From: Nadav Amit namit@vmware.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@kernel.dk Cc: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Nadav Amit namit@vmware.com Link: https://lore.kernel.org/r/20210808001342.964634-3-namit@vmware.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.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); }