Merge tag 'for-5.9/io_uring-20200802' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "Lots of cleanups in here, hardening the code and/or making it easier
  to read and fixing bugs, but a core feature/change too adding support
  for real async buffered reads. With the latter in place, we just need
  buffered write async support and we're done relying on kthreads for
  the fast path. In detail:

   - Cleanup how memory accounting is done on ring setup/free (Bijan)

   - sq array offset calculation fixup (Dmitry)

   - Consistently handle blocking off O_DIRECT submission path (me)

   - Support proper async buffered reads, instead of relying on kthread
     offload for that. This uses the page waitqueue to drive retries
     from task_work, like we handle poll based retry. (me)

   - IO completion optimizations (me)

   - Fix race with accounting and ring fd install (me)

   - Support EPOLLEXCLUSIVE (Jiufei)

   - Get rid of the io_kiocb unionizing, made possible by shrinking
     other bits (Pavel)

   - Completion side cleanups (Pavel)

   - Cleanup REQ_F_ flags handling, and kill off many of them (Pavel)

   - Request environment grabbing cleanups (Pavel)

   - File and socket read/write cleanups (Pavel)

   - Improve kiocb_set_rw_flags() (Pavel)

   - Tons of fixes and cleanups (Pavel)

   - IORING_SQ_NEED_WAKEUP clear fix (Xiaoguang)"

* tag 'for-5.9/io_uring-20200802' of git://git.kernel.dk/linux-block: (127 commits)
  io_uring: flip if handling after io_setup_async_rw
  fs: optimise kiocb_set_rw_flags()
  io_uring: don't touch 'ctx' after installing file descriptor
  io_uring: get rid of atomic FAA for cq_timeouts
  io_uring: consolidate *_check_overflow accounting
  io_uring: fix stalled deferred requests
  io_uring: fix racy overflow count reporting
  io_uring: deduplicate __io_complete_rw()
  io_uring: de-unionise io_kiocb
  io-wq: update hash bits
  io_uring: fix missing io_queue_linked_timeout()
  io_uring: mark ->work uninitialised after cleanup
  io_uring: deduplicate io_grab_files() calls
  io_uring: don't do opcode prep twice
  io_uring: clear IORING_SQ_NEED_WAKEUP after executing task works
  io_uring: batch put_task_struct()
  tasks: add put_task_struct_many()
  io_uring: return locked and pinned page accounting
  io_uring: don't miscount pinned memory
  io_uring: don't open-code recv kbuf managment
  ...

1 files changed, 64 insertions, 27 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 991503bbf922..9f131f1cfde3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -987,19 +987,6 @@ 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)
 {
 	int ret;
@@ -1007,11 +994,7 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
 	struct wait_page_queue *wait_page
 		= container_of(wait, struct wait_page_queue, wait);
 
-	if (wait_page->page != key->page)
-	       return 0;
-	key->page_match = 1;
-
-	if (wait_page->bit_nr != key->bit_nr)
+	if (!wake_page_match(wait_page, key))
 		return 0;
 
 	/*
@@ -1240,6 +1223,44 @@ 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.
@@ -1402,6 +1423,11 @@ 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.
@@ -2061,7 +2087,7 @@ find_page:
 
 		page = find_get_page(mapping, index);
 		if (!page) {
-			if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
+			if (iocb->ki_flags & IOCB_NOIO)
 				goto would_block;
 			page_cache_sync_readahead(mapping,
 					ra, filp,
@@ -2080,17 +2106,25 @@ find_page:
 					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))
@@ -2178,7 +2212,10 @@ page_ok:
 
 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;
 
@@ -2197,7 +2234,7 @@ page_not_up_to_date_locked:
 		}
 
 readpage:
-		if (iocb->ki_flags & IOCB_NOIO) {
+		if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) {
 			unlock_page(page);
 			put_page(page);
 			goto would_block;