Merge tag 'io_uring-5.15-2021-09-17' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "Mostly fixes for regressions in this cycle, but also a few fixes that
  predate this release.

  The odd one out is a tweak to the direct files added in this release,
  where attempting to reuse a slot is allowed instead of needing an
  explicit removal of that slot first. It's a considerable improvement
  in usability to that API, hence I'm sending it for -rc2.

   - io-wq race fix and cleanup (Hao)

   - loop_rw_iter() type fix

   - SQPOLL max worker race fix

   - Allow poll arm for O_NONBLOCK files, fixing a case where it's
     impossible to properly use io_uring if you cannot modify the file
     flags

   - Allow direct open to simply reuse a slot, instead of needing it
     explicitly removed first (Pavel)

   - Fix a case where we missed signal mask restoring in cqring_wait, if
     we hit -EFAULT (Xiaoguang)"

* tag 'io_uring-5.15-2021-09-17' of git://git.kernel.dk/linux-block:
  io_uring: allow retry for O_NONBLOCK if async is supported
  io_uring: auto-removal for direct open/accept
  io_uring: fix missing sigmask restore in io_cqring_wait()
  io_uring: pin SQPOLL data before unlocking ring lock
  io-wq: provide IO_WQ_* constants for IORING_REGISTER_IOWQ_MAX_WORKERS arg items
  io-wq: fix potential race of acct->nr_workers
  io-wq: code clean of io_wqe_create_worker()
  io_uring: ensure symmetry in handling iter types in loop_rw_iter()

fs/io-wq.c

@@ -14,6 +14,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
 #include <linux/tracehook.h>
+#include <uapi/linux/io_uring.h>
 
 #include "io-wq.h"
 
@@ -176,7 +177,6 @@ static void io_worker_ref_put(struct io_wq *wq)
 static void io_worker_exit(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
-	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
 
 	if (refcount_dec_and_test(&worker->ref))
 		complete(&worker->ref_done);
@@ -186,7 +186,6 @@ static void io_worker_exit(struct io_worker *worker)
 	if (worker->flags & IO_WORKER_F_FREE)
 		hlist_nulls_del_rcu(&worker->nulls_node);
 	list_del_rcu(&worker->all_list);
-	acct->nr_workers--;
 	preempt_disable();
 	io_wqe_dec_running(worker);
 	worker->flags = 0;
@@ -246,8 +245,6 @@ static bool io_wqe_activate_free_worker(struct io_wqe *wqe,
  */
 static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
 {
-	bool do_create = false;
-
 	/*
 	 * Most likely an attempt to queue unbounded work on an io_wq that
 	 * wasn't setup with any unbounded workers.
@@ -256,18 +253,15 @@ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
 		pr_warn_once("io-wq is not configured for unbound workers");
 
 	raw_spin_lock(&wqe->lock);
-	if (acct->nr_workers < acct->max_workers) {
-		acct->nr_workers++;
-		do_create = true;
+	if (acct->nr_workers == acct->max_workers) {
+		raw_spin_unlock(&wqe->lock);
+		return true;
 	}
+	acct->nr_workers++;
 	raw_spin_unlock(&wqe->lock);
-	if (do_create) {
 	atomic_inc(&acct->nr_running);
 	atomic_inc(&wqe->wq->worker_refs);
 	return create_io_worker(wqe->wq, wqe, acct->index);
-	}
-
-	return true;
 }
 
 static void io_wqe_inc_running(struct io_worker *worker)
@@ -574,6 +568,7 @@ static int io_wqe_worker(void *data)
 		}
 		/* timed out, exit unless we're the last worker */
 		if (last_timeout && acct->nr_workers > 1) {
+			acct->nr_workers--;
 			raw_spin_unlock(&wqe->lock);
 			__set_current_state(TASK_RUNNING);
 			break;
@@ -1287,6 +1282,10 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count)
 {
 	int i, node, prev = 0;
 
+	BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND   != (int) IO_WQ_BOUND);
+	BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND);
+	BUILD_BUG_ON((int) IO_WQ_ACCT_NR      != 2);
+
 	for (i = 0; i < 2; i++) {
 		if (new_count[i] > task_rlimit(current, RLIMIT_NPROC))
 			new_count[i] = task_rlimit(current, RLIMIT_NPROC);

fs/io_uring.c

@@ -2843,7 +2843,8 @@ static bool io_file_supports_nowait(struct io_kiocb *req, int rw)
 	return __io_file_supports_nowait(req->file, rw);
 }
 
-static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      int rw)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct kiocb *kiocb = &req->rw.kiocb;
@@ -2865,8 +2866,13 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (unlikely(ret))
 		return ret;
 
-	/* don't allow async punt for O_NONBLOCK or RWF_NOWAIT */
-	if ((kiocb->ki_flags & IOCB_NOWAIT) || (file->f_flags & O_NONBLOCK))
+	/*
+	 * If the file is marked O_NONBLOCK, still allow retry for it if it
+	 * supports async. Otherwise it's impossible to use O_NONBLOCK files
+	 * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
+	 */
+	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw)))
 		req->flags |= REQ_F_NOWAIT;
 
 	ioprio = READ_ONCE(sqe->ioprio);
@@ -3263,12 +3269,15 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter)
 				ret = nr;
 			break;
 		}
+		if (!iov_iter_is_bvec(iter)) {
+			iov_iter_advance(iter, nr);
+		} else {
+			req->rw.len -= nr;
+			req->rw.addr += nr;
+		}
 		ret += nr;
 		if (nr != iovec.iov_len)
 			break;
-		req->rw.len -= nr;
-		req->rw.addr += nr;
-		iov_iter_advance(iter, nr);
 	}
 
 	return ret;
@@ -3346,7 +3355,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	if (unlikely(!(req->file->f_mode & FMODE_READ)))
 		return -EBADF;
-	return io_prep_rw(req, sqe);
+	return io_prep_rw(req, sqe, READ);
 }
 
 /*
@@ -3539,7 +3548,7 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
 		return -EBADF;
-	return io_prep_rw(req, sqe);
+	return io_prep_rw(req, sqe, WRITE);
 }
 
 static int io_write(struct io_kiocb *req, unsigned int issue_flags)
@@ -7515,6 +7524,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			break;
 	} while (1);
 
+	if (uts) {
+		struct timespec64 ts;
+
+		if (get_timespec64(&ts, uts))
+			return -EFAULT;
+		timeout = timespec64_to_jiffies(&ts);
+	}
+
 	if (sig) {
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
@@ -7528,14 +7545,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			return ret;
 	}
 
-	if (uts) {
-		struct timespec64 ts;
-
-		if (get_timespec64(&ts, uts))
-			return -EFAULT;
-		timeout = timespec64_to_jiffies(&ts);
-	}
-
 	init_waitqueue_func_entry(&iowq.wq, io_wake_function);
 	iowq.wq.private = current;
 	INIT_LIST_HEAD(&iowq.wq.entry);
@@ -8284,11 +8293,27 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
 #endif
 }
 
+static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
+				 struct io_rsrc_node *node, void *rsrc)
+{
+	struct io_rsrc_put *prsrc;
+
+	prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
+	if (!prsrc)
+		return -ENOMEM;
+
+	prsrc->tag = *io_get_tag_slot(data, idx);
+	prsrc->rsrc = rsrc;
+	list_add(&prsrc->list, &node->rsrc_list);
+	return 0;
+}
+
 static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
 				 unsigned int issue_flags, u32 slot_index)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+	bool needs_switch = false;
 	struct io_fixed_file *file_slot;
 	int ret = -EBADF;
 
@@ -8304,9 +8329,22 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
 
 	slot_index = array_index_nospec(slot_index, ctx->nr_user_files);
 	file_slot = io_fixed_file_slot(&ctx->file_table, slot_index);
-	ret = -EBADF;
-	if (file_slot->file_ptr)
+
+	if (file_slot->file_ptr) {
+		struct file *old_file;
+
+		ret = io_rsrc_node_switch_start(ctx);
+		if (ret)
+			goto err;
+
+		old_file = (struct file *)(file_slot->file_ptr & FFS_MASK);
+		ret = io_queue_rsrc_removal(ctx->file_data, slot_index,
+					    ctx->rsrc_node, old_file);
+		if (ret)
 			goto err;
+		file_slot->file_ptr = 0;
+		needs_switch = true;
+	}
 
 	*io_get_tag_slot(ctx->file_data, slot_index) = 0;
 	io_fixed_file_set(file_slot, file);
@@ -8318,27 +8356,14 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
 
 	ret = 0;
 err:
+	if (needs_switch)
+		io_rsrc_node_switch(ctx, ctx->file_data);
 	io_ring_submit_unlock(ctx, !force_nonblock);
 	if (ret)
 		fput(file);
 	return ret;
 }
 
-static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
-				 struct io_rsrc_node *node, void *rsrc)
-{
-	struct io_rsrc_put *prsrc;
-
-	prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
-	if (!prsrc)
-		return -ENOMEM;
-
-	prsrc->tag = *io_get_tag_slot(data, idx);
-	prsrc->rsrc = rsrc;
-	list_add(&prsrc->list, &node->rsrc_list);
-	return 0;
-}
-
 static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				 struct io_uring_rsrc_update2 *up,
 				 unsigned nr_args)
@@ -10560,9 +10585,11 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 			 * ordering. Fine to drop uring_lock here, we hold
 			 * a ref to the ctx.
 			 */
+			refcount_inc(&sqd->refs);
 			mutex_unlock(&ctx->uring_lock);
 			mutex_lock(&sqd->lock);
 			mutex_lock(&ctx->uring_lock);
+			if (sqd->thread)
 				tctx = sqd->thread->io_uring;
 		}
 	} else {
@@ -10577,16 +10604,20 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 	if (ret)
 		goto err;
 
-	if (sqd)
+	if (sqd) {
 		mutex_unlock(&sqd->lock);
+		io_put_sq_data(sqd);
+	}
 
 	if (copy_to_user(arg, new_count, sizeof(new_count)))
 		return -EFAULT;
 
 	return 0;
 err:
-	if (sqd)
+	if (sqd) {
 		mutex_unlock(&sqd->lock);
+		io_put_sq_data(sqd);
+	}
 	return ret;
 }
 

include/uapi/linux/io_uring.h

@@ -317,13 +317,19 @@ enum {
 	IORING_REGISTER_IOWQ_AFF		= 17,
 	IORING_UNREGISTER_IOWQ_AFF		= 18,
 
-	/* set/get max number of workers */
+	/* set/get max number of io-wq workers */
 	IORING_REGISTER_IOWQ_MAX_WORKERS	= 19,
 
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
 
+/* io-wq worker categories */
+enum {
+	IO_WQ_BOUND,
+	IO_WQ_UNBOUND,
+};
+
 /* deprecated, see struct io_uring_rsrc_update */
 struct io_uring_files_update {
 	__u32 offset;