Merge branch 'async-buffered.8' into for-5.9/io_uring

Pull in async buffered reads branch.

* async-buffered.8:
  io_uring: support true async buffered reads, if file provides it
  mm: add kiocb_wait_page_queue_init() helper
  btrfs: flag files as supporting buffered async reads
  xfs: flag files as supporting buffered async reads
  block: flag block devices as supporting IOCB_WAITQ
  fs: add FMODE_BUF_RASYNC
  mm: support async buffered reads in generic_file_buffered_read()
  mm: add support for async page locking
  mm: abstract out wake_page_match() from wake_page_function()
  mm: allow read-ahead with IOCB_NOWAIT set
  io_uring: re-issue block requests that failed because of resources
  io_uring: catch -EIO from buffered issue request failure
  io_uring: always plug for any number of IOs
  block: provide plug based way of signaling forced no-wait semantics

block/blk-core.c

@@ -958,6 +958,7 @@ generic_make_request_checks(struct bio *bio)
 	struct request_queue *q;
 	int nr_sectors = bio_sectors(bio);
 	blk_status_t status = BLK_STS_IOERR;
+	struct blk_plug *plug;
 	char b[BDEVNAME_SIZE];
 
 	might_sleep();
@@ -971,6 +972,10 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
+	plug = blk_mq_plug(q, bio);
+	if (plug && plug->nowait)
+		bio->bi_opf |= REQ_NOWAIT;
+
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
 	 * if queue is not a request based queue.
@@ -1800,6 +1805,7 @@ void blk_start_plug(struct blk_plug *plug)
 	INIT_LIST_HEAD(&plug->cb_list);
 	plug->rq_count = 0;
 	plug->multiple_queues = false;
+	plug->nowait = false;
 
 	/*
 	 * Store ordering should not be needed here, since a potential

fs/block_dev.c

@@ -1851,7 +1851,7 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	 */
 	filp->f_flags |= O_LARGEFILE;
 
-	filp->f_mode |= FMODE_NOWAIT;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
 
 	if (filp->f_flags & O_NDELAY)
 		filp->f_mode |= FMODE_NDELAY;

fs/btrfs/file.c

@@ -3472,7 +3472,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 
 static int btrfs_file_open(struct inode *inode, struct file *filp)
 {
-	filp->f_mode |= FMODE_NOWAIT;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
 	return generic_file_open(inode, filp);
 }
 

fs/xfs/xfs_file.c

@@ -1080,7 +1080,7 @@ xfs_file_open(
 		return -EFBIG;
 	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
 		return -EIO;
-	file->f_mode |= FMODE_NOWAIT;
+	file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
 	return 0;
 }
 

include/linux/blkdev.h

@@ -1189,6 +1189,7 @@ struct blk_plug {
 	struct list_head cb_list; /* md requires an unplug callback */
 	unsigned short rq_count;
 	bool multiple_queues;
+	bool nowait;
 };
 #define BLK_MAX_REQUEST_COUNT 16
 #define BLK_PLUG_FLUSH_SIZE (128 * 1024)

include/linux/fs.h

@@ -175,6 +175,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File does not contribute to nr_files count */
 #define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
 
+/* File supports async buffered reads */
+#define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
@@ -315,6 +318,8 @@ enum rw_hint {
 #define IOCB_SYNC		(1 << 5)
 #define IOCB_WRITE		(1 << 6)
 #define IOCB_NOWAIT		(1 << 7)
+/* iocb->ki_waitq is valid */
+#define IOCB_WAITQ		(1 << 8)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -328,7 +333,10 @@ struct kiocb {
 	int			ki_flags;
 	u16			ki_hint;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	unsigned int		ki_cookie; /* for ->iopoll */
+	union {
+		unsigned int		ki_cookie; /* for ->iopoll */
+		struct wait_page_queue	*ki_waitq; /* for async buffered IO */
+	};
 
 	randomized_struct_fields_end
 };

include/linux/pagemap.h

@@ -496,8 +496,67 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 	return pgoff;
 }
 
+/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
+struct wait_page_key {
+	struct page *page;
+	int bit_nr;
+	int page_match;
+};
+
+struct wait_page_queue {
+	struct page *page;
+	int bit_nr;
+	wait_queue_entry_t wait;
+};
+
+static inline int wake_page_match(struct wait_page_queue *wait_page,
+				  struct wait_page_key *key)
+{
+	if (wait_page->page != key->page)
+	       return 0;
+	key->page_match = 1;
+
+	if (wait_page->bit_nr != key->bit_nr)
+		return 0;
+
+	/*
+	 * Stop walking if it's locked.
+	 * Is this safe if put_and_wait_on_page_locked() is in use?
+	 * Yes: the waker must hold a reference to this page, and if PG_locked
+	 * has now already been set by another task, that task must also hold
+	 * a reference to the *same usage* of this page; so there is no need
+	 * to walk on to wake even the put_and_wait_on_page_locked() callers.
+	 */
+	if (test_bit(key->bit_nr, &key->page->flags))
+		return -1;
+
+	return 1;
+}
+
+static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb,
+					     struct wait_page_queue *wait,
+					     wait_queue_func_t func,
+					     void *data)
+{
+	/* Can't support async wakeup with polled IO */
+	if (kiocb->ki_flags & IOCB_HIPRI)
+		return -EINVAL;
+	if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) {
+		wait->wait.func = func;
+		wait->wait.private = data;
+		wait->wait.flags = 0;
+		INIT_LIST_HEAD(&wait->wait.entry);
+		kiocb->ki_flags |= IOCB_WAITQ;
+		kiocb->ki_waitq = wait;
+		return 0;
+	}
+
+	return -EOPNOTSUPP;
+}
+
 extern void __lock_page(struct page *page);
 extern int __lock_page_killable(struct page *page);
+extern int __lock_page_async(struct page *page, struct wait_page_queue *wait);
 extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
@@ -534,6 +593,22 @@ static inline int lock_page_killable(struct page *page)
 	return 0;
 }
 
+/*
+ * lock_page_async - Lock the page, unless this would block. If the page
+ * is already locked, then queue a callback when the page becomes unlocked.
+ * This callback can then retry the operation.
+ *
+ * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page
+ * was already locked and the callback defined in 'wait' was queued.
+ */
+static inline int lock_page_async(struct page *page,
+				  struct wait_page_queue *wait)
+{
+	if (!trylock_page(page))
+		return __lock_page_async(page, wait);
+	return 0;
+}
+
 /*
  * lock_page_or_retry - Lock the page, unless this would block and the
  * caller indicated that it can handle a retry.

mm/filemap.c

@@ -987,43 +987,16 @@ void __init pagecache_init(void)
 	page_writeback_init();
 }
 
-/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
-struct wait_page_key {
-	struct page *page;
-	int bit_nr;
-	int page_match;
-};
-
-struct wait_page_queue {
-	struct page *page;
-	int bit_nr;
-	wait_queue_entry_t wait;
-};
-
 static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
 		= container_of(wait, struct wait_page_queue, wait);
+	int ret;
 
-	if (wait_page->page != key->page)
-	       return 0;
-	key->page_match = 1;
-
-	if (wait_page->bit_nr != key->bit_nr)
-		return 0;
-
-	/*
-	 * Stop walking if it's locked.
-	 * Is this safe if put_and_wait_on_page_locked() is in use?
-	 * Yes: the waker must hold a reference to this page, and if PG_locked
-	 * has now already been set by another task, that task must also hold
-	 * a reference to the *same usage* of this page; so there is no need
-	 * to walk on to wake even the put_and_wait_on_page_locked() callers.
-	 */
-	if (test_bit(key->bit_nr, &key->page->flags))
-		return -1;
-
+	ret = wake_page_match(wait_page, key);
+	if (ret != 1)
+		return ret;
 	return autoremove_wake_function(wait, mode, sync, key);
 }
 
@@ -1207,6 +1180,44 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
 }
 EXPORT_SYMBOL(wait_on_page_bit_killable);
 
+static int __wait_on_page_locked_async(struct page *page,
+				       struct wait_page_queue *wait, bool set)
+{
+	struct wait_queue_head *q = page_waitqueue(page);
+	int ret = 0;
+
+	wait->page = page;
+	wait->bit_nr = PG_locked;
+
+	spin_lock_irq(&q->lock);
+	__add_wait_queue_entry_tail(q, &wait->wait);
+	SetPageWaiters(page);
+	if (set)
+		ret = !trylock_page(page);
+	else
+		ret = PageLocked(page);
+	/*
+	 * If we were succesful now, we know we're still on the
+	 * waitqueue as we're still under the lock. This means it's
+	 * safe to remove and return success, we know the callback
+	 * isn't going to trigger.
+	 */
+	if (!ret)
+		__remove_wait_queue(q, &wait->wait);
+	else
+		ret = -EIOCBQUEUED;
+	spin_unlock_irq(&q->lock);
+	return ret;
+}
+
+static int wait_on_page_locked_async(struct page *page,
+				     struct wait_page_queue *wait)
+{
+	if (!PageLocked(page))
+		return 0;
+	return __wait_on_page_locked_async(compound_head(page), wait, false);
+}
+
 /**
  * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
  * @page: The page to wait for.
@@ -1369,6 +1380,11 @@ int __lock_page_killable(struct page *__page)
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
+int __lock_page_async(struct page *page, struct wait_page_queue *wait)
+{
+	return __wait_on_page_locked_async(page, wait, true);
+}
+
 /*
  * Return values:
  * 1 - page is locked; mmap_lock is still held.
@@ -2028,8 +2044,6 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 
 		page = find_get_page(mapping, index);
 		if (!page) {
-			if (iocb->ki_flags & IOCB_NOWAIT)
-				goto would_block;
 			page_cache_sync_readahead(mapping,
 					ra, filp,
 					index, last_index - index);
@@ -2043,17 +2057,25 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 					index, last_index - index);
 		}
 		if (!PageUptodate(page)) {
-			if (iocb->ki_flags & IOCB_NOWAIT) {
-				put_page(page);
-				goto would_block;
-			}
-
 			/*
 			 * See comment in do_read_cache_page on why
 			 * wait_on_page_locked is used to avoid unnecessarily
 			 * serialisations and why it's safe.
 			 */
-			error = wait_on_page_locked_killable(page);
+			if (iocb->ki_flags & IOCB_WAITQ) {
+				if (written) {
+					put_page(page);
+					goto out;
+				}
+				error = wait_on_page_locked_async(page,
+								iocb->ki_waitq);
+			} else {
+				if (iocb->ki_flags & IOCB_NOWAIT) {
+					put_page(page);
+					goto would_block;
+				}
+				error = wait_on_page_locked_killable(page);
+			}
 			if (unlikely(error))
 				goto readpage_error;
 			if (PageUptodate(page))
@@ -2141,7 +2163,10 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 
 page_not_up_to_date:
 		/* Get exclusive access to the page ... */
-		error = lock_page_killable(page);
+		if (iocb->ki_flags & IOCB_WAITQ)
+			error = lock_page_async(page, iocb->ki_waitq);
+		else
+			error = lock_page_killable(page);
 		if (unlikely(error))
 			goto readpage_error;
 
@@ -2160,6 +2185,11 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		}
 
 readpage:
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			unlock_page(page);
+			put_page(page);
+			goto would_block;
+		}
 		/*
 		 * A previous I/O error may have been due to temporary
 		 * failures, eg. multipath errors.