diff mbox series

[07/18] io_uring: support for IO polling

Message ID 20190123153536.7081-9-axboe@kernel.dk (mailing list archive)
State New, archived
Headers show
Series None | expand

Commit Message

Jens Axboe Jan. 23, 2019, 3:35 p.m. UTC
Add support for a polled io_uring context. When a read or write is
submitted to a polled context, the application must poll for completions
on the CQ ring through io_uring_enter(2). Polled IO may not generate
IRQ completions, hence they need to be actively found by the application
itself.

To use polling, io_uring_setup() must be used with the
IORING_SETUP_IOPOLL flag being set. It is illegal to mix and match
polled and non-polled IO on an io_uring.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 263 ++++++++++++++++++++++++++++++++--
 include/uapi/linux/io_uring.h |   5 +
 2 files changed, 257 insertions(+), 11 deletions(-)

Comments

Christoph Hellwig Jan. 28, 2019, 3:02 p.m. UTC | #1
>  	struct {
>  		spinlock_t		completion_lock;
> +		unsigned		poll_multi_file;

This seems to be used as a bool.

>  
> -static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
> -				  long res, unsigned ev_flags)
> +static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
> +				 long res, unsigned ev_flags)
>  {
>  	struct io_uring_cqe *cqe;
>  
> @@ -206,9 +213,15 @@ static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>  		cqe->user_data = ki_user_data;
>  		cqe->res = res;
>  		cqe->flags = ev_flags;
> -		io_commit_cqring(ctx);
>  	} else
>  		ctx->cq_ring->overflow++;
> +}

Maybe we should have created this low-level helper already in the
patch introducing the code?
Jens Axboe Jan. 28, 2019, 4:46 p.m. UTC | #2
On 1/28/19 8:02 AM, Christoph Hellwig wrote:
>>  	struct {
>>  		spinlock_t		completion_lock;
>> +		unsigned		poll_multi_file;
> 
> This seems to be used as a bool.

Fixed

>> -static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>> -				  long res, unsigned ev_flags)
>> +static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>> +				 long res, unsigned ev_flags)
>>  {
>>  	struct io_uring_cqe *cqe;
>>  
>> @@ -206,9 +213,15 @@ static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>>  		cqe->user_data = ki_user_data;
>>  		cqe->res = res;
>>  		cqe->flags = ev_flags;
>> -		io_commit_cqring(ctx);
>>  	} else
>>  		ctx->cq_ring->overflow++;
>> +}
> 
> Maybe we should have created this low-level helper already in the
> patch introducing the code?

I think that can go both ways. If we create it early, it'll just be a
pointless helper. Don't really care too much about this particular case.
Christoph Hellwig Jan. 29, 2019, 6:27 a.m. UTC | #3
On Mon, Jan 28, 2019 at 09:46:17AM -0700, Jens Axboe wrote:
> I think that can go both ways. If we create it early, it'll just be a
> pointless helper. Don't really care too much about this particular case.

Without the no-op locking fix we don't really need the current
__io_cqring_add_event anymore, so we'd still have two somewhat
reasonably defined helpers.
Jens Axboe Jan. 29, 2019, 1:20 p.m. UTC | #4
On 1/28/19 11:27 PM, Christoph Hellwig wrote:
> On Mon, Jan 28, 2019 at 09:46:17AM -0700, Jens Axboe wrote:
>> I think that can go both ways. If we create it early, it'll just be a
>> pointless helper. Don't really care too much about this particular case.
> 
> Without the no-op locking fix we don't really need the current
> __io_cqring_add_event anymore, so we'd still have two somewhat
> reasonably defined helpers.

Yeah, killed it, which also fixes your complaint about adding a new
helper in the poll patch.
diff mbox series

Patch

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 35d25b49ad94..f17c2dc73e40 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -101,6 +101,8 @@  struct io_ring_ctx {
 
 	struct {
 		spinlock_t		completion_lock;
+		unsigned		poll_multi_file;
+		struct list_head	poll_list;
 	} ____cacheline_aligned_in_smp;
 };
 
@@ -119,12 +121,16 @@  struct io_kiocb {
 	struct list_head	list;
 	unsigned int		flags;
 #define REQ_F_FORCE_NONBLOCK	1	/* inline submission attempt */
+#define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
+#define REQ_F_IOPOLL_EAGAIN	4	/* submission got EAGAIN */
 	u64			user_data;
+	u64			res;
 
 	struct work_struct	work;
 };
 
 #define IO_PLUG_THRESHOLD		2
+#define IO_IOPOLL_BATCH			8
 
 static struct kmem_cache *req_cachep;
 
@@ -156,6 +162,7 @@  static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
 	spin_lock_init(&ctx->completion_lock);
+	INIT_LIST_HEAD(&ctx->poll_list);
 	return ctx;
 }
 
@@ -191,8 +198,8 @@  static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	return &ring->cqes[tail & ctx->cq_mask];
 }
 
-static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
-				  long res, unsigned ev_flags)
+static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+				 long res, unsigned ev_flags)
 {
 	struct io_uring_cqe *cqe;
 
@@ -206,9 +213,15 @@  static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
 		cqe->user_data = ki_user_data;
 		cqe->res = res;
 		cqe->flags = ev_flags;
-		io_commit_cqring(ctx);
 	} else
 		ctx->cq_ring->overflow++;
+}
+
+static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+				  long res, unsigned ev_flags)
+{
+	io_cqring_fill_event(ctx, ki_user_data, res, ev_flags);
+	io_commit_cqring(ctx);
 
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
@@ -250,12 +263,158 @@  static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
 	return NULL;
 }
 
+static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
+{
+	if (*nr) {
+		kmem_cache_free_bulk(req_cachep, *nr, reqs);
+		io_ring_drop_ctx_refs(ctx, *nr);
+		*nr = 0;
+	}
+}
+
 static void io_free_req(struct io_kiocb *req)
 {
 	io_ring_drop_ctx_refs(req->ctx, 1);
 	kmem_cache_free(req_cachep, req);
 }
 
+/*
+ * Find and free completed poll iocbs
+ */
+static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
+			       struct list_head *done)
+{
+	void *reqs[IO_IOPOLL_BATCH];
+	struct io_kiocb *req;
+	int to_free = 0;
+
+	while (!list_empty(done)) {
+		req = list_first_entry(done, struct io_kiocb, list);
+		list_del(&req->list);
+
+		io_cqring_fill_event(ctx, req->user_data, req->res, 0);
+
+		reqs[to_free++] = req;
+		(*nr_events)++;
+
+		fput(req->rw.ki_filp);
+		if (to_free == ARRAY_SIZE(reqs))
+			io_free_req_many(ctx, reqs, &to_free);
+	}
+	io_commit_cqring(ctx);
+
+	if (to_free)
+		io_free_req_many(ctx, reqs, &to_free);
+}
+
+static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
+			long min)
+{
+	struct io_kiocb *req, *tmp;
+	LIST_HEAD(done);
+	bool spin;
+	int ret;
+
+	/*
+	 * Only spin for completions if we don't have multiple devices hanging
+	 * off our complete list, and we're under the requested amount.
+	 */
+	spin = !ctx->poll_multi_file && (*nr_events < min);
+
+	ret = 0;
+	list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) {
+		struct kiocb *kiocb = &req->rw;
+
+		/*
+		 * Move completed entries to our local list. If we find a
+		 * request that requires polling, break out and complete
+		 * the done list first, if we have entries there.
+		 */
+		if (req->flags & REQ_F_IOPOLL_COMPLETED) {
+			list_move_tail(&req->list, &done);
+			continue;
+		}
+		if (!list_empty(&done))
+			break;
+
+		ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
+		if (ret < 0)
+			break;
+
+		if (ret && spin)
+			spin = false;
+		ret = 0;
+	}
+
+	if (!list_empty(&done))
+		io_iopoll_complete(ctx, nr_events, &done);
+
+	return ret;
+}
+
+/*
+ * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a
+ * non-spinning poll check - we'll still enter the driver poll loop, but only
+ * as a non-spinning completion check.
+ */
+static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
+				long min)
+{
+	int ret;
+
+	do {
+		if (list_empty(&ctx->poll_list))
+			return 0;
+
+		ret = io_do_iopoll(ctx, nr_events, min);
+		if (ret < 0)
+			break;
+	} while (min && *nr_events < min);
+
+	if (ret < 0)
+		return ret;
+
+	return *nr_events < min;
+}
+
+/*
+ * We can't just wait for polled events to come to us, we have to actively
+ * find and complete them.
+ */
+static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
+{
+	if (!(ctx->flags & IORING_SETUP_IOPOLL))
+		return;
+
+	mutex_lock(&ctx->uring_lock);
+	while (!list_empty(&ctx->poll_list)) {
+		unsigned int nr_events = 0;
+
+		io_iopoll_getevents(ctx, &nr_events, 1);
+	}
+	mutex_unlock(&ctx->uring_lock);
+}
+
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+			   long min)
+{
+	int ret = 0;
+
+	while (!*nr_events || !need_resched()) {
+		int tmin = 0;
+
+		if (*nr_events < min)
+			tmin = min - *nr_events;
+
+		ret = io_iopoll_getevents(ctx, nr_events, tmin);
+		if (ret <= 0)
+			break;
+		ret = 0;
+	}
+
+	return ret;
+}
+
 static void kiocb_end_write(struct kiocb *kiocb)
 {
 	if (kiocb->ki_flags & IOCB_WRITE) {
@@ -282,9 +441,60 @@  static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 	io_free_req(req);
 }
 
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
+{
+	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+	kiocb_end_write(kiocb);
+
+	if (unlikely(res == -EAGAIN)) {
+		req->flags |= REQ_F_IOPOLL_EAGAIN;
+	} else {
+		req->flags |= REQ_F_IOPOLL_COMPLETED;
+		req->res = res;
+	}
+}
+
+/*
+ * After the iocb has been issued, it's safe to be found on the poll list.
+ * Adding the kiocb to the list AFTER submission ensures that we don't
+ * find it from a io_iopoll_getevents() thread before the issuer is done
+ * accessing the kiocb cookie.
+ */
+static void io_iopoll_req_issued(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	/*
+	 * Track whether we have multiple files in our lists. This will impact
+	 * how we do polling eventually, not spinning if we're on potentially
+	 * different devices.
+	 */
+	if (list_empty(&ctx->poll_list)) {
+		ctx->poll_multi_file = 0;
+	} else if (!ctx->poll_multi_file) {
+		struct io_kiocb *list_req;
+
+		list_req = list_first_entry(&ctx->poll_list, struct io_kiocb,
+						list);
+		if (list_req->rw.ki_filp != req->rw.ki_filp)
+			ctx->poll_multi_file = 1;
+	}
+
+	/*
+	 * For fast devices, IO may have already completed. If it has, add
+	 * it to the front so we find it first.
+	 */
+	if (req->flags & REQ_F_IOPOLL_COMPLETED)
+		list_add(&req->list, &ctx->poll_list);
+	else
+		list_add_tail(&req->list, &ctx->poll_list);
+}
+
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		      bool force_nonblock)
 {
+	struct io_ring_ctx *ctx = req->ctx;
 	struct kiocb *kiocb = &req->rw;
 	int ret;
 
@@ -310,12 +520,21 @@  static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		kiocb->ki_flags |= IOCB_NOWAIT;
 		req->flags |= REQ_F_FORCE_NONBLOCK;
 	}
-	if (kiocb->ki_flags & IOCB_HIPRI) {
-		ret = -EINVAL;
-		goto out_fput;
-	}
+	if (ctx->flags & IORING_SETUP_IOPOLL) {
+		ret = -EOPNOTSUPP;
+		if (!(kiocb->ki_flags & IOCB_DIRECT) ||
+		    !kiocb->ki_filp->f_op->iopoll)
+			goto out_fput;
 
-	kiocb->ki_complete = io_complete_rw;
+		kiocb->ki_flags |= IOCB_HIPRI;
+		kiocb->ki_complete = io_complete_rw_iopoll;
+	} else {
+		if (kiocb->ki_flags & IOCB_HIPRI) {
+			ret = -EINVAL;
+			goto out_fput;
+		}
+		kiocb->ki_complete = io_complete_rw;
+	}
 	return 0;
 out_fput:
 	fput(kiocb->ki_filp);
@@ -462,6 +681,9 @@  static int io_nop(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
+	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
 	__io_cqring_add_event(ctx, sqe->user_data, 0, 0);
 	io_free_req(req);
 	return 0;
@@ -479,6 +701,8 @@  static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (force_nonblock)
 		return -EAGAIN;
 
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
 	if (unlikely(sqe->addr || sqe->ioprio))
 		return -EINVAL;
 	if (unlikely(sqe->fsync_flags & ~IORING_FSYNC_DATASYNC))
@@ -526,7 +750,16 @@  static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		break;
 	}
 
-	return ret;
+	if (ret)
+		return ret;
+
+	if (ctx->flags & IORING_SETUP_IOPOLL) {
+		if (req->flags & REQ_F_IOPOLL_EAGAIN)
+			return -EAGAIN;
+		io_iopoll_req_issued(req);
+	}
+
+	return 0;
 }
 
 static void io_sq_wq_submit_work(struct work_struct *work)
@@ -712,12 +945,18 @@  static int __io_uring_enter(struct io_ring_ctx *ctx, unsigned to_submit,
 			return ret;
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
+		unsigned nr_events = 0;
 		int get_ret;
 
 		if (!ret && to_submit)
 			min_complete = 0;
 
-		get_ret = io_cqring_wait(ctx, min_complete);
+		if (ctx->flags & IORING_SETUP_IOPOLL)
+			get_ret = io_iopoll_check(ctx, &nr_events,
+							min_complete);
+		else
+			get_ret = io_cqring_wait(ctx, min_complete);
+
 		if (get_ret < 0 && !ret)
 			ret = get_ret;
 	}
@@ -826,6 +1065,7 @@  static void io_free_scq_urings(struct io_ring_ctx *ctx)
 static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 {
 	io_sq_offload_stop(ctx);
+	io_iopoll_reap_events(ctx);
 	io_free_scq_urings(ctx);
 	percpu_ref_exit(&ctx->refs);
 	io_unaccount_mem(ctx, ring_pages(ctx->sq_entries, ctx->cq_entries));
@@ -860,6 +1100,7 @@  static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	percpu_ref_kill(&ctx->refs);
 	mutex_unlock(&ctx->uring_lock);
 
+	io_iopoll_reap_events(ctx);
 	wait_for_completion(&ctx->ctx_done);
 	io_ring_ctx_free(ctx);
 }
@@ -1090,7 +1331,7 @@  static long io_uring_setup(u32 entries, struct io_uring_params __user *params,
 			return -EINVAL;
 	}
 
-	if (p.flags)
+	if (p.flags & ~IORING_SETUP_IOPOLL)
 		return -EINVAL;
 
 	ret = io_uring_create(entries, &p, compat);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ca503ded73e3..4fc5fbd07688 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -32,6 +32,11 @@  struct io_uring_sqe {
 	__u64	__pad2[3];
 };
 
+/*
+ * io_uring_setup() flags
+ */
+#define IORING_SETUP_IOPOLL	(1 << 0)	/* io_context is polled */
+
 #define IORING_OP_NOP		0
 #define IORING_OP_READV		1
 #define IORING_OP_WRITEV	2