[PATCH] tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"

[PATCH] tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"

[Matthieu Baerts]

From: Eric Dumazet <edumazet@google.com>

commit 29869d66870a715177bfb505f66a7e0e8bcc89c3 upstream.

This reverts commit e70ac171658679ecf6bea4bbd9e9325cd6079d2b.

jtcp_rcv_established() is in fact called with hard irq being disabled.

Initial bug report from Ricardo Nabinger Sanchez [1] still needs
to be investigated, but does not look like a TCP bug.

[1] https://www.spinics.net/lists/netdev/msg420960.html

Note: reasons for the backport in v4.9.y are described there:

    https://www.spinics.net/lists/stable/msg255166.html

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: kernel test robot <xiaolong.ye@intel.com>
Cc: Ricardo Nabinger Sanchez <rnsanchez@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org # 4.9
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
---
 net/ipv4/tcp_probe.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 3d063eb37848..f6c50af24a64 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -117,7 +117,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	     (fwmark > 0 && skb->mark == fwmark)) &&
 	    (full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
 
-		spin_lock_bh(&tcp_probe.lock);
+		spin_lock(&tcp_probe.lock);
 		/* If log fills, just silently drop */
 		if (tcp_probe_avail() > 1) {
 			struct tcp_log *p = tcp_probe.log + tcp_probe.head;
@@ -157,7 +157,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
 		}
 		tcp_probe.lastcwnd = tp->snd_cwnd;
-		spin_unlock_bh(&tcp_probe.lock);
+		spin_unlock(&tcp_probe.lock);
 
 		wake_up(&tcp_probe.wait);
 	}
-- 
2.17.1

Re: [PATCH] tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"

[Greg KH]

On Wed, Sep 12, 2018 at 12:06:06PM +0200, Matthieu Baerts wrote:
> From: Eric Dumazet <edumazet@google.com>
> 
> commit 29869d66870a715177bfb505f66a7e0e8bcc89c3 upstream.
> 
> This reverts commit e70ac171658679ecf6bea4bbd9e9325cd6079d2b.
> 
> jtcp_rcv_established() is in fact called with hard irq being disabled.
> 
> Initial bug report from Ricardo Nabinger Sanchez [1] still needs
> to be investigated, but does not look like a TCP bug.
> 
> [1] https://www.spinics.net/lists/netdev/msg420960.html
> 
> Note: reasons for the backport in v4.9.y are described there:
> 
>     https://www.spinics.net/lists/stable/msg255166.html
> 
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Reported-by: kernel test robot <xiaolong.ye@intel.com>
> Cc: Ricardo Nabinger Sanchez <rnsanchez@gmail.com>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> Cc: stable@vger.kernel.org # 4.9
> Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
> ---
>  net/ipv4/tcp_probe.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)

Thanks for this, now queued up.

greg k-h