Merge tag 'io_uring-7.1-20260430' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring fixes from Jens Axboe:

 - Remove dead struct io_buffer_list member

 - Fix for incrementally consumed buffers with recvmsg multishot, which
   requires a minimum value left in a buffer for any receive for the
   headers. If there's still a bit of buffer left but it's smaller than
   that value, then userspace will see a spurious -EFAULT returned in
   the CQE

 - Locking fix for the DEFER_TASKRUN retry list, which otherwise could
   race with fallback cancelations. If the task is exiting with
   task_work left in both the normal and retry list AND the exit cleanup
   races with the task running task work, then entries could either be
   doubly completed or lost

 - Cap NAPI busy poll timeout to something sane, to avoid syzbot running
   into excessive polling and triggering warnings around that

* tag 'io_uring-7.1-20260430' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring/tw: serialize ctx->retry_llist with ->uring_lock
  io_uring/napi: cap busy_poll_to 10 msec
  io_uring/kbuf: support min length left for incremental buffers
  io_uring/kbuf: kill dead struct io_buffer_list 'nr_entries' member

5 files changed, 29 insertions, 5 deletions

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 17ac1b785440..909fb7aea638 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -905,7 +905,8 @@ struct io_uring_buf_reg {
 	__u32	ring_entries;
 	__u16	bgid;
 	__u16	flags;
-	__u64	resv[3];
+	__u32	min_left;
+	__u32	resv[5];
 };
 
 /* argument for IORING_REGISTER_PBUF_STATUS */
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 8da2ff798170..63061aa1cab9 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -47,7 +47,7 @@ static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
 		this_len = min_t(u32, len, buf_len);
 		buf_len -= this_len;
 		/* Stop looping for invalid buffer length of 0 */
-		if (buf_len || !this_len) {
+		if (buf_len > bl->min_left_sub_one || !this_len) {
 			WRITE_ONCE(buf->addr, READ_ONCE(buf->addr) + this_len);
 			WRITE_ONCE(buf->len, buf_len);
 			return false;
@@ -637,6 +637,10 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	if (reg.ring_entries >= 65536)
 		return -EINVAL;
 
+	/* minimum left byte count is a property of incremental buffers */
+	if (!(reg.flags & IOU_PBUF_RING_INC) && reg.min_left)
+		return -EINVAL;
+
 	bl = io_buffer_get_list(ctx, reg.bgid);
 	if (bl) {
 		/* if mapped buffer ring OR classic exists, don't allow */
@@ -680,10 +684,11 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	}
 #endif
 
-	bl->nr_entries = reg.ring_entries;
 	bl->mask = reg.ring_entries - 1;
 	bl->flags |= IOBL_BUF_RING;
 	bl->buf_ring = br;
+	if (reg.min_left)
+		bl->min_left_sub_one = reg.min_left - 1;
 	if (reg.flags & IOU_PBUF_RING_INC)
 		bl->flags |= IOBL_INC;
 	ret = io_buffer_add_list(ctx, bl, reg.bgid);
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index bf15e26520d3..401773e1ef80 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -27,12 +27,18 @@ struct io_buffer_list {
 	__u16 bgid;
 
 	/* below is for ring provided buffers */
-	__u16 nr_entries;
 	__u16 head;
 	__u16 mask;
 
 	__u16 flags;
 
+	/*
+	 * minimum required amount to be left to reuse an incrementally
+	 * consumed buffer. If less than this is left at consumption time,
+	 * buffer is done and head is incremented to the next buffer.
+	 */
+	__u32 min_left_sub_one;
+
 	struct io_mapped_region region;
 };
 
diff --git a/io_uring/napi.c b/io_uring/napi.c
index 4a10de03e426..8d68366a4b90 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -276,6 +276,8 @@ static int io_napi_register_napi(struct io_ring_ctx *ctx,
 	/* clean the napi list for new settings */
 	io_napi_free(ctx);
 	WRITE_ONCE(ctx->napi_track_mode, napi->op_param);
+	/* cap NAPI at 10 msec of spin time */
+	napi->busy_poll_to = min(10000, napi->busy_poll_to);
 	WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC);
 	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll);
 	return 0;
diff --git a/io_uring/tw.c b/io_uring/tw.c
index fdff81eebc95..023d5e6bc491 100644
--- a/io_uring/tw.c
+++ b/io_uring/tw.c
@@ -273,8 +273,18 @@ void io_req_task_work_add_remote(struct io_kiocb *req, unsigned flags)
 
 void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 {
-	struct llist_node *node = llist_del_all(&ctx->work_llist);
+	struct llist_node *node;
 
+	/*
+	 * Running the work items may utilize ->retry_llist as a means
+	 * for capping the number of task_work entries run at the same
+	 * time. But that list can potentially race with moving the work
+	 * from here, if the task is exiting. As any normal task_work
+	 * running holds ->uring_lock already, just guard this slow path
+	 * with ->uring_lock to avoid racing on ->retry_llist.
+	 */
+	guard(mutex)(&ctx->uring_lock);
+	node = llist_del_all(&ctx->work_llist);
 	__io_fallback_tw(node, false);
 	node = llist_del_all(&ctx->retry_llist);
 	__io_fallback_tw(node, false);