Merge tag 'io_uring-7.2-20260625' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring fixes from Jens Axboe:

 - Fix a file reference leak in the nop opcode when used with
   IOSQE_FIXED_FILE

 - Preserve the SQ array entries when resizing the ring via the register
   path

 - Preserve the partial result for an iopoll request rather than
   overwriting it

 - Don't audit log IORING_OP_RECV_ZC

 - Bound io_pin_pages() by the page array byte size in the memmap path

 - Follow-up cleanup to the task_work mpscq conversion, getting rid of
   the now-unnecessary tw_pending tracking for the !DEFER_TASKRUN path

 - Switch a system_unbound_wq user over to system_dfl_wq

* tag 'io_uring-7.2-20260625' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring/memmap: bound io_pin_pages() by page array byte size
  io_uring: Use system_dfl_wq instead of system_unbound_wq
  io_uring/register: preserve SQ array entries on resize
  io_uring, audit: don't log IORING_OP_RECV_ZC
  io_uring: get rid of tw_pending for !DEFER task work
  io_uring/rw: preserve partial result for iopoll
  io_uring/nop: fix file reference leak with IOSQE_FIXED_FILE

include/linux/io_uring_types.h

@@ -149,8 +149,6 @@ struct io_uring_task {
 
 	struct { /* task_work */
 		struct mpscq		task_list;
-		/* BIT(0) guards adding tw only once */
-		unsigned long		tw_pending;
 		struct callback_head	task_work;
 	} ____cacheline_aligned_in_smp;
 };

io_uring/memmap.c

@@ -53,7 +53,7 @@ struct page **io_pin_pages(unsigned long uaddr, unsigned long len, int *npages)
 	nr_pages = end - start;
 	if (WARN_ON_ONCE(!nr_pages))
 		return ERR_PTR(-EINVAL);
-	if (WARN_ON_ONCE(nr_pages > INT_MAX))
+	if (nr_pages > INT_MAX / sizeof(struct page *))
 		return ERR_PTR(-EOVERFLOW);
 
 	pages = kvmalloc_objs(struct page *, nr_pages, GFP_KERNEL_ACCOUNT);

io_uring/mpscq.h

@@ -122,4 +122,13 @@ static inline struct llist_node *mpscq_pop(struct mpscq *q,
 	return NULL;
 }
 
+/*
+ * Returns true if the most recent mpscq_pop() that returned a node also
+ * emptied the queue. Consumer must be serialized.
+ */
+static inline bool mpscq_pop_emptied(struct mpscq *q, struct llist_node *head)
+{
+	return head == &q->stub;
+}
+
 #endif /* IOU_MPSCQ_H */

io_uring/nop.c

@@ -40,6 +40,8 @@ int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		nop->fd = READ_ONCE(sqe->fd);
 	else
 		nop->fd = -1;
+	if (nop->flags & IORING_NOP_FIXED_FILE)
+		req->flags |= REQ_F_FIXED_FILE;
 	if (nop->flags & IORING_NOP_FIXED_BUFFER)
 		req->buf_index = READ_ONCE(sqe->buf_index);
 	if (nop->flags & IORING_NOP_CQE32) {
@@ -59,12 +61,10 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags)
 	int ret = nop->result;
 
 	if (nop->flags & IORING_NOP_FILE) {
-		if (nop->flags & IORING_NOP_FIXED_FILE) {
+		if (req->flags & REQ_F_FIXED_FILE)
 			req->file = io_file_get_fixed(req, nop->fd, issue_flags);
-			req->flags |= REQ_F_FIXED_FILE;
-		} else {
+		else
 			req->file = io_file_get_normal(req, nop->fd);
-		}
 		if (!req->file) {
 			ret = -EBADF;
 			goto done;

io_uring/opdef.c

@@ -520,6 +520,7 @@ const struct io_issue_def io_issue_defs[] = {
 #endif
 	},
 	[IORING_OP_RECV_ZC] = {
+		.audit_skip		= 1,
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.pollin			= 1,

io_uring/register.c

@@ -503,6 +503,7 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 	unsigned i, tail, old_head;
 	struct io_uring_params *p = &config.p;
 	struct io_rings_layout *rl = &config.layout;
+	u32 *o_sq_array, *n_sq_array = NULL;
 	int ret;
 
 	memset(&config, 0, sizeof(config));
@@ -589,6 +590,9 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 	ctx->rings = NULL;
 	o.sq_sqes = ctx->sq_sqes;
 	ctx->sq_sqes = NULL;
+	o_sq_array = ctx->sq_array;
+	if (!(ctx->flags & IORING_SETUP_NO_SQARRAY))
+		n_sq_array = (u32 *)((char *)n.rings + rl->sq_array_offset);
 
 	/*
 	 * Now copy SQ and CQ entries, if any. If either of the destination
@@ -599,20 +603,27 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 	if (tail - old_head > p->sq_entries)
 		goto overflow;
 	for (i = old_head; i < tail; i++) {
-		unsigned index, dst_mask, src_mask;
+		unsigned int dst, src;
 		size_t sq_size;
 
-		index = i;
-		sq_size = sizeof(struct io_uring_sqe);
-		src_mask = ctx->sq_entries - 1;
-		dst_mask = p->sq_entries - 1;
-		if (ctx->flags & IORING_SETUP_SQE128) {
-			index <<= 1;
-			sq_size <<= 1;
-			src_mask = (ctx->sq_entries << 1) - 1;
-			dst_mask = (p->sq_entries << 1) - 1;
+		dst = i & (p->sq_entries - 1);
+		src = i & (ctx->sq_entries - 1);
+		if (n_sq_array) {
+			src = READ_ONCE(o_sq_array[src]);
+			if (unlikely(src >= ctx->sq_entries)) {
+				WRITE_ONCE(n_sq_array[dst], UINT_MAX);
+				continue;
+			}
+			WRITE_ONCE(n_sq_array[dst], dst);
 		}
-		memcpy(&n.sq_sqes[index & dst_mask], &o.sq_sqes[index & src_mask], sq_size);
+
+		sq_size = sizeof(struct io_uring_sqe);
+		if (ctx->flags & IORING_SETUP_SQE128) {
+			dst <<= 1;
+			src <<= 1;
+			sq_size <<= 1;
+		}
+		memcpy(&n.sq_sqes[dst], &o.sq_sqes[src], sq_size);
 	}
 	WRITE_ONCE(n.rings->sq.head, old_head);
 	WRITE_ONCE(n.rings->sq.tail, tail);
@@ -655,8 +666,8 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg)
 	WRITE_ONCE(n.rings->cq_overflow, READ_ONCE(o.rings->cq_overflow));
 
 	/* all done, store old pointers and assign new ones */
-	if (!(ctx->flags & IORING_SETUP_NO_SQARRAY))
-		ctx->sq_array = (u32 *)((char *)n.rings + rl->sq_array_offset);
+	if (n_sq_array)
+		ctx->sq_array = n_sq_array;
 
 	ctx->sq_entries = p->sq_entries;
 	ctx->cq_entries = p->cq_entries;

io_uring/rw.c

@@ -601,15 +601,15 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 {
 	struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
 	struct io_kiocb *req = cmd_to_io_kiocb(rw);
+	int final_res = io_fixup_rw_res(req, res);
 
 	if (kiocb->ki_flags & IOCB_WRITE)
 		io_req_end_write(req);
-	if (unlikely(res != req->cqe.res)) {
-		if (res == -EAGAIN && io_rw_should_reissue(req))
-			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
-		else
-			req->cqe.res = res;
-	}
+
+	if (res == -EAGAIN && io_rw_should_reissue(req))
+		req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
+	else if (unlikely(final_res != req->cqe.res))
+		req->cqe.res = final_res;
 
 	/* order with io_iopoll_complete() checking ->iopoll_completed */
 	smp_store_release(&req->iopoll_completed, 1);

io_uring/tw.c

@@ -34,10 +34,6 @@ void io_tctx_fallback_work(struct work_struct *work)
 						  fallback_work);
 	unsigned int count = 0;
 
-	/* see tctx_task_work() - a set bit must always have a run coming */
-	clear_bit(0, &tctx->tw_pending);
-	smp_mb__after_atomic();
-
 	/*
 	 * Run the entries directly. We're in PF_KTHRED context, hence
 	 * io_should_terminate_tw() is true and they will be marked as
@@ -55,7 +51,7 @@ static void io_fallback_tw(struct io_uring_task *tctx)
 	 * the queued work) stay around until the drain has run.
 	 */
 	get_task_struct(tctx->task);
-	if (!queue_work(system_unbound_wq, &tctx->fallback_work))
+	if (!queue_work(system_dfl_wq, &tctx->fallback_work))
 		put_task_struct(tctx->task);
 }
 
@@ -101,6 +97,13 @@ void tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries,
 				io_poll_task_func, io_req_rw_complete,
 				(struct io_tw_req){req}, ts);
 		(*count)++;
+		/*
+		 * Break if most recent pop emptied the queue. This helps
+		 * bound task_work run, and also protects the regular
+		 * task_work addition.
+		 */
+		if (mpscq_pop_emptied(&tctx->task_list, tctx->task_head))
+			break;
 		if (unlikely(need_resched())) {
 			ctx_flush_and_put(ctx, ts);
 			ctx = NULL;
@@ -127,8 +130,6 @@ void tctx_task_work(struct callback_head *cb)
 	unsigned int count = 0;
 
 	tctx = container_of(cb, struct io_uring_task, task_work);
-	clear_bit(0, &tctx->tw_pending);
-	smp_mb__after_atomic();
 	tctx_task_work_run(tctx, UINT_MAX, &count);
 }
 
@@ -206,7 +207,7 @@ void io_req_normal_work_add(struct io_kiocb *req)
 	struct io_uring_task *tctx = req->tctx;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	/* task_work already pending, we're done */
+	/* tw run already pending, nothing else to do */
 	if (!mpscq_push(&tctx->task_list, &req->io_task_work.node))
 		return;
 
@@ -223,10 +224,6 @@ void io_req_normal_work_add(struct io_kiocb *req)
 		return;
 	}
 
-	/* task_work must only be added once */
-	if (test_and_set_bit(0, &tctx->tw_pending))
-		return;
-
 	if (likely(!task_work_add(tctx->task, &tctx->task_work, ctx->notify_method)))
 		return;