bpf, sockmap: Pass skb ownership through read_skb

BugLink: https://bugs.launchpad.net/bugs/2028979

[ Upstream commit 78fa0d6 ]

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]  <IRQ>
[  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: 04919be ("tcp: Introduce tcp_read_skb()")
Reported-by: William Findlay <will@isovalent.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: William Findlay <will@isovalent.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20230523025618.113937-2-john.fastabend@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

Author: jrfastab

net/core/skmsg.c

@@ -1180,8 +1180,6 @@ 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)) {

net/ipv4/tcp.c

@@ -1772,7 +1772,6 @@ 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;

net/ipv4/udp.c

@@ -1813,7 +1813,7 @@ 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);
@@ -1832,10 +1832,7 @@ int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 	}
 
 	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);
 

net/unix/af_unix.c

@@ -2552,18 +2552,15 @@ 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);
 	mutex_unlock(&u->iolock);
 	if (!skb)
 		return err;
 
-	copied = recv_actor(sk, skb);
-	kfree_skb(skb);
-
-	return copied;
+	return recv_actor(sk, skb);
 }
 
 /*