linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Duyck <alexander.duyck@gmail.com>
To: nitesh@redhat.com, kvm@vger.kernel.org, mst@redhat.com,
	david@redhat.com, dave.hansen@intel.com,
	linux-kernel@vger.kernel.org, willy@infradead.org,
	mhocko@kernel.org, linux-mm@kvack.org, akpm@linux-foundation.org,
	virtio-dev@lists.oasis-open.org, osalvador@suse.de
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
Subject: [PATCH v6 1/6] mm: Adjust shuffle code to allow for future coalescing
Date: Wed, 21 Aug 2019 07:59:31 -0700	[thread overview]
Message-ID: <20190821145931.20926.97386.stgit@localhost.localdomain> (raw)
In-Reply-To: <20190821145806.20926.22448.stgit@localhost.localdomain>

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

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.

While changing out the code I also opted to go for a bit more thread safe
approach to getting the boolean value. This way we can avoid possible cache
line bouncing of the batched entropy between CPUs.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 include/linux/mmzone.h |   12 --------
 mm/page_alloc.c        |   70 +++++++++++++++++++++++++++---------------------
 mm/shuffle.c           |   40 ++++++++++++++++-----------
 mm/shuffle.h           |   12 ++++++++
 4 files changed, 75 insertions(+), 59 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 8b5f758942a2..62bfb5a280ce 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 5b799e11fba3..3f8d5afe61fa 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -878,6 +878,36 @@ 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
@@ -906,11 +936,12 @@ 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);
 
@@ -979,35 +1010,12 @@ 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_pick_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..345cb4347455 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"
@@ -183,25 +182,34 @@ void __meminit __shuffle_free_memory(pg_data_t *pgdat)
 		shuffle_zone(z);
 }
 
-void add_to_free_area_random(struct page *page, struct free_area *area,
-		int migratetype)
+struct batched_bit_entropy {
+	unsigned long entropy_bool;
+	int position;
+};
+
+static DEFINE_PER_CPU(struct batched_bit_entropy, batched_entropy_bool);
+
+bool __shuffle_pick_tail(void)
 {
-	static u64 rand;
-	static u8 rand_bits;
+	struct batched_bit_entropy *batch;
+	unsigned long entropy;
+	int position;
 
 	/*
-	 * The lack of locking is deliberate. If 2 threads race to
-	 * update the rand state it just adds to the entropy.
+	 * We shouldn't need to disable IRQs as the only caller is
+	 * __free_one_page and it should only be called with the zone lock
+	 * held and either from IRQ context or with local IRQs disabled.
 	 */
-	if (rand_bits == 0) {
-		rand_bits = 64;
-		rand = get_random_u64();
+	batch = raw_cpu_ptr(&batched_entropy_bool);
+	position = batch->position;
+
+	if (--position < 0) {
+		batch->entropy_bool = get_random_long();
+		position = BITS_PER_LONG - 1;
 	}
 
-	if (rand & 1)
-		add_to_free_area(page, area, migratetype);
-	else
-		add_to_free_area_tail(page, area, migratetype);
-	rand_bits--;
-	rand >>= 1;
+	batch->position = position;
+	entropy = batch->entropy_bool;
+
+	return 1ul & (entropy >> position);
 }
diff --git a/mm/shuffle.h b/mm/shuffle.h
index 777a257a0d2f..0723eb97f22f 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
@@ -22,6 +23,7 @@ enum mm_shuffle_ctl {
 DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key);
 extern void page_alloc_shuffle(enum mm_shuffle_ctl ctl);
 extern void __shuffle_free_memory(pg_data_t *pgdat);
+extern bool __shuffle_pick_tail(void);
 static inline void shuffle_free_memory(pg_data_t *pgdat)
 {
 	if (!static_branch_unlikely(&page_alloc_shuffle_key))
@@ -43,6 +45,11 @@ static inline bool is_shuffle_order(int order)
 		return false;
 	return order >= SHUFFLE_ORDER;
 }
+
+static inline bool shuffle_pick_tail(void)
+{
+	return __shuffle_pick_tail();
+}
 #else
 static inline void shuffle_free_memory(pg_data_t *pgdat)
 {
@@ -60,5 +67,10 @@ static inline bool is_shuffle_order(int order)
 {
 	return false;
 }
+
+static inline bool shuffle_pick_tail(void)
+{
+	return false;
+}
 #endif
 #endif /* _MM_SHUFFLE_H */


  reply	other threads:[~2019-08-21 14:59 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-21 14:59 [PATCH v6 0/6] mm / virtio: Provide support for unused page reporting Alexander Duyck
2019-08-21 14:59 ` Alexander Duyck [this message]
2019-08-21 14:59 ` [PATCH v6 2/6] mm: Move set/get_pcppage_migratetype to mmzone.h Alexander Duyck
2019-08-21 14:59 ` [PATCH v6 3/6] mm: Use zone and order instead of free area in free_list manipulators Alexander Duyck
2019-08-21 14:59 ` [PATCH v6 4/6] mm: Introduce Reported pages Alexander Duyck
2019-08-22 16:18   ` [virtio-dev] " Nitesh Narayan Lal
2019-08-22 16:24     ` Alexander Duyck
2019-08-21 14:59 ` [PATCH v6 5/6] virtio-balloon: Pull page poisoning config out of free page hinting Alexander Duyck
2019-08-21 15:00 ` [PATCH v6 6/6] virtio-balloon: Add support for providing unused page reports to host Alexander Duyck
2019-08-21 15:00 ` [PATCH v6 QEMU 1/3] virtio-ballon: Implement support for page poison tracking feature Alexander Duyck
2019-08-21 15:00 ` [PATCH v6 QEMU 2/3] virtio-balloon: Add bit to notify guest of unused page reporting Alexander Duyck
2019-08-21 15:00 ` [PATCH v6 QEMU 3/3] virtio-balloon: Provide a interface for " Alexander Duyck
2019-08-22 10:43 ` [PATCH v6 0/6] mm / virtio: Provide support " Pankaj Gupta
2019-08-22 15:32   ` Alexander Duyck
2019-08-23  5:16     ` Pankaj Gupta
2019-08-23 15:02       ` Alexander Duyck

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190821145931.20926.97386.stgit@localhost.localdomain \
    --to=alexander.duyck@gmail.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.h.duyck@linux.intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=david@redhat.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=lcapitulino@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=mst@redhat.com \
    --cc=nitesh@redhat.com \
    --cc=osalvador@suse.de \
    --cc=pagupta@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=riel@surriel.com \
    --cc=virtio-dev@lists.oasis-open.org \
    --cc=wei.w.wang@intel.com \
    --cc=willy@infradead.org \
    --cc=yang.zhang.wz@gmail.com \
    --subject='Re: [PATCH v6 1/6] mm: Adjust shuffle code to allow for future coalescing' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox