Merge tag 'for-6.12/io_uring-20240922' of git://git.kernel.dk/linux

Pull more io_uring updates from Jens Axboe:
 "Mostly just a set of fixes in here, or little changes that didn't get
  included in the initial pull request. This contains:

   - Move the SQPOLL napi polling outside the submission lock (Olivier)

   - Rename of the "copy buffers" API that got added in the 6.12 merge
     window. There's really no copying going on, it's just referencing
     the buffers. After a bit of consideration, decided that it was
     better to simply rename this to avoid potential confusion (me)

   - Shrink struct io_mapped_ubuf from 48 to 32 bytes, by changing it to
     start + len tracking rather than having start / end in there, and
     by removing the caching of folio_mask when we can just calculate it
     from folio_shift when we need it (me)

   - Fixes for the SQPOLL affinity checking (me, Felix)

   - Fix for how cqring waiting checks for the presence of task_work.
     Just check it directly rather than check for a specific
     notification mechanism (me)

   - Tweak to how request linking is represented in tracing (me)

   - Fix a syzbot report that deliberately sets up a huge list of
     overflow entries, and then hits rcu stalls when flushing this list.
     Just check for the need to preempt, and drop/reacquire locks in the
     loop. There's no state maintained over the loop itself, and each
     entry is yanked from head-of-list (me)"

* tag 'for-6.12/io_uring-20240922' of git://git.kernel.dk/linux:
  io_uring: check if we need to reschedule during overflow flush
  io_uring: improve request linking trace
  io_uring: check for presence of task_work rather than TIF_NOTIFY_SIGNAL
  io_uring/sqpoll: do the napi busy poll outside the submission block
  io_uring: clean up a type in io_uring_register_get_file()
  io_uring/sqpoll: do not put cpumask on stack
  io_uring/sqpoll: retain test for whether the CPU is valid
  io_uring/rsrc: change ubuf->ubuf_end to length tracking
  io_uring/rsrc: get rid of io_mapped_ubuf->folio_mask
  io_uring: rename "copy buffers" to "clone buffers"

include/uapi/linux/io_uring.h

@@ -609,8 +609,8 @@ enum io_uring_register_op {
 
 	IORING_REGISTER_CLOCK			= 29,
 
-	/* copy registered buffers from source ring to current ring */
-	IORING_REGISTER_COPY_BUFFERS		= 30,
+	/* clone registered buffers from source ring to current ring */
+	IORING_REGISTER_CLONE_BUFFERS		= 30,
 
 	/* this goes last */
 	IORING_REGISTER_LAST,
@@ -701,7 +701,7 @@ enum {
 	IORING_REGISTER_SRC_REGISTERED = 1,
 };
 
-struct io_uring_copy_buffers {
+struct io_uring_clone_buffers {
 	__u32	src_fd;
 	__u32	flags;
 	__u32	pad[6];

io_uring/fdinfo.c

@@ -177,9 +177,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 	seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
 	for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
 		struct io_mapped_ubuf *buf = ctx->user_bufs[i];
-		unsigned int len = buf->ubuf_end - buf->ubuf;
 
-		seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len);
+		seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, buf->len);
 	}
 	if (has_lock && !xa_empty(&ctx->personalities)) {
 		unsigned long index;

io_uring/io_uring.c

@@ -635,6 +635,21 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying)
 		}
 		list_del(&ocqe->list);
 		kfree(ocqe);
+
+		/*
+		 * For silly syzbot cases that deliberately overflow by huge
+		 * amounts, check if we need to resched and drop and
+		 * reacquire the locks if so. Nothing real would ever hit this.
+		 * Ideally we'd have a non-posting unlock for this, but hard
+		 * to care for a non-real case.
+		 */
+		if (need_resched()) {
+			io_cq_unlock_post(ctx);
+			mutex_unlock(&ctx->uring_lock);
+			cond_resched();
+			mutex_lock(&ctx->uring_lock);
+			io_cq_lock(ctx);
+		}
 	}
 
 	if (list_empty(&ctx->cq_overflow_list)) {
@@ -2164,7 +2179,7 @@ static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	 * conditions are true (normal request), then just queue it.
 	 */
 	if (unlikely(link->head)) {
-		trace_io_uring_link(req, link->head);
+		trace_io_uring_link(req, link->last);
 		link->last->link = req;
 		link->last = req;
 
@@ -2472,7 +2487,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 		return 1;
 	if (unlikely(!llist_empty(&ctx->work_llist)))
 		return 1;
-	if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL)))
+	if (unlikely(task_work_pending(current)))
 		return 1;
 	if (unlikely(task_sigpending(current)))
 		return -EINTR;
@@ -2579,9 +2594,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 		 * If we got woken because of task_work being processed, run it
 		 * now rather than let the caller do another wait loop.
 		 */
-		io_run_task_work();
 		if (!llist_empty(&ctx->work_llist))
 			io_run_local_work(ctx, nr_wait);
+		io_run_task_work();
 
 		/*
 		 * Non-local task_work will be run on exit to userspace, but

io_uring/register.c

@@ -542,11 +542,11 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_clock(ctx, arg);
 		break;
-	case IORING_REGISTER_COPY_BUFFERS:
+	case IORING_REGISTER_CLONE_BUFFERS:
 		ret = -EINVAL;
 		if (!arg || nr_args != 1)
 			break;
-		ret = io_register_copy_buffers(ctx, arg);
+		ret = io_register_clone_buffers(ctx, arg);
 		break;
 	default:
 		ret = -EINVAL;
@@ -561,7 +561,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
  * true, then the registered index is used. Otherwise, the normal fd table.
  * Caller must call fput() on the returned file, unless it's an ERR_PTR.
  */
-struct file *io_uring_register_get_file(int fd, bool registered)
+struct file *io_uring_register_get_file(unsigned int fd, bool registered)
 {
 	struct file *file;
 

io_uring/register.h

@@ -4,6 +4,6 @@
 
 int io_eventfd_unregister(struct io_ring_ctx *ctx);
 int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id);
-struct file *io_uring_register_get_file(int fd, bool registered);
+struct file *io_uring_register_get_file(unsigned int fd, bool registered);
 
 #endif

io_uring/rsrc.c

@@ -38,7 +38,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 static const struct io_mapped_ubuf dummy_ubuf = {
 	/* set invalid range, so io_import_fixed() fails meeting it */
 	.ubuf = -1UL,
-	.ubuf_end = 0,
+	.len = UINT_MAX,
 };
 
 int __io_account_mem(struct user_struct *user, unsigned long nr_pages)
@@ -991,16 +991,13 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 	size = iov->iov_len;
 	/* store original address for later verification */
 	imu->ubuf = (unsigned long) iov->iov_base;
-	imu->ubuf_end = imu->ubuf + iov->iov_len;
+	imu->len = iov->iov_len;
 	imu->nr_bvecs = nr_pages;
 	imu->folio_shift = PAGE_SHIFT;
-	imu->folio_mask = PAGE_MASK;
-	if (coalesced) {
+	if (coalesced)
 		imu->folio_shift = data.folio_shift;
-		imu->folio_mask = ~((1UL << data.folio_shift) - 1);
-	}
 	refcount_set(&imu->refs, 1);
-	off = (unsigned long) iov->iov_base & ~imu->folio_mask;
+	off = (unsigned long) iov->iov_base & ((1UL << imu->folio_shift) - 1);
 	*pimu = imu;
 	ret = 0;
 
@@ -1100,7 +1097,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 	if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end)))
 		return -EFAULT;
 	/* not inside the mapped region */
-	if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end))
+	if (unlikely(buf_addr < imu->ubuf || buf_end > (imu->ubuf + imu->len)))
 		return -EFAULT;
 
 	/*
@@ -1143,14 +1140,14 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 			iter->bvec = bvec + seg_skip;
 			iter->nr_segs -= seg_skip;
 			iter->count -= bvec->bv_len + offset;
-			iter->iov_offset = offset & ~imu->folio_mask;
+			iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
 		}
 	}
 
 	return 0;
 }
 
-static int io_copy_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx)
+static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx)
 {
 	struct io_mapped_ubuf **user_bufs;
 	struct io_rsrc_data *data;
@@ -1214,9 +1211,9 @@ static int io_copy_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx)
  *
  * Since the memory is already accounted once, don't account it again.
  */
-int io_register_copy_buffers(struct io_ring_ctx *ctx, void __user *arg)
+int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 {
-	struct io_uring_copy_buffers buf;
+	struct io_uring_clone_buffers buf;
 	bool registered_src;
 	struct file *file;
 	int ret;
@@ -1234,7 +1231,7 @@ int io_register_copy_buffers(struct io_ring_ctx *ctx, void __user *arg)
 	file = io_uring_register_get_file(buf.src_fd, registered_src);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
-	ret = io_copy_buffers(ctx, file->private_data);
+	ret = io_clone_buffers(ctx, file->private_data);
 	if (!registered_src)
 		fput(file);
 	return ret;

io_uring/rsrc.h

@@ -42,12 +42,11 @@ struct io_rsrc_node {
 
 struct io_mapped_ubuf {
 	u64		ubuf;
-	u64		ubuf_end;
+	unsigned int	len;
 	unsigned int	nr_bvecs;
 	unsigned int    folio_shift;
-	unsigned long	acct_pages;
-	unsigned long   folio_mask;
 	refcount_t	refs;
+	unsigned long	acct_pages;
 	struct bio_vec	bvec[] __counted_by(nr_bvecs);
 };
 
@@ -68,7 +67,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 			   struct io_mapped_ubuf *imu,
 			   u64 buf_addr, size_t len);
 
-int io_register_copy_buffers(struct io_ring_ctx *ctx, void __user *arg);
+int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg);
 void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
 int io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
 int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,

io_uring/sqpoll.c

@@ -196,9 +196,6 @@ 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);
 
-		if (io_napi(ctx))
-			ret += io_napi_sqpoll_busy_poll(ctx);
-
 		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
 			wake_up(&ctx->sqo_sq_wait);
 		if (creds)
@@ -323,6 +320,10 @@ static int io_sq_thread(void *data)
 		if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE))
 			sqt_spin = true;
 
+		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+			if (io_napi(ctx))
+				io_napi_sqpoll_busy_poll(ctx);
+
 		if (sqt_spin || !time_after(jiffies, timeout)) {
 			if (sqt_spin) {
 				io_sq_update_worktime(sqd, &start);
@@ -461,13 +462,22 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
 			return 0;
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
-			struct cpumask allowed_mask;
+			cpumask_var_t allowed_mask;
 			int cpu = p->sq_thread_cpu;
 
 			ret = -EINVAL;
-			cpuset_cpus_allowed(current, &allowed_mask);
-			if (!cpumask_test_cpu(cpu, &allowed_mask))
+			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 				goto err_sqpoll;
+			ret = -ENOMEM;
+			if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
+				goto err_sqpoll;
+			ret = -EINVAL;
+			cpuset_cpus_allowed(current, allowed_mask);
+			if (!cpumask_test_cpu(cpu, allowed_mask)) {
+				free_cpumask_var(allowed_mask);
+				goto err_sqpoll;
+			}
+			free_cpumask_var(allowed_mask);
 			sqd->sq_cpu = cpu;
 		} else {
 			sqd->sq_cpu = -1;