[PATCH] mm: __alloc_pages cleanup fix

I believe this patch is required to fix breakage in the asynch reclaim
watermark logic introduced by this patch:

http://www.kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=7fb1d9fca5c6e3b06773b69165a73f3fb786b8ee

Just some background of the watermark logic in case it isn't clear...
Basically what we have is this:

 ---  pages_high
   |
   | (a)
   |
 ---  pages_low
   |
   | (b)
   |
 ---  pages_min
   |
   | (c)
   |
 ---  0

Now when pages_low is reached, we want to kick asynch reclaim, which gives us
an interval of "b" before we must start synch reclaim, and gives kswapd an
interval of "a" before it need go back to sleep.

When pages_min is reached, normal allocators must enter synch reclaim, but
PF_MEMALLOC, ALLOC_HARDER, and ALLOC_HIGH (ie.  atomic allocations, recursive
allocations, etc.) get access to varying amounts of the reserve "c".

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: "Seth, Rohit" <rohit.seth@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1731236dec352ffd9dc3e21e11cc9ce27bd9bde2..b257720edfc83ce4d025159d05c82354b9dd220b 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -773,9 +773,12 @@ again:
 }
 
 #define ALLOC_NO_WATERMARKS    0x01 /* don't check watermarks at all */
-#define ALLOC_HARDER           0x02 /* try to alloc harder */
-#define ALLOC_HIGH             0x04 /* __GFP_HIGH set */
-#define ALLOC_CPUSET           0x08 /* check for correct cpuset */
+#define ALLOC_WMARK_MIN                0x02 /* use pages_min watermark */
+#define ALLOC_WMARK_LOW                0x04 /* use pages_low watermark */
+#define ALLOC_WMARK_HIGH       0x08 /* use pages_high watermark */
+#define ALLOC_HARDER           0x10 /* try to alloc harder */
+#define ALLOC_HIGH             0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET           0x40 /* check for correct cpuset */
 
 /*
  * Return 1 if free pages are above 'mark'. This takes into account the order
@@ -830,7 +833,14 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
                        continue;
 
                if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
-                       if (!zone_watermark_ok(*z, order, (*z)->pages_low,
+                       unsigned long mark;
+                       if (alloc_flags & ALLOC_WMARK_MIN)
+                               mark = (*z)->pages_min;
+                       else if (alloc_flags & ALLOC_WMARK_LOW)
+                               mark = (*z)->pages_low;
+                       else
+                               mark = (*z)->pages_high;
+                       if (!zone_watermark_ok(*z, order, mark,
                                    classzone_idx, alloc_flags))
                                continue;
                }
@@ -871,7 +881,7 @@ restart:
        }
 
        page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-                               zonelist, ALLOC_CPUSET);
+                               zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
        if (page)
                goto got_pg;
 
@@ -888,7 +898,7 @@ restart:
         * cannot run direct reclaim, or if the caller has realtime scheduling
         * policy.
         */
-       alloc_flags = 0;
+       alloc_flags = ALLOC_WMARK_MIN;
        if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
                alloc_flags |= ALLOC_HARDER;
        if (gfp_mask & __GFP_HIGH)
@@ -959,7 +969,7 @@ rebalance:
                 * under heavy pressure.
                 */
                page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-                                               zonelist, ALLOC_CPUSET);
+                               zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
                if (page)
                        goto got_pg;