mm/vmscan.c: condense scan_control

Use smaller scan_control fields for order, priority, and reclaim_idx.
Convert fields from int => s8.  All easily fit within a byte:

 - allocation order range: 0..MAX_ORDER(64?)
 - priority range:         0..12(DEF_PRIORITY)
 - reclaim_idx range:      0..6(__MAX_NR_ZONES)

Since 6538b8ea886e ("x86_64: expand kernel stack to 16K") x86_64 stack
overflows are not an issue.  But it's inefficient to use ints.

Use s8 (signed byte) rather than u8 to allow for loops like:
	do {
		...
	} while (--sc.priority >= 0);

Add BUILD_BUG_ON to verify that s8 is capable of storing max values.

This reduces sizeof(struct scan_control):
 - 96 => 80 bytes (x86_64)
 - 68 => 56 bytes (i386)

scan_control structure field order is changed to utilize padding.  After
this patch there is 1 bit of scan_control padding.

akpm: makes my vmscan.o's .text 572 bytes smaller as well.

Link: http://lkml.kernel.org/r/20180530061212.84915-1-gthelen@google.com
Signed-off-by: Greg Thelen <gthelen@google.com>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 20 insertions, 12 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 03822f86f288..a00d94530e57 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -65,12 +65,6 @@ struct scan_control {
         /* How many pages shrink_list() should reclaim */
         unsigned long nr_to_reclaim;
 
-        /* This context's GFP mask */
-        gfp_t gfp_mask;
-
-        /* Allocation order */
-        int order;
-
         /*
          * Nodemask of nodes allowed by the caller. If NULL, all nodes
          * are scanned.
@@ -83,12 +77,6 @@ struct scan_control {
          */
         struct mem_cgroup *target_mem_cgroup;
 
-        /* Scan (total_size >> priority) pages at once */
-        int priority;
-
-        /* The highest zone to isolate pages for reclaim from */
-        enum zone_type reclaim_idx;
-
         /* Writepage batching in laptop mode; RECLAIM_WRITE */
         unsigned int may_writepage:1;
 
@@ -111,6 +99,18 @@ struct scan_control {
         /* One of the zones is ready for compaction */
         unsigned int compaction_ready:1;
 
+        /* Allocation order */
+        s8 order;
+
+        /* Scan (total_size >> priority) pages at once */
+        s8 priority;
+
+        /* The highest zone to isolate pages for reclaim from */
+        s8 reclaim_idx;
+
+        /* This context's GFP mask */
+        gfp_t gfp_mask;
+
         /* Incremented by the number of inactive pages that were scanned */
         unsigned long nr_scanned;
 
@@ -3064,6 +3064,14 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
         };
 
         /*
+         * scan_control uses s8 fields for order, priority, and reclaim_idx.
+         * Confirm they are large enough for max values.
+         */
+        BUILD_BUG_ON(MAX_ORDER > S8_MAX);
+        BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
+        BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);
+
+        /*
          * Do not enter reclaim if fatal signal was delivered while throttled.
          * 1 is returned so that the page allocator does not OOM kill at this
          * point.