Subject: + mm-create-a-separate-slab-for-page-ptl-allocation-try-two.patch added to -mm tree
To: kirill.shutemov@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Fri, 22 Nov 2013 14:19:08 -0800
The patch titled
Subject: mm: create a separate slab for page->ptl allocation
has been added to the -mm tree. Its filename is
mm-create-a-separate-slab-for-page-ptl-allocation-try-two.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-create-a-separate-slab-for-page-ptl-allocation-try-two.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-create-a-separate-slab-for-page-ptl-allocation-try-two.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: mm: create a separate slab for page->ptl allocation
If DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC are enabled spinlock_t on x86_64 is
72 bytes. For page->ptl they will be allocated from kmalloc-96 slab, so
we loose 24 on each. An average system can easily allocate few tens
thousands of page->ptl and overhead is significant.
Let's create a separate slab for page->ptl allocation to solve this.
To make sure that it really works this time, some numbers from my test
machine (just booted, no load):
Before:
# grep '^\(kmalloc-96\|page->ptl\)' /proc/slabinfo
kmalloc-96 31987 32190 128 30 1 : tunables 120 60 8 : slabdata 1073 1073 92
After:
# grep '^\(kmalloc-96\|page->ptl\)' /proc/slabinfo
page->ptl 27516 28143 72 53 1 : tunables 120 60 8 : slabdata 531 531 9
kmalloc-96 3853 5280 128 30 1 : tunables 120 60 8 : slabdata 176 176 0
Note that the patch is useful not only for debug case, but also for
PREEMPT_RT, where spinlock_t is always bloated.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 9 +++++++++
init/main.c | 2 +-
mm/memory.c | 11 +++++++++--
3 files changed, 19 insertions(+), 3 deletions(-)
diff -puN include/linux/mm.h~mm-create-a-separate-slab-for-page-ptl-allocation-try-two include/linux/mm.h
--- a/include/linux/mm.h~mm-create-a-separate-slab-for-page-ptl-allocation-try-two
+++ a/include/linux/mm.h
@@ -1348,6 +1348,7 @@ static inline pmd_t *pmd_alloc(struct mm
#if USE_SPLIT_PTE_PTLOCKS
#if BLOATED_SPINLOCKS
+void __init ptlock_cache_init(void);
extern bool ptlock_alloc(struct page *page);
extern void ptlock_free(struct page *page);
@@ -1356,6 +1357,7 @@ static inline spinlock_t *ptlock_ptr(str
return page->ptl;
}
#else /* BLOATED_SPINLOCKS */
+static inline void ptlock_cache_init(void) {}
static inline bool ptlock_alloc(struct page *page)
{
return true;
@@ -1408,10 +1410,17 @@ static inline spinlock_t *pte_lockptr(st
{
return &mm->page_table_lock;
}
+static inline void ptlock_cache_init(void) {}
static inline bool ptlock_init(struct page *page) { return true; }
static inline void pte_lock_deinit(struct page *page) {}
#endif /* USE_SPLIT_PTE_PTLOCKS */
+static inline void pgtable_init(void)
+{
+ ptlock_cache_init();
+ pgtable_cache_init();
+}
+
static inline bool pgtable_page_ctor(struct page *page)
{
inc_zone_page_state(page, NR_PAGETABLE);
diff -puN init/main.c~mm-create-a-separate-slab-for-page-ptl-allocation-try-two init/main.c
--- a/init/main.c~mm-create-a-separate-slab-for-page-ptl-allocation-try-two
+++ a/init/main.c
@@ -476,7 +476,7 @@ static void __init mm_init(void)
mem_init();
kmem_cache_init();
percpu_init_late();
- pgtable_cache_init();
+ pgtable_init();
vmalloc_init();
}
diff -puN mm/memory.c~mm-create-a-separate-slab-for-page-ptl-allocation-try-two mm/memory.c
--- a/mm/memory.c~mm-create-a-separate-slab-for-page-ptl-allocation-try-two
+++ a/mm/memory.c
@@ -4272,11 +4272,18 @@ void copy_user_huge_page(struct page *ds
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
+static struct kmem_cache *page_ptl_cachep;
+void __init ptlock_cache_init(void)
+{
+ page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
+ SLAB_PANIC, NULL);
+}
+
bool ptlock_alloc(struct page *page)
{
spinlock_t *ptl;
- ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+ ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
if (!ptl)
return false;
page->ptl = ptl;
@@ -4285,6 +4292,6 @@ bool ptlock_alloc(struct page *page)
void ptlock_free(struct page *page)
{
- kfree(page->ptl);
+ kmem_cache_free(page_ptl_cachep, page->ptl);
}
#endif
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
origin.patch
x86-mm-get-aslr-work-for-hugetlb-mappings.patch
mm-create-a-separate-slab-for-page-ptl-allocation-try-two.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
