linux-kernel - [PATCH 07/31] aio: simplify cancellation

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]

Message-Id: <20180522113108.25713-8-hch@lst.de>
Date:   Tue, 22 May 2018 13:30:44 +0200
From:   Christoph Hellwig <hch@....de>
To:     viro@...iv.linux.org.uk
Cc:     Avi Kivity <avi@...lladb.com>, linux-aio@...ck.org,
        linux-fsdevel@...r.kernel.org, netdev@...r.kernel.org,
        linux-api@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH 07/31] aio: simplify cancellation

With the current aio code there is no need for the magic KIOCB_CANCELLED
value, as a cancelation just kicks the driver to queue the completion
ASAP, with all actual completion handling done in another thread. Given
that both the completion path and cancelation take the context lock there
is no need for magic cmpxchg loops either.  If we remove iocbs from the
active list before calling ->ki_cancel we can also rely on the invariant
thay anything found on the list has a ->ki_cancel callback and can be
cancelled, further simplifing the code.

Signed-off-by: Christoph Hellwig <hch@....de>
---
 fs/aio.c | 49 ++++++-------------------------------------------
 1 file changed, 6 insertions(+), 43 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 2e0bc04f7920..8991baa38d5d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -164,19 +164,6 @@ struct fsync_iocb {
 	bool			datasync;
 };
 
-/*
- * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
- * cancelled or completed (this makes a certain amount of sense because
- * successful cancellation - io_cancel() - does deliver the completion to
- * userspace).
- *
- * And since most things don't implement kiocb cancellation and we'd really like
- * kiocb completion to be lockless when possible, we use ki_cancel to
- * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
- * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
- */
-#define KIOCB_CANCELLED		((void *) (~0ULL))
-
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
@@ -574,27 +561,6 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
-static int kiocb_cancel(struct aio_kiocb *kiocb)
-{
-	kiocb_cancel_fn *old, *cancel;
-
-	/*
-	 * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
-	 * actually has a cancel function, hence the cmpxchg()
-	 */
-
-	cancel = READ_ONCE(kiocb->ki_cancel);
-	do {
-		if (!cancel || cancel == KIOCB_CANCELLED)
-			return -EINVAL;
-
-		old = cancel;
-		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
-	} while (cancel != old);
-
-	return cancel(&kiocb->rw);
-}
-
 /*
  * free_ioctx() should be RCU delayed to synchronize against the RCU
  * protected lookup_ioctx() and also needs process context to call
@@ -641,9 +607,8 @@ static void free_ioctx_users(struct percpu_ref *ref)
 	while (!list_empty(&ctx->active_reqs)) {
 		req = list_first_entry(&ctx->active_reqs,
 				       struct aio_kiocb, ki_list);
-
 		list_del_init(&req->ki_list);
-		kiocb_cancel(req);
+		req->ki_cancel(&req->rw);
 	}
 
 	spin_unlock_irq(&ctx->ctx_lock);
@@ -1843,8 +1808,8 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 {
 	struct kioctx *ctx;
 	struct aio_kiocb *kiocb;
+	int ret = -EINVAL;
 	u32 key;
-	int ret;
 
 	if (unlikely(get_user(key, &iocb->aio_key)))
 		return -EFAULT;
@@ -1856,13 +1821,11 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 		return -EINVAL;
 
 	spin_lock_irq(&ctx->ctx_lock);
-
 	kiocb = lookup_kiocb(ctx, iocb);
-	if (kiocb)
-		ret = kiocb_cancel(kiocb);
-	else
-		ret = -EINVAL;
-
+	if (kiocb) {
+		list_del_init(&kiocb->ki_list);
+		ret = kiocb->ki_cancel(&kiocb->rw);
+	}
 	spin_unlock_irq(&ctx->ctx_lock);
 
 	if (!ret) {
-- 
2.17.0