io_uring: add napi busy polling support

index 0e42160a3051..5d6aa783fb97 100644
@@ -2468,33 +2468,12 @@ 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 2711865f1e19..021f9af37c74 100644
@@ -27,6 +27,28 @@ 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 0efe4d784358..fe4033aacc4c 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>

@@ -276,6 +277,15 @@ 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);
+	unsigned int		napi_busy_poll_to; /* napi busy poll default timeout */
+	bool			napi_prefer_busy_poll;
+#endif
+
 	struct {
 		/*
 		 * We cache a range of free CQEs we can use, once exhausted it

index 5d6aa783fb97..556da2de369f 100644
@@ -90,6 +90,7 @@
 #include "rsrc.h"
 #include "cancel.h"
 #include "net.h"
+#include "napi.h"
 #include "notif.h"
 
 #include "timeout.h"

@@ -335,6 +336,8 @@ 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);

@@ -2566,15 +2569,31 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
 	iowq.timeout = KTIME_MAX;
 
-	if (uts) {
-		struct timespec64 ts;
+	if (!io_napi(ctx)) {
+		if (uts) {
+			struct timespec64 ts;
 
-		if (get_timespec64(&ts, uts))
-			return -EFAULT;
-		iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+			if (get_timespec64(&ts, uts))
+				return -EFAULT;
+			iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+		}
+	} else {
+		if (uts) {
+			struct timespec64 ts;
+
+			if (get_timespec64(&ts, uts))
+				return -EFAULT;
+
+			io_napi_adjust_timeout(ctx, &iowq, &ts);
+			iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+		} else {
+			io_napi_adjust_timeout(ctx, &iowq, NULL);
+		}
+		io_napi_busy_loop(ctx, &iowq);
 	}
 
 	trace_io_uring_cqring_wait(ctx, min_events);
+
 	do {
 		unsigned long check_cq;
 

@@ -2806,6 +2825,7 @@ 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 021f9af37c74..2e1b8de8505a 100644
@@ -34,6 +34,10 @@ 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)

243 lines not on this page · raw message

66 lines not on this page · raw message

index 8339a92b4510..ab08299eb341 100644
@@ -15,6 +15,7 @@
 
 #include "io_uring.h"
 #include "refs.h"
+#include "napi.h"
 #include "opdef.h"
 #include "kbuf.h"
 #include "poll.h"

@@ -629,6 +630,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 		__io_poll_execute(req, mask);
 		return 0;
 	}
+	io_napi_add(req);
 
 	if (ipt->owning) {
 		/*

index bb7d2b6b7e90..0fbdfe5eea06 100644
@@ -240,4 +240,29 @@ 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)
+{
+	int ret = 0;
+	LIST_HEAD(napi_list);
+
+	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);
+
+	if (__io_napi_busy_loop(&napi_list, ctx->napi_prefer_busy_poll))
+		ret = 1;
+
+	io_napi_merge_lists(ctx, &napi_list);
+	return ret;
+}
+
 #endif

index 49322a16b6e5..b3455e52170c 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)
 {

@@ -60,6 +61,7 @@ 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 0119d3f1a556..b8b8cf3b6b02 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 636a4c2c1294..fe25ae92744d 100644
@@ -518,6 +518,10 @@ 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
 };

@@ -640,6 +644,13 @@ 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 556da2de369f..23d7f1d64b23 100644
@@ -4291,6 +4291,15 @@ 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;

56 lines not on this page · raw message

index b3455e52170c..8da8f032a441 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,

@@ -50,6 +53,16 @@ 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 fe25ae92744d..e14f31a4b10c 100644
@@ -647,7 +647,8 @@ 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 56a4754efcfb..ca12ff5f5611 100644
@@ -207,15 +207,17 @@ 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,
+		.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;

@@ -235,6 +237,7 @@ 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,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
 	};
 
 	if (arg) {

@@ -243,6 +246,7 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
 	}
 
 	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
 	return 0;
 }