From d5361233e9ab920e135819f73dd8466355f1fddd Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 31 Mar 2022 12:38:46 -0600
Subject: [PATCH] io_uring: drop the old style inflight file tracking
Git-commit: d5361233e9ab920e135819f73dd8466355f1fddd
Patch-mainline: v5.18-rc2
References: bsc#1205205

io_uring tracks requests that are referencing an io_uring descriptor to
be able to cancel without worrying about loops in the references. Since
we now assign the file at execution time, the easier approach is to drop
a potentially problematic reference before we punt the request. This
eliminates the need to special case these types of files beyond just
marking them as such, and simplifies cancelation quite a bit.

This also fixes a recent issue where an async punted tee operation would
with the io_uring descriptor as the output file would crash when
attempting to get a reference to the file from the io-wq worker. We
could have worked around that, but this is the much cleaner fix.

Fixes: 6bf9c47a3989 ("io_uring: defer file assignment")
Reported-by: syzbot+c4b9303500a21750b250@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
---
 fs/io_uring.c | 85 ++++++++++++++++-----------------------------------
 1 file changed, 27 insertions(+), 58 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index bdc090fec29c..ad0d99ffbf0a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -112,8 +112,7 @@
 			IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
 
 #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
-				REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
-				REQ_F_ASYNC_DATA)
+				REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA)
 
 #define IO_TCTX_REFS_CACHE_NR	(1U << 10)
 
@@ -500,7 +499,6 @@ struct io_uring_task {
 	const struct io_ring_ctx *last;
 	struct io_wq		*io_wq;
 	struct percpu_counter	inflight;
-	atomic_t		inflight_tracked;
 	atomic_t		in_idle;
 
 	spinlock_t		task_lock;
@@ -1186,6 +1184,8 @@ static void io_clean_op(struct io_kiocb *req);
 static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 					     unsigned issue_flags);
 static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+static void io_drop_inflight_file(struct io_kiocb *req);
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags);
 static void __io_queue_sqe(struct io_kiocb *req);
 static void io_rsrc_put_work(struct work_struct *work);
 
@@ -1433,29 +1433,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
 			  bool cancel_all)
 	__must_hold(&req->ctx->timeout_lock)
 {
-	struct io_kiocb *req;
-
 	if (task && head->task != task)
 		return false;
-	if (cancel_all)
-		return true;
-
-	io_for_each_link(req, head) {
-		if (req->flags & REQ_F_INFLIGHT)
-			return true;
-	}
-	return false;
-}
-
-static bool io_match_linked(struct io_kiocb *head)
-{
-	struct io_kiocb *req;
-
-	io_for_each_link(req, head) {
-		if (req->flags & REQ_F_INFLIGHT)
-			return true;
-	}
-	return false;
+	return cancel_all;
 }
 
 /*
@@ -1465,24 +1445,9 @@ static bool io_match_linked(struct io_kiocb *head)
 static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			       bool cancel_all)
 {
-	bool matched;
-
 	if (task && head->task != task)
 		return false;
-	if (cancel_all)
-		return true;
-
-	if (head->flags & REQ_F_LINK_TIMEOUT) {
-		struct io_ring_ctx *ctx = head->ctx;
-
-		/* protect against races with linked timeouts */
-		spin_lock_irq(&ctx->timeout_lock);
-		matched = io_match_linked(head);
-		spin_unlock_irq(&ctx->timeout_lock);
-	} else {
-		matched = io_match_linked(head);
-	}
-	return matched;
+	return cancel_all;
 }
 
 static inline bool req_has_async_data(struct io_kiocb *req)
@@ -1645,14 +1610,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req)
 	return req->flags & REQ_F_FIXED_FILE;
 }
 
-static inline void io_req_track_inflight(struct io_kiocb *req)
-{
-	if (!(req->flags & REQ_F_INFLIGHT)) {
-		req->flags |= REQ_F_INFLIGHT;
-		atomic_inc(&current->io_uring->inflight_tracked);
-	}
-}
-
 static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
 {
 	if (WARN_ON_ONCE(!req->link))
@@ -2563,6 +2520,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority)
 
 	WARN_ON_ONCE(!tctx);
 
+	io_drop_inflight_file(req);
+
 	spin_lock_irqsave(&tctx->task_lock, flags);
 	if (priority)
 		wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list);
@@ -6008,7 +5967,10 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked)
 		if (!req->result) {
 			struct poll_table_struct pt = { ._key = req->cflags };
 
-			req->result = vfs_poll(req->file, &pt) & req->cflags;
+			if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED)))
+				req->result = -EBADF;
+			else
+				req->result = vfs_poll(req->file, &pt) & req->cflags;
 		}
 
 		/* multishot, just fill an CQE and proceed */
@@ -7226,11 +7188,6 @@ static void io_clean_op(struct io_kiocb *req)
 		kfree(req->apoll);
 		req->apoll = NULL;
 	}
-	if (req->flags & REQ_F_INFLIGHT) {
-		struct io_uring_task *tctx = req->task->io_uring;
-
-		atomic_dec(&tctx->inflight_tracked);
-	}
 	if (req->flags & REQ_F_CREDS)
 		put_cred(req->creds);
 	if (req->flags & REQ_F_ASYNC_DATA) {
@@ -7522,6 +7479,19 @@ static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 	return file;
 }
 
+/*
+ * Drop the file for requeue operations. Only used of req->file is the
+ * io_uring descriptor itself.
+ */
+static void io_drop_inflight_file(struct io_kiocb *req)
+{
+	if (unlikely(req->flags & REQ_F_INFLIGHT)) {
+		fput(req->file);
+		req->file = NULL;
+		req->flags &= ~REQ_F_INFLIGHT;
+	}
+}
+
 static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
 {
 	struct file *file = fget(fd);
@@ -7529,8 +7499,8 @@ static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
 	trace_io_uring_file_get(req->ctx, req, req->user_data, fd);
 
 	/* we don't allow fixed io_uring files */
-	if (file && unlikely(file->f_op == &io_uring_fops))
-		io_req_track_inflight(req);
+	if (file && file->f_op == &io_uring_fops)
+		req->flags |= REQ_F_INFLIGHT;
 	return file;
 }
 
@@ -9437,7 +9407,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task,
 	xa_init(&tctx->xa);
 	init_waitqueue_head(&tctx->wait);
 	atomic_set(&tctx->in_idle, 0);
-	atomic_set(&tctx->inflight_tracked, 0);
 	task->io_uring = tctx;
 	spin_lock_init(&tctx->task_lock);
 	INIT_WQ_LIST(&tctx->task_list);
@@ -10630,7 +10599,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
 static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
 {
 	if (tracked)
-		return atomic_read(&tctx->inflight_tracked);
+		return 0;
 	return percpu_counter_sum(&tctx->inflight);
 }
 
-- 
2.35.3