Merge tag 'for-4.21/aio-20181221' of git://git.kernel.dk/linux-block

Pull aio updates from Jens Axboe:
 "Flushing out pre-patches for the buffered/polled aio series. Some
  fixes in here, but also optimizations"

* tag 'for-4.21/aio-20181221' of git://git.kernel.dk/linux-block:
  aio: abstract out io_event filler helper
  aio: split out iocb copy from io_submit_one()
  aio: use iocb_put() instead of open coding it
  aio: only use blk plugs for > 2 depth submissions
  aio: don't zero entire aio_kiocb aio_get_req()
  aio: separate out ring reservation from req allocation
  aio: use assigned completion handler

fs/aio.c

@@ -70,6 +70,12 @@ struct aio_ring {
 	struct io_event		io_events[0];
 }; /* 128 bytes + ring size */
 
+/*
+ * Plugging is meant to work with larger batches of IOs. If we don't
+ * have more than the below, then don't bother setting up a plug.
+ */
+#define AIO_PLUG_THRESHOLD	2
+
 #define AIO_RING_PAGES	8
 
 struct kioctx_table {
@@ -902,7 +908,7 @@ static void put_reqs_available(struct kioctx *ctx, unsigned nr)
 	local_irq_restore(flags);
 }
 
-static bool get_reqs_available(struct kioctx *ctx)
+static bool __get_reqs_available(struct kioctx *ctx)
 {
 	struct kioctx_cpu *kcpu;
 	bool ret = false;
@@ -994,6 +1000,14 @@ static void user_refill_reqs_available(struct kioctx *ctx)
 	spin_unlock_irq(&ctx->completion_lock);
 }
 
+static bool get_reqs_available(struct kioctx *ctx)
+{
+	if (__get_reqs_available(ctx))
+		return true;
+	user_refill_reqs_available(ctx);
+	return __get_reqs_available(ctx);
+}
+
 /* aio_get_req
  *	Allocate a slot for an aio request.
  * Returns NULL if no requests are free.
@@ -1002,24 +1016,16 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 {
 	struct aio_kiocb *req;
 
-	if (!get_reqs_available(ctx)) {
-		user_refill_reqs_available(ctx);
-		if (!get_reqs_available(ctx))
-			return NULL;
-	}
-
-	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
+	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
 	if (unlikely(!req))
-		goto out_put;
+		return NULL;
 
 	percpu_ref_get(&ctx->reqs);
+	req->ki_ctx = ctx;
 	INIT_LIST_HEAD(&req->ki_list);
 	refcount_set(&req->ki_refcnt, 0);
-	req->ki_ctx = ctx;
+	req->ki_eventfd = NULL;
 	return req;
-out_put:
-	put_reqs_available(ctx, 1);
-	return NULL;
 }
 
 static struct kioctx *lookup_ioctx(unsigned long ctx_id)
@@ -1059,6 +1065,15 @@ static inline void iocb_put(struct aio_kiocb *iocb)
 	}
 }
 
+static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb,
+			   long res, long res2)
+{
+	ev->obj = (u64)(unsigned long)iocb->ki_user_iocb;
+	ev->data = iocb->ki_user_data;
+	ev->res = res;
+	ev->res2 = res2;
+}
+
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
@@ -1086,10 +1101,7 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 	ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
 	event = ev_page + pos % AIO_EVENTS_PER_PAGE;
 
-	event->obj = (u64)(unsigned long)iocb->ki_user_iocb;
-	event->data = iocb->ki_user_data;
-	event->res = res;
-	event->res2 = res2;
+	aio_fill_event(event, iocb, res, res2);
 
 	kunmap_atomic(ev_page);
 	flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
@@ -1416,7 +1428,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
 	aio_complete(iocb, res, res2);
 }
 
-static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
 {
 	int ret;
 
@@ -1457,7 +1469,7 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
 	return ret;
 }
 
-static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
+static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec,
 		bool vectored, bool compat, struct iov_iter *iter)
 {
 	void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf;
@@ -1492,12 +1504,12 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
 		ret = -EINTR;
 		/*FALLTHRU*/
 	default:
-		aio_complete_rw(req, ret, 0);
+		req->ki_complete(req, ret, 0);
 	}
 }
 
-static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
-		bool compat)
+static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb,
+			bool vectored, bool compat)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
@@ -1529,8 +1541,8 @@ static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 	return ret;
 }
 
-static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
-		bool compat)
+static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
+			 bool vectored, bool compat)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
@@ -1585,7 +1597,8 @@ static void aio_fsync_work(struct work_struct *work)
 	aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
 }
 
-static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
+static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
+		     bool datasync)
 {
 	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
 			iocb->aio_rw_flags))
@@ -1713,7 +1726,7 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 	add_wait_queue(head, &pt->iocb->poll.wait);
 }
 
-static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
 {
 	struct kioctx *ctx = aiocb->ki_ctx;
 	struct poll_iocb *req = &aiocb->poll;
@@ -1733,6 +1746,10 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
 	if (unlikely(!req->file))
 		return -EBADF;
 
+	req->head = NULL;
+	req->woken = false;
+	req->cancelled = false;
+
 	apt.pt._qproc = aio_poll_queue_proc;
 	apt.pt._key = req->events;
 	apt.iocb = aiocb;
@@ -1781,44 +1798,44 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
 	return 0;
 }
 
-static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 bool compat)
+static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
+			   struct iocb __user *user_iocb, bool compat)
 {
 	struct aio_kiocb *req;
-	struct iocb iocb;
 	ssize_t ret;
 
-	if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
-		return -EFAULT;
-
 	/* enforce forwards compatibility on users */
-	if (unlikely(iocb.aio_reserved2)) {
+	if (unlikely(iocb->aio_reserved2)) {
 		pr_debug("EINVAL: reserve field set\n");
 		return -EINVAL;
 	}
 
 	/* prevent overflows */
 	if (unlikely(
-	    (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
-	    (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
-	    ((ssize_t)iocb.aio_nbytes < 0)
+	    (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
+	    (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
+	    ((ssize_t)iocb->aio_nbytes < 0)
 	   )) {
 		pr_debug("EINVAL: overflow check\n");
 		return -EINVAL;
 	}
 
+	if (!get_reqs_available(ctx))
+		return -EAGAIN;
+
+	ret = -EAGAIN;
 	req = aio_get_req(ctx);
 	if (unlikely(!req))
-		return -EAGAIN;
+		goto out_put_reqs_available;
 
-	if (iocb.aio_flags & IOCB_FLAG_RESFD) {
+	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
 		 * instance of the file* now. The file descriptor must be
 		 * an eventfd() fd, and will be signaled for each completed
 		 * event using the eventfd_signal() function.
 		 */
-		req->ki_eventfd = eventfd_ctx_fdget((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;
@@ -1833,32 +1850,32 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	}
 
 	req->ki_user_iocb = user_iocb;
-	req->ki_user_data = iocb.aio_data;
+	req->ki_user_data = iocb->aio_data;
 
-	switch (iocb.aio_lio_opcode) {
+	switch (iocb->aio_lio_opcode) {
 	case IOCB_CMD_PREAD:
-		ret = aio_read(&req->rw, &iocb, false, compat);
+		ret = aio_read(&req->rw, iocb, false, compat);
 		break;
 	case IOCB_CMD_PWRITE:
-		ret = aio_write(&req->rw, &iocb, false, compat);
+		ret = aio_write(&req->rw, iocb, false, compat);
 		break;
 	case IOCB_CMD_PREADV:
-		ret = aio_read(&req->rw, &iocb, true, compat);
+		ret = aio_read(&req->rw, iocb, true, compat);
 		break;
 	case IOCB_CMD_PWRITEV:
-		ret = aio_write(&req->rw, &iocb, true, compat);
+		ret = aio_write(&req->rw, iocb, true, compat);
 		break;
 	case IOCB_CMD_FSYNC:
-		ret = aio_fsync(&req->fsync, &iocb, false);
+		ret = aio_fsync(&req->fsync, iocb, false);
 		break;
 	case IOCB_CMD_FDSYNC:
-		ret = aio_fsync(&req->fsync, &iocb, true);
+		ret = aio_fsync(&req->fsync, iocb, true);
 		break;
 	case IOCB_CMD_POLL:
-		ret = aio_poll(req, &iocb);
+		ret = aio_poll(req, iocb);
 		break;
 	default:
-		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
+		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
 		ret = -EINVAL;
 		break;
 	}
@@ -1872,14 +1889,25 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		goto out_put_req;
 	return 0;
 out_put_req:
-	put_reqs_available(ctx, 1);
-	percpu_ref_put(&ctx->reqs);
 	if (req->ki_eventfd)
 		eventfd_ctx_put(req->ki_eventfd);
-	kmem_cache_free(kiocb_cachep, req);
+	iocb_put(req);
+out_put_reqs_available:
+	put_reqs_available(ctx, 1);
 	return ret;
 }
 
+static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
+			 bool compat)
+{
+	struct iocb iocb;
+
+	if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
+		return -EFAULT;
+
+	return __io_submit_one(ctx, &iocb, user_iocb, compat);
+}
+
 /* sys_io_submit:
  *	Queue the nr iocbs pointed to by iocbpp for processing.  Returns
  *	the number of iocbs queued.  May return -EINVAL if the aio_context
@@ -1912,6 +1940,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 	if (nr > ctx->nr_events)
 		nr = ctx->nr_events;
 
+	if (nr > AIO_PLUG_THRESHOLD)
 		blk_start_plug(&plug);
 	for (i = 0; i < nr; i++) {
 		struct iocb __user *user_iocb;
@@ -1925,6 +1954,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 		if (ret)
 			break;
 	}
+	if (nr > AIO_PLUG_THRESHOLD)
 		blk_finish_plug(&plug);
 
 	percpu_ref_put(&ctx->users);
@@ -1952,6 +1982,7 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
 	if (nr > ctx->nr_events)
 		nr = ctx->nr_events;
 
+	if (nr > AIO_PLUG_THRESHOLD)
 		blk_start_plug(&plug);
 	for (i = 0; i < nr; i++) {
 		compat_uptr_t user_iocb;
@@ -1965,6 +1996,7 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
 		if (ret)
 			break;
 	}
+	if (nr > AIO_PLUG_THRESHOLD)
 		blk_finish_plug(&plug);
 
 	percpu_ref_put(&ctx->users);