[PATCH v8 4/7] io-uring: add napi busy poll support

[Stefan Roesch <shr@devkernel.io>]

This adds the napi busy polling support in io_uring.c. It adds a new
napi_list to the io_ring_ctx structure. This list contains the list of
napi_id's that are currently enabled for busy polling. The list is
synchronized by the new napi_lock spin lock. The current default napi
busy polling time is stored in napi_busy_poll_to. If napi busy polling
is not enabled, the value is 0.

In addition there is also a hash table. The hash table store the napi
id ond the pointer to the above list nodes. The hash table is used to
speed up the lookup to the list elements.

The NAPI_TIMEOUT is stored as a timeout to make sure that the time a
napi entry is stored in the napi list is limited.

The busy poll timeout is also stored as part of the io_wait_queue. This
is necessary as for sq polling the poll interval needs to be adjusted
and the napi callback allows only to pass in one value.

This has been tested with two simple programs from the liburing library
repository: the napi client and the napi server program. The client
sends a request, which has a timestamp in its payload and the server
replies with the same payload. The client calculates the roundtrip time
and stores it to calcualte the results.

The client is running on host1 and the server is running on host 2 (in
the same rack). The measured times below are roundtrip times. They are
average times over 5 runs each. Each run measures 1 million roundtrips.

                   no rx coal          rx coal: frames=88,usecs=33
Default              57us                    56us

client_poll=100us    47us                    46us

server_poll=100us    51us                    46us

client_poll=100us+   40us                    40us
server_poll=100us

client_poll=100us+   41us                    39us
server_poll=100us+
prefer napi busy poll on client

client_poll=100us+   41us                    39us
server_poll=100us+
prefer napi busy poll on server

client_poll=100us+   41us                    39us
server_poll=100us+
prefer napi busy poll on client + server

Signed-off-by: Stefan Roesch <shr@devkernel.io>
Suggested-by: Olivier Langlois <olivier@trillion01.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
---
 io_uring/Makefile   |   1 +
 io_uring/io_uring.c |  12 ++
 io_uring/napi.c     | 281 ++++++++++++++++++++++++++++++++++++++++++++
 io_uring/napi.h     |  49 ++++++++
 io_uring/poll.c     |   2 +
 5 files changed, 345 insertions(+)
 create mode 100644 io_uring/napi.c
 create mode 100644 io_uring/napi.h

diff --git a/io_uring/Makefile b/io_uring/Makefile
index 8cc8e5387a75..2efe7c5f07ba 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
 					cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
+obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 5d6aa783fb97..7074379a9bd0 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -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);
@@ -2534,6 +2537,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	struct io_wait_queue iowq;
 	struct io_rings *rings = ctx->rings;
 	int ret;
+	NAPI_LIST_HEAD(local_napi_list);
 
 	if (!io_allowed_run_tw(ctx))
 		return -EEXIST;
@@ -2566,15 +2570,22 @@ 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;
 
+	io_napi_setup_busy_loop(ctx, &iowq, &local_napi_list);
 	if (uts) {
 		struct timespec64 ts;
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
+
+		io_napi_adjust_busy_loop_timeout(ctx, &iowq, &local_napi_list, &ts);
 		iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+	} else {
+		io_napi_adjust_busy_loop_timeout(ctx, &iowq, &local_napi_list, NULL);
 	}
 
 	trace_io_uring_cqring_wait(ctx, min_events);
+	io_napi_end_busy_loop(ctx, &iowq, &local_napi_list);
+
 	do {
 		unsigned long check_cq;
 
@@ -2806,6 +2817,7 @@ 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);
diff --git a/io_uring/napi.c b/io_uring/napi.c
new file mode 100644
index 000000000000..c9e2afae382d
--- /dev/null
+++ b/io_uring/napi.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "io_uring.h"
+#include "napi.h"
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+/* Timeout for cleanout of stale entries. */
+#define NAPI_TIMEOUT		(60 * SEC_CONVERSION)
+
+struct io_napi_ht_entry {
+	unsigned int		napi_id;
+	struct list_head	list;
+
+	/* Covered by napi lock spinlock.  */
+	unsigned long		timeout;
+	struct hlist_node	node;
+};
+
+static inline bool io_napi_busy_loop_on(struct io_ring_ctx *ctx)
+{
+	return READ_ONCE(ctx->napi_busy_poll_to);
+}
+
+static inline void __io_napi_add(struct io_ring_ctx *ctx, struct file *file)
+{
+	unsigned int napi_id;
+	struct socket *sock;
+	struct sock *sk;
+	struct io_napi_ht_entry *he;
+
+	if (!io_napi_busy_loop_on(ctx))
+		return;
+
+	sock = sock_from_file(file);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each_possible(ctx->napi_ht, he, node, napi_id) {
+		if (he->napi_id == napi_id) {
+			he->timeout = jiffies + NAPI_TIMEOUT;
+			goto out;
+		}
+	}
+
+	he = kmalloc(sizeof(*he), GFP_NOWAIT);
+	if (!he)
+		goto out;
+
+	he->napi_id = napi_id;
+	he->timeout = jiffies + NAPI_TIMEOUT;
+	hash_add(ctx->napi_ht, &he->node, napi_id);
+
+	list_add_tail(&he->list, &ctx->napi_list);
+
+out:
+	spin_unlock(&ctx->napi_lock);
+}
+
+static void __io_napi_adjust_busy_loop_timeout(unsigned int poll_to,
+					     struct timespec64 *ts,
+					     unsigned int *new_poll_to)
+{
+	struct timespec64 pollto = ns_to_timespec64(1000 * (s64)poll_to);
+
+	if (timespec64_compare(ts, &pollto) > 0) {
+		*ts = timespec64_sub(*ts, pollto);
+		*new_poll_to = poll_to;
+	} else {
+		u64 to = timespec64_to_ns(ts);
+
+		do_div(to, 1000);
+		*new_poll_to = to;
+		ts->tv_sec = 0;
+		ts->tv_nsec = 0;
+	}
+}
+
+static inline bool io_napi_busy_loop_timeout(unsigned long start_time,
+					     unsigned long bp_usec)
+{
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	}
+
+	return true;
+}
+
+static bool io_napi_busy_loop_should_end(void *p, unsigned long start_time)
+{
+	struct io_wait_queue *iowq = p;
+
+	return signal_pending(current) ||
+	       io_should_wake(iowq) ||
+	       io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to);
+}
+
+static bool io_napi_busy_loop(struct list_head *napi_list, bool prefer_busy_poll)
+{
+	struct io_napi_ht_entry *e;
+	struct io_napi_ht_entry *n;
+
+	list_for_each_entry_safe(e, n, napi_list, list) {
+		napi_busy_loop(e->napi_id, NULL, NULL, prefer_busy_poll,
+			       BUSY_POLL_BUDGET);
+	}
+
+	return !list_empty(napi_list);
+}
+
+static void io_napi_blocking_busy_loop(struct list_head *napi_list,
+				       struct io_wait_queue *iowq)
+{
+	unsigned long start_time = 0;
+
+	if (!list_is_singular(napi_list))
+		start_time = busy_loop_current_time();
+
+	while (!list_is_singular(napi_list) &&
+		io_napi_busy_loop(napi_list, iowq->napi_prefer_busy_poll) &&
+		!io_napi_busy_loop_should_end(iowq, start_time)) {
+		;
+	}
+
+	if (list_is_singular(napi_list)) {
+		struct io_napi_ht_entry *ne = list_first_entry(napi_list,
+						 struct io_napi_ht_entry, list);
+
+		napi_busy_loop(ne->napi_id, io_napi_busy_loop_should_end, iowq,
+			       iowq->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+	}
+}
+
+static void io_napi_remove_stale(struct io_ring_ctx *ctx)
+{
+	unsigned int i;
+	struct io_napi_ht_entry *he;
+
+	hash_for_each(ctx->napi_ht, i, he, node) {
+		if (time_after(jiffies, he->timeout)) {
+			list_del(&he->list);
+			hash_del(&he->node);
+		}
+	}
+
+}
+
+static void io_napi_merge_lists(struct io_ring_ctx *ctx, struct list_head *napi_list)
+{
+	spin_lock(&ctx->napi_lock);
+	list_splice(napi_list, &ctx->napi_list);
+	io_napi_remove_stale(ctx);
+	spin_unlock(&ctx->napi_lock);
+}
+
+/*
+ * io_napi_init() - Init napi settings
+ * @ctx: pointer to io-uring context structure
+ *
+ * Init napi settings in the io-uring context.
+ */
+void io_napi_init(struct io_ring_ctx *ctx)
+{
+	INIT_LIST_HEAD(&ctx->napi_list);
+	spin_lock_init(&ctx->napi_lock);
+	ctx->napi_prefer_busy_poll = false;
+	ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
+}
+
+/*
+ * io_napi_free() - Deallocate napi
+ * @ctx: pointer to io-uring context structure
+ *
+ * Free the napi list and the hash table in the io-uring context.
+ */
+void io_napi_free(struct io_ring_ctx *ctx)
+{
+	unsigned int i;
+	struct io_napi_ht_entry *he;
+	LIST_HEAD(napi_list);
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, he, node)
+		hash_del(&he->node);
+	spin_unlock(&ctx->napi_lock);
+}
+
+/*
+ * io_napi_add() - Add napi id to the busy poll list
+ * @req: pointer to io_kiocb request
+ *
+ * Add the napi id of the socket to the napi busy poll list and hash table.
+ */
+void io_napi_add(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (!io_napi_busy_loop_on(ctx))
+		return;
+
+	__io_napi_add(ctx, req->file);
+}
+
+/*
+ * io_napi_adjust_busy_loop_timeout() - Add napi id to the busy poll list
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ * @napi_list: pointer to head of napi list
+ * @ts: pointer to timespec or NULL
+ *
+ * Adjust the busy loop timeout according to timespec and busy poll timeout.
+ */
+void io_napi_adjust_busy_loop_timeout(struct io_ring_ctx *ctx,
+				struct io_wait_queue *iowq,
+				struct list_head *napi_list,
+				struct timespec64 *ts)
+{
+	if (!list_empty(napi_list)) {
+		if (ts)
+			__io_napi_adjust_busy_loop_timeout(
+				READ_ONCE(ctx->napi_busy_poll_to),
+				ts, &iowq->napi_busy_poll_to);
+		else
+			iowq->napi_busy_poll_to = READ_ONCE(ctx->napi_busy_poll_to);
+	}
+}
+
+/*
+ * io_napi_setup_busy_loop() - setup the busy poll loop
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ * @napi_list: pointer to head of napi list
+ *
+ * Capture busy poll timeout and prefer busy poll seeting Splice of the napi list.
+ */
+void io_napi_setup_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			struct list_head *napi_list)
+{
+	iowq->napi_busy_poll_to = 0;
+	iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
+
+	if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
+		spin_lock(&ctx->napi_lock);
+		list_splice_init(&ctx->napi_list, napi_list);
+		spin_unlock(&ctx->napi_lock);
+	}
+}
+
+/*
+ * io_napi_end_busy_loop() - execute busy poll loop
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ * @napi_list: pointer to head of napi list
+ *
+ * Execute the busy poll loop and merge the spliced off list.
+ */
+void io_napi_end_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			struct list_head *napi_list)
+{
+	if (iowq->napi_busy_poll_to)
+		io_napi_blocking_busy_loop(napi_list, iowq);
+
+	if (!list_empty(napi_list))
+		io_napi_merge_lists(ctx, napi_list);
+}
+
+#endif
diff --git a/io_uring/napi.h b/io_uring/napi.h
new file mode 100644
index 000000000000..0672592cfb79
--- /dev/null
+++ b/io_uring/napi.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef IOU_NAPI_H
+#define IOU_NAPI_H
+
+#include <linux/kernel.h>
+#include <linux/io_uring.h>
+#include <net/busy_poll.h>
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+#define NAPI_LIST_HEAD(l) LIST_HEAD(l)
+
+void io_napi_init(struct io_ring_ctx *ctx);
+void io_napi_free(struct io_ring_ctx *ctx);
+
+void io_napi_add(struct io_kiocb *req);
+
+void io_napi_setup_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			struct list_head *napi_list);
+void io_napi_adjust_busy_loop_timeout(struct io_ring_ctx *ctx,
+			struct io_wait_queue *iowq, struct list_head *napi_list,
+			struct timespec64 *ts);
+void io_napi_end_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			struct list_head *napi_list);
+
+#else
+
+#define NAPI_LIST_HEAD(l)
+
+static inline void io_napi_init(struct io_ring_ctx *ctx)
+{
+}
+
+static inline void io_napi_free(struct io_ring_ctx *ctx)
+{
+}
+
+static inline void io_napi_add(struct io_kiocb *req)
+{
+}
+
+#define io_napi_setup_busy_loop(ctx, iowq, napi_list) do {} while (0)
+#define io_napi_adjust_busy_loop_timeout(ctx, iowq, napi_list, ts) do {} while (0)
+#define io_napi_end_busy_loop(ctx, iowq, napi_list) do {} while (0)
+
+#endif
+
+#endif
diff --git a/io_uring/poll.c b/io_uring/poll.c
index 8339a92b4510..ab08299eb341 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -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) {
 		/*
-- 
2.30.2