; + else channel_type = NL80211_CHAN_HT40PLUS; - break; - case IEEE80211_HT_PARAM_CHA_SEC_BELOW: + break; + case IEEE80211_HT_PARAM_CHA_SEC_BELOW: + if (cbss->channel->flags & IEEE80211_CHAN_NO_HT40MINUS) + ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; + else channel_type = NL80211_CHAN_HT40MINUS; - break; - } + break; } } -- cgit v1.2.3 From 212ba90696ab4884e2025b0b13726d67aadc2cd4 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Tue, 17 Jul 2012 00:01:26 +0200 Subject: SUNRPC: Prevent kernel stack corruption on long values of flush The buffer size in read_flush() is too small for the longest possible values for it. This can lead to a kernel stack corruption: [ 43.047329] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: ffffffff833e64b4 [ 43.047329] [ 43.049030] Pid: 6015, comm: trinity-child18 Tainted: G W 3.5.0-rc7-next-20120716-sasha #221 [ 43.050038] Call Trace: [ 43.050435] [] panic+0xcd/0x1f4 [ 43.050931] [] ? read_flush.isra.7+0xe4/0x100 [ 43.051602] [] __stack_chk_fail+0x16/0x20 [ 43.052206] [] read_flush.isra.7+0xe4/0x100 [ 43.052951] [] ? read_flush_pipefs+0x30/0x30 [ 43.053594] [] read_flush_procfs+0x2c/0x30 [ 43.053596] [] proc_reg_read+0x9c/0xd0 [ 43.053596] [] ? proc_reg_write+0xd0/0xd0 [ 43.053596] [] do_loop_readv_writev+0x4b/0x90 [ 43.053596] [] do_readv_writev+0xf6/0x1d0 [ 43.053596] [] vfs_readv+0x3e/0x60 [ 43.053596] [] sys_readv+0x48/0xb0 [ 43.053596] [] system_call_fastpath+0x1a/0x1f Signed-off-by: Sasha Levin Cc: stable@kernel.org Signed-off-by: J. Bruce Fields --- net/sunrpc/cache.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2a68bb3db772..fc2f7aa4dca7 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1409,11 +1409,11 @@ static ssize_t read_flush(struct file *file, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { - char tbuf[20]; + char tbuf[22]; unsigned long p = *ppos; size_t len; - sprintf(tbuf, "%lu\n", convert_to_wallclock(cd->flush_time)); + snprintf(tbuf, sizeof(tbuf), "%lu\n", convert_to_wallclock(cd->flush_time)); len = strlen(tbuf); if (p >= len) return 0; -- cgit v1.2.3 From c4a9fafc77a5318f5ed26c509bbcddf03e18c201 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 17 Oct 2012 13:56:19 +0200 Subject: cfg80211: fix antenna gain handling No driver initializes chan->max_antenna_gain to something sensible, and the only place where it is being used right now is inside ath9k. This leads to ath9k potentially using less tx power than it can use, which can decrease performance/range in some rare cases. Rather than going through every single driver, this patch initializes chan->orig_mag in wiphy_register(), ignoring whatever value the driver left in there. If a driver for some reason wishes to limit it independent from regulatory rulesets, it can do so internally. Signed-off-by: Felix Fietkau Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/wireless/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/wireless/core.c b/net/wireless/core.c index 443d4d7deea2..3f7253052088 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -526,8 +526,7 @@ int wiphy_register(struct wiphy *wiphy) for (i = 0; i < sband->n_channels; i++) { sband->channels[i].orig_flags = sband->channels[i].flags; - sband->channels[i].orig_mag = - sband->channels[i].max_antenna_gain; + sband->channels[i].orig_mag = INT_MAX; sband->channels[i].orig_mpwr = sband->channels[i].max_power; sband->channels[i].band = band; -- cgit v1.2.3 From 279f0f55249820d8129470c0e104084b252f26f3 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 17 Oct 2012 13:56:20 +0200 Subject: cfg80211: fix initialization of chan->max_reg_power A few places touch chan->max_power based on updated tx power rules, but forget to do the same to chan->max_reg_power. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/wireless/reg.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3b8cbbc214db..bcc7d7ee5a51 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -908,7 +908,7 @@ static void handle_channel(struct wiphy *wiphy, map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = chan->orig_mag = (int) MBI_TO_DBI(power_rule->max_antenna_gain); - chan->max_power = chan->orig_mpwr = + chan->max_reg_power = chan->max_power = chan->orig_mpwr = (int) MBM_TO_DBM(power_rule->max_eirp); return; } @@ -1331,7 +1331,8 @@ static void handle_channel_custom(struct wiphy *wiphy, chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = (int) MBI_TO_DBI(power_rule->max_antenna_gain); - chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); + chan->max_reg_power = chan->max_power = + (int) MBM_TO_DBM(power_rule->max_eirp); } static void handle_band_custom(struct wiphy *wiphy, enum ieee80211_band band, -- cgit v1.2.3 From 7f112af40fecf5399b61e69ffc6b55a9d82789f7 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Wed, 17 Oct 2012 14:53:04 +0200 Subject: batman-adv: Fix broadcast packet CRC calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far the crc16 checksum for a batman-adv broadcast data packet, received on a batman-adv hard interface, was calculated over zero bytes of its content leading to many incoming broadcast data packets wrongly being dropped (60-80% packet loss). This patch fixes this issue by calculating the crc16 over the actual, complete broadcast payload. The issue is a regression introduced by ("batman-adv: add broadcast duplicate check"). Signed-off-by: Linus Lüssing Acked-by: Simon Wunderlich Signed-off-by: Marek Lindner --- net/batman-adv/bridge_loop_avoidance.c | 8 ++++---- net/batman-adv/routing.c | 8 +++++++- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 0a9084ad19a6..eebab20c7478 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1210,8 +1210,8 @@ int batadv_bla_init(struct batadv_priv *bat_priv) /** * batadv_bla_check_bcast_duplist * @bat_priv: the bat priv with all the soft interface information - * @bcast_packet: originator mac address - * @hdr_size: maximum length of the frame + * @bcast_packet: encapsulated broadcast frame plus batman header + * @bcast_packet_len: length of encapsulated broadcast frame plus batman header * * check if it is on our broadcast list. Another gateway might * have sent the same packet because it is connected to the same backbone, @@ -1224,14 +1224,14 @@ int batadv_bla_init(struct batadv_priv *bat_priv) */ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct batadv_bcast_packet *bcast_packet, - int hdr_size) + int bcast_packet_len) { int i, length, curr; uint8_t *content; uint16_t crc; struct batadv_bcast_duplist_entry *entry; - length = hdr_size - sizeof(*bcast_packet); + length = bcast_packet_len - sizeof(*bcast_packet); content = (uint8_t *)bcast_packet; content += sizeof(*bcast_packet); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 939fc01371df..376b4cc6ca82 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1124,8 +1124,14 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, spin_unlock_bh(&orig_node->bcast_seqno_lock); + /* keep skb linear for crc calculation */ + if (skb_linearize(skb) < 0) + goto out; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + /* check whether this has been sent by another originator before */ - if (batadv_bla_check_bcast_duplist(bat_priv, bcast_packet, hdr_size)) + if (batadv_bla_check_bcast_duplist(bat_priv, bcast_packet, skb->len)) goto out; /* rebroadcast packet */ -- cgit v1.2.3 From 7dac7b76b8db87fc79857a53a09730fb2148579b Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Wed, 17 Oct 2012 14:53:05 +0200 Subject: batman-adv: Fix potential broadcast BLA-duplicate-check race condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Threads in the bottom half of batadv_bla_check_bcast_duplist() might otherwise for instance overwrite variables which other threads might be using/reading at the same time in the top half, potentially leading to messing up the bcast_duplist, possibly resulting in false bridge loop avoidance duplicate check decisions. Signed-off-by: Linus Lüssing Acked-by: Simon Wunderlich Signed-off-by: Marek Lindner --- net/batman-adv/bridge_loop_avoidance.c | 19 ++++++++++++++----- net/batman-adv/types.h | 2 ++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index eebab20c7478..fd8d5afec0dd 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1167,6 +1167,8 @@ int batadv_bla_init(struct batadv_priv *bat_priv) uint16_t crc; unsigned long entrytime; + spin_lock_init(&bat_priv->bla.bcast_duplist_lock); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hash registering\n"); /* setting claim destination address */ @@ -1226,7 +1228,7 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct batadv_bcast_packet *bcast_packet, int bcast_packet_len) { - int i, length, curr; + int i, length, curr, ret = 0; uint8_t *content; uint16_t crc; struct batadv_bcast_duplist_entry *entry; @@ -1238,6 +1240,8 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, /* calculate the crc ... */ crc = crc16(0, content, length); + spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); + for (i = 0; i < BATADV_DUPLIST_SIZE; i++) { curr = (bat_priv->bla.bcast_duplist_curr + i); curr %= BATADV_DUPLIST_SIZE; @@ -1259,9 +1263,12 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, /* this entry seems to match: same crc, not too old, * and from another gw. therefore return 1 to forbid it. */ - return 1; + ret = 1; + goto out; } - /* not found, add a new entry (overwrite the oldest entry) */ + /* not found, add a new entry (overwrite the oldest entry) + * and allow it, its the first occurence. + */ curr = (bat_priv->bla.bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1); curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bla.bcast_duplist[curr]; @@ -1270,8 +1277,10 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, memcpy(entry->orig, bcast_packet->orig, ETH_ALEN); bat_priv->bla.bcast_duplist_curr = curr; - /* allow it, its the first occurence. */ - return 0; +out: + spin_unlock_bh(&bat_priv->bla.bcast_duplist_lock); + + return ret; } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 2ed82caacdca..ac1e07a80454 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -205,6 +205,8 @@ struct batadv_priv_bla { struct batadv_hashtable *backbone_hash; struct batadv_bcast_duplist_entry bcast_duplist[BATADV_DUPLIST_SIZE]; int bcast_duplist_curr; + /* protects bcast_duplist and bcast_duplist_curr */ + spinlock_t bcast_duplist_lock; struct batadv_bla_claim_dst claim_dest; struct delayed_work work; }; -- cgit v1.2.3 From 18c22a03a2187bcbda7d3a7fa1061584a6348e7b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 Oct 2012 01:37:36 +0000 Subject: vlan: allow to change type when no vlan device is hooked on netdev vlan_info might be present but still no vlan devices might be there. That is in case of vlan0 automatically added. So in that case, allow to change netdev type. Reported-by: Jon Stanley Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/8021q/vlan.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9096bcb08132..ee070722a3a3 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -463,7 +463,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ - return NOTIFY_BAD; + if (vlan_uses_dev(dev)) + return NOTIFY_BAD; + break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: -- cgit v1.2.3 From 13d82bf50dce632355fcccafa4fe44a9b5e706d8 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 17 Oct 2012 21:17:44 +0000 Subject: ipv4: Fix flushing of cached routing informations Currently we can not flush cached pmtu/redirect informations via the ipv4_sysctl_rtcache_flush sysctl. We need to check the rt_genid of the old route and reset the nh exeption if the old route is expired when we bind a new route to a nh exeption. Signed-off-by: Steffen Klassert Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/route.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 432f4bb77238..a8c651216fa6 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1163,8 +1163,12 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { - struct rtable *orig; - + struct rtable *orig = rcu_dereference(fnhe->fnhe_rth); + if (orig && rt_is_expired(orig)) { + fnhe->fnhe_gw = 0; + fnhe->fnhe_pmtu = 0; + fnhe->fnhe_expires = 0; + } if (fnhe->fnhe_pmtu) { unsigned long expires = fnhe->fnhe_expires; unsigned long diff = expires - jiffies; @@ -1181,7 +1185,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, } else if (!rt->rt_gateway) rt->rt_gateway = daddr; - orig = rcu_dereference(fnhe->fnhe_rth); rcu_assign_pointer(fnhe->fnhe_rth, rt); if (orig) rt_free(orig); -- cgit v1.2.3 From 6d772ac5578f711d1ce7b03535d1c95bffb21dff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Oct 2012 03:21:55 +0000 Subject: netlink: use kfree_rcu() in netlink_release() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On some suspend/resume operations involving wimax device, we have noticed some intermittent memory corruptions in netlink code. Stéphane Marchesin tracked this corruption in netlink_update_listeners() and suggested a patch. It appears netlink_release() should use kfree_rcu() instead of kfree() for the listeners structure as it may be used by other cpus using RCU protection. netlink_release() must set to NULL the listeners pointer when it is about to be freed. Also have to protect netlink_update_listeners() and netlink_has_listeners() if listeners is NULL. Add a nl_deref_protected() lockdep helper to properly document which locks protects us. Reported-by: Jonathan Kliegman Signed-off-by: Eric Dumazet Cc: Stéphane Marchesin Cc: Sam Leffler Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 01e944a017a4..4da797fa5ec5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -138,6 +138,8 @@ static int netlink_dump(struct sock *sk); static DEFINE_RWLOCK(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); +#define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); + static ATOMIC_NOTIFIER_HEAD(netlink_chain); static inline u32 netlink_group_mask(u32 group) @@ -345,6 +347,11 @@ netlink_update_listeners(struct sock *sk) struct hlist_node *node; unsigned long mask; unsigned int i; + struct listeners *listeners; + + listeners = nl_deref_protected(tbl->listeners); + if (!listeners) + return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; @@ -352,7 +359,7 @@ netlink_update_listeners(struct sock *sk) if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } - tbl->listeners->masks[i] = mask; + listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ @@ -536,7 +543,11 @@ static int netlink_release(struct socket *sock) if (netlink_is_kernel(sk)) { BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { - kfree(nl_table[sk->sk_protocol].listeners); + struct listeners *old; + + old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); + RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); + kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].flags = 0; @@ -982,7 +993,7 @@ int netlink_has_listeners(struct sock *sk, unsigned int group) rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); - if (group - 1 < nl_table[sk->sk_protocol].groups) + if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); @@ -1625,7 +1636,7 @@ int __netlink_change_ngroups(struct sock *sk, unsigned int groups) new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; - old = rcu_dereference_protected(tbl->listeners, 1); + old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); -- cgit v1.2.3 From a3374c42aa5f7237e87ff3b0622018636b0c847e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Oct 2012 09:14:12 +0000 Subject: tcp: fix FIONREAD/SIOCINQ tcp_ioctl() tries to take into account if tcp socket received a FIN to report correct number bytes in receive queue. But its flaky because if the application ate the last skb, we return 1 instead of 0. Correct way to detect that FIN was received is to test SOCK_DONE. Reported-by: Elliot Hughes Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f32c02e2a543..b7c2f439b54f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -549,14 +549,12 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { - struct sk_buff *skb; answ = tp->rcv_nxt - tp->copied_seq; - /* Subtract 1, if FIN is in queue. */ - skb = skb_peek_tail(&sk->sk_receive_queue); - if (answ && skb) - answ -= tcp_hdr(skb)->fin; + /* Subtract 1, if FIN was received */ + if (answ && sock_flag(sk, SOCK_DONE)) + answ--; } else answ = tp->urg_seq - tp->copied_seq; release_sock(sk); -- cgit v1.2.3 From bbb5823cf742a7e955f35c7d891e4e936944c33a Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 9 Oct 2012 13:00:47 +0000 Subject: netfilter: nf_conntrack: fix rt_gateway checks for H.323 helper After the change "Adjust semantics of rt->rt_gateway" (commit f8126f1d51) we should properly match the nexthop when destinations are directly connected because rt_gateway can be 0. The rt_gateway checks in H.323 helper try to avoid the creation of an unnecessary expectation in this call-forwarding case: http://people.netfilter.org/zhaojingmin/h323_conntrack_nat_helper/#_Toc133598073 However, the existing code fails to avoid that in many cases, see this thread: http://marc.info/?l=linux-netdev&m=135043175028620&w=2 It seems it is not trivial to know from the kernel if two hosts have to go through the firewall to communicate each other, which is the main point of the call-forwarding filter code to avoid creating unnecessary expectations. So this patch just gets things the way they were as before commit f8126f1d51. Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_h323_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 1b30b0dee708..962795e839ab 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -753,7 +753,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi4_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi4_to_flowi(&fl2), false)) { - if (rt1->rt_gateway == rt2->rt_gateway && + if (rt_nexthop(rt1, fl1.daddr) == + rt_nexthop(rt2, fl2.daddr) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); -- cgit v1.2.3 From 6f73601efb35c7003f5c58c2bc6fd08f3652169c Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 19 Oct 2012 15:14:44 +0000 Subject: tcp: add SYN/data info to TCP_INFO Add a bit TCPI_OPT_SYN_DATA (32) to the socket option TCP_INFO:tcpi_options. It's set if the data in SYN (sent or received) is acked by SYN-ACK. Server or client application can use this information to check Fast Open success rate. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_input.c | 1 + net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_minisocks.c | 1 + 6 files changed, 8 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8a7fc4be2d75..60b7aac15e0e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -191,7 +191,8 @@ struct tcp_sock { u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ early_retrans_delayed:1, /* Delayed ER timer installed */ syn_data:1, /* SYN includes data */ - syn_fastopen:1; /* SYN includes Fast Open option */ + syn_fastopen:1, /* SYN includes Fast Open option */ + syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ /* RTT measurement */ u32 srtt; /* smoothed round trip time << 3 */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c4b89a5cb7df..e962faa5ab0d 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -130,6 +130,7 @@ enum { #define TCPI_OPT_WSCALE 4 #define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ #define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ +#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ enum tcp_ca_state { TCP_CA_Open = 0, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b7c2f439b54f..197c0008503c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2764,6 +2764,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; + if (tp->syn_data_acked) + info->tcpi_options |= TCPI_OPT_SYN_DATA; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 432c36649db3..036f85738141 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5646,6 +5646,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_rearm_rto(sk); return true; } + tp->syn_data_acked = tp->syn_data; return false; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ef998b008a57..0c4a64355603 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1461,6 +1461,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, skb_set_owner_r(skb, child); __skb_queue_tail(&child->sk_receive_queue, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tp->syn_data_acked = 1; } sk->sk_data_ready(sk, 0); bh_unlock_sock(child); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 27536ba16c9d..a7302d974f32 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -510,6 +510,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->rx_opt.mss_clamp = req->mss; TCP_ECN_openreq_child(newtp, req); newtp->fastopen_rsk = NULL; + newtp->syn_data_acked = 0; TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS); } -- cgit v1.2.3 From 3d861f661006606bf159fd6bd973e83dbf21d0f9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Oct 2012 09:03:40 +0000 Subject: net: fix secpath kmemleak Mike Kazantsev found 3.5 kernels and beyond were leaking memory, and tracked the faulty commit to a1c7fff7e18f59e ("net: netdev_alloc_skb() use build_skb()") While this commit seems fine, it uncovered a bug introduced in commit bad43ca8325 ("net: introduce skb_try_coalesce()), in function kfree_skb_partial()"): If head is stolen, we free the sk_buff, without removing references on secpath (skb->sp). So IPsec + IP defrag/reassembly (using skb coalescing), or TCP coalescing could leak secpath objects. Fix this bug by calling skb_release_head_state(skb) to properly release all possible references to linked objects. Reported-by: Mike Kazantsev Signed-off-by: Eric Dumazet Bisected-by: Mike Kazantsev Tested-by: Mike Kazantsev Signed-off-by: David S. Miller --- net/core/skbuff.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6e04b1fa11f2..4007c1437fda 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3379,10 +3379,12 @@ EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { - if (head_stolen) + if (head_stolen) { + skb_release_head_state(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } } EXPORT_SYMBOL(kfree_skb_partial); -- cgit v1.2.3 From 37561f68bd527ec39076e32effdc7b1dcdfb17ea Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Mon, 22 Oct 2012 11:26:36 +0000 Subject: tcp: Reject invalid ack_seq to Fast Open sockets A packet with an invalid ack_seq may cause a TCP Fast Open socket to switch to the unexpected TCP_CLOSING state, triggering a BUG_ON kernel panic. When a FIN packet with an invalid ack_seq# arrives at a socket in the TCP_FIN_WAIT1 state, rather than discarding the packet, the current code will accept the FIN, causing state transition to TCP_CLOSING. This may be a small deviation from RFC793, which seems to say that the packet should be dropped. Unfortunately I did not expect this case for Fast Open hence it will trigger a BUG_ON panic. It turns out there is really nothing bad about a TFO socket going into TCP_CLOSING state so I could just remove the BUG_ON statements. But after some thought I think it's better to treat this case like TCP_SYN_RECV and return a RST to the confused peer who caused the unacceptable ack_seq to be generated in the first place. Signed-off-by: H.K. Jerry Chu Cc: Neal Cardwell Cc: Yuchung Cheng Acked-by: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 12 ++++++++++-- net/ipv4/tcp_timer.c | 4 ++-- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 036f85738141..1db663983587 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5964,7 +5964,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, req = tp->fastopen_rsk; if (req != NULL) { - BUG_ON(sk->sk_state != TCP_SYN_RECV && + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); if (tcp_check_req(sk, skb, req, NULL, true) == NULL) @@ -6053,7 +6053,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * ACK we have received, this would have acknowledged * our SYNACK so stop the SYNACK timer. */ - if (acceptable && req != NULL) { + if (req != NULL) { + /* Return RST if ack_seq is invalid. + * Note that RFC793 only says to generate a + * DUPACK for it but for TCP Fast Open it seems + * better to treat this case like TCP_SYN_RECV + * above. + */ + if (!acceptable) + return 1; /* We no longer need the request sock. */ reqsk_fastopen_remove(sk, req, false); tcp_rearm_rto(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index fc04711e80c8..d47c1b4421a3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -347,8 +347,8 @@ void tcp_retransmit_timer(struct sock *sk) return; } if (tp->fastopen_rsk) { - BUG_ON(sk->sk_state != TCP_SYN_RECV && - sk->sk_state != TCP_FIN_WAIT1); + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); tcp_fastopen_synack_timer(sk); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). -- cgit v1.2.3 From d0bea455dd48da1ecbd04fedf00eb89437455fdc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 23 Oct 2012 11:35:47 -0400 Subject: SUNRPC: Clear the connect flag when socket state is TCP_CLOSE_WAIT This is needed to ensure that we call xprt_connect() upon the next call to call_connect(). Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org Tested-by: Chris Perl --- net/sunrpc/xprtsock.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index aaaadfbe36e9..6e6967d5400e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1516,6 +1516,7 @@ static void xs_tcp_state_change(struct sock *sk) case TCP_CLOSE_WAIT: /* The server initiated a shutdown of the socket */ xprt->connect_cookie++; + clear_bit(XPRT_CONNECTED, &xprt->state); xs_tcp_force_close(xprt); case TCP_CLOSING: /* -- cgit v1.2.3 From b9d2bb2ee537424a7f855e1f93eed44eb9ee0854 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 23 Oct 2012 11:40:02 -0400 Subject: Revert "SUNRPC: Ensure we close the socket on EPIPE errors too..." This reverts commit 55420c24a0d4d1fce70ca713f84aa00b6b74a70e. Now that we clear the connected flag when entering TCP_CLOSE_WAIT, the deadlock described in this commit is no longer possible. Instead, the resulting call to xs_tcp_shutdown() can interfere with pending reconnection attempts. Reported-by: Chris Perl Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org Tested-by: Chris Perl --- net/sunrpc/xprtsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 6e6967d5400e..7e2dd0d69f1b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -737,10 +737,10 @@ static int xs_tcp_send_request(struct rpc_task *task) dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); case -ECONNRESET: - case -EPIPE: xs_tcp_shutdown(xprt); case -ECONNREFUSED: case -ENOTCONN: + case -EPIPE: clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); } -- cgit v1.2.3 From 4bc1e68ed6a8b59be8a79eb719be515a55c7bc68 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 23 Oct 2012 17:50:07 -0400 Subject: SUNRPC: Prevent races in xs_abort_connection() The call to xprt_disconnect_done() that is triggered by a successful connection reset will trigger another automatic wakeup of all tasks on the xprt->pending rpc_wait_queue. In particular it will cause an early wake up of the task that called xprt_connect(). All we really want to do here is clear all the socket-specific state flags, so we split that functionality out of xs_sock_mark_closed() into a helper that can be called by xs_abort_connection() Reported-by: Chris Perl Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org Tested-by: Chris Perl --- net/sunrpc/xprtsock.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 7e2dd0d69f1b..1f105c2d2e15 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1453,7 +1453,7 @@ static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt) xprt_clear_connecting(xprt); } -static void xs_sock_mark_closed(struct rpc_xprt *xprt) +static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { smp_mb__before_clear_bit(); clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); @@ -1461,6 +1461,11 @@ static void xs_sock_mark_closed(struct rpc_xprt *xprt) clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); smp_mb__after_clear_bit(); +} + +static void xs_sock_mark_closed(struct rpc_xprt *xprt) +{ + xs_sock_reset_connection_flags(xprt); /* Mark transport as closed and wake up all pending tasks */ xprt_disconnect_done(xprt); } @@ -2051,10 +2056,8 @@ static void xs_abort_connection(struct sock_xprt *transport) any.sa_family = AF_UNSPEC; result = kernel_connect(transport->sock, &any, sizeof(any), 0); if (!result) - xs_sock_mark_closed(&transport->xprt); - else - dprintk("RPC: AF_UNSPEC connect return code %d\n", - result); + xs_sock_reset_connection_flags(&transport->xprt); + dprintk("RPC: AF_UNSPEC connect return code %d\n", result); } static void xs_tcp_reuse_connection(struct sock_xprt *transport) -- cgit v1.2.3 From f878b657ce8e7d3673afe48110ec208a29e38c4a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 22 Oct 2012 17:14:36 -0400 Subject: SUNRPC: Get rid of the xs_error_report socket callback Chris Perl reports that we're seeing races between the wakeup call in xs_error_report and the connect attempts. Basically, Chris has shown that in certain circumstances, the call to xs_error_report causes the rpc_task that is responsible for reconnecting to wake up early, thus triggering a disconnect and retry. Since the sk->sk_error_report() calls in the socket layer are always followed by a tcp_done() in the cases where we care about waking up the rpc_tasks, just let the state_change callbacks take responsibility for those wake ups. Reported-by: Chris Perl Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org Tested-by: Chris Perl --- net/sunrpc/xprtsock.c | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 1f105c2d2e15..75853cabf4c9 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -254,7 +254,6 @@ struct sock_xprt { void (*old_data_ready)(struct sock *, int); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); - void (*old_error_report)(struct sock *); }; /* @@ -781,7 +780,6 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk) transport->old_data_ready = sk->sk_data_ready; transport->old_state_change = sk->sk_state_change; transport->old_write_space = sk->sk_write_space; - transport->old_error_report = sk->sk_error_report; } static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk) @@ -789,7 +787,6 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_data_ready = transport->old_data_ready; sk->sk_state_change = transport->old_state_change; sk->sk_write_space = transport->old_write_space; - sk->sk_error_report = transport->old_error_report; } static void xs_reset_transport(struct sock_xprt *transport) @@ -1546,25 +1543,6 @@ static void xs_tcp_state_change(struct sock *sk) read_unlock_bh(&sk->sk_callback_lock); } -/** - * xs_error_report - callback mainly for catching socket errors - * @sk: socket - */ -static void xs_error_report(struct sock *sk) -{ - struct rpc_xprt *xprt; - - read_lock_bh(&sk->sk_callback_lock); - if (!(xprt = xprt_from_sock(sk))) - goto out; - dprintk("RPC: %s client %p...\n" - "RPC: error %d\n", - __func__, xprt, sk->sk_err); - xprt_wake_pending_tasks(xprt, -EAGAIN); -out: - read_unlock_bh(&sk->sk_callback_lock); -} - static void xs_write_space(struct sock *sk) { struct socket *sock; @@ -1864,7 +1842,6 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_local_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; xprt_clear_connected(xprt); @@ -1989,7 +1966,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_error_report = xs_error_report; sk->sk_no_check = UDP_CSUM_NORCV; sk->sk_allocation = GFP_ATOMIC; @@ -2102,7 +2078,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; - sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */ -- cgit v1.2.3 From 9690fb169b433a66485c808e4fc352b8a0f8d866 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 24 Oct 2012 14:19:53 +0200 Subject: mac80211: use blacklist for duplicate IE check Instead of the current whitelist which accepts duplicates only for the quiet and vendor IEs, use a blacklist of all IEs (that we currently parse) that can't be duplicated. This avoids detecting a beacon as corrupt in the future when new IEs are added that can be duplicated. Cc: stable@vger.kernel.org Signed-off-by: Paul Stewart Signed-off-by: Johannes Berg --- net/mac80211/util.c | 42 +++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 22ca35054dd0..e6e4bda0528e 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -643,13 +643,41 @@ u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, break; } - if (id != WLAN_EID_VENDOR_SPECIFIC && - id != WLAN_EID_QUIET && - test_bit(id, seen_elems)) { - elems->parse_error = true; - left -= elen; - pos += elen; - continue; + switch (id) { + case WLAN_EID_SSID: + case WLAN_EID_SUPP_RATES: + case WLAN_EID_FH_PARAMS: + case WLAN_EID_DS_PARAMS: + case WLAN_EID_CF_PARAMS: + case WLAN_EID_TIM: + case WLAN_EID_IBSS_PARAMS: + case WLAN_EID_CHALLENGE: + case WLAN_EID_RSN: + case WLAN_EID_ERP_INFO: + case WLAN_EID_EXT_SUPP_RATES: + case WLAN_EID_HT_CAPABILITY: + case WLAN_EID_HT_OPERATION: + case WLAN_EID_VHT_CAPABILITY: + case WLAN_EID_VHT_OPERATION: + case WLAN_EID_MESH_ID: + case WLAN_EID_MESH_CONFIG: + case WLAN_EID_PEER_MGMT: + case WLAN_EID_PREQ: + case WLAN_EID_PREP: + case WLAN_EID_PERR: + case WLAN_EID_RANN: + case WLAN_EID_CHANNEL_SWITCH: + case WLAN_EID_EXT_CHANSWITCH_ANN: + case WLAN_EID_COUNTRY: + case WLAN_EID_PWR_CONSTRAINT: + case WLAN_EID_TIMEOUT_INTERVAL: + if (test_bit(id, seen_elems)) { + elems->parse_error = true; + left -= elen; + pos += elen; + continue; + } + break; } if (calc_crc && id < 64 && (filter & (1ULL << id))) -- cgit v1.2.3 From 9bd952615a42d7e2ce3fa2c632e808e804637a1a Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 24 Oct 2012 16:12:58 -0700 Subject: libceph: avoid NULL kref_put when osd reset races with alloc_msg The ceph_on_in_msg_alloc() method drops con->mutex while it allocates a message. If that races with a timeout that resends a zillion messages and resets the connection, and the ->alloc_msg() method returns a NULL message, it will call ceph_msg_put(NULL) and BUG. Fix by only calling put if msg is non-NULL. Fixes http://tracker.newdream.net/issues/3142 Signed-off-by: Sage Weil --- net/ceph/messenger.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index cad0d17ec45e..3ef1759403b4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2750,7 +2750,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) msg = con->ops->alloc_msg(con, hdr, skip); mutex_lock(&con->mutex); if (con->state != CON_STATE_OPEN) { - ceph_msg_put(msg); + if (msg) + ceph_msg_put(msg); return -EAGAIN; } con->in_msg = msg; -- cgit v1.2.3 From 14edd87dc67311556f1254a8f29cf4dd6cb5b7d1 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Wed, 24 Oct 2012 14:01:18 +0800 Subject: ipv6: Set default hoplimit as zero. Commit a02e4b7dae4551(Demark default hoplimit as zero) only changes the hoplimit checking condition and default value in ip6_dst_hoplimit, not zeros all hoplimit default value. Keep the zeroing ip6_template_metrics[RTAX_HOPLIMIT - 1] to force it as const, cause as a37e6e344910(net: force dst_default_metrics to const section) Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- net/ipv6/route.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7c7e963260e1..b1e6cf0b95fd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -219,7 +219,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { }; static const u32 ip6_template_metrics[RTAX_MAX] = { - [RTAX_HOPLIMIT - 1] = 255, + [RTAX_HOPLIMIT - 1] = 0, }; static const struct rt6_info ip6_null_entry_template = { @@ -1232,7 +1232,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; -- cgit v1.2.3 From 555cb715be8ef98b8ec362b23dfc254d432a35b1 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Wed, 24 Oct 2012 12:43:30 -0700 Subject: mac80211: Only process mesh config header on frames that RA_MATCH Doing otherwise is wrong, and may wreak havoc on the mpp tables, specially if the frame is encrypted. Cc: stable@vger.kernel.org Reported-by: Chaoxing Lin Signed-off-by: Javier Cardona Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 61c621e9273f..1222127de9be 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1897,7 +1897,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) mesh_rmc_check(hdr->addr3, mesh_hdr, rx->sdata)) return RX_DROP_MONITOR; - if (!ieee80211_is_data(hdr->frame_control)) + if (!ieee80211_is_data(hdr->frame_control) || + !(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_CONTINUE; if (!mesh_hdr->ttl) @@ -1941,9 +1942,6 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) } skb_set_queue_mapping(skb, q); - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - goto out; - if (!--mesh_hdr->ttl) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); return RX_DROP_MONITOR; -- cgit v1.2.3 From 2ac64cd17f9af6d6adaa921bd9846a3c9bb9235c Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Wed, 24 Oct 2012 12:43:31 -0700 Subject: mac80211: Don't drop frames received with mesh ttl == 1 Prior this fix, those frames were not received, nor forwarded. Fix this to receive and not forward. Signed-off-by: Javier Cardona Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1222127de9be..f73e0dda0d86 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1944,7 +1944,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!--mesh_hdr->ttl) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); - return RX_DROP_MONITOR; + goto out; } if (!ifmsh->mshcfg.dot11MeshForwarding) -- cgit v1.2.3 From f7fbf70ee9db6da6033ae50d100e017ac1f26555 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 25 Oct 2012 11:10:18 -0700 Subject: mac80211: don't inspect Sequence Control field on control frames Per IEEE Std. 802.11-2012, Sec 8.2.4.4.1, the sequence Control field is not present in control frames. We noticed this problem when processing Block Ack Requests. Cc: stable@vger.kernel.org Signed-off-by: Javier Cardona Signed-off-by: Javier Lopez Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index f73e0dda0d86..c6865f2f47f8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1462,6 +1462,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; + + if (ieee80211_is_ctl(fc)) + return RX_CONTINUE; + sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; -- cgit v1.2.3 From badecb001a310408d3473b1fc2ed5aefd0bc92a9 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Fri, 26 Oct 2012 18:54:25 +0200 Subject: mac80211: fix SSID copy on IBSS JOIN The 'ssid' field of the cfg80211_ibss_params is a u8 pointer and its length is likely to be less than IEEE80211_MAX_SSID_LEN most of the time. This patch fixes the ssid copy in ieee80211_ibss_join() by using the SSID length to prevent it from reading beyond the string. Cc: stable@vger.kernel.org Signed-off-by: Antonio Quartulli [rewrapped commit message, small rewording] Signed-off-by: Johannes Berg --- net/mac80211/ibss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 5f3620f0bc0a..bf87c70ac6c5 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1108,7 +1108,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH; sdata->u.ibss.ibss_join_req = jiffies; - memcpy(sdata->u.ibss.ssid, params->ssid, IEEE80211_MAX_SSID_LEN); + memcpy(sdata->u.ibss.ssid, params->ssid, params->ssid_len); sdata->u.ibss.ssid_len = params->ssid_len; mutex_unlock(&sdata->u.ibss.mtx); -- cgit v1.2.3 From 7dd111e8ee10cc6816669eabcad3334447673236 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 25 Oct 2012 21:51:59 +0200 Subject: wireless: drop invalid mesh address extension frames The mesh header can have address extension by a 4th or a 5th and 6th address, but never both. Drop such frames in 802.11 -> 802.3 conversion along with any frames that have the wrong extension. Cc: stable@vger.kernel.org Reviewed-by: Javier Cardona Signed-off-by: Johannes Berg --- net/wireless/util.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/wireless/util.c b/net/wireless/util.c index ef35f4ef2aa6..45a09de1ffe3 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -312,18 +312,15 @@ EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); static int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) { int ae = meshhdr->flags & MESH_FLAGS_AE; - /* 7.1.3.5a.2 */ + /* 802.11-2012, 8.2.4.7.3 */ switch (ae) { + default: case 0: return 6; case MESH_FLAGS_AE_A4: return 12; case MESH_FLAGS_AE_A5_A6: return 18; - case (MESH_FLAGS_AE_A4 | MESH_FLAGS_AE_A5_A6): - return 24; - default: - return 6; } } @@ -373,6 +370,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, /* make sure meshdr->flags is on the linear part */ if (!pskb_may_pull(skb, hdrlen + 1)) return -1; + if (meshdr->flags & MESH_FLAGS_AE_A4) + return -1; if (meshdr->flags & MESH_FLAGS_AE_A5_A6) { skb_copy_bits(skb, hdrlen + offsetof(struct ieee80211s_hdr, eaddr1), @@ -397,6 +396,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, /* make sure meshdr->flags is on the linear part */ if (!pskb_may_pull(skb, hdrlen + 1)) return -1; + if (meshdr->flags & MESH_FLAGS_AE_A5_A6) + return -1; if (meshdr->flags & MESH_FLAGS_AE_A4) skb_copy_bits(skb, hdrlen + offsetof(struct ieee80211s_hdr, eaddr1), -- cgit v1.2.3 From 4a4f1a5808c8bb0b72a4f6e5904c53fb8c9cd966 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Oct 2012 00:33:36 +0200 Subject: mac80211: check management frame header length Due to pskb_may_pull() checking the skb length, all non-management frames are checked on input whether their 802.11 header is fully present. Also add that check for management frames and remove a check that is now duplicate. This prevents accessing skb data beyond the frame end. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index c6865f2f47f8..99cdee16e31b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1470,7 +1470,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) frag = sc & IEEE80211_SCTL_FRAG; if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - (rx->skb)->len < 24 || is_multicast_ether_addr(hdr->addr1))) { /* not fragmented */ goto out; @@ -2915,10 +2914,15 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) local->dot11ReceivedFragmentCount++; - if (ieee80211_is_mgmt(fc)) - err = skb_linearize(skb); - else + if (ieee80211_is_mgmt(fc)) { + /* drop frame if too short for header */ + if (skb->len < ieee80211_hdrlen(fc)) + err = -ENOBUFS; + else + err = skb_linearize(skb); + } else { err = !pskb_may_pull(skb, ieee80211_hdrlen(fc)); + } if (err) { dev_kfree_skb(skb); -- cgit v1.2.3 From 9b395bc3be1cebf0144a127c7e67d56dbdac0930 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Oct 2012 00:36:40 +0200 Subject: mac80211: verify that skb data is present A number of places in the mesh code don't check that the frame data is present and in the skb header when trying to access. Add those checks and the necessary pskb_may_pull() calls. This prevents accessing data that doesn't actually exist. To do this, export ieee80211_get_mesh_hdrlen() to be able to use it in mac80211. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 9 +++++++++ net/mac80211/rx.c | 32 +++++++++++++++++++++++++++++++- net/wireless/util.c | 3 ++- 3 files changed, 42 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f8cd4cf3fad8..7d5b6000378b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2651,6 +2651,15 @@ unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb); */ unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc); +/** + * ieee80211_get_mesh_hdrlen - get mesh extension header length + * @meshhdr: the mesh extension header, only the flags field + * (first byte) will be accessed + * Returns the length of the extension header, which is always at + * least 6 bytes and at most 18 if address 5 and 6 are present. + */ +unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); + /** * DOC: Data path helpers * diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 99cdee16e31b..265a032dec49 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -531,6 +531,11 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) if (ieee80211_is_action(hdr->frame_control)) { u8 category; + + /* make sure category field is present */ + if (rx->skb->len < IEEE80211_MIN_ACTION_SIZE) + return RX_DROP_MONITOR; + mgmt = (struct ieee80211_mgmt *)hdr; category = mgmt->u.action.category; if (category != WLAN_CATEGORY_MESH_ACTION && @@ -1892,6 +1897,20 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdrlen + 6)) + return RX_DROP_MONITOR; + + mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + + /* make sure full mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, + hdrlen + ieee80211_get_mesh_hdrlen(mesh_hdr))) + return RX_DROP_MONITOR; + + /* reload pointers */ + hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); /* frame is in RMC, don't forward */ @@ -1915,9 +1934,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (is_multicast_ether_addr(hdr->addr1)) { mpp_addr = hdr->addr3; proxied_addr = mesh_hdr->eaddr1; - } else { + } else if (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6) { + /* has_a4 already checked in ieee80211_rx_mesh_check */ mpp_addr = hdr->addr4; proxied_addr = mesh_hdr->eaddr2; + } else { + return RX_DROP_MONITOR; } rcu_read_lock(); @@ -2354,6 +2376,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) } break; case WLAN_CATEGORY_SELF_PROTECTED: + if (len < (IEEE80211_MIN_ACTION_SIZE + + sizeof(mgmt->u.action.u.self_prot.action_code))) + break; + switch (mgmt->u.action.u.self_prot.action_code) { case WLAN_SP_MESH_PEERING_OPEN: case WLAN_SP_MESH_PEERING_CLOSE: @@ -2372,6 +2398,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) } break; case WLAN_CATEGORY_MESH_ACTION: + if (len < (IEEE80211_MIN_ACTION_SIZE + + sizeof(mgmt->u.action.u.mesh_action.action_code))) + break; + if (!ieee80211_vif_is_mesh(&sdata->vif)) break; if (mesh_action_is_path_sel(mgmt) && diff --git a/net/wireless/util.c b/net/wireless/util.c index 45a09de1ffe3..2762e8329986 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -309,7 +309,7 @@ unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) } EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); -static int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) +unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) { int ae = meshhdr->flags & MESH_FLAGS_AE; /* 802.11-2012, 8.2.4.7.3 */ @@ -323,6 +323,7 @@ static int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) return 18; } } +EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) -- cgit v1.2.3 From 6dbda2d00d466225f9db1dc695ff852443f28832 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Oct 2012 00:41:23 +0200 Subject: mac80211: make sure data is accessible in EAPOL check The code to allow EAPOL frames even when the station isn't yet marked associated needs to check that the incoming frame is long enough and due to paged RX it also can't assume skb->data contains the right data, it must use skb_copy_bits(). Fix this to avoid using data that doesn't really exist. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 265a032dec49..00ade7feb2e3 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -888,14 +888,16 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) */ if (rx->sta && rx->sdata->vif.type == NL80211_IFTYPE_STATION && ieee80211_is_data_present(hdr->frame_control)) { - u16 ethertype; - u8 *payload; - - payload = rx->skb->data + - ieee80211_hdrlen(hdr->frame_control); - ethertype = (payload[6] << 8) | payload[7]; - if (cpu_to_be16(ethertype) == - rx->sdata->control_port_protocol) + unsigned int hdrlen; + __be16 ethertype; + + hdrlen = ieee80211_hdrlen(hdr->frame_control); + + if (rx->skb->len < hdrlen + 8) + return RX_DROP_MONITOR; + + skb_copy_bits(rx->skb, hdrlen + 6, ðertype, 2); + if (ethertype == rx->sdata->control_port_protocol) return RX_CONTINUE; } -- cgit v1.2.3 From 38fe36a248ec3228f8e6507955d7ceb0432d2000 Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Thu, 25 Oct 2012 05:34:45 +0000 Subject: netfilter: nf_nat: don't check for port change on ICMP tuples ICMP tuples have id in src and type/code in dst. So comparing src.u.all with dst.u.all will always fail here and ip_xfrm_me_harder() is called for every ICMP packet, even if there was no NAT. Signed-off-by: Ulrich Weber Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/iptable_nat.c | 4 +++- net/ipv6/netfilter/ip6table_nat.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 9e0ffaf1d942..a82047282dbb 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -184,7 +184,8 @@ nf_nat_ipv4_out(unsigned int hooknum, if ((ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET) < 0) ret = NF_DROP; @@ -221,6 +222,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET) < 0) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index e418bd6350a4..d57dab17a182 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -186,7 +186,8 @@ nf_nat_ipv6_out(unsigned int hooknum, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET6) < 0) ret = NF_DROP; @@ -222,6 +223,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET6)) -- cgit v1.2.3 From f1df1374dc83d62588667e566e959df384718ad1 Mon Sep 17 00:00:00 2001 From: Hein Tibosch Date: Fri, 26 Oct 2012 23:49:26 +0000 Subject: netfilter: nf_defrag_ipv6: solve section mismatch in nf_conntrack_reasm WARNING: net/ipv6/netfilter/nf_defrag_ipv6.o(.text+0xe0): Section mismatch in reference from the function nf_ct_net_init() to the function .init.text:nf_ct_frag6_sysctl_register() The function nf_ct_net_init() references the function __init nf_ct_frag6_sysctl_register(). In case nf_conntrack_ipv6 is compiled as a module, nf_ct_net_init could be called after the init code and data are unloaded. Therefore remove the "__net_init" annotation from nf_ct_frag6_sysctl_register(). Signed-off-by: Hein Tibosch Acked-by: Cong Wang Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 18bd9bbbd1c6..22c8ea951185 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -85,7 +85,7 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { { } }; -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -127,7 +127,7 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #else -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } -- cgit v1.2.3 From 35f5149ead73e8e635b417b6c3aece43ffdfe5bc Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 31 Oct 2012 15:50:34 +0100 Subject: mac80211: do not call ieee80211_configure_filter if no interfaces are up Drivers are not expected to handle it before drv_start has been called. It will be called again after an interface has been brought up. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/cfg.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 05f3a313db88..7371f676cf41 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2594,6 +2594,9 @@ static void ieee80211_mgmt_frame_register(struct wiphy *wiphy, else local->probe_req_reg--; + if (!local->open_count) + break; + ieee80211_queue_work(&local->hw, &local->reconfig_filter); break; default: -- cgit v1.2.3 From bca1e29fb54c51856dda6772d488d41b10ed91da Mon Sep 17 00:00:00 2001 From: David Spinadel Date: Mon, 29 Oct 2012 14:49:41 +0200 Subject: mac80211: init sched_scan_ies In case that there is an unsupported band, the ie will be unallocated and the free will crash. Cc: stable@vger.kernel.org Signed-off-by: David Spinadel Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- net/mac80211/scan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index c4cdbde24fd3..43e60b5a7546 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -917,7 +917,7 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; - struct ieee80211_sched_scan_ies sched_scan_ies; + struct ieee80211_sched_scan_ies sched_scan_ies = {}; int ret, i; mutex_lock(&local->mtx); -- cgit v1.2.3 From d24bab93e42b1f90d89c86b3edbb81ec34bb9474 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 1 Nov 2012 11:21:53 -0400 Subject: SUNRPC: return proper errno from backchannel_rqst The one and only caller (in fs/nfs/nfs4client.c) uses the result as an errno and would have interpreted an error as EPERM. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- net/sunrpc/backchannel_rqst.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 5a3d675d2f2f..a9c0bbccad6b 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -172,7 +172,7 @@ out_free: xprt_free_allocation(req); dprintk("RPC: setup backchannel transport failed\n"); - return -1; + return -ENOMEM; } EXPORT_SYMBOL_GPL(xprt_setup_backchannel); -- cgit v1.2.3 From d3e9a1dc7c34c3c5a253091289a54883bf27f6ba Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Wed, 31 Oct 2012 05:48:19 +0000 Subject: net: sctp: Fix typo in net/sctp Correct spelling typo in net/sctp/socket.c Signed-off-by: Masanari Iida Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 59d16ea927f0..a60d1f8b41c5 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -974,7 +974,7 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk, void *addr_buf; struct sctp_af *af; - SCTP_DEBUG_PRINTK("sctp_setsocktopt_bindx: sk %p addrs %p" + SCTP_DEBUG_PRINTK("sctp_setsockopt_bindx: sk %p addrs %p" " addrs_size %d opt %d\n", sk, addrs, addrs_size, op); if (unlikely(addrs_size <= 0)) -- cgit v1.2.3 From 8f363b77ee4fbf7c3bbcf5ec2c5ca482d396d664 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Wed, 31 Oct 2012 02:45:32 +0000 Subject: net: fix divide by zero in tcp algorithm illinois Reading TCP stats when using TCP Illinois congestion control algorithm can cause a divide by zero kernel oops. The division by zero occur in tcp_illinois_info() at: do_div(t, ca->cnt_rtt); where ca->cnt_rtt can become zero (when rtt_reset is called) Steps to Reproduce: 1. Register tcp_illinois: # sysctl -w net.ipv4.tcp_congestion_control=illinois 2. Monitor internal TCP information via command "ss -i" # watch -d ss -i 3. Establish new TCP conn to machine Either it fails at the initial conn, or else it needs to wait for a loss or a reset. This is only related to reading stats. The function avg_delay() also performs the same divide, but is guarded with a (ca->cnt_rtt > 0) at its calling point in update_params(). Thus, simply fix tcp_illinois_info(). Function tcp_illinois_info() / get_info() is called without socket lock. Thus, eliminate any race condition on ca->cnt_rtt by using a local stack variable. Simply reuse info.tcpv_rttcnt, as its already set to ca->cnt_rtt. Function avg_delay() is not affected by this race condition, as its called with the socket lock. Cc: Petr Matousek Signed-off-by: Jesper Dangaard Brouer Acked-by: Eric Dumazet Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/tcp_illinois.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 813b43a76fec..834857f3c871 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -313,11 +313,13 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, .tcpv_rttcnt = ca->cnt_rtt, .tcpv_minrtt = ca->base_rtt, }; - u64 t = ca->sum_rtt; - do_div(t, ca->cnt_rtt); - info.tcpv_rtt = t; + if (info.tcpv_rttcnt > 0) { + u64 t = ca->sum_rtt; + do_div(t, info.tcpv_rttcnt); + info.tcpv_rtt = t; + } nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); } } -- cgit v1.2.3 From 2c42a3fb30845867bfcaf0747ff50c1375884ff2 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 30 Oct 2012 12:03:09 +0000 Subject: tcp: Fix double sizeof in new tcp_metrics code Fix double sizeof when parsing IPv6 address from user space because it breaks get/del by specific IPv6 address. Problem noticed by David Binderman: https://bugzilla.kernel.org/show_bug.cgi?id=49171 Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv4/tcp_metrics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4c752a6e0bcd..53bc5847bfa8 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -864,7 +864,7 @@ static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, } a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6]; if (a) { - if (nla_len(a) != sizeof(sizeof(struct in6_addr))) + if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; addr->family = AF_INET6; memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6)); -- cgit v1.2.3 From 789336360e0a2aeb9750c16ab704a02cbe035e9e Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Mon, 29 Oct 2012 23:41:48 +0000 Subject: l2tp: fix oops in l2tp_eth_create() error path When creating an L2TPv3 Ethernet session, if register_netdev() should fail for any reason (for example, automatic naming for "l2tpeth%d" interfaces hits the 32k-interface limit), the netdev is freed in the error path. However, the l2tp_eth_sess structure's dev pointer is left uncleared, and this results in l2tp_eth_delete() then attempting to unregister the same netdev later in the session teardown. This results in an oops. To avoid this, clear the session dev pointer in the error path. Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_eth.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 37b8b8ba31f7..76125c57ee6d 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -291,6 +291,7 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p out_del_dev: free_netdev(dev); + spriv->dev = NULL; out_del_session: l2tp_session_delete(session); out: -- cgit v1.2.3 From c454e6111d1ef4268fe98e87087216e51c2718c3 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 29 Oct 2012 05:05:33 +0000 Subject: tcp-repair: Handle zero-length data put in rcv queue When sending data into a tcp socket in repair state we should check for the amount of data being 0 explicitly. Otherwise we'll have an skb with seq == end_seq in rcv queue, but tcp doesn't expect this to happen (in particular a warn_on in tcp_recvmsg shoots). Signed-off-by: Pavel Emelyanov Reported-by: Giorgos Mavrikas Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1db663983587..2c2b13a999ea 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4529,6 +4529,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) struct tcphdr *th; bool fragstolen; + if (size == 0) + return 0; + skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; -- cgit v1.2.3 From d145f7ec23b6366e2b75442eaefafa11077ed568 Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Tue, 30 Oct 2012 22:06:01 +0000 Subject: tipc: do not use tasklet_disable before tasklet_kill If tasklet_disable() is called before related tasklet handled, tasklet_kill will never be finished. tasklet_kill is enough. Signed-off-by: Xiaotian Feng Cc: Jon Maloy Cc: Allan Stephens Cc: "David S. Miller" Cc: netdev@vger.kernel.org Cc: tipc-discussion@lists.sourceforge.net Signed-off-by: David S. Miller --- net/tipc/handler.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/tipc/handler.c b/net/tipc/handler.c index 111ff8300ae5..b36f0fcd9bdf 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -116,7 +116,6 @@ void tipc_handler_stop(void) return; handler_enabled = 0; - tasklet_disable(&tipc_tasklet); tasklet_kill(&tipc_tasklet); spin_lock_bh(&qitem_lock); -- cgit v1.2.3 From a7a558fe426adf22b0b979705167146bf16c37fa Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 1 Nov 2012 16:23:10 +0000 Subject: rtnetlink: Use nlmsg type RTM_NEWNEIGH from dflt fdb dump Change the dflt fdb dump handler to use RTM_NEWNEIGH to be compatible with bridge dump routines. The dump reply from the network driver handlers should match the reply from bridge handler. The fact they were not in the ixgbe case was effectively a bug. This patch resolves it. Applications that were not checking the nlmsg type will continue to work. And now applications that do check the type will work as expected. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 76d4c2c3c89b..fad649ae4dec 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2192,7 +2192,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, - portid, seq, 0, NTF_SELF); + portid, seq, + RTM_NEWNEIGH, NTF_SELF); if (err < 0) return err; skip: -- cgit v1.2.3 From cacb6ba0f36ab14a507f4ee7697e8332899015d2 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Sat, 3 Nov 2012 09:30:34 +0000 Subject: net: inet_diag -- Return error code if protocol handler is missed We've observed that in case if UDP diag module is not supported in kernel the netlink returns NLMSG_DONE without notifying a caller that handler is missed. This patch makes __inet_diag_dump to return error code instead. So as example it become possible to detect such situation and handle it gracefully on userspace level. Signed-off-by: Cyrill Gorcunov CC: David Miller CC: Eric Dumazet CC: Pavel Emelyanov Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv4/inet_diag.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 535584c00f91..0c34bfabc11f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -892,13 +892,16 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc) { const struct inet_diag_handler *handler; + int err = 0; handler = inet_diag_lock_handler(r->sdiag_protocol); if (!IS_ERR(handler)) handler->dump(skb, cb, r, bc); + else + err = PTR_ERR(handler); inet_diag_unlock_handler(handler); - return skb->len; + return err ? : skb->len; } static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) -- cgit v1.2.3 From 987c285c2ae2e4e32aca3a9b3252d28171c75711 Mon Sep 17 00:00:00 2001 From: Arik Nemtsov Date: Mon, 5 Nov 2012 10:27:52 +0200 Subject: mac80211: sync acccess to tx_filtered/ps_tx_buf queues These are accessed without a lock when ending STA PSM. If the sta_cleanup timer accesses these lists at the same time, we might crash. This may fix some mysterious crashes we had during ieee80211_sta_ps_deliver_wakeup. Cc: stable@vger.kernel.org Signed-off-by: Arik Nemtsov Signed-off-by: Ido Yariv Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 797dd36a220d..89ccd3ec7eb8 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -961,6 +961,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) struct ieee80211_local *local = sdata->local; struct sk_buff_head pending; int filtered = 0, buffered = 0, ac; + unsigned long flags; clear_sta_flag(sta, WLAN_STA_SP); @@ -976,12 +977,16 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; + spin_lock_irqsave(&sta->tx_filtered[ac].lock, flags); skb_queue_splice_tail_init(&sta->tx_filtered[ac], &pending); + spin_unlock_irqrestore(&sta->tx_filtered[ac].lock, flags); tmp = skb_queue_len(&pending); filtered += tmp - count; count = tmp; + spin_lock_irqsave(&sta->ps_tx_buf[ac].lock, flags); skb_queue_splice_tail_init(&sta->ps_tx_buf[ac], &pending); + spin_unlock_irqrestore(&sta->ps_tx_buf[ac].lock, flags); tmp = skb_queue_len(&pending); buffered += tmp - count; } -- cgit v1.2.3 From 3015f3d2a3cd9614294025849d3ed89fd2f3a7f5 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Mon, 5 Nov 2012 20:29:24 +0000 Subject: pkt_sched: enable QFQ to support TSO/GSO If the max packet size for some class (configured through tc) is violated by the actual size of the packets of that class, then QFQ would not schedule classes correctly, and the data structures implementing the bucket lists may get corrupted. This problem occurs with TSO/GSO even if the max packet size is set to the MTU, and is, e.g., the cause of the failure reported in [1]. Two patches have been proposed to solve this problem in [2], one of them is a preliminary version of this patch. This patch addresses the above issues by: 1) setting QFQ parameters to proper values for supporting TSO/GSO (in particular, setting the maximum possible packet size to 64KB), 2) automatically increasing the max packet size for a class, lmax, when a packet with a larger size than the current value of lmax arrives. The drawback of the first point is that the maximum weight for a class is now limited to 4096, which is equal to 1/16 of the maximum weight sum. Finally, this patch also forcibly caps the timestamps of a class if they are too high to be stored in the bucket list. This capping, taken from QFQ+ [3], handles the unfrequent case described in the comment to the function slot_insert. [1] http://marc.info/?l=linux-netdev&m=134968777902077&w=2 [2] http://marc.info/?l=linux-netdev&m=135096573507936&w=2 [3] http://marc.info/?l=linux-netdev&m=134902691421670&w=2 Signed-off-by: Paolo Valente Tested-by: Cong Wang Acked-by: Stephen Hemminger Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/sched/sch_qfq.c | 109 +++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 79 insertions(+), 30 deletions(-) (limited to 'net') diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f0dd83cff906..9687fa1c2275 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -84,18 +84,19 @@ * grp->index is the index of the group; and grp->slot_shift * is the shift for the corresponding (scaled) sigma_i. */ -#define QFQ_MAX_INDEX 19 -#define QFQ_MAX_WSHIFT 16 +#define QFQ_MAX_INDEX 24 +#define QFQ_MAX_WSHIFT 12 #define QFQ_MAX_WEIGHT (1<wsum += delta_w; } +static void qfq_update_reactivate_class(struct qfq_sched *q, + struct qfq_class *cl, + u32 inv_w, u32 lmax, int delta_w) +{ + bool need_reactivation = false; + int i = qfq_calc_index(inv_w, lmax); + + if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { + /* + * shift cl->F back, to not charge the + * class for the not-yet-served head + * packet + */ + cl->F = cl->S; + /* remove class from its slot in the old group */ + qfq_deactivate_class(q, cl); + need_reactivation = true; + } + + qfq_update_class_params(q, cl, lmax, inv_w, delta_w); + + if (need_reactivation) /* activate in new group */ + qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); +} + + static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg) { @@ -238,7 +265,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct qfq_class *cl = (struct qfq_class *)*arg; struct nlattr *tb[TCA_QFQ_MAX + 1]; u32 weight, lmax, inv_w; - int i, err; + int err; int delta_w; if (tca[TCA_OPTIONS] == NULL) { @@ -270,16 +297,14 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) { + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { pr_notice("qfq: invalid max length %u\n", lmax); return -EINVAL; } } else - lmax = 1UL << QFQ_MTU_SHIFT; + lmax = psched_mtu(qdisc_dev(sch)); if (cl != NULL) { - bool need_reactivation = false; - if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, &cl->rate_est, qdisc_root_sleeping_lock(sch), @@ -291,24 +316,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (lmax == cl->lmax && inv_w == cl->inv_w) return 0; /* nothing to update */ - i = qfq_calc_index(inv_w, lmax); sch_tree_lock(sch); - if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { - /* - * shift cl->F back, to not charge the - * class for the not-yet-served head - * packet - */ - cl->F = cl->S; - /* remove class from its slot in the old group */ - qfq_deactivate_class(q, cl); - need_reactivation = true; - } - - qfq_update_class_params(q, cl, lmax, inv_w, delta_w); - - if (need_reactivation) /* activate in new group */ - qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); + qfq_update_reactivate_class(q, cl, inv_w, lmax, delta_w); sch_tree_unlock(sch); return 0; @@ -663,15 +672,48 @@ static void qfq_make_eligible(struct qfq_sched *q, u64 old_V) /* - * XXX we should make sure that slot becomes less than 32. - * This is guaranteed by the input values. - * roundedS is always cl->S rounded on grp->slot_shift bits. + * If the weight and lmax (max_pkt_size) of the classes do not change, + * then QFQ guarantees that the slot index is never higher than + * 2 + ((1<S) >> grp->slot_shift; - unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS; + unsigned int i; /* slot index in the bucket list */ + + if (unlikely(slot > QFQ_MAX_SLOTS - 2)) { + u64 deltaS = roundedS - grp->S - + ((u64)(QFQ_MAX_SLOTS - 2)<slot_shift); + cl->S -= deltaS; + cl->F -= deltaS; + slot = QFQ_MAX_SLOTS - 2; + } + + i = (grp->front + slot) % QFQ_MAX_SLOTS; hlist_add_head(&cl->next, &grp->slots[i]); __set_bit(slot, &grp->full_slots); @@ -892,6 +934,13 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); + if (unlikely(cl->lmax < qdisc_pkt_len(skb))) { + pr_debug("qfq: increasing maxpkt from %u to %u for class %u", + cl->lmax, qdisc_pkt_len(skb), cl->common.classid); + qfq_update_reactivate_class(q, cl, cl->inv_w, + qdisc_pkt_len(skb), 0); + } + err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); -- cgit v1.2.3 From a3d744e995d2b936c500585ae39d99ee251c89b4 Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Tue, 6 Nov 2012 02:10:10 +0000 Subject: af-packet: fix oops when socket is not present MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Due to a NULL dereference, the following patch is causing oops in normal trafic condition: commit c0de08d04215031d68fa13af36f347a6cfa252ca Author: Eric Leblond Date:   Thu Aug 16 22:02:58 2012 +0000     af_packet: don't emit packet on orig fanout group This buggy patch was a feature fix and has reached most stable branches. When skb->sk is NULL and when packet fanout is used, there is a crash in match_fanout_group where skb->sk is accessed. This patch fixes the issue by returning false as soon as the socket is NULL: this correspond to the wanted behavior because the kernel as to resend the skb to all the listening socket in this case. Signed-off-by: Eric Leblond Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 09cb3f6dc40c..bda6d004f9f0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1666,7 +1666,7 @@ static inline int deliver_skb(struct sk_buff *skb, static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { - if (ptype->af_packet_priv == NULL) + if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) -- cgit v1.2.3 From cfff2f999d9baa561f20d999c8b83b03f078fb8f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 9 Nov 2012 09:47:27 +0100 Subject: mac80211: fix memory leak in device registration error path If the cipher suites need to be allocated, but this allocation fails, this leaks the internal scan request. Fix that by going to the correct error handling label. Signed-off-by: Johannes Berg --- net/mac80211/main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/mac80211/main.c b/net/mac80211/main.c index c80c4490351c..f57f597972f8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -871,8 +871,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->cipher_suites, sizeof(u32) * local->hw.wiphy->n_cipher_suites, GFP_KERNEL); - if (!suites) - return -ENOMEM; + if (!suites) { + result = -ENOMEM; + goto fail_wiphy_register; + } for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) { u32 suite = local->hw.wiphy->cipher_suites[r]; if (suite == WLAN_CIPHER_SUITE_WEP40 || -- cgit v1.2.3 From 476e44cb19f1fbf2d5883dddcc0ce31b33b45915 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 19 Oct 2012 20:10:46 +0300 Subject: Bluetooth: Fix having bogus entries in mgmt_read_index_list reply The mgmt_read_index_list uses one loop to calculate the max needed size of its response with the help of an upper-bound of the controller count. The second loop is more strict as it checks for HCI_SETUP (which might have gotten set after the first loop) and could result in some indexes being skipped. Because of this the function needs to readjust the event length and index count after filling in the response array. Signed-off-by: Johan Hedberg Cc: stable@vger.kernel.org Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- net/bluetooth/mgmt.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index aa2ea0a8142c..2cfabe27d3e0 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -326,7 +326,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, struct hci_dev *d; size_t rp_len; u16 count; - int i, err; + int err; BT_DBG("sock %p", sk); @@ -347,9 +347,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, return -ENOMEM; } - rp->num_controllers = cpu_to_le16(count); - - i = 0; + count = 0; list_for_each_entry(d, &hci_dev_list, list) { if (test_bit(HCI_SETUP, &d->dev_flags)) continue; @@ -357,10 +355,13 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, if (!mgmt_valid_hdev(d)) continue; - rp->index[i++] = cpu_to_le16(d->id); + rp->index[count++] = cpu_to_le16(d->id); BT_DBG("Added hci%u", d->id); } + rp->num_controllers = cpu_to_le16(count); + rp_len = sizeof(*rp) + (2 * count); + read_unlock(&hci_dev_list_lock); err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST, 0, rp, -- cgit v1.2.3 From 896ea28ea824d49671fc7e9315d9c5be491a644f Mon Sep 17 00:00:00 2001 From: Paulo Sérgio Date: Thu, 25 Oct 2012 16:55:51 -0300 Subject: Bluetooth: Fix error status when pairing fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When pairing fails due to wrong confirm value, the management layer doesn't report a proper error status. It sends MGMT_STATUS_CONNECT_FAILED instead of MGMT_STATUS_AUTH_FAILED. Most of management functions that receive a status as a parameter expects for it to be encoded as a HCI status. But when a SMP pairing fails, the SMP layer sends the SMP reason as the error status to the management layer. This commit maps all SMP reasons to HCI_ERROR_AUTH_FAILURE, which will be converted to MGMT_STATUS_AUTH_FAILED in the management layer. Reported-by: Claudio Takahasi Reviewed-by: João Paulo Rechi Vita Signed-off-by: Paulo Sérgio Signed-off-by: Gustavo Padovan --- net/bluetooth/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 2ac8d50861e0..a5923378bdf0 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -267,7 +267,7 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason, u8 send) clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->hcon->flags); mgmt_auth_failed(conn->hcon->hdev, conn->dst, hcon->type, - hcon->dst_type, reason); + hcon->dst_type, HCI_ERROR_AUTH_FAILURE); cancel_delayed_work_sync(&conn->security_timer); -- cgit v1.2.3 From fbe96d6ff9f4e361e1b2ec0a30140e17af7e3854 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Tue, 30 Oct 2012 01:35:40 -0700 Subject: Bluetooth: Notify about device registration before power on It is important that the monitor interface gets notified about a new device before its power on procedure has been started. For some reason that is no longer working as expected and the power on procedure runs first. It is safe to just notify about device registration and trigger the power on procedure afterwards. Signed-off-by: Marcel Holtmann Acked-by: Johan Hedberg Signed-off-by: Gustavo Padovan --- net/bluetooth/hci_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8a0ce706aebd..a0a2f97b9c62 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1754,11 +1754,11 @@ int hci_register_dev(struct hci_dev *hdev) if (hdev->dev_type != HCI_AMP) set_bit(HCI_AUTO_OFF, &hdev->dev_flags); - schedule_work(&hdev->power_on); - hci_notify(hdev, HCI_DEV_REG); hci_dev_hold(hdev); + schedule_work(&hdev->power_on); + return id; err_wqueue: -- cgit v1.2.3 From 482049f75750d73358e65236b933417b69f9cc25 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 8 Nov 2012 10:25:26 +0100 Subject: Bluetooth: Fix memory leak when removing a UUID When removing a UUID from the list in the remove_uuid() function we must also kfree the entry in addition to removing it from the list. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo Padovan --- net/bluetooth/mgmt.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 2cfabe27d3e0..91de4239da66 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1367,6 +1367,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, continue; list_del(&match->list); + kfree(match); found++; } -- cgit v1.2.3 From 20f544eea03db4b498942558b882d463ce575c3e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 8 Nov 2012 14:06:28 +0100 Subject: mac80211: don't send null data packet when not associated On resume or firmware recovery, mac80211 sends a null data packet to see if the AP is still around and hasn't disconnected us. However, it always does this even if it wasn't even connected before, leading to a warning in the new channel context code. Fix this by checking that it's associated. Cc: stable@vger.kernel.org Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- net/mac80211/util.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/mac80211/util.c b/net/mac80211/util.c index e6e4bda0528e..fa1d343faa4b 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1491,6 +1491,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_STATION) continue; + if (!sdata->u.mgd.associated) + continue; ieee80211_send_nullfunc(local, sdata, 0); } -- cgit v1.2.3 From 60713a0ca7fd6651b951cc1b4dbd528d1fc0281b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Tue, 6 Nov 2012 16:18:41 +0000 Subject: ipv6: send unsolicited neighbour advertisements to all-nodes As documented in RFC4861 (Neighbor Discovery for IP version 6) 7.2.6., unsolicited neighbour advertisements should be sent to the all-nodes multicast address. Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ff36194a71aa..2edce30ef733 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -535,7 +535,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; - struct in6_addr mcaddr; + struct in6_addr mcaddr = IN6ADDR_LINKLOCAL_ALLNODES_INIT; idev = in6_dev_get(dev); if (!idev) @@ -543,7 +543,6 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - addrconf_addr_solict_mult(&ifa->addr, &mcaddr); ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, -- cgit v1.2.3 From a375413311b39005ef281bfd71ae8f4e3df22e97 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 9 Nov 2012 05:34:56 +0000 Subject: gre6: fix rtnl dump messages Spotted after a code review. Introduced by c12b395a46646bab69089ce7016ac78177f6001f (gre: Support GRE over IPv6). Signed-off-by: Nicolas Dichtel Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 0185679c5f53..d5cb3c4e66f8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1633,9 +1633,9 @@ static size_t ip6gre_get_size(const struct net_device *dev) /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_REMOTE */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ @@ -1659,8 +1659,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) || - nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || -- cgit v1.2.3 From 1f98ab7fef48a2968f37f422c256c9fbd978c3f0 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sat, 10 Nov 2012 03:44:14 +0100 Subject: mac80211: call skb_dequeue/ieee80211_free_txskb instead of __skb_queue_purge Fixes more wifi status skb leaks, leading to hostapd/wpa_supplicant hangs. Signed-off-by: Felix Fietkau Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/ieee80211_i.h | 2 ++ net/mac80211/sta_info.c | 6 +++--- net/mac80211/status.c | 9 +++++++++ net/mac80211/tx.c | 9 ++++++--- 4 files changed, 20 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8c804550465b..156e5835e37f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1314,6 +1314,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs); /* HT */ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 89ccd3ec7eb8..3b5911ed4312 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -117,8 +117,8 @@ static void free_sta_work(struct work_struct *wk) for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]); - __skb_queue_purge(&sta->ps_tx_buf[ac]); - __skb_queue_purge(&sta->tx_filtered[ac]); + ieee80211_purge_tx_queue(&local->hw, &sta->ps_tx_buf[ac]); + ieee80211_purge_tx_queue(&local->hw, &sta->tx_filtered[ac]); } #ifdef CONFIG_MAC80211_MESH @@ -141,7 +141,7 @@ static void free_sta_work(struct work_struct *wk) tid_tx = rcu_dereference_raw(sta->ampdu_mlme.tid_tx[i]); if (!tid_tx) continue; - __skb_queue_purge(&tid_tx->pending); + ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending); kfree(tid_tx); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3af0cc4130f1..101eb88a2b78 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -668,3 +668,12 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb) dev_kfree_skb_any(skb); } EXPORT_SYMBOL(ieee80211_free_txskb); + +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs) +{ + struct sk_buff *skb; + + while ((skb = __skb_dequeue(skbs))) + ieee80211_free_txskb(hw, skb); +} diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index c9bf83f36657..b858ebe41fda 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1358,7 +1358,7 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx) if (tx->skb) ieee80211_free_txskb(&tx->local->hw, tx->skb); else - __skb_queue_purge(&tx->skbs); + ieee80211_purge_tx_queue(&tx->local->hw, &tx->skbs); return -1; } else if (unlikely(res == TX_QUEUED)) { I802_DEBUG_INC(tx->local->tx_handlers_queued); @@ -2120,10 +2120,13 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, */ void ieee80211_clear_tx_pending(struct ieee80211_local *local) { + struct sk_buff *skb; int i; - for (i = 0; i < local->hw.queues; i++) - skb_queue_purge(&local->pending[i]); + for (i = 0; i < local->hw.queues; i++) { + while ((skb = skb_dequeue(&local->pending[i])) != NULL) + ieee80211_free_txskb(&local->hw, skb); + } } /* -- cgit v1.2.3 From 0c9f79be295c99ac7e4b569ca493d75fdcc19e4e Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Sun, 11 Nov 2012 11:20:01 +0000 Subject: ipv4: avoid undefined behavior in do_ip_setsockopt() (1< Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 35 ++++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) (limited to 'net') diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5eea4a811042..14bbfcf717ac 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -457,19 +457,28 @@ static int do_ip_setsockopt(struct sock *sk, int level, struct inet_sock *inet = inet_sk(sk); int val = 0, err; - if (((1<= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; -- cgit v1.2.3 From 43c771a1963ab461a2f194e3c97fded1d5fe262f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 12 Nov 2012 10:51:34 +0100 Subject: wireless: allow 40 MHz on world roaming channels 12/13 When in world roaming mode, allow 40 MHz to be used on channels 12 and 13 so that an AP that is, e.g., using HT40+ on channel 9 (in the UK) can be used. Cc: stable@vger.kernel.org Reported-by: Eddie Chapman Tested-by: Eddie Chapman Acked-by: Luis R. Rodriguez Signed-off-by: Johannes Berg --- net/wireless/reg.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/wireless/reg.c b/net/wireless/reg.c index bcc7d7ee5a51..b75756b05af7 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -141,9 +141,8 @@ static const struct ieee80211_regdomain world_regdom = { .reg_rules = { /* IEEE 802.11b/g, channels 1..11 */ REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), - /* IEEE 802.11b/g, channels 12..13. No HT40 - * channel fits here. */ - REG_RULE(2467-10, 2472+10, 20, 6, 20, + /* IEEE 802.11b/g, channels 12..13. */ + REG_RULE(2467-10, 2472+10, 40, 6, 20, NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS), /* IEEE 802.11 channel 14 - Only JP enables -- cgit v1.2.3 From bd090dfc634ddd711a5fbd0cadc6e0ab4977bcaf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 13 Nov 2012 05:37:18 +0000 Subject: tcp: tcp_replace_ts_recent() should not be called from tcp_validate_incoming() We added support for RFC 5961 in latest kernels but TCP fails to perform exhaustive check of ACK sequence. We can update our view of peer tsval from a frame that is later discarded by tcp_ack() This makes timestamps enabled sessions vulnerable to injection of a high tsval : peers start an ACK storm, since the victim sends a dupack each time it receives an ACK from the other peer. As tcp_validate_incoming() is called before tcp_ack(), we should not peform tcp_replace_ts_recent() from it, and let callers do it at the right time. Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Yuchung Cheng Cc: Nandita Dukkipati Cc: H.K. Jerry Chu Cc: Romain Francoise Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2c2b13a999ea..609ff98aeb47 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5313,11 +5313,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, goto discard; } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 3: check security and precedence [ignored] */ /* step 4: Check for a SYN @@ -5552,6 +5547,11 @@ step5: if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -6130,6 +6130,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + /* step 6: check the URG bit */ tcp_urg(sk, skb, th); -- cgit v1.2.3 From d4596bad2a713fcd0def492b1960e6d899d5baa8 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 10 Nov 2012 19:52:34 +0000 Subject: ipv6: setsockopt(IPIPPROTO_IPV6, IPV6_MINHOPCOUNT) forgot to set return value Cc: Stephen Hemminger Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ipv6_sockglue.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ba6d13d1f1e1..e02faed6d17e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -827,6 +827,7 @@ pref_skip_coa: if (val < 0 || val > 255) goto e_inval; np->min_hopcount = val; + retv = 0; break; case IPV6_DONTFRAG: np->dontfrag = valbool; -- cgit v1.2.3 From b2942004fb5c9f3304b77e187b8a1977b3626c9b Mon Sep 17 00:00:00 2001 From: Saurabh Mohan Date: Wed, 14 Nov 2012 18:08:15 -0800 Subject: ipv4/ip_vti.c: VTI fix post-decryption forwarding With the latest kernel there are two things that must be done post decryption so that the packet are forwarded. 1. Remove the mark from the packet. This will cause the packet to not match the ipsec-policy again. However doing this causes the post-decryption check to fail also and the packet will get dropped. (cat /proc/net/xfrm_stat). 2. Remove the sp association in the skbuff so that no policy check is done on the packet for VTI tunnels. Due to #2 above we must now do a security-policy check in the vti rcv path prior to resetting the mark in the skbuff. Signed-off-by: Saurabh Mohan Reported-by: Ruben Herold Signed-off-by: David S. Miller --- net/ipv4/ip_vti.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1831092f999f..858fddf6482a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -338,12 +338,17 @@ static int vti_rcv(struct sk_buff *skb) if (tunnel != NULL) { struct pcpu_tstats *tstats; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + return -1; + tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); + skb->mark = 0; + secpath_reset(skb); skb->dev = tunnel->dev; return 1; } -- cgit v1.2.3 From 0da9a0c2638c8476b4a5021841912f249e3187dc Mon Sep 17 00:00:00 2001 From: Tommi Rantala Date: Thu, 15 Nov 2012 03:49:05 +0000 Subject: sctp: fix /proc/net/sctp/ memory leak Commit 13d782f ("sctp: Make the proc files per network namespace.") changed the /proc/net/sctp/ struct file_operations opener functions to use single_open_net() and seq_open_net(). Avoid leaking memory by using single_release_net() and seq_release_net() as the release functions. Discovered with Trinity (the syscall fuzzer). Signed-off-by: Tommi Rantala Acked-by: Neil Horman Cc: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/sctp/proc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/sctp/proc.c b/net/sctp/proc.c index c3bea269faf4..9966e7b16451 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -102,7 +102,7 @@ static const struct file_operations sctp_snmp_seq_fops = { .open = sctp_snmp_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; /* Set up the proc fs entry for 'snmp' object. */ @@ -251,7 +251,7 @@ static const struct file_operations sctp_eps_seq_fops = { .open = sctp_eps_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; /* Set up the proc fs entry for 'eps' object. */ @@ -372,7 +372,7 @@ static const struct file_operations sctp_assocs_seq_fops = { .open = sctp_assocs_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; /* Set up the proc fs entry for 'assocs' object. */ @@ -517,7 +517,7 @@ static const struct file_operations sctp_remaddr_seq_fops = { .open = sctp_remaddr_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; int __net_init sctp_remaddr_proc_init(struct net *net) -- cgit v1.2.3 From ec34232575083fd0f43d3a101e8ebb041b203761 Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Thu, 15 Nov 2012 04:03:17 +0000 Subject: tcp: fix retransmission in repair mode Currently if a socket was repaired with a few packet in a write queue, a kernel bug may be triggered: kernel BUG at net/ipv4/tcp_output.c:2330! RIP: 0010:[] tcp_retransmit_skb+0x5ff/0x610 According to the initial realization v3.4-rc2-963-gc0e88ff, all skb-s should look like already posted. This patch fixes code according with this sentence. Here are three points, which were not done in the initial patch: 1. A tcp send head should not be changed 2. Initialize TSO state of a skb 3. Reset the retransmission time This patch moves logic from tcp_sendmsg to tcp_write_xmit. A packet passes the ussual way, but isn't sent to network. This patch solves all described problems and handles tcp_sendpages. Cc: Pavel Emelyanov Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Signed-off-by: Andrey Vagin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 197c0008503c..083092e3aed6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1212,7 +1212,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied && likely(!tp->repair)) + if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) @@ -1223,7 +1223,7 @@ wait_for_memory: } out: - if (copied && likely(!tp->repair)) + if (copied) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); return copied + copied_syn; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cfe6ffe1c177..2798706cb063 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1986,6 +1986,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + goto repair; /* Skip network transmission */ + cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) break; @@ -2026,6 +2029,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; +repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ -- cgit v1.2.3 From a652208e0b52c190e57f2a075ffb5e897fe31c3b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Nov 2012 02:51:04 +0000 Subject: net: correct check in dev_addr_del() Check (ha->addr == dev->dev_addr) is always true because dev_addr_init() sets this. Correct the check to behave properly on addr removal. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev_addr_lists.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 87cc17db2d56..b079c7bbc157 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -319,7 +319,8 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); - if (ha->addr == dev->dev_addr && ha->refcount == 1) + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, -- cgit v1.2.3 From e9c00136a4754829faf885cf966c9754c7734660 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Wed, 7 Nov 2012 15:05:33 +0100 Subject: batman-adv: fix tt_global_entries flags update Flags carried by a change_entry have to be always copied into the client entry as they may contain important attributes (e.g. TT_CLIENT_WIFI). For instance, a client added by means of the "early detection mechanism" has no flag set at the beginning, so they must be updated once the proper ADD event is received. This was introduced by 30cfd02b60e1cb16f5effb0a01f826c5bb7e4c59 ("batman-adv: detect not yet announced clients") Signed-off-by: Antonio Quartulli Signed-off-by: Marek Lindner --- net/batman-adv/translation-table.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 112edd371b2f..64c00120c9f0 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -769,6 +769,12 @@ int batadv_tt_global_add(struct batadv_priv *bat_priv, */ tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_TEMP; + /* the change can carry possible "attribute" flags like the + * TT_CLIENT_WIFI, therefore they have to be copied in the + * client entry + */ + tt_global_entry->common.flags |= flags; + /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a * delete + roaming change for this originator. -- cgit v1.2.3 From 27b37ebfa2d2a1b6acef6f2d21c497475c9b9709 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Thu, 8 Nov 2012 14:21:11 +0100 Subject: batman-adv: correctly pass the client flag on tt_response When a TT response with the full table is sent, the client flags should be sent as well. This patch fix the flags assignment when populating the tt_response to send back This was introduced by 30cfd02b60e1cb16f5effb0a01f826c5bb7e4c59 ("batman-adv: detect not yet announced clients") Signed-off-by: Antonio Quartulli Signed-off-by: Marek Lindner --- net/batman-adv/translation-table.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 64c00120c9f0..fec1a00a0699 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1502,7 +1502,7 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, memcpy(tt_change->addr, tt_common_entry->addr, ETH_ALEN); - tt_change->flags = BATADV_NO_FLAGS; + tt_change->flags = tt_common_entry->flags; tt_count++; tt_change++; -- cgit v1.2.3 From 1f36aebcc5fa53c5d98f3329186466b5eb76a168 Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Thu, 8 Nov 2012 21:55:29 +0100 Subject: batman-adv: don't add TEMP clients belonging to other backbone nodes The "early client detection" mechanism must not add clients belonging to other backbone nodes. Such clients must be reached by directly using the LAN instead of the mesh. This was introduced by 30cfd02b60e1cb16f5effb0a01f826c5bb7e4c59 ("batman-adv: detect not yet announced clients") Reported-by: Glen Page Signed-off-by: Antonio Quartulli Signed-off-by: Marek Lindner --- net/batman-adv/translation-table.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net') diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index fec1a00a0699..baae71585804 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -2456,6 +2456,13 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, { bool ret = false; + /* if the originator is a backbone node (meaning it belongs to the same + * LAN of this node) the temporary client must not be added because to + * reach such destination the node must use the LAN instead of the mesh + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig)) + goto out; + if (!batadv_tt_global_add(bat_priv, orig_node, addr, BATADV_TT_CLIENT_TEMP, atomic_read(&orig_node->last_ttvn))) -- cgit v1.2.3 From 74490f969155caf1ec945ad2d35d3a8eec6be71d Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Thu, 8 Nov 2012 21:55:30 +0100 Subject: batman-adv: process broadcast packets in BLA earlier The logic in the BLA mechanism may decide to drop broadcast packets because the node may still be in the setup phase. For this reason, further broadcast processing like the early client detection mechanism must be done only after the BLA check. This patches moves the invocation to BLA before any other broadcast processing. This was introduced 30cfd02b60e1cb16f5effb0a01f826c5bb7e4c59 ("batman-adv: detect not yet announced clients") Reported-by: Glen Page Signed-off-by: Simon Wunderlich Signed-off-by: Antonio Quartulli Signed-off-by: Marek Lindner --- net/batman-adv/soft-interface.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index b9a28d2dd3e8..ce0684a1fc83 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -325,6 +325,12 @@ void batadv_interface_rx(struct net_device *soft_iface, soft_iface->last_rx = jiffies; + /* Let the bridge loop avoidance check the packet. If will + * not handle it, we can safely push it up. + */ + if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) + goto out; + if (orig_node) batadv_tt_add_temporary_global_entry(bat_priv, orig_node, ethhdr->h_source); @@ -332,12 +338,6 @@ void batadv_interface_rx(struct net_device *soft_iface, if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest)) goto dropped; - /* Let the bridge loop avoidance check the packet. If will - * not handle it, we can safely push it up. - */ - if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) - goto out; - netif_rx(skb); goto out; -- cgit v1.2.3 From 976a702ac9eeacea09e588456ab165dc06f9ee83 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 16 Nov 2012 05:31:53 +0000 Subject: tcp: handle tcp_net_metrics_init() order-5 memory allocation failures order-5 allocations can fail with current kernels, we should try vmalloc() as well. Reported-by: Julien Tinnes Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_metrics.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 53bc5847bfa8..f696d7c2e9fa 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1,7 +1,6 @@ #include #include #include -#include #include #include #include @@ -9,6 +8,7 @@ #include #include #include +#include #include #include @@ -1034,7 +1034,10 @@ static int __net_init tcp_net_metrics_init(struct net *net) net->ipv4.tcp_metrics_hash_log = order_base_2(slots); size = sizeof(struct tcpm_hash_bucket) << net->ipv4.tcp_metrics_hash_log; - net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL); + net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!net->ipv4.tcp_metrics_hash) + net->ipv4.tcp_metrics_hash = vzalloc(size); + if (!net->ipv4.tcp_metrics_hash) return -ENOMEM; @@ -1055,7 +1058,10 @@ static void __net_exit tcp_net_metrics_exit(struct net *net) tm = next; } } - kfree(net->ipv4.tcp_metrics_hash); + if (is_vmalloc_addr(net->ipv4.tcp_metrics_hash)) + vfree(net->ipv4.tcp_metrics_hash); + else + kfree(net->ipv4.tcp_metrics_hash); } static __net_initdata struct pernet_operations tcp_net_metrics_ops = { -- cgit v1.2.3 From baefa31db2f2b13a05d1b81bdf2d20d487f58b0a Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 16 Nov 2012 09:04:15 +0000 Subject: net-rps: Fix brokeness causing OOO packets In commit c445477d74ab3779 which adds aRFS to the kernel, the CPU selected for RFS is not set correctly when CPU is changing. This is causing OOO packets and probably other issues. Signed-off-by: Tom Herbert Acked-by: Eric Dumazet Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index bda6d004f9f0..c0946cb2b354 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2818,8 +2818,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (unlikely(tcpu != next_cpu) && (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - - rflow->last_qtail)) >= 0)) + rflow->last_qtail)) >= 0)) { + tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); + } if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { *rflowp = rflow; -- cgit v1.2.3