Instability in current -git tree

Commit Message

Linus Torvalds July 14, 2018, 3:04 a.m. UTC

On Fri, Jul 13, 2018 at 7:40 PM Linus Torvalds
<[e-mail]> wrote:
>
> Should we perhaps just revert
>
>   124049decbb1 x86/e820: put !E820_TYPE_RAM regions into memblock.reserved
>   f7f99100d8d9 mm: stop zeroing memory during allocation in vmemmap
>
> it still reverts fairly cleanly (there's a trivial conflict with the
> older commit).

This is the revert I'm testing right now..  It seems to be stable for
me (doing that "limited memory, nasty memory hogs" test that I did
before), but I'll keep running this for a while. Even with the memory
limit and the memory hogs, it sometimes took some time to crash.

                  Linus

Patch

 arch/x86/kernel/e820.c | 15 +++------------
 mm/page_alloc.c        |  1 -
 mm/sparse-vmemmap.c    | 23 ++++++-----------------
 mm/sparse.c            |  6 +++---
 4 files changed, 12 insertions(+), 33 deletions(-)

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index c88c23c658c1..d1f25c831447 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1248,7 +1248,6 @@  void __init e820__memblock_setup(void)
 {
 	int i;
 	u64 end;
-	u64 addr = 0;
 
 	/*
 	 * The bootstrap memblock region count maximum is 128 entries
@@ -1265,21 +1264,13 @@  void __init e820__memblock_setup(void)
 		struct e820_entry *entry = &e820_table->entries[i];
 
 		end = entry->addr + entry->size;
-		if (addr < entry->addr)
-			memblock_reserve(addr, entry->addr - addr);
-		addr = end;
 		if (end != (resource_size_t)end)
 			continue;
 
-		/*
-		 * all !E820_TYPE_RAM ranges (including gap ranges) are put
-		 * into memblock.reserved to make sure that struct pages in
-		 * such regions are not left uninitialized after bootup.
-		 */
 		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
-			memblock_reserve(entry->addr, entry->size);
-		else
-			memblock_add(entry->addr, entry->size);
+			continue;
+
+		memblock_add(entry->addr, entry->size);
 	}
 
 	/* Throw away partial pages: */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..2fe859726f9a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1171,7 +1171,6 @@  static void free_one_page(struct zone *zone,
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
 				unsigned long zone, int nid)
 {
-	mm_zero_struct_page(page);
 	set_page_links(page, zone, nid, pfn);
 	init_page_count(page);
 	page_mapcount_reset(page);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index bd0276d5f66b..c363c60be7d3 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -42,7 +42,7 @@  static void * __ref __earlyonly_bootmem_alloc(int node,
 				unsigned long align,
 				unsigned long goal)
 {
-	return memblock_virt_alloc_try_nid_raw(size, align, goal,
+	return memblock_virt_alloc_try_nid(size, align, goal,
 					    BOOTMEM_ALLOC_ACCESSIBLE, node);
 }
 
@@ -53,7 +53,7 @@  void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 {
 	/* If the main allocator is up use that, fallback to bootmem. */
 	if (slab_is_available()) {
-		gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
+		gfp_t gfp_mask = GFP_KERNEL|__GFP_ZERO|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
 		int order = get_order(size);
 		static bool warned;
 		struct page *page;
@@ -165,22 +165,11 @@  pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
 	return pte;
 }
 
-static void * __meminit 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;
-}
-
 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_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pmd_populate_kernel(&init_mm, pmd, p);
@@ -192,7 +181,7 @@  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_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pud_populate(&init_mm, pud, p);
@@ -204,7 +193,7 @@  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_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		p4d_populate(&init_mm, p4d, p);
@@ -216,7 +205,7 @@  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_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pgd_populate(&init_mm, pgd, p);
diff --git a/mm/sparse.c b/mm/sparse.c
index f13f2723950a..4cc1558fd10c 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -419,9 +419,9 @@  void __init sparse_mem_maps_populate_node(struct page **map_map,
 	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
 
 	size = PAGE_ALIGN(size);
-	map = memblock_virt_alloc_try_nid_raw(size * map_count,
-					      PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
-					      BOOTMEM_ALLOC_ACCESSIBLE, nodeid);
+	map = memblock_virt_alloc_try_nid(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))