| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20130830131710.4947.14283.stgit@srivatsabhat.in.ibm.com>
Date: Fri, 30 Aug 2013 18:47:13 +0530
From: "Srivatsa S. Bhat" <srivatsa.bhat@...ux.vnet.ibm.com>
To: akpm@...ux-foundation.org, mgorman@...e.de, hannes@...xchg.org,
tony.luck@...el.com, matthew.garrett@...ula.com, dave@...1.net,
riel@...hat.com, arjan@...ux.intel.com,
srinivas.pandruvada@...ux.intel.com, willy@...ux.intel.com,
kamezawa.hiroyu@...fujitsu.com, lenb@...nel.org, rjw@...k.pl
Cc: gargankita@...il.com, paulmck@...ux.vnet.ibm.com,
svaidy@...ux.vnet.ibm.com, andi@...stfloor.org,
isimatu.yasuaki@...fujitsu.com, santosh.shilimkar@...com,
kosaki.motohiro@...il.com, srivatsa.bhat@...ux.vnet.ibm.com,
linux-pm@...r.kernel.org, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: [RFC PATCH v3 11/35] mm: Add an optimized version of
del_from_freelist to keep page allocation fast
One of the main advantages of this design of memory regions is that page
allocations can potentially be extremely fast - almost with no extra
overhead from memory regions.
To exploit that, introduce an optimized version of del_from_freelist(), which
utilizes the fact that we always delete items from the head of the list
during page allocation.
Basically, we want to keep a note of the region from which we are allocating
in a given freelist, to avoid having to compute the page-to-zone-region for
every page allocation. So introduce a 'next_region' pointer in every freelist
to achieve that, and use it to keep the fastpath of page allocation almost as
fast as it would have been without memory regions.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@...ux.vnet.ibm.com>
---
include/linux/mm.h | 14 +++++++++++
include/linux/mmzone.h | 6 +++++
mm/page_alloc.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 81 insertions(+), 1 deletion(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 52329d1..156d7db 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -747,6 +747,20 @@ static inline int page_zone_region_id(const struct page *page)
return pgdat->node_regions[node_region_idx].zone_region_idx[z_num];
}
+static inline void set_next_region_in_freelist(struct free_list *free_list)
+{
+ struct page *page;
+ int region_id;
+
+ if (unlikely(list_empty(&free_list->list))) {
+ free_list->next_region = NULL;
+ } else {
+ page = list_entry(free_list->list.next, struct page, lru);
+ region_id = page_zone_region_id(page);
+ free_list->next_region = &free_list->mr_list[region_id];
+ }
+}
+
#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 201ab42..932e71f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -92,6 +92,12 @@ struct free_list {
struct list_head list;
/*
+ * Pointer to the region from which the next allocation will be
+ * satisfied. (Same as the freelist's first pageblock's region.)
+ */
+ struct mem_region_list *next_region; /* for fast page allocation */
+
+ /*
* Demarcates pageblocks belonging to different regions within
* this freelist.
*/
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 07ac019..52b6655 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -548,6 +548,15 @@ static void add_to_freelist(struct page *page, struct free_list *free_list)
/* This is the first region, so add to the head of the list */
prev_region_list = &free_list->list;
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ WARN((list_empty(&free_list->list) && free_list->next_region != NULL),
+ "%s: next_region not NULL\n", __func__);
+#endif
+ /*
+ * Set 'next_region' to this region, since this is the first region now
+ */
+ free_list->next_region = region;
+
out:
list_add(lru, prev_region_list);
@@ -555,6 +564,47 @@ out:
region->page_block = lru;
}
+/**
+ * __rmqueue_smallest() *always* deletes elements from the head of the
+ * list. Use this knowledge to keep page allocation fast, despite being
+ * region-aware.
+ *
+ * Do *NOT* call this function if you are deleting from somewhere deep
+ * inside the freelist.
+ */
+static void rmqueue_del_from_freelist(struct page *page,
+ struct free_list *free_list)
+{
+ struct list_head *lru = &page->lru;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ WARN((free_list->list.next != lru),
+ "%s: page not at head of list", __func__);
+#endif
+
+ list_del(lru);
+
+ /* Fastpath */
+ if (--(free_list->next_region->nr_free)) {
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ WARN(free_list->next_region->nr_free < 0,
+ "%s: nr_free is negative\n", __func__);
+#endif
+ return;
+ }
+
+ /*
+ * Slowpath, when this is the last pageblock of this region
+ * in this freelist.
+ */
+ free_list->next_region->page_block = NULL;
+
+ /* Set 'next_region' to the new first region in the freelist. */
+ set_next_region_in_freelist(free_list);
+}
+
+/* Generic delete function for region-aware buddy allocator. */
static void del_from_freelist(struct page *page, struct free_list *free_list)
{
struct list_head *prev_page_lru, *lru, *p;
@@ -562,6 +612,11 @@ static void del_from_freelist(struct page *page, struct free_list *free_list)
int region_id;
lru = &page->lru;
+
+ /* Try to fastpath, if deleting from the head of the list */
+ if (lru == free_list->list.next)
+ return rmqueue_del_from_freelist(page, free_list);
+
region_id = page_zone_region_id(page);
region = &free_list->mr_list[region_id];
region->nr_free--;
@@ -597,6 +652,11 @@ page_found:
prev_page_lru = lru->prev;
list_del(lru);
+ /*
+ * Since we are not deleting from the head of the freelist, the
+ * 'next_region' pointer doesn't have to change.
+ */
+
if (region->nr_free == 0) {
region->page_block = NULL;
} else {
@@ -1022,7 +1082,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
page = list_entry(area->free_list[migratetype].list.next,
struct page, lru);
- del_from_freelist(page, &area->free_list[migratetype]);
+ rmqueue_del_from_freelist(page, &area->free_list[migratetype]);
rmv_page_order(page);
area->nr_free--;
expand(zone, page, order, current_order, area, migratetype);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists