From fd9c31f834416e3060061dbcb45ababaa25cdfe2 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Wed, 8 Mar 2023 10:11:53 +0800 Subject: udp: introduce __sk_mem_schedule() usage Keep the accounting schema consistent across different protocols with __sk_mem_schedule(). Besides, it adjusts a little bit on how to calculate forward allocated memory compared to before. After applied this patch, we could avoid receive path scheduling extra amount of memory. Link: https://lore.kernel.org/lkml/20230221110344.82818-1-kerneljasonxing@gmail.com/ Signed-off-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230308021153.99777-1-kerneljasonxing@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/udp.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c605d171eb2d..dc8feb54d835 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1531,10 +1531,21 @@ static void busylock_release(spinlock_t *busy) spin_unlock(busy); } +static int udp_rmem_schedule(struct sock *sk, int size) +{ + int delta; + + delta = size - sk->sk_forward_alloc; + if (delta > 0 && !__sk_mem_schedule(sk, delta, SK_MEM_RECV)) + return -ENOBUFS; + + return 0; +} + int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; - int rmem, delta, amt, err = -ENOMEM; + int rmem, err = -ENOMEM; spinlock_t *busy = NULL; int size; @@ -1567,16 +1578,10 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) goto uncharge_drop; spin_lock(&list->lock); - if (size >= sk->sk_forward_alloc) { - amt = sk_mem_pages(size); - delta = amt << PAGE_SHIFT; - if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) { - err = -ENOBUFS; - spin_unlock(&list->lock); - goto uncharge_drop; - } - - sk->sk_forward_alloc += delta; + err = udp_rmem_schedule(sk, size); + if (err) { + spin_unlock(&list->lock); + goto uncharge_drop; } sk->sk_forward_alloc -= size; -- cgit v1.2.3 From a0a989d3007538cd7dae9431d8ac47850ced3100 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Mar 2023 15:31:57 +0000 Subject: udp: constify __udp_is_mcast_sock() socket argument This clarifies __udp_is_mcast_sock() intent. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/ipv4/udp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index dc8feb54d835..aa32afd871ee 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -578,12 +578,12 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, EXPORT_SYMBOL_GPL(udp4_lib_lookup); #endif -static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, +static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif, unsigned short hnum) { - struct inet_sock *inet = inet_sk(sk); + const struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || -- cgit v1.2.3 From 78fa0d61d97a728d306b0c23d353c0e340756437 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 22 May 2023 19:56:05 -0700 Subject: bpf, sockmap: Pass skb ownership through read_skb The read_skb hook calls consume_skb() now, but this means that if the recv_actor program wants to use the skb it needs to inc the ref cnt so that the consume_skb() doesn't kfree the sk_buff. This is problematic because in some error cases under memory pressure we may need to linearize the sk_buff from sk_psock_skb_ingress_enqueue(). Then we get this, skb_linearize() __pskb_pull_tail() pskb_expand_head() BUG_ON(skb_shared(skb)) Because we incremented users refcnt from sk_psock_verdict_recv() we hit the bug on with refcnt > 1 and trip it. To fix lets simply pass ownership of the sk_buff through the skb_read call. Then we can drop the consume from read_skb handlers and assume the verdict recv does any required kfree. Bug found while testing in our CI which runs in VMs that hit memory constraints rather regularly. William tested TCP read_skb handlers. [ 106.536188] ------------[ cut here ]------------ [ 106.536197] kernel BUG at net/core/skbuff.c:1693! [ 106.536479] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 106.536726] CPU: 3 PID: 1495 Comm: curl Not tainted 5.19.0-rc5 #1 [ 106.537023] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ArchLinux 1.16.0-1 04/01/2014 [ 106.537467] RIP: 0010:pskb_expand_head+0x269/0x330 [ 106.538585] RSP: 0018:ffffc90000138b68 EFLAGS: 00010202 [ 106.538839] RAX: 000000000000003f RBX: ffff8881048940e8 RCX: 0000000000000a20 [ 106.539186] RDX: 0000000000000002 RSI: 0000000000000000 RDI: ffff8881048940e8 [ 106.539529] RBP: ffffc90000138be8 R08: 00000000e161fd1a R09: 0000000000000000 [ 106.539877] R10: 0000000000000018 R11: 0000000000000000 R12: ffff8881048940e8 [ 106.540222] R13: 0000000000000003 R14: 0000000000000000 R15: ffff8881048940e8 [ 106.540568] FS: 00007f277dde9f00(0000) GS:ffff88813bd80000(0000) knlGS:0000000000000000 [ 106.540954] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 106.541227] CR2: 00007f277eeede64 CR3: 000000000ad3e000 CR4: 00000000000006e0 [ 106.541569] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 106.541915] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 106.542255] Call Trace: [ 106.542383] [ 106.542487] __pskb_pull_tail+0x4b/0x3e0 [ 106.542681] skb_ensure_writable+0x85/0xa0 [ 106.542882] sk_skb_pull_data+0x18/0x20 [ 106.543084] bpf_prog_b517a65a242018b0_bpf_skskb_http_verdict+0x3a9/0x4aa9 [ 106.543536] ? migrate_disable+0x66/0x80 [ 106.543871] sk_psock_verdict_recv+0xe2/0x310 [ 106.544258] ? sk_psock_write_space+0x1f0/0x1f0 [ 106.544561] tcp_read_skb+0x7b/0x120 [ 106.544740] tcp_data_queue+0x904/0xee0 [ 106.544931] tcp_rcv_established+0x212/0x7c0 [ 106.545142] tcp_v4_do_rcv+0x174/0x2a0 [ 106.545326] tcp_v4_rcv+0xe70/0xf60 [ 106.545500] ip_protocol_deliver_rcu+0x48/0x290 [ 106.545744] ip_local_deliver_finish+0xa7/0x150 Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Reported-by: William Findlay Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Tested-by: William Findlay Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230523025618.113937-2-john.fastabend@gmail.com --- net/core/skmsg.c | 2 -- net/ipv4/tcp.c | 1 - net/ipv4/udp.c | 7 ++----- net/unix/af_unix.c | 7 ++----- net/vmw_vsock/virtio_transport_common.c | 5 +---- 5 files changed, 5 insertions(+), 17 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f81883759d38..4a3dc8d27295 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1183,8 +1183,6 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) int ret = __SK_DROP; int len = skb->len; - skb_get(skb); - rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4d6392c16b7a..e914e3446377 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1773,7 +1773,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); - consume_skb(skb); if (used < 0) { if (!copied) copied = used; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index aa32afd871ee..9482def1f310 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1818,7 +1818,7 @@ EXPORT_SYMBOL(__skb_recv_udp); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; - int err, copied; + int err; try_again: skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); @@ -1837,10 +1837,7 @@ try_again: } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL(udp_read_skb); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cc695c9f09ec..e7728b57a8c7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2553,7 +2553,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; - int err, copied; + int err; mutex_lock(&u->iolock); skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); @@ -2561,10 +2561,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } /* diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e4878551f140..b769fc258931 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1441,7 +1441,6 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto struct sock *sk = sk_vsock(vsk); struct sk_buff *skb; int off = 0; - int copied; int err; spin_lock_bh(&vvs->rx_lock); @@ -1454,9 +1453,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL_GPL(virtio_transport_read_skb); -- cgit v1.2.3