@@ -370,6 +370,10 @@ struct io_ring_ctx {
struct io_alloc_cache futex_cache;
#endif
+#ifdef CONFIG_EPOLL
+ struct hlist_head epoll_list;
+#endif
+
const struct cred *sq_creds; /* cred used for __io_sq_thread() */
struct io_sq_data *sq_data; /* if using sq thread polling */
@@ -278,6 +278,7 @@ enum io_uring_op {
IORING_OP_FTRUNCATE,
IORING_OP_BIND,
IORING_OP_LISTEN,
+ IORING_OP_EPOLL_WAIT,
/* this goes last, obviously */
IORING_OP_LAST,
@@ -17,6 +17,7 @@
#include "timeout.h"
#include "waitid.h"
#include "futex.h"
+#include "epoll.h"
#include "cancel.h"
struct io_cancel {
@@ -128,6 +129,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,
if (ret != -ENOENT)
return ret;
+ ret = io_epoll_wait_cancel(ctx, cd, issue_flags);
+ if (ret != -ENOENT)
+ return ret;
+
spin_lock(&ctx->completion_lock);
if (!(cd->flags & IORING_ASYNC_CANCEL_FD))
ret = io_timeout_cancel(ctx, cd);
@@ -11,6 +11,7 @@
#include "io_uring.h"
#include "epoll.h"
+#include "poll.h"
struct io_epoll {
struct file *file;
@@ -20,6 +21,13 @@ struct io_epoll {
struct epoll_event event;
};
+struct io_epoll_wait {
+ struct file *file;
+ int maxevents;
+ struct epoll_event __user *events;
+ struct wait_queue_entry wait;
+};
+
int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll);
@@ -57,3 +65,163 @@ int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
io_req_set_res(req, ret, 0);
return IOU_OK;
}
+
+static void __io_epoll_cancel(struct io_kiocb *req)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+ epoll_wait_remove(req->file, &iew->wait);
+ hlist_del_init(&req->hash_node);
+ io_req_set_res(req, -ECANCELED, 0);
+ req->io_task_work.func = io_req_task_complete;
+ io_req_task_work_add(req);
+}
+
+static void __io_epoll_wait_cancel(struct io_kiocb *req)
+{
+ io_poll_mark_cancelled(req);
+ if (io_poll_get_ownership(req)) {
+ __io_epoll_cancel(req);
+ io_req_set_res(req, -ECANCELED, 0);
+ req->io_task_work.func = io_req_task_complete;
+ io_req_task_work_add(req);
+ }
+}
+
+bool io_epoll_wait_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+ bool cancel_all)
+{
+ struct hlist_node *tmp;
+ struct io_kiocb *req;
+ bool found = false;
+
+ lockdep_assert_held(&ctx->uring_lock);
+
+ hlist_for_each_entry_safe(req, tmp, &ctx->epoll_list, hash_node) {
+ if (!io_match_task_safe(req, tctx, cancel_all))
+ continue;
+ __io_epoll_wait_cancel(req);
+ found = true;
+ }
+
+ return found;
+}
+
+int io_epoll_wait_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+ unsigned int issue_flags)
+{
+ struct hlist_node *tmp;
+ struct io_kiocb *req;
+ int nr = 0;
+
+ io_ring_submit_lock(ctx, issue_flags);
+ hlist_for_each_entry_safe(req, tmp, &ctx->epoll_list, hash_node) {
+ if (!io_cancel_req_match(req, cd))
+ continue;
+ __io_epoll_wait_cancel(req);
+ nr++;
+ }
+ io_ring_submit_unlock(ctx, issue_flags);
+ return nr ?: -ENOENT;
+}
+
+static void io_epoll_retry(struct io_kiocb *req, struct io_tw_state *ts)
+{
+ int v;
+
+ do {
+ v = atomic_read(&req->poll_refs);
+ if (unlikely(v != 1)) {
+ if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK)))
+ return;
+ if (v & IO_POLL_CANCEL_FLAG) {
+ __io_epoll_cancel(req);
+ return;
+ }
+ }
+ v &= IO_POLL_REF_MASK;
+ } while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
+
+ io_req_task_submit(req, ts);
+}
+
+static int io_epoll_execute(struct io_kiocb *req)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+ if (io_poll_get_ownership(req)) {
+ list_del_init_careful(&iew->wait.entry);
+ req->io_task_work.func = io_epoll_retry;
+ io_req_task_work_add(req);
+ return 1;
+ }
+
+ return 0;
+}
+
+static __cold int io_epoll_pollfree_wake(struct io_kiocb *req)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+ io_poll_mark_cancelled(req);
+ list_del_init_careful(&iew->wait.entry);
+ io_epoll_execute(req);
+ return 1;
+}
+
+static int io_epoll_wait_fn(struct wait_queue_entry *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct io_kiocb *req = wait->private;
+ __poll_t mask = key_to_poll(key);
+
+ if (unlikely(mask & POLLFREE))
+ return io_epoll_pollfree_wake(req);
+
+ return io_epoll_execute(req);
+}
+
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+ if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+ return -EINVAL;
+
+ iew->maxevents = READ_ONCE(sqe->len);
+ iew->events = u64_to_user_ptr(READ_ONCE(sqe->addr));
+
+ iew->wait.flags = 0;
+ iew->wait.private = req;
+ iew->wait.func = io_epoll_wait_fn;
+ INIT_LIST_HEAD(&iew->wait.entry);
+ atomic_set(&req->poll_refs, 0);
+ return 0;
+}
+
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+ struct io_ring_ctx *ctx = req->ctx;
+ int ret;
+
+ io_ring_submit_lock(ctx, issue_flags);
+ hlist_add_head(&req->hash_node, &ctx->epoll_list);
+ io_ring_submit_unlock(ctx, issue_flags);
+
+ /*
+ * Timeout is fake here, it doesn't indicate any kind of sleep time.
+ * It's just set to something that is non-zero, so that wait queue
+ * wakeup is armed if no events are available.
+ */
+ ret = epoll_wait(req->file, iew->events, iew->maxevents, NULL, &iew->wait);
+ if (ret == -EIOCBQUEUED)
+ return IOU_ISSUE_SKIP_COMPLETE;
+ else if (ret < 0)
+ req_set_fail(req);
+ io_ring_submit_lock(ctx, issue_flags);
+ hlist_del_init(&req->hash_node);
+ io_ring_submit_unlock(ctx, issue_flags);
+ io_req_set_res(req, ret, 0);
+ return IOU_OK;
+}
@@ -1,6 +1,28 @@
// SPDX-License-Identifier: GPL-2.0
+#include "cancel.h"
+
#if defined(CONFIG_EPOLL)
+int io_epoll_wait_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+ unsigned int issue_flags);
+bool io_epoll_wait_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+ bool cancel_all);
+
int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags);
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags);
+#else
+static inline bool io_epoll_wait_remove_all(struct io_ring_ctx *ctx,
+ struct io_uring_task *tctx,
+ bool cancel_all)
+{
+ return false;
+}
+static inline int io_epoll_wait_cancel(struct io_ring_ctx *ctx,
+ struct io_cancel_data *cd,
+ unsigned int issue_flags)
+{
+ return 0;
+}
#endif
@@ -93,6 +93,7 @@
#include "notif.h"
#include "waitid.h"
#include "futex.h"
+#include "epoll.h"
#include "napi.h"
#include "uring_cmd.h"
#include "msg_ring.h"
@@ -358,6 +359,9 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_HLIST_HEAD(&ctx->waitid_list);
#ifdef CONFIG_FUTEX
INIT_HLIST_HEAD(&ctx->futex_list);
+#endif
+#ifdef CONFIG_EPOLL
+ INIT_HLIST_HEAD(&ctx->epoll_list);
#endif
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
@@ -3095,6 +3099,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
ret |= io_poll_remove_all(ctx, tctx, cancel_all);
ret |= io_waitid_remove_all(ctx, tctx, cancel_all);
ret |= io_futex_remove_all(ctx, tctx, cancel_all);
+ ret |= io_epoll_wait_remove_all(ctx, tctx, cancel_all);
ret |= io_uring_try_cancel_uring_cmd(ctx, tctx, cancel_all);
mutex_unlock(&ctx->uring_lock);
ret |= io_kill_timeouts(ctx, tctx, cancel_all);
@@ -514,6 +514,17 @@ const struct io_issue_def io_issue_defs[] = {
.async_size = sizeof(struct io_async_msghdr),
#else
.prep = io_eopnotsupp_prep,
+#endif
+ },
+ [IORING_OP_EPOLL_WAIT] = {
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ .audit_skip = 1,
+#if defined(CONFIG_EPOLL)
+ .prep = io_epoll_wait_prep,
+ .issue = io_epoll_wait,
+#else
+ .prep = io_eopnotsupp_prep,
#endif
},
};
@@ -745,6 +756,9 @@ const struct io_cold_def io_cold_defs[] = {
[IORING_OP_LISTEN] = {
.name = "LISTEN",
},
+ [IORING_OP_EPOLL_WAIT] = {
+ .name = "EPOLL_WAIT",
+ },
};
const char *io_uring_get_opcode(u8 opcode)
For existing epoll event loops that can't fully convert to io_uring, the used approach is usually to add the io_uring fd to the epoll instance and use epoll_wait() to wait on both "legacy" and io_uring events. While this work, it isn't optimal as: 1) epoll_wait() is pretty limited in what it can do. It does not support partial reaping of events, or waiting on a batch of events. 2) When an io_uring ring is added to an epoll instance, it activates the io_uring "I'm being polled" logic which slows things down. Rather than use this approach, with EPOLL_WAIT support added to io_uring, event loops can use the normal io_uring wait logic for everything, as long as an epoll wait request has been armed with io_uring. Note that IORING_OP_EPOLL_WAIT does NOT take a timeout value, as this is an async request. Waiting on io_uring events in general has various timeout parameters, and those are the ones that should be used when waiting on any kind of request. If events are immediately available for reaping, then This opcode will return those immediately. If none are available, then it will post an async completion when they become available. cqe->res will contain either an error code (< 0 value) for a malformed request, invalid epoll instance, etc. It will return a positive result indicating how many events were reaped. IORING_OP_EPOLL_WAIT requests may be canceled using the normal io_uring cancelation infrastructure. The poll logic for managing ownership is adopted to guard the epoll side too. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- include/linux/io_uring_types.h | 4 + include/uapi/linux/io_uring.h | 1 + io_uring/cancel.c | 5 + io_uring/epoll.c | 168 +++++++++++++++++++++++++++++++++ io_uring/epoll.h | 22 +++++ io_uring/io_uring.c | 5 + io_uring/opdef.c | 14 +++ 7 files changed, 219 insertions(+)