From 071249b1d501b1f31a6b1af3fbcbe03158a84e5c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 25 Aug 2010 14:47:38 +0200 Subject: mac80211: delete work timer The new workqueue changes helped me find this bug that's been lingering since the changes to the work processing in mac80211 -- the work timer is never deleted properly. Do that to avoid having it fire after all data structures have been freed. It can't be re-armed because all it will do, if running, is schedule the work, but that gets flushed later and won't have anything to do since all work items are gone by now (by way of interface removal). Cc: stable@kernel.org [2.6.34+] Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/mac80211/main.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net') diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 798a91b100cc..ded5c3843e06 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -732,6 +732,12 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) rtnl_unlock(); + /* + * Now all work items will be gone, but the + * timer might still be armed, so delete it + */ + del_timer_sync(&local->work_timer); + cancel_work_sync(&local->reconfig_filter); ieee80211_clear_tx_pending(local); -- cgit v1.2.1 From 42da2f948d949efd0111309f5827bf0298bcc9a4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 30 Aug 2010 12:24:54 +0200 Subject: wireless extensions: fix kernel heap content leak Wireless extensions have an unfortunate, undocumented requirement which requires drivers to always fill iwp->length when returning a successful status. When a driver doesn't do this, it leads to a kernel heap content leak when userspace offers a larger buffer than would have been necessary. Arguably, this is a driver bug, as it should, if it returns 0, fill iwp->length, even if it separately indicated that the buffer contents was not valid. However, we can also at least avoid the memory content leak if the driver doesn't do this by setting the iwp length to max_tokens, which then reflects how big the buffer is that the driver may fill, regardless of how big the userspace buffer is. To illustrate the point, this patch also fixes a corresponding cfg80211 bug (since this requirement isn't documented nor was ever pointed out by anyone during code review, I don't trust all drivers nor all cfg80211 handlers to implement it correctly). Cc: stable@kernel.org [all the way back] Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- net/wireless/wext-compat.c | 3 +++ net/wireless/wext-core.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'net') diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index bb5e0a5ecfa1..7e5c3a45f811 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1420,6 +1420,9 @@ int cfg80211_wext_giwessid(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; + data->flags = 0; + data->length = 0; + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 0ef17bc42bac..8f5116f5af19 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -782,6 +782,22 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, } } + if (IW_IS_GET(cmd) && !(descr->flags & IW_DESCR_FLAG_NOMAX)) { + /* + * If this is a GET, but not NOMAX, it means that the extra + * data is not bounded by userspace, but by max_tokens. Thus + * set the length to max_tokens. This matches the extra data + * allocation. + * The driver should fill it with the number of tokens it + * provided, and it may check iwp->length rather than having + * knowledge of max_tokens. If the driver doesn't change the + * iwp->length, this ioctl just copies back max_token tokens + * filled with zeroes. Hopefully the driver isn't claiming + * them to be valid data. + */ + iwp->length = descr->max_tokens; + } + err = handler(dev, info, (union iwreq_data *) iwp, extra); iwp->length += essid_compat; -- cgit v1.2.1 From 628e300cccaa628d8fb92aa28cb7530a3d5f2257 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 30 Aug 2010 18:35:24 -0700 Subject: irda: Correctly clean up self->ias_obj on irda_bind() failure. If irda_open_tsap() fails, the irda_bind() code tries to destroy the ->ias_obj object by hand, but does so wrongly. In particular, it fails to a) release the hashbin attached to the object and b) reset the self->ias_obj pointer to NULL. Fix both problems by using irias_delete_object() and explicitly setting self->ias_obj to NULL, just as irda_release() does. Reported-by: Tavis Ormandy Signed-off-by: David S. Miller --- net/irda/af_irda.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 79986a674f6e..fd55b5135de5 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -824,8 +824,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = irda_open_tsap(self, addr->sir_lsap_sel, addr->sir_name); if (err < 0) { - kfree(self->ias_obj->name); - kfree(self->ias_obj); + irias_delete_object(self->ias_obj); + self->ias_obj = NULL; goto out; } -- cgit v1.2.1 From b963ea89f00f13c648af4082e5efb2172d369727 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 30 Aug 2010 19:08:01 -0700 Subject: netlink: Make NETLINK_USERSOCK work again. Once we started enforcing the a nl_table[] entry exist for a protocol, NETLINK_USERSOCK stopped working. Add a dummy table entry so that it works again. Reported-by: Thomas Voegtle Tested-by: Thomas Voegtle Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 980fe4ad0016..cd96ed3ccee4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2102,6 +2102,26 @@ static void __net_exit netlink_net_exit(struct net *net) #endif } +static void __init netlink_add_usersock_entry(void) +{ + unsigned long *listeners; + int groups = 32; + + listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head), + GFP_KERNEL); + if (!listeners) + panic("netlink_add_usersock_entry: Cannot allocate listneres\n"); + + netlink_table_grab(); + + nl_table[NETLINK_USERSOCK].groups = groups; + nl_table[NETLINK_USERSOCK].listeners = listeners; + nl_table[NETLINK_USERSOCK].module = THIS_MODULE; + nl_table[NETLINK_USERSOCK].registered = 1; + + netlink_table_ungrab(); +} + static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, @@ -2150,6 +2170,8 @@ static int __init netlink_proto_init(void) hash->rehash_time = jiffies; } + netlink_add_usersock_entry(); + sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); /* The netlink device handler may be needed early. */ -- cgit v1.2.1 From c3d34d5d9654ec9c2510f9341bfb1030b8f029d1 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Mon, 30 Aug 2010 17:36:40 -0400 Subject: wireless: register wiphy rfkill w/o holding cfg80211_mutex Otherwise lockdep complains... https://bugzilla.kernel.org/show_bug.cgi?id=17311 [ INFO: possible circular locking dependency detected ] 2.6.36-rc2-git4 #12 ------------------------------------------------------- kworker/0:3/3630 is trying to acquire lock: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x12/0x14 but task is already holding lock: (rfkill_global_mutex){+.+.+.}, at: [] rfkill_switch_all+0x24/0x49 [rfkill] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (rfkill_global_mutex){+.+.+.}: [] lock_acquire+0x120/0x15b [] __mutex_lock_common+0x54/0x52e [] mutex_lock_nested+0x34/0x39 [] rfkill_register+0x2b/0x29c [rfkill] [] wiphy_register+0x1ae/0x270 [cfg80211] [] ieee80211_register_hw+0x1b4/0x3cf [mac80211] [] iwl_ucode_callback+0x9e9/0xae3 [iwlagn] [] request_firmware_work_func+0x54/0x6f [] kthread+0x8c/0x94 [] kernel_thread_helper+0x4/0x10 -> #1 (cfg80211_mutex){+.+.+.}: [] lock_acquire+0x120/0x15b [] __mutex_lock_common+0x54/0x52e [] mutex_lock_nested+0x34/0x39 [] cfg80211_get_dev_from_ifindex+0x1b/0x7c [cfg80211] [] cfg80211_wext_giwscan+0x58/0x990 [cfg80211] [] ioctl_standard_iw_point+0x1a8/0x272 [] ioctl_standard_call+0x91/0xa7 [] T.723+0xbd/0x12c [] wext_handle_ioctl+0x31/0x6d [] dev_ioctl+0x63d/0x67a [] sock_ioctl+0x48/0x21d [] do_vfs_ioctl+0x4ba/0x509 [] sys_ioctl+0x51/0x74 [] system_call_fastpath+0x16/0x1b -> #0 (rtnl_mutex){+.+.+.}: [] __lock_acquire+0xa93/0xd9a [] lock_acquire+0x120/0x15b [] __mutex_lock_common+0x54/0x52e [] mutex_lock_nested+0x34/0x39 [] rtnl_lock+0x12/0x14 [] cfg80211_rfkill_set_block+0x1a/0x7b [cfg80211] [] rfkill_set_block+0x80/0xd5 [rfkill] [] __rfkill_switch_all+0x3f/0x6f [rfkill] [] rfkill_switch_all+0x38/0x49 [rfkill] [] rfkill_op_handler+0x105/0x136 [rfkill] [] process_one_work+0x248/0x403 [] worker_thread+0x139/0x214 [] kthread+0x8c/0x94 [] kernel_thread_helper+0x4/0x10 Signed-off-by: John W. Linville Acked-by: Johannes Berg --- net/wireless/core.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/wireless/core.c b/net/wireless/core.c index 541e2fff5e9c..d6d046b9f6f2 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -475,12 +475,10 @@ int wiphy_register(struct wiphy *wiphy) mutex_lock(&cfg80211_mutex); res = device_add(&rdev->wiphy.dev); - if (res) - goto out_unlock; - - res = rfkill_register(rdev->rfkill); - if (res) - goto out_rm_dev; + if (res) { + mutex_unlock(&cfg80211_mutex); + return res; + } /* set up regulatory info */ wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); @@ -509,13 +507,18 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_debugfs_rdev_add(rdev); mutex_unlock(&cfg80211_mutex); + /* + * due to a locking dependency this has to be outside of the + * cfg80211_mutex lock + */ + res = rfkill_register(rdev->rfkill); + if (res) + goto out_rm_dev; + return 0; out_rm_dev: device_del(&rdev->wiphy.dev); - -out_unlock: - mutex_unlock(&cfg80211_mutex); return res; } EXPORT_SYMBOL(wiphy_register); -- cgit v1.2.1 From 0f04cfd098fb81fded74e78ea1a1b86cc6c6c31e Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 31 Aug 2010 13:21:42 +0000 Subject: net sched: fix kernel leak in act_police While reviewing commit 1c40be12f7d8ca1d387510d39787b12e512a7ce8, I audited other users of tc_action_ops->dump for information leaks. That commit covered almost all of them but act_police still had a leak. opt.limit and opt.capab aren't zeroed out before the structure is passed out. This patch uses the C99 initializers to zero everything unused out. Signed-off-by: Jeff Mahoney Acked-by: Jeff Mahoney Signed-off-by: David S. Miller --- net/sched/act_police.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'net') diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 537a48732e9e..7ebf7439b478 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -350,22 +350,19 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = a->priv; - struct tc_police opt; - - opt.index = police->tcf_index; - opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = police->tcfp_burst; - opt.refcnt = police->tcf_refcnt - ref; - opt.bindcnt = police->tcf_bindcnt - bind; + struct tc_police opt = { + .index = police->tcf_index, + .action = police->tcf_action, + .mtu = police->tcfp_mtu, + .burst = police->tcfp_burst, + .refcnt = police->tcf_refcnt - ref, + .bindcnt = police->tcf_bindcnt - bind, + }; + if (police->tcfp_R_tab) opt.rate = police->tcfp_R_tab->rate; - else - memset(&opt.rate, 0, sizeof(opt.rate)); if (police->tcfp_P_tab) opt.peakrate = police->tcfp_P_tab->rate; - else - memset(&opt.peakrate, 0, sizeof(opt.peakrate)); NLA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); if (police->tcfp_result) NLA_PUT_U32(skb, TCA_POLICE_RESULT, police->tcfp_result); -- cgit v1.2.1 From 3b2eb6131e2f6ff646abb0fc69648179b8b70216 Mon Sep 17 00:00:00 2001 From: Michal Soltys Date: Mon, 30 Aug 2010 11:34:10 +0000 Subject: net/sched/sch_hfsc.c: initialize parent's cl_cfmin properly in init_vf() This patch fixes init_vf() function, so on each new backlog period parent's cl_cfmin is properly updated (including further propgation towards the root), even if the activated leaf has no upperlimit curve defined. Signed-off-by: Michal Soltys Signed-off-by: David S. Miller --- net/sched/sch_hfsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index abd904be4287..47496098d35c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -761,8 +761,8 @@ init_vf(struct hfsc_class *cl, unsigned int len) if (f != cl->cl_f) { cl->cl_f = f; cftree_update(cl); - update_cfmin(cl->cl_parent); } + update_cfmin(cl->cl_parent); } } -- cgit v1.2.1 From 928497f0209027ccd649480a38a499fab9c3f6f6 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 31 Aug 2010 05:54:00 +0000 Subject: xfrm_user: avoid a warning with some compiler Attached is a small patch to remove a warning ("warning: ISO C90 forbids mixed declarations and code" with gcc 4.3.2). Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/xfrm/xfrm_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b14ed4b1f27c..8bae6b22c846 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1801,7 +1801,7 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_user_expire *ue = nlmsg_data(nlh); struct xfrm_usersa_info *p = &ue->state; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m);; + u32 mark = xfrm_mark_get(attrs, &m); x = xfrm_state_lookup(net, mark, &p->id.daddr, p->id.spi, p->id.proto, p->family); -- cgit v1.2.1 From 750e9fad8c7f44e0005ffb7195f72dd76978c2cf Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 31 Aug 2010 05:50:43 +0000 Subject: ipv4: minor fix about RPF in help of Kconfig Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv4/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 7c3a7d191249..571f8950ed06 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -46,7 +46,7 @@ config IP_ADVANCED_ROUTER rp_filter on use: echo 1 > /proc/sys/net/ipv4/conf//rp_filter - and + or echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter Note that some distributions enable it in startup scripts. -- cgit v1.2.1 From 87f94b4e91dc042620c527f3c30c37e5127ef757 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 1 Sep 2010 18:06:39 -0700 Subject: bridge: Clear INET control block of SKBs passed into ip_fragment(). In a similar vain to commit 17762060c25590bfddd68cc1131f28ec720f405f ("bridge: Clear IPCB before possible entry into IP stack") Any time we call into the IP stack we have to make sure the state there is as expected by the ipv4 code. With help from Eric Dumazet and Herbert Xu. Reported-by: Bandan Das Signed-off-by: David S. Miller --- net/bridge/br_netfilter.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 5ed00bd7009f..137f23259a93 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -761,9 +761,11 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) { if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) && skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && - !skb_is_gso(skb)) + !skb_is_gso(skb)) { + /* BUG: Should really parse the IP options here. */ + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); return ip_fragment(skb, br_dev_queue_push_xmit); - else + } else return br_dev_queue_push_xmit(skb); } #else -- cgit v1.2.1 From 3d3be4333fdf6faa080947b331a6a19bce1a4f57 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 Sep 2010 00:50:51 +0000 Subject: gro: fix different skb headrooms Packets entering GRO might have different headrooms, even for a given flow (because of implementation details in drivers, like copybreak). We cant force drivers to deliver packets with a fixed headroom. 1) fix skb_segment() skb_segment() makes the false assumption headrooms of fragments are same than the head. When CHECKSUM_PARTIAL is used, this can give csum_start errors, and crash later in skb_copy_and_csum_dev() 2) allocate a minimal skb for head of frag_list skb_gro_receive() uses netdev_alloc_skb(headroom + skb_gro_offset(p)) to allocate a fresh skb. This adds NET_SKB_PAD to a padding already provided by netdevice, depending on various things, like copybreak. Use alloc_skb() to allocate an exact padding, to reduce cache line needs: NET_SKB_PAD + NET_IP_ALIGN bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=16626 Many thanks to Plamen Petrov, testing many debugging patches ! With help of Jarek Poplawski. Reported-by: Plamen Petrov Signed-off-by: Eric Dumazet CC: Jarek Poplawski Signed-off-by: David S. Miller --- net/core/skbuff.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3a2513f0d0c3..26396ff67cf9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2573,6 +2573,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; + /* nskb and skb might have different headroom */ + if (nskb->ip_summed == CHECKSUM_PARTIAL) + nskb->csum_start += skb_headroom(nskb) - headroom; + skb_reset_mac_header(nskb); skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + @@ -2702,8 +2706,8 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } else if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; - headroom = skb_headroom(p); - nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); + headroom = NET_SKB_PAD + NET_IP_ALIGN; + nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; -- cgit v1.2.1 From 7bcbf81a2296a8f71342445560dcbe16100b567c Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Wed, 1 Sep 2010 23:07:10 +0000 Subject: ipvs: avoid oops for passive FTP Fix Passive FTP problem in ip_vs_ftp: - Do not oops in nf_nat_set_seq_adjust (adjust_tcp_sequence) when iptable_nat module is not loaded Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/netfilter/ipvs/ip_vs_ftp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index f228a17ec649..33b329bfc2d2 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -359,7 +360,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); - if (ct && !nf_ct_is_untracked(ct)) { + if (ct && !nf_ct_is_untracked(ct) && nfct_nat(ct)) { /* If mangling fails this function will return 0 * which will cause the packet to be dropped. * Mangling can only fail under memory pressure, -- cgit v1.2.1 From 0b5d404e349c0236b11466c0a4785520c0be6982 Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Thu, 2 Sep 2010 13:22:11 -0700 Subject: pkt_sched: Fix lockdep warning on est_tree_lock in gen_estimator This patch fixes a lockdep warning: [ 516.287584] ========================================================= [ 516.288386] [ INFO: possible irq lock inversion dependency detected ] [ 516.288386] 2.6.35b #7 [ 516.288386] --------------------------------------------------------- [ 516.288386] swapper/0 just changed the state of lock: [ 516.288386] (&qdisc_tx_lock){+.-...}, at: [] est_timer+0x62/0x1b4 [ 516.288386] but this lock took another, SOFTIRQ-unsafe lock in the past: [ 516.288386] (est_tree_lock){+.+...} [ 516.288386] [ 516.288386] and interrupts could create inverse lock ordering between them. ... So, est_tree_lock needs BH protection because it's taken by qdisc_tx_lock, which is used both in BH and process contexts. (Full warning with this patch at netdev, 02 Sep 2010.) Fixes commit: ae638c47dc040b8def16d05dc6acdd527628f231 ("pkt_sched: gen_estimator: add a new lock") Signed-off-by: Jarek Poplawski Signed-off-by: David S. Miller --- net/core/gen_estimator.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 9fbe7f7429b0..6743146e4d6b 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -232,7 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, est->last_packets = bstats->packets; est->avpps = rate_est->pps<<10; - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); if (!elist[idx].timer.function) { INIT_LIST_HEAD(&elist[idx].list); setup_timer(&elist[idx].timer, est_timer, idx); @@ -243,7 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, list_add_rcu(&est->list, &elist[idx].list); gen_add_node(est); - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); return 0; } @@ -270,7 +270,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, { struct gen_estimator *e; - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); while ((e = gen_find_node(bstats, rate_est))) { rb_erase(&e->node, &est_root); @@ -281,7 +281,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, list_del_rcu(&e->list); call_rcu(&e->e_rcu, __gen_kill_estimator); } - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); } EXPORT_SYMBOL(gen_kill_estimator); @@ -320,9 +320,9 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, ASSERT_RTNL(); - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); res = gen_find_node(bstats, rate_est) != NULL; - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); return res; } -- cgit v1.2.1