eventfd: revised interface and cleanups

Change the eventfd interface to de-couple the eventfd memory context, from
the file pointer instance.

Without such change, there is no clean way to racely free handle the
POLLHUP event sent when the last instance of the file* goes away.  Also,
now the internal eventfd APIs are using the eventfd context instead of the
file*.

This patch is required by KVM's IRQfd code, which is still under
development.

Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Gregory Haskins <ghaskins@novell.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Cc: Avi Kivity <avi@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 7 insertions, 17 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 76da1253795..d065b2c3273 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -485,6 +485,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 {
 	assert_spin_locked(&ctx->ctx_lock);
 
+	if (req->ki_eventfd != NULL)
+		eventfd_ctx_put(req->ki_eventfd);
 	if (req->ki_dtor)
 		req->ki_dtor(req);
 	if (req->ki_iovec != &req->ki_inline_vec)
@@ -509,8 +511,6 @@ static void aio_fput_routine(struct work_struct *data)
 		/* Complete the fput(s) */
 		if (req->ki_filp != NULL)
 			__fput(req->ki_filp);
-		if (req->ki_eventfd != NULL)
-			__fput(req->ki_eventfd);
 
 		/* Link the iocb into the context's free list */
 		spin_lock_irq(&ctx->ctx_lock);
@@ -528,8 +528,6 @@ static void aio_fput_routine(struct work_struct *data)
  */
 static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 {
-	int schedule_putreq = 0;
-
 	dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
 		req, atomic_long_read(&req->ki_filp->f_count));
 
@@ -549,24 +547,16 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	 * we would not be holding the last reference to the file*, so
 	 * this function will be executed w/out any aio kthread wakeup.
 	 */
-	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count)))
-		schedule_putreq++;
-	else
-		req->ki_filp = NULL;
-	if (req->ki_eventfd != NULL) {
-		if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count)))
-			schedule_putreq++;
-		else
-			req->ki_eventfd = NULL;
-	}
-	if (unlikely(schedule_putreq)) {
+	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
 		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
 		spin_unlock(&fput_lock);
 		queue_work(aio_wq, &fput_work);
-	} else
+	} else {
+		req->ki_filp = NULL;
 		really_put_req(ctx, req);
+	}
 	return 1;
 }
 
@@ -1622,7 +1612,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		 * an eventfd() fd, and will be signaled for each completed
 		 * event using the eventfd_signal() function.
 		 */
-		req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
+		req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
 		if (IS_ERR(req->ki_eventfd)) {
 			ret = PTR_ERR(req->ki_eventfd);
 			req->ki_eventfd = NULL;