linux/io_uring/opdef.c

776 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* io_uring opcode handling table
*/
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/io_uring.h>
#include "io_uring.h"
#include "opdef.h"
#include "refs.h"
#include "tctx.h"
#include "sqpoll.h"
#include "fdinfo.h"
#include "kbuf.h"
#include "rsrc.h"
#include "xattr.h"
#include "nop.h"
#include "fs.h"
#include "splice.h"
#include "sync.h"
#include "advise.h"
#include "openclose.h"
#include "uring_cmd.h"
#include "epoll.h"
#include "statx.h"
#include "net.h"
#include "msg_ring.h"
#include "timeout.h"
#include "poll.h"
#include "cancel.h"
#include "rw.h"
#include "waitid.h"
io_uring: add support for futex wake and wait Add support for FUTEX_WAKE/WAIT primitives. IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset. Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET. For both of them, they are using the futex2 interface. FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary. Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request. This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later. Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts. The SQE format is as follows: `addr` Address of futex `fd` futex2(2) FUTEX2_* flags `futex_flags` io_uring specific command flags. None valid now. `addr2` Value of futex `addr3` Mask to wake/wait Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-06-08 17:57:40 +00:00
#include "futex.h"
#include "truncate.h"
static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
{
WARN_ON_ONCE(1);
return -ECANCELED;
}
static __maybe_unused int io_eopnotsupp_prep(struct io_kiocb *kiocb,
const struct io_uring_sqe *sqe)
{
return -EOPNOTSUPP;
}
const struct io_issue_def io_issue_defs[] = {
[IORING_OP_NOP] = {
.audit_skip = 1,
.iopoll = 1,
.prep = io_nop_prep,
.issue = io_nop,
},
[IORING_OP_READV] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
.plug = 1,
.audit_skip = 1,
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
.vectored = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_readv,
.issue = io_read,
},
[IORING_OP_WRITEV] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.plug = 1,
.audit_skip = 1,
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
.vectored = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_writev,
.issue = io_write,
},
[IORING_OP_FSYNC] = {
.needs_file = 1,
.audit_skip = 1,
.prep = io_fsync_prep,
.issue = io_fsync,
},
[IORING_OP_READ_FIXED] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.plug = 1,
.audit_skip = 1,
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_read_fixed,
.issue = io_read,
},
[IORING_OP_WRITE_FIXED] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.plug = 1,
.audit_skip = 1,
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_write_fixed,
.issue = io_write,
},
[IORING_OP_POLL_ADD] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.audit_skip = 1,
.prep = io_poll_add_prep,
.issue = io_poll_add,
},
[IORING_OP_POLL_REMOVE] = {
.audit_skip = 1,
.prep = io_poll_remove_prep,
.issue = io_poll_remove,
},
[IORING_OP_SYNC_FILE_RANGE] = {
.needs_file = 1,
.audit_skip = 1,
.prep = io_sfr_prep,
.issue = io_sync_file_range,
},
[IORING_OP_SENDMSG] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.ioprio = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_sendmsg_prep,
.issue = io_sendmsg,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_RECVMSG] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
.ioprio = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_recvmsg_prep,
.issue = io_recvmsg,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_TIMEOUT] = {
.audit_skip = 1,
.async_size = sizeof(struct io_timeout_data),
.prep = io_timeout_prep,
.issue = io_timeout,
},
[IORING_OP_TIMEOUT_REMOVE] = {
/* used by timeout updates' prep() */
.audit_skip = 1,
.prep = io_timeout_remove_prep,
.issue = io_timeout_remove,
},
[IORING_OP_ACCEPT] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.poll_exclusive = 1,
.ioprio = 1, /* used for flags */
#if defined(CONFIG_NET)
.prep = io_accept_prep,
.issue = io_accept,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_ASYNC_CANCEL] = {
.audit_skip = 1,
.prep = io_async_cancel_prep,
.issue = io_async_cancel,
},
[IORING_OP_LINK_TIMEOUT] = {
.audit_skip = 1,
.async_size = sizeof(struct io_timeout_data),
.prep = io_link_timeout_prep,
.issue = io_no_issue,
},
[IORING_OP_CONNECT] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_connect_prep,
.issue = io_connect,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_FALLOCATE] = {
.needs_file = 1,
.prep = io_fallocate_prep,
.issue = io_fallocate,
},
[IORING_OP_OPENAT] = {
.prep = io_openat_prep,
.issue = io_openat,
},
[IORING_OP_CLOSE] = {
.prep = io_close_prep,
.issue = io_close,
},
[IORING_OP_FILES_UPDATE] = {
.audit_skip = 1,
.iopoll = 1,
.prep = io_files_update_prep,
.issue = io_files_update,
},
[IORING_OP_STATX] = {
.audit_skip = 1,
.prep = io_statx_prep,
.issue = io_statx,
},
[IORING_OP_READ] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
.plug = 1,
.audit_skip = 1,
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_read,
.issue = io_read,
},
[IORING_OP_WRITE] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.plug = 1,
.audit_skip = 1,
.ioprio = 1,
.iopoll = 1,
.iopoll_queue = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_write,
.issue = io_write,
},
[IORING_OP_FADVISE] = {
.needs_file = 1,
.audit_skip = 1,
.prep = io_fadvise_prep,
.issue = io_fadvise,
},
[IORING_OP_MADVISE] = {
.audit_skip = 1,
.prep = io_madvise_prep,
.issue = io_madvise,
},
[IORING_OP_SEND] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.audit_skip = 1,
.ioprio = 1,
io_uring/net: add provided buffer support for IORING_OP_SEND It's pretty trivial to wire up provided buffer support for the send side, just like how it's done the receive side. This enables setting up a buffer ring that an application can use to push pending sends to, and then have a send pick a buffer from that ring. One of the challenges with async IO and networking sends is that you can get into reordering conditions if you have more than one inflight at the same time. Consider the following scenario where everything is fine: 1) App queues sendA for socket1 2) App queues sendB for socket1 3) App does io_uring_submit() 4) sendA is issued, completes successfully, posts CQE 5) sendB is issued, completes successfully, posts CQE All is fine. Requests are always issued in-order, and both complete inline as most sends do. However, if we're flooding socket1 with sends, the following could also result from the same sequence: 1) App queues sendA for socket1 2) App queues sendB for socket1 3) App does io_uring_submit() 4) sendA is issued, socket1 is full, poll is armed for retry 5) Space frees up in socket1, this triggers sendA retry via task_work 6) sendB is issued, completes successfully, posts CQE 7) sendA is retried, completes successfully, posts CQE Now we've sent sendB before sendA, which can make things unhappy. If both sendA and sendB had been using provided buffers, then it would look as follows instead: 1) App queues dataA for sendA, queues sendA for socket1 2) App queues dataB for sendB queues sendB for socket1 3) App does io_uring_submit() 4) sendA is issued, socket1 is full, poll is armed for retry 5) Space frees up in socket1, this triggers sendA retry via task_work 6) sendB is issued, picks first buffer (dataA), completes successfully, posts CQE (which says "I sent dataA") 7) sendA is retried, picks first buffer (dataB), completes successfully, posts CQE (which says "I sent dataB") Now we've sent the data in order, and everybody is happy. It's worth noting that this also opens the door for supporting multishot sends, as provided buffers would be a prerequisite for that. Those can trigger either when new buffers are added to the outgoing ring, or (if stalled due to lack of space) when space frees up in the socket. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-02-19 17:46:44 +00:00
.buffer_select = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_sendmsg_prep,
.issue = io_send,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_RECV] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
.audit_skip = 1,
.ioprio = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_recvmsg_prep,
.issue = io_recv,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_OPENAT2] = {
.prep = io_openat2_prep,
.issue = io_openat2,
},
[IORING_OP_EPOLL_CTL] = {
.unbound_nonreg_file = 1,
.audit_skip = 1,
#if defined(CONFIG_EPOLL)
.prep = io_epoll_ctl_prep,
.issue = io_epoll_ctl,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_SPLICE] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
.audit_skip = 1,
.prep = io_splice_prep,
.issue = io_splice,
},
[IORING_OP_PROVIDE_BUFFERS] = {
.audit_skip = 1,
.iopoll = 1,
.prep = io_provide_buffers_prep,
.issue = io_provide_buffers,
},
[IORING_OP_REMOVE_BUFFERS] = {
.audit_skip = 1,
.iopoll = 1,
.prep = io_remove_buffers_prep,
.issue = io_remove_buffers,
},
[IORING_OP_TEE] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
.audit_skip = 1,
.prep = io_tee_prep,
.issue = io_tee,
},
[IORING_OP_SHUTDOWN] = {
.needs_file = 1,
#if defined(CONFIG_NET)
.prep = io_shutdown_prep,
.issue = io_shutdown,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_RENAMEAT] = {
.prep = io_renameat_prep,
.issue = io_renameat,
},
[IORING_OP_UNLINKAT] = {
.prep = io_unlinkat_prep,
.issue = io_unlinkat,
},
[IORING_OP_MKDIRAT] = {
.prep = io_mkdirat_prep,
.issue = io_mkdirat,
},
[IORING_OP_SYMLINKAT] = {
.prep = io_symlinkat_prep,
.issue = io_symlinkat,
},
[IORING_OP_LINKAT] = {
.prep = io_linkat_prep,
.issue = io_linkat,
},
[IORING_OP_MSG_RING] = {
.needs_file = 1,
.iopoll = 1,
.prep = io_msg_ring_prep,
.issue = io_msg_ring,
},
[IORING_OP_FSETXATTR] = {
.needs_file = 1,
.prep = io_fsetxattr_prep,
.issue = io_fsetxattr,
},
[IORING_OP_SETXATTR] = {
.prep = io_setxattr_prep,
.issue = io_setxattr,
},
[IORING_OP_FGETXATTR] = {
.needs_file = 1,
.prep = io_fgetxattr_prep,
.issue = io_fgetxattr,
},
[IORING_OP_GETXATTR] = {
.prep = io_getxattr_prep,
.issue = io_getxattr,
},
[IORING_OP_SOCKET] = {
.audit_skip = 1,
#if defined(CONFIG_NET)
.prep = io_socket_prep,
.issue = io_socket,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_URING_CMD] = {
.needs_file = 1,
.plug = 1,
.iopoll = 1,
.iopoll_queue = 1,
.async_size = 2 * sizeof(struct io_uring_sqe),
.prep = io_uring_cmd_prep,
.issue = io_uring_cmd,
},
[IORING_OP_SEND_ZC] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.audit_skip = 1,
.ioprio = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_send_zc_prep,
.issue = io_send_zc,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_SENDMSG_ZC] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
.ioprio = 1,
#if defined(CONFIG_NET)
.async_size = sizeof(struct io_async_msghdr),
.prep = io_send_zc_prep,
.issue = io_sendmsg_zc,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_READ_MULTISHOT] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
.audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_read_mshot_prep,
.issue = io_read_mshot,
},
[IORING_OP_WAITID] = {
.async_size = sizeof(struct io_waitid_async),
.prep = io_waitid_prep,
.issue = io_waitid,
},
io_uring: add support for futex wake and wait Add support for FUTEX_WAKE/WAIT primitives. IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset. Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET. For both of them, they are using the futex2 interface. FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary. Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request. This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later. Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts. The SQE format is as follows: `addr` Address of futex `fd` futex2(2) FUTEX2_* flags `futex_flags` io_uring specific command flags. None valid now. `addr2` Value of futex `addr3` Mask to wake/wait Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-06-08 17:57:40 +00:00
[IORING_OP_FUTEX_WAIT] = {
#if defined(CONFIG_FUTEX)
.prep = io_futex_prep,
.issue = io_futex_wait,
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_FUTEX_WAKE] = {
#if defined(CONFIG_FUTEX)
.prep = io_futex_prep,
.issue = io_futex_wake,
#else
.prep = io_eopnotsupp_prep,
2023-06-13 01:04:32 +00:00
#endif
},
[IORING_OP_FUTEX_WAITV] = {
#if defined(CONFIG_FUTEX)
.prep = io_futexv_prep,
.issue = io_futexv_wait,
#else
.prep = io_eopnotsupp_prep,
io_uring: add support for futex wake and wait Add support for FUTEX_WAKE/WAIT primitives. IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset. Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET. For both of them, they are using the futex2 interface. FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary. Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request. This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later. Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts. The SQE format is as follows: `addr` Address of futex `fd` futex2(2) FUTEX2_* flags `futex_flags` io_uring specific command flags. None valid now. `addr2` Value of futex `addr3` Mask to wake/wait Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-06-08 17:57:40 +00:00
#endif
},
[IORING_OP_FIXED_FD_INSTALL] = {
.needs_file = 1,
.prep = io_install_fixed_fd_prep,
.issue = io_install_fixed_fd,
},
[IORING_OP_FTRUNCATE] = {
.needs_file = 1,
.hash_reg_file = 1,
.prep = io_ftruncate_prep,
.issue = io_ftruncate,
},
[IORING_OP_BIND] = {
#if defined(CONFIG_NET)
.needs_file = 1,
.prep = io_bind_prep,
.issue = io_bind,
.async_size = sizeof(struct io_async_msghdr),
#else
.prep = io_eopnotsupp_prep,
#endif
},
[IORING_OP_LISTEN] = {
#if defined(CONFIG_NET)
.needs_file = 1,
.prep = io_listen_prep,
.issue = io_listen,
.async_size = sizeof(struct io_async_msghdr),
#else
.prep = io_eopnotsupp_prep,
#endif
},
};
const struct io_cold_def io_cold_defs[] = {
[IORING_OP_NOP] = {
.name = "NOP",
},
[IORING_OP_READV] = {
.name = "READV",
.cleanup = io_readv_writev_cleanup,
.fail = io_rw_fail,
},
[IORING_OP_WRITEV] = {
.name = "WRITEV",
.cleanup = io_readv_writev_cleanup,
.fail = io_rw_fail,
},
[IORING_OP_FSYNC] = {
.name = "FSYNC",
},
[IORING_OP_READ_FIXED] = {
.name = "READ_FIXED",
io_uring/rw: Free iovec before cleaning async data kmemleak shows that there is a memory leak in io_uring read operation, where a buffer is allocated at iovec import, but never de-allocated. The memory is allocated at io_async_rw->free_iovec, but, then io_async_rw is kfreed, taking the allocated memory with it. I saw this happening when the read operation fails with -11 (EAGAIN). This is the kmemleak splat. unreferenced object 0xffff8881da591c00 (size 256): ... backtrace (crc 7a15bdee): [<00000000256f2de4>] __kmalloc+0x2d6/0x410 [<000000007a9f5fc7>] iovec_from_user.part.0+0xc6/0x160 [<00000000cecdf83a>] __import_iovec+0x50/0x220 [<00000000d1d586a2>] __io_import_iovec+0x13d/0x220 [<0000000054ee9bd2>] io_prep_rw+0x186/0x340 [<00000000a9c0372d>] io_prep_rwv+0x31/0x120 [<000000001d1170b9>] io_prep_readv+0xe/0x30 [<0000000070b8eb67>] io_submit_sqes+0x1bd/0x780 [<00000000812496d4>] __do_sys_io_uring_enter+0x3ed/0x5b0 [<0000000081499602>] do_syscall_64+0x5d/0x170 [<00000000de1c5a4d>] entry_SYSCALL_64_after_hwframe+0x76/0x7e This occurs because the async data cleanup functions are not set for read/write operations. As a result, the potentially allocated iovec in the rw async data is not freed before the async data is released, leading to a memory leak. With this following patch, kmemleak does not show the leaked memory anymore, and all liburing tests pass. Fixes: a9165b83c193 ("io_uring/rw: always setup io_async_rw for read/write requests") Signed-off-by: Breno Leitao <leitao@debian.org> Link: https://lore.kernel.org/r/20240530142340.1248216-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-05-30 14:23:39 +00:00
.cleanup = io_readv_writev_cleanup,
.fail = io_rw_fail,
},
[IORING_OP_WRITE_FIXED] = {
.name = "WRITE_FIXED",
io_uring/rw: Free iovec before cleaning async data kmemleak shows that there is a memory leak in io_uring read operation, where a buffer is allocated at iovec import, but never de-allocated. The memory is allocated at io_async_rw->free_iovec, but, then io_async_rw is kfreed, taking the allocated memory with it. I saw this happening when the read operation fails with -11 (EAGAIN). This is the kmemleak splat. unreferenced object 0xffff8881da591c00 (size 256): ... backtrace (crc 7a15bdee): [<00000000256f2de4>] __kmalloc+0x2d6/0x410 [<000000007a9f5fc7>] iovec_from_user.part.0+0xc6/0x160 [<00000000cecdf83a>] __import_iovec+0x50/0x220 [<00000000d1d586a2>] __io_import_iovec+0x13d/0x220 [<0000000054ee9bd2>] io_prep_rw+0x186/0x340 [<00000000a9c0372d>] io_prep_rwv+0x31/0x120 [<000000001d1170b9>] io_prep_readv+0xe/0x30 [<0000000070b8eb67>] io_submit_sqes+0x1bd/0x780 [<00000000812496d4>] __do_sys_io_uring_enter+0x3ed/0x5b0 [<0000000081499602>] do_syscall_64+0x5d/0x170 [<00000000de1c5a4d>] entry_SYSCALL_64_after_hwframe+0x76/0x7e This occurs because the async data cleanup functions are not set for read/write operations. As a result, the potentially allocated iovec in the rw async data is not freed before the async data is released, leading to a memory leak. With this following patch, kmemleak does not show the leaked memory anymore, and all liburing tests pass. Fixes: a9165b83c193 ("io_uring/rw: always setup io_async_rw for read/write requests") Signed-off-by: Breno Leitao <leitao@debian.org> Link: https://lore.kernel.org/r/20240530142340.1248216-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-05-30 14:23:39 +00:00
.cleanup = io_readv_writev_cleanup,
.fail = io_rw_fail,
},
[IORING_OP_POLL_ADD] = {
.name = "POLL_ADD",
},
[IORING_OP_POLL_REMOVE] = {
.name = "POLL_REMOVE",
},
[IORING_OP_SYNC_FILE_RANGE] = {
.name = "SYNC_FILE_RANGE",
},
[IORING_OP_SENDMSG] = {
.name = "SENDMSG",
#if defined(CONFIG_NET)
.cleanup = io_sendmsg_recvmsg_cleanup,
.fail = io_sendrecv_fail,
#endif
},
[IORING_OP_RECVMSG] = {
.name = "RECVMSG",
#if defined(CONFIG_NET)
.cleanup = io_sendmsg_recvmsg_cleanup,
.fail = io_sendrecv_fail,
#endif
},
[IORING_OP_TIMEOUT] = {
.name = "TIMEOUT",
},
[IORING_OP_TIMEOUT_REMOVE] = {
.name = "TIMEOUT_REMOVE",
},
[IORING_OP_ACCEPT] = {
.name = "ACCEPT",
},
[IORING_OP_ASYNC_CANCEL] = {
.name = "ASYNC_CANCEL",
},
[IORING_OP_LINK_TIMEOUT] = {
.name = "LINK_TIMEOUT",
},
[IORING_OP_CONNECT] = {
.name = "CONNECT",
},
[IORING_OP_FALLOCATE] = {
.name = "FALLOCATE",
},
[IORING_OP_OPENAT] = {
.name = "OPENAT",
.cleanup = io_open_cleanup,
},
[IORING_OP_CLOSE] = {
.name = "CLOSE",
},
[IORING_OP_FILES_UPDATE] = {
.name = "FILES_UPDATE",
},
[IORING_OP_STATX] = {
.name = "STATX",
.cleanup = io_statx_cleanup,
},
[IORING_OP_READ] = {
.name = "READ",
io_uring/rw: Free iovec before cleaning async data kmemleak shows that there is a memory leak in io_uring read operation, where a buffer is allocated at iovec import, but never de-allocated. The memory is allocated at io_async_rw->free_iovec, but, then io_async_rw is kfreed, taking the allocated memory with it. I saw this happening when the read operation fails with -11 (EAGAIN). This is the kmemleak splat. unreferenced object 0xffff8881da591c00 (size 256): ... backtrace (crc 7a15bdee): [<00000000256f2de4>] __kmalloc+0x2d6/0x410 [<000000007a9f5fc7>] iovec_from_user.part.0+0xc6/0x160 [<00000000cecdf83a>] __import_iovec+0x50/0x220 [<00000000d1d586a2>] __io_import_iovec+0x13d/0x220 [<0000000054ee9bd2>] io_prep_rw+0x186/0x340 [<00000000a9c0372d>] io_prep_rwv+0x31/0x120 [<000000001d1170b9>] io_prep_readv+0xe/0x30 [<0000000070b8eb67>] io_submit_sqes+0x1bd/0x780 [<00000000812496d4>] __do_sys_io_uring_enter+0x3ed/0x5b0 [<0000000081499602>] do_syscall_64+0x5d/0x170 [<00000000de1c5a4d>] entry_SYSCALL_64_after_hwframe+0x76/0x7e This occurs because the async data cleanup functions are not set for read/write operations. As a result, the potentially allocated iovec in the rw async data is not freed before the async data is released, leading to a memory leak. With this following patch, kmemleak does not show the leaked memory anymore, and all liburing tests pass. Fixes: a9165b83c193 ("io_uring/rw: always setup io_async_rw for read/write requests") Signed-off-by: Breno Leitao <leitao@debian.org> Link: https://lore.kernel.org/r/20240530142340.1248216-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-05-30 14:23:39 +00:00
.cleanup = io_readv_writev_cleanup,
.fail = io_rw_fail,
},
[IORING_OP_WRITE] = {
.name = "WRITE",
io_uring/rw: Free iovec before cleaning async data kmemleak shows that there is a memory leak in io_uring read operation, where a buffer is allocated at iovec import, but never de-allocated. The memory is allocated at io_async_rw->free_iovec, but, then io_async_rw is kfreed, taking the allocated memory with it. I saw this happening when the read operation fails with -11 (EAGAIN). This is the kmemleak splat. unreferenced object 0xffff8881da591c00 (size 256): ... backtrace (crc 7a15bdee): [<00000000256f2de4>] __kmalloc+0x2d6/0x410 [<000000007a9f5fc7>] iovec_from_user.part.0+0xc6/0x160 [<00000000cecdf83a>] __import_iovec+0x50/0x220 [<00000000d1d586a2>] __io_import_iovec+0x13d/0x220 [<0000000054ee9bd2>] io_prep_rw+0x186/0x340 [<00000000a9c0372d>] io_prep_rwv+0x31/0x120 [<000000001d1170b9>] io_prep_readv+0xe/0x30 [<0000000070b8eb67>] io_submit_sqes+0x1bd/0x780 [<00000000812496d4>] __do_sys_io_uring_enter+0x3ed/0x5b0 [<0000000081499602>] do_syscall_64+0x5d/0x170 [<00000000de1c5a4d>] entry_SYSCALL_64_after_hwframe+0x76/0x7e This occurs because the async data cleanup functions are not set for read/write operations. As a result, the potentially allocated iovec in the rw async data is not freed before the async data is released, leading to a memory leak. With this following patch, kmemleak does not show the leaked memory anymore, and all liburing tests pass. Fixes: a9165b83c193 ("io_uring/rw: always setup io_async_rw for read/write requests") Signed-off-by: Breno Leitao <leitao@debian.org> Link: https://lore.kernel.org/r/20240530142340.1248216-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-05-30 14:23:39 +00:00
.cleanup = io_readv_writev_cleanup,
.fail = io_rw_fail,
},
[IORING_OP_FADVISE] = {
.name = "FADVISE",
},
[IORING_OP_MADVISE] = {
.name = "MADVISE",
},
[IORING_OP_SEND] = {
.name = "SEND",
#if defined(CONFIG_NET)
.cleanup = io_sendmsg_recvmsg_cleanup,
.fail = io_sendrecv_fail,
#endif
},
[IORING_OP_RECV] = {
.name = "RECV",
#if defined(CONFIG_NET)
.cleanup = io_sendmsg_recvmsg_cleanup,
.fail = io_sendrecv_fail,
#endif
},
[IORING_OP_OPENAT2] = {
.name = "OPENAT2",
.cleanup = io_open_cleanup,
},
[IORING_OP_EPOLL_CTL] = {
.name = "EPOLL",
},
[IORING_OP_SPLICE] = {
.name = "SPLICE",
},
[IORING_OP_PROVIDE_BUFFERS] = {
.name = "PROVIDE_BUFFERS",
},
[IORING_OP_REMOVE_BUFFERS] = {
.name = "REMOVE_BUFFERS",
},
[IORING_OP_TEE] = {
.name = "TEE",
},
[IORING_OP_SHUTDOWN] = {
.name = "SHUTDOWN",
},
[IORING_OP_RENAMEAT] = {
.name = "RENAMEAT",
.cleanup = io_renameat_cleanup,
},
[IORING_OP_UNLINKAT] = {
.name = "UNLINKAT",
.cleanup = io_unlinkat_cleanup,
},
[IORING_OP_MKDIRAT] = {
.name = "MKDIRAT",
.cleanup = io_mkdirat_cleanup,
},
[IORING_OP_SYMLINKAT] = {
.name = "SYMLINKAT",
.cleanup = io_link_cleanup,
},
[IORING_OP_LINKAT] = {
.name = "LINKAT",
.cleanup = io_link_cleanup,
},
[IORING_OP_MSG_RING] = {
.name = "MSG_RING",
.cleanup = io_msg_ring_cleanup,
},
[IORING_OP_FSETXATTR] = {
.name = "FSETXATTR",
.cleanup = io_xattr_cleanup,
},
[IORING_OP_SETXATTR] = {
.name = "SETXATTR",
.cleanup = io_xattr_cleanup,
},
[IORING_OP_FGETXATTR] = {
.name = "FGETXATTR",
.cleanup = io_xattr_cleanup,
},
[IORING_OP_GETXATTR] = {
.name = "GETXATTR",
.cleanup = io_xattr_cleanup,
},
[IORING_OP_SOCKET] = {
.name = "SOCKET",
},
[IORING_OP_URING_CMD] = {
.name = "URING_CMD",
},
[IORING_OP_SEND_ZC] = {
.name = "SEND_ZC",
#if defined(CONFIG_NET)
.cleanup = io_send_zc_cleanup,
.fail = io_sendrecv_fail,
#endif
},
[IORING_OP_SENDMSG_ZC] = {
.name = "SENDMSG_ZC",
#if defined(CONFIG_NET)
.cleanup = io_send_zc_cleanup,
.fail = io_sendrecv_fail,
#endif
},
[IORING_OP_READ_MULTISHOT] = {
.name = "READ_MULTISHOT",
io_uring/rw: Free iovec before cleaning async data kmemleak shows that there is a memory leak in io_uring read operation, where a buffer is allocated at iovec import, but never de-allocated. The memory is allocated at io_async_rw->free_iovec, but, then io_async_rw is kfreed, taking the allocated memory with it. I saw this happening when the read operation fails with -11 (EAGAIN). This is the kmemleak splat. unreferenced object 0xffff8881da591c00 (size 256): ... backtrace (crc 7a15bdee): [<00000000256f2de4>] __kmalloc+0x2d6/0x410 [<000000007a9f5fc7>] iovec_from_user.part.0+0xc6/0x160 [<00000000cecdf83a>] __import_iovec+0x50/0x220 [<00000000d1d586a2>] __io_import_iovec+0x13d/0x220 [<0000000054ee9bd2>] io_prep_rw+0x186/0x340 [<00000000a9c0372d>] io_prep_rwv+0x31/0x120 [<000000001d1170b9>] io_prep_readv+0xe/0x30 [<0000000070b8eb67>] io_submit_sqes+0x1bd/0x780 [<00000000812496d4>] __do_sys_io_uring_enter+0x3ed/0x5b0 [<0000000081499602>] do_syscall_64+0x5d/0x170 [<00000000de1c5a4d>] entry_SYSCALL_64_after_hwframe+0x76/0x7e This occurs because the async data cleanup functions are not set for read/write operations. As a result, the potentially allocated iovec in the rw async data is not freed before the async data is released, leading to a memory leak. With this following patch, kmemleak does not show the leaked memory anymore, and all liburing tests pass. Fixes: a9165b83c193 ("io_uring/rw: always setup io_async_rw for read/write requests") Signed-off-by: Breno Leitao <leitao@debian.org> Link: https://lore.kernel.org/r/20240530142340.1248216-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-05-30 14:23:39 +00:00
.cleanup = io_readv_writev_cleanup,
},
[IORING_OP_WAITID] = {
.name = "WAITID",
},
io_uring: add support for futex wake and wait Add support for FUTEX_WAKE/WAIT primitives. IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset. Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET. For both of them, they are using the futex2 interface. FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary. Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request. This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later. Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts. The SQE format is as follows: `addr` Address of futex `fd` futex2(2) FUTEX2_* flags `futex_flags` io_uring specific command flags. None valid now. `addr2` Value of futex `addr3` Mask to wake/wait Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-06-08 17:57:40 +00:00
[IORING_OP_FUTEX_WAIT] = {
.name = "FUTEX_WAIT",
},
[IORING_OP_FUTEX_WAKE] = {
.name = "FUTEX_WAKE",
},
2023-06-13 01:04:32 +00:00
[IORING_OP_FUTEX_WAITV] = {
.name = "FUTEX_WAITV",
},
[IORING_OP_FIXED_FD_INSTALL] = {
.name = "FIXED_FD_INSTALL",
},
[IORING_OP_FTRUNCATE] = {
.name = "FTRUNCATE",
},
[IORING_OP_BIND] = {
.name = "BIND",
},
[IORING_OP_LISTEN] = {
.name = "LISTEN",
},
};
const char *io_uring_get_opcode(u8 opcode)
{
if (opcode < IORING_OP_LAST)
return io_cold_defs[opcode].name;
return "INVALID";
}
bool io_uring_op_supported(u8 opcode)
{
if (opcode < IORING_OP_LAST &&
io_issue_defs[opcode].prep != io_eopnotsupp_prep)
return true;
return false;
}
void __init io_uring_optable_init(void)
{
int i;
BUILD_BUG_ON(ARRAY_SIZE(io_cold_defs) != IORING_OP_LAST);
BUILD_BUG_ON(ARRAY_SIZE(io_issue_defs) != IORING_OP_LAST);
for (i = 0; i < ARRAY_SIZE(io_issue_defs); i++) {
BUG_ON(!io_issue_defs[i].prep);
if (io_issue_defs[i].prep != io_eopnotsupp_prep)
BUG_ON(!io_issue_defs[i].issue);
WARN_ON_ONCE(!io_cold_defs[i].name);
}
}