1 files changed, 96 insertions, 106 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 381d50becd04..bb25e3997d41 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -524,6 +524,7 @@ enum {
 	REQ_F_OVERFLOW_BIT,
 	REQ_F_POLLED_BIT,
 	REQ_F_BUFFER_SELECTED_BIT,
+	REQ_F_NO_FILE_TABLE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -577,6 +578,8 @@ enum {
 	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
 	/* buffer already selected */
 	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	/* doesn't need file table for this request */
+	REQ_F_NO_FILE_TABLE	= BIT(REQ_F_NO_FILE_TABLE_BIT),
 };
 
 struct async_poll {
@@ -616,6 +619,8 @@ struct io_kiocb {
 	bool				needs_fixed_file;
 	u8				opcode;
 
+	u16				buf_index;
+
 	struct io_ring_ctx	*ctx;
 	struct list_head	list;
 	unsigned int		flags;
@@ -677,8 +682,6 @@ struct io_op_def {
 	unsigned		needs_mm : 1;
 	/* needs req->file assigned */
 	unsigned		needs_file : 1;
-	/* needs req->file assigned IFF fd is >= 0 */
-	unsigned		fd_non_neg : 1;
 	/* hash wq insertion if file is a regular file */
 	unsigned		hash_reg_file : 1;
 	/* unbound wq insertion if file is a non-regular file */
@@ -781,8 +784,6 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 	},
 	[IORING_OP_OPENAT] = {
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.file_table		= 1,
 		.needs_fs		= 1,
 	},
@@ -796,9 +797,8 @@ static const struct io_op_def io_op_defs[] = {
 	},
 	[IORING_OP_STATX] = {
 		.needs_mm		= 1,
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.needs_fs		= 1,
+		.file_table		= 1,
 	},
 	[IORING_OP_READ] = {
 		.needs_mm		= 1,
@@ -833,8 +833,6 @@ static const struct io_op_def io_op_defs[] = {
 		.buffer_select		= 1,
 	},
 	[IORING_OP_OPENAT2] = {
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.file_table		= 1,
 		.needs_fs		= 1,
 	},
@@ -928,6 +926,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 		goto err;
 
 	ctx->flags = p->flags;
+	init_waitqueue_head(&ctx->sqo_wait);
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->completions[0]);
@@ -1291,7 +1290,7 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
 	struct io_kiocb *req;
 
 	req = ctx->fallback_req;
-	if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+	if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req))
 		return req;
 
 	return NULL;
@@ -1378,7 +1377,7 @@ static void __io_free_req(struct io_kiocb *req)
 	if (likely(!io_is_fallback_req(req)))
 		kmem_cache_free(req_cachep, req);
 	else
-		clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+		clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req);
 }
 
 struct req_batch {
@@ -1398,10 +1397,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
 		for (i = 0; i < rb->to_free; i++) {
 			struct io_kiocb *req = rb->reqs[i];
 
-			if (req->flags & REQ_F_FIXED_FILE) {
-				req->file = NULL;
-				percpu_ref_put(req->fixed_file_refs);
-			}
 			if (req->flags & REQ_F_INFLIGHT)
 				inflight++;
 			__io_req_aux_free(req);
@@ -1674,7 +1669,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
 	if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
 		return false;
 
-	if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+	if (req->file || req->io)
 		rb->need_iter++;
 
 	rb->reqs[rb->to_free++] = req;
@@ -2034,7 +2029,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
  * any file. For now, just ensure that anything potentially problematic is done
  * inline.
  */
-static bool io_file_supports_async(struct file *file)
+static bool io_file_supports_async(struct file *file, int rw)
 {
 	umode_t mode = file_inode(file)->i_mode;
 
@@ -2043,7 +2038,13 @@ static bool io_file_supports_async(struct file *file)
 	if (S_ISREG(mode) && file->f_op != &io_uring_fops)
 		return true;
 
-	return false;
+	if (!(file->f_mode & FMODE_NOWAIT))
+		return false;
+
+	if (rw == READ)
+		return file->f_op->read_iter != NULL;
+
+	return file->f_op->write_iter != NULL;
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
@@ -2102,9 +2103,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	req->rw.addr = READ_ONCE(sqe->addr);
 	req->rw.len = READ_ONCE(sqe->len);
-	/* we own ->private, reuse it for the buffer index  / buffer ID */
-	req->rw.kiocb.private = (void *) (unsigned long)
-					READ_ONCE(sqe->buf_index);
+	req->buf_index = READ_ONCE(sqe->buf_index);
 	return 0;
 }
 
@@ -2147,7 +2146,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 	struct io_ring_ctx *ctx = req->ctx;
 	size_t len = req->rw.len;
 	struct io_mapped_ubuf *imu;
-	unsigned index, buf_index;
+	u16 index, buf_index;
 	size_t offset;
 	u64 buf_addr;
 
@@ -2155,7 +2154,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 	if (unlikely(!ctx->user_bufs))
 		return -EFAULT;
 
-	buf_index = (unsigned long) req->rw.kiocb.private;
+	buf_index = req->buf_index;
 	if (unlikely(buf_index >= ctx->nr_user_bufs))
 		return -EFAULT;
 
@@ -2271,10 +2270,10 @@ static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
 					bool needs_lock)
 {
 	struct io_buffer *kbuf;
-	int bgid;
+	u16 bgid;
 
 	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
-	bgid = (int) (unsigned long) req->rw.kiocb.private;
+	bgid = req->buf_index;
 	kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
 	if (IS_ERR(kbuf))
 		return kbuf;
@@ -2365,7 +2364,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	}
 
 	/* buffer index only valid with fixed read/write, or buffer select  */
-	if (req->rw.kiocb.private && !(req->flags & REQ_F_BUFFER_SELECT))
+	if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))
 		return -EINVAL;
 
 	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
@@ -2571,7 +2570,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file))
+	if (force_nonblock && !io_file_supports_async(req->file, READ))
 		goto copy_iov;
 
 	iov_count = iov_iter_count(&iter);
@@ -2594,7 +2593,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			if (!(req->flags & REQ_F_NOWAIT))
+			if (!(req->flags & REQ_F_NOWAIT) &&
+			    !file_can_poll(req->file))
 				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
@@ -2662,7 +2662,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file))
+	if (force_nonblock && !io_file_supports_async(req->file, WRITE))
 		goto copy_iov;
 
 	/* file path doesn't support NOWAIT for non-direct_IO */
@@ -2716,7 +2716,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			req->flags |= REQ_F_MUST_PUNT;
+			if (!file_can_poll(req->file))
+				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
 	}
@@ -2756,15 +2757,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static bool io_splice_punt(struct file *file)
-{
-	if (get_pipe_info(file))
-		return false;
-	if (!io_file_supports_async(file))
-		return true;
-	return !(file->f_flags & O_NONBLOCK);
-}
-
 static int io_splice(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_splice *sp = &req->splice;
@@ -2772,19 +2764,16 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock)
 	struct file *out = sp->file_out;
 	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
 	loff_t *poff_in, *poff_out;
-	long ret;
+	long ret = 0;
 
-	if (force_nonblock) {
-		if (io_splice_punt(in) || io_splice_punt(out))
-			return -EAGAIN;
-		flags |= SPLICE_F_NONBLOCK;
-	}
+	if (force_nonblock)
+		return -EAGAIN;
 
 	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
 	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
-	ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
-	if (force_nonblock && ret == -EAGAIN)
-		return -EAGAIN;
+
+	if (sp->len)
+		ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
 
 	io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
 	req->flags &= ~REQ_F_NEED_CLEANUP;
@@ -3355,8 +3344,12 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock)
 	struct kstat stat;
 	int ret;
 
-	if (force_nonblock)
+	if (force_nonblock) {
+		/* only need file table for an actual valid fd */
+		if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD)
+			req->flags |= REQ_F_NO_FILE_TABLE;
 		return -EAGAIN;
+	}
 
 	if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
 		return -EINVAL;
@@ -3502,7 +3495,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr)
 	if (io_req_cancelled(req))
 		return;
 	__io_sync_file_range(req);
-	io_put_req(req); /* put submission ref */
+	io_steal_work(req, workptr);
 }
 
 static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
@@ -4142,12 +4135,14 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	req->result = mask;
 	init_task_work(&req->task_work, func);
 	/*
-	 * If this fails, then the task is exiting. Punt to one of the io-wq
-	 * threads to ensure the work gets run, we can't always rely on exit
-	 * cancelation taking care of this.
+	 * If this fails, then the task is exiting. When a task exits, the
+	 * work gets canceled, so just cancel this request as well instead
+	 * of executing it. We can't safely execute it anyway, as we may not
+	 * have the needed state needed for it anyway.
 	 */
 	ret = task_work_add(tsk, &req->task_work, true);
 	if (unlikely(ret)) {
+		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
 		task_work_add(tsk, &req->task_work, true);
 	}
@@ -4200,17 +4195,17 @@ static void io_async_task_func(struct callback_head *cb)
 
 	spin_unlock_irq(&ctx->completion_lock);
 
+	/* restore ->work in case we need to retry again */
+	memcpy(&req->work, &apoll->work, sizeof(req->work));
+
 	if (canceled) {
 		kfree(apoll);
 		io_cqring_ev_posted(ctx);
 		req_set_fail_links(req);
-		io_put_req(req);
+		io_double_put_req(req);
 		return;
 	}
 
-	/* restore ->work in case we need to retry again */
-	memcpy(&req->work, &apoll->work, sizeof(req->work));
-
 	__set_current_state(TASK_RUNNING);
 	mutex_lock(&ctx->uring_lock);
 	__io_queue_sqe(req, NULL);
@@ -4369,7 +4364,7 @@ static bool io_poll_remove_one(struct io_kiocb *req)
 
 	hash_del(&req->hash_node);
 
-	if (apoll) {
+	if (do_complete && apoll) {
 		/*
 		 * restore ->work because we need to call io_req_work_drop_env.
 		 */
@@ -5015,15 +5010,16 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	int ret;
 
 	/* Still need defer if there is pending req in defer list. */
-	if (!req_need_defer(req) && list_empty(&ctx->defer_list))
+	if (!req_need_defer(req) && list_empty_careful(&ctx->defer_list))
 		return 0;
 
-	if (!req->io && io_alloc_async_ctx(req))
-		return -EAGAIN;
-
-	ret = io_req_defer_prep(req, sqe);
-	if (ret < 0)
-		return ret;
+	if (!req->io) {
+		if (io_alloc_async_ctx(req))
+			return -EAGAIN;
+		ret = io_req_defer_prep(req, sqe);
+		if (ret < 0)
+			return ret;
+	}
 
 	spin_lock_irq(&ctx->completion_lock);
 	if (!req_need_defer(req) && list_empty(&ctx->defer_list)) {
@@ -5310,7 +5306,8 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (ret)
 		return ret;
 
-	if (ctx->flags & IORING_SETUP_IOPOLL) {
+	/* If the op doesn't have a file, we're not polling for it */
+	if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) {
 		const bool in_async = io_wq_current_is_worker();
 
 		if (req->result == -EAGAIN)
@@ -5364,15 +5361,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 	io_steal_work(req, workptr);
 }
 
-static int io_req_needs_file(struct io_kiocb *req, int fd)
-{
-	if (!io_op_defs[req->opcode].needs_file)
-		return 0;
-	if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
-		return 0;
-	return 1;
-}
-
 static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
 					      int index)
 {
@@ -5410,14 +5398,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
 }
 
 static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
-			   int fd, unsigned int flags)
+			   int fd)
 {
 	bool fixed;
 
-	if (!io_req_needs_file(req, fd))
-		return 0;
-
-	fixed = (flags & IOSQE_FIXED_FILE);
+	fixed = (req->flags & REQ_F_FIXED_FILE) != 0;
 	if (unlikely(!fixed && req->needs_fixed_file))
 		return -EBADF;
 
@@ -5429,7 +5414,7 @@ static int io_grab_files(struct io_kiocb *req)
 	int ret = -EBADF;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (req->work.files)
+	if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
 		return 0;
 	if (!ctx->ring_file)
 		return -EBADF;
@@ -5623,9 +5608,15 @@ fail_req:
 			io_double_put_req(req);
 		}
 	} else if (req->flags & REQ_F_FORCE_ASYNC) {
-		ret = io_req_defer_prep(req, sqe);
-		if (unlikely(ret < 0))
-			goto fail_req;
+		if (!req->io) {
+			ret = -EAGAIN;
+			if (io_alloc_async_ctx(req))
+				goto fail_req;
+			ret = io_req_defer_prep(req, sqe);
+			if (unlikely(ret < 0))
+				goto fail_req;
+		}
+
 		/*
 		 * Never try inline submit of IOSQE_ASYNC is set, go straight
 		 * to async execution.
@@ -5794,7 +5785,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		       struct io_submit_state *state, bool async)
 {
 	unsigned int sqe_flags;
-	int id, fd;
+	int id;
 
 	/*
 	 * All io need record the previous position, if LINK vs DARIN,
@@ -5846,8 +5837,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 					IOSQE_ASYNC | IOSQE_FIXED_FILE |
 					IOSQE_BUFFER_SELECT | IOSQE_IO_LINK);
 
-	fd = READ_ONCE(sqe->fd);
-	return io_req_set_file(state, req, fd, sqe_flags);
+	if (!io_op_defs[req->opcode].needs_file)
+		return 0;
+
+	return io_req_set_file(state, req, READ_ONCE(sqe->fd));
 }
 
 static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
@@ -6039,6 +6032,7 @@ static int io_sq_thread(void *data)
 				finish_wait(&ctx->sqo_wait, &wait);
 
 				ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+				ret = 0;
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
@@ -6852,7 +6846,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 {
 	int ret;
 
-	init_waitqueue_head(&ctx->sqo_wait);
 	mmgrab(current->mm);
 	ctx->sqo_mm = current->mm;
 
@@ -7327,7 +7320,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	 * it could cause shutdown to hang.
 	 */
 	while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait))
-		cpu_relax();
+		cond_resched();
 
 	io_kill_timeouts(ctx);
 	io_poll_remove_all(ctx);
@@ -7356,11 +7349,9 @@ static int io_uring_release(struct inode *inode, struct file *file)
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct files_struct *files)
 {
-	struct io_kiocb *req;
-	DEFINE_WAIT(wait);
-
 	while (!list_empty_careful(&ctx->inflight_list)) {
-		struct io_kiocb *cancel_req = NULL;
+		struct io_kiocb *cancel_req = NULL, *req;
+		DEFINE_WAIT(wait);
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
@@ -7400,6 +7391,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			 */
 			if (refcount_sub_and_test(2, &cancel_req->refs)) {
 				io_put_req(cancel_req);
+				finish_wait(&ctx->inflight_wait, &wait);
 				continue;
 			}
 		}
@@ -7407,8 +7399,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 		io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
 		io_put_req(cancel_req);
 		schedule();
+		finish_wait(&ctx->inflight_wait, &wait);
 	}
-	finish_wait(&ctx->inflight_wait, &wait);
 }
 
 static int io_uring_flush(struct file *file, void *data)
@@ -7757,7 +7749,8 @@ err:
 	return ret;
 }
 
-static int io_uring_create(unsigned entries, struct io_uring_params *p)
+static int io_uring_create(unsigned entries, struct io_uring_params *p,
+			   struct io_uring_params __user *params)
 {
 	struct user_struct *user = NULL;
 	struct io_ring_ctx *ctx;
@@ -7849,6 +7842,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
 	p->cq_off.cqes = offsetof(struct io_rings, cqes);
 
+	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+
+	if (copy_to_user(params, p, sizeof(*p))) {
+		ret = -EFAULT;
+		goto err;
+	}
 	/*
 	 * Install ring fd as the very last thing, so we don't risk someone
 	 * having closed it before we finish setup
@@ -7857,9 +7858,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	if (ret < 0)
 		goto err;
 
-	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
-			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
-			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
@@ -7875,7 +7873,6 @@ err:
 static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 {
 	struct io_uring_params p;
-	long ret;
 	int i;
 
 	if (copy_from_user(&p, params, sizeof(p)))
@@ -7890,14 +7887,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
 		return -EINVAL;
 
-	ret = io_uring_create(entries, &p);
-	if (ret < 0)
-		return ret;
-
-	if (copy_to_user(params, &p, sizeof(p)))
-		return -EFAULT;
-
-	return ret;
+	return  io_uring_create(entries, &p, params);
 }
 
 SYSCALL_DEFINE2(io_uring_setup, u32, entries,