From 779e2445a64e462c9717dd2a51ea6b3ead5bda29 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:47 -0800 Subject: [PATCH 1/9] refcount: provide ops for cases when object's memory can be reused mainline inclusion from mainline-v6.15-rc1 commit 7f8ceea0c58039dcea3d31b8d5da58aa5f6e12bf category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/21180 CVE: CVE-2026-99288 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=7f8ceea0c58039dcea3d31b8d5da58aa5f6e12bf -------------------------------- For speculative lookups where a successful inc_not_zero() pins the object, but where we still need to double check if the object acquired is indeed the one we set out to acquire (identity check), needs this validation to happen *after* the increment. Similarly, when a new object is initialized and its memory might have been previously occupied by another object, all stores to initialize the object should happen *before* refcount initialization. Notably SLAB_TYPESAFE_BY_RCU is one such an example when this ordering is required for reference counting. Add refcount_{add|inc}_not_zero_acquire() to guarantee the proper ordering between acquiring a reference count on an object and performing the identity check for that object. Add refcount_set_release() to guarantee proper ordering between stores initializing object attributes and the store initializing the refcount. refcount_set_release() should be done after all other object attributes are initialized. Once refcount_set_release() is called, the object should be considered visible to other tasks even if it was not yet added into an object collection normally used to discover it. This is because other tasks might have discovered the object previously occupying the same memory and after memory reuse they can succeed in taking refcount for the new object and start using it. Object reuse example to consider: consumer: obj = lookup(collection, key); if (!refcount_inc_not_zero_acquire(&obj->ref)) return; if (READ_ONCE(obj->key) != key) { /* identity check */ put_ref(obj); return; } use(obj->value); producer: remove(collection, obj->key); if (!refcount_dec_and_test(&obj->ref)) return; obj->key = KEY_INVALID; free(obj); obj = malloc(); /* obj is reused */ obj->key = new_key; obj->value = new_value; refcount_set_release(obj->ref, 1); add(collection, new_key, obj); refcount_{add|inc}_not_zero_acquire() is required to prevent the following reordering when refcount_inc_not_zero() is used instead: consumer: obj = lookup(collection, key); if (READ_ONCE(obj->key) != key) { /* reordered identity check */ put_ref(obj); return; } producer: remove(collection, obj->key); if (!refcount_dec_and_test(&obj->ref)) return; obj->key = KEY_INVALID; free(obj); obj = malloc(); /* obj is reused */ obj->key = new_key; obj->value = new_value; refcount_set_release(obj->ref, 1); add(collection, new_key, obj); if (!refcount_inc_not_zero(&obj->ref)) return; use(obj->value); /* USING WRONG OBJECT */ refcount_set_release() is required to prevent the following reordering when refcount_set() is used instead: consumer: obj = lookup(collection, key); producer: remove(collection, obj->key); if (!refcount_dec_and_test(&obj->ref)) return; obj->key = KEY_INVALID; free(obj); obj = malloc(); /* obj is reused */ obj->key = new_key; /* new_key == old_key */ refcount_set(obj->ref, 1); if (!refcount_inc_not_zero_acquire(&obj->ref)) return; if (READ_ONCE(obj->key) != key) { /* pass since new_key == old_key */ put_ref(obj); return; } use(obj->value); /* USING STALE obj->value */ obj->value = new_value; /* reordered store */ add(collection, key, obj); [surenb@google.com: fix title underlines in refcount-vs-atomic.rst] Link: https://lkml.kernel.org/r/20250217161645.3137927-1-surenb@google.com Link: https://lkml.kernel.org/r/20250213224655.1680278-11-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Vlastimil Babka [slab] Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Cc: Peter Zijlstra Cc: Will Deacon Cc: Paul E. McKenney Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Liam R. Howlett Cc: Lokesh Gidra Cc: Lorenzo Stoakes Cc: Mateusz Guzik Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: Peter Xu Cc: Shakeel Butt Cc: Sourav Panda Cc: Wei Yang Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton Conflicts: Documentation/RCU/whatisRCU.rst include/linux/refcount.h [Keep the 6.6 documentation wording and drop __signed_wrap, which is not available in this tree.] Stable-dep-of: c9341307ea16 ("RDMA/mlx4: Fix mis-use of RCU in mlx4_srq_event()") Signed-off-by: Sasha Levin (cherry picked from commit 82290418744d1368d02c5f082350d80c07870808) Signed-off-by: Wentao Guan --- Documentation/RCU/whatisRCU.rst | 10 ++ Documentation/core-api/refcount-vs-atomic.rst | 37 +++++- include/linux/refcount.h | 106 ++++++++++++++++++ include/linux/slab.h | 9 ++ 4 files changed, 156 insertions(+), 6 deletions(-) diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst index e488c8e557a9c..0e0eb4c65a600 100644 --- a/Documentation/RCU/whatisRCU.rst +++ b/Documentation/RCU/whatisRCU.rst @@ -952,6 +952,16 @@ unfortunately any spinlock in a ``SLAB_TYPESAFE_BY_RCU`` object must be initialized after each and every call to kmem_cache_alloc(), which renders reference-free spinlock acquisition completely unsafe. Therefore, when using ``SLAB_TYPESAFE_BY_RCU``, make proper use of a reference counter. +If using refcount_t, the specialized refcount_{add|inc}_not_zero_acquire() +and refcount_set_release() APIs should be used to ensure correct operation +ordering when verifying object identity and when initializing newly +allocated objects. Acquire fence in refcount_{add|inc}_not_zero_acquire() +ensures that identity checks happen *after* reference count is taken. +refcount_set_release() should be called after a newly allocated object is +fully initialized and release fence ensures that new values are visible +*before* refcount can be successfully taken by other users. Once +refcount_set_release() is called, the object should be considered visible +by other tasks. (Those willing to use a kmem_cache constructor may also use locking, including cache-friendly sequence locking.) diff --git a/Documentation/core-api/refcount-vs-atomic.rst b/Documentation/core-api/refcount-vs-atomic.rst index 79a009ce11df9..94e628c1eb497 100644 --- a/Documentation/core-api/refcount-vs-atomic.rst +++ b/Documentation/core-api/refcount-vs-atomic.rst @@ -86,7 +86,19 @@ Memory ordering guarantee changes: * none (both fully unordered) -case 2) - increment-based ops that return no value +case 2) - non-"Read/Modify/Write" (RMW) ops with release ordering +----------------------------------------------------------------- + +Function changes: + + * atomic_set_release() --> refcount_set_release() + +Memory ordering guarantee changes: + + * none (both provide RELEASE ordering) + + +case 3) - increment-based ops that return no value -------------------------------------------------- Function changes: @@ -98,7 +110,7 @@ Memory ordering guarantee changes: * none (both fully unordered) -case 3) - decrement-based RMW ops that return no value +case 4) - decrement-based RMW ops that return no value ------------------------------------------------------ Function changes: @@ -110,7 +122,7 @@ Memory ordering guarantee changes: * fully unordered --> RELEASE ordering -case 4) - increment-based RMW ops that return a value +case 5) - increment-based RMW ops that return a value ----------------------------------------------------- Function changes: @@ -126,7 +138,20 @@ Memory ordering guarantees changes: result of obtaining pointer to the object! -case 5) - generic dec/sub decrement-based RMW ops that return a value +case 6) - increment-based RMW ops with acquire ordering that return a value +--------------------------------------------------------------------------- + +Function changes: + + * atomic_inc_not_zero() --> refcount_inc_not_zero_acquire() + * no atomic counterpart --> refcount_add_not_zero_acquire() + +Memory ordering guarantees changes: + + * fully ordered --> ACQUIRE ordering on success + + +case 7) - generic dec/sub decrement-based RMW ops that return a value --------------------------------------------------------------------- Function changes: @@ -139,7 +164,7 @@ Memory ordering guarantees changes: * fully ordered --> RELEASE ordering + ACQUIRE ordering on success -case 6) other decrement-based RMW ops that return a value +case 8) other decrement-based RMW ops that return a value --------------------------------------------------------- Function changes: @@ -154,7 +179,7 @@ Memory ordering guarantees changes: .. note:: atomic_add_unless() only provides full order on success. -case 7) - lock-based RMW +case 9) - lock-based RMW ------------------------ Function changes: diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 85c6df0d1bef4..167aaa45a3961 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -87,6 +87,15 @@ * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * + * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() provide + * acquire and release ordering for cases when the memory occupied by the + * object might be reused to store another object. This is important for the + * cases where secondary validation is required to detect such reuse, e.g. + * SLAB_TYPESAFE_BY_RCU. The secondary validation checks have to happen after + * the refcount is taken, hence acquire order is necessary. Similarly, when the + * object is initialized, all stores to its attributes should be visible before + * the refcount is set, otherwise a stale attribute value might be used by + * another task which succeeds in taking a refcount to the new object. */ #ifndef _LINUX_REFCOUNT_H @@ -125,6 +134,31 @@ static inline void refcount_set(refcount_t *r, int n) atomic_set(&r->refs, n); } +/** + * refcount_set_release - set a refcount's value with release ordering + * @r: the refcount + * @n: value to which the refcount will be set + * + * This function should be used when memory occupied by the object might be + * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. + * + * Provides release memory ordering which will order previous memory operations + * against this store. This ensures all updates to this object are visible + * once the refcount is set and stale values from the object previously + * occupying this memory are overwritten with new ones. + * + * This function should be called only after new object is fully initialized. + * After this call the object should be considered visible to other tasks even + * if it was not yet added into an object collection normally used to discover + * it. This is because other tasks might have discovered the object previously + * occupying the same memory and after memory reuse they can succeed in taking + * refcount to the new object and start using it. + */ +static inline void refcount_set_release(refcount_t *r, int n) +{ + atomic_set_release(&r->refs, n); +} + /** * refcount_read - get a refcount's value * @r: the refcount @@ -177,6 +211,52 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) return __refcount_add_not_zero(i, r, NULL); } +static inline __must_check bool +__refcount_add_not_zero_acquire(int i, refcount_t *r, int *oldp) +{ + int old = refcount_read(r); + + do { + if (!old) + break; + } while (!atomic_try_cmpxchg_acquire(&r->refs, &old, old + i)); + + if (oldp) + *oldp = old; + + if (unlikely(old < 0 || old + i < 0)) + refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); + + return old; +} + +/** + * refcount_add_not_zero_acquire - add a value to a refcount with acquire ordering unless it is 0 + * + * @i: the value to add to the refcount + * @r: the refcount + * + * Will saturate at REFCOUNT_SATURATED and WARN. + * + * This function should be used when memory occupied by the object might be + * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. + * + * Provides acquire memory ordering on success, it is assumed the caller has + * guaranteed the object memory to be stable (RCU, etc.). It does provide a + * control dependency and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc_not_zero_acquire() should instead be used to increment a + * reference count. + * + * Return: false if the passed refcount is 0, true otherwise + */ +static inline __must_check bool refcount_add_not_zero_acquire(int i, refcount_t *r) +{ + return __refcount_add_not_zero_acquire(i, r, NULL); +} + static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); @@ -234,6 +314,32 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) return __refcount_inc_not_zero(r, NULL); } +static inline __must_check bool __refcount_inc_not_zero_acquire(refcount_t *r, int *oldp) +{ + return __refcount_add_not_zero_acquire(1, r, oldp); +} + +/** + * refcount_inc_not_zero_acquire - increment a refcount with acquire ordering unless it is 0 + * @r: the refcount to increment + * + * Similar to refcount_inc_not_zero(), but provides acquire memory ordering on + * success. + * + * This function should be used when memory occupied by the object might be + * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. + * + * Provides acquire memory ordering on success, it is assumed the caller has + * guaranteed the object memory to be stable (RCU, etc.). It does provide a + * control dependency and thereby orders future stores. See the comment on top. + * + * Return: true if the increment was successful, false otherwise + */ +static inline __must_check bool refcount_inc_not_zero_acquire(refcount_t *r) +{ + return __refcount_inc_not_zero_acquire(r, NULL); +} + static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); diff --git a/include/linux/slab.h b/include/linux/slab.h index a761cc3559f29..579523c3135b6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -81,6 +81,15 @@ * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * + * Note that object identity check has to be done *after* acquiring a + * reference, therefore user has to ensure proper ordering for loads. + * Similarly, when initializing objects allocated with SLAB_TYPESAFE_BY_RCU, + * the newly allocated object has to be fully initialized *before* its + * refcount gets initialized and proper ordering for stores is required. + * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() are + * designed with the proper fences required for reference counting objects + * allocated with SLAB_TYPESAFE_BY_RCU. + * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages From eea9d29885294324fd69c202dce7e90d62046375 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 6 May 2026 03:59:18 +0000 Subject: [PATCH 2/9] tcp: Fix potential UAF in reqsk_timer_handler(). mainline inclusion from mainline-v7.1-rc4 commit 97c8a3c1f73d828de43a5a88e8a9a143efb2b661 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/21112 CVE: CVE-2026-99270 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=97c8a3c1f73d828de43a5a88e8a9a143efb2b661 -------------------------------- When TCP socket migration fails at inet_ehash_insert() in reqsk_timer_handler(), we jump to the no_ownership: label and free the new reqsk immediately with __reqsk_free(). Thus, we must stop the new reqsk's timer before jumping to the label, but the timer might be missed since the cited commit, resulting in UAF. As we are in the original reqsk's timer context, we can safely call timer_delete_sync() for the new reqsk. Let's pass false to __inet_csk_reqsk_queue_drop() to stop the new reqsk's timer. Fixes: 83fccfc3940c ("inet: fix potential deadlock in reqsk_queue_unlink()") Reported-by: Damiano Melotti Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260506035954.1563147-2-kuniyu@google.com Signed-off-by: Jakub Kicinski (cherry picked from commit 97c8a3c1f73d828de43a5a88e8a9a143efb2b661) Signed-off-by: Wentao Guan --- net/ipv4/inet_connection_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c7466ba00b337..60f72bbe1a379 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1095,7 +1095,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ - __inet_csk_reqsk_queue_drop(sk_listener, nreq, true); + __inet_csk_reqsk_queue_drop(sk_listener, nreq, false); goto no_ownership; } From 8b66449157486ae388fbee37696fd14b52ae2640 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Fri, 30 Oct 2026 06:42:16 +0900 Subject: [PATCH 3/9] inet: reject unhashed sockets during established lookups mainline inclusion from mainline-v7.4-rc2 commit 4e2b3ef19e0e04adca38442f07dd6bc93c712bf1 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/21180 CVE: CVE-2026-99288 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=4e2b3ef19e0e04adca38442f07dd6bc93c712bf1 -------------------------------- TCP established ehash lookups are lockless. The socket caches involved use SLAB_TYPESAFE_BY_RCU, so memory can be reused before an RCU reader that retained its old address has finished. After a tuple match, __inet_lookup_established() and __inet6_lookup_established() acquire a reference and repeat the tuple check. They do not check whether the new object is hashed. If the address is reused for a socket with the same tuple, the lookup can acquire a reference to the new object and return it while its nulls node is unhashed. A PoC that drives reuse with a SYN cookie request socket reproduced the crash. The new request socket is unhashed and has a NULL rsk_listener. A lookup that had loaded the address of the old request socket acquired the reference published by tcp_get_cookie_sock() and returned the new object. tcp_v4_rcv() then read sk_state through the NULL listener. The resulting crash was: BUG: kernel NULL pointer dereference, address: 0000000000000012 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page ... Oops: Oops: 0000 [#1] SMP NOPTI CPU: 4 UID: 0 PID: 0 Comm: swapper/4 Not tainted 7.3.0-00591-g0e135910deec #1 PREEMPT(lazy) ... RIP: 0010:tcp_v4_rcv+0x44e/0x1280 ... R10: 0000000000000001 R11: 00000000024ca8c0 R12: 0000000000000000 ... CR2: 0000000000000012 CR3: 0000000103d50004 CR4: 0000000000770ef0 ... Call Trace: ? raw_local_deliver+0xae/0x240 ip_protocol_deliver_rcu+0x2d/0x180 ip_local_deliver_finish+0x84/0x100 ip_sublist_rcv_finish+0x5f/0x70 ip_sublist_rcv+0x12a/0x1d0 ip_list_rcv+0xfd/0x130 __netif_receive_skb_list_core+0x223/0x250 netif_receive_skb_list_internal+0x1d2/0x2c0 ? try_fill_recv+0x39/0x7b0 napi_complete_done+0x74/0x170 virtnet_poll+0x445/0x600 __napi_poll+0x27/0x1e0 net_rx_action+0x2fe/0x3b0 handle_softirqs+0xc2/0x2c0 __irq_exit_rcu+0x74/0xd0 common_interrupt+0x7f/0x90 ... Kernel panic - not syncing: Fatal exception in interrupt After taking a reference, check whether the nulls node is unhashed in both IPv4 and IPv6 established lookups. If it is unhashed or the tuple no longer matches, drop the reference and restart the lookup. Lookups racing with the TIME_WAIT hashdance, or with a request being replaced by its child, now restart and find the new socket instead of returning the old one. Request sockets that were never inserted into ehash can have a nonzero refcount, and a stale lookup can hold a transient reference. Therefore, when SYN cookie, Fast Open, and request migration paths fail after setting a nonzero refcount, release the references held by those paths with reqsk_put() instead of freeing the request directly. Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Cc: stable@vger.kernel.org Signed-off-by: Hyunwoo Kim Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20261029214219.1035176-2-imv4bel@gmail.com Signed-off-by: Paolo Abeni Co-authored-by: BackportAgent@deepseek-v4.1-flash Signed-off-by: Hulk Robot Signed-off-by: openeuler-ci-bot Signed-off-by: Wentao Guan --- net/ipv4/inet_connection_sock.c | 10 +++++++--- net/ipv4/inet_hashtables.c | 5 +++-- net/ipv4/syncookies.c | 2 ++ net/ipv4/tcp_input.c | 4 +++- net/ipv6/inet6_hashtables.c | 4 +++- 5 files changed, 18 insertions(+), 7 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 60f72bbe1a379..8a23a6e91cb3e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1114,10 +1114,14 @@ static void reqsk_timer_handler(struct timer_list *t) */ if (nreq) { __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE); + /* The timer was not armed, drop its reference here. */ + reqsk_put(nreq); no_ownership: reqsk_migrate_reset(nreq); reqsk_queue_removed(queue, nreq); - __reqsk_free(nreq); + /* Drop the temporary reference and the one reserved for ehash. */ + reqsk_put(nreq); + reqsk_put(nreq); } drop: @@ -1398,7 +1402,7 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); - __reqsk_free(nreq); + reqsk_put(nreq); } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; } @@ -1454,7 +1458,7 @@ void inet_csk_listen_stop(struct sock *sk) __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); - __reqsk_free(nreq); + reqsk_put(nreq); } rcu_read_unlock(); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 560327bbf95d1..4d8309bfa2d10 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -513,8 +513,9 @@ struct sock *__inet_lookup_established(struct net *net, if (likely(inet_match(net, sk, acookie, ports, dif, sdif))) { if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; - if (unlikely(!inet_match(net, sk, acookie, - ports, dif, sdif))) { + if (unlikely(hlist_nulls_unhashed_lockless(&sk->sk_nulls_node) || + !inet_match(net, sk, acookie, ports, dif, + sdif))) { sock_gen_put(sk); goto begin; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 349e96d029c3d..3140c7742b30f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -215,6 +215,8 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, bh_unlock_sock(child); sock_put(child); + reqsk_put(req); + return NULL; } __reqsk_free(req); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ed5e0101c04f2..aa39e9ec7ef74 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7279,7 +7279,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); - goto drop_and_free; + /* tcp_disconnect() already dropped one reqsk ref. */ + reqsk_put(req); + goto drop; } READ_ONCE(sk->sk_data_ready)(sk); bh_unlock_sock(fastopen_sk); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b72ebbd65f8d9..1d0d94c6c582f 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -75,7 +75,9 @@ struct sock *__inet6_lookup_established(struct net *net, if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; - if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) { + if (unlikely(hlist_nulls_unhashed_lockless(&sk->sk_nulls_node) || + !inet6_match(net, sk, saddr, daddr, ports, dif, + sdif))) { sock_gen_put(sk); goto begin; } From 6354e8e299505453946668cda294a09acfdbf405 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Fri, 30 Oct 2026 06:42:17 +0900 Subject: [PATCH 4/9] net: restore refcount ordering for lockless socket access mainline inclusion from mainline-v7.4-rc2 commit 5b5d8f351dd96f56a58bb516a80e2d4d742fe4e2 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/21180 CVE: CVE-2026-99288 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=5b5d8f351dd96f56a58bb516a80e2d4d742fe4e2 -------------------------------- Before commit fb041bb7c0a9 ("locking/refcount: Consolidate implementations of refcount_t"), default builds implemented refcount_inc_not_zero() using atomic_add_unless(), which provided full memory ordering on success. The commit removed that ordering on weakly ordered architectures, allowing accesses after a successful reference acquisition to be reordered before it. Use refcount_inc_not_zero_acquire() in the IPv4 and IPv6 established lookups and in inet_twsk_purge(), where the socket is validated again after taking a reference. bpf_sk_assign() can receive a socket pointer obtained through BTF without a reference. Use acquire ordering when it takes its own reference for a refcounted socket. Use refcount_set_release() when setting refcounts in the SYN cookie, TCP Fast Open, request migration, and TIME_WAIT paths. Keep the existing TIME_WAIT smp_wmb(), which separately orders the refcount store before ehash publication. Conflicts: net/ipv4/inet_timewait_sock.c net/ipv4/syncookies.c [Keep the 6.6 inet_twsk_hashdance() structure and the existing tsoffset assignment. Also keep timer_setup() before refcount_set_release() in the request migration path.] Fixes: fb041bb7c0a9 ("locking/refcount: Consolidate implementations of refcount_t") Fixes: 27e5203bd9c5 ("bpf: Change bpf_sk_assign to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON") Cc: stable@vger.kernel.org Signed-off-by: Hyunwoo Kim Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20261029214219.1035176-3-imv4bel@gmail.com Signed-off-by: Paolo Abeni (cherry picked from commit 5b5d8f351dd96f56a58bb516a80e2d4d742fe4e2) Signed-off-by: Wentao Guan --- net/core/filter.c | 2 +- net/ipv4/inet_connection_sock.c | 6 +++--- net/ipv4/inet_hashtables.c | 2 +- net/ipv4/inet_timewait_sock.c | 4 ++-- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_fastopen.c | 2 +- net/ipv6/inet6_hashtables.c | 2 +- 7 files changed, 10 insertions(+), 10 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 4dc79ea65eb81..f40d4877826fb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7555,7 +7555,7 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && - unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + unlikely(!refcount_inc_not_zero_acquire(&sk->sk_refcnt))) return -ENOENT; skb_orphan(skb); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8a23a6e91cb3e..bd11f7da96f0e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1038,8 +1038,8 @@ static void reqsk_timer_handler(struct timer_list *t) * hold another count to prevent use-after-free and * call reqsk_put() just before return. */ - refcount_set(&nreq->rsk_refcnt, 2 + 1); timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); + refcount_set_release(&nreq->rsk_refcnt, 2 + 1); reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); req = nreq; @@ -1392,7 +1392,7 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, goto child_put; } - refcount_set(&nreq->rsk_refcnt, 1); + refcount_set_release(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(sk, nreq, child)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); @@ -1446,7 +1446,7 @@ void inet_csk_listen_stop(struct sock *sk) if (nsk) { nreq = inet_reqsk_clone(req, nsk); if (nreq) { - refcount_set(&nreq->rsk_refcnt, 1); + refcount_set_release(&nreq->rsk_refcnt, 1); rcu_read_lock(); if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 4d8309bfa2d10..d9c6fc892e68f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -511,7 +511,7 @@ struct sock *__inet_lookup_established(struct net *net, if (sk->sk_hash != hash) continue; if (likely(inet_match(net, sk, acookie, ports, dif, sdif))) { - if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero_acquire(&sk->sk_refcnt))) goto out; if (unlikely(hlist_nulls_unhashed_lockless(&sk->sk_nulls_node) || !inet_match(net, sk, acookie, ports, dif, diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index aa4fd34f30b23..6f5f15988b91b 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -146,7 +146,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * Also note that after this point, we lost our implicit reference * so we are not allowed to use tw anymore. */ - refcount_set(&tw->tw_refcnt, 3); + refcount_set_release(&tw->tw_refcnt, 3); } EXPORT_SYMBOL_GPL(inet_twsk_hashdance); @@ -290,7 +290,7 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo) if (refcount_read(&sock_net(sk)->ns.count)) continue; - if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero_acquire(&sk->sk_refcnt))) continue; if (refcount_read(&sock_net(sk)->ns.count)) { diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3140c7742b30f..9cc61b9eb488e 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -201,7 +201,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, NULL, &own_req, NULL); if (child) { - refcount_set(&req->rsk_refcnt, 1); + refcount_set_release(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index d36a1ceb75101..82ff794cae2a8 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -278,7 +278,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, req->timeout, TCP_RTO_MAX); - refcount_set(&req->rsk_refcnt, 2); + refcount_set_release(&req->rsk_refcnt, 2); sk_mark_napi_id_set(child, skb); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1d0d94c6c582f..c33ef953a6eb6 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -72,7 +72,7 @@ struct sock *__inet6_lookup_established(struct net *net, continue; if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif)) continue; - if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero_acquire(&sk->sk_refcnt))) goto out; if (unlikely(hlist_nulls_unhashed_lockless(&sk->sk_nulls_node) || From 934e0d412fcb3ea58df38f607e5e6e3f02c21508 Mon Sep 17 00:00:00 2001 From: Wentao Guan Date: Wed, 18 Nov 2026 18:17:12 +0800 Subject: [PATCH 5/9] tcp: cancel cloned request timers without waiting maillist inclusion category: bugfix When a cloned request is migrated again, its timer has the same lockdep class as the running request callback. Using timer_delete_sync() through __inet_csk_reqsk_queue_drop(..., false) can therefore trigger a recursive-locking splat and disable lockdep. The clone is unhashed when inet_ehash_insert() fails, so reqsk_queue_unlink() is a no-op. Its timer is pinned to the current CPU, allowing it to be cancelled without waiting for its callback. Use timer_delete() and drop the timer reference directly instead of synchronously deleting it through the queue helper. This change depends on the request lifetime changes in commit 4e2b3ef19e0e ("inet: reject unhashed sockets during established lookups") Without them, __reqsk_free() frees nreq immediately and the pending timer can still trigger a UAF. Link: https://lore.kernel.org/all/72918C6B4A6E0CC7+20261120040954.57832-2-guanwentao@uniontech.com/ Signed-off-by: Wentao Guan --- net/ipv4/inet_connection_sock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index bd11f7da96f0e..707c0e5e4f1fc 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1094,8 +1094,8 @@ static void reqsk_timer_handler(struct timer_list *t) return; if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { - /* delete timer */ - __inet_csk_reqsk_queue_drop(sk_listener, nreq, false); + if (timer_delete(&nreq->rsk_timer)) + reqsk_put(nreq); goto no_ownership; } From 739545ad518a4f7a882b698e10aa4ec32564a8fc Mon Sep 17 00:00:00 2001 From: Wentao Guan Date: Wed, 18 Nov 2026 18:17:12 +0800 Subject: [PATCH 6/9] inet: reject unhashed sockets during timewait purge maillist inclusion category: bugfix A shared ehash can retain a stale pointer that is recycled as an unhashed SYN-cookie request from another dead namespace. The namespace recheck alone accepts that request, and inet_csk_reqsk_queue_drop_and_put() then operates on an uninitialized timer and a NULL listener. Recheck the nulls node after taking the reference. If it is unhashed, drop the reference and restart the purge instead of operating on the recycled request. Link: https://lore.kernel.org/all/1595ACC3A3D11BB8+20261119041113.3514099-2-guanwentao@uniontech.com/ Fixes: 4e2b3ef19e0e ("inet: reject unhashed sockets during established lookups") Signed-off-by: Wentao Guan --- net/ipv4/inet_timewait_sock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 6f5f15988b91b..d7d95c217fccc 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -293,7 +293,8 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo) if (unlikely(!refcount_inc_not_zero_acquire(&sk->sk_refcnt))) continue; - if (refcount_read(&sock_net(sk)->ns.count)) { + if (unlikely(hlist_nulls_unhashed_lockless(&sk->sk_nulls_node) || + refcount_read(&sock_net(sk)->ns.count))) { sock_gen_put(sk); goto restart; } From 8a6c7f4a6aac3ccec1dfcfdadf6d18626e12f7cd Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 6 Jun 2024 17:11:37 +0200 Subject: [PATCH 7/9] net: tcp/dccp: prepare for tw_timer un-pinning mainline inclusion from mainline-v6.11-rc1 commit b334b924c9b709bc969644fb5c406f5c9d01dceb category: bugfix Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b334b924c9b709bc969644fb5c406f5c9d01dceb -------------------------------- The TCP timewait timer is proving to be problematic for setups where scheduler CPU isolation is achieved at runtime via cpusets (as opposed to statically via isolcpus=domains). What happens there is a CPU goes through tcp_time_wait(), arming the time_wait timer, then gets isolated. TCP_TIMEWAIT_LEN later, the timer fires, causing interference for the now-isolated CPU. This is conceptually similar to the issue described in commit e02b93124855 ("workqueue: Unbind kworkers before sending them to exit()") Move inet_twsk_schedule() to within inet_twsk_hashdance(), with the ehash lock held. Expand the lock's critical section from inet_twsk_kill() to inet_twsk_deschedule_put(), serializing the scheduling vs descheduling of the timer. IOW, this prevents the following race: tcp_time_wait() inet_twsk_hashdance() inet_twsk_deschedule_put() del_timer_sync() inet_twsk_schedule() Thanks to Paolo Abeni for suggesting to leverage the ehash lock. This also restores a comment from commit ec94c2696f0b ("tcp/dccp: avoid one atomic operation for timewait hashdance") as inet_twsk_hashdance() had a "Step 1" and "Step 3" comment, but the "Step 2" had gone missing. inet_twsk_deschedule_put() now acquires the ehash spinlock to synchronize with inet_twsk_hashdance_schedule(). To ease possible regression search, actual un-pin is done in next patch. Conflicts: net/ipv4/inet_timewait_sock.c net/ipv4/tcp_ipv4.c [Retain refcount_set_release() and the existing tcptw timestamp field.] Link: https://lore.kernel.org/all/ZPhpfMjSiHVjQkTk@localhost.localdomain/ Reviewed-by: Eric Dumazet Signed-off-by: Valentin Schneider Co-developed-by: Florian Westphal Signed-off-by: Florian Westphal Signed-off-by: David S. Miller (cherry picked from commit b334b924c9b709bc969644fb5c406f5c9d01dceb) Signed-off-by: Wentao Guan --- include/net/inet_timewait_sock.h | 6 ++-- net/dccp/minisocks.c | 3 +- net/ipv4/inet_timewait_sock.c | 52 +++++++++++++++++++++++++++----- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 3 +- 5 files changed, 52 insertions(+), 14 deletions(-) diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 49787a0683ed2..b2b03afdd51bb 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -92,8 +92,10 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, struct inet_timewait_death_row *dr, const int state); -void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, - struct inet_hashinfo *hashinfo); +void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, + struct sock *sk, + struct inet_hashinfo *hashinfo, + int timeo); void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 0210d38442ec8..1b409804d82af 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -58,11 +58,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) * we complete the initialization. */ local_bh_disable(); - inet_twsk_schedule(tw, timeo); /* Linkage updates. * Note that access to tw after this point is illegal. */ - inet_twsk_hashdance(tw, sk, &dccp_hashinfo); + inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo); local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index d7d95c217fccc..c8cd8dda3507d 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -96,9 +96,13 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it * from the SK, and mess with hash chains and list linkage. + * + * The caller must not access @tw anymore after this function returns. */ -void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, - struct inet_hashinfo *hashinfo) +void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, + struct sock *sk, + struct inet_hashinfo *hashinfo, + int timeo) { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -129,26 +133,33 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); + /* Step 2: Hash TW into tcp ehash chain */ inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - spin_unlock(lock); + /* Ensure above writes are committed into memory before updating the + * refcount. + * Provides ordering vs later refcount_inc(). + */ + smp_wmb(); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. * - one reference for timer. - * We can use atomic_set() because prior spin_lock()/spin_unlock() - * committed into memory all tw fields. * Also note that after this point, we lost our implicit reference * so we are not allowed to use tw anymore. */ refcount_set_release(&tw->tw_refcnt, 3); + + inet_twsk_schedule(tw, timeo); + + spin_unlock(lock); } -EXPORT_SYMBOL_GPL(inet_twsk_hashdance); +EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule); static void tw_timer_handler(struct timer_list *t) { @@ -217,7 +228,34 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc); */ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { - if (del_timer_sync(&tw->tw_timer)) + struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; + spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + + /* inet_twsk_purge() walks over all sockets, including tw ones, + * and removes them via inet_twsk_deschedule_put() after a + * refcount_inc_not_zero(). + * + * inet_twsk_hashdance_schedule() must (re)init the refcount before + * arming the timer, i.e. inet_twsk_purge can obtain a reference to + * a twsk that did not yet schedule the timer. + * + * The ehash lock synchronizes these two: + * After acquiring the lock, the timer is always scheduled (else + * timer_shutdown returns false), because hashdance_schedule releases + * the ehash lock only after completing the timer initialization. + * + * Without grabbing the ehash lock, we get: + * 1) cpu x sets twsk refcount to 3 + * 2) cpu y bumps refcount to 4 + * 3) cpu y calls inet_twsk_deschedule_put() and shuts timer down + * 4) cpu x tries to start timer, but mod_timer is a noop post-shutdown + * -> timer refcount is never decremented. + */ + spin_lock(lock); + /* Makes sure hashdance_schedule() has completed */ + spin_unlock(lock); + + if (timer_shutdown_sync(&tw->tw_timer)) inet_twsk_kill(tw); inet_twsk_put(tw); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 10c06eeea7cd2..c38a128b4cd01 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -158,7 +158,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { - /* inet_twsk_hashdance() sets sk_refcnt after putting twsk + /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index da69835c56b65..2718a5fbea5b7 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -328,11 +328,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) * we complete the initialization. */ local_bh_disable(); - inet_twsk_schedule(tw, timeo); /* Linkage updates. * Note that access to tw after this point is illegal. */ - inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo); + inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo); local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this From 30d8d7cebb9e1cb1f414a6bb29446628dbee0b48 Mon Sep 17 00:00:00 2001 From: Xuanqiang Luo Date: Wed, 15 Oct 2025 10:02:36 +0800 Subject: [PATCH 8/9] inet: Avoid ehash lookup race in inet_twsk_hashdance_schedule() mainline inclusion from mainline-v6.19-rc1 commit b8ec80b130211e7bf076ef72365952979d5f7a72 category: bugfix Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b8ec80b130211e7bf076ef72365952979d5f7a72 -------------------------------- Since ehash lookups are lockless, if another CPU is converting sk to tw concurrently, fetching the newly inserted tw with tw->tw_refcnt == 0 cause lookup failure. The call trace map is drawn as follows: CPU 0 CPU 1 ----- ----- inet_twsk_hashdance_schedule() spin_lock() inet_twsk_add_node_rcu(tw, ...) __inet_lookup_established() (find tw, failure due to tw_refcnt = 0) __sk_nulls_del_node_init_rcu(sk) refcount_set(&tw->tw_refcnt, 3) spin_unlock() By replacing sk with tw atomically via hlist_nulls_replace_init_rcu() after setting tw_refcnt, we ensure that tw is either fully initialized or not visible to other CPUs, eliminating the race. It's worth noting that we held lock_sock() before the replacement, so there's no need to check if sk is hashed. Thanks to Kuniyuki Iwashima! Conflicts: net/ipv4/inet_timewait_sock.c [Retain refcount_set_release() for the existing memory-ordering fix.] Fixes: 3ab5aee7fe84 ("net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls") Reviewed-by: Kuniyuki Iwashima Reviewed-by: Jiayuan Chen Signed-off-by: Xuanqiang Luo Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20251015020236.431822-4-xuanqiang.luo@linux.dev Signed-off-by: Jakub Kicinski (cherry picked from commit b8ec80b130211e7bf076ef72365952979d5f7a72) Signed-off-by: Wentao Guan --- net/ipv4/inet_timewait_sock.c | 35 ++++++++++++----------------------- 1 file changed, 12 insertions(+), 23 deletions(-) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c8cd8dda3507d..6a4be5d6cbc7e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -86,12 +86,6 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) -{ - hlist_nulls_add_head_rcu(&tw->tw_node, list); -} - /* * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it @@ -106,13 +100,12 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead, *bhead2; - /* Step 1: Put TW into bind hash. Original socket stays there too. - Note, that any socket with inet->num != 0 MUST be bound in - binding cache, even if it is closed. + /* Put TW into bind hash. Original socket stays there too. + * Note, that any socket with inet->num != 0 MUST be bound in + * binding cache, even if it is closed. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; @@ -133,19 +126,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, spin_lock(lock); - /* Step 2: Hash TW into tcp ehash chain */ - inet_twsk_add_node_rcu(tw, &ehead->chain); - - /* Step 3: Remove SK from hash chain */ - if (__sk_nulls_del_node_init_rcu(sk)) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - - - /* Ensure above writes are committed into memory before updating the - * refcount. - * Provides ordering vs later refcount_inc(). - */ - smp_wmb(); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. @@ -155,6 +135,15 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, */ refcount_set_release(&tw->tw_refcnt, 3); + /* Ensure tw_refcnt has been set before tw is published. + * smp_wmb() provides the necessary memory barrier to enforce this + * ordering. + */ + smp_wmb(); + + hlist_nulls_replace_init_rcu(&sk->sk_nulls_node, &tw->tw_node); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + inet_twsk_schedule(tw, timeo); spin_unlock(lock); From 5199f790584d4ce8a58eec0459da40610012f077 Mon Sep 17 00:00:00 2001 From: Wentao Guan Date: Fri, 20 Nov 2026 14:22:19 +0800 Subject: [PATCH 9/9] tcp: fix TIME_WAIT refcount publication comment deepin inclusion category: bugfix The hashdance now sets tw_refcnt before publishing tw into ehash. Update the tcp_twsk_unique() comment accordingly. No functional change. Fixes: b8ec80b130211 ("inet: Avoid ehash lookup race in inet_twsk_hashdance_schedule()") Signed-off-by: Wentao Guan --- net/ipv4/tcp_ipv4.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c38a128b4cd01..04a015174128f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -158,9 +158,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { - /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk - * and releasing the bucket lock. - */ + /* inet_twsk_hashdance_schedule() sets sk_refcnt before publishing twsk. */ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) return 0;