linux/io_uring
Linus Torvalds 764e77d868 Locking updates for v7.2:
Futex updates:
 
  - Optimize futex hash bucket access patterns (Peter Zijlstra)
 
  - Large series to address the robust futex unlock race for real,
    by Thomas Gleixner:
 
     "The robust futex unlock mechanism is racy in respect
      to the clearing of the robust_list_head::list_op_pending
      pointer because unlock and clearing the pointer are not
      atomic. The race window is between the unlock and clearing the
      pending op pointer. If the task is forced to exit in this
      window, exit will access a potentially invalid pending op
      pointer when cleaning up the robust list. That happens if
      another task manages to unmap the object containing the lock
      before the cleanup, which results in an UAF. In the worst case
      this UAF can lead to memory corruption when unrelated content
      has been mapped to the same address by the time the access
      happens.
 
      User space can't solve this problem without help from the kernel.
      This series provides the kernel side infrastructure to help it
      along:
 
       1) Combined unlock, pointer clearing, wake-up for the
          contended case
 
       2) VDSO based unlock and pointer clearing helpers with a
          fix-up function in the kernel when user space was interrupted
          within the critical section.
 
     ... with help by André Almeida:
 
      - Add a note about robust list race condition (André Almeida)
      - Add self-tests for robust release operations (André Almeida)
 
 Context analysis updates:
 
  - Implement context analysis for 'struct rt_mutex'.
    (Bart Van Assche)
  - Bump required Clang version to 23 (Marco Elver)
 
 Guard infrastructure updates:
 
  - Series to remove NULL check from unconditional guards
    (Dmitry Ilvokhin)
 
 Lockdep updates:
 
  - Restore self-test migrate_disable() and sched_rt_mutex
    state on PREEMPT_RT (Karl Mehltretter)
 
 Membarriers updates:
 
  - Use per-CPU mutexes for targeted commands (Aniket Gattani)
  - Modernize membarrier_global_expedited with cleanup guards
    (Aniket Gattani)
  - Add rseq stress test for CFS throttle interactions (Aniket Gattani)
 
 percpu-rwsems updates:
 
  - Extract __percpu_up_read() to optimize inlining overhead
    (Dmitry Ilvokhin)
 
 Seqlocks updates:
 
  - Allow UBSAN_ALIGNMENT to fail optimizing (Heiko Carstens)
 
 Lock tracing:
 
  - Add contended_release tracepoint to sleepable locks
    such as mutexes, percpu-rwsems, rtmutexes, rwsems
    and semaphores. (Dmitry Ilvokhin)
 
 MAINTAINERS updates:
 
  - MAINTAINERS: Add RUST [SYNC] entry (Boqun Feng)
 
 Misc updates and fixes by Randy Dunlap, YE WEI-HONG,
 Fabricio Parra, Dmitry Ilvokhin and Peter Zijlstra.
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmoujYURHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1jQFw//SNo1zxqGJuVudIWTpk5hUbWO6La9dc2C
 2RW4lMNM551AaGFK6V01u1hD7dBZkWBqER+f3+CMtkqi734pAevTfkYJOitnGOOX
 YZicGqTufV+Q+hcEiHAY3ADF6384SiyvAGNHL5wk3eLqC+Raug0f0cNt4opzFvr7
 I6vRcW02JQMRKBe50+Aoa5zg7ymmbqaH0KkiPvfY5UFl38MKABhkY1izA9o+/Q/S
 1/joNo5iQ3Ciqf6tn76vTg4Xiz7napikHB5LfWxorgmQo7FEdUY54GGMaa8aBOPi
 EfgIV9p+qOJhmWn4H1HgVSYlnUn3tJICYnVVCruXWXD+pzITS+F5qSQ3p25F3VIt
 c3jh3NaVW71pR/Sbj4zGvf8QguJL340RGJs/e5qcj91pjOSCH5B75ruNgFgYK9Lv
 iRi6dnHBBHxaN57YHTOrhphvjyfc0L7i6cGyJgHJWwyi0y3XBYlNuP/VLPuwquKl
 anK86hlkl9W4kO0OOukD1xhfuRv7066EdJc3iWWlp9yz+yI5xDGuV4FhvEHRoy38
 R9VY2bwzgZrW/NkodHIb95+W30qEmeq2z1W4wiBu+mf1JnyW2g/n8jKkc6AINMpI
 VGcom3MdinxjUtmybZT9Fx0SzBYCc+aRPkh7lPV7eXdZAWufxUO/6eVKiHBQ2HUO
 RFDkOZU0r+c=
 =gpHw
 -----END PGP SIGNATURE-----

Merge tag 'locking-core-2026-06-14' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Futex updates:

   - Optimize futex hash bucket access patterns (Peter Zijlstra)

   - Large series to address the robust futex unlock race for real, by
     Thomas Gleixner:

      "The robust futex unlock mechanism is racy in respect to the
       clearing of the robust_list_head::list_op_pending pointer because
       unlock and clearing the pointer are not atomic.

       The race window is between the unlock and clearing the pending op
       pointer. If the task is forced to exit in this window, exit will
       access a potentially invalid pending op pointer when cleaning up
       the robust list.

       That happens if another task manages to unmap the object
       containing the lock before the cleanup, which results in an UAF.

       In the worst case this UAF can lead to memory corruption when
       unrelated content has been mapped to the same address by the time
       the access happens.

       User space can't solve this problem without help from the kernel.
       This series provides the kernel side infrastructure to help it
       along:

        1) Combined unlock, pointer clearing, wake-up for the
           contended case

        2) VDSO based unlock and pointer clearing helpers with a
           fix-up function in the kernel when user space was interrupted
           within the critical section.

      ... with help by André Almeida:

        - Add a note about robust list race condition (André Almeida)
        - Add self-tests for robust release operations (André Almeida)

  Context analysis updates:

   - Implement context analysis for 'struct rt_mutex'. (Bart Van Assche)
   - Bump required Clang version to 23 (Marco Elver)

  Guard infrastructure updates:

   - Series to remove NULL check from unconditional guards (Dmitry
     Ilvokhin)

  Lockdep updates:

   - Restore self-test migrate_disable() and sched_rt_mutex state on
     PREEMPT_RT (Karl Mehltretter)

  Membarriers updates:

   - Use per-CPU mutexes for targeted commands (Aniket Gattani)
   - Modernize membarrier_global_expedited with cleanup guards (Aniket
     Gattani)
   - Add rseq stress test for CFS throttle interactions (Aniket Gattani)

  percpu-rwsems updates:

   - Extract __percpu_up_read() to optimize inlining overhead (Dmitry
     Ilvokhin)

  Seqlocks updates:

   - Allow UBSAN_ALIGNMENT to fail optimizing (Heiko Carstens)

  Lock tracing:

   - Add contended_release tracepoint to sleepable locks such as
     mutexes, percpu-rwsems, rtmutexes, rwsems and semaphores (Dmitry
     Ilvokhin)

  MAINTAINERS updates:

   - MAINTAINERS: Add RUST [SYNC] entry (Boqun Feng)

  Misc updates and fixes by Randy Dunlap, YE WEI-HONG, Fabricio Parra,
  Dmitry Ilvokhin and Peter Zijlstra"

* tag 'locking-core-2026-06-14' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip: (36 commits)
  locking: Add contended_release tracepoint to sleepable locks
  locking/percpu-rwsem: Extract __percpu_up_read()
  tracing/lock: Remove unnecessary linux/sched.h include
  futex: Optimize futex hash bucket access patterns
  rust: sync: completion: Mark inline complete_all and wait_for_completion
  MAINTAINERS: Add RUST [SYNC] entry
  cleanup: Specify nonnull argument index
  selftests: futex: Add tests for robust release operations
  Documentation: futex: Add a note about robust list race condition
  x86/vdso: Implement __vdso_futex_robust_try_unlock()
  x86/vdso: Prepare for robust futex unlock support
  futex: Provide infrastructure to plug the non contended robust futex unlock race
  futex: Add robust futex unlock IP range
  futex: Add support for unlocking robust futexes
  futex: Cleanup UAPI defines
  x86: Select ARCH_MEMORY_ORDER_TSO
  uaccess: Provide unsafe_atomic_store_release_user()
  futex: Provide UABI defines for robust list entry modifiers
  futex: Move futex related mm_struct data into a struct
  futex: Make futex_mm_init() void
  ...
History 2026-06-15 14:21:14 +05:30
..
advise.c io_uring: finish IOU_OK -> IOU_COMPLETE transition 2025-05-21 08:41:16 -06:00
advise.h io_uring: split out fadvise/madvise operations 2022-07-24 18:39:11 -06:00
alloc_cache.c io_uring: add alloc_cache.c 2025-01-28 15:10:40 -07:00
alloc_cache.h io_uring/rsrc: use kvfree() for the imu cache 2026-04-21 12:19:01 -06:00
bpf-ops.c io_uring: unify getting ctx from passed in file descriptor 2026-04-08 13:21:35 -06:00
bpf-ops.h io_uring/bpf-ops: implement bpf ops registration 2026-03-16 16:15:00 -06:00
bpf_filter.c Merge branch 'io_uring-7.0' into for-7.1/io_uring 2026-03-14 08:57:15 -06:00
bpf_filter.h io_uring: allow registration of per-task restrictions 2026-02-06 07:29:19 -07:00
cancel.c io_uring: hold uring_lock across io_kill_timeouts() in cancel path 2026-05-11 11:14:38 -06:00
cancel.h io_uring/cancel: de-unionize file and user_data in struct io_cancel_data 2026-02-16 14:16:27 -07:00
cmd_net.c io_uring/cmd_net: split ioctl code out of io_uring_cmd_sock() 2026-03-09 07:21:53 -06:00
epoll.c io_uring: finish IOU_OK -> IOU_COMPLETE transition 2025-05-21 08:41:16 -06:00
epoll.h io_uring/epoll: add support for IORING_OP_EPOLL_WAIT 2025-02-20 07:59:56 -07:00
eventfd.c io_uring/eventfd: reset deferred signal state 2026-05-03 23:21:40 -06:00
eventfd.h io_uring: Add SPDX id lines to remaining source files 2026-02-04 07:23:45 -07:00
fdinfo.c io_uring/fdinfo: translate SqThread PID through caller's pid_ns 2026-05-11 07:44:09 -06:00
fdinfo.h io_uring: move fdinfo helpers to its own file 2022-07-24 18:39:12 -06:00
filetable.c io_uring/filetable: clamp alloc_hint to the configured alloc range 2026-02-11 15:20:44 -07:00
filetable.h io_uring: Trim out unused includes 2026-01-05 17:08:20 -07:00
fs.c non-consuming variants of do_{unlinkat,rmdir}() 2026-01-16 12:51:50 -05:00
fs.h io_uring: split out filesystem related operations 2022-07-24 18:39:11 -06:00
futex.c futex: Add support for unlocking robust futexes 2026-06-03 11:38:51 +02:00
futex.h io_uring: move cancelations to be io_uring_task based 2024-11-06 13:55:38 -07:00
io-wq.c io-wq: check that the predecessor is hashed in io_wq_remove_pending() 2026-05-13 13:06:37 -06:00
io-wq.h io_uring: Add SPDX id lines to remaining source files 2026-02-04 07:23:45 -07:00
io_uring.c io_uring: propagate array_index_nospec opcode into req->opcode 2026-05-18 08:59:12 -06:00
io_uring.h for-7.1/io_uring-20260411 2026-04-13 16:22:30 -07:00
kbuf.c io_uring/kbuf: don't truncate end buffer for bundles 2026-06-07 16:11:47 -06:00
kbuf.h io_uring/kbuf: support min length left for incremental buffers 2026-04-28 16:08:56 -06:00
Kconfig io_uring/bpf-ops: implement loop_step with BPF struct_ops 2026-03-16 16:15:00 -06:00
loop.c io_uring: introduce callback driven main loop 2026-03-16 16:15:00 -06:00
loop.h io_uring: introduce callback driven main loop 2026-03-16 16:15:00 -06:00
Makefile io_uring/bpf-ops: implement loop_step with BPF struct_ops 2026-03-16 16:15:00 -06:00
memmap.c io_uring: take page references for NOMMU pbuf_ring mmaps 2026-04-21 20:14:39 -06:00
memmap.h io_uring: Add SPDX id lines to remaining source files 2026-02-04 07:23:45 -07:00
mock_file.c Convert 'alloc_obj' family to use the new default GFP_KERNEL argument 2026-02-21 17:09:51 -08:00
msg_ring.c io_uring: switch struct io_ring_ctx internal bitfields to flags 2026-03-16 15:32:59 -06:00
msg_ring.h io_uring/msg_ring: Drop custom destructor 2024-12-27 10:08:21 -07:00
napi.c io_uring/napi: clear tracked NAPI entries on unregister 2026-05-03 23:21:23 -06:00
napi.h io_uring/napi: clear tracked NAPI entries on unregister 2026-05-03 23:21:23 -06:00
net.c io_uring/net: inherit IORING_CQE_F_BUF_MORE across bundle recv retries 2026-06-05 05:20:25 -06:00
net.h io_uring/zctx: unify zerocopy issue variants 2026-03-09 07:21:54 -06:00
nop.c io_uring/nop: pass all errors to userspace 2026-05-21 11:10:56 -06:00
nop.h io_uring: move nop into its own file 2022-07-24 18:39:11 -06:00
notif.c io_uring: Add SPDX id lines to remaining source files 2026-02-04 07:23:45 -07:00
notif.h io_uring/notif: implement notification stacking 2024-04-22 19:31:18 -06:00
opdef.c io_uring: remove iopoll_queue from struct io_issue_def 2026-03-16 16:14:14 -06:00
opdef.h io_uring: remove iopoll_queue from struct io_issue_def 2026-03-16 16:14:14 -06:00
openclose.c io_uring/openclose: fix io_pipe_fixed() slot tracking for specific slots 2026-02-11 20:31:21 -07:00
openclose.h io_uring/bpf_filter: allow filtering on contents of struct open_how 2026-01-27 11:10:46 -07:00
poll.c io_uring/poll: ensure EPOLL_ONESHOT is propagated for EPOLL_URING_WAKE 2026-04-21 19:18:34 -06:00
poll.h io_uring: add wrapper type for io_req_tw_func_t arg 2025-11-03 08:31:26 -07:00
query.c io_uring/zcrx: declare some constants for query 2026-03-09 07:21:54 -06:00
query.h io_uring/query: drop unused io_handle_query_entry() ctx arg 2025-11-26 09:37:10 -07:00
refs.h io_uring: Add SPDX id lines to remaining source files 2026-02-04 07:23:45 -07:00
register.c io_uring/register: fix ring resizing with mixed/large SQEs/CQEs 2026-04-21 12:19:08 -06:00
register.h io_uring: unify getting ctx from passed in file descriptor 2026-04-08 13:21:35 -06:00
rsrc.c io_uring/rsrc: use kvfree() for the imu cache 2026-04-21 12:19:01 -06:00
rsrc.h io_uring/rsrc: unify nospec indexing for direct descriptors 2026-04-21 12:18:54 -06:00
rw.c io_uring/rw: drop unused attr_type_mask from io_prep_rw_pi() 2026-05-13 06:35:57 -06:00
rw.h io_uring: add wrapper type for io_req_tw_func_t arg 2025-11-03 08:31:26 -07:00
slist.h io_uring: Add SPDX id lines to remaining source files 2026-02-04 07:23:45 -07:00
splice.c io_uring: don't include filetable.h in io_uring.h 2025-09-08 13:20:46 -06:00
splice.h io_uring/splice: open code 2nd direct file assignment 2024-10-29 13:43:28 -06:00
sqpoll.c io_uring/tctx: have io_uring_alloc_task_context() return tctx 2026-04-08 13:21:30 -06:00
sqpoll.h io_uring/sqpoll: switch away from getrusage() for CPU accounting 2025-10-22 10:51:20 -06:00
statx.c allow incomplete imports of filenames 2026-01-13 15:18:07 -05:00
statx.h io_uring: move statx handling to its own file 2022-07-24 18:39:11 -06:00
sync.c io_uring/sync: validate passed in offset 2026-01-21 11:50:59 -07:00
sync.h io_uring: split out fs related sync/fallocate functions 2022-07-24 18:39:11 -06:00
tctx.c io_uring/tctx: set ->io_uring before publishing the tctx node 2026-05-24 12:01:15 -06:00
tctx.h io_uring/tctx: have io_uring_alloc_task_context() return tctx 2026-04-08 13:21:30 -06:00
timeout.c io_uring/timeout: splice timed out link in timeout handler 2026-05-20 10:02:58 -06:00
timeout.h io_uring/timeout: migrate reqs from ts64 to ktime 2026-03-09 07:21:54 -06:00
truncate.c fs: pass on FTRUNCATE_* flags to do_truncate 2026-03-23 12:41:57 +01:00
truncate.h io_uring: add support for ftruncate 2024-02-09 09:04:39 -07:00
tw.c io_uring/tw: serialize ctx->retry_llist with ->uring_lock 2026-04-30 06:57:20 -06:00
tw.h io_uring: split out CQ waiting code into wait.c 2026-01-22 09:21:16 -07:00
uring_cmd.c io_uring/uring_cmd: allow non-iopoll cmds with IORING_SETUP_IOPOLL 2026-03-16 16:14:14 -06:00
uring_cmd.h io_uring/cmd: remove struct io_uring_cmd_data 2025-07-18 12:34:56 -06:00
wait.c io_uring/wait: fix min_timeout behavior 2026-06-07 16:12:32 -06:00
wait.h for-7.1/io_uring-20260411 2026-04-13 16:22:30 -07:00
waitid.c io_uring/waitid: clear waitid info before copying it to userspace 2026-05-16 12:58:21 -06:00
waitid.h io_uring: move cancelations to be io_uring_task based 2024-11-06 13:55:38 -07:00
xattr.c Convert 'alloc_obj' family to use the new default GFP_KERNEL argument 2026-02-21 17:09:51 -08:00
xattr.h io_uring: move xattr related opcodes to its own file 2022-07-24 18:39:11 -06:00
zcrx.c net: add net_iov_init() and use it to initialize ->page_type 2026-04-29 16:40:08 -07:00
zcrx.h io_uring/zcrx: rename zcrx [un]register functions 2026-04-01 10:21:13 -06:00