From fc217a22983058348a1526ada43ffbae37651e1f Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Fri, 28 Dec 2018 00:35:48 -0800
Subject: [PATCH] mm: use alloc_flags to record if kswapd can wake

References: Fragmentation avoidance and control bnc#1120919
Patch-mainline: v5.0
Git-commit: 0a79cdad5eb213b3a629e624565b1b3bf9192b7c

This is a preparation patch that copies the GFP flag __GFP_KSWAPD_RECLAIM
into alloc_flags.  This is a preparation patch only that avoids having to
pass gfp_mask through a long callchain in a future patch.

Note that the setting in the fast path happens in alloc_flags_nofragment()
and it may be claimed that this has nothing to do with ALLOC_NO_FRAGMENT.
That's true in this patch but is not true later so it's done now for
easier review to show where the flag needs to be recorded.

No functional change.

[mgorman@techsingularity.net: ALLOC_KSWAPD flag needs to be applied in the !CONFIG_ZONE_DMA32 case]
  Link: http://lkml.kernel.org/r/20181126143503.GO23260@techsingularity.net
Link: http://lkml.kernel.org/r/20181123114528.28802-4-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/internal.h   |  1 +
 mm/page_alloc.c | 33 ++++++++++++++++++---------------
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 0825f4d47e2a..0ac59a50ea60 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -489,6 +489,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #else
 #define ALLOC_NOFRAGMENT	  0x0
 #endif
+#define ALLOC_KSWAPD		0x200 /* allow waking of kswapd */
 
 enum ttu_flags;
 struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b6cd659754c9..f70224adedb4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3150,7 +3150,6 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 }
 #endif	/* CONFIG_NUMA */
 
-#ifdef CONFIG_ZONE_DMA32
 /*
  * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid
  * fragmentation is subtle. If the preferred zone was HIGHMEM then
@@ -3160,10 +3159,16 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
  * fragmentation between the Normal and DMA32 zones.
  */
 static inline unsigned int
-alloc_flags_nofragment(struct zone *zone)
+alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 {
+	unsigned int alloc_flags = 0;
+
+	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+		alloc_flags |= ALLOC_KSWAPD;
+
+#ifdef CONFIG_ZONE_DMA32
 	if (zone_idx(zone) != ZONE_NORMAL)
-		return 0;
+		goto out;
 
 	/*
 	 * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
@@ -3172,17 +3177,12 @@ alloc_flags_nofragment(struct zone *zone)
 	 */
 	BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
 	if (nr_online_nodes > 1 && !populated_zone(--zone))
-		return 0;
+		goto out;
 
-	return ALLOC_NOFRAGMENT;
-}
-#else
-static inline unsigned int
-alloc_flags_nofragment(struct zone *zone)
-{
-	return 0;
+out:
+#endif /* CONFIG_ZONE_DMA32 */
+	return alloc_flags;
 }
-#endif
 
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
@@ -3753,6 +3753,9 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
+	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+		alloc_flags |= ALLOC_KSWAPD;
+
 #ifdef CONFIG_CMA
 	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
@@ -3938,7 +3941,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	if (!ac->preferred_zoneref->zone)
 		goto nopage;
 
-	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+	if (alloc_flags & ALLOC_KSWAPD)
 		wake_all_kswapds(order, gfp_mask, ac);
 
 	/*
@@ -3996,7 +3999,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 retry:
 	/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
-	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+	if (alloc_flags & ALLOC_KSWAPD)
 		wake_all_kswapds(order, gfp_mask, ac);
 
 	if (gfp_pfmemalloc_allowed(gfp_mask))
@@ -4223,7 +4226,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	 * Forbid the first pass from falling back to types that fragment
 	 * memory until all local zones are considered.
 	 */
-	alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone);
+	alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp_mask);
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);