From 54f89b3178d5448dd4457afbb98fc1ab99090a65 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 10 Dec 2024 01:20:38 +0000 Subject: tcp_bpf: Charge receive socket buffer in bpf_tcp_ingress() When bpf_tcp_ingress() is called, the skmsg is being redirected to the ingress of the destination socket. Therefore, we should charge its receive socket buffer, instead of sending socket buffer. Because sk_rmem_schedule() tests pfmemalloc of skb, we need to introduce a wrapper and call it for skmsg. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Reviewed-by: John Fastabend Link: https://lore.kernel.org/bpf/20241210012039.1669389-2-zijianzhang@bytedance.com --- include/net/sock.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 7464e9f9f47c..c383126f691d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1527,7 +1527,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; @@ -1535,7 +1535,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || - skb_pfmemalloc(skb); + pfmemalloc; +} + +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +{ + return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) -- cgit v1.2.3 From 542ed8145e6f9392e3d0a86a0e9027d2ffd183e4 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 21 Dec 2024 00:29:20 +0100 Subject: netfilter: nft_set_hash: unaligned atomic read on struct nft_set_ext Access to genmask field in struct nft_set_ext results in unaligned atomic read: [ 72.130109] Unable to handle kernel paging request at virtual address ffff0000c2bb708c [ 72.131036] Mem abort info: [ 72.131213] ESR = 0x0000000096000021 [ 72.131446] EC = 0x25: DABT (current EL), IL = 32 bits [ 72.132209] SET = 0, FnV = 0 [ 72.133216] EA = 0, S1PTW = 0 [ 72.134080] FSC = 0x21: alignment fault [ 72.135593] Data abort info: [ 72.137194] ISV = 0, ISS = 0x00000021, ISS2 = 0x00000000 [ 72.142351] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 72.145989] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 72.150115] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000237d27000 [ 72.154893] [ffff0000c2bb708c] pgd=0000000000000000, p4d=180000023ffff403, pud=180000023f84b403, pmd=180000023f835403, +pte=0068000102bb7707 [ 72.163021] Internal error: Oops: 0000000096000021 [#1] SMP [...] [ 72.170041] CPU: 7 UID: 0 PID: 54 Comm: kworker/7:0 Tainted: G E 6.13.0-rc3+ #2 [ 72.170509] Tainted: [E]=UNSIGNED_MODULE [ 72.170720] Hardware name: QEMU QEMU Virtual Machine, BIOS edk2-stable202302-for-qemu 03/01/2023 [ 72.171192] Workqueue: events_power_efficient nft_rhash_gc [nf_tables] [ 72.171552] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 72.171915] pc : nft_rhash_gc+0x200/0x2d8 [nf_tables] [ 72.172166] lr : nft_rhash_gc+0x128/0x2d8 [nf_tables] [ 72.172546] sp : ffff800081f2bce0 [ 72.172724] x29: ffff800081f2bd40 x28: ffff0000c2bb708c x27: 0000000000000038 [ 72.173078] x26: ffff0000c6780ef0 x25: ffff0000c643df00 x24: ffff0000c6778f78 [ 72.173431] x23: 000000000000001a x22: ffff0000c4b1f000 x21: ffff0000c6780f78 [ 72.173782] x20: ffff0000c2bb70dc x19: ffff0000c2bb7080 x18: 0000000000000000 [ 72.174135] x17: ffff0000c0a4e1c0 x16: 0000000000003000 x15: 0000ac26d173b978 [ 72.174485] x14: ffffffffffffffff x13: 0000000000000030 x12: ffff0000c6780ef0 [ 72.174841] x11: 0000000000000000 x10: ffff800081f2bcf8 x9 : ffff0000c3000000 [ 72.175193] x8 : 00000000000004be x7 : 0000000000000000 x6 : 0000000000000000 [ 72.175544] x5 : 0000000000000040 x4 : ffff0000c3000010 x3 : 0000000000000000 [ 72.175871] x2 : 0000000000003a98 x1 : ffff0000c2bb708c x0 : 0000000000000004 [ 72.176207] Call trace: [ 72.176316] nft_rhash_gc+0x200/0x2d8 [nf_tables] (P) [ 72.176653] process_one_work+0x178/0x3d0 [ 72.176831] worker_thread+0x200/0x3f0 [ 72.176995] kthread+0xe8/0xf8 [ 72.177130] ret_from_fork+0x10/0x20 [ 72.177289] Code: 54fff984 d503201f d2800080 91003261 (f820303f) [ 72.177557] ---[ end trace 0000000000000000 ]--- Align struct nft_set_ext to word size to address this and documentation it. pahole reports that this increases the size of elements for rhash and pipapo in 8 bytes on x86_64. Fixes: 7ffc7481153b ("netfilter: nft_set_hash: skip duplicated elements pending gc run") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4afa64c81304..0027beca5cd5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -733,15 +733,18 @@ struct nft_set_ext_tmpl { /** * struct nft_set_ext - set extensions * - * @genmask: generation mask + * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT) * @offset: offsets of individual extension types * @data: beginning of extension data + * + * This structure must be aligned to word size, otherwise atomic bitops + * on genmask field can cause alignment failure on some archs. */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; -}; +} __aligned(BITS_PER_LONG / 8); static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { -- cgit v1.2.3 From 3479c7549fb1dfa7a1db4efb7347c7b8ef50de4b Mon Sep 17 00:00:00 2001 From: Zhongqiu Duan Date: Thu, 2 Jan 2025 17:14:26 +0000 Subject: tcp/dccp: allow a connection when sk_max_ack_backlog is zero If the backlog of listen() is set to zero, sk_acceptq_is_full() allows one connection to be made, but inet_csk_reqsk_queue_is_full() does not. When the net.ipv4.tcp_syncookies is zero, inet_csk_reqsk_queue_is_full() will cause an immediate drop before the sk_acceptq_is_full() check in tcp_conn_request(), resulting in no connection can be made. This patch tries to keep consistent with 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes."). Link: https://lore.kernel.org/netdev/20250102080258.53858-1-kuniyu@amazon.com/ Fixes: ef547f2ac16b ("tcp: remove max_qlen_log") Signed-off-by: Zhongqiu Duan Reviewed-by: Kuniyuki Iwashima Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250102171426.915276-1-dzq.aishenghu0@gmail.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3c82fad904d4..c7f42844c79a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog); + return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); -- cgit v1.2.3 From b2849867b3a70c2d675ddca01c4e4540f7d3b8e9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 7 Jan 2025 17:27:36 +0100 Subject: sock_poll_wait: kill the no longer necessary barrier after poll_wait() Now that poll_wait() provides a full barrier we can remove smp_mb() from sock_poll_wait(). Also, the poll_does_not_wait() check before poll_wait() just adds the unnecessary confusion, kill it. poll_wait() does the same "p && p->_qproc" check. Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20250107162736.GA18944@redhat.com Signed-off-by: Christian Brauner --- include/net/sock.h | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 7464e9f9f47c..305f3ae5edc2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2291,7 +2291,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) } /** - * sock_poll_wait - place memory barrier behind the poll_wait call. + * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table @@ -2301,15 +2301,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { - if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq.wait, p); - /* We need to be sure we are in sync with the - * socket flags modification. - * - * This memory barrier is paired in the wq_has_sleeper. - */ - smp_mb(); - } + /* Provides a barrier we need to be sure we are in sync + * with the socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) -- cgit v1.2.3