[v7,11/11] mm: stop zeroing memory during allocation in vmemmap

Commit Message

Pavel Tatashin Aug. 29, 2017, 2:02 a.m. UTC

vmemmap_alloc_block() will no longer zero the block, so zero memory
at its call sites for everything except struct pages.  Struct page memory
is zero'd by struct page initialization.

Replace allocators in sprase-vmemmap to use the non-zeroing version. So,
we will get the performance improvement by zeroing the memory in parallel
when struct pages are zeroed.

Signed-off-by: Pavel Tatashin <[e-mail]>
Reviewed-by: Steven Sistare <[e-mail]>
Reviewed-by: Daniel Jordan <[e-mail]>
Reviewed-by: Bob Picco <[e-mail]>
---
 include/linux/mm.h  | 11 +++++++++++
 mm/sparse-vmemmap.c | 14 +++++++-------
 mm/sparse.c         |  6 +++---
 3 files changed, 21 insertions(+), 10 deletions(-)

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0a440ff8f226..fba540aef1da 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2456,6 +2456,17 @@  static inline void *vmemmap_alloc_block_buf(unsigned long size, int node)
 	return __vmemmap_alloc_block_buf(size, node, NULL);
 }
 
+static inline void *vmemmap_alloc_block_zero(unsigned long size, int node)
+{
+	void *p = vmemmap_alloc_block(size, node);
+
+	if (!p)
+		return NULL;
+	memset(p, 0, size);
+
+	return p;
+}
+
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(unsigned long start, unsigned long end,
 			       int node);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index c50b1a14d55e..423d4da85a91 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -41,7 +41,7 @@  static void * __ref __earlyonly_bootmem_alloc(int node,
 				unsigned long align,
 				unsigned long goal)
 {
-	return memblock_virt_alloc_try_nid(size, align, goal,
+	return memblock_virt_alloc_try_nid_raw(size, align, goal,
 					    BOOTMEM_ALLOC_ACCESSIBLE, node);
 }
 
@@ -56,11 +56,11 @@  void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 
 		if (node_state(node, N_HIGH_MEMORY))
 			page = alloc_pages_node(
-				node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
+				node, GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		else
 			page = alloc_pages(
-				GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
+				GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		if (page)
 			return page_address(page);
@@ -188,7 +188,7 @@  pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 {
 	pmd_t *pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd)) {
-		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pmd_populate_kernel(&init_mm, pmd, p);
@@ -200,7 +200,7 @@  pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
 {
 	pud_t *pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
-		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pud_populate(&init_mm, pud, p);
@@ -212,7 +212,7 @@  p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
 {
 	p4d_t *p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d)) {
-		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		p4d_populate(&init_mm, p4d, p);
@@ -224,7 +224,7 @@  pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 {
 	pgd_t *pgd = pgd_offset_k(addr);
 	if (pgd_none(*pgd)) {
-		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pgd_populate(&init_mm, pgd, p);
diff --git a/mm/sparse.c b/mm/sparse.c
index 7b4be3fd5cac..0e315766ad11 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -441,9 +441,9 @@  void __init sparse_mem_maps_populate_node(struct page **map_map,
 	}
 
 	size = PAGE_ALIGN(size);
-	map = memblock_virt_alloc_try_nid(size * map_count,
-					  PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
-					  BOOTMEM_ALLOC_ACCESSIBLE, nodeid);
+	map = memblock_virt_alloc_try_nid_raw(size * map_count,
+					      PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
+					      BOOTMEM_ALLOC_ACCESSIBLE, nodeid);
 	if (map) {
 		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
 			if (!present_section_nr(pnum))