io-uring
5,659 threads 37,539 messages Latest
About Subsystems, Archive
- Subsystems
- io_uring, io_uring zcrx, io_uring BPF-ops
- Archive
- lore.kernel.org/io-uring
Show bot threadsBotsLatest activityActivityNewest threadsNewMost repliesRepliesMost participantsPeople
- xsk: Zero copy through page-pool memory providers In review 9 replies
- io_uring: opaque TCP payload objects New 0 replies
- scsi: release completed passthrough requests before user copyback In review 3 replies
- io_uring: add IORING_OP_UTIMENSAT In review 3 replies
- io_uring: cancel pending poll activation on ring exit New 0 replies
- io_uring: improve alloc_cache branch prediction Applied 3 replies
- io_uring/napi: don't end the single NAPI busy poll early on need_resched() Applied 2 replies
- memcg: account the remaining uncharged kernel allocations In review 8 replies
- io_uring/kbuf: fix cross-mm interpretation of provided buffers In review 3 replies
- io_uring/sqpoll: make io_sq_thread_stop() idempotent IO_SQ_THREAD_SHOULD_STOP may already be set when io_sq_thread() exits on its own. The last ring still calls io_sq_thread_stop() from io_put_sq_data(), which tripped WARN_ON_ONCE(). Reproduced on 7.4-rc1 with IORING_SETUP_SQPOLL + close(ring_fd), which triggered WARNING at io_uring/sqpoll.c:88 before this patch. With this patch applied, the same repro no longer warns (also verified via QEMU initramfs repro). Fixes: 22d9db9fd64a ("io_uring/sqpoll: don't attach to a thread that is canceling") Reported-by: [email protected] Link: https://syzbot.org/bug?extid=9f32706bfd7c4ff81434 Tested-by: yanghaoming <[email protected]> New 0 replies
- fs: add RWF_DIRECT for preadv2/pwritev2/io_uring to set IOCB_DIRECT per io In review 7 replies
- io_uring: only wait for in-flight requests if the closing task uses the ring Applied 1 reply
- io_uring: add feature flag for dma-buf support Applied 1 reply
- io_uring/wait: don't sleep on an already expired timeout Applied 1 reply
- io_uring/rsrc: hold uring_lock across index-alloc put_user Applied 1 reply
- io_uring/zcrx: don't sync for cpu dma-bufs In review 1 reply
- io_uring: only wait for in-flight requests if the closing task uses the ring Superseded 1 reply
- io_uring/rsrc: hold uring_lock across index-alloc put_user Superseded 2 replies
- selftests/io_uring: cast optval through uintptr_t in mini_liburing.h Applied 1 reply
- selftests/io_uring: cast optval through uintptr_t in mini_liburing.h Superseded 1 reply
- uaccess: Refuse and warn on user accesses when current->mm is NULL Applied 19 replies
- allow dma-buf-io ctx reuse across files In review 1 reply
- net: prevent mixing incompatible memory providers in skbs Superseded 3 replies
- io_uring/cancel: cancel all poll matches in one pass Applied 1 reply
- io_uring/sqpoll: do the return-to-userspace work in the SQPOLL thread Applied 1 reply
- block: only fail dma-buf bios that need block layer PI Applied 3 replies
- io_uring/sqpoll: don't set IO_SQ_THREAD_SHOULD_STOP on thread exit Applied 3 replies
- btrfs: add io_uring interface for BTRFS_IOC_DEFRAG_RANGE New 0 replies
- af_unix: introduce MSG_CMSG_SEALED In review 4 replies
- io_uring/napi: clean up list traversal with list_for_each_entry_safe() Applied 2 replies
- io_uring: add IORING_OP_UTIMENSAT Superseded 0 replies
- Various io_uring fixes In review 4 replies
- io_uring/io-wq: save worker type before dropping its reference In review 1 reply
- dma-buf backed NVMe passthrough I/O New 0 replies
- ci: Temporarily remove alpine-musl-build In review 3 replies
- Change a lot of min_t() that might mask high bits Applied 67 replies
- scsi: release completed passthrough requests before user copyback Superseded 5 replies
- io_uring/net: fix multishot recv length limit accounting Applied 1 reply
- io_uring/timeout: count cancelled timeouts in cq_timeouts Applied 1 reply
- io_uring/napi: fix list use-after-free on PREEMPT_RT In review 5 replies
- block: only fail dma-buf bios that need block layer PI Superseded 4 replies
- dma-buf backed NVMe passthrough I/O Superseded 6 replies
- nvme: make passthrough user copyback failure-safe In review 4 replies
- io_uring: don't sleep on a claimed DEFER_TASKRUN wakeup In review 2 replies
- misc: fgds: enable GPU-NVMe direct I/O via POSIX and io_uring In review 12 replies
- io_uring: keep the drain active when a deferred drain request is started New 0 replies
- io_uring/net: don't retry a non-blocking connect() that fails with -EAGAIN Applied 1 reply
- io_uring/napi: drop the single NAPI busy poll special case In review 3 replies
- io_uring/register: enforce per-task restrictions in io_uring_register_blind() Applied 1 reply
- io_uring/net: mask socket type with SOCK_TYPE_MASK in io_socket_bpf_populate() Applied 1 reply