return ctx;
}
+static inline bool __io_sequence_defer(struct io_ring_ctx *ctx,
+ struct io_kiocb *req)
+{
+ return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+}
+
static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
struct io_kiocb *req)
{
- /* timeout requests always honor sequence */
- if (!(req->flags & REQ_F_TIMEOUT) &&
- (req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
+ if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
return false;
- return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+ return __io_sequence_defer(ctx, req);
}
-static struct io_kiocb *__io_get_deferred_req(struct io_ring_ctx *ctx,
- struct list_head *list)
+static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
{
struct io_kiocb *req;
- if (list_empty(list))
- return NULL;
-
- req = list_first_entry(list, struct io_kiocb, list);
- if (!io_sequence_defer(ctx, req)) {
+ req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list);
+ if (req && !io_sequence_defer(ctx, req)) {
list_del_init(&req->list);
return req;
}
return NULL;
}
-static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
-{
- return __io_get_deferred_req(ctx, &ctx->defer_list);
-}
-
static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx)
{
- return __io_get_deferred_req(ctx, &ctx->timeout_list);
+ struct io_kiocb *req;
+
+ req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list);
+ if (req && !__io_sequence_defer(ctx, req)) {
+ list_del_init(&req->list);
+ return req;
+ }
+
+ return NULL;
}
static void __io_commit_cqring(struct io_ring_ctx *ctx)
return submit;
}
+struct io_wait_queue {
+ struct wait_queue_entry wq;
+ struct io_ring_ctx *ctx;
+ unsigned to_wait;
+ unsigned nr_timeouts;
+};
+
+static inline bool io_should_wake(struct io_wait_queue *iowq)
+{
+ struct io_ring_ctx *ctx = iowq->ctx;
+
+ /*
+ * Wake up if we have enough events, or if a timeout occured since we
+ * started waiting. For timeouts, we always want to return to userspace,
+ * regardless of event count.
+ */
+ return io_cqring_events(ctx->rings) >= iowq->to_wait ||
+ atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
+}
+
+static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
+ int wake_flags, void *key)
+{
+ struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
+ wq);
+
+ if (!io_should_wake(iowq))
+ return -1;
+
+ return autoremove_wake_function(curr, mode, wake_flags, key);
+}
+
/*
* Wait until events become available, if we don't already have some. The
* application must reap them itself, as they reside on the shared cq ring.
static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
const sigset_t __user *sig, size_t sigsz)
{
+ struct io_wait_queue iowq = {
+ .wq = {
+ .private = current,
+ .func = io_wake_function,
+ .entry = LIST_HEAD_INIT(iowq.wq.entry),
+ },
+ .ctx = ctx,
+ .to_wait = min_events,
+ };
struct io_rings *rings = ctx->rings;
- unsigned nr_timeouts;
int ret;
if (io_cqring_events(rings) >= min_events)
return ret;
}
- nr_timeouts = atomic_read(&ctx->cq_timeouts);
- /*
- * Return if we have enough events, or if a timeout occured since
- * we started waiting. For timeouts, we always want to return to
- * userspace.
- */
- ret = wait_event_interruptible(ctx->wait,
- io_cqring_events(rings) >= min_events ||
- atomic_read(&ctx->cq_timeouts) != nr_timeouts);
+ ret = 0;
+ iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
+ do {
+ prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
+ TASK_INTERRUPTIBLE);
+ if (io_should_wake(&iowq))
+ break;
+ schedule();
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+ } while (1);
+ finish_wait(&ctx->wait, &iowq.wq);
+
restore_saved_sigmask_unless(ret == -ERESTARTSYS);
if (ret == -ERESTARTSYS)
ret = -EINTR;
static void io_destruct_skb(struct sk_buff *skb)
{
struct io_ring_ctx *ctx = skb->sk->sk_user_data;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++)
+ if (ctx->sqo_wq[i])
+ flush_workqueue(ctx->sqo_wq[i]);
- io_finish_async(ctx);
unix_destruct_scm(skb);
}
if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head !=
ctx->rings->sq_ring_entries)
mask |= EPOLLOUT | EPOLLWRNORM;
- if (READ_ONCE(ctx->rings->sq.head) != ctx->cached_cq_tail)
+ if (READ_ONCE(ctx->rings->cq.head) != ctx->cached_cq_tail)
mask |= EPOLLIN | EPOLLRDNORM;
return mask;