user/sven/linux.git/io_uring, branch v6.1.43

io_uring: don't audit the capability check in io_uring_create()

2023-08-03T08:23:48Z

[ Upstream commit 6adc2272aaaf84f34b652cf77f770c6fcc4b8336 ] The check being unconditional may lead to unwanted denials reported by LSMs when a process has the capability granted by DAC, but denied by an LSM. In the case of SELinux such denials are a problem, since they can't be effectively filtered out via the policy and when not silenced, they produce noise that may hide a true problem or an attack. Since not having the capability merely means that the created io_uring context will be accounted against the current user's RLIMIT_MEMLOCK limit, we can disable auditing of denials for this check by using ns_capable_noaudit() instead of capable(). Fixes: 2b188cc1bb85 ("Add io_uring IO interface") Link: https://bugzilla.redhat.com/show_bug.cgi?id=2193317 Signed-off-by: Ondrej Mosnacek Reviewed-by: Jeff Moyer Link: https://lore.kernel.org/r/20230718115607.65652-1-omosnace@redhat.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin

io_uring: treat -EAGAIN for REQ_F_NOWAIT as final for io-wq

2023-07-27T06:50:23Z

commit a9be202269580ca611c6cebac90eaf1795497800 upstream. io-wq assumes that an issue is blocking, but it may not be if the request type has asked for a non-blocking attempt. If we get -EAGAIN for that case, then we need to treat it as a final result and not retry or arm poll for it. Cc: stable@vger.kernel.org # 5.10+ Link: https://github.com/axboe/liburing/issues/897 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring: Use io_schedule* in cqring wait

2023-07-19T14:22:18Z

Commit 8a796565cec3601071cbbd27d6304e202019d014 upstream. I observed poor performance of io_uring compared to synchronous IO. That turns out to be caused by deeper CPU idle states entered with io_uring, due to io_uring using plain schedule(), whereas synchronous IO uses io_schedule(). The losses due to this are substantial. On my cascade lake workstation, t/io_uring from the fio repository e.g. yields regressions between 20% and 40% with the following command: ./t/io_uring -r 5 -X0 -d 1 -s 1 -c 1 -p 0 -S$use_sync -R 0 /mnt/t2/fio/write.0.0 This is repeatable with different filesystems, using raw block devices and using different block devices. Use io_schedule_prepare() / io_schedule_finish() in io_cqring_wait_schedule() to address the difference. After that using io_uring is on par or surpassing synchronous IO (using registered files etc makes it reliably win, but arguably is a less fair comparison). There are other calls to schedule() in io_uring/, but none immediately jump out to be similarly situated, so I did not touch them. Similarly, it's possible that mutex_lock_io() should be used, but it's not clear if there are cases where that matters. Cc: stable@vger.kernel.org # 5.10+ Cc: Pavel Begunkov Cc: io-uring@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Andres Freund Link: https://lore.kernel.org/r/20230707162007.194068-1-andres@anarazel.de [axboe: minor style fixup] Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring: wait interruptibly for request completions on exit

2023-07-19T14:22:09Z

commit 4826c59453b3b4677d6bf72814e7ababdea86949 upstream. WHen the ring exits, cleanup is done and the final cancelation and waiting on completions is done by io_ring_exit_work. That function is invoked by kworker, which doesn't take any signals. Because of that, it doesn't really matter if we wait for completions in TASK_INTERRUPTIBLE or TASK_UNINTERRUPTIBLE state. However, it does matter to the hung task detection checker! Normally we expect cancelations and completions to happen rather quickly. Some test cases, however, will exit the ring and park the owning task stopped (eg via SIGSTOP). If the owning task needs to run task_work to complete requests, then io_ring_exit_work won't make any progress until the task is runnable again. Hence io_ring_exit_work can trigger the hung task detection, which is particularly problematic if panic-on-hung-task is enabled. As the ring exit doesn't take signals to begin with, have it wait interruptibly rather than uninterruptibly. io_uring has a separate stuck-exit warning that triggers independently anyway, so we're not really missing anything by making this switch. Cc: stable@vger.kernel.org # 5.10+ Link: https://lore.kernel.org/r/b0e4aaef-7088-56ce-244c-976edeac0e66@kernel.dk Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring/net: use the correct msghdr union member in io_sendmsg_copy_hdr

2023-06-28T09:12:33Z

[ Upstream commit 26fed83653d0154704cadb7afc418f315c7ac1f0 ] Rather than assign the user pointer to msghdr->msg_control, assign it to msghdr->msg_control_user to make sparse happy. They are in a union so the end result is the same, but let's avoid new sparse warnings and squash this one. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306210654.mDMcyMuB-lkp@intel.com/ Fixes: cac9e4418f4c ("io_uring/net: save msghdr->msg_control for retries") Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin

io_uring/poll: serialize poll linked timer start with poll removal

2023-06-28T09:12:27Z

Commit ef7dfac51d8ed961b742218f526bd589f3900a59 upstream. We selectively grab the ctx->uring_lock for poll update/removal, but we really should grab it from the start to fully synchronize with linked timeouts. Normally this is indeed the case, but if requests are forced async by the application, we don't fully cover removal and timer disarm within the uring_lock. Make this simpler by having consistent locking state for poll removal. Cc: stable@vger.kernel.org # 6.1+ Reported-by: Querijn Voet Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring/net: disable partial retries for recvmsg with cmsg

2023-06-28T09:12:24Z

commit 78d0d2063bab954d19a1696feae4c7706a626d48 upstream. We cannot sanely handle partial retries for recvmsg if we have cmsg attached. If we don't, then we'd just be overwriting the initial cmsg header on retries. Alternatively we could increment and handle this appropriately, but it doesn't seem worth the complication. Move the MSG_WAITALL check into the non-multishot case while at it, since MSG_WAITALL is explicitly disabled for multishot anyway. Link: https://lore.kernel.org/io-uring/0b0d4411-c8fd-4272-770b-e030af6919a0@kernel.dk/ Cc: stable@vger.kernel.org # 5.10+ Reported-by: Stefan Metzmacher Reviewed-by: Stefan Metzmacher Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring/net: clear msg_controllen on partial sendmsg retry

2023-06-28T09:12:24Z

commit b1dc492087db0f2e5a45f1072a743d04618dd6be upstream. If we have cmsg attached AND we transferred partial data at least, clear msg_controllen on retry so we don't attempt to send that again. Cc: stable@vger.kernel.org # 5.10+ Fixes: cac9e4418f4c ("io_uring/net: save msghdr->msg_control for retries") Reported-by: Stefan Metzmacher Reviewed-by: Stefan Metzmacher Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring/net: save msghdr->msg_control for retries

2023-06-21T14:00:55Z

commit cac9e4418f4cbd548ccb065b3adcafe073f7f7d2 upstream. If the application sets ->msg_control and we have to later retry this command, or if it got queued with IOSQE_ASYNC to begin with, then we need to retain the original msg_control value. This is due to the net stack overwriting this field with an in-kernel pointer, to copy it in. Hitting that path for the second time will now fail the copy from user, as it's attempting to copy from a non-user address. Cc: stable@vger.kernel.org # 5.10+ Link: https://github.com/axboe/liburing/issues/880 Reported-and-tested-by: Marek Majkowski Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

io_uring: unlock sqd->lock before sq thread release CPU

2023-06-21T14:00:53Z

[ Upstream commit 533ab73f5b5c95dcb4152b52d5482abcc824c690 ] The sq thread actively releases CPU resources by calling the cond_resched() and schedule() interfaces when it is idle. Therefore, more resources are available for other threads to run. There exists a problem in sq thread: it does not unlock sqd->lock before releasing CPU resources every time. This makes other threads pending on sqd->lock for a long time. For example, the following interfaces all require sqd->lock: io_sq_offload_create(), io_register_iowq_max_workers() and io_ring_exit_work(). Before the sq thread releases CPU resources, unlocking sqd->lock will provide the user a better experience because it can respond quickly to user requests. Signed-off-by: Kanchan Joshi Signed-off-by: Wenwen Chen Link: https://lore.kernel.org/r/20230525082626.577862-1-wenwen.chen@samsung.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin