[PATCH net v2] bpf, sockmap: fix the sk->sk_forward_alloc warning of sk_stream_kill_queues()

[PATCH net v2] bpf, sockmap: fix the sk->sk_forward_alloc warning of sk_stream_kill_queues()

[Wang Yufen]

When running `test_sockmap` selftests, got the following warning:

WARNING: CPU: 2 PID: 197 at net/core/stream.c:205 sk_stream_kill_queues+0xd3/0xf0
Call Trace:
  <TASK>
  inet_csk_destroy_sock+0x55/0x110
  tcp_rcv_state_process+0xd28/0x1380
  ? tcp_v4_do_rcv+0x77/0x2c0
  tcp_v4_do_rcv+0x77/0x2c0
  __release_sock+0x106/0x130
  __tcp_close+0x1a7/0x4e0
  tcp_close+0x20/0x70
  inet_release+0x3c/0x80
  __sock_release+0x3a/0xb0
  sock_close+0x14/0x20
  __fput+0xa3/0x260
  task_work_run+0x59/0xb0
  exit_to_user_mode_prepare+0x1b3/0x1c0
  syscall_exit_to_user_mode+0x19/0x50
  do_syscall_64+0x48/0x90
  entry_SYSCALL_64_after_hwframe+0x44/0xae

The root case is: In commit 84472b436e76 ("bpf, sockmap: Fix more
uncharged while msg has more_data") , I used msg->sg.size replace
tosend rudely, which break the
   if (msg->apply_bytes && msg->apply_bytes < send)
scene.

Fixes: 84472b436e76 ("bpf, sockmap: Fix more uncharged while msg has more_data")
Reported-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Wang Yufen <wangyufen@huawei.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
v1 -> v2: typo fixup
 net/ipv4/tcp_bpf.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a1626af..774d481 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 {
 	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
-	u32 tosend, delta = 0;
+	u32 tosend, orgsize, sent, delta = 0;
 	u32 eval = __SK_NONE;
 	int ret;
 
@@ -333,10 +333,12 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 			cork = true;
 			psock->cork = NULL;
 		}
-		sk_msg_return(sk, msg, msg->sg.size);
+		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
 
+		orgsize = msg->sg.size;
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+		sent = orgsize - msg->sg.size;
 
 		if (eval == __SK_REDIRECT)
 			sock_put(sk_redir);
@@ -375,7 +377,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 		    msg->sg.data[msg->sg.start].page_link &&
 		    msg->sg.data[msg->sg.start].length) {
 			if (eval == __SK_REDIRECT)
-				sk_mem_charge(sk, msg->sg.size);
+				sk_mem_charge(sk, tosend - sent);
 			goto more_data;
 		}
 	}
-- 
1.8.3.1

Re: [PATCH net v2] bpf, sockmap: fix the sk->sk_forward_alloc warning of sk_stream_kill_queues()

[Jakub Sitnicki]

On Sat, Oct 29, 2022 at 07:44 AM +08, Wang Yufen wrote:
> When running `test_sockmap` selftests, got the following warning:
>
> WARNING: CPU: 2 PID: 197 at net/core/stream.c:205 sk_stream_kill_queues+0xd3/0xf0
> Call Trace:
>   <TASK>
>   inet_csk_destroy_sock+0x55/0x110
>   tcp_rcv_state_process+0xd28/0x1380
>   ? tcp_v4_do_rcv+0x77/0x2c0
>   tcp_v4_do_rcv+0x77/0x2c0
>   __release_sock+0x106/0x130
>   __tcp_close+0x1a7/0x4e0
>   tcp_close+0x20/0x70
>   inet_release+0x3c/0x80
>   __sock_release+0x3a/0xb0
>   sock_close+0x14/0x20
>   __fput+0xa3/0x260
>   task_work_run+0x59/0xb0
>   exit_to_user_mode_prepare+0x1b3/0x1c0
>   syscall_exit_to_user_mode+0x19/0x50
>   do_syscall_64+0x48/0x90
>   entry_SYSCALL_64_after_hwframe+0x44/0xae
>
> The root case is: In commit 84472b436e76 ("bpf, sockmap: Fix more
> uncharged while msg has more_data") , I used msg->sg.size replace
> tosend rudely, which break the
>    if (msg->apply_bytes && msg->apply_bytes < send)
> scene.
>
> Fixes: 84472b436e76 ("bpf, sockmap: Fix more uncharged while msg has more_data")
> Reported-by: Jakub Sitnicki <jakub@cloudflare.com>
> Signed-off-by: Wang Yufen <wangyufen@huawei.com>
> Acked-by: John Fastabend <john.fastabend@gmail.com>
> ---
> v1 -> v2: typo fixup
>  net/ipv4/tcp_bpf.c | 8 +++++---
>  1 file changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
> index a1626af..774d481 100644
> --- a/net/ipv4/tcp_bpf.c
> +++ b/net/ipv4/tcp_bpf.c
> @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>  {
>  	bool cork = false, enospc = sk_msg_full(msg);
>  	struct sock *sk_redir;
> -	u32 tosend, delta = 0;
> +	u32 tosend, orgsize, sent, delta = 0;
>  	u32 eval = __SK_NONE;
>  	int ret;
>  
> @@ -333,10 +333,12 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>  			cork = true;
>  			psock->cork = NULL;
>  		}
> -		sk_msg_return(sk, msg, msg->sg.size);
> +		sk_msg_return(sk, msg, tosend);
>  		release_sock(sk);
>  
> +		orgsize = msg->sg.size;
>  		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
> +		sent = orgsize - msg->sg.size;

If I'm reading the code right, it's the same as:

                sent = tosend - msg->sg.size;

If so, no need for orgsize.

>  
>  		if (eval == __SK_REDIRECT)
>  			sock_put(sk_redir);
> @@ -375,7 +377,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>  		    msg->sg.data[msg->sg.start].page_link &&
>  		    msg->sg.data[msg->sg.start].length) {
>  			if (eval == __SK_REDIRECT)
> -				sk_mem_charge(sk, msg->sg.size);
> +				sk_mem_charge(sk, tosend - sent);
>  			goto more_data;
>  		}
>  	}

Re: [PATCH net v2] bpf, sockmap: fix the sk->sk_forward_alloc warning of sk_stream_kill_queues()

[Jakub Sitnicki]

On Mon, Oct 31, 2022 at 06:56 PM +01, Jakub Sitnicki wrote:
> On Sat, Oct 29, 2022 at 07:44 AM +08, Wang Yufen wrote:
>> When running `test_sockmap` selftests, got the following warning:
>>
>> WARNING: CPU: 2 PID: 197 at net/core/stream.c:205 sk_stream_kill_queues+0xd3/0xf0
>> Call Trace:
>>   <TASK>
>>   inet_csk_destroy_sock+0x55/0x110
>>   tcp_rcv_state_process+0xd28/0x1380
>>   ? tcp_v4_do_rcv+0x77/0x2c0
>>   tcp_v4_do_rcv+0x77/0x2c0
>>   __release_sock+0x106/0x130
>>   __tcp_close+0x1a7/0x4e0
>>   tcp_close+0x20/0x70
>>   inet_release+0x3c/0x80
>>   __sock_release+0x3a/0xb0
>>   sock_close+0x14/0x20
>>   __fput+0xa3/0x260
>>   task_work_run+0x59/0xb0
>>   exit_to_user_mode_prepare+0x1b3/0x1c0
>>   syscall_exit_to_user_mode+0x19/0x50
>>   do_syscall_64+0x48/0x90
>>   entry_SYSCALL_64_after_hwframe+0x44/0xae
>>
>> The root case is: In commit 84472b436e76 ("bpf, sockmap: Fix more
>> uncharged while msg has more_data") , I used msg->sg.size replace
>> tosend rudely, which break the
>>    if (msg->apply_bytes && msg->apply_bytes < send)
>> scene.
>>
>> Fixes: 84472b436e76 ("bpf, sockmap: Fix more uncharged while msg has more_data")
>> Reported-by: Jakub Sitnicki <jakub@cloudflare.com>
>> Signed-off-by: Wang Yufen <wangyufen@huawei.com>
>> Acked-by: John Fastabend <john.fastabend@gmail.com>
>> ---
>> v1 -> v2: typo fixup
>>  net/ipv4/tcp_bpf.c | 8 +++++---
>>  1 file changed, 5 insertions(+), 3 deletions(-)
>>
>> diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
>> index a1626af..774d481 100644
>> --- a/net/ipv4/tcp_bpf.c
>> +++ b/net/ipv4/tcp_bpf.c
>> @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>>  {
>>  	bool cork = false, enospc = sk_msg_full(msg);
>>  	struct sock *sk_redir;
>> -	u32 tosend, delta = 0;
>> +	u32 tosend, orgsize, sent, delta = 0;
>>  	u32 eval = __SK_NONE;
>>  	int ret;
>>  
>> @@ -333,10 +333,12 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>>  			cork = true;
>>  			psock->cork = NULL;
>>  		}
>> -		sk_msg_return(sk, msg, msg->sg.size);
>> +		sk_msg_return(sk, msg, tosend);
>>  		release_sock(sk);
>>  
>> +		orgsize = msg->sg.size;
>>  		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
>> +		sent = orgsize - msg->sg.size;
>
> If I'm reading the code right, it's the same as:
>
>                 sent = tosend - msg->sg.size;
>
> If so, no need for orgsize.

Sorry, that doesn't make any sense. I misread the code.

The fix is correct.

If I can have a small ask to rename `orgsize` to something more common.

We have `orig_size` or `origsize` in use today, but no `orgsize`:

$ git grep -c '\<orig_size\>' -- net
net/core/sysctl_net_core.c:3
net/psample/psample.c:1
net/tls/tls_device.c:5
net/tls/tls_sw.c:7
$ git grep -c '\<origsize\>' -- net
net/bridge/netfilter/ebtables.c:5
net/ipv4/netfilter/arp_tables.c:10
net/ipv4/netfilter/ip_tables.c:10
net/ipv6/netfilter/ip6_tables.c:10

It reads a bit better, IMHO.

Thanks for fixing it so quickly.

Acked-by: Jakub Sitnicki <jakub@cloudflare.com>

Re: [PATCH net v2] bpf, sockmap: fix the sk->sk_forward_alloc warning of sk_stream_kill_queues()

[wangyufen]

在 2022/11/1 6:26, Jakub Sitnicki 写道:
> On Mon, Oct 31, 2022 at 06:56 PM +01, Jakub Sitnicki wrote:
>> On Sat, Oct 29, 2022 at 07:44 AM +08, Wang Yufen wrote:
>>> When running `test_sockmap` selftests, got the following warning:
>>>
>>> WARNING: CPU: 2 PID: 197 at net/core/stream.c:205 sk_stream_kill_queues+0xd3/0xf0
>>> Call Trace:
>>>    <TASK>
>>>    inet_csk_destroy_sock+0x55/0x110
>>>    tcp_rcv_state_process+0xd28/0x1380
>>>    ? tcp_v4_do_rcv+0x77/0x2c0
>>>    tcp_v4_do_rcv+0x77/0x2c0
>>>    __release_sock+0x106/0x130
>>>    __tcp_close+0x1a7/0x4e0
>>>    tcp_close+0x20/0x70
>>>    inet_release+0x3c/0x80
>>>    __sock_release+0x3a/0xb0
>>>    sock_close+0x14/0x20
>>>    __fput+0xa3/0x260
>>>    task_work_run+0x59/0xb0
>>>    exit_to_user_mode_prepare+0x1b3/0x1c0
>>>    syscall_exit_to_user_mode+0x19/0x50
>>>    do_syscall_64+0x48/0x90
>>>    entry_SYSCALL_64_after_hwframe+0x44/0xae
>>>
>>> The root case is: In commit 84472b436e76 ("bpf, sockmap: Fix more
>>> uncharged while msg has more_data") , I used msg->sg.size replace
>>> tosend rudely, which break the
>>>     if (msg->apply_bytes && msg->apply_bytes < send)
>>> scene.

Sorry, I made a mistake here:  send --> tosend

alse will change in v3

>>>
>>> Fixes: 84472b436e76 ("bpf, sockmap: Fix more uncharged while msg has more_data")
>>> Reported-by: Jakub Sitnicki <jakub@cloudflare.com>
>>> Signed-off-by: Wang Yufen <wangyufen@huawei.com>
>>> Acked-by: John Fastabend <john.fastabend@gmail.com>
>>> ---
>>> v1 -> v2: typo fixup
>>>   net/ipv4/tcp_bpf.c | 8 +++++---
>>>   1 file changed, 5 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
>>> index a1626af..774d481 100644
>>> --- a/net/ipv4/tcp_bpf.c
>>> +++ b/net/ipv4/tcp_bpf.c
>>> @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>>>   {
>>>   	bool cork = false, enospc = sk_msg_full(msg);
>>>   	struct sock *sk_redir;
>>> -	u32 tosend, delta = 0;
>>> +	u32 tosend, orgsize, sent, delta = 0;
>>>   	u32 eval = __SK_NONE;
>>>   	int ret;
>>>   
>>> @@ -333,10 +333,12 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
>>>   			cork = true;
>>>   			psock->cork = NULL;
>>>   		}
>>> -		sk_msg_return(sk, msg, msg->sg.size);
>>> +		sk_msg_return(sk, msg, tosend);
>>>   		release_sock(sk);
>>>   
>>> +		orgsize = msg->sg.size;
>>>   		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
>>> +		sent = orgsize - msg->sg.size;
>> If I'm reading the code right, it's the same as:
>>
>>                  sent = tosend - msg->sg.size;
>>
>> If so, no need for orgsize.
> Sorry, that doesn't make any sense. I misread the code.
>
> The fix is correct.
>
> If I can have a small ask to rename `orgsize` to something more common.
>
> We have `orig_size` or `origsize` in use today, but no `orgsize`:
ok, I will change in v3, thanks.
>
> $ git grep -c '\<orig_size\>' -- net
> net/core/sysctl_net_core.c:3
> net/psample/psample.c:1
> net/tls/tls_device.c:5
> net/tls/tls_sw.c:7
> $ git grep -c '\<origsize\>' -- net
> net/bridge/netfilter/ebtables.c:5
> net/ipv4/netfilter/arp_tables.c:10
> net/ipv4/netfilter/ip_tables.c:10
> net/ipv6/netfilter/ip6_tables.c:10
>
> It reads a bit better, IMHO.
>
> Thanks for fixing it so quickly.
>
> Acked-by: Jakub Sitnicki <jakub@cloudflare.com>