)]}'
{
  "log": [
    {
      "commit": "a10946dc51eeababc48ee10baf0d17489f647a80",
      "tree": "1c2719dcc94382a836b596313eeceeb44cf49a8f",
      "parents": [
        "67bc5dcc7dc31b81bc623074887e2a231ede3b54",
        "2ffb54892358920e18ceb7aee375dc75263b6e43"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Thu Nov 12 09:40:07 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Thu Nov 12 09:40:07 2026 -0700"
      },
      "message": "Merge branch \u0027sqpoll-disable-exit-null-out\u0027 of github.com:ManoharPaturi/liburing\n\n* \u0027sqpoll-disable-exit-null-out\u0027 of github.com:ManoharPaturi/liburing:\n  test/sqpoll-disable-exit: pass real output pointers to the setup helper\n"
    },
    {
      "commit": "2ffb54892358920e18ceb7aee375dc75263b6e43",
      "tree": "d5673ec4aca23d4d567fc4e0cd3beff8b42a311c",
      "parents": [
        "78dce99b660fd1caaf70ef6573a88bae9bbf6476"
      ],
      "author": {
        "name": "Manohar Paturi",
        "email": "manoharpaturi777@gmail.com",
        "time": "Thu Nov 12 08:04:49 2026 +0530"
      },
      "committer": {
        "name": "Manohar Paturi",
        "email": "manoharpaturi777@gmail.com",
        "time": "Thu Nov 12 08:04:49 2026 +0530"
      },
      "message": "test/sqpoll-disable-exit: pass real output pointers to the setup helper\n\nsyz_io_uring_setup() stores the mapped ring and SQEs pointers through\nits last two arguments, but execute_one() passes NULL for both, so every\nforked iteration crashes on a NULL write right after the first mmap().\nThe reproduction therefore never reaches the exit path it is meant to\nexercise, and the run spams crashes (and core dumps, where enabled) for\nall 100 iterations.\n\nHand it the addresses of local variables instead, so the setup runs to\ncompletion like the original syzkaller program.\n\nFixes: https://github.com/axboe/liburing/issues/1632\nSigned-off-by: Manohar Paturi \u003cmanoharpaturi777@gmail.com\u003e\n"
    },
    {
      "commit": "67bc5dcc7dc31b81bc623074887e2a231ede3b54",
      "tree": "71276f7363f22dc1a8b35bbed9415f8f79741bed",
      "parents": [
        "c63f4aa6f930bed36589b4c738a9da5a6cd564bd",
        "dbed114ea8c17abd5a2eeb6224e592bb3bca9e01"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Nov 09 14:04:45 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Nov 09 14:04:45 2026 -0700"
      },
      "message": "Merge branch \u0027fix/ffi-map-shift-helpers\u0027 of github.com:0z5a/liburing\n\n* \u0027fix/ffi-map-shift-helpers\u0027 of github.com:0z5a/liburing:\n  liburing-ffi.map: add the SQ/CQ index helpers\n"
    },
    {
      "commit": "dbed114ea8c17abd5a2eeb6224e592bb3bca9e01",
      "tree": "71276f7363f22dc1a8b35bbed9415f8f79741bed",
      "parents": [
        "c63f4aa6f930bed36589b4c738a9da5a6cd564bd"
      ],
      "author": {
        "name": "Dezhen Lu",
        "email": "dezhen.lu@student.uni-tuebingen.de",
        "time": "Mon Nov 09 13:43:50 2026 +0100"
      },
      "committer": {
        "name": "Dezhen Lu",
        "email": "dezhen.lu@student.uni-tuebingen.de",
        "time": "Mon Nov 09 13:46:15 2026 +0100"
      },
      "message": "liburing-ffi.map: add the SQ/CQ index helpers\n\nio_uring_sqe_shift(), io_uring_cqe_shift(), their _from_flags()\nvariants and io_uring_load_sq_head() are inline helpers in liburing.h,\nand the header documents the shift helpers as the way to index the SQE\nand CQE arrays. liburing-ffi exports the other inline helpers, but not\nthese, so FFI users get \"undefined symbol\" when they look them up.\n\nAdd them to the 2.16 section of the ffi map.\n\nCloses: https://github.com/axboe/liburing/issues/1672\nAssisted-by: Claude:claude-opus-5-5 \u003cnoreply@anthropic.com\u003e\nSigned-off-by: Dezhen Lu \u003cdezhen.lu@student.uni-tuebingen.de\u003e\n"
    },
    {
      "commit": "c63f4aa6f930bed36589b4c738a9da5a6cd564bd",
      "tree": "b54f1ff8e3a31247a2df70a788b35c4cc8820b79",
      "parents": [
        "6ee9012ddb7fd865a5f61623da4448210097ce7e"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:13:45 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:13:45 2026 -0700"
      },
      "message": "Bump version to 2.16\n\nNext version released will be 2.16, and we\u0027re overdue for bumping\nthe release number. Do that now.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "6ee9012ddb7fd865a5f61623da4448210097ce7e",
      "tree": "d717ae8ca24c3f5b6a2b153f25eec20b9d021b22",
      "parents": [
        "4670765af76a52dd782e95daa98a4fa029c8ed79",
        "bae030303c7afaac3dab65813941a4fba87cbb94"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:11:03 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:11:03 2026 -0700"
      },
      "message": "Merge branch \u0027hunt/liburing-dontfork\u0027 of github.com:Nexory/liburing\n\n* \u0027hunt/liburing-dontfork\u0027 of github.com:Nexory/liburing:\n  test: add ring-dontfork-mem test\n  setup: make io_uring_ring_dontfork() cover rings on app memory\n"
    },
    {
      "commit": "4670765af76a52dd782e95daa98a4fa029c8ed79",
      "tree": "375bbd0cbea1d7ee79baf20d859fe5dd7cd6aa31",
      "parents": [
        "f99f3792d17a459270787bbb57c48ecbff820359",
        "3306b24d472335d201ef0d0dbe6caa1d63dc9735"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:10:03 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:10:03 2026 -0700"
      },
      "message": "Merge branch \u0027io_uring_setup_buf_ring_param\u0027 of github.com:eqvinox/liburing\n\n* \u0027io_uring_setup_buf_ring_param\u0027 of github.com:eqvinox/liburing:\n  setup: add variant taking io_uring_buf_reg input\n"
    },
    {
      "commit": "f99f3792d17a459270787bbb57c48ecbff820359",
      "tree": "d9dcdf379456ecddce3e23730735e61bf19a5a2b",
      "parents": [
        "5f11d35bd735959b89145e284259b5e082bab333",
        "c2324f910dd7287446eee2026e4e5215eca70c4e"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:09:10 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:09:10 2026 -0700"
      },
      "message": "Merge branch \u0027resize-closed-ring-fd\u0027 of github.com:immanuwell/liburing\n\n* \u0027resize-closed-ring-fd\u0027 of github.com:immanuwell/liburing:\n  test/reg-reg-ring: resize rings after closing the ring fd\n  src/register: fail io_uring_resize_rings() early if ring fd is closed\n"
    },
    {
      "commit": "5f11d35bd735959b89145e284259b5e082bab333",
      "tree": "1e92344a75ce7270de5541c4d827ea924c55a980",
      "parents": [
        "4de23eba502321acfab4332d0edf769e4e8c2351",
        "00cc8aab78709cea5f55371ab61f560ec3f7cea5"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:07:41 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:07:41 2026 -0700"
      },
      "message": "Merge branch \u0027read-mshot-fuse-test\u0027 of github.com:7z0423arsenova/liburing\n\n* \u0027read-mshot-fuse-test\u0027 of github.com:7z0423arsenova/liburing:\n  test: cover FUSE multishot read completion after unmount\n"
    },
    {
      "commit": "4de23eba502321acfab4332d0edf769e4e8c2351",
      "tree": "227be7c42810b2dc1f8a17600c64b1d0f7742e5b",
      "parents": [
        "8479f6cb9d37932ddb1793aea1c67b04ad6ce011",
        "36c5b9d3fc6ea03e772616139604487a5ca1bcc5"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:06:06 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:06:06 2026 -0700"
      },
      "message": "Merge branch \u0027fix/manIoUringSetupAtomicLoadAcquire\u0027 of github.com:danielzgtg/liburing\n\n* \u0027fix/manIoUringSetupAtomicLoadAcquire\u0027 of github.com:danielzgtg/liburing:\n  man: use atomic_load_acquire from comment\n"
    },
    {
      "commit": "8479f6cb9d37932ddb1793aea1c67b04ad6ce011",
      "tree": "bc1107c3cb811904b106f4fc2ed72bcf4ad57626",
      "parents": [
        "c6da6135fd7366fd3b18cec04f2df219f3a73979",
        "568b2ba68c6d5b8d2d3accb5be2c72664924027b"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:05:40 2026 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Nov 04 12:05:40 2026 -0700"
      },
      "message": "Merge branch \u0027fix/manIoUringOutOfBoundsReadStrlen\u0027 of github.com:danielzgtg/liburing\n\n* \u0027fix/manIoUringOutOfBoundsReadStrlen\u0027 of github.com:danielzgtg/liburing:\n  man: use actual len to avoid out-of-bounds strlen read\n"
    },
    {
      "commit": "568b2ba68c6d5b8d2d3accb5be2c72664924027b",
      "tree": "bc1107c3cb811904b106f4fc2ed72bcf4ad57626",
      "parents": [
        "c6da6135fd7366fd3b18cec04f2df219f3a73979"
      ],
      "author": {
        "name": "Daniel Tang",
        "email": "danielzgtg.opensource@gmail.com",
        "time": "Mon Nov 02 22:04:07 2026 -0500"
      },
      "committer": {
        "name": "Daniel Tang",
        "email": "danielzgtg.opensource@gmail.com",
        "time": "Wed Nov 04 01:35:32 2026 -0500"
      },
      "message": "man: use actual len to avoid out-of-bounds strlen read\n\nWe have the actual count of bytes read, so use it instead of\nrecalculating using strlen. That strlen was unsafe, as gdb\u0027s rwatch\nshows it dereferencing a read past the end of buf and into the following\noffset variable. Logically, the strlen also resulted in NUL bytes being\nwrongly discarded in `cat /bin/bash | ./a.out | wc -c`.\n\nWe also have the count of bytes written, so use it instead of imputing\nit from the bytes read.\n\nSigned-off-by: Daniel Tang \u003cdanielzgtg.opensource@gmail.com\u003e\nFixes: 26afb36efb3c (\"Adding full example to io_uring(7) man page while also fixing some text to comply to the \"semantic new lines\" recommendation from man-pages(7).\")\n"
    },
    {
      "commit": "36c5b9d3fc6ea03e772616139604487a5ca1bcc5",
      "tree": "d51f048e47572a0a19a6f97008320270f24b615e",
      "parents": [
        "c6da6135fd7366fd3b18cec04f2df219f3a73979"
      ],
      "author": {
        "name": "Daniel Tang",
        "email": "danielzgtg.opensource@gmail.com",
        "time": "Sun Nov 01 20:53:05 2026 -0500"
      },
      "committer": {
        "name": "Daniel Tang",
        "email": "danielzgtg.opensource@gmail.com",
        "time": "Sun Nov 01 20:57:25 2026 -0500"
      },
      "message": "man: use atomic_load_acquire from comment\n\nA commit replaced a memory barrier with a comment saying only\nmemory_order_acquire semantics are required. This PR fixes the typo\nwhere atomic_load_relaxed was used instead.\n\nFixes: 6768ddcc562a (\"man/io_uring_setup.2: improve SQPOLL wakeup example\")\nSigned-off-by: Daniel Tang \u003cdanielzgtg.opensource@gmail.com\u003e\n"
    },
    {
      "commit": "00cc8aab78709cea5f55371ab61f560ec3f7cea5",
      "tree": "856b2fa68293901712bc510323c3b5cf64eaf2d8",
      "parents": [
        "236c1525ff1b2ea5870ecada04951eb2d053275e"
      ],
      "author": {
        "name": "Arsenova",
        "email": "7z0423arsenova@proton.me",
        "time": "Fri Oct 30 03:23:22 2026 +0800"
      },
      "committer": {
        "name": "Arsenova",
        "email": "7z0423arsenova@proton.me",
        "time": "Fri Oct 30 03:23:22 2026 +0800"
      },
      "message": "test: cover FUSE multishot read completion after unmount\n\nA pending READ_MULTISHOT on /dev/fuse can remain armed indefinitely\nafter the FUSE filesystem is unmounted. The disconnected device signals\nEPOLLERR, while io_uring waits for EPOLLIN before retrying the read.\n\nAdd a raw FUSE test in a private mount namespace. Complete FUSE_INIT\nsynchronously, arm a multishot read, unmount, and require a terminal\n-ENODEV CQE without IORING_CQE_F_MORE. Use a user namespace when running\nunprivileged, and skip if the required FUSE or namespace support is\nunavailable.\n\nLink: https://github.com/axboe/liburing/issues/1631\nSigned-off-by: Arsenova \u003c7z0423arsenova@proton.me\u003e\n"
    },
    {
      "commit": "c2324f910dd7287446eee2026e4e5215eca70c4e",
      "tree": "930cb57d0fbb1df7c2c1cff2b06020d2a142f6de",
      "parents": [
        "39fa759107738bfaf7d98448604a40c0a715e5f6"
      ],
      "author": {
        "name": "Immanuel Tikhonov",
        "email": "pchpr.00@list.ru",
        "time": "Thu Oct 29 16:53:13 2026 +0400"
      },
      "committer": {
        "name": "Immanuel Tikhonov",
        "email": "pchpr.00@list.ru",
        "time": "Thu Oct 29 16:53:13 2026 +0400"
      },
      "message": "test/reg-reg-ring: resize rings after closing the ring fd\n\nCheck that io_uring_resize_rings() fails with -EBADF and leaves the ring\nusable once the ring fd is closed. Without the previous change the ring\nis resized anyway and io_uring_submit_and_wait() returns 0.\n\nSigned-off-by: Immanuel Tikhonov \u003cpchpr.00@list.ru\u003e\n"
    },
    {
      "commit": "39fa759107738bfaf7d98448604a40c0a715e5f6",
      "tree": "72146605dc906fab412ffe52337c9822d1811a39",
      "parents": [
        "c6da6135fd7366fd3b18cec04f2df219f3a73979"
      ],
      "author": {
        "name": "Immanuel Tikhonov",
        "email": "pchpr.00@list.ru",
        "time": "Thu Oct 29 16:53:13 2026 +0400"
      },
      "committer": {
        "name": "Immanuel Tikhonov",
        "email": "pchpr.00@list.ru",
        "time": "Thu Oct 29 16:53:13 2026 +0400"
      },
      "message": "src/register: fail io_uring_resize_rings() early if ring fd is closed\n\nio_uring_resize_rings() mmaps the new rings through ring-\u003ering_fd, which\nis -1 after io_uring_close_ring_fd(). The mmap then fails with -EBADF,\nbut only after the kernel already resized the ring, so liburing is left\non the old mappings. Submits go nowhere and no CQEs show up.\n\nReturn -EBADF before the resize, so a failed call leaves the ring\nusable.\n\nSigned-off-by: Immanuel Tikhonov \u003cpchpr.00@list.ru\u003e\n"
    },
    {
      "commit": "c6da6135fd7366fd3b18cec04f2df219f3a73979",
      "tree": "3025796ea3c18872f056ee5c88702d233281bbe7",
      "parents": [
        "cc4b521548b12d5466db07a5481211eedcdea54d",
        "255edcdc6db4e3502902f01245daf569e54ef082"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Oct 27 19:03:09 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Oct 27 19:03:09 2026 -0600"
      },
      "message": "Merge branch \u0027connect-backlog\u0027 of github.com:daandemeyer/liburing\n\n* \u0027connect-backlog\u0027 of github.com:daandemeyer/liburing:\n  test: add connect-backlog test\n"
    },
    {
      "commit": "255edcdc6db4e3502902f01245daf569e54ef082",
      "tree": "f221e05834d940bb8a957233890181f9af2731cd",
      "parents": [
        "a33a770d8379978660036251e14710c6ee8a3d34"
      ],
      "author": {
        "name": "Daan De Meyer",
        "email": "daan@amutable.com",
        "time": "Tue Oct 27 14:56:58 2026 +0100"
      },
      "committer": {
        "name": "Daan De Meyer",
        "email": "daan@amutable.com",
        "time": "Tue Oct 27 20:52:26 2026 +0100"
      },
      "message": "test: add connect-backlog test\n\nIORING_OP_CONNECT on a non-blocking AF_UNIX socket whose listener has a\nfull backlog retries the connect 128 times and then punts it to io-wq.\nThe io-wq attempt is non-blocking too, so the request fails with -EAGAIN\nanyway, like connect(2) does right away. Let\u0027s test that the request\ncompletes with -EAGAIN without starting an io-wq worker.\n\nAlso test that a blocking connect to a full backlog waits until accept()\nmakes room, and that a non-blocking TCP connect that gets -EINPROGRESS\nwaits for the handshake to complete. Each test runs in its own process,\nso it doesn\u0027t see io-wq workers that an earlier test started.\n\nThe non-blocking test fails on kernels without the kernel commit\n\"io_uring/net: don\u0027t retry a non-blocking connect() that fails with\n-EAGAIN\".\n\nSigned-off-by: Daan De Meyer \u003cdaan@amutable.com\u003e\n"
    },
    {
      "commit": "cc4b521548b12d5466db07a5481211eedcdea54d",
      "tree": "abe007ec42b42cb1ac7ec978019e1fd7ede70591",
      "parents": [
        "5a328214d775f44f5934130cd5d323b564da98c2",
        "6c0f9da7f38fc3cb41c6d68ec9320ec7d7cfcca7"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Oct 26 10:04:21 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Oct 26 10:04:21 2026 -0600"
      },
      "message": "Merge branch \u0027bpf-filter-docs\u0027 of github.com:gvozdetsky/liburing\n\n* \u0027bpf-filter-docs\u0027 of github.com:gvozdetsky/liburing:\n  man/io_uring_register_bpf_filter.3: document CONNECT, word loads and exec\n  io_uring/bpf_filter.h: update for IORING_OP_CONNECT\n"
    },
    {
      "commit": "5a328214d775f44f5934130cd5d323b564da98c2",
      "tree": "4e5cc8f9362924cb58e850e405660ff849a747aa",
      "parents": [
        "236c1525ff1b2ea5870ecada04951eb2d053275e",
        "d0bf5385954feeac9330e82b16e19aeb33746a5a"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Oct 24 10:35:41 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Oct 24 10:35:41 2026 -0600"
      },
      "message": "Merge branch \u0027wait-timeout-boottime\u0027 of github.com:7z0423arsenova/liburing\n\n* \u0027wait-timeout-boottime\u0027 of github.com:7z0423arsenova/liburing:\n  test/wait-timeout: use the registered clock for absolute timeouts\n"
    },
    {
      "commit": "d0bf5385954feeac9330e82b16e19aeb33746a5a",
      "tree": "4e5cc8f9362924cb58e850e405660ff849a747aa",
      "parents": [
        "236c1525ff1b2ea5870ecada04951eb2d053275e"
      ],
      "author": {
        "name": "Arsenova",
        "email": "7z0423arsenova@proton.me",
        "time": "Sat Oct 24 15:33:49 2026 +0800"
      },
      "committer": {
        "name": "Arsenova",
        "email": "7z0423arsenova@proton.me",
        "time": "Sat Oct 24 15:33:49 2026 +0800"
      },
      "message": "test/wait-timeout: use the registered clock for absolute timeouts\n\nWhen the test registers CLOCK_BOOTTIME on the ring, it still computes\nthe absolute deadlines and the elapsed time from CLOCK_MONOTONIC. The\ntwo clocks only agree on a machine that has never been suspended. Once\nit has, BOOTTIME runs ahead of MONOTONIC by the total suspend time, so\nthe \"2 seconds from now\" deadline is already in the past and the wait\nreturns -ETIME right away:\n\n  early wake up, 2563\n  test_timeout failed 1 1\n\nRead the time from the same clock that the ring uses.\n\nFixes: 050dd942 (\"test: test clockids and abs timeouts\")\nSigned-off-by: Arsenova \u003c7z0423arsenova@proton.me\u003e\n"
    },
    {
      "commit": "236c1525ff1b2ea5870ecada04951eb2d053275e",
      "tree": "7b92f6c148bc025d490d3fe1fef322ff371316ad",
      "parents": [
        "8cdf2ff078244bab35c2b35517e04f36cde69153"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 23 09:47:36 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 23 09:49:31 2026 -0600"
      },
      "message": "test/task-restrict: test register op restrictions on ring-less register ops\n\nWith a per-task register opcode allowlist, check that an allowed\nring-less operation (IORING_REGISTER_QUERY) still works, and that the\ndenied ones fail with -EACCES: a synchronous msg_ring must not post a\nCQE to the target ring, and a task BPF filter must not register.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "8cdf2ff078244bab35c2b35517e04f36cde69153",
      "tree": "10b62d1c44abd3c5e9b15b059c279909d719b39f",
      "parents": [
        "f33bc2f24cf3b38df8553aab5f9714fc5cf0aff4"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 23 09:47:36 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 23 09:49:09 2026 -0600"
      },
      "message": "man: document per-task restrictions ring-less register ops\n\nIORING_REGISTER_RESTRICTIONS with fd \u003d\u003d -1 registers restrictions for\nthe task rather than a ring. Describe that form, and note that the\nregister opcode allowlist also covers the operations issued with fd \u003d\u003d\n-1. In particular IORING_REGISTER_SEND_MSG_RING has no source ring, so\nneither an IORING_OP_MSG_RING restriction nor a BPF filter applies to\nit; a sandbox must exclude the register opcode itself.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "3306b24d472335d201ef0d0dbe6caa1d63dc9735",
      "tree": "e65fbf1a10e5d8d4be9af4cbe76af0d471105743",
      "parents": [
        "f33bc2f24cf3b38df8553aab5f9714fc5cf0aff4"
      ],
      "author": {
        "name": "David \u0027equinox\u0027 Lamparter",
        "email": "equinox@diac24.net",
        "time": "Thu Oct 22 02:18:14 2026 +0200"
      },
      "committer": {
        "name": "David \u0027equinox\u0027 Lamparter",
        "email": "equinox@diac24.net",
        "time": "Fri Oct 23 00:25:53 2026 +0200"
      },
      "message": "setup: add variant taking io_uring_buf_reg input\n\nstruct io_uring_buf_reg has gotten the \"min_size\" field added recently,\nand now something for alignment for incremental consumption is being\nworked on.  io_uring_setup_buf_ring has the original fields as function\nparameters, individually, so there\u0027s no way to pass min_size or anything\nelse added in the future.\n\nRather than creating a new variant with different parameters each time\nsomething gets added, this just creates one that takes io_uring_buf_reg\nas input.  This way, at least additions that don\u0027t need special handling\nin setup can just be transparently passed through to the kernel.  It\u0027s\nconst since (a) it can indeed be a constant for simple applications and\n(b) it makes obvious to consumers it won\u0027t be updated for changes.\n\nTest by running recvmsg-inc-tail twice, the 2nd time using this new\nfunction instead of setting up its own buffer ring.\n\nSigned-off-by: David \u0027equinox\u0027 Lamparter \u003cequinox@diac24.net\u003e\n"
    },
    {
      "commit": "f33bc2f24cf3b38df8553aab5f9714fc5cf0aff4",
      "tree": "cbd95e7fcef28400baaa5ffa3fb546f686f77da2",
      "parents": [
        "73e93dfd1167cfce66ce1b09466fc97fa6dedd6d",
        "30b07bf2c3199676cc77a0a2b82e2ab3f3e41fda"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Thu Oct 22 13:28:14 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Thu Oct 22 13:28:14 2026 -0600"
      },
      "message": "Merge branch \u0027man-small-fixes\u0027 of github.com:ilyas-mallah/liburing\n\n* \u0027man-small-fixes\u0027 of github.com:ilyas-mallah/liburing:\n  man/io_uring_for_each_cqe.3: advance by CQ slots, not by CQEs\n  man/io_uring_prep_futex_waitv.3: drop the claim that flags is used\n  man/io_uring_prep_cmd_zone_reset_all.3: fill in the kernel version\n  man/io_uring_prep_send_zc.3: fix the send_zc_fixed prototype\n"
    },
    {
      "commit": "30b07bf2c3199676cc77a0a2b82e2ab3f3e41fda",
      "tree": "cbd95e7fcef28400baaa5ffa3fb546f686f77da2",
      "parents": [
        "6a55b6ff47ee651b9cf10a64addbc514a569f04c"
      ],
      "author": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "committer": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "message": "man/io_uring_for_each_cqe.3: advance by CQ slots, not by CQEs\n\nWith IORING_SETUP_CQE_MIXED the iterator steps over two CQ ring slots\nfor a 32b CQE, but the example counts one per CQE and passes that to\nio_uring_cq_advance(). The head ends short and CQEs are seen again.\nCount with io_uring_cqe_nr(), as io_uring_cqe_seen() does.\n\nFixes: 9cecbdb6092c (\"Add support for IORING_SETUP_CQE_MIXED\")\nSigned-off-by: Ilyas Mallah \u003cgithub@ilyasm.dev\u003e\n"
    },
    {
      "commit": "6a55b6ff47ee651b9cf10a64addbc514a569f04c",
      "tree": "9841cb129f60d670dbf62192122e2fdaf5e21b55",
      "parents": [
        "63d35490fecfa12af1290036ac74a3a95761a602"
      ],
      "author": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "committer": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "message": "man/io_uring_prep_futex_waitv.3: drop the claim that flags is used\n\nThe page says flags must be set to the futex flags, then that flags are\nunused and 0 must be passed. The second is right: io_futexv_prep()\nreturns -EINVAL for a non-zero sqe-\u003efutex_flags.\n\nFixes: e58e411434b2 (\"Add futex related man pages\")\nSigned-off-by: Ilyas Mallah \u003cgithub@ilyasm.dev\u003e\n"
    },
    {
      "commit": "63d35490fecfa12af1290036ac74a3a95761a602",
      "tree": "ab289e58209a56a62c2c0b5b1028bb78d18deb4d",
      "parents": [
        "e750261e751bf57092c8d95002f72bfe1e28251d"
      ],
      "author": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "committer": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "message": "man/io_uring_prep_cmd_zone_reset_all.3: fill in the kernel version\n\nThe page says \"Available since Linux 7.TBD\". The command is in Linux\n7.3, where block/ioctl.c handles BLOCK_URING_CMD_ZONE_RESET_ALL.\n\nFixes: 9d179918fcd0 (\"man: add io_uring_prep_cmd_zone_reset_all.3 man page\")\nSigned-off-by: Ilyas Mallah \u003cgithub@ilyasm.dev\u003e\n"
    },
    {
      "commit": "e750261e751bf57092c8d95002f72bfe1e28251d",
      "tree": "0fba5ffb96a0790846effd53bf2490e5f0dc6703",
      "parents": [
        "73e93dfd1167cfce66ce1b09466fc97fa6dedd6d"
      ],
      "author": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "committer": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Wed Oct 21 16:47:23 2026 +0200"
      },
      "message": "man/io_uring_prep_send_zc.3: fix the send_zc_fixed prototype\n\nThe prototype ends the zc_flags line with \");\" and puts buf_index on\nthe next line, so the synopsis is not a valid declaration. End the line\nwith a comma.\n\nFixes: d0ba54471342 (\"man: Add manpage for io_uring_prep_send_zc_fixed()\")\nSigned-off-by: Ilyas Mallah \u003cgithub@ilyasm.dev\u003e\n"
    },
    {
      "commit": "73e93dfd1167cfce66ce1b09466fc97fa6dedd6d",
      "tree": "fe3797a14152d0e702f6f13a0c021b1e0c33fd74",
      "parents": [
        "f4fdfd910ad15e5477c68f2eec208581e3f2239e",
        "acbe866a91a76737d343bae63de782e73234a537"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Oct 21 08:20:46 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Oct 21 08:20:46 2026 -0600"
      },
      "message": "Merge branch \u0027ffi-map-buf-ring-head\u0027 of github.com:ilyas-mallah/liburing\n\n* \u0027ffi-map-buf-ring-head\u0027 of github.com:ilyas-mallah/liburing:\n  src/liburing-ffi.map: add io_uring_buf_ring_head\n"
    },
    {
      "commit": "acbe866a91a76737d343bae63de782e73234a537",
      "tree": "fe3797a14152d0e702f6f13a0c021b1e0c33fd74",
      "parents": [
        "f4fdfd910ad15e5477c68f2eec208581e3f2239e"
      ],
      "author": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Tue Oct 20 03:28:39 2026 +0200"
      },
      "committer": {
        "name": "Ilyas Mallah",
        "email": "github@ilyasm.dev",
        "time": "Tue Oct 20 03:33:01 2026 +0200"
      },
      "message": "src/liburing-ffi.map: add io_uring_buf_ring_head\n\nFixes: 9304009f5546 (\"Add io_uring_buf_ring_head/available() to the exported list\")\nSigned-off-by: Ilyas Mallah \u003cgithub@ilyasm.dev\u003e\n"
    },
    {
      "commit": "f4fdfd910ad15e5477c68f2eec208581e3f2239e",
      "tree": "0b898508cecb3ad9c08d83dabb1f9801dd33c72d",
      "parents": [
        "5ff75106b614b3e8f28ad578a45179f295ff56da"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Oct 19 15:03:06 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Oct 19 15:03:12 2026 -0600"
      },
      "message": "test/waitid: test a non-blocking pidfd\n\nA pidfd opened with PIDFD_NONBLOCK implies WNOHANG, and waitid(2) fails\nwith -EAGAIN if the child hasn\u0027t changed state and WNOHANG wasn\u0027t passed\nin. Check that IORING_OP_WAITID does the same, that WNOHANG still\nreturns 0, and that the pidfd reaps the child once it has exited.\n\nLink: https://lore.kernel.org/io-uring/20261018025824.799245-1-nickolai@csail.mit.edu/\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "5ff75106b614b3e8f28ad578a45179f295ff56da",
      "tree": "4b01f8deb2725ea409182790d610d48c7bfadb28",
      "parents": [
        "efa5f5efbeef6967d0a69e3b2c620650e76f4624"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Oct 19 11:19:38 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Oct 19 12:58:48 2026 -0600"
      },
      "message": "test/waitid: accept -ETIME for a fired linked timeout\n\nA linked timeout that fires and cancels a waitid request now completes\nwith -ETIME, like it does for other requests. Older kernels completed\nit with 1. Accept both.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "efa5f5efbeef6967d0a69e3b2c620650e76f4624",
      "tree": "8b83b6f625f2390ed586221f0fd8574feb416455",
      "parents": [
        "d5b6007d06969c7ed4b4430ab439b388cb19607f"
      ],
      "author": {
        "name": "Pavel Begunkov",
        "email": "asml.silence@gmail.com",
        "time": "Fri Oct 16 17:25:05 2026 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 16 10:38:42 2026 -0600"
      },
      "message": "examples/zcrx: don\u0027t forget to sync dmabuf\n\ndma-bufs are not always coherent and we need to sync it before\naccessing. Use proper dma-buf API for that.\n\nSigned-off-by: Pavel Begunkov \u003casml.silence@gmail.com\u003e\nFixes: 93d3a7a70b4a6 (\"examples/zcrx: udmabuf backed areas\")\nLink: https://patch.msgid.link/73b2654e41519acb2ec310ba1d6dc99cbafcbdfd.1792167723.git.asml.silence@gmail.com\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "bae030303c7afaac3dab65813941a4fba87cbb94",
      "tree": "fce0f9b56a82c803c4a0600c5ce78d9e83178003",
      "parents": [
        "cfa2a3eb50f5012a33915e4a9e2bf32fb4a02e0e"
      ],
      "author": {
        "name": "Nexory",
        "email": "St4yl3r30@hotmail.de",
        "time": "Sat Oct 10 20:04:16 2026 +0200"
      },
      "committer": {
        "name": "Nexory",
        "email": "St4yl3r30@hotmail.de",
        "time": "Sat Oct 10 21:21:07 2026 +0200"
      },
      "message": "test: add ring-dontfork-mem test\n\nCheck that io_uring_ring_dontfork() keeps both the SQE region and the\nSQ/CQ ring region from a child after fork(), for a ring from\nio_uring_queue_init() and for one on application provided memory from\nio_uring_queue_init_mem().\n\nSigned-off-by: Nexory \u003cSt4yl3r30@hotmail.de\u003e\n"
    },
    {
      "commit": "cfa2a3eb50f5012a33915e4a9e2bf32fb4a02e0e",
      "tree": "63c21fd15244a4ab388b5f2e2c1babbb23864904",
      "parents": [
        "d5b6007d06969c7ed4b4430ab439b388cb19607f"
      ],
      "author": {
        "name": "Nexory",
        "email": "St4yl3r30@hotmail.de",
        "time": "Sat Oct 10 20:04:16 2026 +0200"
      },
      "committer": {
        "name": "Nexory",
        "email": "St4yl3r30@hotmail.de",
        "time": "Sat Oct 10 21:21:07 2026 +0200"
      },
      "message": "setup: make io_uring_ring_dontfork() cover rings on app memory\n\nFor a ring set up on application provided memory with\nio_uring_queue_init_mem(), io_uring_alloc_huge() sets sq-\u003ering_sz and\ncq-\u003ering_sz to 0, as io_uring_unmap_rings() uses them to tell whether\nthe library owns the mapping. io_uring_ring_dontfork() reads the same\nfields as the length passed to madvise(), so for such a ring the call\nfor the SQ/CQ ring region has a length of 0. It succeeds without effect,\nand io_uring_ring_dontfork() returns 0 although only the SQE region got\nMADV_DONTFORK.\n\nDerive the length of the ring region from the ring state when the field\nis 0, the same way io_uring_sqes_size() already does for the SQE region.\n\nSigned-off-by: Nexory \u003cSt4yl3r30@hotmail.de\u003e\n"
    },
    {
      "commit": "6c0f9da7f38fc3cb41c6d68ec9320ec7d7cfcca7",
      "tree": "bcad2f25f218d85df9212dc3ca4115c5122215b7",
      "parents": [
        "e5130046535c42b749f488563badb8e4eea3d959"
      ],
      "author": {
        "name": "Eugene Gvozdetsky",
        "email": "gvozdet@gmail.com",
        "time": "Fri Oct 09 18:47:28 2026 +0200"
      },
      "committer": {
        "name": "Eugene Gvozdetsky",
        "email": "gvozdet@gmail.com",
        "time": "Fri Oct 09 18:55:24 2026 +0200"
      },
      "message": "man/io_uring_register_bpf_filter.3: document CONNECT, word loads and exec\n\n- IORING_OP_CONNECT filtering (Linux 7.2): the context layout, when the\n  fields are populated, and its pdu_size.\n- Filters can only load aligned 32-bit words. Explain how to test\n  sqe_flags, with an example that denies provided-buffer selection.\n- Task filters are kept across exec; older kernels dropped them once the\n  task had used io_uring (bc0e8faf90e7).\n- A task filter makes a later task IORING_REGISTER_RESTRICTIONS fail\n  with -EPERM, so register the opcode allowlist first.\n\nChecked on 7.0 and 7.2.9: the CONNECT pdu_size write-back (0 on 7.0,\n24 on 7.2.9), the example (reads allowed, reads with buffer selection\nget -EACCES), and the -EPERM ordering.\n\nAssisted-by: Claude:claude-opus-5-5\nSigned-off-by: Eugene Gvozdetsky \u003cgvozdet@gmail.com\u003e\n"
    },
    {
      "commit": "e5130046535c42b749f488563badb8e4eea3d959",
      "tree": "6188df0c224ff5694ac00a50a5209fd69241208b",
      "parents": [
        "d5b6007d06969c7ed4b4430ab439b388cb19607f"
      ],
      "author": {
        "name": "Eugene Gvozdetsky",
        "email": "gvozdet@gmail.com",
        "time": "Fri Oct 09 18:47:27 2026 +0200"
      },
      "committer": {
        "name": "Eugene Gvozdetsky",
        "email": "gvozdet@gmail.com",
        "time": "Fri Oct 09 18:55:24 2026 +0200"
      },
      "message": "io_uring/bpf_filter.h: update for IORING_OP_CONNECT\n\nSync with the kernel uapi header. Since 899bea8248ce (\"io_uring/net:\nallow filtering on IORING_OP_CONNECT\"), Linux 7.2 passes the address\nfamily, port and address of IORING_OP_CONNECT to BPF filters. The new\nunion member doesn\u0027t change the size of struct io_uring_bpf_ctx.\n\nAssisted-by: Claude:claude-opus-5-5\nSigned-off-by: Eugene Gvozdetsky \u003cgvozdet@gmail.com\u003e\n"
    },
    {
      "commit": "d5b6007d06969c7ed4b4430ab439b388cb19607f",
      "tree": "ed875ea1e0de5ca200e376eb40daad20993a2870",
      "parents": [
        "78dce99b660fd1caaf70ef6573a88bae9bbf6476",
        "13f0072a4109d94069efbbb01ee8391ed26b4a58"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 09 08:41:46 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Oct 09 08:41:46 2026 -0600"
      },
      "message": "Merge branch \u0027task-restrict-exec\u0027 of github.com:gvozdetsky/liburing\n\n* \u0027task-restrict-exec\u0027 of github.com:gvozdetsky/liburing:\n  test: check that per-task restrictions survive exec\n"
    },
    {
      "commit": "13f0072a4109d94069efbbb01ee8391ed26b4a58",
      "tree": "ed875ea1e0de5ca200e376eb40daad20993a2870",
      "parents": [
        "78dce99b660fd1caaf70ef6573a88bae9bbf6476"
      ],
      "author": {
        "name": "Eugene Gvozdetsky",
        "email": "gvozdet@gmail.com",
        "time": "Thu Oct 08 22:55:39 2026 +0200"
      },
      "committer": {
        "name": "Eugene Gvozdetsky",
        "email": "gvozdet@gmail.com",
        "time": "Fri Oct 09 01:22:33 2026 +0200"
      },
      "message": "test: check that per-task restrictions survive exec\n\nPer-task io_uring restrictions must keep applying to rings created after\nexec, also when the task used io_uring before exec. Kernels without\ncommit bc0e8faf90e7 (\"io_uring: preserve task restrictions across exec\")\nfree the restrictions with the task context on exec in that case, so the\nnew image can create unrestricted rings. task-restrict.t doesn\u0027t cover\nexec, so it passes on those kernels.\n\nRestrict a child to NOP, optionally use a ring, re-exec the test and\ncheck that a fresh ring still denies a read. Cover both the opcode\nallowlist and a BPF filter.\n\nSkips on 6.18, fails on 7.0, passes on 7.2.9.\n\nAssisted-by: Claude:claude-opus-5-5\nSigned-off-by: Eugene Gvozdetsky \u003cgvozdet@gmail.com\u003e\n"
    },
    {
      "commit": "78dce99b660fd1caaf70ef6573a88bae9bbf6476",
      "tree": "f78153b0f48d2d5ca3160a5a73c6c637aaff21e4",
      "parents": [
        "e9e4ac2147dba2dda70575f2f09f0d2eac5e0ae4",
        "b041e95a7c0beaac03f117b0f313c52ddbe9ec34"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Sep 11 13:00:18 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Sep 11 13:00:18 2026 -0600"
      },
      "message": "Merge branch \u0027harden/sanitize-second-pointers\u0027 of github.com:StressTestor/liburing\n\n* \u0027harden/sanitize-second-pointers\u0027 of github.com:StressTestor/liburing:\n  src/register: check the tags array in the buffers registration helpers\n  src/sanitize: check the timespec of a timeout update\n  src/sanitize: check the statx output buffer too\n"
    },
    {
      "commit": "e9e4ac2147dba2dda70575f2f09f0d2eac5e0ae4",
      "tree": "93fd23f77293e5c1480c2d798200415145d66a80",
      "parents": [
        "4cf73437863c2e492d2a1d0f24330f391c0f075b",
        "3cd017e37bd9d57914bd34caadad55dccf69b1c1"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Sep 11 10:40:49 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Sep 11 10:40:49 2026 -0600"
      },
      "message": "Merge branch \u0027liburing-noexcept-inline-helpers\u0027 of github.com:businessarshgoyal/liburing\n\n* \u0027liburing-noexcept-inline-helpers\u0027 of github.com:businessarshgoyal/liburing:\n  liburing.h: add missing LIBURING_NOEXCEPT to inline helpers\n"
    },
    {
      "commit": "3cd017e37bd9d57914bd34caadad55dccf69b1c1",
      "tree": "93fd23f77293e5c1480c2d798200415145d66a80",
      "parents": [
        "4cf73437863c2e492d2a1d0f24330f391c0f075b"
      ],
      "author": {
        "name": "Arsh Goyal",
        "email": "business.arshgoyal@gmail.com",
        "time": "Tue Sep 08 08:38:43 2026 +0000"
      },
      "committer": {
        "name": "Arsh Goyal",
        "email": "business.arshgoyal@gmail.com",
        "time": "Tue Sep 08 08:38:43 2026 +0000"
      },
      "message": "liburing.h: add missing LIBURING_NOEXCEPT to inline helpers\n\nio_uring_cqe_nr(), io_uring_cqe_get_data64(), io_uring_prep_pipe() and\nio_uring_prep_pipe_direct() are the only IOURINGINLINE helpers that are\nnot annotated with LIBURING_NOEXCEPT. All other public inline helpers\ncarry the annotation, so C++ consumers see these four as potentially\nthrowing, which is inconsistent and can inhibit optimizations in\nnoexcept contexts. Mark them like the rest of the header.\n\nSigned-off-by: Arsh Goyal \u003cbusiness.arshgoyal@gmail.com\u003e\nCo-Authored-By: business.arshgoyal@gmail.com \u003cbusiness.arshgoyal@gmail.com\u003e\n"
    },
    {
      "commit": "4cf73437863c2e492d2a1d0f24330f391c0f075b",
      "tree": "a895d7e921be2986ffc6db338edc1dc6a3cb5640",
      "parents": [
        "914062b3b65644cb9deee25083bffe69d54f1e94"
      ],
      "author": {
        "name": "Gabriel Krisman Bertazi",
        "email": "krisman@suse.de",
        "time": "Mon Aug 31 12:52:21 2026 -0300"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 31 17:00:18 2026 -0600"
      },
      "message": "test/iowait.t: Skip if system is not quiesced for too long\n\niowait.t reads the system-wide iowait metric, which is unreliable if the\ncpu is busy with other tasks.  Identify this scenario by checking the\nuser+sys time, and retry to avoid spurious failures.\n\nSigned-off-by: Gabriel Krisman Bertazi \u003ckrisman@suse.de\u003e\nLink: https://patch.msgid.link/20260831155222.121857-2-krisman@suse.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "914062b3b65644cb9deee25083bffe69d54f1e94",
      "tree": "8a92368a9bcc9e55a1c95c341047cb203bffd0dc",
      "parents": [
        "88add766c22ca9cee55e84145de29bd9d78dd685"
      ],
      "author": {
        "name": "Gabriel Krisman Bertazi",
        "email": "krisman@suse.de",
        "time": "Mon Aug 31 12:44:26 2026 -0300"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 31 16:58:30 2026 -0600"
      },
      "message": "man/io_uring_submit*.3: Point to error code documentation\n\nThere\u0027s an open issue in gh asking about the possible error codes\nreturned by io_uring_submit.  Add pointers to io_uring_enter(2) in all\nio_uring_submit* variants where the error codes are explained in\ndetail.  The minor exception are _wait_timeout, wait_and_reg and\nwait_min_timeout, where there are more error codes to be described.\n\nCloses: https://github.com/axboe/liburing/issues/1511\nSigned-off-by: Gabriel Krisman Bertazi \u003ckrisman@suse.de\u003e\nLink: https://patch.msgid.link/20260831154426.115944-3-krisman@suse.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "88add766c22ca9cee55e84145de29bd9d78dd685",
      "tree": "1671a67821e644e5e3d8eba4a9a253b64c6a1c77",
      "parents": [
        "ae61c975e168d78a9d10c6d332d2f0a4839a8b71"
      ],
      "author": {
        "name": "Gabriel Krisman Bertazi",
        "email": "krisman@suse.de",
        "time": "Mon Aug 31 12:44:25 2026 -0300"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 31 16:58:30 2026 -0600"
      },
      "message": "man: Fix FUTEX_WAIT/FUTEX_WAKE explanation\n\nThe description of the futex_wait parameters is incorrect when\nexplaining the futex value.  Correct it and rewrite the rest of the\nfutex operations description to make them clearer.\n\nCloses: https://github.com/axboe/liburing/issues/1625\nSigned-off-by: Gabriel Krisman Bertazi \u003ckrisman@suse.de\u003e\nLink: https://patch.msgid.link/20260831154426.115944-2-krisman@suse.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "ae61c975e168d78a9d10c6d332d2f0a4839a8b71",
      "tree": "e4a25bc03726a552d0c249360114bacb82cb4a28",
      "parents": [
        "27255f4ceda937b3540e425ed58284f5c03c8ad4"
      ],
      "author": {
        "name": "Prateek",
        "email": "kprateek283@gmail.com",
        "time": "Tue Jun 23 21:13:05 2026 +0530"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri Aug 28 15:28:04 2026 -0600"
      },
      "message": "setup: dynamically detect default huge page size\n\n    Replaces the hardcoded 2MB huge page size with dynamic detection by\n    parsing /proc/meminfo. This fixes no-mmap allocation failures on\n    architectures with different default huge page sizes (like ARM64\n    which often uses 512MB) or x86 systems configured for 1GB pages.\n\n    - Safely parses /proc/meminfo without allocating memory.\n    - Adds a __uring_memcmp shim for CONFIG_NOLIBC builds, allowing\n      setup.c to use standard memcmp for the Hugepagesize: match.\n    - Drops the MAP_HUGE_2MB mmap flag to allow the kernel to correctly\n      apply the system\u0027s default huge page size.\n    - Falls back safely to 2MB if /proc/meminfo is unreadable.\n\nSigned-off-by: Prateek \u003ckprateek283@gmail.com\u003e\nReviewed-by: Gabriel Krisman Bertazi \u003ckrisman@suse.de\u003e\nLink: https://patch.msgid.link/20260623154305.1115403-1-kprateek283@gmail.com\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "b041e95a7c0beaac03f117b0f313c52ddbe9ec34",
      "tree": "ab07bda4d4ecbd10c64eab2d366c1597c2cc84a0",
      "parents": [
        "86e9fbce98db20bdc1777a5782bd700d63a665bf"
      ],
      "author": {
        "name": "Joe Grey",
        "email": "212606152+StressTestor@users.noreply.github.com",
        "time": "Mon Aug 24 13:33:54 2026 -0600"
      },
      "committer": {
        "name": "Joe Grey",
        "email": "212606152+StressTestor@users.noreply.github.com",
        "time": "Mon Aug 24 13:33:54 2026 -0600"
      },
      "message": "src/register: check the tags array in the buffers registration helpers\n\nio_uring_register_files_update_tag() and io_uring_register_files_tags()\ncheck both of their user pointers. Their buffers counterparts check only\nthe iovec array and never look at tags.\n\ndo_register()\u0027s own liburing_sanitize_address(arg) does not cover it,\nsince arg is the address of the on-stack io_uring_rsrc_update2 or\nio_uring_rsrc_register, not of the caller\u0027s tags array. A NULL tags\nargument is legal and passes through liburing_sanitize_address()\nunharmed, as it already does on the files paths.\n\nSigned-off-by: Joe Grey \u003c212606152+StressTestor@users.noreply.github.com\u003e\n"
    },
    {
      "commit": "86e9fbce98db20bdc1777a5782bd700d63a665bf",
      "tree": "c676b250130b9bb5a8ae66f4b8cd0c090b9d8f6a",
      "parents": [
        "8ec38e3feae0a0b9764522bab889bb4b910030a8"
      ],
      "author": {
        "name": "Joe Grey",
        "email": "212606152+StressTestor@users.noreply.github.com",
        "time": "Mon Aug 24 13:33:54 2026 -0600"
      },
      "committer": {
        "name": "Joe Grey",
        "email": "212606152+StressTestor@users.noreply.github.com",
        "time": "Mon Aug 24 13:33:54 2026 -0600"
      },
      "message": "src/sanitize: check the timespec of a timeout update\n\nio_uring_prep_timeout_update() writes its struct __kernel_timespec pointer\ninto sqe-\u003eaddr2, but IORING_OP_TIMEOUT_REMOVE is handled by\nsanitize_sqe_nop() and nothing looks at it.\n\nThe opcode is shared with io_uring_prep_timeout_remove(), which is why\nsanitize_sqe_addr_and_add2() is the wrong handler here: both helpers put a\nuser_data value in sqe-\u003eaddr, not a pointer. sanitize_sqe_addr2() checks\nonly the slot that actually holds one. The remove variant leaves addr2 at\nzero, and __asan_address_is_poisoned(NULL) is 0, so it stays a no-op there.\n\nSigned-off-by: Joe Grey \u003c212606152+StressTestor@users.noreply.github.com\u003e\n"
    },
    {
      "commit": "8ec38e3feae0a0b9764522bab889bb4b910030a8",
      "tree": "c23c6cfbc52a813dc6113cc086e0189f8dbcdbe3",
      "parents": [
        "27255f4ceda937b3540e425ed58284f5c03c8ad4"
      ],
      "author": {
        "name": "Joe Grey",
        "email": "212606152+StressTestor@users.noreply.github.com",
        "time": "Mon Aug 24 13:33:53 2026 -0600"
      },
      "committer": {
        "name": "Joe Grey",
        "email": "212606152+StressTestor@users.noreply.github.com",
        "time": "Mon Aug 24 13:33:53 2026 -0600"
      },
      "message": "src/sanitize: check the statx output buffer too\n\n835f697 (\"src/sanitize: check secondary user pointers as well\") swept the\nopcodes carrying a second user pointer in -\u003eaddr2 and moved them to\nsanitize_sqe_addr_and_add2(). IORING_OP_STATX was missed.\n\nio_uring_prep_statx() passes statxbuf as the offset argument of\nio_uring_prep_rw(), which stores it in sqe-\u003eoff, and off and addr2 are the\nsame union member. So the buffer the kernel writes the statx result into\nsits in exactly the slot that sweep taught the sanitizer to check.\n\nSigned-off-by: Joe Grey \u003c212606152+StressTestor@users.noreply.github.com\u003e\n"
    },
    {
      "commit": "27255f4ceda937b3540e425ed58284f5c03c8ad4",
      "tree": "9e254995e33f51dc75609589f5ca788a24b8b161",
      "parents": [
        "6bfe0f9180f95d23b0c7e9724d2d0c84972141a4",
        "e620d33bbb533685dc6bbdd708bf8f53fe6d2697"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Aug 19 12:44:42 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Aug 19 12:44:42 2026 -0600"
      },
      "message": "Merge branch \u0027fix/reg-wait-feature-check\u0027 of github.com:srkyn/liburing\n\n* \u0027fix/reg-wait-feature-check\u0027 of github.com:srkyn/liburing:\n  queue: check EXT_ARG support before flushing registered waits\n"
    },
    {
      "commit": "e620d33bbb533685dc6bbdd708bf8f53fe6d2697",
      "tree": "9e254995e33f51dc75609589f5ca788a24b8b161",
      "parents": [
        "6bfe0f9180f95d23b0c7e9724d2d0c84972141a4"
      ],
      "author": {
        "name": "David Sarkisyan",
        "email": "david@srkyn.com",
        "time": "Wed Aug 19 04:23:50 2026 -0400"
      },
      "committer": {
        "name": "David Sarkisyan",
        "email": "david@srkyn.com",
        "time": "Wed Aug 19 10:29:44 2026 -0400"
      },
      "message": "queue: check EXT_ARG support before flushing registered waits\n\nio_uring_submit_and_wait_reg() initializes get_data before checking\nIORING_FEAT_EXT_ARG. The initializer calls __io_uring_flush_sq(), so an\nunsupported call returns -EINVAL after advancing the private SQ head and\npublishing the SQ tail.\n\nThat can strand pending entries on a normal ring. If an SQPOLL thread is\nactive, it can execute them even though the helper returned an error.\n\nCheck the feature first, as io_uring_submit_and_wait_min_timeout()\nalready does. Add a regression test which verifies that the unsupported\npath leaves both the private SQ head and published SQ tail unchanged.\n\nFixes: a43647016762 (\"Add support for registered waits\")\nSigned-off-by: David Sarkisyan \u003cdavid@srkyn.com\u003e\n"
    },
    {
      "commit": "6bfe0f9180f95d23b0c7e9724d2d0c84972141a4",
      "tree": "cc9e620354273370cdf9d8103d67ee2aa807620f",
      "parents": [
        "9d179918fcd060494c680f42eba525e9c656e766"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Aug 17 10:28:32 2026 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 17 12:21:56 2026 -0600"
      },
      "message": "test: add zone_reset_all command test\n\nBasic sanity checking for the zone_reset_all command, mostly taken from\nthe discard test.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: Damien Le Moal \u003cdlemoal@kernel.org\u003e\nLink: https://patch.msgid.link/20260817082837.762276-6-hch@lst.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "9d179918fcd060494c680f42eba525e9c656e766",
      "tree": "7fd524cec6628224bfd2e121dac61170a265205a",
      "parents": [
        "fae20287f440d59b12a1626ef9d7dc15f7764933"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Aug 17 10:28:31 2026 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 17 12:21:56 2026 -0600"
      },
      "message": "man: add io_uring_prep_cmd_zone_reset_all.3 man page\n\nAdd documentation for the new zone reset all io_uring cmd.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: Damien Le Moal \u003cdlemoal@kernel.org\u003e\nLink: https://patch.msgid.link/20260817082837.762276-5-hch@lst.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "fae20287f440d59b12a1626ef9d7dc15f7764933",
      "tree": "a99e584d8165301794c3e1e8ce1e023f6c0914d8",
      "parents": [
        "96980531859b99fc21feda893c49750879e8c6c1"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Aug 17 10:28:30 2026 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 17 12:21:56 2026 -0600"
      },
      "message": "liburing: add io_uring_prep_cmd_zone_reset\n\nAdd a helper for io_uring zone_reset_all commands.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: Damien Le Moal \u003cdlemoal@kernel.org\u003e\nLink: https://patch.msgid.link/20260817082837.762276-4-hch@lst.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "96980531859b99fc21feda893c49750879e8c6c1",
      "tree": "56e3b30a6c343d846d1dfff5a216962d768fa10c",
      "parents": [
        "16390826c1ffe9e989c4b8e922d8aeec30cbe030"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Aug 17 10:28:29 2026 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 17 12:21:56 2026 -0600"
      },
      "message": "man: fixups for io_uring_prep_cmd_discard.3\n\nMention the ioctl this is modelled after instead of the io_uring\ncmd used to implement io_uring_prep_cmd_discard.3, and drop an\nincorrect plural for page cache.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: Damien Le Moal \u003cdlemoal@kernel.org\u003e\nLink: https://patch.msgid.link/20260817082837.762276-3-hch@lst.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "16390826c1ffe9e989c4b8e922d8aeec30cbe030",
      "tree": "34eafda9125ec172544fa7098d44b51c8800ece3",
      "parents": [
        "5cdb10f1a1334e8c7a3604ddfbaed4e4ff8ec30a"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Aug 17 10:28:28 2026 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Aug 17 12:21:56 2026 -0600"
      },
      "message": "configure: shorten the message for the discard command\n\nThe current message is pretty long, drop the redundant io_uring.\nThis aligns it with the soon to be added zone_reset_all message.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: Damien Le Moal \u003cdlemoal@kernel.org\u003e\nLink: https://patch.msgid.link/20260817082837.762276-2-hch@lst.de\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "5cdb10f1a1334e8c7a3604ddfbaed4e4ff8ec30a",
      "tree": "3e66baad9ef2dcf8ec88fcdcda66757df528bd3b",
      "parents": [
        "b12a090919b400b401e5eb35be2065429fb6489e",
        "99f87a67e499cc8a3996e62bcae9b93588c06f30"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jul 28 16:26:28 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jul 28 16:26:28 2026 -0600"
      },
      "message": "Merge branch \u0027man-page-fixes\u0027 of github.com:cmazakas/liburing\n\n* \u0027man-page-fixes\u0027 of github.com:cmazakas/liburing:\n  man: Fixup dead links in man pages\n"
    },
    {
      "commit": "b12a090919b400b401e5eb35be2065429fb6489e",
      "tree": "06585a40c24d12e091faf8051359beb68f133306",
      "parents": [
        "4acaaeceb71cc5915cf11f9a2463c1467d460847"
      ],
      "author": {
        "name": "Ammar Faizi",
        "email": "ammarfaizi2@openresty.com",
        "time": "Sat Jul 25 05:59:05 2026 +0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Jul 25 04:56:53 2026 -0600"
      },
      "message": "liburing{{,-ffi}.pc.in,.spec}: Replace dead git tree links with the new one\n\nThe old git tree link:\n\n  https://git.kernel.dk/cgit/liburing/\n\nis dead. Replace it with the new kernel.org git tree:\n\n  https://git.kernel.org/pub/scm/linux/kernel/git/axboe/liburing.git/\n\nCc: Stefan Hajnoczi \u003cstefanha@redhat.com\u003e\nCc: Guillem Jover \u003cguillem@hadrons.org\u003e\nCc: Changcheng Liu \u003cchangcheng.liu@aliyun.com\u003e\nSigned-off-by: Ammar Faizi \u003cammarfaizi2@openresty.com\u003e\nLink: https://patch.msgid.link/20260724225905.747718-5-ammarfaizi2@openresty.com\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "4acaaeceb71cc5915cf11f9a2463c1467d460847",
      "tree": "2a7004af49317939138e3886e9380744b4a565da",
      "parents": [
        "3a6320a6008afee1c8febf16a9aa1428084a146f"
      ],
      "author": {
        "name": "Ammar Faizi",
        "email": "ammarfaizi2@openresty.com",
        "time": "Sat Jul 25 05:59:04 2026 +0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Jul 25 04:56:53 2026 -0600"
      },
      "message": "ci: Upgrade clang version to 23\n\nClang 23 is now available. Upgrade the clang version used in the CI.\n\nCc: Christian Mazakas \u003cchristian.mazakas@gmail.com\u003e\nSigned-off-by: Ammar Faizi \u003cammarfaizi2@openresty.com\u003e\nLink: https://patch.msgid.link/20260724225905.747718-4-ammarfaizi2@openresty.com\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "3a6320a6008afee1c8febf16a9aa1428084a146f",
      "tree": "395e341f1ee8d792d421710fe285ffd5acd6e166",
      "parents": [
        "ca274ec7289fd4ea56f20651be1814b9614b2745"
      ],
      "author": {
        "name": "Ammar Faizi",
        "email": "ammarfaizi2@openresty.com",
        "time": "Sat Jul 25 05:59:03 2026 +0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Jul 25 04:56:53 2026 -0600"
      },
      "message": "ci: Fix the wrong `cc_pkg` comparison\n\nCommit 7a65e5a4f294 (\"github: Build all newly pushed commits\") nested\nthe `cc_pkg` variable into `build_args`, but the if statement is still\nusing the old matrix variable. Fix it; the correct variable is\n`matrix.build_args.cc_pkg`.\n\nFixes: 7a65e5a4f294 (\"github: Build all newly pushed commits\")\nCc: Christian Mazakas \u003cchristian.mazakas@gmail.com\u003e\nSigned-off-by: Ammar Faizi \u003cammarfaizi2@openresty.com\u003e\nLink: https://patch.msgid.link/20260724225905.747718-3-ammarfaizi2@openresty.com\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "ca274ec7289fd4ea56f20651be1814b9614b2745",
      "tree": "443a35bdbe68c7d511c66f36befab59c7aacab87",
      "parents": [
        "639d05b5e7f202ca8a400fc3158d91fa30914883"
      ],
      "author": {
        "name": "Ammar Faizi",
        "email": "ammarfaizi2@openresty.com",
        "time": "Sat Jul 25 05:59:02 2026 +0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Jul 25 04:56:53 2026 -0600"
      },
      "message": "test: Remove unused global variables found by clang-23\n\nIn preparation for upgrading to Clang 23, fix the following warnings:\n\n  iopoll.c:26:12: error: variable \u0027no_hybrid\u0027 set but not used [-Werror,-Wunused-but-set-global]\n  recvmsg-inc-tail.c:66:25: error: variable \u0027no_recv_mshot\u0027 set but not used [-Werror,-Wunused-but-set-global]\n  reg-wait.c:26:13: error: variable \u0027has_kernel_regions\u0027 set but not used [-Werror,-Wunused-but-set-global]\n\n`no_hybrid` has been unused since commit c5eead2659ef (\"test/iopoll:\nfix over-eager no_hybrid check\"); `no_recv_mshot` was never used since\nit was introduced. `has_kernel_regions` has been unused since commit\n30ce99006af9 (\"test/reg-wait: basic test + probing of kernel regions\").\n\nFixes: c5eead2659ef (\"test/iopoll: fix over-eager no_hybrid check\")\nFixes: 3891a21ffec6 (\"Add test case for minimum length left for incremental buffers\")\nFixes: 30ce99006af9 (\"test/reg-wait: basic test + probing of kernel regions\")\nCc: Christian Mazakas \u003cchristian.mazakas@gmail.com\u003e\nSigned-off-by: Ammar Faizi \u003cammarfaizi2@openresty.com\u003e\nLink: https://patch.msgid.link/20260724225905.747718-2-ammarfaizi2@openresty.com\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "639d05b5e7f202ca8a400fc3158d91fa30914883",
      "tree": "6d3e5d985fcdd9b5f97ba5cfa5f109e1dd4b9985",
      "parents": [
        "14f0c69ea525fdf328d24c78ca89c53e5ac96cc9",
        "72d5cafb5454e57b23882d16b4501c34e1e7189c"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 22 07:20:06 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 22 07:20:06 2026 -0600"
      },
      "message": "Merge branch \u0027reg_fd_only\u0027 of github.com:chrehrhardt/liburing\n\n* \u0027reg_fd_only\u0027 of github.com:chrehrhardt/liburing:\n  test/reg-fd-only: Relax io_uring_submit() return value check\n"
    },
    {
      "commit": "14f0c69ea525fdf328d24c78ca89c53e5ac96cc9",
      "tree": "ee0fa2c4674cdcde9e8c2be6c542b7a028f81f54",
      "parents": [
        "d332e4dfb2489453b1aa89775e903794d52e5649",
        "7cbb2b323b74ab42e6eef293e7f5c0c588375e9c"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 22 07:19:30 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 22 07:19:30 2026 -0600"
      },
      "message": "Merge branch \u0027connect\u0027 of github.com:Flowdalic/liburing\n\n* \u0027connect\u0027 of github.com:Flowdalic/liburing:\n  test/connect: fix sporadic \"Address already in use\" failures\n"
    },
    {
      "commit": "d332e4dfb2489453b1aa89775e903794d52e5649",
      "tree": "8e3c80362517bb2fda18cbb4402191c7a858476e",
      "parents": [
        "1136bf22b9df5f61b493a13ef25397484a551d62",
        "7394b073da8d1e1030344300ef446b70539294e7"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 22 04:43:50 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 22 04:43:50 2026 -0600"
      },
      "message": "Merge branch \u0027fix-open-direct-link\u0027 of github.com:Flowdalic/liburing\n\n* \u0027fix-open-direct-link\u0027 of github.com:Flowdalic/liburing:\n  test/open-direct-link: fix sporadic -EBADF failure\n"
    },
    {
      "commit": "7394b073da8d1e1030344300ef446b70539294e7",
      "tree": "8e3c80362517bb2fda18cbb4402191c7a858476e",
      "parents": [
        "1136bf22b9df5f61b493a13ef25397484a551d62"
      ],
      "author": {
        "name": "Florian Schmaus",
        "email": "florian.schmaus@codasip.com",
        "time": "Wed Jul 22 08:44:35 2026 +0200"
      },
      "committer": {
        "name": "Florian Schmaus",
        "email": "flo@geekplace.eu",
        "time": "Wed Jul 22 08:56:18 2026 +0200"
      },
      "message": "test/open-direct-link: fix sporadic -EBADF failure\n\nThe test runs consecutive test iterations that chain openat_direct,\nread, and close_direct operations. Some iterations, like test(1, 0, 0)\nwhere skip_success\u003d1, configure the openat and close operations to skip\nproducing CQEs upon success. As a result, the test suite only waits on\nthe CQE generated by the read operation before proceeding to the next\ntest run.\n\nBecause the previous iteration\u0027s close_direct might still be in-flight\nor deferred to task_work, and all iterations were hardcoding file index\n0, a race condition occurs: an asynchronous close_direct from a prior\ntest run can inadvertently close the newly installed file from a\nsubsequent test run. This causes the newly submitted read operation to\nunexpectedly fail with -EBADF (\"bad read -9\").\n\nFix this by passing an incrementally unique file_idx to each test\niteration. This isolates the test iterations and prevents them from\nracing over the same fixed file descriptor slot.\n\nSigned-off-by: Florian Schmaus \u003cflorian.schmaus@codasip.com\u003e\n"
    },
    {
      "commit": "1136bf22b9df5f61b493a13ef25397484a551d62",
      "tree": "66f98a9f09feab540eb7d9b1a6ed323dbf57683c",
      "parents": [
        "e50e32a6b9030faba2e30fa0ba999571a0cffe28",
        "374139ab86b2706f46480ede8317e0eabd5c02a0"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jul 21 11:39:45 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jul 21 11:39:45 2026 -0600"
      },
      "message": "Merge branch \u0027man_page\u0027 of github.com:jiv4/liburing\n\n* \u0027man_page\u0027 of github.com:jiv4/liburing:\n  clarify registered buffers iovec lifetime\n"
    },
    {
      "commit": "374139ab86b2706f46480ede8317e0eabd5c02a0",
      "tree": "f7547b94c88f96bb158cc548cf88717110f673c9",
      "parents": [
        "9d707e2b7f1f56158921ec7d45fcecbf5eb6222f"
      ],
      "author": {
        "name": "jiva",
        "email": "jiv4@proton.me",
        "time": "Tue Jul 21 15:55:53 2026 +0100"
      },
      "committer": {
        "name": "jiva",
        "email": "jiv4@proton.me",
        "time": "Tue Jul 21 18:38:37 2026 +0100"
      },
      "message": "clarify registered buffers iovec lifetime\n\nThe io_uring_register_buffers* functions don\u0027t require that the\nmemory that is backing the iovec structs stay valid for the lifetime\nof the ring. The caller is therefore allowed to free the iovecs in\ncase they were allocated on the heap.\n\nSigned-off-by: Arthur Leclerc \u003cjiv4@proton.me\u003e\n"
    },
    {
      "commit": "7cbb2b323b74ab42e6eef293e7f5c0c588375e9c",
      "tree": "50bba494e0bfad52381fb1f6705ca84b5e19404a",
      "parents": [
        "e50e32a6b9030faba2e30fa0ba999571a0cffe28"
      ],
      "author": {
        "name": "Florian Schmaus",
        "email": "flo@geekplace.eu",
        "time": "Mon Jul 13 10:29:38 2026 +0200"
      },
      "committer": {
        "name": "Florian Schmaus",
        "email": "flo@geekplace.eu",
        "time": "Tue Jul 14 11:16:06 2026 +0200"
      },
      "message": "test/connect: fix sporadic \"Address already in use\" failures\n\nThe connect.t test previously generated a pseudo-random port number\nusing rand(). This approach occasionally resulted in port collisions\nwhen the randomly selected port was already in use by another process\nor lingering in a TIME_WAIT state, causing the test suite to\nsporadically fail with \"bind(): Address already in use\".\n\nUpdate the tests in connect.t to bind sockets using sin_port\u003d0,\nallowing the operating system to assign an available ephemeral\nport. Afterwards, getsockname() is used to retrieve the assigned port\nso that the client sockets can be configured to connect to it.\n\nFor test_connect_with_no_peer(), we introduce a new helper\nblock_port(). This test explicitly requires connecting to a port where\nno server is listening to verify that an ECONNREFUSED error is\nreturned. block_port() binds a temporary socket to port 0 to acquire\nan unused port from the OS, and keeps the file descriptor open to\nprevent other processes from claiming the port before and during the\ntest run. Because listen() is never called on this socket, connecting\nto it is guaranteed to be refused. After test_connect_with_no_peer()\ncompleted the socket is closed.\n\nRemove the port randomization code in test() as it is now unused.\n\nSigned-off-by: Florian Schmaus \u003cflo@geekplace.eu\u003e\n"
    },
    {
      "commit": "99f87a67e499cc8a3996e62bcae9b93588c06f30",
      "tree": "8d54f47d460ea676db6ddc836a55eccca3330607",
      "parents": [
        "e50e32a6b9030faba2e30fa0ba999571a0cffe28"
      ],
      "author": {
        "name": "Christian Mazakas",
        "email": "christian.mazakas@gmail.com",
        "time": "Wed Jul 08 15:56:32 2026 -0700"
      },
      "committer": {
        "name": "Christian Mazakas",
        "email": "christian.mazakas@gmail.com",
        "time": "Thu Jul 09 09:35:02 2026 -0700"
      },
      "message": "man: Fixup dead links in man pages\n\nSigned-off-by: Christian Mazakas \u003cchristian.mazakas@gmail.com\u003e\n"
    },
    {
      "commit": "e50e32a6b9030faba2e30fa0ba999571a0cffe28",
      "tree": "a627f0c347bc1df13e2c7920e52069068d024177",
      "parents": [
        "d41bf9220ec39277ff235379e9089d9e0fd6c2a5",
        "e9909c7b1d63df480a974eaa4accdec3ed268e12"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 01 06:24:23 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jul 01 06:24:23 2026 -0600"
      },
      "message": "Merge branch \u0027user/cge/improve-zcrx-test\u0027 of https://github.com/zeehha/liburing\n\n* \u0027user/cge/improve-zcrx-test\u0027 of https://github.com/zeehha/liburing:\n  test/zcrx: Fix return values of test_area()\n  test/zcrx: Fix error message\n  test/zcrx: Fix contradicting mmap call\n"
    },
    {
      "commit": "e9909c7b1d63df480a974eaa4accdec3ed268e12",
      "tree": "a627f0c347bc1df13e2c7920e52069068d024177",
      "parents": [
        "0dab19a487abfe90cc30b46b23aa1efbeb75ac54"
      ],
      "author": {
        "name": "Chris Gellermann",
        "email": "christian.gellermann@codasip.com",
        "time": "Tue Jun 30 12:22:39 2026 +0200"
      },
      "committer": {
        "name": "Chris Gellermann",
        "email": "christian.gellermann@codasip.com",
        "time": "Wed Jul 01 09:14:37 2026 +0200"
      },
      "message": "test/zcrx: Fix return values of test_area()\n\ntest_area() prints an error message and returns ret if a test call to\nio_uring_register_ifq returns an unexpected result. With illegal\narguments, an unexpected result would be success, i.e. ret \u003d\u003d 0, which\nleads to test_area() returning zero aka success. Return T_EXIT_FAIL.\n\nSigned-off-by: Chris Gellermann \u003cchristian.gellermann@codasip.com\u003e\n"
    },
    {
      "commit": "0dab19a487abfe90cc30b46b23aa1efbeb75ac54",
      "tree": "f2858ed954f0cdecd07e3677ff6d8a762ad96922",
      "parents": [
        "140d47cb6966b420337d13516fb0e32fedacb8e5"
      ],
      "author": {
        "name": "Chris Gellermann",
        "email": "christian.gellermann@codasip.com",
        "time": "Tue Jun 30 12:08:31 2026 +0200"
      },
      "committer": {
        "name": "Chris Gellermann",
        "email": "christian.gellermann@codasip.com",
        "time": "Tue Jun 30 12:16:37 2026 +0200"
      },
      "message": "test/zcrx: Fix error message\n\nSigned-off-by: Chris Gellermann \u003cchristian.gellermann@codasip.com\u003e\n"
    },
    {
      "commit": "140d47cb6966b420337d13516fb0e32fedacb8e5",
      "tree": "c7dd54aa6a365e16a72780b601ca708c3daa90d7",
      "parents": [
        "d41bf9220ec39277ff235379e9089d9e0fd6c2a5"
      ],
      "author": {
        "name": "Chris Gellermann",
        "email": "christian.gellermann@codasip.com",
        "time": "Tue Jun 30 11:59:37 2026 +0200"
      },
      "committer": {
        "name": "Chris Gellermann",
        "email": "christian.gellermann@codasip.com",
        "time": "Tue Jun 30 12:16:29 2026 +0200"
      },
      "message": "test/zcrx: Fix contradicting mmap call\n\nCalling mmap with addr set to NULL allows the kernel to pick an address,\nbut specifying MAP_FIXED forces the kernel to place the mapping at addr.\nThis does not make sense, remove MAP_FIXED.\n\nSigned-off-by: Chris Gellermann \u003cchristian.gellermann@codasip.com\u003e\n"
    },
    {
      "commit": "d41bf9220ec39277ff235379e9089d9e0fd6c2a5",
      "tree": "b00d083db5be86a33526ceabb8cda4bff2818e97",
      "parents": [
        "650d8fb7acb5952a12530b617f09da75b95c979c",
        "36eab8bdafea85bbd2fa9e84800df3bb85eddf73"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Jun 27 17:41:18 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Sat Jun 27 17:41:18 2026 -0600"
      },
      "message": "Merge branch \u0027fix-typo\u0027 of https://github.com/sleiphan/liburing\n\n* \u0027fix-typo\u0027 of https://github.com/sleiphan/liburing:\n  man: Fix one typo\n"
    },
    {
      "commit": "36eab8bdafea85bbd2fa9e84800df3bb85eddf73",
      "tree": "b00d083db5be86a33526ceabb8cda4bff2818e97",
      "parents": [
        "650d8fb7acb5952a12530b617f09da75b95c979c"
      ],
      "author": {
        "name": "Håkon F. Fjellanger",
        "email": "hfredrif@gmail.com",
        "time": "Sat Jun 27 22:46:11 2026 +0000"
      },
      "committer": {
        "name": "Hakon F. Fjellanger",
        "email": "hfredrif@gmail.com",
        "time": "Sat Jun 27 23:24:48 2026 +0000"
      },
      "message": "man: Fix one typo\n\nFixes: https://github.com/axboe/liburing/issues/1604\nSigned-off-by: Hakon F. Fjellanger \u003chfredrif@gmail.com\u003e\n"
    },
    {
      "commit": "72d5cafb5454e57b23882d16b4501c34e1e7189c",
      "tree": "0c1801d56538d15c1d66d6f87c471b8cfc50c97c",
      "parents": [
        "650d8fb7acb5952a12530b617f09da75b95c979c"
      ],
      "author": {
        "name": "Christian A. Ehrhardt",
        "email": "christian.ehrhardt@codasip.com",
        "time": "Tue Jun 23 11:50:50 2026 +0200"
      },
      "committer": {
        "name": "Christian A. Ehrhardt",
        "email": "christian.ehrhardt@codasip.com",
        "time": "Tue Jun 23 13:11:18 2026 +0200"
      },
      "message": "test/reg-fd-only: Relax io_uring_submit() return value check\n\nFor SQPOLL rings the man page of io_uring_submit(3) states that the\nreturn value can be higher than the number of submitted SQEs and on\na very slow overloaded system we sometimes see the test fail with:\n\n| short submit 16\n| test 8 failed\n\nTo fix this, allow the return value to be higher than expected.\n\nSigned-off-by: Christian A. Ehrhardt \u003clk@c--e.de\u003e\n"
    },
    {
      "commit": "650d8fb7acb5952a12530b617f09da75b95c979c",
      "tree": "e9798a2959f1db7fa52cc956d2755ad000089e59",
      "parents": [
        "16fe1c096d770d29727ef3a65a0eabb8448d59c6",
        "500c7b4d456338ca1b1eb1c90ac7753d6ee59d3a"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 16 10:21:37 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 16 10:21:37 2026 -0600"
      },
      "message": "Merge branch \u0027harden-ci-workflow-security\u0027 of https://github.com/Alb3e3/liburing\n\n* \u0027harden-ci-workflow-security\u0027 of https://github.com/Alb3e3/liburing:\n  Harden CI workflow security\n"
    },
    {
      "commit": "16fe1c096d770d29727ef3a65a0eabb8448d59c6",
      "tree": "c5f6fa7d14a410b41a554a1fc7a68039fbb03664",
      "parents": [
        "66c8aed4b8189d4bb0dde6c88d1879afce3a4647",
        "81ab27d6d3ce42995f5a4b8a8d384f5ced8e6884"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 16 06:32:12 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 16 06:32:12 2026 -0600"
      },
      "message": "Merge branch \u0027man\u0027 of https://github.com/jiripospisil/liburing\n\n* \u0027man\u0027 of https://github.com/jiripospisil/liburing:\n  man: Fix a few typos\n"
    },
    {
      "commit": "81ab27d6d3ce42995f5a4b8a8d384f5ced8e6884",
      "tree": "c5f6fa7d14a410b41a554a1fc7a68039fbb03664",
      "parents": [
        "66c8aed4b8189d4bb0dde6c88d1879afce3a4647"
      ],
      "author": {
        "name": "Jiri Pospisil",
        "email": "jiri@jpospisil.com",
        "time": "Tue Jun 16 12:00:16 2026 +0000"
      },
      "committer": {
        "name": "Jiri Pospisil",
        "email": "jiri@jpospisil.com",
        "time": "Tue Jun 16 12:10:08 2026 +0000"
      },
      "message": "man: Fix a few typos\n\nSigned-off-by: Jiri Pospisil \u003cjiri@jpospisil.com\u003e\n"
    },
    {
      "commit": "66c8aed4b8189d4bb0dde6c88d1879afce3a4647",
      "tree": "e0ba143d01a8edac3e08f9dd9627a50a8ddcfae8",
      "parents": [
        "2750b94a77ea9e4e156fd0caa5c14552e7d1397f"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Jun 15 10:07:47 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Mon Jun 15 10:07:47 2026 -0600"
      },
      "message": "test/nop-fixed-file-leak.c: add fixed file leak test\n\nTest case for linked issue.\n\nLink: https://lore.kernel.org/io-uring/20260615144619.482749-1-vasilisalmpanis@gmail.com/\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "500c7b4d456338ca1b1eb1c90ac7753d6ee59d3a",
      "tree": "935a618faf739e355e4d1de3aac6a86b45671b57",
      "parents": [
        "2750b94a77ea9e4e156fd0caa5c14552e7d1397f"
      ],
      "author": {
        "name": "Alb3e3",
        "email": "74142887+Alb3e3@users.noreply.github.com",
        "time": "Thu Jun 11 11:58:48 2026 +0200"
      },
      "committer": {
        "name": "Alb3e3",
        "email": "74142887+Alb3e3@users.noreply.github.com",
        "time": "Thu Jun 11 14:23:45 2026 +0200"
      },
      "message": "Harden CI workflow security\n\nLimit the workflow token for the CI workflow to read-only contents\naccess. The job only needs repository reads, so the default write-capable\ntoken is broader than necessary.\n\nAlso avoid direct GitHub expression interpolation in the shell command\nthat builds the commit list. The generated matrix values are passed\nthrough environment variables and quoted before checkout so the shell does\nnot evaluate attacker-controlled pull request metadata.\n\nSigned-off-by: Alb3e3 \u003c74142887+Alb3e3@users.noreply.github.com\u003e\n"
    },
    {
      "commit": "2750b94a77ea9e4e156fd0caa5c14552e7d1397f",
      "tree": "12d7dc5c811f794d8e20bf1352ce39a62cd481fa",
      "parents": [
        "b7fc10a54a413758c9612953541993c0c2b6be4e",
        "a6566d59ba3ba826862bbd4bb8d9a90fcea1ee49"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jun 10 06:57:31 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jun 10 06:57:31 2026 -0600"
      },
      "message": "Merge branch \u0027poll-update-trigger\u0027 of https://github.com/schlad/liburing\n\n* \u0027poll-update-trigger\u0027 of https://github.com/schlad/liburing:\n  test/poll-update-trigger: fix poll mask byte order\n"
    },
    {
      "commit": "a6566d59ba3ba826862bbd4bb8d9a90fcea1ee49",
      "tree": "90ad66ccb81c89d04ea70c4601f2f5b6621dbe2e",
      "parents": [
        "e3d35ea59d3ba09075ed4d7751e4bb9049cce64a"
      ],
      "author": {
        "name": "Sebastian Chlad",
        "email": "sebastian.chlad@suse.com",
        "time": "Wed Jun 10 13:31:50 2026 +0200"
      },
      "committer": {
        "name": "Sebastian Chlad",
        "email": "sebastian.chlad@suse.com",
        "time": "Wed Jun 10 14:51:46 2026 +0200"
      },
      "message": "test/poll-update-trigger: fix poll mask byte order\n\nsqe-\u003epoll32_events is \"word-reversed for BE\", so assigning POLLOUT\ndirectly gives the kernel the wrong mask on s390 and the test hangs.\nUse io_uring_prep_poll_update() which handles the byte swap correctly.\n\nSigned-off-by: Sebastian Chlad \u003csebastian.chlad@suse.com\u003e\n"
    },
    {
      "commit": "b7fc10a54a413758c9612953541993c0c2b6be4e",
      "tree": "33774f445014daa7b65572f05882767f641e4405",
      "parents": [
        "41533f6fac2ae241f50d22787dc8461682fe9195"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jun 10 06:21:56 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jun 10 06:21:56 2026 -0600"
      },
      "message": "examples/echo-server: add to .gitignore\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "41533f6fac2ae241f50d22787dc8461682fe9195",
      "tree": "30481c94096edf6888bdfc43380ab3541f2321d3",
      "parents": [
        "5290dd89cc198d101a651fe1756d505297de0f81",
        "395f27d55f794c8ba133ab2001fdbc52da013d5d"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jun 10 06:19:17 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jun 10 06:19:17 2026 -0600"
      },
      "message": "Merge branch \u0027add-multishot-echo-server\u0027 of https://github.com/Kprateek283/liburing\n\n* \u0027add-multishot-echo-server\u0027 of https://github.com/Kprateek283/liburing:\n  examples: add minimal multishot echo server\n"
    },
    {
      "commit": "395f27d55f794c8ba133ab2001fdbc52da013d5d",
      "tree": "4d6e30a1de20174322e4db994962d41faf61835b",
      "parents": [
        "e6852bc031d4f1036fd4b3fd40feeac579bbff90"
      ],
      "author": {
        "name": "Prateek",
        "email": "kprateek283@gmail.com",
        "time": "Wed Jun 10 17:29:55 2026 +0530"
      },
      "committer": {
        "name": "Prateek",
        "email": "kprateek283@gmail.com",
        "time": "Wed Jun 10 17:29:55 2026 +0530"
      },
      "message": "examples: add minimal multishot echo server\n\n    Adds a basic echo server to demonstrate modern io_uring networking\n    best practices including:\n    - Multishot accept\n    - Multishot receive\n    - Provided buffer rings with proper lifecycle management\n\n    This serves as a simpler entry point than proxy.c for beginners\n    learning the API.\n\nSigned-off-by: Prateek \u003ckprateek283@gmail.com\u003e\n"
    },
    {
      "commit": "5290dd89cc198d101a651fe1756d505297de0f81",
      "tree": "97a024b23bcc6a1523648698f68e9d370744b5ef",
      "parents": [
        "eed315ffb7b4269cb0e420050712e988a1edf580",
        "cd78157180fc8cfca2431bb31327fa763f9210f2"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:31:52 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:31:52 2026 -0600"
      },
      "message": "Merge branch \u0027fixes\u0027\n\nSet of fixes, and a test case for one of the issues.\n\n* fixes:\n  liburing.h: avoid OOL round trip in io_uring_peek_cqe() on empty CQ\n  liburing.h: drop acquire ordering on CQ head load in __io_uring_peek_cqe()\n  src/setup: explicitly request 2MB huge pages\n  src/arch: use sysconf() for page size on aarch64/riscv64 libc builds\n  src/setup: account SQ array in rings_size()\n  src/sanitize: check secondary user pointers as well\n  src/sanitize: initialize the handler table at compile time\n  src/queue: io_uring_wait_cqes_min_timeout() should -EINVAL if unsupported\n  liburing.h: don\u0027t return stale CQE pointer with timeout error\n  src/arch: use prlimit64 for the rlimit syscall wrappers\n  src/setup: account SQ array in the rings region in io_uring_alloc_huge()\n  src/setup: restore ring fd and flags init in io_uring_queue_mmap()\n  test/cq-peek-batch-mixed: add peek-batch test for mixed CQE rings\n  src/queue: handle mixed CQEs in io_uring_peek_batch_cqe()\n  src/register: fix mmap leak in io_uring_resize_rings()\n"
    },
    {
      "commit": "cd78157180fc8cfca2431bb31327fa763f9210f2",
      "tree": "97a024b23bcc6a1523648698f68e9d370744b5ef",
      "parents": [
        "a4d619a2869a1b4390c6da4ee7addad968b330e6"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:06:56 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:15:06 2026 -0600"
      },
      "message": "liburing.h: avoid OOL round trip in io_uring_peek_cqe() on empty CQ\n\nWith the CQ empty, io_uring_peek_cqe() called into __io_uring_get_cqe()\njust to do a second full peek and conclude -EAGAIN, costing a function\ncall, a redundant acquire load of the CQ tail, and the get_data setup\non every poll. That\u0027s wasted work for spin-poll style users.\n\nReturn -EAGAIN directly if the peek found nothing and there\u0027s nothing\nthe kernel could flush to the CQ: no IOPOLL completions to reap, no\noverflown CQEs, and no pending task work. Those cases, and a peek that\nconsumed an internal timeout CQE, still take the slow path as before.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "a4d619a2869a1b4390c6da4ee7addad968b330e6",
      "tree": "434c43cc60736aa66f26151201ad258cd8b3c190",
      "parents": [
        "37297be2d260de4418a837f44b30fece8f0f6e13"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:06:03 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:14:54 2026 -0600"
      },
      "message": "liburing.h: drop acquire ordering on CQ head load in __io_uring_peek_cqe()\n\nThe CQ head is only ever written by the application itself, so there\u0027s\nno inter-thread ordering to be had from an acquire load - the ordering\nthat protects the CQE contents is the acquire on the tail load, pairing\nwith the kernel publishing CQEs. The double load_acquire serializes the\nhottest CQ path on weakly ordered architectures, and both\nio_uring_cqe_iter_init() and io_uring_cq_ready() already read the head\nwith a plain load.\n\nEffectively a revert of 81cb9479c8c4 (\"smp_load_acquire(ring-\u003ecq.khead)\nin __io_uring_peek_cqe() for consistent dereferencing\")\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "37297be2d260de4418a837f44b30fece8f0f6e13",
      "tree": "01e3f1f475333fbad636231409bdf163eea01ebb",
      "parents": [
        "284b1a8be2ca2ea546204ed2c501414c89bea48f"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:37:02 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:14:40 2026 -0600"
      },
      "message": "src/setup: explicitly request 2MB huge pages\n\nThe huge page allocations assume a 2MB huge page size, but a plain\nMAP_HUGETLB mmap uses the system default hugetlb size. On setups where\nthat\u0027s not 2MB (1GB default on x86, 512MB on 64K page arm64), the\nkernel rounds the mapping up to the default size while liburing thinks\nit\u0027s 2MB - and the later munmap of a partial hugetlb VMA fails with\nEINVAL, silently leaking the entire mapping on every ring teardown.\n\nPass MAP_HUGE_2MB so the mapping matches the assumed size.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "284b1a8be2ca2ea546204ed2c501414c89bea48f",
      "tree": "bcc918e8f0aca4d3f6ba07db8e839cd0a9068e5c",
      "parents": [
        "a0d356e8c42cf81d22a06d0787556ba0c1365523"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:36:36 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:14:31 2026 -0600"
      },
      "message": "src/arch: use sysconf() for page size on aarch64/riscv64 libc builds\n\nThe /proc/self/auxv parsing silently falls back to 4096 if /proc isn\u0027t\nmounted (chroots, minimal containers), which yields a wrong page size\non 16K/64K page kernels and hence broken ring size/offset calculations.\nOnly nolibc builds need the manual auxv parsing, use sysconf() when\nbuilding with a libc like the generic arch code does.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "a0d356e8c42cf81d22a06d0787556ba0c1365523",
      "tree": "b6fa81a9eacb012257218e81103868566ab91c6a",
      "parents": [
        "835f6979f82c8385190e6bc74b02af443a02eee8"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:35:51 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:14:19 2026 -0600"
      },
      "message": "src/setup: account SQ array in rings_size()\n\nrings_size() never accounted the SQ array, which the kernel places at\nthe tail of the rings allocation. As a result, io_uring_mlock_size()\nunder-reported the required memlock memory by sq_entries * 4 (rounded\nup) for entries \u003e\u003d 1024 - and the pre-5.12 kernels it matters for\nalways have the SQ array. io_uring_memory_size() was similarly short\nfor rings setup without IORING_SETUP_NO_SQARRAY.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "835f6979f82c8385190e6bc74b02af443a02eee8",
      "tree": "e0f5583dc3ce7be2f77bd2bc813764ee19cf823f",
      "parents": [
        "107b1498fa79eab005485dd879ae7a9c128c5f7d"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:35:34 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:14:12 2026 -0600"
      },
      "message": "src/sanitize: check secondary user pointers as well\n\nSeveral opcodes carry a second (or third) user pointer that was never\nchecked: the newpath/linkpath of RENAMEAT/LINKAT/SYMLINKAT, the\nopen_how of OPENAT2, the value pointer of the xattr ops, the addrlen\npointer of ACCEPT, and the destination address of SEND_ZC - all in\n-\u003eaddr2. Check those too. Also check the full iovec array in\nliburing_sanitize_iovecs() rather than just its first byte.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "107b1498fa79eab005485dd879ae7a9c128c5f7d",
      "tree": "6c0b50655d0454b547a96d7fdc42413889504233",
      "parents": [
        "80f35586d3298866cf8d1008bc6d83c02255bd82"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:34:44 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:13:59 2026 -0600"
      },
      "message": "src/sanitize: initialize the handler table at compile time\n\nThe handler table was filled lazily on first submit with plain stores,\nwith a plain bool guarding initialization. Two threads doing their\nfirst submit on separate rings could race: the flag store may become\nvisible before the table stores, and the second thread would then call\na NULL handler. Make the table const and initialized at compile time,\nwhich also stops both symbols leaking into the global namespace.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "80f35586d3298866cf8d1008bc6d83c02255bd82",
      "tree": "306ba4553258fd1c25ece7eba82b5b9584ea153b",
      "parents": [
        "7e01907b4a9d46da7215269949db66384657e510"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:33:43 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:13:34 2026 -0600"
      },
      "message": "src/queue: io_uring_wait_cqes_min_timeout() should -EINVAL if unsupported\n\nIf the kernel doesn\u0027t support IORING_FEAT_MIN_TIMEOUT, the min wait\ntime was silently dropped and the call degraded into a plain\nio_uring_wait_cqes(). The man page documents -EINVAL for this case,\nand io_uring_submit_and_wait_min_timeout() already returns it.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "7e01907b4a9d46da7215269949db66384657e510",
      "tree": "75ac39f8dc98dabc7d08d89121cfb0a6bd6b19f2",
      "parents": [
        "80664fa659531d1f1a7f52fc80e0a69fe99f0845"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:33:27 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:13:11 2026 -0600"
      },
      "message": "liburing.h: don\u0027t return stale CQE pointer with timeout error\n\nOn kernels without IORING_FEAT_EXT_ARG, when the internal timeout CQE\ncompletes with res \u003c 0, io_uring_skip_cqe() sets the error, advances\nthe CQ head past the CQE, and returns false. __io_uring_peek_cqe()\nwould then break out with cqe still pointing at the released slot, and\nthe get_cqe path stored that to *cqe_ptr - handing the application\n-ETIME along with a pointer to a CQE the kernel is free to overwrite.\nThe pre-refactor code cleared the CQE pointer in this case.\n\nFixes: 9cecbdb6092c (\"Add support for IORING_SETUP_CQE_MIXED\")\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "80664fa659531d1f1a7f52fc80e0a69fe99f0845",
      "tree": "4b658e5f0e7657928339028eb82a4b8e2018be6b",
      "parents": [
        "692585d63b77417d184356c902c6447605eb9a64"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:33:11 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:13:06 2026 -0600"
      },
      "message": "src/arch: use prlimit64 for the rlimit syscall wrappers\n\nThe raw __NR_getrlimit/__NR_setrlimit syscalls use the legacy kernel\nstruct rlimit, which has 32-bit fields on i386 - but liburing is built\nwith -D_FILE_OFFSET_BITS\u003d64, where the userspace struct rlimit carries\n64-bit fields. On i386 nolibc builds, increase_rlimit_nofile() would\nthus read garbage limits and could write garbage back via setrlimit,\nbreaking the EMFILE fallback in io_uring_register_files().\n\nUse __NR_prlimit64, which takes struct rlimit64 on every arch, matching\nthe 64-bit userspace struct.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "692585d63b77417d184356c902c6447605eb9a64",
      "tree": "95d46d1e9ec8bac0ae7f227fadb18575b9b6f80a",
      "parents": [
        "435e6b286e40552f5c07f86a098e410c3670b54e"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:32:00 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:12:59 2026 -0600"
      },
      "message": "src/setup: account SQ array in the rings region in io_uring_alloc_huge()\n\nThe SQ array bytes were added to the sqes region, but the kernel places\nthe SQ array at the tail of the rings region for IORING_SETUP_NO_MMAP.\nThat left the rings region budget short by the SQ array size, so for\nsq_entries \u003e\u003d 1024 the kernel would pin (and liburing\u0027s SQ array init\nwould write) beyond the rings budget - and beyond the returned mem_used,\nwhich io_uring_queue_init_mem() callers use to pack multiple rings into\none buffer, silently corrupting the previous ring. Only reachable via\nthe NO_SQARRAY fallback, i.e. kernels that have NO_MMAP but not\nNO_SQARRAY support.\n\nAccount the SQ array in the rings region, matching the kernel layout.\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "435e6b286e40552f5c07f86a098e410c3670b54e",
      "tree": "c77cf30c55496fdbdbcecf3e8ef27ba216ccd180",
      "parents": [
        "705bf6828b7174a3acd7fd5f974d3f26cd9ecb38"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 12:31:42 2026 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Tue Jun 09 13:12:52 2026 -0600"
      },
      "message": "src/setup: restore ring fd and flags init in io_uring_queue_mmap()\n\nCommit 6102a6e848b2 dropped the assignment of ring-\u003eflags and the ring\nfds from io_uring_queue_mmap(). It\u0027s an exported and documented API for\napplications that call io_uring_setup(2) themselves, and such users\nended up with a ring that had ring_fd/enter_ring_fd set to 0, where\nio_uring_submit() would target stdin and io_uring_queue_exit() would\nclose fd 0. The internal caller sets the fields up after the call,\nhence liburing itself didn\u0027t notice.\n\nRestore the assignments, and also set -\u003efeatures which is needed for\ncorrect CQE handling these days.\n\nFixes: 6102a6e848b2 (\"setup: add support for IORING_SETUP_NO_MMAP\")\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    }
  ],
  "next": "705bf6828b7174a3acd7fd5f974d3f26cd9ecb38"
}
