* [PATCH v8 1/7] io-uring: move io_wait_queue definition to header file
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 2/7] io-uring: add napi fields to io_ring_ctx Stefan Roesch
` (5 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team; +Cc: shr, axboe, ammarfaizi2
This moves the definition of the io_wait_queue structure to the header
file so it can be also used from other files.
Signed-off-by: Stefan Roesch <[email protected]>
---
io_uring/io_uring.c | 21 ---------------------
io_uring/io_uring.h | 22 ++++++++++++++++++++++
2 files changed, 22 insertions(+), 21 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 0e42160a3051..5d6aa783fb97 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -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)
{
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 2711865f1e19..021f9af37c74 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -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);
--
2.30.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 2/7] io-uring: add napi fields to io_ring_ctx
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 1/7] io-uring: move io_wait_queue definition to header file Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 3/7] io-uring: add busy poll timeout, prefer busy poll to io_wait_queue Stefan Roesch
` (4 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team; +Cc: shr, axboe, ammarfaizi2
Add the napi fields to the io_ring_ctx data structure. It contains of a
list, a hash table and two settings. The settings are the busy poll
timeout and prefer busy poll.
The list and the hash table operate on the same data structure. The hash
table is used when adding elements and the list is used when executing
the busy poll loop.
Signed-off-by: Stefan Roesch <[email protected]>
---
include/linux/io_uring_types.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 0efe4d784358..fe4033aacc4c 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -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
--
2.30.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 3/7] io-uring: add busy poll timeout, prefer busy poll to io_wait_queue
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 1/7] io-uring: move io_wait_queue definition to header file Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 2/7] io-uring: add napi fields to io_ring_ctx Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 4/7] io-uring: add napi busy poll support Stefan Roesch
` (3 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team; +Cc: shr, axboe, ammarfaizi2
This adds the two fields busy poll timeout and prefer busy poll to the
io_wait_queue structure. They are used during the busy poll processing.
Signed-off-by: Stefan Roesch <[email protected]>
---
io_uring/io_uring.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 021f9af37c74..2e1b8de8505a 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -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)
--
2.30.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 4/7] io-uring: add napi busy poll support
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
` (2 preceding siblings ...)
2023-02-09 23:01 ` [PATCH v8 3/7] io-uring: add busy poll timeout, prefer busy poll to io_wait_queue Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-10 0:00 ` Jens Axboe
2023-02-09 23:01 ` [PATCH v8 5/7] io-uring: add sqpoll support for napi busy poll Stefan Roesch
` (2 subsequent siblings)
6 siblings, 1 reply; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team
Cc: shr, axboe, ammarfaizi2, Olivier Langlois, Jakub Kicinski
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 <[email protected]>
Suggested-by: Olivier Langlois <[email protected]>
Acked-by: Jakub Kicinski <[email protected]>
---
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
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [PATCH v8 4/7] io-uring: add napi busy poll support
2023-02-09 23:01 ` [PATCH v8 4/7] io-uring: add napi busy poll support Stefan Roesch
@ 2023-02-10 0:00 ` Jens Axboe
2023-02-15 17:22 ` Stefan Roesch
0 siblings, 1 reply; 13+ messages in thread
From: Jens Axboe @ 2023-02-10 0:00 UTC (permalink / raw)
To: Stefan Roesch, io-uring, kernel-team
Cc: ammarfaizi2, Olivier Langlois, Jakub Kicinski
I'd fold 2+3 into this patch again, having them standalone don't really
make a lot of sense without this patch.
This looks a lot better and gets rid of the ifdef infestation! Minor
comments below, mostly just because I think we should fold those 3
patches anyway.
> 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);
> +}
I'd probably get rid of this helper, to be honest.
> +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);
> + }
Looks like 8 spaces before that BUSY_POLL_BUDGET, should be a tab?
> +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);
> + }
> +}
This does look a LOT better! I do think a helper for the first while
would make sense, and then have a comment in that helper on what this is
doing exactly.
static void io_napi_multi_busy_loop(napi_list, iowq)
{
unsigned long start_time = busy_loop_current_time();
do {
if (list_is_singular(napi_list))
break;
if (!io_napi_busy_loop(napi_list, iowq->napi_prefer_busy_poll))
break;
} while (!io_napi_busy_loop_should_end(iowq, start_time));
}
static void io_napi_blocking_busy_loop(struct list_head *napi_list,
struct io_wait_queue *iowq)
{
if (!list_is_singular(napi_list))
io_napi_multi_busy_loop(napi_list, iowq);
if (list_is_singular(napi_list)) {
struct io_napi_ht_entry *ne;
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);
}
}
I think that is still much easier to read rather than all of these
combined statements. What do you think?
> +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);
> +}
First line too long, split it into two. Did you look into the locking
side like I mentioned in the previous review?
> +/*
> + * 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);
> + }
> +}
I'd make this:
void io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
struct list_head *napi_list, struct timespec64 *ts)
{
if (list_empty(napi_list))
return;
__io_napi_adjust_timeout(ctx, iowq, napi_list, ts);
}
and put it in the header. That leaves the fast path mostly untouched,
rather than forcing a function call here.
Also note the alignment of the variables in the function header, this
applies in a bunch of spots. And just drop the busy_loop thing from the
naming where it isn't strictly needed, lots of these function names are
really long.
> +/*
> + * 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);
> + }
> +}
Might need a comment here on why SQPOLL needs something extra?
> +/*
> + * 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);
> +}
This should go above the users in this file. Maybe others are like that
too, didn't check.
> +++ 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)
This looks way better!
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread* Re: [PATCH v8 4/7] io-uring: add napi busy poll support
2023-02-10 0:00 ` Jens Axboe
@ 2023-02-15 17:22 ` Stefan Roesch
0 siblings, 0 replies; 13+ messages in thread
From: Stefan Roesch @ 2023-02-15 17:22 UTC (permalink / raw)
To: Jens Axboe
Cc: io-uring, kernel-team, ammarfaizi2, Olivier Langlois,
Jakub Kicinski
Jens Axboe <[email protected]> writes:
> I'd fold 2+3 into this patch again, having them standalone don't really
> make a lot of sense without this patch.
>
> This looks a lot better and gets rid of the ifdef infestation! Minor
> comments below, mostly just because I think we should fold those 3
> patches anyway.
>
>> 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);
>> +}
>
> I'd probably get rid of this helper, to be honest.
>
I removed the helper in the next version.
>> +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);
>> + }
>
> Looks like 8 spaces before that BUSY_POLL_BUDGET, should be a tab?
>
Fixed.
>> +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);
>> + }
>> +}
>
> This does look a LOT better! I do think a helper for the first while
> would make sense, and then have a comment in that helper on what this is
> doing exactly.
>
> static void io_napi_multi_busy_loop(napi_list, iowq)
> {
> unsigned long start_time = busy_loop_current_time();
>
> do {
> if (list_is_singular(napi_list))
> break;
> if (!io_napi_busy_loop(napi_list, iowq->napi_prefer_busy_poll))
> break;
> } while (!io_napi_busy_loop_should_end(iowq, start_time));
> }
>
> static void io_napi_blocking_busy_loop(struct list_head *napi_list,
> struct io_wait_queue *iowq)
> {
> if (!list_is_singular(napi_list))
> io_napi_multi_busy_loop(napi_list, iowq);
> if (list_is_singular(napi_list)) {
> struct io_napi_ht_entry *ne;
>
> 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);
> }
> }
>
> I think that is still much easier to read rather than all of these
> combined statements. What do you think?
>
I personally prefer the while loop, but I made the above change in the
next version.
>> +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);
>> +}
>
> First line too long, split it into two. Did you look into the locking
> side like I mentioned in the previous review?
>
Fixed.
I looked at the locking, however not all code path where io_napi_add is
called guarantee that the io-uring lock is taken.
>> +/*
>> + * 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);
>> + }
>> +}
>
> I'd make this:
>
> void io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
> struct list_head *napi_list, struct timespec64 *ts)
> {
> if (list_empty(napi_list))
> return;
>
> __io_napi_adjust_timeout(ctx, iowq, napi_list, ts);
> }
>
> and put it in the header. That leaves the fast path mostly untouched,
> rather than forcing a function call here.
>
> Also note the alignment of the variables in the function header, this
> applies in a bunch of spots. And just drop the busy_loop thing from the
> naming where it isn't strictly needed, lots of these function names are
> really long.
>
>
Unfortunately the function doesn't get inlined. I added a new helper
io_napi to avoid this case.
>> +/*
>> + * 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);
>> + }
>> +}
>
> Might need a comment here on why SQPOLL needs something extra?
>
I added a comment.
>> +/*
>> + * 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);
>> +}
>
> This should go above the users in this file. Maybe others are like that
> too, didn't check.
>
There are no users in this file.
>> +++ 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)
>
> This looks way better!
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH v8 5/7] io-uring: add sqpoll support for napi busy poll
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
` (3 preceding siblings ...)
2023-02-09 23:01 ` [PATCH v8 4/7] io-uring: add napi busy poll support Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-10 0:14 ` Jens Axboe
2023-02-09 23:01 ` [PATCH v8 6/7] io_uring: add api to set / get napi configuration Stefan Roesch
2023-02-09 23:01 ` [PATCH v8 7/7] " Stefan Roesch
6 siblings, 1 reply; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team; +Cc: shr, axboe, ammarfaizi2, Olivier Langlois
This adds the sqpoll support to the io-uring napi.
Signed-off-by: Stefan Roesch <[email protected]>
Suggested-by: Olivier Langlois <[email protected]>
---
io_uring/napi.c | 25 +++++++++++++++++++++++++
io_uring/napi.h | 2 ++
io_uring/sqpoll.c | 4 ++++
3 files changed, 31 insertions(+)
diff --git a/io_uring/napi.c b/io_uring/napi.c
index c9e2afae382d..038957b46a0e 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -278,4 +278,29 @@ void io_napi_end_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
io_napi_merge_lists(ctx, napi_list);
}
+/*
+ * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
+ * @ctx: pointer to io-uring context structure
+ * @napi_list: pointer to head of napi list
+ *
+ * Splice of the napi list and execute the napi busy poll loop.
+ */
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx, struct list_head *napi_list)
+{
+ int ret = 0;
+
+ spin_lock(&ctx->napi_lock);
+ list_splice_init(&ctx->napi_list, napi_list);
+ spin_unlock(&ctx->napi_lock);
+
+ if (!list_empty(napi_list) &&
+ READ_ONCE(ctx->napi_busy_poll_to) > 0 &&
+ io_napi_busy_loop(napi_list, ctx->napi_prefer_busy_poll)) {
+ io_napi_merge_lists(ctx, napi_list);
+ ret = 1;
+ }
+
+ return ret;
+}
+
#endif
diff --git a/io_uring/napi.h b/io_uring/napi.h
index 0672592cfb79..23a6df32805f 100644
--- a/io_uring/napi.h
+++ b/io_uring/napi.h
@@ -23,6 +23,7 @@ void io_napi_adjust_busy_loop_timeout(struct io_ring_ctx *ctx,
struct timespec64 *ts);
void io_napi_end_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
struct list_head *napi_list);
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx, struct list_head *napi_list);
#else
@@ -43,6 +44,7 @@ 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)
+#define io_napi_sqpoll_busy_poll(ctx, napi_list) (0)
#endif
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 0119d3f1a556..90fdbd87434a 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -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
@@ -168,6 +169,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
{
unsigned int to_submit;
int ret = 0;
+ NAPI_LIST_HEAD(local_napi_list);
to_submit = io_sqring_entries(ctx);
/* if we're handling multiple rings, cap submit size for fairness */
@@ -193,6 +195,8 @@ 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);
+ ret += io_napi_sqpoll_busy_poll(ctx, &local_napi_list);
+
if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
wake_up(&ctx->sqo_sq_wait);
if (creds)
--
2.30.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [PATCH v8 5/7] io-uring: add sqpoll support for napi busy poll
2023-02-09 23:01 ` [PATCH v8 5/7] io-uring: add sqpoll support for napi busy poll Stefan Roesch
@ 2023-02-10 0:14 ` Jens Axboe
0 siblings, 0 replies; 13+ messages in thread
From: Jens Axboe @ 2023-02-10 0:14 UTC (permalink / raw)
To: Stefan Roesch, io-uring, kernel-team; +Cc: ammarfaizi2, Olivier Langlois
On 2/9/23 4:01?PM, Stefan Roesch wrote:
> This adds the sqpoll support to the io-uring napi.
This should also have a bit more of an explanation of _why_ this
is needed and being done.
> diff --git a/io_uring/napi.c b/io_uring/napi.c
> index c9e2afae382d..038957b46a0e 100644
> --- a/io_uring/napi.c
> +++ b/io_uring/napi.c
> @@ -278,4 +278,29 @@ void io_napi_end_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
> io_napi_merge_lists(ctx, napi_list);
> }
>
> +/*
> + * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
> + * @ctx: pointer to io-uring context structure
> + * @napi_list: pointer to head of napi list
> + *
> + * Splice of the napi list and execute the napi busy poll loop.
> + */
> +int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx, struct list_head *napi_list)
> +{
> + int ret = 0;
> +
> + spin_lock(&ctx->napi_lock);
> + list_splice_init(&ctx->napi_list, napi_list);
> + spin_unlock(&ctx->napi_lock);
> +
> + if (!list_empty(napi_list) &&
> + READ_ONCE(ctx->napi_busy_poll_to) > 0 &&
> + io_napi_busy_loop(napi_list, ctx->napi_prefer_busy_poll)) {
> + io_napi_merge_lists(ctx, napi_list);
> + ret = 1;
> + }
> +
> + return ret;
Should 'ret' be a bool and the return value of the function too?
> diff --git a/io_uring/napi.h b/io_uring/napi.h
> index 0672592cfb79..23a6df32805f 100644
> --- a/io_uring/napi.h
> +++ b/io_uring/napi.h
> @@ -23,6 +23,7 @@ void io_napi_adjust_busy_loop_timeout(struct io_ring_ctx *ctx,
> struct timespec64 *ts);
> void io_napi_end_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
> struct list_head *napi_list);
> +int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx, struct list_head *napi_list);
>
> #else
>
> @@ -43,6 +44,7 @@ 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)
> +#define io_napi_sqpoll_busy_poll(ctx, napi_list) (0)
This should be:
#define io_napi_sqpoll_busy_poll(ctx, napi_list)
{(
)}
do { } while (0)
>
> #endif
>
> diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
> index 0119d3f1a556..90fdbd87434a 100644
> --- a/io_uring/sqpoll.c
> +++ b/io_uring/sqpoll.c
> @@ -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
> @@ -168,6 +169,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
> {
> unsigned int to_submit;
> int ret = 0;
> + NAPI_LIST_HEAD(local_napi_list);
In general, keep these roughly in inverse xmas tree.
> to_submit = io_sqring_entries(ctx);
> /* if we're handling multiple rings, cap submit size for fairness */
> @@ -193,6 +195,8 @@ 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);
>
> + ret += io_napi_sqpoll_busy_poll(ctx, &local_napi_list);
> +
> if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
> wake_up(&ctx->sqo_sq_wait);
> if (creds)
Not clear to me what this ret += ... does here? We're currently
returning number of sqes submitted. Maybe this is fine and just means
'we did some work', but if so, should add a comment for that.
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH v8 6/7] io_uring: add api to set / get napi configuration.
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
` (4 preceding siblings ...)
2023-02-09 23:01 ` [PATCH v8 5/7] io-uring: add sqpoll support for napi busy poll Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-10 0:02 ` Jens Axboe
2023-02-09 23:01 ` [PATCH v8 7/7] " Stefan Roesch
6 siblings, 1 reply; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team; +Cc: shr, axboe, ammarfaizi2, Jakub Kicinski
This adds an api to register the busy poll timeout from liburing. To be
able to use this functionality, the corresponding liburing patch is needed.
Signed-off-by: Stefan Roesch <[email protected]>
Acked-by: Jakub Kicinski <[email protected]>
---
include/uapi/linux/io_uring.h | 11 +++++++++++
io_uring/io_uring.c | 9 +++++++++
io_uring/napi.c | 35 +++++++++++++++++++++++++++++++++++
io_uring/napi.h | 13 +++++++++++++
4 files changed, 68 insertions(+)
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 636a4c2c1294..fe25ae92744d 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -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
*/
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 7074379a9bd0..be501e1024bc 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -4283,6 +4283,15 @@ 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;
diff --git a/io_uring/napi.c b/io_uring/napi.c
index 038957b46a0e..34513b284234 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -199,6 +199,41 @@ void io_napi_free(struct io_ring_ctx *ctx)
spin_unlock(&ctx->napi_lock);
}
+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,
+ };
+ struct io_uring_napi napi;
+
+ if (copy_from_user(&napi, arg, sizeof(napi)))
+ return -EFAULT;
+ if (napi.pad || napi.resv)
+ return -EINVAL;
+
+ WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+
+ if (copy_to_user(arg, &curr, sizeof(curr)))
+ return -EFAULT;
+
+ return 0;
+}
+
+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,
+ };
+
+ if (arg) {
+ if (copy_to_user(arg, &curr, sizeof(curr)))
+ return -EFAULT;
+ }
+
+ WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+ return 0;
+}
+
/*
* io_napi_add() - Add napi id to the busy poll list
* @req: pointer to io_kiocb request
diff --git a/io_uring/napi.h b/io_uring/napi.h
index 23a6df32805f..a5abe433c3e7 100644
--- a/io_uring/napi.h
+++ b/io_uring/napi.h
@@ -14,6 +14,9 @@
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_kiocb *req);
void io_napi_setup_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
@@ -37,6 +40,16 @@ 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 void io_napi_add(struct io_kiocb *req)
{
}
--
2.30.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 7/7] io_uring: add api to set / get napi configuration.
2023-02-09 23:01 [PATCH v8 0/7] io_uring: add napi busy polling support Stefan Roesch
` (5 preceding siblings ...)
2023-02-09 23:01 ` [PATCH v8 6/7] io_uring: add api to set / get napi configuration Stefan Roesch
@ 2023-02-09 23:01 ` Stefan Roesch
2023-02-10 0:02 ` Jens Axboe
6 siblings, 1 reply; 13+ messages in thread
From: Stefan Roesch @ 2023-02-09 23:01 UTC (permalink / raw)
To: io-uring, kernel-team; +Cc: shr, axboe, ammarfaizi2, Jakub Kicinski
This adds an api to register and unregister the napi prefer busy poll
setting from liburing. To be able to use this functionality, the
corresponding liburing patch is needed.
Signed-off-by: Stefan Roesch <[email protected]>
Acked-by: Jakub Kicinski <[email protected]>
---
include/uapi/linux/io_uring.h | 3 ++-
io_uring/napi.c | 6 +++++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index fe25ae92744d..e14f31a4b10c 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -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;
};
diff --git a/io_uring/napi.c b/io_uring/napi.c
index 34513b284234..a1605bef2bbc 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -203,15 +203,17 @@ 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;
@@ -223,6 +225,7 @@ 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) {
@@ -231,6 +234,7 @@ 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;
}
--
2.30.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [PATCH v8 7/7] io_uring: add api to set / get napi configuration.
2023-02-09 23:01 ` [PATCH v8 7/7] " Stefan Roesch
@ 2023-02-10 0:02 ` Jens Axboe
0 siblings, 0 replies; 13+ messages in thread
From: Jens Axboe @ 2023-02-10 0:02 UTC (permalink / raw)
To: Stefan Roesch, io-uring, kernel-team; +Cc: ammarfaizi2, Jakub Kicinski
On 2/9/23 4:01 PM, Stefan Roesch wrote:
> This adds an api to register and unregister the napi prefer busy poll
> setting from liburing. To be able to use this functionality, the
> corresponding liburing patch is needed.
Same comment as for patch 6, and additionally the subject line here
is a dupe of the previous patch while this is not what this patch
does at all. It adds support for setting 'prefer_busy_poll', that
is what should be mentioned in the subject and explained in this
commit message.
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread