Merge tag 'for-7.0/io_uring-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring updates from Jens Axboe:

 - Clean up the IORING_SETUP_R_DISABLED and submitter task checking,
   mostly just in preparation for relaxing the locking for SINGLE_ISSUER
   in the future.

 - Improve IOPOLL by using a doubly linked list to manage completions.

   Previously it was singly listed, which meant that to complete request
   N in the chain 0..N-1 had to have completed first. With a doubly
   linked list we can complete whatever request completes in that order,
   rather than need to wait for a consecutive range to be available.
   This reduces latencies.

 - Improve the restriction setup and checking. Mostly in preparation for
   adding further features on top of that. Coming in a separate pull
   request.

 - Split out task_work and wait handling into separate files. These are
   mostly nicely abstracted already, but still remained in the
   io_uring.c file which is on the larger side.

 - Use GFP_KERNEL_ACCOUNT in a few more spots, where appropriate.

 - Ensure even the idle io-wq worker exits if a task no longer has any
   rings open.

 - Add support for a non-circular submission queue.

   By default, the SQ ring keeps moving around, even if only a few
   entries are used for each submission. This can be wasteful in terms
   of cachelines.

   If IORING_SETUP_SQ_REWIND is set for the ring when created, each
   submission will start at offset 0 instead of where we last left off
   doing submissions.

 - Various little cleanups

* tag 'for-7.0/io_uring-20260206' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (30 commits)
  io_uring/kbuf: fix memory leak if io_buffer_add_list fails
  io_uring: Add SPDX id lines to remaining source files
  io_uring: allow io-wq workers to exit when unused
  io_uring/io-wq: add exit-on-idle state
  io_uring/net: don't continue send bundle if poll was required for retry
  io_uring/rsrc: use GFP_KERNEL_ACCOUNT consistently
  io_uring/futex: use GFP_KERNEL_ACCOUNT for futex data allocation
  io_uring/io-wq: handle !sysctl_hung_task_timeout_secs
  io_uring: fix bad indentation for setup flags if statement
  io_uring/rsrc: take unsigned index in io_rsrc_node_lookup()
  io_uring: introduce non-circular SQ
  io_uring: split out CQ waiting code into wait.c
  io_uring: split out task work code into tw.c
  io_uring/io-wq: don't trigger hung task for syzbot craziness
  io_uring: add IO_URING_EXIT_WAIT_MAX definition
  io_uring/sync: validate passed in offset
  io_uring/eventfd: remove unused ctx->evfd_last_cq_tail member
  io_uring/timeout: annotate data race in io_flush_timeouts()
  io_uring/uring_cmd: explicitly disallow cancelations for IOPOLL
  io_uring: fix IOPOLL with passthrough I/O
  ...

1 files changed, 48 insertions, 3 deletions

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 2fa7d3601edb..7ed04911f7b9 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -17,6 +17,7 @@
 #include <linux/task_work.h>
 #include <linux/audit.h>
 #include <linux/mmu_context.h>
+#include <linux/sched/sysctl.h>
 #include <uapi/linux/io_uring.h>
 
 #include "io-wq.h"
@@ -34,6 +35,7 @@ enum {
 
 enum {
 	IO_WQ_BIT_EXIT		= 0,	/* wq exiting */
+	IO_WQ_BIT_EXIT_ON_IDLE	= 1,	/* allow all workers to exit on idle */
 };
 
 enum {
@@ -706,9 +708,13 @@ static int io_wq_worker(void *data)
 		raw_spin_lock(&acct->workers_lock);
 		/*
 		 * Last sleep timed out. Exit if we're not the last worker,
-		 * or if someone modified our affinity.
+		 * or if someone modified our affinity. If wq is marked
+		 * idle-exit, drop the worker as well. This is used to avoid
+		 * keeping io-wq workers around for tasks that no longer have
+		 * any active io_uring instances.
 		 */
-		if (last_timeout && (exit_mask || acct->nr_workers > 1)) {
+		if ((last_timeout && (exit_mask || acct->nr_workers > 1)) ||
+		    test_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) {
 			acct->nr_workers--;
 			raw_spin_unlock(&acct->workers_lock);
 			__set_current_state(TASK_RUNNING);
@@ -963,6 +969,24 @@ static bool io_wq_worker_wake(struct io_worker *worker, void *data)
 	return false;
 }
 
+void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable)
+{
+	if (!wq->task)
+		return;
+
+	if (!enable) {
+		clear_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state);
+		return;
+	}
+
+	if (test_and_set_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state))
+		return;
+
+	rcu_read_lock();
+	io_wq_for_each_worker(wq, io_wq_worker_wake, NULL);
+	rcu_read_unlock();
+}
+
 static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq)
 {
 	do {
@@ -1313,6 +1337,8 @@ static void io_wq_cancel_tw_create(struct io_wq *wq)
 
 static void io_wq_exit_workers(struct io_wq *wq)
 {
+	unsigned long timeout, warn_timeout;
+
 	if (!wq->task)
 		return;
 
@@ -1322,7 +1348,26 @@ static void io_wq_exit_workers(struct io_wq *wq)
 	io_wq_for_each_worker(wq, io_wq_worker_wake, NULL);
 	rcu_read_unlock();
 	io_worker_ref_put(wq);
-	wait_for_completion(&wq->worker_done);
+
+	/*
+	 * Shut up hung task complaint, see for example
+	 *
+	 * https://lore.kernel.org/all/696fc9e7.a70a0220.111c58.0006.GAE@google.com/
+	 *
+	 * where completely overloading the system with tons of long running
+	 * io-wq items can easily trigger the hung task timeout. Only sleep
+	 * uninterruptibly for half that time, and warn if we exceeded end
+	 * up waiting more than IO_URING_EXIT_WAIT_MAX.
+	 */
+	timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+	if (!timeout)
+		timeout = MAX_SCHEDULE_TIMEOUT;
+	warn_timeout = jiffies + IO_URING_EXIT_WAIT_MAX;
+	do {
+		if (wait_for_completion_timeout(&wq->worker_done, timeout))
+			break;
+		WARN_ON_ONCE(time_after(jiffies, warn_timeout));
+	} while (1);
 
 	spin_lock_irq(&wq->hash->wait.lock);
 	list_del_init(&wq->wait.entry);