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>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1cedd00..0548eb2 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1318,6 +1318,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 
 #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);
 
@@ -1326,6 +1327,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page)
        return page->ptl;
 }
 #else /* BLOATED_SPINLOCKS */
+static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_alloc(struct page *page)
 {
        return true;
@@ -1378,10 +1380,17 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
        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 --git a/init/main.c b/init/main.c
index 6ad1a53..5f19113 100644 (file)
--- a/init/main.c
+++ b/init/main.c
@@ -473,7 +473,7 @@ static void __init mm_init(void)
        mem_init();
        kmem_cache_init();
        percpu_init_late();
-       pgtable_cache_init();
+       pgtable_init();
        vmalloc_init();
 }
 

diff --git a/mm/memory.c b/mm/memory.c
index 5d9025f..0409e8f 100644 (file)
--- 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;