From patchwork Fri Apr 20 16:19:34 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Joseph Salisbury X-Patchwork-Id: 902032 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=lists.ubuntu.com (client-ip=91.189.94.19; helo=huckleberry.canonical.com; envelope-from=kernel-team-bounces@lists.ubuntu.com; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=canonical.com Received: from huckleberry.canonical.com (huckleberry.canonical.com [91.189.94.19]) by ozlabs.org (Postfix) with ESMTP id 40SLfV3Vf8z9s5b; Sat, 21 Apr 2018 02:19:46 +1000 (AEST) Received: from localhost ([127.0.0.1] helo=huckleberry.canonical.com) by huckleberry.canonical.com with esmtp (Exim 4.86_2) (envelope-from ) id 1f9YlC-0006GH-5q; Fri, 20 Apr 2018 16:19:42 +0000 Received: from youngberry.canonical.com ([91.189.89.112]) by huckleberry.canonical.com with esmtps (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:128) (Exim 4.86_2) (envelope-from ) id 1f9Yl6-0006Ew-Ru for kernel-team@lists.ubuntu.com; Fri, 20 Apr 2018 16:19:36 +0000 Received: from 1.general.jsalisbury.us.vpn ([10.172.67.212] helo=salisbury) by youngberry.canonical.com with esmtpsa (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.76) (envelope-from ) id 1f9Yl6-0007Ck-De for kernel-team@lists.ubuntu.com; Fri, 20 Apr 2018 16:19:36 +0000 Received: by salisbury (Postfix, from userid 1000) id 4329E7E08D8; Fri, 20 Apr 2018 12:19:35 -0400 (EDT) From: Joseph Salisbury To: kernel-team@lists.ubuntu.com Subject: [SRU][Artful][PATCH 1/2] ipv4: convert dst_metrics.refcnt from atomic_t to refcount_t Date: Fri, 20 Apr 2018 12:19:34 -0400 Message-Id: X-Mailer: git-send-email 2.7.4 In-Reply-To: References: In-Reply-To: References: X-BeenThere: kernel-team@lists.ubuntu.com X-Mailman-Version: 2.1.20 Precedence: list List-Id: Kernel team discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Errors-To: kernel-team-bounces@lists.ubuntu.com Sender: "kernel-team" From: Eric Dumazet BugLink: http://bugs.launchpad.net/bugs/1746474 refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller (cherry picked from commit 9620fef27ed2cdb37bf6fd028f32bea2ef5119a8) Signed-off-by: Joseph Salisbury --- include/net/dst.h | 3 ++- net/core/dst.c | 6 +++--- net/ipv4/fib_semantics.c | 4 ++-- net/ipv4/route.c | 4 ++-- 4 files changed, 9 insertions(+), 8 deletions(-) diff --git a/include/net/dst.h b/include/net/dst.h index f73611e..93568bd 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -107,7 +108,7 @@ struct dst_entry { struct dst_metrics { u32 metrics[RTAX_MAX]; - atomic_t refcnt; + refcount_t refcnt; }; extern const struct dst_metrics dst_default_metrics; diff --git a/net/core/dst.c b/net/core/dst.c index 00aa972..d6ead75 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -55,7 +55,7 @@ const struct dst_metrics dst_default_metrics = { * We really want to avoid false sharing on this variable, and catch * any writes on it. */ - .refcnt = ATOMIC_INIT(1), + .refcnt = REFCOUNT_INIT(1), }; void dst_init(struct dst_entry *dst, struct dst_ops *ops, @@ -213,7 +213,7 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); unsigned long prev, new; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 1); memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); new = (unsigned long) p; @@ -225,7 +225,7 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) if (prev & DST_METRICS_READ_ONLY) p = NULL; } else if (prev & DST_METRICS_REFCOUNTED) { - if (atomic_dec_and_test(&old_p->refcnt)) + if (refcount_dec_and_test(&old_p->refcnt)) kfree(old_p); } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ec3a9ce..a663c09 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -219,7 +219,7 @@ static void free_fib_info_rcu(struct rcu_head *head) } endfor_nexthops(fi); m = fi->fib_metrics; - if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt)) + if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) kfree(m); kfree(fi); } @@ -1089,7 +1089,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, kfree(fi); return ERR_PTR(err); } - atomic_set(&fi->fib_metrics->refcnt, 1); + refcount_set(&fi->fib_metrics->refcnt, 1); } else { fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 72afa4c..83a2c494 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1398,7 +1398,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst) struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rtable *rt = (struct rtable *) dst; - if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt)) + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) kfree(p); if (!list_empty(&rt->rt_uncached)) { @@ -1456,7 +1456,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true); if (fi->fib_metrics != &dst_default_metrics) { rt->dst._metrics |= DST_METRICS_REFCOUNTED; - atomic_inc(&fi->fib_metrics->refcnt); + refcount_inc(&fi->fib_metrics->refcnt); } #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; From patchwork Fri Apr 20 16:19:35 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Joseph Salisbury X-Patchwork-Id: 902030 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=lists.ubuntu.com (client-ip=91.189.94.19; helo=huckleberry.canonical.com; envelope-from=kernel-team-bounces@lists.ubuntu.com; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=canonical.com Received: from huckleberry.canonical.com (huckleberry.canonical.com [91.189.94.19]) by ozlabs.org (Postfix) with ESMTP id 40SLfT1267z9s1p; Sat, 21 Apr 2018 02:19:45 +1000 (AEST) Received: from localhost ([127.0.0.1] helo=huckleberry.canonical.com) by huckleberry.canonical.com with esmtp (Exim 4.86_2) (envelope-from ) id 1f9Yl9-0006FS-0a; Fri, 20 Apr 2018 16:19:39 +0000 Received: from youngberry.canonical.com ([91.189.89.112]) by huckleberry.canonical.com with esmtps (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:128) (Exim 4.86_2) (envelope-from ) id 1f9Yl6-0006Ev-RZ for kernel-team@lists.ubuntu.com; Fri, 20 Apr 2018 16:19:36 +0000 Received: from 1.general.jsalisbury.us.vpn ([10.172.67.212] helo=salisbury) by youngberry.canonical.com with esmtpsa (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.76) (envelope-from ) id 1f9Yl6-0007Cl-Db for kernel-team@lists.ubuntu.com; Fri, 20 Apr 2018 16:19:36 +0000 Received: by salisbury (Postfix, from userid 1000) id 44C6F7E256E; Fri, 20 Apr 2018 12:19:35 -0400 (EDT) From: Joseph Salisbury To: kernel-team@lists.ubuntu.com Subject: [SRU][Artful][PATCH 2/2] xfrm: reuse uncached_list to track xdsts Date: Fri, 20 Apr 2018 12:19:35 -0400 Message-Id: X-Mailer: git-send-email 2.7.4 In-Reply-To: References: In-Reply-To: References: X-BeenThere: kernel-team@lists.ubuntu.com X-Mailman-Version: 2.1.20 Precedence: list List-Id: Kernel team discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Errors-To: kernel-team-bounces@lists.ubuntu.com Sender: "kernel-team" From: Xin Long BugLink: http://bugs.launchpad.net/bugs/1746474 In early time, when freeing a xdst, it would be inserted into dst_garbage.list first. Then if it's refcnt was still held somewhere, later it would be put into dst_busy_list in dst_gc_task(). When one dev was being unregistered, the dev of these dsts in dst_busy_list would be set with loopback_dev and put this dev. So that this dev's removal wouldn't get blocked, and avoid the kmsg warning: kernel:unregister_netdevice: waiting for veth0 to become \ free. Usage count = 2 However after Commit 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle"), the xdst will not be freed with dst gc, and this warning happens. To fix it, we need to find these xdsts that are still held by others when removing the dev, and free xdst's dev and set it with loopback_dev. But unfortunately after flow_cache for xfrm was deleted, no list tracks them anymore. So we need to save these xdsts somewhere to release the xdst's dev later. To make this easier, this patch is to reuse uncached_list to track xdsts, so that the dev refcnt can be released in the event NETDEV_UNREGISTER process of fib_netdev_notifier. Thanks to Florian, we could move forward this fix quickly. Fixes: 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle") Reported-by: Jianlin Shi Reported-by: Hangbin Liu Tested-by: Eyal Birger Signed-off-by: Xin Long Signed-off-by: Steffen Klassert (back ported from commit 510c321b557121861601f9d259aadd65aa274f35) Signed-off-by: Joseph Salisbury --- include/net/ip6_fib.h | 2 ++ include/net/ip6_route.h | 13 +++++++++++++ include/net/route.h | 3 +++ net/ipv4/route.c | 21 +++++++++++++-------- net/ipv4/xfrm4_policy.c | 4 +++- net/ipv6/route.c | 4 ++-- net/ipv6/xfrm6_policy.c | 5 +++++ 7 files changed, 41 insertions(+), 11 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index af509f8..8e1d61b 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -242,6 +242,8 @@ struct rt6_statistics { __u32 fib_rt_entries; /* rt entries in table */ __u32 fib_rt_cache; /* cache routes */ __u32 fib_discarded_routes; + /* The following stats are not protected by any lock */ + atomic_t fib_rt_uncache; /* rt entries in uncached list */ }; #define RTN_TL_ROOT 0x0001 diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 1990569..f37ea3e 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -163,6 +163,19 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); +void rt6_uncached_list_add(struct rt6_info *rt); +void rt6_uncached_list_del(struct rt6_info *rt); + +static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) +{ + const struct dst_entry *dst = skb_dst(skb); + const struct rt6_info *rt6 = NULL; + + if (dst) + rt6 = container_of(dst, struct rt6_info, dst); + + return rt6; +} /* * Store a destination cache entry in a socket diff --git a/include/net/route.h b/include/net/route.h index 5845896..09a3507 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -226,6 +226,9 @@ struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); +void rt_add_uncached_list(struct rtable *rt); +void rt_del_uncached_list(struct rtable *rt); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 83a2c494..33db041 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1382,7 +1382,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); -static void rt_add_uncached_list(struct rtable *rt) +void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); @@ -1393,14 +1393,8 @@ static void rt_add_uncached_list(struct rtable *rt) spin_unlock_bh(&ul->lock); } -static void ipv4_dst_destroy(struct dst_entry *dst) +void rt_del_uncached_list(struct rtable *rt) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); - struct rtable *rt = (struct rtable *) dst; - - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1410,6 +1404,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst) } } +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *)dst; + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + + rt_del_uncached_list(rt); +} + void rt_flush_dev(struct net_device *dev) { struct net *net = dev_net(dev); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 71b4ecc1..cb9890a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -97,6 +97,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + rt_add_uncached_list(&xdst->u.rt); return 0; } @@ -244,7 +245,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); - + if (xdst->u.rt.rt_uncached_list) + rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d00e41c..6062c65 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -124,7 +124,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); -static void rt6_uncached_list_add(struct rt6_info *rt) +void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@ -135,7 +135,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt) spin_unlock_bh(&ul->lock); } -static void rt6_uncached_list_del(struct rt6_info *rt) +void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 79651bc..7a6191c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -109,6 +109,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; + INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + rt6_uncached_list_add(&xdst->u.rt6); + atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } @@ -247,6 +250,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); + if (xdst->u.rt6.rt6i_uncached_list) + rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); }