io_uring: add napi busy polling support

index 3d43df8f1e4e..efbd6c9c56e5 100644
@@ -2516,33 +2516,12 @@ int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	return ret;
 }
 
-struct io_wait_queue {
-	struct wait_queue_entry wq;
-	struct io_ring_ctx *ctx;
-	unsigned cq_tail;
-	unsigned nr_timeouts;
-	ktime_t timeout;
-};
-
 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);
 }
 
-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;
-}
-
 static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
 			    int wake_flags, void *key)
 {

index 25515d69d205..5f04bd47562a 100644
@@ -41,6 +41,28 @@ enum {
 	IOU_STOP_MULTISHOT	= -ECANCELED,
 };
 
+struct io_wait_queue {
+	struct wait_queue_entry wq;
+	struct io_ring_ctx *ctx;
+	unsigned cq_tail;
+	unsigned nr_timeouts;
+	ktime_t timeout;
+
+};
+
+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;
+}
+
 struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow);
 bool io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);

index 0716cb17e436..278c1a9de78c 100644
@@ -523,6 +523,10 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
+	/* set/clear busy poll settings */
+	IORING_REGISTER_NAPI			= 26,
+	IORING_UNREGISTER_NAPI			= 27,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 

@@ -649,6 +653,13 @@ struct io_uring_buf_reg {
 	__u64	resv[3];
 };
 
+/* argument for IORING_(UN)REGISTER_NAPI */
+struct io_uring_napi {
+	__u32	busy_poll_to;
+	__u32	pad;
+	__u64	resv;
+};
+
 /*
  * io_uring_restriction->opcode values
  */

index f06175b36b41..66e4591fbe2b 100644
@@ -4405,6 +4405,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_file_alloc_range(ctx, arg);
 		break;
+	case IORING_REGISTER_NAPI:
+		ret = -EINVAL;
+		if (!arg)
+			break;
+		ret = io_register_napi(ctx, arg);
+		break;
+	case IORING_UNREGISTER_NAPI:
+		ret = io_unregister_napi(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

54 lines not on this page · raw message

index 0484dfd9a396..b5e93b3777c0 100644
@@ -12,6 +12,9 @@
 void io_napi_init(struct io_ring_ctx *ctx);
 void io_napi_free(struct io_ring_ctx *ctx);
 
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg);
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg);
+
 void __io_napi_add(struct io_ring_ctx *ctx, struct file *file);
 
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,

@@ -67,6 +70,16 @@ static inline void io_napi_free(struct io_ring_ctx *ctx)
 {
 }
 
+static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline bool io_napi(struct io_ring_ctx *ctx)
 {
 	return false;

index a085122cae8b..6933375e3737 100644
@@ -237,4 +237,27 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
 	}
 }
 
+/*
+ * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
+ * @ctx: pointer to io-uring context structure
+ *
+ * Splice of the napi list and execute the napi busy poll loop.
+ */
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	LIST_HEAD(napi_list);
+	int ret = 0;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return 0;
+
+	spin_lock(&ctx->napi_lock);
+	list_splice_init(&ctx->napi_list, &napi_list);
+	spin_unlock(&ctx->napi_lock);
+
+	__io_napi_do_busy_loop(&napi_list, ctx->napi_prefer_busy_poll);
+	io_napi_merge_lists(ctx, &napi_list);
+	return ret;
+}
+
 #endif

index 1bdf8442081f..0484dfd9a396 100644
@@ -17,6 +17,7 @@ void __io_napi_add(struct io_ring_ctx *ctx, struct file *file);
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
 		struct io_wait_queue *iowq, struct timespec64 *ts);
 void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq);
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx);
 
 static inline bool io_napi(struct io_ring_ctx *ctx)
 {

@@ -77,6 +78,7 @@ static inline void io_napi_add(struct io_kiocb *req)
 
 #define io_napi_adjust_timeout(ctx, iowq, ts) do {} while (0)
 #define io_napi_busy_loop(ctx, iowq) do {} while (0)
+#define io_napi_sqpoll_busy_poll(ctx) (0)
 
 #endif
 

index 9db4bc1f521a..0c8d53ef134a 100644
@@ -15,6 +15,7 @@
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "napi.h"
 #include "sqpoll.h"
 
 #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8

@@ -193,6 +194,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 
+		if (io_napi(ctx))
+			ret += io_napi_sqpoll_busy_poll(ctx);
+
 		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
 			wake_up(&ctx->sqo_sq_wait);
 		if (creds)

index 278c1a9de78c..16d17d6ab7f7 100644
@@ -656,7 +656,8 @@ struct io_uring_buf_reg {
 /* argument for IORING_(UN)REGISTER_NAPI */
 struct io_uring_napi {
 	__u32	busy_poll_to;
-	__u32	pad;
+	__u8	prefer_busy_poll;
+	__u8	pad[3];
 	__u64	resv;
 };
 

index 2d4817d1413a..5851e7eff1e8 100644
@@ -191,16 +191,18 @@ void io_napi_free(struct io_ring_ctx *ctx)
 int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 {
 	const struct io_uring_napi curr = {
-		.busy_poll_to = ctx->napi_busy_poll_to,
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
 	};
 	struct io_uring_napi napi;
 
 	if (copy_from_user(&napi, arg, sizeof(napi)))
 		return -EFAULT;
-	if (napi.pad || napi.resv)
+	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
 		return -EINVAL;
 
 	WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
 
 	if (copy_to_user(arg, &curr, sizeof(curr)))
 		return -EFAULT;

@@ -219,13 +221,15 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
 int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
 {
 	const struct io_uring_napi curr = {
-		.busy_poll_to = ctx->napi_busy_poll_to,
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
 	};
 
 	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
 		return -EFAULT;
 
 	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
 	return 0;
 }
 

index 1b2a20a42413..9def1de4eaf4 100644
@@ -2,6 +2,7 @@
 #define IO_URING_TYPES_H
 
 #include <linux/blkdev.h>
+#include <linux/hashtable.h>
 #include <linux/task_work.h>
 #include <linux/bitmap.h>
 #include <linux/llist.h>

@@ -277,6 +278,16 @@ struct io_ring_ctx {
 	struct xarray		personalities;
 	u32			pers_next;
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct list_head	napi_list;	/* track busy poll napi_id */
+	spinlock_t		napi_lock;	/* napi_list lock */
+
+	DECLARE_HASHTABLE(napi_ht, 4);
+	/* napi busy poll default timeout */
+	unsigned int		napi_busy_poll_to;
+	bool			napi_prefer_busy_poll;
+#endif
+
 	struct {
 		/*
 		 * We cache a range of free CQEs we can use, once exhausted it

index efbd6c9c56e5..f06175b36b41 100644
@@ -91,6 +91,7 @@
 #include "rsrc.h"
 #include "cancel.h"
 #include "net.h"
+#include "napi.h"
 #include "notif.h"
 
 #include "timeout.h"

@@ -337,6 +338,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_WQ_LIST(&ctx->locked_free_list);
 	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
 	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
+	io_napi_init(ctx);
+
 	return ctx;
 err:
 	kfree(ctx->dummy_ubuf);

@@ -2619,9 +2622,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
+
 		iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+		io_napi_adjust_timeout(ctx, &iowq, &ts);
 	}
 
+	io_napi_busy_loop(ctx, &iowq);
+
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
 		unsigned long check_cq;

@@ -2856,6 +2863,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_req_caches_free(ctx);
 	if (ctx->hash_map)
 		io_wq_put_hash(ctx->hash_map);
+	io_napi_free(ctx);
 	kfree(ctx->cancel_table.hbs);
 	kfree(ctx->cancel_table_locked.hbs);
 	kfree(ctx->dummy_ubuf);

index 5f04bd47562a..d669e06f54f0 100644
@@ -48,6 +48,10 @@ struct io_wait_queue {
 	unsigned nr_timeouts;
 	ktime_t timeout;
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_busy_poll_to;
+	bool napi_prefer_busy_poll;
+#endif
 };
 
 static inline bool io_should_wake(struct io_wait_queue *iowq)

240 lines not on this page · raw message

83 lines not on this page · raw message

index c90e47dc1e29..0284849793bb 100644
@@ -15,6 +15,7 @@
 
 #include "io_uring.h"
 #include "refs.h"
+#include "napi.h"
 #include "opdef.h"
 #include "kbuf.h"
 #include "poll.h"

@@ -631,6 +632,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 		__io_poll_execute(req, mask);
 		return 0;
 	}
+	io_napi_add(req);
 
 	if (ipt->owning) {
 		/*