linux-stable.git/io_uring, branch v6.16.2 Linux kernel stable tree io_uring/zcrx: don't leak pages on account failure 2025-08-20T16:41:44+00:00 Pavel Begunkov asml.silence@gmail.com 2025-07-21T09:56:21+00:00 32830e9f24f6251e4a276bfbbc5ea448e7a0d4dc commit 6bbd3411ff87df1ca38ff32d36eb5dc673ca8021 upstream. Someone needs to release pinned pages in io_import_umem() if accounting fails. Assign them to the area but return an error, the following io_zcrx_free_area() will clean them up. Fixes: 262ab205180d2 ("io_uring/zcrx: account area memory") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/e19f283a912f200c0d427e376cb789fc3f3d69bc.1753091564.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 6bbd3411ff87df1ca38ff32d36eb5dc673ca8021 upstream.

Someone needs to release pinned pages in io_import_umem() if accounting
fails. Assign them to the area but return an error, the following
io_zcrx_free_area() will clean them up.

Fixes: 262ab205180d2 ("io_uring/zcrx: account area memory")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e19f283a912f200c0d427e376cb789fc3f3d69bc.1753091564.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
io_uring/zcrx: fix null ifq on area destruction 2025-08-20T16:41:44+00:00 Pavel Begunkov asml.silence@gmail.com 2025-07-21T09:56:20+00:00 e004d86dc5f53780dccbf394bcdef814dfff0e0a commit 720df2310b89cf76c1dc1a05902536282506f8bf upstream. Dan reports that ifq can be null when infering arguments for io_unaccount_mem() from io_zcrx_free_area(). Fix it by always setting a correct ifq. Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@linaro.org> Closes: https://lore.kernel.org/r/202507180628.gBxrOgqr-lkp@intel.com/ Fixes: 262ab205180d2 ("io_uring/zcrx: account area memory") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/20670d163bb90dba2a81a4150f1125603cefb101.1753091564.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 720df2310b89cf76c1dc1a05902536282506f8bf upstream.

Dan reports that ifq can be null when infering arguments for
io_unaccount_mem() from io_zcrx_free_area(). Fix it by always setting a
correct ifq.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202507180628.gBxrOgqr-lkp@intel.com/
Fixes: 262ab205180d2 ("io_uring/zcrx: account area memory")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/20670d163bb90dba2a81a4150f1125603cefb101.1753091564.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
io_uring/rw: cast rw->flags assignment to rwf_t 2025-08-20T16:41:43+00:00 Jens Axboe axboe@kernel.dk 2025-07-07T22:46:30+00:00 a249c291703a66f495bde738903a23e8fb467ca2 commit 825aea662b492571877b32aeeae13689fd9fbee4 upstream. kernel test robot reports that a recent change of the sqe->rw_flags field throws a sparse warning on 32-bit archs: >> io_uring/rw.c:291:19: sparse: sparse: incorrect type in assignment (different base types) @@ expected restricted __kernel_rwf_t [usertype] flags @@ got unsigned int @@ io_uring/rw.c:291:19: sparse: expected restricted __kernel_rwf_t [usertype] flags io_uring/rw.c:291:19: sparse: got unsigned int Force cast it to rwf_t to silence that new sparse warning. Fixes: cf73d9970ea4 ("io_uring: don't use int for ABI") Reported-by: kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202507032211.PwSNPNSP-lkp@intel.com/ Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 825aea662b492571877b32aeeae13689fd9fbee4 upstream.

kernel test robot reports that a recent change of the sqe->rw_flags
field throws a sparse warning on 32-bit archs:

>> io_uring/rw.c:291:19: sparse: sparse: incorrect type in assignment (different base types) @@     expected restricted __kernel_rwf_t [usertype] flags @@     got unsigned int @@
   io_uring/rw.c:291:19: sparse:     expected restricted __kernel_rwf_t [usertype] flags
   io_uring/rw.c:291:19: sparse:     got unsigned int

Force cast it to rwf_t to silence that new sparse warning.

Fixes: cf73d9970ea4 ("io_uring: don't use int for ABI")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507032211.PwSNPNSP-lkp@intel.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
io_uring/net: commit partial buffers on retry 2025-08-20T16:40:44+00:00 Jens Axboe axboe@kernel.dk 2025-08-12T14:30:11+00:00 2eb7937b5fc7fcd90eab7bebb0181214b61b9283 commit 41b70df5b38bc80967d2e0ed55cc3c3896bba781 upstream. Ring provided buffers are potentially only valid within the single execution context in which they were acquired. io_uring deals with this and invalidates them on retry. But on the networking side, if MSG_WAITALL is set, or if the socket is of the streaming type and too little was processed, then it will hang on to the buffer rather than recycle or commit it. This is problematic for two reasons: 1) If someone unregisters the provided buffer ring before a later retry, then the req->buf_list will no longer be valid. 2) If multiple sockers are using the same buffer group, then multiple receives can consume the same memory. This can cause data corruption in the application, as either receive could land in the same userspace buffer. Fix this by disallowing partial retries from pinning a provided buffer across multiple executions, if ring provided buffers are used. Cc: stable@vger.kernel.org Reported-by: pt x <superman.xpt@gmail.com> Fixes: c56e022c0a27 ("io_uring: add support for user mapped provided buffer ring") Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 41b70df5b38bc80967d2e0ed55cc3c3896bba781 upstream.

Ring provided buffers are potentially only valid within the single
execution context in which they were acquired. io_uring deals with this
and invalidates them on retry. But on the networking side, if
MSG_WAITALL is set, or if the socket is of the streaming type and too
little was processed, then it will hang on to the buffer rather than
recycle or commit it. This is problematic for two reasons:

1) If someone unregisters the provided buffer ring before a later retry,
   then the req->buf_list will no longer be valid.

2) If multiple sockers are using the same buffer group, then multiple
   receives can consume the same memory. This can cause data corruption
   in the application, as either receive could land in the same
   userspace buffer.

Fix this by disallowing partial retries from pinning a provided buffer
across multiple executions, if ring provided buffers are used.

Cc: stable@vger.kernel.org
Reported-by: pt x <superman.xpt@gmail.com>
Fixes: c56e022c0a27 ("io_uring: add support for user mapped provided buffer ring")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
io_uring/memmap: cast nr_pages to size_t before shifting 2025-08-20T16:40:43+00:00 Jens Axboe axboe@kernel.dk 2025-08-08T12:35:14+00:00 a69a9b53c54e2d33e2a5b1ea4a9a71fd01c6cf3a commit 33503c083fda048c77903460ac0429e1e2c0e341 upstream. If the allocated size exceeds UINT_MAX, then it's necessary to cast the mr->nr_pages value to size_t to prevent it from overflowing. In practice this isn't much of a concern as the required memory size will have been validated upfront, and accounted to the user. And > 4GB sizes will be necessary to make the lack of a cast a problem, which greatly exceeds normal user locked_vm settings that are generally in the kb to mb range. However, if root is used, then accounting isn't done, and then it's possible to hit this issue. Link: https://lore.kernel.org/all/6895b298.050a0220.7f033.0059.GAE@google.com/ Cc: stable@vger.kernel.org Reported-by: syzbot+23727438116feb13df15@syzkaller.appspotmail.com Fixes: 087f997870a9 ("io_uring/memmap: implement mmap for regions") Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 33503c083fda048c77903460ac0429e1e2c0e341 upstream.

If the allocated size exceeds UINT_MAX, then it's necessary to cast
the mr->nr_pages value to size_t to prevent it from overflowing. In
practice this isn't much of a concern as the required memory size will
have been validated upfront, and accounted to the user. And > 4GB sizes
will be necessary to make the lack of a cast a problem, which greatly
exceeds normal user locked_vm settings that are generally in the kb to
mb range. However, if root is used, then accounting isn't done, and
then it's possible to hit this issue.

Link: https://lore.kernel.org/all/6895b298.050a0220.7f033.0059.GAE@google.com/
Cc: stable@vger.kernel.org
Reported-by: syzbot+23727438116feb13df15@syzkaller.appspotmail.com
Fixes: 087f997870a9 ("io_uring/memmap: implement mmap for regions")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
io_uring/zcrx: account area memory 2025-08-20T16:40:43+00:00 Pavel Begunkov asml.silence@gmail.com 2025-07-16T21:04:09+00:00 97431d2f357654f523d11dcd23f4bcfe4b922a90 commit 262ab205180d2ba3ab6110899a4dbe439c51dfaa upstream. zcrx areas can be quite large and need to be accounted and checked against RLIMIT_MEMLOCK. In practise it shouldn't be a big issue as the inteface already requires cap_net_admin. Cc: stable@vger.kernel.org Fixes: cf96310c5f9a0 ("io_uring/zcrx: add io_zcrx_area") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/4b53f0c575bd062f63d12bec6cac98037fc66aeb.1752699568.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 262ab205180d2ba3ab6110899a4dbe439c51dfaa upstream.

zcrx areas can be quite large and need to be accounted and checked
against RLIMIT_MEMLOCK. In practise it shouldn't be a big issue as
the inteface already requires cap_net_admin.

Cc: stable@vger.kernel.org
Fixes: cf96310c5f9a0 ("io_uring/zcrx: add io_zcrx_area")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4b53f0c575bd062f63d12bec6cac98037fc66aeb.1752699568.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
io_uring: export io_[un]account_mem 2025-08-20T16:40:43+00:00 Pavel Begunkov asml.silence@gmail.com 2025-07-16T21:04:08+00:00 6ced80a09bcc76a0bbca774da5fcc8bfc53b03c0 commit 11fbada7184f9e19bcdfa2f6b15828a78b8897a6 upstream. Export pinned memory accounting helpers, they'll be used by zcrx shortly. Cc: stable@vger.kernel.org Fixes: cf96310c5f9a0 ("io_uring/zcrx: add io_zcrx_area") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/9a61e54bd89289b39570ae02fe620e12487439e4.1752699568.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 11fbada7184f9e19bcdfa2f6b15828a78b8897a6 upstream.

Export pinned memory accounting helpers, they'll be used by zcrx
shortly.

Cc: stable@vger.kernel.org
Fixes: cf96310c5f9a0 ("io_uring/zcrx: add io_zcrx_area")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9a61e54bd89289b39570ae02fe620e12487439e4.1752699568.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Merge tag 'io_uring-6.16-20250718' of git://git.kernel.dk/linux 2025-07-18T19:21:26+00:00 Linus Torvalds torvalds@linux-foundation.org 2025-07-18T19:21:26+00:00 e347810e84094078d155663acbf36d82efe91f95 Pull io_uring fixes from Jens Axboe: - dmabug offset fix for zcrx - Fix for the POLLERR connect work around handling * tag 'io_uring-6.16-20250718' of git://git.kernel.dk/linux: io_uring/poll: fix POLLERR handling io_uring/zcrx: disallow user selected dmabuf offset and size 
Pull io_uring fixes from Jens Axboe:

 - dmabug offset fix for zcrx

 - Fix for the POLLERR connect work around handling

* tag 'io_uring-6.16-20250718' of git://git.kernel.dk/linux:
  io_uring/poll: fix POLLERR handling
  io_uring/zcrx: disallow user selected dmabuf offset and size
io_uring/poll: fix POLLERR handling 2025-07-16T16:28:28+00:00 Pavel Begunkov asml.silence@gmail.com 2025-07-16T16:20:17+00:00 c7cafd5b81cc07fb402e3068d134c21e60ea688c 8c8492ca64e7 ("io_uring/net: don't retry connect operation on EPOLLERR") is a little dirty hack that 1) wrongfully assumes that POLLERR equals to a failed request, which breaks all POLLERR users, e.g. all error queue recv interfaces. 2) deviates the connection request behaviour from connect(2), and 3) racy and solved at a wrong level. Nothing can be done with 2) now, and 3) is beyond the scope of the patch. At least solve 1) by moving the hack out of generic poll handling into io_connect(). Cc: stable@vger.kernel.org Fixes: 8c8492ca64e79 ("io_uring/net: don't retry connect operation on EPOLLERR") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/3dc89036388d602ebd84c28e5042e457bdfc952b.1752682444.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
8c8492ca64e7 ("io_uring/net: don't retry connect operation on EPOLLERR")
is a little dirty hack that
1) wrongfully assumes that POLLERR equals to a failed request, which
breaks all POLLERR users, e.g. all error queue recv interfaces.
2) deviates the connection request behaviour from connect(2), and
3) racy and solved at a wrong level.

Nothing can be done with 2) now, and 3) is beyond the scope of the
patch. At least solve 1) by moving the hack out of generic poll handling
into io_connect().

Cc: stable@vger.kernel.org
Fixes: 8c8492ca64e79 ("io_uring/net: don't retry connect operation on EPOLLERR")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/3dc89036388d602ebd84c28e5042e457bdfc952b.1752682444.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring/zcrx: disallow user selected dmabuf offset and size 2025-07-14T14:54:43+00:00 Pavel Begunkov asml.silence@gmail.com 2025-07-14T10:57:23+00:00 08ca1409c4fa37ec93de08b9963390ed68a5ae8c zcrx shouldn't be so frivolous about cutting a dmabuf sgtable and taking a subrange into it, the dmabuf layer might be not expecting that. It shouldn't be a problem for now, but since the zcrx dmabuf support is new and there shouldn't be any real users, let's play safe and reject user provided ranges into dmabufs. Also, it shouldn't be needed as userspace should size them appropriately. Fixes: a5c98e9424573 ("io_uring/zcrx: dmabuf backed zerocopy receive") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/be899f1afed32053eb2e2079d0da241514674aca.1752443579.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
zcrx shouldn't be so frivolous about cutting a dmabuf sgtable and taking
a subrange into it, the dmabuf layer might be not expecting that. It
shouldn't be a problem for now, but since the zcrx dmabuf support is new
and there shouldn't be any real users, let's play safe and reject user
provided ranges into dmabufs. Also, it shouldn't be needed as userspace
should size them appropriately.

Fixes: a5c98e9424573 ("io_uring/zcrx: dmabuf backed zerocopy receive")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/be899f1afed32053eb2e2079d0da241514674aca.1752443579.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>