[PATCH 3/4] aio: implement IOCB_CMD_POLL

[Christoph Hellwig]

Simple one-shot poll through the io_submit() interface.  To poll for
a file descriptor the application should submit an iocb of type
IOCB_CMD_POLL.  It will poll the fd for the events specified in the
the first 32 bits of the aio_buf field of the iocb.

Unlike poll or epoll without EPOLLONESHOT this interface always works
in one shot mode, that is once the iocb is completed, it will have to be
resubmitted.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
 fs/aio.c                     | 178 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/aio_abi.h |   6 +-
 2 files changed, 180 insertions(+), 4 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index fe2018ada32c..6993684d0665 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
  *	Implements an efficient asynchronous io interface.
  *
  *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
+ *	Copyright 2018 Christoph Hellwig.
  *
  *	See ../COPYING for licensing terms.
  */
@@ -165,10 +166,21 @@ struct fsync_iocb {
 	bool			datasync;
 };
 
+struct poll_iocb {
+	struct file		*file;
+	struct wait_queue_head	*head;
+	__poll_t		events;
+	bool			cancelled;
+	bool			done;
+	struct wait_queue_entry	wait;
+	struct work_struct	work;
+};
+
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
 		struct fsync_iocb	fsync;
+		struct poll_iocb	poll;
 	};
 
 	struct kioctx		*ki_ctx;
@@ -1601,6 +1613,169 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	return 0;
 }
 
+static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
+{
+	struct file *file = iocb->poll.file;
+
+	aio_complete(iocb, mangle_poll(mask), 0);
+	fput(file);
+}
+
+static void aio_poll_complete_work(struct work_struct *work)
+{
+	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+	struct poll_table_struct pt = { ._key = req->events };
+	struct kioctx *ctx = iocb->ki_ctx;
+	__poll_t mask;
+
+	if (READ_ONCE(req->cancelled)) {
+		/* synchronize with ki_list removal in the callers: */
+		spin_lock_irq(&ctx->ctx_lock);
+		WARN_ON_ONCE(!list_empty(&iocb->ki_list));
+		spin_unlock_irq(&ctx->ctx_lock);
+
+		aio_poll_complete(iocb, 0);
+		return;
+	}
+
+	mask = vfs_poll(req->file, &pt) & req->events;
+	if (!mask) {
+		add_wait_queue(req->head, &req->wait);
+		return;
+	}
+
+	spin_lock_irq(&ctx->ctx_lock);
+	req->done = true;
+	list_del(&iocb->ki_list);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+	aio_poll_complete(iocb, mask);
+}
+
+/* assumes we are called with irqs disabled */
+static int aio_poll_cancel(struct kiocb *iocb)
+{
+	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
+	struct poll_iocb *req = &aiocb->poll;
+
+	spin_lock(&req->head->lock);
+	if (!list_empty(&req->wait.entry)) {
+		WRITE_ONCE(req->cancelled, true);
+		list_del_init(&req->wait.entry);
+		schedule_work(&aiocb->poll.work);
+	}
+	spin_unlock(&req->head->lock);
+
+	return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+		void *key)
+{
+	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+	__poll_t mask = key_to_poll(key);
+
+	/* for instances that support it check for an event match first: */
+	if (mask && !(mask & req->events))
+		return 0;
+
+	list_del_init(&req->wait.entry);
+	schedule_work(&req->work);
+	return 1;
+}
+
+struct aio_poll_table {
+	struct poll_table_struct	pt;
+	struct aio_kiocb		*iocb;
+	int				error;
+};
+
+static void
+aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
+		struct poll_table_struct *p)
+{
+	struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
+
+	/* multiple wait queues per file are not supported */
+	if (unlikely(pt->iocb->poll.head)) {
+		pt->error = -EINVAL;
+		return;
+	}
+
+	pt->error = 0;
+	pt->iocb->poll.head = head;
+	add_wait_queue(head, &pt->iocb->poll.wait);
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+	struct kioctx *ctx = aiocb->ki_ctx;
+	struct poll_iocb *req = &aiocb->poll;
+	struct aio_poll_table apt;
+	__poll_t mask;
+
+	/* reject any unknown events outside the normal event mask. */
+	if ((u16)iocb->aio_buf != iocb->aio_buf)
+		return -EINVAL;
+	/* reject fields that are not defined for poll */
+	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+		return -EINVAL;
+
+	INIT_WORK(&req->work, aio_poll_complete_work);
+	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
+	req->file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+
+	apt.pt._qproc = aio_poll_queue_proc;
+	apt.pt._key = req->events;
+	apt.iocb = aiocb;
+	apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
+
+	/* initialized the list so that we can do list_empty checks */
+	INIT_LIST_HEAD(&req->wait.entry);
+	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+
+	/* one for removal from waitqueue, one for this function */
+	refcount_set(&aiocb->ki_refcnt, 2);
+
+	mask = vfs_poll(req->file, &apt.pt) & req->events;
+	if (mask || apt.error) {
+		bool removed = false;
+
+		/* we did not manage to set up a waitqueue, done */
+		if (unlikely(!req->head))
+			goto out_fput;
+
+		spin_lock_irq(&req->head->lock);
+		if (!list_empty(&req->wait.entry)) {
+			list_del_init(&req->wait.entry);
+			removed = true;
+		}
+		spin_unlock_irq(&req->head->lock);
+
+		if (removed) {
+			if (apt.error)
+				goto out_fput;
+			aio_poll_complete(aiocb, mask);
+		}
+	} else {
+		spin_lock_irq(&ctx->ctx_lock);
+		if (!req->done) {
+			list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+			aiocb->ki_cancel = aio_poll_cancel;
+		}
+		spin_unlock_irq(&ctx->ctx_lock);
+	}
+
+	iocb_put(aiocb);
+	return 0;
+out_fput:
+	fput(req->file);
+	return apt.error;
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 bool compat)
 {
@@ -1674,6 +1849,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_FDSYNC:
 		ret = aio_fsync(&req->fsync, &iocb, true);
 		break;
+	case IOCB_CMD_POLL:
+		ret = aio_poll(req, &iocb);
+		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index d4593a6062ef..ce43d340f010 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -38,10 +38,8 @@ enum {
 	IOCB_CMD_PWRITE = 1,
 	IOCB_CMD_FSYNC = 2,
 	IOCB_CMD_FDSYNC = 3,
-	/* These two are experimental.
-	 * IOCB_CMD_PREADX = 4,
-	 * IOCB_CMD_POLL = 5,
-	 */
+	/* 4 was the experimental IOCB_CMD_PREADX */
+	IOCB_CMD_POLL = 5,
 	IOCB_CMD_NOOP = 6,
 	IOCB_CMD_PREADV = 7,
 	IOCB_CMD_PWRITEV = 8,
-- 
2.18.0