1 files changed, 43 insertions, 19 deletions

diff --git a/mm/mlock.c b/mm/mlock.c
index d480cd6..10819ed 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -133,7 +133,10 @@ static void __munlock_isolation_failed(struct page *page)
 
 /**
  * munlock_vma_page - munlock a vma page
- * @page - page to be unlocked
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ *         HPAGE_PMD_NR - 1 for THP head page)
  *
  * called from munlock()/munmap() path with page supposedly on the LRU.
  * When we munlock a page, because the vma where we found the page is being
@@ -148,21 +151,30 @@ static void __munlock_isolation_failed(struct page *page)
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int page_mask = 0;
+	unsigned int nr_pages;
 
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
-		unsigned int nr_pages = hpage_nr_pages(page);
+		nr_pages = hpage_nr_pages(page);
 		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
-		page_mask = nr_pages - 1;
 		if (!isolate_lru_page(page))
 			__munlock_isolated_page(page);
 		else
 			__munlock_isolation_failed(page);
+	} else {
+		nr_pages = hpage_nr_pages(page);
 	}
 
-	return page_mask;
+	/*
+	 * Regardless of the original PageMlocked flag, we determine nr_pages
+	 * after touching the flag. This leaves a possible race with a THP page
+	 * split, such that a whole THP page was munlocked, but nr_pages == 1.
+	 * Returning a smaller mask due to that is OK, the worst that can
+	 * happen is subsequent useless scanning of the former tail pages.
+	 * The NR_MLOCK accounting can however become broken.
+	 */
+	return nr_pages - 1;
 }
 
 /**
@@ -286,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked = -nr;
+	int delta_munlocked;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
+	pagevec_init(&pvec_putback, 0);
+
 	/* Phase 1: page isolation */
 	spin_lock_irq(&zone->lru_lock);
 	for (i = 0; i < nr; i++) {
@@ -318,18 +332,21 @@ skip_munlock:
 			/*
 			 * We won't be munlocking this page in the next phase
 			 * but we still need to release the follow_page_mask()
-			 * pin.
+			 * pin. We cannot do it under lru_lock however. If it's
+			 * the last pin, __page_cache_release would deadlock.
 			 */
+			pagevec_add(&pvec_putback, pvec->pages[i]);
 			pvec->pages[i] = NULL;
-			put_page(page);
-			delta_munlocked++;
 		}
 	}
+	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(&zone->lru_lock);
 
+	/* Now we can release pins of pages that we are not munlocking */
+	pagevec_release(&pvec_putback);
+
 	/* Phase 2: page munlock */
-	pagevec_init(&pvec_putback, 0);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -440,7 +457,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page = NULL;
-		unsigned int page_mask, page_increm;
+		unsigned int page_mask;
+		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
 		int zoneid;
@@ -490,7 +508,9 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				goto next;
 			}
 		}
-		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+		/* It's a bug to munlock in the middle of a THP page */
+		VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+		page_increm = 1 + page_mask;
 		start += page_increm * PAGE_SIZE;
 next:
 		cond_resched();
@@ -689,19 +709,21 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 	lru_add_drain_all();	/* flush pagevec */
 
-	down_write(&current->mm->mmap_sem);
 	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
 	start &= PAGE_MASK;
 
-	locked = len >> PAGE_SHIFT;
-	locked += current->mm->locked_vm;
-
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
+	locked = len >> PAGE_SHIFT;
+
+	down_write(&current->mm->mmap_sem);
+
+	locked += current->mm->locked_vm;
 
 	/* check against resource limits */
 	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
 		error = do_mlock(start, len, 1);
+
 	up_write(&current->mm->mmap_sem);
 	if (!error)
 		error = __mm_populate(start, len, 0);
@@ -712,11 +734,13 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
-	down_write(&current->mm->mmap_sem);
 	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
 	start &= PAGE_MASK;
+
+	down_write(&current->mm->mmap_sem);
 	ret = do_mlock(start, len, 0);
 	up_write(&current->mm->mmap_sem);
+
 	return ret;
 }
 
@@ -761,12 +785,12 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	if (flags & MCL_CURRENT)
 		lru_add_drain_all();	/* flush pagevec */
 
-	down_write(&current->mm->mmap_sem);
-
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
 
 	ret = -ENOMEM;
+	down_write(&current->mm->mmap_sem);
+
 	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
 	    capable(CAP_IPC_LOCK))
 		ret = do_mlockall(flags);