[PATCH 3/4] PM/Hibernate: Use memory allocations to free memory (rev. 2)

[Rafael J. Wysocki]

From: Rafael J. Wysocki <rjw@xxxxxxx>

Modify the hibernation memory shrinking code so that it will make
memory allocations to free memory instead of using an artificial
memory shrinking mechanism for that.  Remove the shrinking of
memory from the suspend-to-RAM code, where it is not really
necessary.  Finally, remove the no longer used memory shrinking
functions from mm/vmscan.c .

[rev. 2: Use the existing memory bitmaps for marking preallocated
 image pages and use swsusp_free() from releasing them, introduce
 GFP_IMAGE, add comments describing the memory shrinking strategy.]

Signed-off-by: Rafael J. Wysocki <rjw@xxxxxxx>
---
 kernel/power/main.c     |   20 ------
 kernel/power/snapshot.c |  132 +++++++++++++++++++++++++++++++++-----------
 mm/vmscan.c             |  142 ------------------------------------------------
 3 files changed, 101 insertions(+), 193 deletions(-)

Index: linux-2.6/kernel/power/snapshot.c
===================================================================
--- linux-2.6.orig/kernel/power/snapshot.c
+++ linux-2.6/kernel/power/snapshot.c
@@ -1066,41 +1066,97 @@ void swsusp_free(void)
 	buffer = NULL;
 }
 
+/* Helper functions used for the shrinking of memory. */
+
+#ifdef CONFIG_HIGHMEM
+#define GFP_IMAGE	(GFP_KERNEL | __GFP_HIGHMEM | __GFP_NO_OOM_KILL)
+#else
+#define GFP_IMAGE	(GFP_KERNEL | __GFP_NO_OOM_KILL)
+#endif
+
+#define SHRINK_BITE	10000
+
 /**
- *	swsusp_shrink_memory -  Try to free as much memory as needed
+ * prealloc_pages - preallocate given number of pages and mark their PFNs
+ * @nr_pages: Number of pages to allocate.
  *
- *	... but do not OOM-kill anyone
- *
- *	Notice: all userland should be stopped before it is called, or
- *	livelock is possible.
+ * Allocate given number of pages and mark their PFNs in the hibernation memory
+ * bitmaps, so that they can be released by swsusp_free().
+ * Return value: The number of normal (ie. non-highmem) pages allocated or
+ * -ENOMEM on failure.
  */
-
-#define SHRINK_BITE	10000
-static inline unsigned long __shrink_memory(long tmp)
+static long prealloc_pages(long nr_pages)
 {
-	if (tmp > SHRINK_BITE)
-		tmp = SHRINK_BITE;
-	return shrink_all_memory(tmp);
+	long nr_normal = 0;
+
+	while (nr_pages-- > 0) {
+		struct page *page;
+
+		page = alloc_image_page(GFP_IMAGE);
+		if (!page)
+			return -ENOMEM;
+		if (!PageHighMem(page))
+			nr_normal++;
+	}
+
+	return nr_normal;
 }
 
+/**
+ * swsusp_shrink_memory -  Make the kernel release as much memory as needed
+ *
+ * To create a hibernation image it is necessary to make a copy of every page
+ * frame in use.  We also need a number of page frames to be free during
+ * hibernation for allocations made while saving the image and for device
+ * drivers, in case they need to allocate memory from their hibernation
+ * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
+ * respectively, both of which are rough estimates).  To make this happen, we
+ * preallocate memory in SHRINK_BITE chunks in a loop until the following
+ * condition is satisfied:
+ *
+ * [number of preallocated page frames] >=
+ *	(1/2) * ([total number of page frames in use] + PAGES_FOR_IO
+ *		+ SPARE_PAGES - [number of free page frames])
+ *
+ * because in that case, if all of the preallocated page frames are released,
+ * the total number of free page frames will be equal to or greater than the sum
+ * of the total number of page frames in use with PAGES_FOR_IO and SPARE_PAGES,
+ * which is what we need.
+ *
+ * If image_size is set below the number following from the above inequality,
+ * the preallocation of memory is continued until the total number of page
+ * frames in use is below the requested image size.
+ */
 int swsusp_shrink_memory(void)
 {
-	long tmp;
-	struct zone *zone;
-	unsigned long pages = 0;
+	unsigned long pages = 0, alloc_normal = 0, alloc_highmem = 0;
 	unsigned int i = 0;
 	char *p = "-\\|/";
 	struct timeval start, stop;
+	int error = 0;
 
 	printk(KERN_INFO "PM: Shrinking memory...  ");
 	do_gettimeofday(&start);
-	do {
-		long size, highmem_size;
 
-		highmem_size = count_highmem_pages();
-		size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
-		tmp = size;
+	for (;;) {
+		struct zone *zone;
+		long size, highmem_size, tmp, ret;
+
+		/*
+		 * Pages preallocated by this loop are not counted as data pages
+		 * by count_data_pages() and count_highmem_pages(), so we only
+		 * need to subtract their numbers once here to verify the
+		 * satisfaction of the stop condition.
+		 */
+		size = count_data_pages() - alloc_normal;
+		tmp = size + PAGES_FOR_IO + SPARE_PAGES;
+		highmem_size = count_highmem_pages() - alloc_highmem;
 		size += highmem_size;
+		/*
+		 * Highmem is treated differently, because we prefer not to
+		 * store copies of normal page frames in it during image
+		 * creation.
+		 */
 		for_each_populated_zone(zone) {
 			tmp += snapshot_additional_pages(zone);
 			if (is_highmem(zone)) {
@@ -1111,27 +1167,39 @@ int swsusp_shrink_memory(void)
 				tmp += zone->lowmem_reserve[ZONE_NORMAL];
 			}
 		}
-
 		if (highmem_size < 0)
 			highmem_size = 0;
-
 		tmp += highmem_size;
-		if (tmp > 0) {
-			tmp = __shrink_memory(tmp);
-			if (!tmp)
-				return -ENOMEM;
-			pages += tmp;
-		} else if (size > image_size / PAGE_SIZE) {
-			tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
-			pages += tmp;
+
+		if (tmp <= 0 && size > image_size / PAGE_SIZE)
+			tmp = size - (image_size / PAGE_SIZE);
+
+		if (tmp > SHRINK_BITE)
+			tmp = SHRINK_BITE;
+		else if (tmp <= 0)
+			break;
+
+		ret = prealloc_pages(tmp);
+		if (ret < 0) {
+			error = -ENOMEM;
+			goto out;
 		}
+		alloc_normal += ret;
+		alloc_highmem += tmp - ret;
+		pages += tmp;
+
 		printk("\b%c", p[i++%4]);
-	} while (tmp > 0);
+	}
+
 	do_gettimeofday(&stop);
-	printk("\bdone (%lu pages freed)\n", pages);
+	printk("\bdone (preallocated %lu free pages)\n", pages);
 	swsusp_show_speed(&start, &stop, pages, "Freed");
 
-	return 0;
+ out:
+	/* Release the preallocated page frames. */
+	swsusp_free();
+
+	return error;
 }
 
 #ifdef CONFIG_HIGHMEM
Index: linux-2.6/mm/vmscan.c
===================================================================
--- linux-2.6.orig/mm/vmscan.c
+++ linux-2.6/mm/vmscan.c
@@ -2054,148 +2054,6 @@ unsigned long global_lru_pages(void)
 		+ global_page_state(NR_INACTIVE_FILE);
 }
 
-#ifdef CONFIG_PM
-/*
- * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
- * from LRU lists system-wide, for given pass and priority.
- *
- * For pass > 3 we also try to shrink the LRU lists that contain a few pages
- */
-static void shrink_all_zones(unsigned long nr_pages, int prio,
-				      int pass, struct scan_control *sc)
-{
-	struct zone *zone;
-	unsigned long nr_reclaimed = 0;
-
-	for_each_populated_zone(zone) {
-		enum lru_list l;
-
-		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
-			continue;
-
-		for_each_evictable_lru(l) {
-			enum zone_stat_item ls = NR_LRU_BASE + l;
-			unsigned long lru_pages = zone_page_state(zone, ls);
-
-			/* For pass = 0, we don't shrink the active list */
-			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
-						l == LRU_ACTIVE_FILE))
-				continue;
-
-			zone->lru[l].nr_scan += (lru_pages >> prio) + 1;
-			if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
-				unsigned long nr_to_scan;
-
-				zone->lru[l].nr_scan = 0;
-				nr_to_scan = min(nr_pages, lru_pages);
-				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
-								sc, prio);
-				if (nr_reclaimed >= nr_pages) {
-					sc->nr_reclaimed += nr_reclaimed;
-					return;
-				}
-			}
-		}
-	}
-	sc->nr_reclaimed += nr_reclaimed;
-}
-
-/*
- * Try to free `nr_pages' of memory, system-wide, and return the number of
- * freed pages.
- *
- * Rather than trying to age LRUs the aim is to preserve the overall
- * LRU order by reclaiming preferentially
- * inactive > active > active referenced > active mapped
- */
-unsigned long shrink_all_memory(unsigned long nr_pages)
-{
-	unsigned long lru_pages, nr_slab;
-	int pass;
-	struct reclaim_state reclaim_state;
-	struct scan_control sc = {
-		.gfp_mask = GFP_KERNEL,
-		.may_unmap = 0,
-		.may_writepage = 1,
-		.isolate_pages = isolate_pages_global,
-		.nr_reclaimed = 0,
-	};
-
-	current->reclaim_state = &reclaim_state;
-
-	lru_pages = global_lru_pages();
-	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
-	/* If slab caches are huge, it's better to hit them first */
-	while (nr_slab >= lru_pages) {
-		reclaim_state.reclaimed_slab = 0;
-		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
-		if (!reclaim_state.reclaimed_slab)
-			break;
-
-		sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		if (sc.nr_reclaimed >= nr_pages)
-			goto out;
-
-		nr_slab -= reclaim_state.reclaimed_slab;
-	}
-
-	/*
-	 * We try to shrink LRUs in 5 passes:
-	 * 0 = Reclaim from inactive_list only
-	 * 1 = Reclaim from active list but don't reclaim mapped
-	 * 2 = 2nd pass of type 1
-	 * 3 = Reclaim mapped (normal reclaim)
-	 * 4 = 2nd pass of type 3
-	 */
-	for (pass = 0; pass < 5; pass++) {
-		int prio;
-
-		/* Force reclaiming mapped pages in the passes #3 and #4 */
-		if (pass > 2)
-			sc.may_unmap = 1;
-
-		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
-			unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
-
-			sc.nr_scanned = 0;
-			sc.swap_cluster_max = nr_to_scan;
-			shrink_all_zones(nr_to_scan, prio, pass, &sc);
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-					global_lru_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(WRITE, HZ / 10);
-		}
-	}
-
-	/*
-	 * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
-	 * something in slab caches
-	 */
-	if (!sc.nr_reclaimed) {
-		do {
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		} while (sc.nr_reclaimed < nr_pages &&
-				reclaim_state.reclaimed_slab > 0);
-	}
-
-
-out:
-	current->reclaim_state = NULL;
-
-	return sc.nr_reclaimed;
-}
-#endif
-
 /* It's optimal to keep kswapds on the same CPUs as their memory, but
    not required for correctness.  So if the last cpu in a node goes
    away, we get changed to run anywhere: as the first one comes back,
Index: linux-2.6/kernel/power/main.c
===================================================================
--- linux-2.6.orig/kernel/power/main.c
+++ linux-2.6/kernel/power/main.c
@@ -188,9 +188,6 @@ static void suspend_test_finish(const ch
 
 #endif
 
-/* This is just an arbitrary number */
-#define FREE_PAGE_NUMBER (100)
-
 static struct platform_suspend_ops *suspend_ops;
 
 /**
@@ -226,7 +223,6 @@ int suspend_valid_only_mem(suspend_state
 static int suspend_prepare(void)
 {
 	int error;
-	unsigned int free_pages;
 
 	if (!suspend_ops || !suspend_ops->enter)
 		return -EPERM;
@@ -241,24 +237,10 @@ static int suspend_prepare(void)
 	if (error)
 		goto Finish;
 
-	if (suspend_freeze_processes()) {
-		error = -EAGAIN;
-		goto Thaw;
-	}
-
-	free_pages = global_page_state(NR_FREE_PAGES);
-	if (free_pages < FREE_PAGE_NUMBER) {
-		pr_debug("PM: free some memory\n");
-		shrink_all_memory(FREE_PAGE_NUMBER - free_pages);
-		if (nr_free_pages() < FREE_PAGE_NUMBER) {
-			error = -ENOMEM;
-			printk(KERN_ERR "PM: No enough memory\n");
-		}
-	}
+	error = suspend_freeze_processes();
 	if (!error)
 		return 0;
 
- Thaw:
 	suspend_thaw_processes();
 	usermodehelper_enable();
  Finish:

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/