1 files changed, 335 insertions, 58 deletions

diff --git a/mm/mlock.c b/mm/mlock.c
index 79b7cf7d1bc..b1eb5363400 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -11,6 +11,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/pagemap.h>
+#include <linux/pagevec.h>
 #include <linux/mempolicy.h>
 #include <linux/syscalls.h>
 #include <linux/sched.h>
@@ -18,6 +19,8 @@
 #include <linux/rmap.h>
 #include <linux/mmzone.h>
 #include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
 
 #include "internal.h"
 
@@ -76,6 +79,7 @@ void clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -87,9 +91,73 @@ void mlock_vma_page(struct page *page)
 	}
 }
 
+/*
+ * Isolate a page from LRU with optional get_page() pin.
+ * Assumes lru_lock already held and page already pinned.
+ */
+static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
+{
+	if (PageLRU(page)) {
+		struct lruvec *lruvec;
+
+		lruvec = mem_cgroup_page_lruvec(page, page_zone(page));
+		if (getpage)
+			get_page(page);
+		ClearPageLRU(page);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Finish munlock after successful page isolation
+ *
+ * Page must be locked. This is a wrapper for try_to_munlock()
+ * and putback_lru_page() with munlock accounting.
+ */
+static void __munlock_isolated_page(struct page *page)
+{
+	int ret = SWAP_AGAIN;
+
+	/*
+	 * Optimization: if the page was mapped just once, that's our mapping
+	 * and we don't need to check all the other vmas.
+	 */
+	if (page_mapcount(page) > 1)
+		ret = try_to_munlock(page);
+
+	/* Did try_to_unlock() succeed or punt? */
+	if (ret != SWAP_MLOCK)
+		count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+
+	putback_lru_page(page);
+}
+
+/*
+ * Accounting for page isolation fail during munlock
+ *
+ * Performs accounting when page isolation fails in munlock. There is nothing
+ * else to do because it means some other task has already removed the page
+ * from the LRU. putback_lru_page() will take care of removing the page from
+ * the unevictable list, if necessary. vmscan [page_referenced()] will move
+ * the page back to the unevictable list if some other vma has it mlocked.
+ */
+static void __munlock_isolation_failed(struct page *page)
+{
+	if (PageUnevictable(page))
+		__count_vm_event(UNEVICTABLE_PGSTRANDED);
+	else
+		__count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+}
+
 /**
  * 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
@@ -104,48 +172,37 @@ void mlock_vma_page(struct page *page)
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int page_mask = 0;
+	unsigned int nr_pages;
+	struct zone *zone = page_zone(page);
 
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
-	if (TestClearPageMlocked(page)) {
-		unsigned int 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)) {
-			int ret = SWAP_AGAIN;
+	/*
+	 * Serialize with any parallel __split_huge_page_refcount() which
+	 * might otherwise copy PageMlocked to part of the tail pages before
+	 * we clear it in the head page. It also stabilizes hpage_nr_pages().
+	 */
+	spin_lock_irq(&zone->lru_lock);
 
-			/*
-			 * Optimization: if the page was mapped just once,
-			 * that's our mapping and we don't need to check all the
-			 * other vmas.
-			 */
-			if (page_mapcount(page) > 1)
-				ret = try_to_munlock(page);
-			/*
-			 * did try_to_unlock() succeed or punt?
-			 */
-			if (ret != SWAP_MLOCK)
-				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+	nr_pages = hpage_nr_pages(page);
+	if (!TestClearPageMlocked(page))
+		goto unlock_out;
 
-			putback_lru_page(page);
-		} else {
-			/*
-			 * Some other task has removed the page from the LRU.
-			 * putback_lru_page() will take care of removing the
-			 * page from the unevictable list, if necessary.
-			 * vmscan [page_referenced()] will move the page back
-			 * to the unevictable list if some other vma has it
-			 * mlocked.
-			 */
-			if (PageUnevictable(page))
-				count_vm_event(UNEVICTABLE_PGSTRANDED);
-			else
-				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
-		}
+	__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
+
+	if (__munlock_isolate_lru_page(page, true)) {
+		spin_unlock_irq(&zone->lru_lock);
+		__munlock_isolated_page(page);
+		goto out;
 	}
+	__munlock_isolation_failed(page);
 
-	return page_mask;
+unlock_out:
+	spin_unlock_irq(&zone->lru_lock);
+
+out:
+	return nr_pages - 1;
 }
 
 /**
@@ -210,6 +267,190 @@ static int __mlock_posix_error_return(long retval)
 }
 
 /*
+ * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec()
+ *
+ * The fast path is available only for evictable pages with single mapping.
+ * Then we can bypass the per-cpu pvec and get better performance.
+ * when mapcount > 1 we need try_to_munlock() which can fail.
+ * when !page_evictable(), we need the full redo logic of putback_lru_page to
+ * avoid leaving evictable page in unevictable list.
+ *
+ * In case of success, @page is added to @pvec and @pgrescued is incremented
+ * in case that the page was previously unevictable. @page is also unlocked.
+ */
+static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec,
+		int *pgrescued)
+{
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+	if (page_mapcount(page) <= 1 && page_evictable(page)) {
+		pagevec_add(pvec, page);
+		if (TestClearPageUnevictable(page))
+			(*pgrescued)++;
+		unlock_page(page);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Putback multiple evictable pages to the LRU
+ *
+ * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of
+ * the pages might have meanwhile become unevictable but that is OK.
+ */
+static void __putback_lru_fast(struct pagevec *pvec, int pgrescued)
+{
+	count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec));
+	/*
+	 *__pagevec_lru_add() calls release_pages() so we don't call
+	 * put_page() explicitly
+	 */
+	__pagevec_lru_add(pvec);
+	count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
+}
+
+/*
+ * Munlock a batch of pages from the same zone
+ *
+ * The work is split to two main phases. First phase clears the Mlocked flag
+ * and attempts to isolate the pages, all under a single zone lru lock.
+ * The second phase finishes the munlock only for pages where isolation
+ * succeeded.
+ *
+ * Note that the pagevec may be modified during the process.
+ */
+static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
+{
+	int i;
+	int nr = pagevec_count(pvec);
+	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++) {
+		struct page *page = pvec->pages[i];
+
+		if (TestClearPageMlocked(page)) {
+			/*
+			 * We already have pin from follow_page_mask()
+			 * so we can spare the get_page() here.
+			 */
+			if (__munlock_isolate_lru_page(page, false))
+				continue;
+			else
+				__munlock_isolation_failed(page);
+		}
+
+		/*
+		 * We won't be munlocking this page in the next phase
+		 * but we still need to release the follow_page_mask()
+		 * 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;
+	}
+	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 */
+	for (i = 0; i < nr; i++) {
+		struct page *page = pvec->pages[i];
+
+		if (page) {
+			lock_page(page);
+			if (!__putback_lru_fast_prepare(page, &pvec_putback,
+					&pgrescued)) {
+				/*
+				 * Slow path. We don't want to lose the last
+				 * pin before unlock_page()
+				 */
+				get_page(page); /* for putback_lru_page() */
+				__munlock_isolated_page(page);
+				unlock_page(page);
+				put_page(page); /* from follow_page_mask() */
+			}
+		}
+	}
+
+	/*
+	 * Phase 3: page putback for pages that qualified for the fast path
+	 * This will also call put_page() to return pin from follow_page_mask()
+	 */
+	if (pagevec_count(&pvec_putback))
+		__putback_lru_fast(&pvec_putback, pgrescued);
+}
+
+/*
+ * Fill up pagevec for __munlock_pagevec using pte walk
+ *
+ * The function expects that the struct page corresponding to @start address is
+ * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone.
+ *
+ * The rest of @pvec is filled by subsequent pages within the same pmd and same
+ * zone, as long as the pte's are present and vm_normal_page() succeeds. These
+ * pages also get pinned.
+ *
+ * Returns the address of the next page that should be scanned. This equals
+ * @start + PAGE_SIZE when no page could be added by the pte walk.
+ */
+static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
+		struct vm_area_struct *vma, int zoneid,	unsigned long start,
+		unsigned long end)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	/*
+	 * Initialize pte walk starting at the already pinned page where we
+	 * are sure that there is a pte, as it was pinned under the same
+	 * mmap_sem write op.
+	 */
+	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
+	/* Make sure we do not cross the page table boundary */
+	end = pgd_addr_end(start, end);
+	end = pud_addr_end(start, end);
+	end = pmd_addr_end(start, end);
+
+	/* The page next to the pinned page is the first we will try to get */
+	start += PAGE_SIZE;
+	while (start < end) {
+		struct page *page = NULL;
+		pte++;
+		if (pte_present(*pte))
+			page = vm_normal_page(vma, start, *pte);
+		/*
+		 * Break if page could not be obtained or the page's node+zone does not
+		 * match
+		 */
+		if (!page || page_zone_id(page) != zoneid)
+			break;
+
+		get_page(page);
+		/*
+		 * Increase the address that will be returned *before* the
+		 * eventual break due to pvec becoming full by adding the page
+		 */
+		start += PAGE_SIZE;
+		if (pagevec_add(pvec, page) == 0)
+			break;
+	}
+	pte_unmap_unlock(pte, ptl);
+	return start;
+}
+
+/*
  * munlock_vma_pages_range() - munlock all pages in the vma range.'
  * @vma - vma containing range to be munlock()ed.
  * @start - start address in @vma of the range
@@ -233,9 +474,14 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 	vma->vm_flags &= ~VM_LOCKED;
 
 	while (start < end) {
-		struct page *page;
-		unsigned int page_mask, page_increm;
-
+		struct page *page = NULL;
+		unsigned int page_mask;
+		unsigned long page_increm;
+		struct pagevec pvec;
+		struct zone *zone;
+		int zoneid;
+
+		pagevec_init(&pvec, 0);
 		/*
 		 * Although FOLL_DUMP is intended for get_dump_page(),
 		 * it just so happens that its special treatment of the
@@ -244,21 +490,47 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 		 * has sneaked into the range, we won't oops here: great).
 		 */
 		page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
-					&page_mask);
+				&page_mask);
+
 		if (page && !IS_ERR(page)) {
-			lock_page(page);
-			lru_add_drain();
-			/*
-			 * Any THP page found by follow_page_mask() may have
-			 * gotten split before reaching munlock_vma_page(),
-			 * so we need to recompute the page_mask here.
-			 */
-			page_mask = munlock_vma_page(page);
-			unlock_page(page);
-			put_page(page);
+			if (PageTransHuge(page)) {
+				lock_page(page);
+				/*
+				 * Any THP page found by follow_page_mask() may
+				 * have gotten split before reaching
+				 * munlock_vma_page(), so we need to recompute
+				 * the page_mask here.
+				 */
+				page_mask = munlock_vma_page(page);
+				unlock_page(page);
+				put_page(page); /* follow_page_mask() */
+			} else {
+				/*
+				 * Non-huge pages are handled in batches via
+				 * pagevec. The pin from follow_page_mask()
+				 * prevents them from collapsing by THP.
+				 */
+				pagevec_add(&pvec, page);
+				zone = page_zone(page);
+				zoneid = page_zone_id(page);
+
+				/*
+				 * Try to fill the rest of pagevec using fast
+				 * pte walk. This will also update start to
+				 * the next page to process. Then munlock the
+				 * pagevec.
+				 */
+				start = __munlock_pagevec_fill(&pvec, vma,
+						zoneid, start, end);
+				__munlock_pagevec(&pvec, zone);
+				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();
 	}
 }
@@ -455,19 +727,21 @@ 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);
@@ -478,11 +752,13 @@ 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;
 }
 
@@ -506,6 +782,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
+		cond_resched();
 	}
 out:
 	return 0;
@@ -526,12 +803,12 @@ 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);