Skip to contentSkip to conversation

napi tracking strategy

PATCH Superseded Olivier Langlois 2 participants 9 messages Sep 18, 2024 – Sep 21, 2024 io_uring

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

v3 cover napi tracking strategy

the actual napi tracking strategy is inducing a non-negligeable overhead. Everytime a multishot poll is triggered or any poll armed, if the napi is enabled on the ring a lookup is performed to either add a new napi id into the napi_list or its timeout value is updated.

For many scenarios, this is overkill as the napi id list will be pretty much static most of the time. To address this common scenario, a new abstraction has been created following the common Linux kernel idiom of creating an abstract interface with a struct filled with function pointers.

the patch serie consist of very minor fixes followed by the core of the changes to implement the new feature.

v3 changes:
- address minor comments in patch #3
- replace the double for loop hash macro with the single loop list macro to iterate the napi elements in patch #2
- add __cold attribute to common_tracking_show_fdinfo() and napi_show_fdinfo()

v2 changes:
- extract small changes from the core changes to ease minor fixes backport
- totally remove the io_napi_tracking_ops interface

Olivier Langlois (3):
io_uring/napi: protect concurrent io_napi_entry timeout accesses io_uring/napi: fix io_napi_entry RCU accesses io_uring/napi: add static napi tracking strategy

 include/linux/io_uring_types.h |   2 +-
 include/uapi/linux/io_uring.h  |  32 +++++++-
 io_uring/fdinfo.c              |  41 ++++++++++
 io_uring/napi.c                | 140 +++++++++++++++++++++++++--------
 io_uring/napi.h                |  15 +++-
 5 files changed, 192 insertions(+), 38 deletions(-)
Signature · 1 line
2.46.1
#1 lore raw

PATCH v3 1/3 io_uring/napi: protect concurrent io_napi_entry timeout accesses

io_napi_entry timeout value can be updated while accessed from the poll functions.

Its concurrent accesses are wrapped with READ_ONCE()/WRITE_ONCE() macros to avoid incorrect compiler optimizations.

---
 io_uring/napi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
io_uring/napi.c +3 -3
index 1de1d4d62925..1dd2df9da468 100644
@@ -60,7 +60,7 @@ void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
 	rcu_read_lock();
 	e = io_napi_hash_find(hash_list, napi_id);
 	if (e) {
-		e->timeout = jiffies + NAPI_TIMEOUT;
+		WRITE_ONCE(e->timeout, jiffies + NAPI_TIMEOUT);
 		rcu_read_unlock();
 		return;
 	}
@@ -92,7 +92,7 @@ static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
 
 	spin_lock(&ctx->napi_lock);
 	hash_for_each(ctx->napi_ht, i, e, node) {
-		if (time_after(jiffies, e->timeout)) {
+		if (time_after(jiffies, READ_ONCE(e->timeout))) {
 			list_del(&e->list);
 			hash_del_rcu(&e->node);
 			kfree_rcu(e, rcu);
@@ -150,7 +150,7 @@ static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
 		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
 				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
 
-		if (time_after(jiffies, e->timeout))
+		if (time_after(jiffies, READ_ONCE(e->timeout)))
 			is_stale = true;
 	}
 
Signature · 1 line
2.46.1
#2 lore raw

PATCH v3 2/3 io_uring/napi: fix io_napi_entry RCU accesses

In reply to Olivier Langlois

correct 3 RCU structures modifications that were not using the RCU functions to make their update.

---
 io_uring/napi.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)
io_uring/napi.c +11 -6
index 1dd2df9da468..6fc127e74f10 100644
@@ -81,19 +81,24 @@ void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
 	}
 
 	hlist_add_tail_rcu(&e->node, hash_list);
-	list_add_tail(&e->list, &ctx->napi_list);
+	list_add_tail_rcu(&e->list, &ctx->napi_list);
 	spin_unlock(&ctx->napi_lock);
 }
 
 static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
 {
 	struct io_napi_entry *e;
-	unsigned int i;
 
 	spin_lock(&ctx->napi_lock);
-	hash_for_each(ctx->napi_ht, i, e, node) {
+	/*
+	 * list_for_each_entry_safe() is not required as long as:
+	 * 1. list_del_rcu() does not reset the deleted node next pointer
+	 * 2. kfree_rcu() delays the memory freeing until the next quiescent
+	 *    state
+	 */
+	list_for_each_entry(e, &ctx->napi_list, list) {
 		if (time_after(jiffies, READ_ONCE(e->timeout))) {
-			list_del(&e->list);
+			list_del_rcu(&e->list);
 			hash_del_rcu(&e->node);
 			kfree_rcu(e, rcu);
 		}
@@ -204,13 +209,13 @@ void io_napi_init(struct io_ring_ctx *ctx)
 void io_napi_free(struct io_ring_ctx *ctx)
 {
 	struct io_napi_entry *e;
-	unsigned int i;
 
 	spin_lock(&ctx->napi_lock);
-	hash_for_each(ctx->napi_ht, i, e, node) {
+	list_for_each_entry(e, &ctx->napi_list, list) {
 		hash_del_rcu(&e->node);
 		kfree_rcu(e, rcu);
 	}
+	INIT_LIST_HEAD_RCU(&ctx->napi_list);
 	spin_unlock(&ctx->napi_lock);
 }
 
Signature · 1 line
2.46.1
#3 lore raw

PATCH v3 3/3 io_uring/napi: add static napi tracking strategy

In reply to Olivier Langlois

add the static napi tracking strategy that allows the user to manually manage the napi ids list to busy poll and offload the ring from dynamically update the list.

---
 include/linux/io_uring_types.h |   2 +-
 include/uapi/linux/io_uring.h  |  32 ++++++++-
 io_uring/fdinfo.c              |  41 ++++++++++++
 io_uring/napi.c                | 117 ++++++++++++++++++++++++++-------
 io_uring/napi.h                |  15 +++--
 5 files changed, 178 insertions(+), 29 deletions(-)
include/linux/io_uring_types.h +1 -1
index 3315005df117..f0a0cb2518bb 100644
@@ -406,7 +406,7 @@ struct io_ring_ctx {
 	/* napi busy poll default timeout */
 	ktime_t			napi_busy_poll_dt;
 	bool			napi_prefer_busy_poll;
-	bool			napi_enabled;
+	u8			napi_track_mode;
 
 	DECLARE_HASHTABLE(napi_ht, 4);
 #endif
include/uapi/linux/io_uring.h +30 -2
index adc2524fd8e3..10d9030c4242 100644
@@ -728,12 +728,40 @@ struct io_uring_buf_status {
 	__u32	resv[8];
 };
 
+enum io_uring_napi_op {
+	/* register/ungister backward compatible opcode */
+	IO_URING_NAPI_REGISTER_OP = 0,
+
+	/* opcodes to update napi_list when static tracking is used */
+	IO_URING_NAPI_STATIC_ADD_ID = 1,
+	IO_URING_NAPI_STATIC_DEL_ID = 2
+};
+
+enum io_uring_napi_tracking_strategy {
+	/* value must be 0 for backward compatibility */
+	IO_URING_NAPI_TRACKING_DYNAMIC = 0,
+	IO_URING_NAPI_TRACKING_STATIC = 1,
+	IO_URING_NAPI_TRACKING_INACTIVE = 255
+};
+
 /* argument for IORING_(UN)REGISTER_NAPI */
 struct io_uring_napi {
 	__u32	busy_poll_to;
 	__u8	prefer_busy_poll;
-	__u8	pad[3];
-	__u64	resv;
+
+	/* a io_uring_napi_op value */
+	__u8	opcode;
+	__u8	pad[2];
+
+	/*
+	 * for IO_URING_NAPI_REGISTER_OP, it is a
+	 * io_uring_napi_tracking_strategy value.
+	 *
+	 * for IO_URING_NAPI_STATIC_ADD_ID/IO_URING_NAPI_STATIC_DEL_ID
+	 * it is the napi id to add/del from napi_list.
+	 */
+	__u32	op_param;
+	__u32	resv;
 };
 
 /*
io_uring/fdinfo.c +41 -0

52 lines not on this page · raw message

io_uring/napi.c +95 -22

198 lines not on this page · raw message

io_uring/napi.h +11 -4
index 27b88c3eb428..220574522484 100644
@@ -15,7 +15,7 @@ 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 socket *sock);
+int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id);
 
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
 		struct io_wait_queue *iowq, ktime_t to_wait);
@@ -54,13 +54,20 @@ static inline void io_napi_add(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct socket *sock;
+	struct sock *sk;
 
-	if (!READ_ONCE(ctx->napi_enabled))
+	if (READ_ONCE(ctx->napi_track_mode) != IO_URING_NAPI_TRACKING_DYNAMIC)
 		return;
 
 	sock = sock_from_file(req->file);
-	if (sock)
-		__io_napi_add(ctx, sock);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	__io_napi_add_id(ctx, READ_ONCE(sk->sk_napi_id));
 }
 
 #else
Signature · 1 line
2.46.1
maintainer
#6 lore raw
In reply to Olivier Langlois
Quoted 9 lines · Olivier Langlois

the actual napi tracking strategy is inducing a non-negligeable overhead. Everytime a multishot poll is triggered or any poll armed, if the napi is enabled on the ring a lookup is performed to either add a new napi id into the napi_list or its timeout value is updated.

For many scenarios, this is overkill as the napi id list will be pretty much static most of the time. To address this common scenario, a new abstraction has been created following the common Linux kernel idiom of creating an abstract interface with a struct filled with function pointers.

This paragraph seems to be a remnant of the v1 implementation?

Signature · 1 line
Jens Axboe
maintainer
#4 lore raw

Re: [PATCH v3 3/3] io_uring/napi: add static napi tracking strategy

In reply to Olivier Langlois
Quoted 3 lines · Olivier Langlois

add the static napi tracking strategy that allows the user to manually manage the napi ids list to busy poll and offload the ring from dynamically update the list.

Add the static napi tracking strategy. That allows the user to manually manage the napi ids list for busy polling, and eliminate the overhead of dynamically updating the list from the fast path.

Maybe?

Quoted 36 lines

index b1e0e0d85349..6f0e40e1469c 100644

io_uring/fdinfo.c +29 -0
@@ -46,6 +46,46 @@ static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
 	return 0;
 }
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static __cold void common_tracking_show_fdinfo(struct io_ring_ctx *ctx,
+					       struct seq_file *m,
+					       const char *tracking_strategy)
+{
+	seq_puts(m, "NAPI:\tenabled\n");
+	seq_printf(m, "napi tracking:\t%s\n", tracking_strategy);
+	seq_printf(m, "napi_busy_poll_dt:\t%llu\n", ctx->napi_busy_poll_dt);
+	if (ctx->napi_prefer_busy_poll)
+		seq_puts(m, "napi_prefer_busy_poll:\ttrue\n");
+	else
+		seq_puts(m, "napi_prefer_busy_poll:\tfalse\n");
+}
+
+static __cold void napi_show_fdinfo(struct io_ring_ctx *ctx,
+				    struct seq_file *m)
+{
+	unsigned int mode = READ_ONCE(ctx->napi_track_mode);
+
+	switch (mode) {
+	case IO_URING_NAPI_TRACKING_INACTIVE:
+		seq_puts(m, "NAPI:\tdisabled\n");
+		break;
+	case IO_URING_NAPI_TRACKING_DYNAMIC:
+		common_tracking_show_fdinfo(ctx, m, "dynamic");
+		break;
+	case IO_URING_NAPI_TRACKING_STATIC:
+		common_tracking_show_fdinfo(ctx, m, "static");
+		break;

io_uring/fdinfo.c static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, · line 87

Quoted 10 lines
io_uring/fdinfo.c +10 -0
+	default:
+		seq_printf(m, "NAPI:\tunknown mode (%u)\n", mode);
+	}
+}
+#else
+static inline void napi_show_fdinfo(struct io_ring_ctx *ctx,
+				    struct seq_file *m)
+{
+}
+#endif

I think this code should go in napi.c, with the stub CONFIG_NET_RX_BUSY_POLL in napi.h. Not a huge deal.

This also conflicts with your previous napi patch adding fdinfo support. What kernel is this patchset based on? You should rebase it for-6.12/io_uring, then it should apply to the development branch going forward too.

Quoted 46 lines
io_uring/napi.c +4 -12
index 6fc127e74f10..d98b87d346ca 100644
@@ -38,22 +38,14 @@ static inline ktime_t net_to_ktime(unsigned long t)
 	return ns_to_ktime(t << 10);
 }
 
-void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id)
 {
 	struct hlist_head *hash_list;
-	unsigned int napi_id;
-	struct sock *sk;
 	struct io_napi_entry *e;
 
-	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;
+		return -EINVAL;
 
 	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
 
@@ -62,13 +54,13 @@ void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
 	if (e) {
 		WRITE_ONCE(e->timeout, jiffies + NAPI_TIMEOUT);
 		rcu_read_unlock();
-		return;
+		return -EEXIST;
 	}
 	rcu_read_unlock();
 
 	e = kmalloc(sizeof(*e), GFP_NOWAIT);
 	if (!e)
-		return;
+		return -ENOMEM;
 
 	e->napi_id = napi_id;
 	e->timeout = jiffies + NAPI_TIMEOUT;

io_uring/napi.c void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) · line 73

Quoted 6 lines
io_uring/napi.c +1 -1
@@ -77,12 +69,37 @@ void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
 	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
 		spin_unlock(&ctx->napi_lock);
 		kfree(e);
-		return;
+		return -EEXIST;
 	}

You could abstract this out to a prep patch, having __io_napi_add() return an error value. That would leave the meat of your patch simpler and easier to review.

Quoted 13 lines
io_uring/napi.c +13 -0
+static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id)
+{
+	struct hlist_head *hash_list;
+	struct io_napi_entry *e;
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return -EINVAL;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+	spin_lock(&ctx->napi_lock);
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (unlikely(!e)) {

io_uring/napi.c void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) · line 103

Quoted 10 lines
io_uring/napi.c +9 -0
+		spin_unlock(&ctx->napi_lock);
+		return -ENOENT;
+	}
+
+	list_del_rcu(&e->list);
+	hash_del_rcu(&e->node);
+	kfree_rcu(e, rcu);
+	spin_unlock(&ctx->napi_lock);
+	return 0;
 }

For new code, not a bad idea to use:

	guard(spinlock)(&ctx->napi_lock);

Only one cleanup path here, but...

Quoted 20 lines
io_uring/napi.c +13 -2
 static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
@@ -141,8 +158,26 @@ static bool io_napi_busy_loop_should_end(void *data,
 	return false;
 }
 
-static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
-				   void *loop_end_arg)
+/*
+ * never report stale entries
+ */
+static bool static_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+					 void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool (*loop_end)(void *, unsigned long) = NULL;
+
+	if (loop_end_arg)
+		loop_end = io_napi_busy_loop_should_end;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list)

io_uring/napi.c static bool io_napi_busy_loop_should_end(void *data, · line 183

Quoted 10 lines
io_uring/napi.c +7 -0
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+	return false;
+}
+
+static bool dynamic_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+					  void *loop_end_arg)
 {
 	struct io_napi_entry *e;
 	bool (*loop_end)(void *, unsigned long) = NULL;

This is somewhat convoluted, but I think it'd be cleaner to have a prep patch that just passes in both loop_end and loop_end_arg to the caller? Some of this predates your changes here, but seems there's room for cleaning this up. What do you think?

Quoted 16 lines
io_uring/napi.h +2 -2
index 27b88c3eb428..220574522484 100644
@@ -54,13 +54,20 @@ static inline void io_napi_add(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct socket *sock;
+	struct sock *sk;
 
-	if (!READ_ONCE(ctx->napi_enabled))
+	if (READ_ONCE(ctx->napi_track_mode) != IO_URING_NAPI_TRACKING_DYNAMIC)
 		return;
 
 	sock = sock_from_file(req->file);
-	if (sock)

io_uring/napi.h static inline void io_napi_add(struct io_kiocb *req) · line 71

Quoted 10 lines
io_uring/napi.h +8 -1
-		__io_napi_add(ctx, sock);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	__io_napi_add_id(ctx, READ_ONCE(sk->sk_napi_id));
 }

I like having this follow the expected outcome, which is that sock and sk are valid.

	sock = sock_from_file(req->file);
	if (sock && sock->sk)
		__io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id));

or something like that. At least to me that's more readable.

Signature · 1 line
Jens Axboe
#7 lore raw
In reply to Jens Axboe
Quoted 18 lines · Jens Axboe
Quoted 8 lines · Olivier Langlois

the actual napi tracking strategy is inducing a non-negligeable overhead.
Everytime a multishot poll is triggered or any poll armed, if the napi is
enabled on the ring a lookup is performed to either add a new napi id into
the napi_list or its timeout value is updated.

Quoted 8 lines

For many scenarios, this is overkill as the napi id list will be pretty
much static most of the time. To address this common scenario, a new
abstraction has been created following the common Linux kernel idiom of
creating an abstract interface with a struct filled with function pointers.

Quoted 2 lines

This paragraph seems to be a remnant of the v1 implementation?

you are right. At least the last sentence is. Is the cover letter injected somewhere in any way once the patch is accepted? Would that detail alone justify the creation of a v4?

I am taking note of the detail and I will correct this if there is a need for a v4.

maintainer
#8 lore raw
Quoted 19 lines · Olivier Langlois
Quoted 18 lines · Jens Axboe
Quoted 16 lines · Olivier Langlois

the actual napi tracking strategy is inducing a non-negligeable overhead.
Everytime a multishot poll is triggered or any poll armed, if the napi is
enabled on the ring a lookup is performed to either add a new napi id into
the napi_list or its timeout value is updated.

For many scenarios, this is overkill as the napi id list will be pretty
much static most of the time. To address this common scenario, a new
abstraction has been created following the common Linux kernel idiom of
creating an abstract interface with a struct filled with function pointers.

Quoted 8 lines
Quoted 2 lines

This paragraph seems to be a remnant of the v1 implementation?

you are right. At least the last sentence is. Is the cover letter injected somewhere in any way once the patch is accepted? Would that detail alone justify the creation of a v4?

I am taking note of the detail and I will correct this if there is a need for a v4.

Right just make a note of it if you need to send a v4 for other reasons, cover letter doesn't go anywhere in the git log - but is, however, linked off the git commits in terms of the Link in there. But since we now have this discussion in there as well clarifying it, that is fine.

Doing conferences in Europe until end of next week, I'll see if I can do some thorough looking at this version during that, or worst case end of that.

Signature · 1 line
Jens Axboe
#5 lore raw

Re: [PATCH v3 3/3] io_uring/napi: add static napi tracking strategy

In reply to Jens Axboe
Quoted 6 lines · Jens Axboe
Quoted 4 lines · Olivier Langlois

add the static napi tracking strategy that allows the user to manually
manage the napi ids list to busy poll and offload the ring from dynamically update the list.

Quoted 7 lines

Add the static napi tracking strategy. That allows the user to manually
manage the napi ids list for busy polling, and eliminate the overhead of
dynamically updating the list from the fast path.

Maybe?

ok

Quoted 55 lines
Quoted 41 lines

index b1e0e0d85349..6f0e40e1469c 100644

io_uring/fdinfo.c +0 -0
@@ -46,6 +46,46 @@ static __cold int io_uring_show_cred(struct
 seq_file *m, unsigned int id,
  	return 0;
  }

io_uring/fdinfo.c +2 -0
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static __cold void common_tracking_show_fdinfo(struct io_ring_ctx

*ctx,

io_uring/fdinfo.c +2 -0
+					       struct seq_file *m,
+					       const char

*tracking_strategy)

io_uring/fdinfo.c +4 -0
+{
+	seq_puts(m, "NAPI:\tenabled\n");
+	seq_printf(m, "napi tracking:\t%s\n", tracking_strategy);
+	seq_printf(m, "napi_busy_poll_dt:\t%llu\n", ctx-
Quoted 1 line

napi_busy_poll_dt);

io_uring/fdinfo.c +21 -0
+	if (ctx->napi_prefer_busy_poll)
+		seq_puts(m, "napi_prefer_busy_poll:\ttrue\n");
+	else
+		seq_puts(m, "napi_prefer_busy_poll:\tfalse\n");
+}
+
+static __cold void napi_show_fdinfo(struct io_ring_ctx *ctx,
+				    struct seq_file *m)
+{
+	unsigned int mode = READ_ONCE(ctx->napi_track_mode);
+
+	switch (mode) {
+	case IO_URING_NAPI_TRACKING_INACTIVE:
+		seq_puts(m, "NAPI:\tdisabled\n");
+		break;
+	case IO_URING_NAPI_TRACKING_DYNAMIC:
+		common_tracking_show_fdinfo(ctx, m, "dynamic");
+		break;
+	case IO_URING_NAPI_TRACKING_STATIC:
+		common_tracking_show_fdinfo(ctx, m, "static");
+		break;

io_uring/fdinfo.c static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, · line 87

Quoted 10 lines
io_uring/fdinfo.c +10 -0
+	default:
+		seq_printf(m, "NAPI:\tunknown mode (%u)\n", mode);
+	}
+}
+#else
+static inline void napi_show_fdinfo(struct io_ring_ctx *ctx,
+				    struct seq_file *m)
+{
+}
+#endif

I think this code should go in napi.c, with the stub CONFIG_NET_RX_BUSY_POLL in napi.h. Not a huge deal.

Quoted 6 lines

This also conflicts with your previous napi patch adding fdinfo support.
What kernel is this patchset based on? You should rebase it for-6.12/io_uring, then it should apply to the development branch going
forward too.

The repo used is Linus head. Yes I was surprised to not see my own patch there. Kernel dev process is still a bit obscure to me... but I figured that the conflict would be very trivial to solve. Basically, simply drop the previous patch to replace it with this one.

but yes. I can rebase the patch into your repo. Can you provide me the URL of your repo?

About your suggestion to move stuff in napi.h. I did though about it. In fact, the code was there at some point before submission (or in v1). but I did conclude the exact opposite. That it would be cleaner to keep the fdinfo stuff together instead of polluting napi TU with it...

with this argument, if you still prefer to see that code in napi TU, I will move it there.

Quoted 55 lines
Quoted 55 lines
io_uring/napi.c +0 -0
index 6fc127e74f10..d98b87d346ca 100644
@@ -38,22 +38,14 @@ static inline ktime_t net_to_ktime(unsigned
 long t)
  	return ns_to_ktime(t << 10);
  }

io_uring/napi.c +1 -1
-void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int

napi_id)
 {
  struct hlist_head *hash_list;

io_uring/napi.c +0 -2
-	unsigned int napi_id;
-	struct sock *sk;

  struct io_napi_entry *e;

io_uring/napi.c +0 -6
-	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)

io_uring/napi.c +1 -1
-		return;
+		return -EINVAL;


  hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx-

Quoted 1 line

napi_ht))];

io_uring/napi.c +1 -1
@@ -62,13 +54,13 @@ void __io_napi_add(struct io_ring_ctx *ctx,
 struct socket *sock)
  	if (e) {
  		WRITE_ONCE(e->timeout, jiffies + NAPI_TIMEOUT);
  		rcu_read_unlock();
-		return;
+		return -EEXIST;
  	}
  	rcu_read_unlock();


  e = kmalloc(sizeof(*e), GFP_NOWAIT);
  if (!e)

io_uring/napi.c +1 -1
-		return;
+		return -ENOMEM;


  e->napi_id = napi_id;
  e->timeout = jiffies + NAPI_TIMEOUT;

io_uring/napi.c +0 -0
@@ -77,12 +69,37 @@ void __io_napi_add(struct io_ring_ctx *ctx,
 struct socket *sock)
  	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
  		spin_unlock(&ctx->napi_lock);
  		kfree(e);
Quoted 8 lines

io_uring/napi.c void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) · line 58

Quoted 3 lines
io_uring/napi.c +1 -1
-		return;
+		return -EEXIST;
  	}

You could abstract this out to a prep patch, having __io_napi_add() return an error value. That would leave the meat of your patch simpler
and easier to review.

ok

Quoted 29 lines
Quoted 16 lines
io_uring/napi.c +13 -0
+static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int
 napi_id)
+{
+	struct hlist_head *hash_list;
+	struct io_napi_entry *e;
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return -EINVAL;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx-
 >napi_ht))];
+	spin_lock(&ctx->napi_lock);
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (unlikely(!e)) {

io_uring/napi.c void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) · line 103

Quoted 10 lines
io_uring/napi.c +9 -0
+		spin_unlock(&ctx->napi_lock);
+		return -ENOENT;
+	}
+
+	list_del_rcu(&e->list);
+	hash_del_rcu(&e->node);
+	kfree_rcu(e, rcu);
+	spin_unlock(&ctx->napi_lock);
+	return 0;
  }

For new code, not a bad idea to use:

Quoted 3 lines
	guard(spinlock)(&ctx->napi_lock);

Only one cleanup path here, but...

first time I hear about this... Some sort of RAII where the compiler adds automatically unlock function call at every exit points?

ok, I'll look into it

Quoted 33 lines
Quoted 33 lines
io_uring/napi.c +0 -0
  static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
@@ -141,8 +158,26 @@ static bool io_napi_busy_loop_should_end(void
 *data,
  	return false;
  }

io_uring/napi.c +14 -2
-static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
-				   void *loop_end_arg)
+/*
+ * never report stale entries
+ */
+static bool static_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+					 void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool (*loop_end)(void *, unsigned long) = NULL;
+
+	if (loop_end_arg)
+		loop_end = io_napi_busy_loop_should_end;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list)
+		napi_busy_loop_rcu(e->napi_id, loop_end,

loop_end_arg,

io_uring/napi.c +1 -0
+				   ctx->napi_prefer_busy_poll,

BUSY_POLL_BUDGET);

io_uring/napi.c +5 -0
+	return false;
+}
+
+static bool dynamic_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+					  void *loop_end_arg)

 {
  struct io_napi_entry *e;

Quoted 8 lines
Quoted 1 line

  bool (*loop_end)(void *, unsigned long) = NULL;

This is somewhat convoluted, but I think it'd be cleaner to have a prep
patch that just passes in both loop_end and loop_end_arg to the caller?
Some of this predates your changes here, but seems there's room for cleaning this up. What do you think?

I am not sure that I see your point that it would make the code cleaner. TBH, I did not fully understood what was the point of the whole loop_end business thing but since it was unrelated to my changes, I did leave that thing undisturbed.

I'll take a second look at it to see if I can clean this up a bit...

Quoted 34 lines
Quoted 28 lines
io_uring/napi.h +1 -0
index 27b88c3eb428..220574522484 100644
@@ -54,13 +54,20 @@ static inline void io_napi_add(struct io_kiocb
 *req)
  {
  	struct io_ring_ctx *ctx = req->ctx;
  	struct socket *sock;
+	struct sock *sk;

io_uring/napi.h +1 -1
-	if (!READ_ONCE(ctx->napi_enabled))
+	if (READ_ONCE(ctx->napi_track_mode) !=

IO_URING_NAPI_TRACKING_DYNAMIC)
  return;

  sock = sock_from_file(req->file);

io_uring/napi.h +8 -2
-	if (sock)
-		__io_napi_add(ctx, sock);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	__io_napi_add_id(ctx, READ_ONCE(sk->sk_napi_id));
Quoted 1 line

 }

I like having this follow the expected outcome, which is that sock and
sk are valid.

Quoted 7 lines
	sock = sock_from_file(req->file);
	if (sock && sock->sk)
		__io_napi_add_id(ctx, READ_ONCE(sock->sk-
Quoted 1 line

sk_napi_id));

or something like that. At least to me that's more readable.

ok.

All those points will be addressed in v4