mm, compaction: skip buddy pages by their order in the migrate scanner

The migration scanner skips PageBuddy pages, but does not consider their
order as checking page_order() is generally unsafe without holding the
zone->lock, and acquiring the lock just for the check wouldn't be a good
tradeoff.

Still, this could avoid some iterations over the rest of the buddy page,
and if we are careful, the race window between PageBuddy() check and
page_order() is small, and the worst thing that can happen is that we skip
too much and miss some isolation candidates.  This is not that bad, as
compaction can already fail for many other reasons like parallel
allocations, and those have much larger race window.

This patch therefore makes the migration scanner obtain the buddy page
order and use it to skip the whole buddy page, if the order appears to be
in the valid range.

It's important that the page_order() is read only once, so that the value
used in the checks and in the pfn calculation is the same.  But in theory
the compiler can replace the local variable by multiple inlines of
page_order().  Therefore, the patch introduces page_order_unsafe() that
uses ACCESS_ONCE to prevent this.

Testing with stress-highalloc from mmtests shows a 15% reduction in number
of pages scanned by migration scanner.  The reduction is >60% with
__GFP_NO_KSWAPD allocations, along with success rates better by few
percent.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 1 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 4c1d604..86ae964 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -164,7 +164,8 @@ isolate_migratepages_range(struct compact_control *cc,
  * general, page_zone(page)->lock must be held by the caller to prevent the
  * page from being allocated in parallel and returning garbage as the order.
  * If a caller does not hold page_zone(page)->lock, it must guarantee that the
- * page cannot be allocated or merged in parallel.
+ * page cannot be allocated or merged in parallel. Alternatively, it must
+ * handle invalid values gracefully, and use page_order_unsafe() below.
  */
 static inline unsigned long page_order(struct page *page)
 {
@@ -172,6 +173,19 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+/*
+ * Like page_order(), but for callers who cannot afford to hold the zone lock.
+ * PageBuddy() should be checked first by the caller to minimize race window,
+ * and invalid values must be handled gracefully.
+ *
+ * ACCESS_ONCE is used so that if the caller assigns the result into a local
+ * variable and e.g. tests it for valid range before using, the compiler cannot
+ * decide to remove the variable and inline the page_private(page) multiple
+ * times, potentially observing different values in the tests and the actual
+ * use of the result.
+ */
+#define page_order_unsafe(page)		ACCESS_ONCE(page_private(page))
+
 static inline bool is_cow_mapping(vm_flags_t flags)
 {
 	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;