From 8033c6c2fed235b3d571b5a5ede302b752bc5c7d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 10:54:12 -0800 Subject: bpf: remove unused static inlines Remove two dead stubs, sk_msg_clear_meta() was never used, use of xskq_cons_is_full() got replaced by xsk_tx_writeable() in v5.10. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220126185412.2776254-1-kuba@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux/skmsg.h') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..ddde5f620901 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -171,11 +171,6 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) -static inline void sk_msg_clear_meta(struct sk_msg *msg) -{ - memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); -} - static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); -- cgit v1.2.3 From 5a8fb33e530512ee67a11b30f3451a4f030f4b01 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Feb 2022 20:56:14 -0800 Subject: skmsg: convert struct sk_msg_sg::copy to a bitmap We have plans for increasing MAX_SKB_FRAGS, but sk_msg_sg::copy is currently an unsigned long, limiting MAX_SKB_FRAGS to 30 on 32bit arches. Convert it to a bitmap, as Jakub suggested. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skmsg.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux/skmsg.h') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..1ff68a88c58d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,7 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - unsigned long copy; + DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the @@ -38,7 +38,6 @@ struct sk_msg_sg { */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -234,7 +233,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (test_bit(msg->sg.start, &msg->sg.copy)) { + if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -253,7 +252,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - __set_bit(msg->sg.end, &msg->sg.copy); + __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -262,9 +261,9 @@ static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) - __set_bit(i, &msg->sg.copy); + __set_bit(i, msg->sg.copy); else - __clear_bit(i, &msg->sg.copy); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; -- cgit v1.2.3 From 938d3480b92fa5e454b7734294f12a7b75126f09 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 4 Mar 2022 16:11:42 +0800 Subject: bpf, sockmap: Fix memleak in sk_psock_queue_msg If tcp_bpf_sendmsg is running during a tear down operation we may enqueue data on the ingress msg queue while tear down is trying to free it. sk1 (redirect sk2) sk2 ------------------- --------------- tcp_bpf_sendmsg() tcp_bpf_send_verdict() tcp_bpf_sendmsg_redir() bpf_tcp_ingress() sock_map_close() lock_sock() lock_sock() ... blocking sk_psock_stop sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); release_sock(sk); lock_sock() sk_mem_charge() get_page() sk_psock_queue_msg() sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED); drop_sk_msg() release_sock() While drop_sk_msg(), the msg has charged memory form sk by sk_mem_charge and has sg pages need to put. To fix we use sk_msg_free() and then kfee() msg. This issue can cause the following info: WARNING: CPU: 0 PID: 9202 at net/core/stream.c:205 sk_stream_kill_queues+0xc8/0xe0 Call Trace: inet_csk_destroy_sock+0x55/0x110 tcp_rcv_state_process+0xe5f/0xe90 ? sk_filter_trim_cap+0x10d/0x230 ? tcp_v4_do_rcv+0x161/0x250 tcp_v4_do_rcv+0x161/0x250 tcp_v4_rcv+0xc3a/0xce0 ip_protocol_deliver_rcu+0x3d/0x230 ip_local_deliver_finish+0x54/0x60 ip_local_deliver+0xfd/0x110 ? ip_protocol_deliver_rcu+0x230/0x230 ip_rcv+0xd6/0x100 ? ip_local_deliver+0x110/0x110 __netif_receive_skb_one_core+0x85/0xa0 process_backlog+0xa4/0x160 __napi_poll+0x29/0x1b0 net_rx_action+0x287/0x300 __do_softirq+0xff/0x2fc do_softirq+0x79/0x90 WARNING: CPU: 0 PID: 531 at net/ipv4/af_inet.c:154 inet_sock_destruct+0x175/0x1b0 Call Trace: __sk_destruct+0x24/0x1f0 sk_psock_destroy+0x19b/0x1c0 process_one_work+0x1b3/0x3c0 ? process_one_work+0x3c0/0x3c0 worker_thread+0x30/0x350 ? process_one_work+0x3c0/0x3c0 kthread+0xe6/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 Fixes: 9635720b7c88 ("bpf, sockmap: Fix memleak on ingress msg enqueue") Signed-off-by: Wang Yufen Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20220304081145.2037182-2-wangyufen@huawei.com --- include/linux/skmsg.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux/skmsg.h') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fdb5375f0562..c5a2d6f50f25 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -304,21 +304,16 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) -{ - if (msg->skb) - sock_drop(psock->sk, msg->skb); - kfree(msg); -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) list_add_tail(&msg->list, &psock->ingress_msg); - else - drop_sk_msg(psock, msg); + else { + sk_msg_free(psock->sk, msg); + kfree(msg); + } spin_unlock_bh(&psock->ingress_lock); } -- cgit v1.2.3