Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: [PATCH v2 1/5] mm: Adjust shuffle code to allow for future
 coalescing
From:   Alexander Duyck <alexander.duyck@gmail.com>
To:     nitesh@redhat.com, kvm@vger.kernel.org, david@redhat.com,
        mst@redhat.com, dave.hansen@intel.com,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        akpm@linux-foundation.org
Cc:     yang.zhang.wz@gmail.com, pagupta@redhat.com, riel@surriel.com,
        konrad.wilk@oracle.com, lcapitulino@redhat.com,
        wei.w.wang@intel.com, aarcange@redhat.com, pbonzini@redhat.com,
        dan.j.williams@intel.com, alexander.h.duyck@linux.intel.com
Date:   Wed, 24 Jul 2019 09:56:16 -0700
Message-ID: <20190724165615.6685.24289.stgit@localhost.localdomain>
In-Reply-To: <20190724165158.6685.87228.stgit@localhost.localdomain>
References: <20190724165158.6685.87228.stgit@localhost.localdomain>
User-Agent: StGit/0.17.1-dirty
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Alexander Duyck <alexander.h.duyck@linux.intel.com>

This patch is meant to move the head/tail adding logic out of the shuffle
code and into the __free_one_page function since ultimately that is where
it is really needed anyway. By doing this we should be able to reduce the
overhead and can consolidate all of the list addition bits in one spot.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 include/linux/mmzone.h |   12 --------
 mm/page_alloc.c        |   70 +++++++++++++++++++++++++++---------------------
 mm/shuffle.c           |   24 ----------------
 mm/shuffle.h           |   32 ++++++++++++++++++++++
 4 files changed, 71 insertions(+), 67 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d77d717c620c..738e9c758135 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -116,18 +116,6 @@ static inline void add_to_free_area_tail(struct page *page, struct free_area *ar
 	area->nr_free++;
 }
 
-#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
-/* Used to preserve page allocation order entropy */
-void add_to_free_area_random(struct page *page, struct free_area *area,
-		int migratetype);
-#else
-static inline void add_to_free_area_random(struct page *page,
-		struct free_area *area, int migratetype)
-{
-	add_to_free_area(page, area, migratetype);
-}
-#endif
-
 /* Used for pages which are on another list */
 static inline void move_to_free_area(struct page *page, struct free_area *area,
 			     int migratetype)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 272c6de1bf4e..1c4644b6cdc3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -877,6 +877,36 @@ static inline struct capture_control *task_capc(struct zone *zone)
 #endif /* CONFIG_COMPACTION */
 
 /*
+ * If this is not the largest possible page, check if the buddy
+ * of the next-highest order is free. If it is, it's possible
+ * that pages are being freed that will coalesce soon. In case,
+ * that is happening, add the free page to the tail of the list
+ * so it's less likely to be used soon and more likely to be merged
+ * as a higher order page
+ */
+static inline bool
+buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
+		   struct page *page, unsigned int order)
+{
+	struct page *higher_page, *higher_buddy;
+	unsigned long combined_pfn;
+
+	if (order >= MAX_ORDER - 2)
+		return false;
+
+	if (!pfn_valid_within(buddy_pfn))
+		return false;
+
+	combined_pfn = buddy_pfn & pfn;
+	higher_page = page + (combined_pfn - pfn);
+	buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
+	higher_buddy = higher_page + (buddy_pfn - combined_pfn);
+
+	return pfn_valid_within(buddy_pfn) &&
+	       page_is_buddy(higher_page, higher_buddy, order + 1);
+}
+
+/*
  * Freeing function for a buddy system allocator.
  *
  * The concept of a buddy system is to maintain direct-mapped table
@@ -905,11 +935,12 @@ static inline void __free_one_page(struct page *page,
 		struct zone *zone, unsigned int order,
 		int migratetype)
 {
-	unsigned long combined_pfn;
+	struct capture_control *capc = task_capc(zone);
 	unsigned long uninitialized_var(buddy_pfn);
-	struct page *buddy;
+	unsigned long combined_pfn;
+	struct free_area *area;
 	unsigned int max_order;
-	struct capture_control *capc = task_capc(zone);
+	struct page *buddy;
 
 	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
 
@@ -978,35 +1009,12 @@ static inline void __free_one_page(struct page *page,
 done_merging:
 	set_page_order(page, order);
 
-	/*
-	 * If this is not the largest possible page, check if the buddy
-	 * of the next-highest order is free. If it is, it's possible
-	 * that pages are being freed that will coalesce soon. In case,
-	 * that is happening, add the free page to the tail of the list
-	 * so it's less likely to be used soon and more likely to be merged
-	 * as a higher order page
-	 */
-	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
-			&& !is_shuffle_order(order)) {
-		struct page *higher_page, *higher_buddy;
-		combined_pfn = buddy_pfn & pfn;
-		higher_page = page + (combined_pfn - pfn);
-		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
-		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
-		if (pfn_valid_within(buddy_pfn) &&
-		    page_is_buddy(higher_page, higher_buddy, order + 1)) {
-			add_to_free_area_tail(page, &zone->free_area[order],
-					      migratetype);
-			return;
-		}
-	}
-
-	if (is_shuffle_order(order))
-		add_to_free_area_random(page, &zone->free_area[order],
-				migratetype);
+	area = &zone->free_area[order];
+	if (is_shuffle_order(order) ? shuffle_add_to_tail() :
+	    buddy_merge_likely(pfn, buddy_pfn, page, order))
+		add_to_free_area_tail(page, area, migratetype);
 	else
-		add_to_free_area(page, &zone->free_area[order], migratetype);
-
+		add_to_free_area(page, area, migratetype);
 }
 
 /*
diff --git a/mm/shuffle.c b/mm/shuffle.c
index 3ce12481b1dc..55d592e62526 100644
--- a/mm/shuffle.c
+++ b/mm/shuffle.c
@@ -4,7 +4,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/mmzone.h>
-#include <linux/random.h>
 #include <linux/moduleparam.h>
 #include "internal.h"
 #include "shuffle.h"
@@ -182,26 +181,3 @@ void __meminit __shuffle_free_memory(pg_data_t *pgdat)
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		shuffle_zone(z);
 }
-
-void add_to_free_area_random(struct page *page, struct free_area *area,
-		int migratetype)
-{
-	static u64 rand;
-	static u8 rand_bits;
-
-	/*
-	 * The lack of locking is deliberate. If 2 threads race to
-	 * update the rand state it just adds to the entropy.
-	 */
-	if (rand_bits == 0) {
-		rand_bits = 64;
-		rand = get_random_u64();
-	}
-
-	if (rand & 1)
-		add_to_free_area(page, area, migratetype);
-	else
-		add_to_free_area_tail(page, area, migratetype);
-	rand_bits--;
-	rand >>= 1;
-}
diff --git a/mm/shuffle.h b/mm/shuffle.h
index 777a257a0d2f..add763cc0995 100644
--- a/mm/shuffle.h
+++ b/mm/shuffle.h
@@ -3,6 +3,7 @@
 #ifndef _MM_SHUFFLE_H
 #define _MM_SHUFFLE_H
 #include <linux/jump_label.h>
+#include <linux/random.h>
 
 /*
  * SHUFFLE_ENABLE is called from the command line enabling path, or by
@@ -43,6 +44,32 @@ static inline bool is_shuffle_order(int order)
 		return false;
 	return order >= SHUFFLE_ORDER;
 }
+
+static inline bool shuffle_add_to_tail(void)
+{
+	static u64 rand;
+	static u8 rand_bits;
+	u64 rand_old;
+
+	/*
+	 * The lack of locking is deliberate. If 2 threads race to
+	 * update the rand state it just adds to the entropy.
+	 */
+	if (rand_bits-- == 0) {
+		rand_bits = 64;
+		rand = get_random_u64();
+	}
+
+	/*
+	 * Test highest order bit while shifting our random value. This
+	 * should result in us testing for the carry flag following the
+	 * shift.
+	 */
+	rand_old = rand;
+	rand <<= 1;
+
+	return rand < rand_old;
+}
 #else
 static inline void shuffle_free_memory(pg_data_t *pgdat)
 {
@@ -60,5 +87,10 @@ static inline bool is_shuffle_order(int order)
 {
 	return false;
 }
+
+static inline bool shuffle_add_to_tail(void)
+{
+	return false;
+}
 #endif
 #endif /* _MM_SHUFFLE_H */