kcm: annotate data-races
Subsystems (2)
cover kcm: annotate data-races
This series address two different syzbot reports for KCM.
Eric Dumazet (2):
kcm: annotate data-races around kcm->rx_psock
kcm: annotate data-races around kcm->rx_wait
net/kcm/kcmsock.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-)
Signature · 1 line
2.38.0.135.g90850a2211-goog
PATCH 1/2 kcm: annotate data-races around kcm->rx_psock
kcm->rx_psock can be read locklessly in kcm_rfree(). Annotate the read and writes accordingly.
We do the same for kcm->rx_wait in the following patch.
syzbot reported:
BUG: KCSAN: data-race in kcm_rfree / unreserve_rx_kcm
write to 0xffff888123d827b8 of 8 bytes by task 2758 on cpu 1:
unreserve_rx_kcm+0x72/0x1f0 net/kcm/kcmsock.c:313 kcm_rcv_strparser+0x2b5/0x3a0 net/kcm/kcmsock.c:373 __strp_recv+0x64c/0xd20 net/strparser/strparser.c:301 strp_recv+0x6d/0x80 net/strparser/strparser.c:335 tcp_read_sock+0x13e/0x5a0 net/ipv4/tcp.c:1703 strp_read_sock net/strparser/strparser.c:358 [inline] do_strp_work net/strparser/strparser.c:406 [inline] strp_work+0xe8/0x180 net/strparser/strparser.c:415 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306
read to 0xffff888123d827b8 of 8 bytes by task 5859 on cpu 0:
kcm_rfree+0x14c/0x220 net/kcm/kcmsock.c:181 skb_release_head_state+0x8e/0x160 net/core/skbuff.c:841 skb_release_all net/core/skbuff.c:852 [inline] __kfree_skb net/core/skbuff.c:868 [inline] kfree_skb_reason+0x5c/0x260 net/core/skbuff.c:891 kfree_skb include/linux/skbuff.h:1216 [inline] kcm_recvmsg+0x226/0x2b0 net/kcm/kcmsock.c:1161 ____sys_recvmsg+0x16c/0x2e0 ___sys_recvmsg net/socket.c:2743 [inline] do_recvmmsg+0x2f1/0x710 net/socket.c:2837 __sys_recvmmsg net/socket.c:2916 [inline] __do_sys_recvmmsg net/socket.c:2939 [inline] __se_sys_recvmmsg net/socket.c:2932 [inline] __x64_sys_recvmmsg+0xde/0x160 net/socket.c:2932 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0xffff88812971ce00 -> 0x0000000000000000
Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 5859 Comm: syz-executor.3 Not tainted 6.0.0-syzkaller-12189-g19d17ab7c68b-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022
--- net/kcm/kcmsock.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
net/kcm/kcmsock.c +5 -3
@@ -178,7 +178,7 @@ static void kcm_rfree(struct sk_buff *skb)/* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic (); -if (!kcm->rx_wait && !kcm->rx_psock && +if (!kcm->rx_wait && !READ_ONCE (kcm->rx_psock) &&sk_rmem_alloc_get (sk) < sk->sk_rcvlowat) {spin_lock_bh (&mux->rx_lock);kcm_rcv_ready (kcm);
@@ -283,7 +283,8 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, kcm->rx_wait = false; psock->rx_kcm = kcm; - kcm->rx_psock = psock; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_psock, psock);spin_unlock_bh (&mux->rx_lock);
@@ -310,7 +311,8 @@ static void unreserve_rx_kcm(struct kcm_psock *psock,spin_lock_bh (&mux->rx_lock); psock->rx_kcm =NULL ; - kcm->rx_psock =NULL ; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_psock,NULL );/* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree
Signature · 1 line
2.38.0.135.g90850a2211-goog
PATCH 2/2 kcm: annotate data-races around kcm->rx_wait
In reply to Eric Dumazetkcm->rx_psock can be read locklessly in kcm_rfree(). Annotate the read and writes accordingly.
syzbot reported:
BUG: KCSAN: data-race in kcm_rcv_strparser / kcm_rfree
write to 0xffff88810784e3d0 of 1 bytes by task 1823 on cpu 1:
reserve_rx_kcm net/kcm/kcmsock.c:283 [inline] kcm_rcv_strparser+0x250/0x3a0 net/kcm/kcmsock.c:363 __strp_recv+0x64c/0xd20 net/strparser/strparser.c:301 strp_recv+0x6d/0x80 net/strparser/strparser.c:335 tcp_read_sock+0x13e/0x5a0 net/ipv4/tcp.c:1703 strp_read_sock net/strparser/strparser.c:358 [inline] do_strp_work net/strparser/strparser.c:406 [inline] strp_work+0xe8/0x180 net/strparser/strparser.c:415 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306
read to 0xffff88810784e3d0 of 1 bytes by task 17869 on cpu 0:
kcm_rfree+0x121/0x220 net/kcm/kcmsock.c:181 skb_release_head_state+0x8e/0x160 net/core/skbuff.c:841 skb_release_all net/core/skbuff.c:852 [inline] __kfree_skb net/core/skbuff.c:868 [inline] kfree_skb_reason+0x5c/0x260 net/core/skbuff.c:891 kfree_skb include/linux/skbuff.h:1216 [inline] kcm_recvmsg+0x226/0x2b0 net/kcm/kcmsock.c:1161 ____sys_recvmsg+0x16c/0x2e0 ___sys_recvmsg net/socket.c:2743 [inline] do_recvmmsg+0x2f1/0x710 net/socket.c:2837 __sys_recvmmsg net/socket.c:2916 [inline] __do_sys_recvmmsg net/socket.c:2939 [inline] __se_sys_recvmmsg net/socket.c:2932 [inline] __x64_sys_recvmmsg+0xde/0x160 net/socket.c:2932 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0x01 -> 0x00
Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 17869 Comm: syz-executor.2 Not tainted 6.1.0-rc1-syzkaller-00010-gbb1a1146467a-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022
--- net/kcm/kcmsock.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-)
net/kcm/kcmsock.c +11 -6
@@ -162,7 +162,8 @@ static void kcm_rcv_ready(struct kcm_sock *kcm)/* Buffer limit is okay now, add to ready list */ list_add_tail (&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); - kcm->rx_wait = true; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_wait, true); }static void kcm_rfree (struct sk_buff *skb)
@@ -178,7 +179,7 @@ static void kcm_rfree(struct sk_buff *skb)/* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic (); -if (!kcm->rx_wait && !READ_ONCE (kcm->rx_psock) && +if (!READ_ONCE (kcm->rx_wait) && !READ_ONCE (kcm->rx_psock) &&sk_rmem_alloc_get (sk) < sk->sk_rcvlowat) {spin_lock_bh (&mux->rx_lock);kcm_rcv_ready (kcm);
@@ -237,7 +238,8 @@ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head)if (kcm_queue_rcv_skb (&kcm->sk, skb)) {/* Should mean socket buffer full */ list_del (&kcm->wait_rx_list); - kcm->rx_wait = false; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_wait, false);/* Commit rx_wait to read in kcm_free */ smp_wmb ();
@@ -280,7 +282,8 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, kcm =list_first_entry (&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list);list_del (&kcm->wait_rx_list); - kcm->rx_wait = false; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_wait, false); psock->rx_kcm = kcm;/* paired with lockless reads in kcm_rfree() */
@@ -1242,7 +1245,8 @@ static void kcm_recv_disable(struct kcm_sock *kcm)if (!kcm->rx_psock) {if (kcm->rx_wait) {list_del (&kcm->wait_rx_list); - kcm->rx_wait = false; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_wait, false); }requeue_rx_msgs (mux, &kcm->sk.sk_receive_queue);
@@ -1795,7 +1799,8 @@ static void kcm_done(struct kcm_sock *kcm)if (kcm->rx_wait) {list_del (&kcm->wait_rx_list); - kcm->rx_wait = false; +/* paired with lockless reads in kcm_rfree() */ +WRITE_ONCE (kcm->rx_wait, false); }/* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs (mux, &sk->sk_receive_queue);
Signature · 1 line
2.38.0.135.g90850a2211-goog
Re: [PATCH net 2/2] kcm: annotate data-races around kcm->rx_wait
Quoted 1 line · Eric Dumazet
kcm->rx_psockcan be read locklessly inkcm_rfree().
Copy-n-paste typo here.
Quoted 1 line
Annotate the read and writes accordingly.
I wonder why not simply acquire mux->rx_lock earlier?
Thanks.
Re: [PATCH net 2/2] kcm: annotate data-races around kcm->rx_wait
Quoted 9 lines · Cong Wang
Quoted 1 line · Eric Dumazet
kcm->rx_psockcan be read locklessly inkcm_rfree().Copy-n-paste typo here.
Quoted 1 line
Annotate the read and writes accordingly.
I wonder why not simply acquire
mux->rx_lockearlier?
I would think kcm_rfree() is called very often (per skb)
Grabbing the spinlock would add a performance regression.
READ_ONCE() is a no brainer here.
Quoted 2 lines
Thanks.
This series was applied to netdev/net.git (master) by David S. Miller <[email protected]>:
Hello:
This series was applied to netdev/net.git (master) by David S. Miller <[email protected]>:
Quoted 8 lines · On Thu, 20 Oct 2022 22:45:10 +0000 you wrote:
This series address two different syzbot reports for KCM.
Eric Dumazet (2):
kcm: annotate data-races aroundkcm->rx_psock
kcm: annotate data-races aroundkcm->rx_waitnet/kcm/kcmsock.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-)
Here is the summary with links:
- [net,1/2] kcm: annotate data-races around kcm->rx_psock
https://git.kernel.org/netdev/net/c/15e4dabda11b - [net,2/2] kcm: annotate data-races around kcm->rx_wait https://git.kernel.org/netdev/net/c/0c745b5141a4
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html