summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKirill A. Shutemov <kirill.shutemov@linux.intel.com>2013-11-14 14:31:53 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-11-15 09:32:20 +0900
commitea1e7ed33708c7a760419ff9ded0a6cb90586a50 (patch)
tree553c0c4024639bf2b1706d144fd6bb8ada63861e /mm
parent539edb5846c740d78a8b6c2e43a99ca4323df68f (diff)
downloadop-kernel-dev-ea1e7ed33708c7a760419ff9ded0a6cb90586a50.zip
op-kernel-dev-ea1e7ed33708c7a760419ff9ded0a6cb90586a50.tar.gz
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. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memory.c7
1 files changed, 7 insertions, 0 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 5d9025f..0409e8f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4272,6 +4272,13 @@ void copy_user_huge_page(struct page *dst, struct page *src,
#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;
OpenPOWER on IntegriCloud