mm: add PageWaiters indicating tasks are waiting for a page bit

Add a new page flag, PageWaiters, to indicate the page waitqueue has
tasks waiting. This can be tested rather than testing waitqueue_active
which requires another cacheline load.

This bit is always set when the page has tasks on page_waitqueue(page),
and is set and cleared under the waitqueue lock. It may be set when
there are no tasks on the waitqueue, which will cause a harmless extra
wakeup check that will clears the bit.

The generic bit-waitqueue infrastructure is no longer used for pages.
Instead, waitqueues are used directly with a custom key type. The
generic code was not flexible enough to have PageWaiters manipulation
under the waitqueue lock (which simplifies concurrency).

This improves the performance of page lock intensive microbenchmarks by
2-3%.

Putting two bits in the same word opens the opportunity to remove the
memory barrier between clearing the lock bit and testing the waiters
bit, after some work on the arch primitives (e.g., ensuring memory
operand widths match and cover both bits).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Andrew Lutomirski <luto@kernel.org>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 150 insertions, 35 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 32be3c8..82f26cd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -739,45 +739,159 @@ EXPORT_SYMBOL(__page_cache_alloc);
  * at a cost of "thundering herd" phenomena during rare hash
  * collisions.
  */
-wait_queue_head_t *page_waitqueue(struct page *page)
+#define PAGE_WAIT_TABLE_BITS 8
+#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
+static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+
+static wait_queue_head_t *page_waitqueue(struct page *page)
 {
-	return bit_waitqueue(page, 0);
+	return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
 }
-EXPORT_SYMBOL(page_waitqueue);
 
-void wait_on_page_bit(struct page *page, int bit_nr)
+void __init pagecache_init(void)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+	int i;
 
-	if (test_bit(bit_nr, &page->flags))
-		__wait_on_bit(page_waitqueue(page), &wait, bit_wait_io,
-							TASK_UNINTERRUPTIBLE);
+	for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(&page_wait_table[i]);
+
+	page_writeback_init();
 }
-EXPORT_SYMBOL(wait_on_page_bit);
 
-int wait_on_page_bit_killable(struct page *page, int bit_nr)
+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_t wait;
+};
+
+static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+	struct wait_page_key *key = arg;
+	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 (!test_bit(bit_nr, &page->flags))
+	if (wait_page->bit_nr != key->bit_nr)
+		return 0;
+	if (test_bit(key->bit_nr, &key->page->flags))
 		return 0;
 
-	return __wait_on_bit(page_waitqueue(page), &wait,
-			     bit_wait_io, TASK_KILLABLE);
+	return autoremove_wake_function(wait, mode, sync, key);
 }
 
-int wait_on_page_bit_killable_timeout(struct page *page,
-				       int bit_nr, unsigned long timeout)
+void wake_up_page_bit(struct page *page, int bit_nr)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+	wait_queue_head_t *q = page_waitqueue(page);
+	struct wait_page_key key;
+	unsigned long flags;
 
-	wait.key.timeout = jiffies + timeout;
-	if (!test_bit(bit_nr, &page->flags))
-		return 0;
-	return __wait_on_bit(page_waitqueue(page), &wait,
-			     bit_wait_io_timeout, TASK_KILLABLE);
+	key.page = page;
+	key.bit_nr = bit_nr;
+	key.page_match = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_locked_key(q, TASK_NORMAL, &key);
+	/*
+	 * It is possible for other pages to have collided on the waitqueue
+	 * hash, so in that case check for a page match. That prevents a long-
+	 * term waiter
+	 *
+	 * It is still possible to miss a case here, when we woke page waiters
+	 * and removed them from the waitqueue, but there are still other
+	 * page waiters.
+	 */
+	if (!waitqueue_active(q) || !key.page_match) {
+		ClearPageWaiters(page);
+		/*
+		 * It's possible to miss clearing Waiters here, when we woke
+		 * our page waiters, but the hashed waitqueue has waiters for
+		 * other pages on it.
+		 *
+		 * That's okay, it's a rare case. The next waker will clear it.
+		 */
+	}
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(wake_up_page_bit);
+
+static inline int wait_on_page_bit_common(wait_queue_head_t *q,
+		struct page *page, int bit_nr, int state, bool lock)
+{
+	struct wait_page_queue wait_page;
+	wait_queue_t *wait = &wait_page.wait;
+	int ret = 0;
+
+	init_wait(wait);
+	wait->func = wake_page_function;
+	wait_page.page = page;
+	wait_page.bit_nr = bit_nr;
+
+	for (;;) {
+		spin_lock_irq(&q->lock);
+
+		if (likely(list_empty(&wait->task_list))) {
+			if (lock)
+				__add_wait_queue_tail_exclusive(q, wait);
+			else
+				__add_wait_queue(q, wait);
+			SetPageWaiters(page);
+		}
+
+		set_current_state(state);
+
+		spin_unlock_irq(&q->lock);
+
+		if (likely(test_bit(bit_nr, &page->flags))) {
+			io_schedule();
+			if (unlikely(signal_pending_state(state, current))) {
+				ret = -EINTR;
+				break;
+			}
+		}
+
+		if (lock) {
+			if (!test_and_set_bit_lock(bit_nr, &page->flags))
+				break;
+		} else {
+			if (!test_bit(bit_nr, &page->flags))
+				break;
+		}
+	}
+
+	finish_wait(q, wait);
+
+	/*
+	 * A signal could leave PageWaiters set. Clearing it here if
+	 * !waitqueue_active would be possible (by open-coding finish_wait),
+	 * but still fail to catch it in the case of wait hash collision. We
+	 * already can fail to clear wait hash collision cases, so don't
+	 * bother with signals either.
+	 */
+
+	return ret;
+}
+
+void wait_on_page_bit(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
+}
+EXPORT_SYMBOL(wait_on_page_bit);
+
+int wait_on_page_bit_killable(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
 }
-EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
 
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
@@ -793,6 +907,7 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
 
 	spin_lock_irqsave(&q->lock, flags);
 	__add_wait_queue(q, waiter);
+	SetPageWaiters(page);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
@@ -874,23 +989,19 @@ EXPORT_SYMBOL_GPL(page_endio);
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
  */
-void __lock_page(struct page *page)
+void __lock_page(struct page *__page)
 {
-	struct page *page_head = compound_head(page);
-	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
-	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
-							TASK_UNINTERRUPTIBLE);
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
 }
 EXPORT_SYMBOL(__lock_page);
 
-int __lock_page_killable(struct page *page)
+int __lock_page_killable(struct page *__page)
 {
-	struct page *page_head = compound_head(page);
-	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
-	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
-					bit_wait_io, TASK_KILLABLE);
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
diff --git a/mm/internal.h b/mm/internal.h
index 44d6889..7aa2ea0 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -36,6 +36,8 @@
 /* Do not use these with a slab allocator */
 #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
 
+void page_writeback_init(void);
+
 int do_swap_page(struct vm_fault *vmf);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
diff --git a/mm/swap.c b/mm/swap.c
index 4dcf852..844baed 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -69,6 +69,7 @@ static void __page_cache_release(struct page *page)
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 	}
+	__ClearPageWaiters(page);
 	mem_cgroup_uncharge(page);
 }
 
@@ -784,6 +785,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 
 		/* Clear Active bit in case of parallel mark_page_accessed */
 		__ClearPageActive(page);
+		__ClearPageWaiters(page);
 
 		list_add(&page->lru, &pages_to_free);
 	}