Re: [PATCH net-next v10 08/16] tls: Inline do_tcp_sendpages()

From: Tariq Toukan <ttoukan.linux@gmail.com>
To: David Howells <dhowells@redhat.com>
Cc: netdev@vger.kernel.org, "David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
	David Ahern <dsahern@kernel.org>,
	Matthew Wilcox <willy@infradead.org>,
	Al Viro <viro@zeniv.linux.org.uk>,
	Christoph Hellwig <hch@infradead.org>,
	Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
	Christian Brauner <brauner@kernel.org>,
	Chuck Lever III <chuck.lever@oracle.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, Boris Pismenny <borisp@nvidia.com>,
	John Fastabend <john.fastabend@gmail.com>,
	Gal Pressman <gal@nvidia.com>,
	ranro@nvidia.com, samiram@nvidia.com, drort@nvidia.com,
	Tariq Toukan <tariqt@nvidia.com>
Subject: Re: [PATCH net-next v10 08/16] tls: Inline do_tcp_sendpages()
Date: Tue, 13 Jun 2023 14:15:03 +0300	[thread overview]
Message-ID: <5a9d4ffb-a569-3f60-6ac8-070ab5e5f5ad@gmail.com> (raw)
In-Reply-To: <2267272.1686150217@warthog.procyon.org.uk>


On 07/06/2023 18:03, David Howells wrote:
> Tariq Toukan <ttoukan.linux@gmail.com> wrote:
> 
>> My team spotted a new degradation in TLS TX device offload, bisected to this
>> patch.
> 
> I presume you're using some hardware (I'm guessing Mellanox?) that can
> actually do TLS offload?  Unfortunately, I don't have any hardware that can do
> this, so I can't test the tls_device stuff.
> 
>>  From a quick look at the patch, it's not clear to me what's going wrong.
>> Please let us know of any helpful information that we can provide to help in
>> the debug.
> 
> Can you find out what source line this corresponds to?
> 
> 	RIP: 0010:skb_splice_from_iter+0x102/0x300
> 
> Assuming you're building your own kernel, something like the following might
> do the trick:
> 
> 	echo "RIP: 0010:skb_splice_from_iter+0x102/0x300" |
> 	./scripts/decode_stacktrace.sh /my/built/vmlinux /my/build/tree
> 

Hi,

It's:
RIP: 0010:skb_splice_from_iter (/usr/linux/net/core/skbuff.c:6957)

which coresponds to this line:
                         if (WARN_ON_ONCE(!sendpage_ok(page)))

> if you run it in the kernel source tree you're using and substitute the
> paths to vmlinux and the build tree for modules.
> 
> David
>