linux-kernel - RE: [PATCH] RDMA/siw: Fix the sendmsg byte count in siw_tcp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID:
 <DS0SPRMB00679C99808A4D85BAB6DADF995FA@DS0SPRMB0067.namprd15.prod.outlook.com>
Date: Wed, 23 Jul 2025 14:52:12 +0000
From: Bernard Metzler <BMT@...ich.ibm.com>
To: Pedro Falcato <pfalcato@...e.de>, Jason Gunthorpe <jgg@...pe.ca>,
        Leon
 Romanovsky <leon@...nel.org>, Vlastimil Babka <vbabka@...e.cz>
CC: Jakub Kicinski <kuba@...nel.org>, David Howells <dhowells@...hat.com>,
        Tom
 Talpey <tom@...pey.com>,
        "linux-rdma@...r.kernel.org"
	<linux-rdma@...r.kernel.org>,
        "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>,
        "linux-mm@...ck.org" <linux-mm@...ck.org>,
        "stable@...r.kernel.org" <stable@...r.kernel.org>,
        kernel test robot
	<oliver.sang@...el.com>
Subject: RE:  [PATCH] RDMA/siw: Fix the sendmsg byte count in
 siw_tcp_sendpages



> -----Original Message-----
> From: Pedro Falcato <pfalcato@...e.de>
> Sent: Wednesday, 23 July 2025 12:41
> To: Jason Gunthorpe <jgg@...pe.ca>; Bernard Metzler <BMT@...ich.ibm.com>;
> Leon Romanovsky <leon@...nel.org>; Vlastimil Babka <vbabka@...e.cz>
> Cc: Jakub Kicinski <kuba@...nel.org>; David Howells <dhowells@...hat.com>;
> Tom Talpey <tom@...pey.com>; linux-rdma@...r.kernel.org; linux-
> kernel@...r.kernel.org; linux-mm@...ck.org; Pedro Falcato
> <pfalcato@...e.de>; stable@...r.kernel.org; kernel test robot
> <oliver.sang@...el.com>
> Subject: [EXTERNAL] [PATCH] RDMA/siw: Fix the sendmsg byte count in
> siw_tcp_sendpages
> 
> Ever since commit c2ff29e99a76 ("siw: Inline do_tcp_sendpages()"),
> we have been doing this:
> 
> static int siw_tcp_sendpages(struct socket *s, struct page **page, int
> offset,
>                              size_t size)
> [...]
>         /* Calculate the number of bytes we need to push, for this page
>          * specifically */
>         size_t bytes = min_t(size_t, PAGE_SIZE - offset, size);
>         /* If we can't splice it, then copy it in, as normal */
>         if (!sendpage_ok(page[i]))
>                 msg.msg_flags &= ~MSG_SPLICE_PAGES;
>         /* Set the bvec pointing to the page, with len $bytes */
>         bvec_set_page(&bvec, page[i], bytes, offset);
>         /* Set the iter to $size, aka the size of the whole sendpages (!!!)
> */
>         iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
> try_page_again:
>         lock_sock(sk);
>         /* Sendmsg with $size size (!!!) */
>         rv = tcp_sendmsg_locked(sk, &msg, size);
> 
> This means we've been sending oversized iov_iters and tcp_sendmsg calls
> for a while. This has a been a benign bug because sendpage_ok() always
> returned true. With the recent slab allocator changes being slowly
> introduced into next (that disallow sendpage on large kmalloc
> allocations), we have recently hit out-of-bounds crashes, due to slight
> differences in iov_iter behavior between the MSG_SPLICE_PAGES and
> "regular" copy paths:
> 
> (MSG_SPLICE_PAGES)
> skb_splice_from_iter
>   iov_iter_extract_pages
>     iov_iter_extract_bvec_pages
>       uses i->nr_segs to correctly stop in its tracks before OoB'ing
> everywhere
>   skb_splice_from_iter gets a "short" read
> 
> (!MSG_SPLICE_PAGES)
> skb_copy_to_page_nocache copy=iov_iter_count
>  [...]
>    copy_from_iter
>         /* this doesn't help */
>         if (unlikely(iter->count < len))
>                 len = iter->count;
>           iterate_bvec
>             ... and we run off the bvecs
> 
> Fix this by properly setting the iov_iter's byte count, plus sending the
> correct byte count to tcp_sendmsg_locked.
> 
> Cc: stable@...r.kernel.org
> Fixes: c2ff29e99a76 ("siw: Inline do_tcp_sendpages()")
> Reported-by: kernel test robot <oliver.sang@...el.com>
> Closes: https% 
> 3A__lore.kernel.org_oe-2Dlkp_202507220801.50a7210-2Dlkp-
> 40intel.com&d=DwIDAg&c=BSDicqBQBDjDI9RkVyTcHQ&r=4ynb4Sj_4MUcZXbhvovE4tYSbqx
> yOwdSiLedP4yO55g&m=8FIDji_gvHEZEUL08IM8h6Slg9f_hp4n8OxkdR_OWLnZ9CkPknHCzHVC
> BYkCKt_q&s=IP0c71OgDL-cEe5hFduy0qNhy5WICEkTBTQLrVicotc&e=
> Signed-off-by: Pedro Falcato <pfalcato@...e.de>
> ---
>  drivers/infiniband/sw/siw/siw_qp_tx.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c
> b/drivers/infiniband/sw/siw/siw_qp_tx.c
> index 3a08f57d2211..9576a2b766c4 100644
> --- a/drivers/infiniband/sw/siw/siw_qp_tx.c
> +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
> @@ -340,11 +340,11 @@ static int siw_tcp_sendpages(struct socket *s, struct
> page **page, int offset,
>  		if (!sendpage_ok(page[i]))
>  			msg.msg_flags &= ~MSG_SPLICE_PAGES;
>  		bvec_set_page(&bvec, page[i], bytes, offset);
> -		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
> +		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, bytes);
> 
>  try_page_again:
>  		lock_sock(sk);
> -		rv = tcp_sendmsg_locked(sk, &msg, size);
> +		rv = tcp_sendmsg_locked(sk, &msg, bytes);
>  		release_sock(sk);
> 

Pedro, many thanks for catching this! I completely
missed it during my too sloppy review of that patch.
It's a serious bug which must be fixed asap.
BUT, looking closer, I do not see the offset being taken
into account when retrying a current segment. So,
resend attempts seem to send old data which are already
out. Shouldn't the try_page_again: label be above
bvec_set_page()??

Thanks!
Bernard.



>  		if (rv > 0) {
> --
> 2.50.1