Merge tag 'for-6.9/io_uring-20240310' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:

 - Make running of task_work internal loops more fair, and unify how the
   different methods deal with them (me)

 - Support for per-ring NAPI. The two minor networking patches are in a
   shared branch with netdev (Stefan)

 - Add support for truncate (Tony)

 - Export SQPOLL utilization stats (Xiaobing)

 - Multishot fixes (Pavel)

 - Fix for a race in manipulating the request flags via poll (Pavel)

 - Cleanup the multishot checking by making it generic, moving it out of
   opcode handlers (Pavel)

 - Various tweaks and cleanups (me, Kunwu, Alexander)

* tag 'for-6.9/io_uring-20240310' of git://git.kernel.dk/linux: (53 commits)
  io_uring: Fix sqpoll utilization check racing with dying sqpoll
  io_uring/net: dedup io_recv_finish req completion
  io_uring: refactor DEFER_TASKRUN multishot checks
  io_uring: fix mshot io-wq checks
  io_uring/net: add io_req_msg_cleanup() helper
  io_uring/net: simplify msghd->msg_inq checking
  io_uring/kbuf: rename REQ_F_PARTIAL_IO to REQ_F_BL_NO_RECYCLE
  io_uring/net: remove dependency on REQ_F_PARTIAL_IO for sr->done_io
  io_uring/net: correctly handle multishot recvmsg retry setup
  io_uring/net: clear REQ_F_BL_EMPTY in the multishot retry handler
  io_uring: fix io_queue_proc modifying req->flags
  io_uring: fix mshot read defer taskrun cqe posting
  io_uring/net: fix overflow check in io_recvmsg_mshot_prep()
  io_uring/net: correct the type of variable
  io_uring/sqpoll: statistics of the true utilization of sq threads
  io_uring/net: move recv/recvmsg flags out of retry loop
  io_uring/kbuf: flag request if buffer pool is empty after buffer pick
  io_uring/net: improve the usercopy for sendmsg/recvmsg
  io_uring/net: move receive multishot out of the generic msghdr path
  io_uring/net: unify how recvmsg and sendmsg copy in the msghdr
  ...

1 files changed, 43 insertions, 14 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 76e6438f4858e2..a892f72651890d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6177,8 +6177,13 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
-			   u16 budget)
+enum {
+	NAPI_F_PREFER_BUSY_POLL	= 1,
+	NAPI_F_END_ON_RESCHED	= 2,
+};
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
+			   unsigned flags, u16 budget)
 {
 	bool skip_schedule = false;
 	unsigned long timeout;
@@ -6198,7 +6203,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 
 	local_bh_disable();
 
-	if (prefer_busy_poll) {
+	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
 		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
 		if (napi->defer_hard_irqs_count && timeout) {
@@ -6222,23 +6227,23 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 	local_bh_enable();
 }
 
-void napi_busy_loop(unsigned int napi_id,
-		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+static void __napi_busy_loop(unsigned int napi_id,
+		      bool (*loop_end)(void *, unsigned long),
+		      void *loop_end_arg, unsigned flags, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
 
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 restart:
 	napi_poll = NULL;
 
-	rcu_read_lock();
-
 	napi = napi_by_id(napi_id);
 	if (!napi)
-		goto out;
+		return;
 
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_disable();
@@ -6254,14 +6259,14 @@ restart:
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
 				   NAPIF_STATE_IN_BUSY_POLL)) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
 					  NAPIF_STATE_SCHED) != val) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
@@ -6281,12 +6286,15 @@ count:
 			break;
 
 		if (unlikely(need_resched())) {
+			if (flags & NAPI_F_END_ON_RESCHED)
+				break;
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+				busy_poll_stop(napi, have_poll_lock, flags, budget);
 			if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 				preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
+			rcu_read_lock();
 			if (loop_end(loop_end_arg, start_time))
 				return;
 			goto restart;
@@ -6294,10 +6302,31 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+		busy_poll_stop(napi, have_poll_lock, flags, budget);
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_enable();
-out:
+}
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = NAPI_F_END_ON_RESCHED;
+
+	if (prefer_busy_poll)
+		flags |= NAPI_F_PREFER_BUSY_POLL;
+
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
+}
+
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
+
+	rcu_read_lock();
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(napi_busy_loop);