linux-kernel - [PATCH 5.13 002/127] io_uring: Use WRITE_ONCE() when writing to sq

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 24 Aug 2021 12:54:02 -0400
From:   Sasha Levin <sashal@...nel.org>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:     Nadav Amit <namit@...are.com>, Jens Axboe <axboe@...nel.dk>,
        Pavel Begunkov <asml.silence@...il.com>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH 5.13 002/127] io_uring: Use WRITE_ONCE() when writing to sq_flags

From: Nadav Amit <namit@...are.com>

[ Upstream commit 20c0b380f971e7d48f5d978bc27d827f7eabb21a ]

The compiler should be forbidden from any strange optimization for async
writes to user visible data-structures. Without proper protection, the
compiler can cause write-tearing or invent writes that would confuse the
userspace.

However, there are writes to sq_flags which are not protected by
WRITE_ONCE(). Use WRITE_ONCE() for these writes.

This is purely a theoretical issue. Presumably, any compiler is very
unlikely to do such optimizations.

Fixes: 75b28affdd6a ("io_uring: allocate the two rings together")
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Pavel Begunkov <asml.silence@...il.com>
Signed-off-by: Nadav Amit <namit@...are.com>
Link: https://lore.kernel.org/r/20210808001342.964634-3-namit@vmware.com
Signed-off-by: Jens Axboe <axboe@...nel.dk>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 fs/io_uring.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f23ff39f7697..0a5f105c657c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1482,7 +1482,8 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	if (all_flushed) {
 		clear_bit(0, &ctx->sq_check_overflow);
 		clear_bit(0, &ctx->cq_check_overflow);
-		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
+		WRITE_ONCE(ctx->rings->sq_flags,
+			   ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW);
 	}
 
 	if (posted)
@@ -1562,7 +1563,9 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
 	if (list_empty(&ctx->cq_overflow_list)) {
 		set_bit(0, &ctx->sq_check_overflow);
 		set_bit(0, &ctx->cq_check_overflow);
-		ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
+		WRITE_ONCE(ctx->rings->sq_flags,
+			   ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW);
+
 	}
 	ocqe->cqe.user_data = user_data;
 	ocqe->cqe.res = res;
@@ -6790,14 +6793,16 @@ static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx)
 {
 	/* Tell userspace we may need a wakeup call */
 	spin_lock_irq(&ctx->completion_lock);
-	ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
+	WRITE_ONCE(ctx->rings->sq_flags,
+		   ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP);
 	spin_unlock_irq(&ctx->completion_lock);
 }
 
 static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx)
 {
 	spin_lock_irq(&ctx->completion_lock);
-	ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+	WRITE_ONCE(ctx->rings->sq_flags,
+		   ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP);
 	spin_unlock_irq(&ctx->completion_lock);
 }
 
-- 
2.30.2