4 files changed, 115 insertions, 1 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 66f172fdf5fe..581e74b7df95 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -36,6 +36,7 @@ struct vm_area_struct;
 #endif
 #define ___GFP_NO_KSWAPD        0x400000u
 #define ___GFP_OTHER_NODE       0x800000u
+#define ___GFP_WRITE            0x1000000u
 
 /*
  * GFP bitmasks..
@@ -85,6 +86,7 @@ struct vm_area_struct;
 
 #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
+#define __GFP_WRITE     ((__force gfp_t)___GFP_WRITE)   /* Allocator intends to dirty page */
 
 /*
  * This may seem redundant, but it's a way of annotating false positives vs.
@@ -92,7 +94,7 @@ struct vm_area_struct;
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 24     /* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 25     /* Room for N __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 34a005515fef..6dff47304971 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -124,6 +124,7 @@ void laptop_mode_timer_fn(unsigned long data);
 static inline void laptop_sync_completion(void) { }
 #endif
 void throttle_vm_writeout(gfp_t gfp_mask);
+bool zone_dirty_ok(struct zone *zone);
 
 extern unsigned long global_dirty_limit;
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 433fa990fe8b..5cdd4f2b0c9d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -147,6 +147,24 @@ static struct prop_descriptor vm_completions;
  * clamping level.
  */
 
+/*
+ * In a memory zone, there is a certain amount of pages we consider
+ * available for the page cache, which is essentially the number of
+ * free and reclaimable pages, minus some zone reserves to protect
+ * lowmem and the ability to uphold the zone's watermarks without
+ * requiring writeback.
+ *
+ * This number of dirtyable pages is the base value of which the
+ * user-configurable dirty ratio is the effictive number of pages that
+ * are allowed to be actually dirtied.  Per individual zone, or
+ * globally by using the sum of dirtyable pages over all zones.
+ *
+ * Because the user is allowed to specify the dirty limit globally as
+ * absolute number of bytes, calculating the per-zone dirty limit can
+ * require translating the configured limit into a percentage of
+ * global dirtyable memory first.
+ */
+
 static unsigned long highmem_dirtyable_memory(unsigned long total)
 {
 #ifdef CONFIG_HIGHMEM
@@ -232,6 +250,70 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
         trace_global_dirty_state(background, dirty);
 }
 
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+        /*
+         * The effective global number of dirtyable pages may exclude
+         * highmem as a big-picture measure to keep the ratio between
+         * dirty memory and lowmem reasonable.
+         *
+         * But this function is purely about the individual zone and a
+         * highmem zone can hold its share of dirty pages, so we don't
+         * care about vm_highmem_is_dirtyable here.
+         */
+        return zone_page_state(zone, NR_FREE_PAGES) +
+               zone_reclaimable_pages(zone) -
+               zone->dirty_balance_reserve;
+}
+
+/**
+ * zone_dirty_limit - maximum number of dirty pages allowed in a zone
+ * @zone: the zone
+ *
+ * Returns the maximum number of dirty pages allowed in a zone, based
+ * on the zone's dirtyable memory.
+ */
+static unsigned long zone_dirty_limit(struct zone *zone)
+{
+        unsigned long zone_memory = zone_dirtyable_memory(zone);
+        struct task_struct *tsk = current;
+        unsigned long dirty;
+
+        if (vm_dirty_bytes)
+                dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
+                        zone_memory / global_dirtyable_memory();
+        else
+                dirty = vm_dirty_ratio * zone_memory / 100;
+
+        if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
+                dirty += dirty / 4;
+
+        return dirty;
+}
+
+/**
+ * zone_dirty_ok - tells whether a zone is within its dirty limits
+ * @zone: the zone to check
+ *
+ * Returns %true when the dirty pages in @zone are within the zone's
+ * dirty limit, %false if the limit is exceeded.
+ */
+bool zone_dirty_ok(struct zone *zone)
+{
+        unsigned long limit = zone_dirty_limit(zone);
+
+        return zone_page_state(zone, NR_FILE_DIRTY) +
+               zone_page_state(zone, NR_UNSTABLE_NFS) +
+               zone_page_state(zone, NR_WRITEBACK) <= limit;
+}
+
 /*
  * couple the period to the dirty_ratio:
  *
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2cb9eb71e282..4f95bcf0f2b1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1735,6 +1735,35 @@ zonelist_scan:
                 if ((alloc_flags & ALLOC_CPUSET) &&
                         !cpuset_zone_allowed_softwall(zone, gfp_mask))
                                 continue;
+                /*
+                 * When allocating a page cache page for writing, we
+                 * want to get it from a zone that is within its dirty
+                 * limit, such that no single zone holds more than its
+                 * proportional share of globally allowed dirty pages.
+                 * The dirty limits take into account the zone's
+                 * lowmem reserves and high watermark so that kswapd
+                 * should be able to balance it without having to
+                 * write pages from its LRU list.
+                 *
+                 * This may look like it could increase pressure on
+                 * lower zones by failing allocations in higher zones
+                 * before they are full.  But the pages that do spill
+                 * over are limited as the lower zones are protected
+                 * by this very same mechanism.  It should not become
+                 * a practical burden to them.
+                 *
+                 * XXX: For now, allow allocations to potentially
+                 * exceed the per-zone dirty limit in the slowpath
+                 * (ALLOC_WMARK_LOW unset) before going into reclaim,
+                 * which is important when on a NUMA setup the allowed
+                 * zones are together not big enough to reach the
+                 * global limit.  The proper fix for these situations
+                 * will require awareness of zones in the
+                 * dirty-throttling and the flusher threads.
+                 */
+                if ((alloc_flags & ALLOC_WMARK_LOW) &&
+                    (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
+                        goto this_zone_full;
 
                 BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
                 if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {