Commit 560773de authored by Jens Axboe's avatar Jens Axboe Committed by Zhihao Cheng
Browse files

io_uring: ensure IOPOLL locks around deferred work 

stable inclusion
from stable-v5.10.188
commit 810e401b34c4c4c244d8b93b9947ea5b3d4d49f8
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I7KXLN
CVE: CVE-2023-21400

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=810e401b34c4c4c244d8b93b9947ea5b3d4d49f8



--------------------------------

No direct upstream commit exists for this issue. It was fixed in
5.18 as part of a larger rework of the completion side.

io_commit_cqring() writes the CQ ring tail to make it visible, but it
also kicks off any deferred work we have. A ring setup with IOPOLL
does not need any locking around the CQ ring updates, as we're always
under the ctx uring_lock. But if we have deferred work that needs
processing, then io_queue_deferred() assumes that the completion_lock
is held, as it is for !IOPOLL.

Add a lockdep assertion to check and document this fact, and have
io_iopoll_complete() check if we have deferred work and run that
separately with the appropriate lock grabbed.

Cc: stable@vger.kernel.org # 5.10, 5.15
Reported-by: default avatardghost david <daviduniverse18@gmail.com>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: default avatarLin Yujun <linyujun809@huawei.com>
Signed-off-by: default avatarZhihao Cheng <chengzhihao1@huawei.com>
parent e80d0dac

io_uring/io_uring.c

+21 −4
Original line number Diff line number Diff line
@@ -1521,6 +1521,8 @@ static void io_kill_timeout(struct io_kiocb *req, int status) 


static void io_queue_deferred(struct io_ring_ctx *ctx)

{

	lockdep_assert_held(&ctx->completion_lock);



	while (!list_empty(&ctx->defer_list)) {

		struct io_defer_entry *de = list_first_entry(&ctx->defer_list,

						struct io_defer_entry, list);
@@ -1572,14 +1574,24 @@ static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) 
		io_queue_deferred(ctx);

}



static inline void io_commit_cqring(struct io_ring_ctx *ctx)

static inline bool io_commit_needs_flush(struct io_ring_ctx *ctx)

{

	return ctx->off_timeout_used || ctx->drain_active;

}



static inline void __io_commit_cqring(struct io_ring_ctx *ctx)

{

	if (unlikely(ctx->off_timeout_used || ctx->drain_active))

		__io_commit_cqring_flush(ctx);

	/* order cqe stores with ring update */

	smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);

}



static inline void io_commit_cqring(struct io_ring_ctx *ctx)

{

	if (unlikely(io_commit_needs_flush(ctx)))

		__io_commit_cqring_flush(ctx);

	__io_commit_cqring(ctx);

}



static inline bool io_sqring_full(struct io_ring_ctx *ctx)

{

	struct io_rings *r = ctx->rings;
@@ -2509,7 +2521,12 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, 
			io_req_free_batch(&rb, req, &ctx->submit_state);

	}



	io_commit_cqring(ctx);

	if (io_commit_needs_flush(ctx)) {

		spin_lock(&ctx->completion_lock);

		__io_commit_cqring_flush(ctx);

		spin_unlock(&ctx->completion_lock);

	}

	__io_commit_cqring(ctx);

	io_cqring_ev_posted_iopoll(ctx);

	io_req_free_batch_finish(ctx, &rb);

}