linux/io_uring/io_uring.h
Jens Axboe 8f7033aa40 io_uring/sqpoll: ensure task state is TASK_RUNNING when running task_work
When the sqpoll is exiting and cancels pending work items, it may need
to run task_work. If this happens from within io_uring_cancel_generic(),
then it may be under waiting for the io_uring_task waitqueue. This
results in the below splat from the scheduler, as the ring mutex may be
attempted grabbed while in a TASK_INTERRUPTIBLE state.

Ensure that the task state is set appropriately for that, just like what
is done for the other cases in io_run_task_work().

do not call blocking ops when !TASK_RUNNING; state=1 set at [<0000000029387fd2>] prepare_to_wait+0x88/0x2fc
WARNING: CPU: 6 PID: 59939 at kernel/sched/core.c:8561 __might_sleep+0xf4/0x140
Modules linked in:
CPU: 6 UID: 0 PID: 59939 Comm: iou-sqp-59938 Not tainted 6.12.0-rc3-00113-g8d020023b155 #7456
Hardware name: linux,dummy-virt (DT)
pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
pc : __might_sleep+0xf4/0x140
lr : __might_sleep+0xf4/0x140
sp : ffff80008c5e7830
x29: ffff80008c5e7830 x28: ffff0000d93088c0 x27: ffff60001c2d7230
x26: dfff800000000000 x25: ffff0000e16b9180 x24: ffff80008c5e7a50
x23: 1ffff000118bcf4a x22: ffff0000e16b9180 x21: ffff0000e16b9180
x20: 000000000000011b x19: ffff80008310fac0 x18: 1ffff000118bcd90
x17: 30303c5b20746120 x16: 74657320313d6574 x15: 0720072007200720
x14: 0720072007200720 x13: 0720072007200720 x12: ffff600036c64f0b
x11: 1fffe00036c64f0a x10: ffff600036c64f0a x9 : dfff800000000000
x8 : 00009fffc939b0f6 x7 : ffff0001b6327853 x6 : 0000000000000001
x5 : ffff0001b6327850 x4 : ffff600036c64f0b x3 : ffff8000803c35bc
x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0000e16b9180
Call trace:
 __might_sleep+0xf4/0x140
 mutex_lock+0x84/0x124
 io_handle_tw_list+0xf4/0x260
 tctx_task_work_run+0x94/0x340
 io_run_task_work+0x1ec/0x3c0
 io_uring_cancel_generic+0x364/0x524
 io_sq_thread+0x820/0x124c
 ret_from_fork+0x10/0x20

Cc: stable@vger.kernel.org
Fixes: af5d68f889 ("io_uring/sqpoll: manage task_work privately")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-10-17 08:38:04 -06:00

472 lines
13 KiB
C

#ifndef IOU_CORE_H
#define IOU_CORE_H
#include <linux/errno.h>
#include <linux/lockdep.h>
#include <linux/resume_user_mode.h>
#include <linux/kasan.h>
#include <linux/poll.h>
#include <linux/io_uring_types.h>
#include <uapi/linux/eventpoll.h>
#include "io-wq.h"
#include "slist.h"
#include "filetable.h"
#ifndef CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
#endif
enum {
IOU_OK = 0,
IOU_ISSUE_SKIP_COMPLETE = -EIOCBQUEUED,
/*
* Requeue the task_work to restart operations on this request. The
* actual value isn't important, should just be not an otherwise
* valid error code, yet less than -MAX_ERRNO and valid internally.
*/
IOU_REQUEUE = -3072,
/*
* Intended only when both IO_URING_F_MULTISHOT is passed
* to indicate to the poll runner that multishot should be
* removed and the result is set on req->cqe.res.
*/
IOU_STOP_MULTISHOT = -ECANCELED,
};
struct io_wait_queue {
struct wait_queue_entry wq;
struct io_ring_ctx *ctx;
unsigned cq_tail;
unsigned cq_min_tail;
unsigned nr_timeouts;
int hit_timeout;
ktime_t min_timeout;
ktime_t timeout;
struct hrtimer t;
#ifdef CONFIG_NET_RX_BUSY_POLL
ktime_t napi_busy_poll_dt;
bool napi_prefer_busy_poll;
#endif
};
static inline bool io_should_wake(struct io_wait_queue *iowq)
{
struct io_ring_ctx *ctx = iowq->ctx;
int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
/*
* Wake up if we have enough events, or if a timeout occurred since we
* started waiting. For timeouts, we always want to return to userspace,
* regardless of event count.
*/
return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
}
bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
int io_run_task_work_sig(struct io_ring_ctx *ctx);
void io_req_defer_failed(struct io_kiocb *req, s32 res);
bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags);
void __io_commit_cqring_flush(struct io_ring_ctx *ctx);
struct file *io_file_get_normal(struct io_kiocb *req, int fd);
struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
unsigned issue_flags);
void __io_req_task_work_add(struct io_kiocb *req, unsigned flags);
void io_req_task_work_add_remote(struct io_kiocb *req, struct io_ring_ctx *ctx,
unsigned flags);
bool io_alloc_async_data(struct io_kiocb *req);
void io_req_task_queue(struct io_kiocb *req);
void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts);
void io_req_task_queue_fail(struct io_kiocb *req, int ret);
void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts);
struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries);
struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
void tctx_task_work(struct callback_head *cb);
__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
int io_uring_alloc_task_context(struct task_struct *task,
struct io_ring_ctx *ctx);
int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
int start, int end);
void io_req_queue_iowq(struct io_kiocb *req);
int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts);
int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr);
int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin);
void __io_submit_flush_completions(struct io_ring_ctx *ctx);
struct io_wq_work *io_wq_free_work(struct io_wq_work *work);
void io_wq_submit_work(struct io_wq_work *work);
void io_free_req(struct io_kiocb *req);
void io_queue_next(struct io_kiocb *req);
void io_task_refs_refill(struct io_uring_task *tctx);
bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all);
void io_activate_pollwq(struct io_ring_ctx *ctx);
static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
{
#if defined(CONFIG_PROVE_LOCKING)
lockdep_assert(in_task());
if (ctx->flags & IORING_SETUP_IOPOLL) {
lockdep_assert_held(&ctx->uring_lock);
} else if (!ctx->task_complete) {
lockdep_assert_held(&ctx->completion_lock);
} else if (ctx->submitter_task) {
/*
* ->submitter_task may be NULL and we can still post a CQE,
* if the ring has been setup with IORING_SETUP_R_DISABLED.
* Not from an SQE, as those cannot be submitted, but via
* updating tagged resources.
*/
if (ctx->submitter_task->flags & PF_EXITING)
lockdep_assert(current_work());
else
lockdep_assert(current == ctx->submitter_task);
}
#endif
}
static inline void io_req_task_work_add(struct io_kiocb *req)
{
__io_req_task_work_add(req, 0);
}
static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
{
if (!wq_list_empty(&ctx->submit_state.compl_reqs) ||
ctx->submit_state.cq_flush)
__io_submit_flush_completions(ctx);
}
#define io_for_each_link(pos, head) \
for (pos = (head); pos; pos = pos->link)
static inline bool io_get_cqe_overflow(struct io_ring_ctx *ctx,
struct io_uring_cqe **ret,
bool overflow)
{
io_lockdep_assert_cq_locked(ctx);
if (unlikely(ctx->cqe_cached >= ctx->cqe_sentinel)) {
if (unlikely(!io_cqe_cache_refill(ctx, overflow)))
return false;
}
*ret = ctx->cqe_cached;
ctx->cached_cq_tail++;
ctx->cqe_cached++;
if (ctx->flags & IORING_SETUP_CQE32)
ctx->cqe_cached++;
return true;
}
static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret)
{
return io_get_cqe_overflow(ctx, ret, false);
}
static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
struct io_kiocb *req)
{
struct io_uring_cqe *cqe;
/*
* If we can't get a cq entry, userspace overflowed the
* submission (by quite a lot). Increment the overflow count in
* the ring.
*/
if (unlikely(!io_get_cqe(ctx, &cqe)))
return false;
if (trace_io_uring_complete_enabled())
trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
req->cqe.res, req->cqe.flags,
req->big_cqe.extra1, req->big_cqe.extra2);
memcpy(cqe, &req->cqe, sizeof(*cqe));
if (ctx->flags & IORING_SETUP_CQE32) {
memcpy(cqe->big_cqe, &req->big_cqe, sizeof(*cqe));
memset(&req->big_cqe, 0, sizeof(req->big_cqe));
}
return true;
}
static inline void req_set_fail(struct io_kiocb *req)
{
req->flags |= REQ_F_FAIL;
if (req->flags & REQ_F_CQE_SKIP) {
req->flags &= ~REQ_F_CQE_SKIP;
req->flags |= REQ_F_SKIP_LINK_CQES;
}
}
static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
{
req->cqe.res = res;
req->cqe.flags = cflags;
}
static inline bool req_has_async_data(struct io_kiocb *req)
{
return req->flags & REQ_F_ASYNC_DATA;
}
static inline void io_put_file(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_FIXED_FILE) && req->file)
fput(req->file);
}
static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx,
unsigned issue_flags)
{
lockdep_assert_held(&ctx->uring_lock);
if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
mutex_unlock(&ctx->uring_lock);
}
static inline void io_ring_submit_lock(struct io_ring_ctx *ctx,
unsigned issue_flags)
{
/*
* "Normal" inline submissions always hold the uring_lock, since we
* grab it from the system call. Same is true for the SQPOLL offload.
* The only exception is when we've detached the request and issue it
* from an async worker thread, grab the lock for that case.
*/
if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
mutex_lock(&ctx->uring_lock);
lockdep_assert_held(&ctx->uring_lock);
}
static inline void io_commit_cqring(struct io_ring_ctx *ctx)
{
/* order cqe stores with ring update */
smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
}
static inline void io_poll_wq_wake(struct io_ring_ctx *ctx)
{
if (wq_has_sleeper(&ctx->poll_wq))
__wake_up(&ctx->poll_wq, TASK_NORMAL, 0,
poll_to_key(EPOLL_URING_WAKE | EPOLLIN));
}
static inline void io_cqring_wake(struct io_ring_ctx *ctx)
{
/*
* Trigger waitqueue handler on all waiters on our waitqueue. This
* won't necessarily wake up all the tasks, io_should_wake() will make
* that decision.
*
* Pass in EPOLLIN|EPOLL_URING_WAKE as the poll wakeup key. The latter
* set in the mask so that if we recurse back into our own poll
* waitqueue handlers, we know we have a dependency between eventfd or
* epoll and should terminate multishot poll at that point.
*/
if (wq_has_sleeper(&ctx->cq_wait))
__wake_up(&ctx->cq_wait, TASK_NORMAL, 0,
poll_to_key(EPOLL_URING_WAKE | EPOLLIN));
}
static inline bool io_sqring_full(struct io_ring_ctx *ctx)
{
struct io_rings *r = ctx->rings;
/*
* SQPOLL must use the actual sqring head, as using the cached_sq_head
* is race prone if the SQPOLL thread has grabbed entries but not yet
* committed them to the ring. For !SQPOLL, this doesn't matter, but
* since this helper is just used for SQPOLL sqring waits (or POLLOUT),
* just read the actual sqring head unconditionally.
*/
return READ_ONCE(r->sq.tail) - READ_ONCE(r->sq.head) == ctx->sq_entries;
}
static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
unsigned int entries;
/* make sure SQ entry isn't read before tail */
entries = smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
return min(entries, ctx->sq_entries);
}
static inline int io_run_task_work(void)
{
bool ret = false;
/*
* Always check-and-clear the task_work notification signal. With how
* signaling works for task_work, we can find it set with nothing to
* run. We need to clear it for that case, like get_signal() does.
*/
if (test_thread_flag(TIF_NOTIFY_SIGNAL))
clear_notify_signal();
/*
* PF_IO_WORKER never returns to userspace, so check here if we have
* notify work that needs processing.
*/
if (current->flags & PF_IO_WORKER) {
if (test_thread_flag(TIF_NOTIFY_RESUME)) {
__set_current_state(TASK_RUNNING);
resume_user_mode_work(NULL);
}
if (current->io_uring) {
unsigned int count = 0;
__set_current_state(TASK_RUNNING);
tctx_task_work_run(current->io_uring, UINT_MAX, &count);
if (count)
ret = true;
}
}
if (task_work_pending(current)) {
__set_current_state(TASK_RUNNING);
task_work_run();
ret = true;
}
return ret;
}
static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
{
return task_work_pending(current) || !llist_empty(&ctx->work_llist);
}
static inline void io_tw_lock(struct io_ring_ctx *ctx, struct io_tw_state *ts)
{
lockdep_assert_held(&ctx->uring_lock);
}
/*
* Don't complete immediately but use deferred completion infrastructure.
* Protected by ->uring_lock and can only be used either with
* IO_URING_F_COMPLETE_DEFER or inside a tw handler holding the mutex.
*/
static inline void io_req_complete_defer(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
struct io_submit_state *state = &req->ctx->submit_state;
lockdep_assert_held(&req->ctx->uring_lock);
wq_list_add_tail(&req->comp_list, &state->compl_reqs);
}
static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
if (unlikely(ctx->off_timeout_used || ctx->drain_active ||
ctx->has_evfd || ctx->poll_activated))
__io_commit_cqring_flush(ctx);
}
static inline void io_get_task_refs(int nr)
{
struct io_uring_task *tctx = current->io_uring;
tctx->cached_refs -= nr;
if (unlikely(tctx->cached_refs < 0))
io_task_refs_refill(tctx);
}
static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
{
return !ctx->submit_state.free_list.next;
}
extern struct kmem_cache *req_cachep;
extern struct kmem_cache *io_buf_cachep;
static inline struct io_kiocb *io_extract_req(struct io_ring_ctx *ctx)
{
struct io_kiocb *req;
req = container_of(ctx->submit_state.free_list.next, struct io_kiocb, comp_list);
wq_stack_extract(&ctx->submit_state.free_list);
return req;
}
static inline bool io_alloc_req(struct io_ring_ctx *ctx, struct io_kiocb **req)
{
if (unlikely(io_req_cache_empty(ctx))) {
if (!__io_alloc_req_refill(ctx))
return false;
}
*req = io_extract_req(ctx);
return true;
}
static inline bool io_allowed_defer_tw_run(struct io_ring_ctx *ctx)
{
return likely(ctx->submitter_task == current);
}
static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx)
{
return likely(!(ctx->flags & IORING_SETUP_DEFER_TASKRUN) ||
ctx->submitter_task == current);
}
static inline void io_req_queue_tw_complete(struct io_kiocb *req, s32 res)
{
io_req_set_res(req, res, 0);
req->io_task_work.func = io_req_task_complete;
io_req_task_work_add(req);
}
/*
* IORING_SETUP_SQE128 contexts allocate twice the normal SQE size for each
* slot.
*/
static inline size_t uring_sqe_size(struct io_ring_ctx *ctx)
{
if (ctx->flags & IORING_SETUP_SQE128)
return 2 * sizeof(struct io_uring_sqe);
return sizeof(struct io_uring_sqe);
}
static inline bool io_file_can_poll(struct io_kiocb *req)
{
if (req->flags & REQ_F_CAN_POLL)
return true;
if (req->file && file_can_poll(req->file)) {
req->flags |= REQ_F_CAN_POLL;
return true;
}
return false;
}
static inline ktime_t io_get_time(struct io_ring_ctx *ctx)
{
if (ctx->clockid == CLOCK_MONOTONIC)
return ktime_get();
return ktime_get_with_offset(ctx->clock_offset);
}
enum {
IO_CHECK_CQ_OVERFLOW_BIT,
IO_CHECK_CQ_DROPPED_BIT,
};
static inline bool io_has_work(struct io_ring_ctx *ctx)
{
return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
!llist_empty(&ctx->work_llist);
}
#endif