1 files changed, 313 insertions, 99 deletions

diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 523a451b45d..97955b0e44f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -233,7 +233,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 
 #define BM_END_OF_MAP   (~0UL)
 
-#define BM_BITS_PER_BLOCK       (PAGE_SIZE << 3)
+#define BM_BITS_PER_BLOCK       (PAGE_SIZE * BITS_PER_BYTE)
 
 struct bm_block {
         struct list_head hook;  /* hook into a list of bitmap blocks */
@@ -275,7 +275,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *      create_bm_block_list - create a list of block bitmap objects
- *      @nr_blocks - number of blocks to allocate
+ *      @pages - number of pages to track
  *      @list - list to put the allocated blocks into
  *      @ca - chain allocator to be used for allocating memory
  */
@@ -853,7 +853,7 @@ static unsigned int count_highmem_pages(void)
         struct zone *zone;
         unsigned int n = 0;
 
-        for_each_zone(zone) {
+        for_each_populated_zone(zone) {
                 unsigned long pfn, max_zone_pfn;
 
                 if (!is_highmem(zone))
@@ -916,7 +916,7 @@ static unsigned int count_data_pages(void)
         unsigned long pfn, max_zone_pfn;
         unsigned int n = 0;
 
-        for_each_zone(zone) {
+        for_each_populated_zone(zone) {
                 if (is_highmem(zone))
                         continue;
 
@@ -1010,7 +1010,7 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
         struct zone *zone;
         unsigned long pfn;
 
-        for_each_zone(zone) {
+        for_each_populated_zone(zone) {
                 unsigned long max_zone_pfn;
 
                 mark_free_pages(zone);
@@ -1033,6 +1033,25 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 static unsigned int nr_copy_pages;
 /* Number of pages needed for saving the original pfns of the image pages */
 static unsigned int nr_meta_pages;
+/*
+ * Numbers of normal and highmem page frames allocated for hibernation image
+ * before suspending devices.
+ */
+unsigned int alloc_normal, alloc_highmem;
+/*
+ * Memory bitmap used for marking saveable pages (during hibernation) or
+ * hibernation image pages (during restore)
+ */
+static struct memory_bitmap orig_bm;
+/*
+ * Memory bitmap used during hibernation for marking allocated page frames that
+ * will contain copies of saveable pages.  During restore it is initially used
+ * for marking hibernation image pages, but then the set bits from it are
+ * duplicated in @orig_bm and it is released.  On highmem systems it is next
+ * used for marking "safe" highmem pages, but it has to be reinitialized for
+ * this purpose.
+ */
+static struct memory_bitmap copy_bm;
 
 /**
  *      swsusp_free - free pages allocated for the suspend.
@@ -1046,7 +1065,7 @@ void swsusp_free(void)
         struct zone *zone;
         unsigned long pfn, max_zone_pfn;
 
-        for_each_zone(zone) {
+        for_each_populated_zone(zone) {
                 max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
                 for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
                         if (pfn_valid(pfn)) {
@@ -1064,74 +1083,286 @@ void swsusp_free(void)
         nr_meta_pages = 0;
         restore_pblist = NULL;
         buffer = NULL;
+        alloc_normal = 0;
+        alloc_highmem = 0;
 }
 
+/* Helper functions used for the shrinking of memory. */
+
+#define GFP_IMAGE       (GFP_KERNEL | __GFP_NOWARN)
+
 /**
- *      swsusp_shrink_memory -  Try to free as much memory as needed
- *
- *      ... but do not OOM-kill anyone
+ * preallocate_image_pages - Allocate a number of pages for hibernation image
+ * @nr_pages: Number of page frames to allocate.
+ * @mask: GFP flags to use for the allocation.
  *
- *      Notice: all userland should be stopped before it is called, or
- *      livelock is possible.
+ * Return value: Number of page frames actually allocated
+ */
+static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask)
+{
+        unsigned long nr_alloc = 0;
+
+        while (nr_pages > 0) {
+                struct page *page;
+
+                page = alloc_image_page(mask);
+                if (!page)
+                        break;
+                memory_bm_set_bit(&copy_bm, page_to_pfn(page));
+                if (PageHighMem(page))
+                        alloc_highmem++;
+                else
+                        alloc_normal++;
+                nr_pages--;
+                nr_alloc++;
+        }
+
+        return nr_alloc;
+}
+
+static unsigned long preallocate_image_memory(unsigned long nr_pages)
+{
+        return preallocate_image_pages(nr_pages, GFP_IMAGE);
+}
+
+#ifdef CONFIG_HIGHMEM
+static unsigned long preallocate_image_highmem(unsigned long nr_pages)
+{
+        return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM);
+}
+
+/**
+ *  __fraction - Compute (an approximation of) x * (multiplier / base)
  */
+static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
+{
+        x *= multiplier;
+        do_div(x, base);
+        return (unsigned long)x;
+}
+
+static unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+                                                unsigned long highmem,
+                                                unsigned long total)
+{
+        unsigned long alloc = __fraction(nr_pages, highmem, total);
 
-#define SHRINK_BITE     10000
-static inline unsigned long __shrink_memory(long tmp)
+        return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM);
+}
+#else /* CONFIG_HIGHMEM */
+static inline unsigned long preallocate_image_highmem(unsigned long nr_pages)
 {
-        if (tmp > SHRINK_BITE)
-                tmp = SHRINK_BITE;
-        return shrink_all_memory(tmp);
+        return 0;
 }
 
-int swsusp_shrink_memory(void)
+static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+                                                unsigned long highmem,
+                                                unsigned long total)
+{
+        return 0;
+}
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ * free_unnecessary_pages - Release preallocated pages not needed for the image
+ */
+static void free_unnecessary_pages(void)
+{
+        unsigned long save_highmem, to_free_normal, to_free_highmem;
+
+        to_free_normal = alloc_normal - count_data_pages();
+        save_highmem = count_highmem_pages();
+        if (alloc_highmem > save_highmem) {
+                to_free_highmem = alloc_highmem - save_highmem;
+        } else {
+                to_free_highmem = 0;
+                to_free_normal -= save_highmem - alloc_highmem;
+        }
+
+        memory_bm_position_reset(&copy_bm);
+
+        while (to_free_normal > 0 && to_free_highmem > 0) {
+                unsigned long pfn = memory_bm_next_pfn(&copy_bm);
+                struct page *page = pfn_to_page(pfn);
+
+                if (PageHighMem(page)) {
+                        if (!to_free_highmem)
+                                continue;
+                        to_free_highmem--;
+                        alloc_highmem--;
+                } else {
+                        if (!to_free_normal)
+                                continue;
+                        to_free_normal--;
+                        alloc_normal--;
+                }
+                memory_bm_clear_bit(&copy_bm, pfn);
+                swsusp_unset_page_forbidden(page);
+                swsusp_unset_page_free(page);
+                __free_page(page);
+        }
+}
+
+/**
+ * minimum_image_size - Estimate the minimum acceptable size of an image
+ * @saveable: Number of saveable pages in the system.
+ *
+ * We want to avoid attempting to free too much memory too hard, so estimate the
+ * minimum acceptable size of a hibernation image to use as the lower limit for
+ * preallocating memory.
+ *
+ * We assume that the minimum image size should be proportional to
+ *
+ * [number of saveable pages] - [number of pages that can be freed in theory]
+ *
+ * where the second term is the sum of (1) reclaimable slab pages, (2) active
+ * and (3) inactive anonymouns pages, (4) active and (5) inactive file pages,
+ * minus mapped file pages.
+ */
+static unsigned long minimum_image_size(unsigned long saveable)
+{
+        unsigned long size;
+
+        size = global_page_state(NR_SLAB_RECLAIMABLE)
+                + global_page_state(NR_ACTIVE_ANON)
+                + global_page_state(NR_INACTIVE_ANON)
+                + global_page_state(NR_ACTIVE_FILE)
+                + global_page_state(NR_INACTIVE_FILE)
+                - global_page_state(NR_FILE_MAPPED);
+
+        return saveable <= size ? 0 : saveable - size;
+}
+
+/**
+ * hibernate_preallocate_memory - Preallocate memory for hibernation image
+ *
+ * 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
+ * compute the total number of available page frames and allocate at least
+ *
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ *
+ * of them, which corresponds to the maximum size of a hibernation image.
+ *
+ * If image_size is set below the number following from the above formula,
+ * the preallocation of memory is continued until the total number of saveable
+ * pages in the system is below the requested image size or the minimum
+ * acceptable image size returned by minimum_image_size(), whichever is greater.
+ */
+int hibernate_preallocate_memory(void)
 {
-        long tmp;
         struct zone *zone;
-        unsigned long pages = 0;
-        unsigned int i = 0;
-        char *p = "-\\|/";
+        unsigned long saveable, size, max_size, count, highmem, pages = 0;
+        unsigned long alloc, save_highmem, pages_highmem;
         struct timeval start, stop;
+        int error;
 
-        printk(KERN_INFO "PM: Shrinking memory...  ");
+        printk(KERN_INFO "PM: Preallocating image 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;
-                size += highmem_size;
-                for_each_populated_zone(zone) {
-                        tmp += snapshot_additional_pages(zone);
-                        if (is_highmem(zone)) {
-                                highmem_size -=
-                                        zone_page_state(zone, NR_FREE_PAGES);
-                        } else {
-                                tmp -= zone_page_state(zone, NR_FREE_PAGES);
-                                tmp += zone->lowmem_reserve[ZONE_NORMAL];
-                        }
-                }
 
-                if (highmem_size < 0)
-                        highmem_size = 0;
+        error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY);
+        if (error)
+                goto err_out;
 
-                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;
-                }
-                printk("\b%c", p[i++%4]);
-        } while (tmp > 0);
+        error = memory_bm_create(&copy_bm, GFP_IMAGE, PG_ANY);
+        if (error)
+                goto err_out;
+
+        alloc_normal = 0;
+        alloc_highmem = 0;
+
+        /* Count the number of saveable data pages. */
+        save_highmem = count_highmem_pages();
+        saveable = count_data_pages();
+
+        /*
+         * Compute the total number of page frames we can use (count) and the
+         * number of pages needed for image metadata (size).
+         */
+        count = saveable;
+        saveable += save_highmem;
+        highmem = save_highmem;
+        size = 0;
+        for_each_populated_zone(zone) {
+                size += snapshot_additional_pages(zone);
+                if (is_highmem(zone))
+                        highmem += zone_page_state(zone, NR_FREE_PAGES);
+                else
+                        count += zone_page_state(zone, NR_FREE_PAGES);
+        }
+        count += highmem;
+        count -= totalreserve_pages;
+
+        /* Compute the maximum number of saveable pages to leave in memory. */
+        max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+        size = DIV_ROUND_UP(image_size, PAGE_SIZE);
+        if (size > max_size)
+                size = max_size;
+        /*
+         * If the maximum is not less than the current number of saveable pages
+         * in memory, allocate page frames for the image and we're done.
+         */
+        if (size >= saveable) {
+                pages = preallocate_image_highmem(save_highmem);
+                pages += preallocate_image_memory(saveable - pages);
+                goto out;
+        }
+
+        /* Estimate the minimum size of the image. */
+        pages = minimum_image_size(saveable);
+        if (size < pages)
+                size = min_t(unsigned long, pages, max_size);
+
+        /*
+         * Let the memory management subsystem know that we're going to need a
+         * large number of page frames to allocate and make it free some memory.
+         * NOTE: If this is not done, performance will be hurt badly in some
+         * test cases.
+         */
+        shrink_all_memory(saveable - size);
+
+        /*
+         * The number of saveable pages in memory was too high, so apply some
+         * pressure to decrease it.  First, make room for the largest possible
+         * image and fail if that doesn't work.  Next, try to decrease the size
+         * of the image as much as indicated by 'size' using allocations from
+         * highmem and non-highmem zones separately.
+         */
+        pages_highmem = preallocate_image_highmem(highmem / 2);
+        alloc = (count - max_size) - pages_highmem;
+        pages = preallocate_image_memory(alloc);
+        if (pages < alloc)
+                goto err_out;
+        size = max_size - size;
+        alloc = size;
+        size = preallocate_highmem_fraction(size, highmem, count);
+        pages_highmem += size;
+        alloc -= size;
+        pages += preallocate_image_memory(alloc);
+        pages += pages_highmem;
+
+        /*
+         * We only need as many page frames for the image as there are saveable
+         * pages in memory, but we have allocated more.  Release the excessive
+         * ones now.
+         */
+        free_unnecessary_pages();
+
+ out:
         do_gettimeofday(&stop);
-        printk("\bdone (%lu pages freed)\n", pages);
-        swsusp_show_speed(&start, &stop, pages, "Freed");
+        printk(KERN_CONT "done (allocated %lu pages)\n", pages);
+        swsusp_show_speed(&start, &stop, pages, "Allocated");
 
         return 0;
+
+ err_out:
+        printk(KERN_CONT "\n");
+        swsusp_free();
+        return -ENOMEM;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1142,7 +1373,7 @@ int swsusp_shrink_memory(void)
 
 static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
 {
-        unsigned int free_highmem = count_free_highmem_pages();
+        unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem;
 
         if (free_highmem >= nr_highmem)
                 nr_highmem = 0;
@@ -1164,19 +1395,17 @@ count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
 static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
 {
         struct zone *zone;
-        unsigned int free = 0, meta = 0;
+        unsigned int free = alloc_normal;
 
-        for_each_zone(zone) {
-                meta += snapshot_additional_pages(zone);
+        for_each_populated_zone(zone)
                 if (!is_highmem(zone))
                         free += zone_page_state(zone, NR_FREE_PAGES);
-        }
 
         nr_pages += count_pages_for_highmem(nr_highmem);
-        pr_debug("PM: Normal pages needed: %u + %u + %u, available pages: %u\n",
-                nr_pages, PAGES_FOR_IO, meta, free);
+        pr_debug("PM: Normal pages needed: %u + %u, available pages: %u\n",
+                nr_pages, PAGES_FOR_IO, free);
 
-        return free > nr_pages + PAGES_FOR_IO + meta;
+        return free > nr_pages + PAGES_FOR_IO;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1198,7 +1427,7 @@ static inline int get_highmem_buffer(int safe_needed)
  */
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 {
         unsigned int to_alloc = count_free_highmem_pages();
 
@@ -1218,7 +1447,7 @@ alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 static inline int get_highmem_buffer(int safe_needed) { return 0; }
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -1237,51 +1466,36 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
                 unsigned int nr_pages, unsigned int nr_highmem)
 {
-        int error;
-
-        error = memory_bm_create(orig_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-        if (error)
-                goto Free;
-
-        error = memory_bm_create(copy_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-        if (error)
-                goto Free;
+        int error = 0;
 
         if (nr_highmem > 0) {
                 error = get_highmem_buffer(PG_ANY);
                 if (error)
-                        goto Free;
-
-                nr_pages += alloc_highmem_image_pages(copy_bm, nr_highmem);
+                        goto err_out;
+                if (nr_highmem > alloc_highmem) {
+                        nr_highmem -= alloc_highmem;
+                        nr_pages += alloc_highmem_pages(copy_bm, nr_highmem);
+                }
         }
-        while (nr_pages-- > 0) {
-                struct page *page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
-
-                if (!page)
-                        goto Free;
+        if (nr_pages > alloc_normal) {
+                nr_pages -= alloc_normal;
+                while (nr_pages-- > 0) {
+                        struct page *page;
 
-                memory_bm_set_bit(copy_bm, page_to_pfn(page));
+                        page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
+                        if (!page)
+                                goto err_out;
+                        memory_bm_set_bit(copy_bm, page_to_pfn(page));
+                }
         }
+
         return 0;
 
- Free:
+ err_out:
         swsusp_free();
-        return -ENOMEM;
+        return error;
 }
 
-/* Memory bitmap used for marking saveable pages (during suspend) or the
- * suspend image pages (during resume)
- */
-static struct memory_bitmap orig_bm;
-/* Memory bitmap used on suspend for marking allocated pages that will contain
- * the copies of saveable pages.  During resume it is initially used for
- * marking the suspend image pages, but then its set bits are duplicated in
- * @orig_bm and it is released.  Next, on systems with high memory, it may be
- * used for marking "safe" highmem pages, but it has to be reinitialized for
- * this purpose.
- */
-static struct memory_bitmap copy_bm;
-
 asmlinkage int swsusp_save(void)
 {
         unsigned int nr_pages, nr_highmem;
@@ -1474,7 +1688,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
         unsigned long pfn, max_zone_pfn;
 
         /* Clear page flags */
-        for_each_zone(zone) {
+        for_each_populated_zone(zone) {
                 max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
                 for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
                         if (pfn_valid(pfn))