Merge branch 'master' into for-linus

Conflicts:
	include/linux/percpu.h
	mm/percpu.c

13 files changed, 851 insertions, 504 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 142c84a5499..13b0caa9793 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
+#include <linux/memblock.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -434,7 +435,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(physaddr, physaddr + size);
+	kmemleak_free_part(__va(physaddr), size);
+	memblock_x86_free_range(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
 
@@ -459,7 +461,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(addr, addr + size);
+	kmemleak_free_part(__va(addr), size);
+	memblock_x86_free_range(addr, addr + size);
 #else
 	unsigned long start, end;
 
@@ -526,6 +529,12 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 }
 
 #ifndef CONFIG_NO_BOOTMEM
+int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+				   int flags)
+{
+	return reserve_bootmem(phys, len, flags);
+}
+
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
diff --git a/mm/ksm.c b/mm/ksm.c
index b1873cf03ed..65ab5c7067d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -712,7 +712,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	if (!ptep)
 		goto out;
 
-	if (pte_write(*ptep)) {
+	if (pte_write(*ptep) || pte_dirty(*ptep)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
@@ -735,7 +735,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			set_pte_at(mm, addr, ptep, entry);
 			goto out_unlock;
 		}
-		entry = pte_wrprotect(entry);
+		if (pte_dirty(entry))
+			set_page_dirty(page);
+		entry = pte_mkclean(pte_wrprotect(entry));
 		set_pte_at_notify(mm, addr, ptep, entry);
 	}
 	*orig_pte = *ptep;
diff --git a/mm/memblock.c b/mm/memblock.c
index 43840b305ec..400dc62697d 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -11,237 +11,423 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
+#include <linux/poison.h>
+#include <linux/pfn.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/memblock.h>
 
-#define MEMBLOCK_ALLOC_ANYWHERE	0
+struct memblock memblock __initdata_memblock;
 
-struct memblock memblock;
+int memblock_debug __initdata_memblock;
+int memblock_can_resize __initdata_memblock;
+static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
+static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
 
-static int memblock_debug;
+/* inline so we don't get a warning when pr_debug is compiled out */
+static inline const char *memblock_type_name(struct memblock_type *type)
+{
+	if (type == &memblock.memory)
+		return "memory";
+	else if (type == &memblock.reserved)
+		return "reserved";
+	else
+		return "unknown";
+}
 
-static int __init early_memblock(char *p)
+/*
+ * Address comparison utilities
+ */
+
+static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size)
 {
-	if (p && strstr(p, "debug"))
-		memblock_debug = 1;
+	return addr & ~(size - 1);
+}
+
+static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size)
+{
+	return (addr + (size - 1)) & ~(size - 1);
+}
+
+static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				       phys_addr_t base2, phys_addr_t size2)
+{
+	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
+}
+
+static long __init_memblock memblock_addrs_adjacent(phys_addr_t base1, phys_addr_t size1,
+			       phys_addr_t base2, phys_addr_t size2)
+{
+	if (base2 == base1 + size1)
+		return 1;
+	else if (base1 == base2 + size2)
+		return -1;
+
 	return 0;
 }
-early_param("memblock", early_memblock);
 
-static void memblock_dump(struct memblock_region *region, char *name)
+static long __init_memblock memblock_regions_adjacent(struct memblock_type *type,
+				 unsigned long r1, unsigned long r2)
 {
-	unsigned long long base, size;
-	int i;
+	phys_addr_t base1 = type->regions[r1].base;
+	phys_addr_t size1 = type->regions[r1].size;
+	phys_addr_t base2 = type->regions[r2].base;
+	phys_addr_t size2 = type->regions[r2].size;
 
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+	return memblock_addrs_adjacent(base1, size1, base2, size2);
+}
 
-	for (i = 0; i < region->cnt; i++) {
-		base = region->region[i].base;
-		size = region->region[i].size;
+long __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+{
+	unsigned long i;
 
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
+		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
+			break;
 	}
+
+	return (i < type->cnt) ? i : -1;
 }
 
-void memblock_dump_all(void)
+/*
+ * Find, allocate, deallocate or reserve unreserved regions. All allocations
+ * are top-down.
+ */
+
+static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_addr_t end,
+					  phys_addr_t size, phys_addr_t align)
 {
-	if (!memblock_debug)
-		return;
+	phys_addr_t base, res_base;
+	long j;
 
-	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)memblock.rmo_size);
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size);
+	/* In case, huge size is requested */
+	if (end < size)
+		return MEMBLOCK_ERROR;
 
-	memblock_dump(&memblock.memory, "memory");
-	memblock_dump(&memblock.reserved, "reserved");
+	base = memblock_align_down((end - size), align);
+
+	/* Prevent allocations returning 0 as it's also used to
+	 * indicate an allocation failure
+	 */
+	if (start == 0)
+		start = PAGE_SIZE;
+
+	while (start <= base) {
+		j = memblock_overlaps_region(&memblock.reserved, base, size);
+		if (j < 0)
+			return base;
+		res_base = memblock.reserved.regions[j].base;
+		if (res_base < size)
+			break;
+		base = memblock_align_down(res_base - size, align);
+	}
+
+	return MEMBLOCK_ERROR;
 }
 
-static unsigned long memblock_addrs_overlap(u64 base1, u64 size1, u64 base2,
-					u64 size2)
+static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
+			phys_addr_t align, phys_addr_t start, phys_addr_t end)
 {
-	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
+	long i;
+
+	BUG_ON(0 == size);
+
+	size = memblock_align_up(size, align);
+
+	/* Pump up max_addr */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
+
+	/* We do a top-down search, this tends to limit memory
+	 * fragmentation by keeping early boot allocs near the
+	 * top of memory
+	 */
+	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
+		phys_addr_t memblockbase = memblock.memory.regions[i].base;
+		phys_addr_t memblocksize = memblock.memory.regions[i].size;
+		phys_addr_t bottom, top, found;
+
+		if (memblocksize < size)
+			continue;
+		if ((memblockbase + memblocksize) <= start)
+			break;
+		bottom = max(memblockbase, start);
+		top = min(memblockbase + memblocksize, end);
+		if (bottom >= top)
+			continue;
+		found = memblock_find_region(bottom, top, size, align);
+		if (found != MEMBLOCK_ERROR)
+			return found;
+	}
+	return MEMBLOCK_ERROR;
 }
 
-static long memblock_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
 {
-	if (base2 == base1 + size1)
-		return 1;
-	else if (base1 == base2 + size2)
-		return -1;
+	return memblock_find_base(size, align, start, end);
+}
 
-	return 0;
+/*
+ * Free memblock.reserved.regions
+ */
+int __init_memblock memblock_free_reserved_regions(void)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	return memblock_free(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
 }
 
-static long memblock_regions_adjacent(struct memblock_region *rgn,
-		unsigned long r1, unsigned long r2)
+/*
+ * Reserve memblock.reserved.regions
+ */
+int __init_memblock memblock_reserve_reserved_regions(void)
 {
-	u64 base1 = rgn->region[r1].base;
-	u64 size1 = rgn->region[r1].size;
-	u64 base2 = rgn->region[r2].base;
-	u64 size2 = rgn->region[r2].size;
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
 
-	return memblock_addrs_adjacent(base1, size1, base2, size2);
+	return memblock_reserve(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
 }
 
-static void memblock_remove_region(struct memblock_region *rgn, unsigned long r)
+static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	unsigned long i;
 
-	for (i = r; i < rgn->cnt - 1; i++) {
-		rgn->region[i].base = rgn->region[i + 1].base;
-		rgn->region[i].size = rgn->region[i + 1].size;
+	for (i = r; i < type->cnt - 1; i++) {
+		type->regions[i].base = type->regions[i + 1].base;
+		type->regions[i].size = type->regions[i + 1].size;
 	}
-	rgn->cnt--;
+	type->cnt--;
 }
 
 /* Assumption: base addr of region 1 < base addr of region 2 */
-static void memblock_coalesce_regions(struct memblock_region *rgn,
+static void __init_memblock memblock_coalesce_regions(struct memblock_type *type,
 		unsigned long r1, unsigned long r2)
 {
-	rgn->region[r1].size += rgn->region[r2].size;
-	memblock_remove_region(rgn, r2);
+	type->regions[r1].size += type->regions[r2].size;
+	memblock_remove_region(type, r2);
 }
 
-void __init memblock_init(void)
+/* Defined below but needed now */
+static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size);
+
+static int __init_memblock memblock_double_array(struct memblock_type *type)
 {
-	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
-	 * This simplifies the memblock_add() code below...
+	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_size, new_size, addr;
+	int use_slab = slab_is_available();
+
+	/* We don't allow resizing until we know about the reserved regions
+	 * of memory that aren't suitable for allocation
 	 */
-	memblock.memory.region[0].base = 0;
-	memblock.memory.region[0].size = 0;
-	memblock.memory.cnt = 1;
+	if (!memblock_can_resize)
+		return -1;
 
-	/* Ditto. */
-	memblock.reserved.region[0].base = 0;
-	memblock.reserved.region[0].size = 0;
-	memblock.reserved.cnt = 1;
-}
+	/* Calculate new doubled size */
+	old_size = type->max * sizeof(struct memblock_region);
+	new_size = old_size << 1;
+
+	/* Try to find some space for it.
+	 *
+	 * WARNING: We assume that either slab_is_available() and we use it or
+	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
+	 * when bootmem is currently active (unless bootmem itself is implemented
+	 * on top of MEMBLOCK which isn't the case yet)
+	 *
+	 * This should however not be an issue for now, as we currently only
+	 * call into MEMBLOCK while it's still active, or much later when slab is
+	 * active for memory hotplug operations
+	 */
+	if (use_slab) {
+		new_array = kmalloc(new_size, GFP_KERNEL);
+		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+	} else
+		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
+	if (addr == MEMBLOCK_ERROR) {
+		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
+		       memblock_type_name(type), type->max, type->max * 2);
+		return -1;
+	}
+	new_array = __va(addr);
 
-void __init memblock_analyze(void)
-{
-	int i;
+	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
+		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
 
-	memblock.memory.size = 0;
+	/* Found space, we now need to move the array over before
+	 * we add the reserved region since it may be our reserved
+	 * array itself that is full.
+	 */
+	memcpy(new_array, type->regions, old_size);
+	memset(new_array + type->max, 0, old_size);
+	old_array = type->regions;
+	type->regions = new_array;
+	type->max <<= 1;
+
+	/* If we use SLAB that's it, we are done */
+	if (use_slab)
+		return 0;
 
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memblock.memory.size += memblock.memory.region[i].size;
+	/* Add the new reserved region now. Should not fail ! */
+	BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size) < 0);
+
+	/* If the array wasn't our static init one, then free it. We only do
+	 * that before SLAB is available as later on, we don't know whether
+	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
+	 * anyways
+	 */
+	if (old_array != memblock_memory_init_regions &&
+	    old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_size);
+
+	return 0;
 }
 
-static long memblock_add_region(struct memblock_region *rgn, u64 base, u64 size)
+extern int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+					  phys_addr_t addr2, phys_addr_t size2)
+{
+	return 1;
+}
+
+static long __init_memblock memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;
 	long adjacent, i;
 
-	if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if ((type->cnt == 1) && (type->regions[0].size == 0)) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
 		return 0;
 	}
 
 	/* First try and coalesce this MEMBLOCK with another. */
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
 
 		if ((rgnbase == base) && (rgnsize == size))
 			/* Already have this region, so we're done */
 			return 0;
 
 		adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize);
+		/* Check if arch allows coalescing */
+		if (adjacent != 0 && type == &memblock.memory &&
+		    !memblock_memory_can_coalesce(base, size, rgnbase, rgnsize))
+			break;
 		if (adjacent > 0) {
-			rgn->region[i].base -= size;
-			rgn->region[i].size += size;
+			type->regions[i].base -= size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		} else if (adjacent < 0) {
-			rgn->region[i].size += size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		}
 	}
 
-	if ((i < rgn->cnt - 1) && memblock_regions_adjacent(rgn, i, i+1)) {
-		memblock_coalesce_regions(rgn, i, i+1);
+	/* If we plugged a hole, we may want to also coalesce with the
+	 * next region
+	 */
+	if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1) &&
+	    ((type != &memblock.memory || memblock_memory_can_coalesce(type->regions[i].base,
+							     type->regions[i].size,
+							     type->regions[i+1].base,
+							     type->regions[i+1].size)))) {
+		memblock_coalesce_regions(type, i, i+1);
 		coalesced++;
 	}
 
 	if (coalesced)
 		return coalesced;
-	if (rgn->cnt >= MAX_MEMBLOCK_REGIONS)
+
+	/* If we are out of space, we fail. It's too late to resize the array
+	 * but then this shouldn't have happened in the first place.
+	 */
+	if (WARN_ON(type->cnt >= type->max))
 		return -1;
 
 	/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */
-	for (i = rgn->cnt - 1; i >= 0; i--) {
-		if (base < rgn->region[i].base) {
-			rgn->region[i+1].base = rgn->region[i].base;
-			rgn->region[i+1].size = rgn->region[i].size;
+	for (i = type->cnt - 1; i >= 0; i--) {
+		if (base < type->regions[i].base) {
+			type->regions[i+1].base = type->regions[i].base;
+			type->regions[i+1].size = type->regions[i].size;
 		} else {
-			rgn->region[i+1].base = base;
-			rgn->region[i+1].size = size;
+			type->regions[i+1].base = base;
+			type->regions[i+1].size = size;
 			break;
 		}
 	}
 
-	if (base < rgn->region[0].base) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if (base < type->regions[0].base) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
+	}
+	type->cnt++;
+
+	/* The array is full ? Try to resize it. If that fails, we undo
+	 * our allocation and return an error
+	 */
+	if (type->cnt == type->max && memblock_double_array(type)) {
+		type->cnt--;
+		return -1;
 	}
-	rgn->cnt++;
 
 	return 0;
 }
 
-long memblock_add(u64 base, u64 size)
+long __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.memory;
-
-	/* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */
-	if (base == 0)
-		memblock.rmo_size = size;
-
-	return memblock_add_region(_rgn, base, size);
+	return memblock_add_region(&memblock.memory, base, size);
 
 }
 
-static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
+static long __init_memblock __memblock_remove(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
-	u64 rgnbegin, rgnend;
-	u64 end = base + size;
+	phys_addr_t rgnbegin, rgnend;
+	phys_addr_t end = base + size;
 	int i;
 
 	rgnbegin = rgnend = 0; /* supress gcc warnings */
 
 	/* Find the region where (base, size) belongs to */
-	for (i=0; i < rgn->cnt; i++) {
-		rgnbegin = rgn->region[i].base;
-		rgnend = rgnbegin + rgn->region[i].size;
+	for (i=0; i < type->cnt; i++) {
+		rgnbegin = type->regions[i].base;
+		rgnend = rgnbegin + type->regions[i].size;
 
 		if ((rgnbegin <= base) && (end <= rgnend))
 			break;
 	}
 
 	/* Didn't find the region */
-	if (i == rgn->cnt)
+	if (i == type->cnt)
 		return -1;
 
 	/* Check to see if we are removing entire region */
 	if ((rgnbegin == base) && (rgnend == end)) {
-		memblock_remove_region(rgn, i);
+		memblock_remove_region(type, i);
 		return 0;
 	}
 
 	/* Check to see if region is matching at the front */
 	if (rgnbegin == base) {
-		rgn->region[i].base = end;
-		rgn->region[i].size -= size;
+		type->regions[i].base = end;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
 	/* Check to see if the region is matching at the end */
 	if (rgnend == end) {
-		rgn->region[i].size -= size;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
@@ -249,208 +435,189 @@ static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
 	 * We need to split the entry -  adjust the current one to the
 	 * beginging of the hole and add the region after hole.
 	 */
-	rgn->region[i].size = base - rgn->region[i].base;
-	return memblock_add_region(rgn, end, rgnend - end);
+	type->regions[i].size = base - type->regions[i].base;
+	return memblock_add_region(type, end, rgnend - end);
 }
 
-long memblock_remove(u64 base, u64 size)
+long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.memory, base, size);
 }
 
-long __init memblock_free(u64 base, u64 size)
+long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.reserved, base, size);
 }
 
-long __init memblock_reserve(u64 base, u64 size)
+long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.reserved;
+	struct memblock_type *_rgn = &memblock.reserved;
 
 	BUG_ON(0 == size);
 
 	return memblock_add_region(_rgn, base, size);
 }
 
-long memblock_overlaps_region(struct memblock_region *rgn, u64 base, u64 size)
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	unsigned long i;
+	phys_addr_t found;
 
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
+	size = memblock_align_up(size, align);
 
-	return (i < rgn->cnt) ? i : -1;
+	found = memblock_find_base(size, align, 0, max_addr);
+	if (found != MEMBLOCK_ERROR &&
+	    memblock_add_region(&memblock.reserved, found, size) >= 0)
+		return found;
+
+	return 0;
 }
 
-static u64 memblock_align_down(u64 addr, u64 size)
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	return addr & ~(size - 1);
+	phys_addr_t alloc;
+
+	alloc = __memblock_alloc_base(size, align, max_addr);
+
+	if (alloc == 0)
+		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
+		      (unsigned long long) size, (unsigned long long) max_addr);
+
+	return alloc;
 }
 
-static u64 memblock_align_up(u64 addr, u64 size)
+phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-	return (addr + (size - 1)) & ~(size - 1);
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
-static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
+
+/*
+ * Additional node-local allocators. Search for node memory is bottom up
+ * and walks memblock regions within that node bottom-up as well, but allocation
+ * within an memblock region is top-down. XXX I plan to fix that at some stage
+ *
+ * WARNING: Only available after early_node_map[] has been populated,
+ * on some architectures, that is after all the calls to add_active_range()
+ * have been done to populate it.
+ */
+
+phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {
-	u64 base, res_base;
-	long j;
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+	/*
+	 * This code originates from sparc which really wants use to walk by addresses
+	 * and returns the nid. This is not very convenient for early_pfn_map[] users
+	 * as the map isn't sorted yet, and it really wants to be walked by nid.
+	 *
+	 * For now, I implement the inefficient method below which walks the early
+	 * map multiple times. Eventually we may want to use an ARCH config option
+	 * to implement a completely different method for both case.
+	 */
+	unsigned long start_pfn, end_pfn;
+	int i;
 
-	base = memblock_align_down((end - size), align);
-	while (start <= base) {
-		j = memblock_overlaps_region(&memblock.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (memblock_add_region(&memblock.reserved, base, size) < 0)
-				base = ~(u64)0;
-			return base;
-		}
-		res_base = memblock.reserved.region[j].base;
-		if (res_base < size)
-			break;
-		base = memblock_align_down(res_base - size, align);
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
+		if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
+			continue;
+		*nid = i;
+		return min(end, PFN_PHYS(end_pfn));
 	}
+#endif
+	*nid = 0;
 
-	return ~(u64)0;
+	return end;
 }
 
-static u64 __init memblock_alloc_nid_region(struct memblock_property *mp,
-				       u64 (*nid_range)(u64, u64, int *),
-				       u64 size, u64 align, int nid)
+static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
+					       phys_addr_t size,
+					       phys_addr_t align, int nid)
 {
-	u64 start, end;
+	phys_addr_t start, end;
 
 	start = mp->base;
 	end = start + mp->size;
 
 	start = memblock_align_up(start, align);
 	while (start < end) {
-		u64 this_end;
+		phys_addr_t this_end;
 		int this_nid;
 
-		this_end = nid_range(start, end, &this_nid);
+		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
-			u64 ret = memblock_alloc_nid_unreserved(start, this_end,
-							   size, align);
-			if (ret != ~(u64)0)
+			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
+			if (ret != MEMBLOCK_ERROR &&
+			    memblock_add_region(&memblock.reserved, ret, size) >= 0)
 				return ret;
 		}
 		start = this_end;
 	}
 
-	return ~(u64)0;
+	return MEMBLOCK_ERROR;
 }
 
-u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
+phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	struct memblock_region *mem = &memblock.memory;
+	struct memblock_type *mem = &memblock.memory;
 	int i;
 
 	BUG_ON(0 == size);
 
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
 	size = memblock_align_up(size, align);
 
+	/* We do a bottom-up search for a region with the right
+	 * nid since that's easier considering how memblock_nid_range()
+	 * works
+	 */
 	for (i = 0; i < mem->cnt; i++) {
-		u64 ret = memblock_alloc_nid_region(&mem->region[i],
-					       nid_range,
+		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);
-		if (ret != ~(u64)0)
+		if (ret != MEMBLOCK_ERROR)
 			return ret;
 	}
 
-	return memblock_alloc(size, align);
-}
-
-u64 __init memblock_alloc(u64 size, u64 align)
-{
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
+	return 0;
 }
 
-u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr)
+phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	u64 alloc;
-
-	alloc = __memblock_alloc_base(size, align, max_addr);
+	phys_addr_t res = memblock_alloc_nid(size, align, nid);
 
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
+	if (res)
+		return res;
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
 }
 
-u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	long i, j;
-	u64 base = 0;
-	u64 res_base;
-
-	BUG_ON(0 == size);
 
-	size = memblock_align_up(size, align);
-
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */
-	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-		max_addr = MEMBLOCK_REAL_LIMIT;
-
-	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
-		u64 memblockbase = memblock.memory.region[i].base;
-		u64 memblocksize = memblock.memory.region[i].size;
-
-		if (memblocksize < size)
-			continue;
-		if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-			base = memblock_align_down(memblockbase + memblocksize - size, align);
-		else if (memblockbase < max_addr) {
-			base = min(memblockbase + memblocksize, max_addr);
-			base = memblock_align_down(base - size, align);
-		} else
-			continue;
-
-		while (base && memblockbase <= base) {
-			j = memblock_overlaps_region(&memblock.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (memblock_add_region(&memblock.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = memblock.reserved.region[j].base;
-			if (res_base < size)
-				break;
-			base = memblock_align_down(res_base - size, align);
-		}
-	}
-	return 0;
-}
+/*
+ * Remaining API functions
+ */
 
 /* You must call memblock_analyze() before this. */
-u64 __init memblock_phys_mem_size(void)
+phys_addr_t __init memblock_phys_mem_size(void)
 {
-	return memblock.memory.size;
+	return memblock.memory_size;
 }
 
-u64 memblock_end_of_DRAM(void)
+phys_addr_t __init_memblock memblock_end_of_DRAM(void)
 {
 	int idx = memblock.memory.cnt - 1;
 
-	return (memblock.memory.region[idx].base + memblock.memory.region[idx].size);
+	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
 }
 
 /* You must call memblock_analyze() after this. */
-void __init memblock_enforce_memory_limit(u64 memory_limit)
+void __init memblock_enforce_memory_limit(phys_addr_t memory_limit)
 {
 	unsigned long i;
-	u64 limit;
-	struct memblock_property *p;
+	phys_addr_t limit;
+	struct memblock_region *p;
 
 	if (!memory_limit)
 		return;
@@ -458,24 +625,21 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 	/* Truncate the memblock regions to satisfy the memory limit. */
 	limit = memory_limit;
 	for (i = 0; i < memblock.memory.cnt; i++) {
-		if (limit > memblock.memory.region[i].size) {
-			limit -= memblock.memory.region[i].size;
+		if (limit > memblock.memory.regions[i].size) {
+			limit -= memblock.memory.regions[i].size;
 			continue;
 		}
 
-		memblock.memory.region[i].size = limit;
+		memblock.memory.regions[i].size = limit;
 		memblock.memory.cnt = i + 1;
 		break;
 	}
 
-	if (memblock.memory.region[0].size < memblock.rmo_size)
-		memblock.rmo_size = memblock.memory.region[0].size;
-
 	memory_limit = memblock_end_of_DRAM();
 
 	/* And truncate any reserves above the limit also. */
 	for (i = 0; i < memblock.reserved.cnt; i++) {
-		p = &memblock.reserved.region[i];
+		p = &memblock.reserved.regions[i];
 
 		if (p->base > memory_limit)
 			p->size = 0;
@@ -489,53 +653,190 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 	}
 }
 
-int __init memblock_is_reserved(u64 addr)
+static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
+{
+	unsigned int left = 0, right = type->cnt;
+
+	do {
+		unsigned int mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else
+			return mid;
+	} while (left < right);
+	return -1;
+}
+
+int __init memblock_is_reserved(phys_addr_t addr)
+{
+	return memblock_search(&memblock.reserved, addr) != -1;
+}
+
+int __init_memblock memblock_is_memory(phys_addr_t addr)
+{
+	return memblock_search(&memblock.memory, addr) != -1;
+}
+
+int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
+{
+	int idx = memblock_search(&memblock.reserved, base);
+
+	if (idx == -1)
+		return 0;
+	return memblock.reserved.regions[idx].base <= base &&
+		(memblock.reserved.regions[idx].base +
+		 memblock.reserved.regions[idx].size) >= (base + size);
+}
+
+int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+}
+
+
+void __init_memblock memblock_set_current_limit(phys_addr_t limit)
 {
+	memblock.current_limit = limit;
+}
+
+static void __init_memblock memblock_dump(struct memblock_type *region, char *name)
+{
+	unsigned long long base, size;
 	int i;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		u64 upper = memblock.reserved.region[i].base +
-			memblock.reserved.region[i].size - 1;
-		if ((addr >= memblock.reserved.region[i].base) && (addr <= upper))
-			return 1;
+	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+
+	for (i = 0; i < region->cnt; i++) {
+		base = region->regions[i].base;
+		size = region->regions[i].size;
+
+		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n",
+		    name, i, base, base + size - 1, size);
 	}
-	return 0;
 }
 
-int memblock_is_region_reserved(u64 base, u64 size)
+void __init_memblock memblock_dump_all(void)
 {
-	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+	if (!memblock_debug)
+		return;
+
+	pr_info("MEMBLOCK configuration:\n");
+	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
+
+	memblock_dump(&memblock.memory, "memory");
+	memblock_dump(&memblock.reserved, "reserved");
 }
 
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int memblock_find(struct memblock_property *res)
+void __init memblock_analyze(void)
 {
 	int i;
-	u64 rstart, rend;
 
-	rstart = res->base;
-	rend = rstart + res->size - 1;
+	/* Check marker in the unused last array entry */
+	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+
+	memblock.memory_size = 0;
+
+	for (i = 0; i < memblock.memory.cnt; i++)
+		memblock.memory_size += memblock.memory.regions[i].size;
+
+	/* We allow resizing from there */
+	memblock_can_resize = 1;
+}
+
+void __init memblock_init(void)
+{
+	static int init_done __initdata = 0;
+
+	if (init_done)
+		return;
+	init_done = 1;
+
+	/* Hookup the initial arrays */
+	memblock.memory.regions	= memblock_memory_init_regions;
+	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
+	memblock.reserved.regions	= memblock_reserved_init_regions;
+	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
+
+	/* Write a marker in the unused last array entry */
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
+	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
+	 * This simplifies the memblock_add() code below...
+	 */
+	memblock.memory.regions[0].base = 0;
+	memblock.memory.regions[0].size = 0;
+	memblock.memory.cnt = 1;
+
+	/* Ditto. */
+	memblock.reserved.regions[0].base = 0;
+	memblock.reserved.regions[0].size = 0;
+	memblock.reserved.cnt = 1;
+
+	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
+}
+
+static int __init early_memblock(char *p)
+{
+	if (p && strstr(p, "debug"))
+		memblock_debug = 1;
+	return 0;
+}
+early_param("memblock", early_memblock);
+
+#if defined(CONFIG_DEBUG_FS) && !defined(ARCH_DISCARD_MEMBLOCK)
+
+static int memblock_debug_show(struct seq_file *m, void *private)
+{
+	struct memblock_type *type = m->private;
+	struct memblock_region *reg;
+	int i;
+
+	for (i = 0; i < type->cnt; i++) {
+		reg = &type->regions[i];
+		seq_printf(m, "%4d: ", i);
+		if (sizeof(phys_addr_t) == 4)
+			seq_printf(m, "0x%08lx..0x%08lx\n",
+				   (unsigned long)reg->base,
+				   (unsigned long)(reg->base + reg->size - 1));
+		else
+			seq_printf(m, "0x%016llx..0x%016llx\n",
+				   (unsigned long long)reg->base,
+				   (unsigned long long)(reg->base + reg->size - 1));
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		u64 start = memblock.memory.region[i].base;
-		u64 end = start + memblock.memory.region[i].size - 1;
-
-		if (start > rend)
-			return -1;
-
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
 	}
-	return -1;
+	return 0;
+}
+
+static int memblock_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, memblock_debug_show, inode->i_private);
 }
+
+static const struct file_operations memblock_debug_fops = {
+	.open = memblock_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init memblock_init_debugfs(void)
+{
+	struct dentry *root = debugfs_create_dir("memblock", NULL);
+	if (!root)
+		return -ENXIO;
+	debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
+	debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+
+	return 0;
+}
+__initcall(memblock_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3eed583895a..9be3cf8a5da 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3587,9 +3587,13 @@ unlock:
 
 static void mem_cgroup_threshold(struct mem_cgroup *memcg)
 {
-	__mem_cgroup_threshold(memcg, false);
-	if (do_swap_account)
-		__mem_cgroup_threshold(memcg, true);
+	while (memcg) {
+		__mem_cgroup_threshold(memcg, false);
+		if (do_swap_account)
+			__mem_cgroup_threshold(memcg, true);
+
+		memcg = parent_mem_cgroup(memcg);
+	}
 }
 
 static int compare_thresholds(const void *a, const void *b)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9c26eeca134..757f6b0accf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -183,7 +183,7 @@ EXPORT_SYMBOL_GPL(hwpoison_filter);
  * signal.
  */
 static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
-			unsigned long pfn)
+			unsigned long pfn, struct page *page)
 {
 	struct siginfo si;
 	int ret;
@@ -198,7 +198,7 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
 #ifdef __ARCH_SI_TRAPNO
 	si.si_trapno = trapno;
 #endif
-	si.si_addr_lsb = PAGE_SHIFT;
+	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
 	/*
 	 * Don't use force here, it's convenient if the signal
 	 * can be temporarily blocked.
@@ -235,7 +235,7 @@ void shake_page(struct page *p, int access)
 		int nr;
 		do {
 			nr = shrink_slab(1000, GFP_KERNEL, 1000);
-			if (page_count(p) == 0)
+			if (page_count(p) == 1)
 				break;
 		} while (nr > 10);
 	}
@@ -327,7 +327,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
  * wrong earlier.
  */
 static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
-			  int fail, unsigned long pfn)
+			  int fail, struct page *page, unsigned long pfn)
 {
 	struct to_kill *tk, *next;
 
@@ -352,7 +352,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
 			 * process anyways.
 			 */
 			else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
-					      pfn) < 0)
+					      pfn, page) < 0)
 				printk(KERN_ERR
 		"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
 					pfn, tk->tsk->comm, tk->tsk->pid);
@@ -928,7 +928,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * any accesses to the poisoned memory.
 	 */
 	kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
-		      ret != SWAP_SUCCESS, pfn);
+		      ret != SWAP_SUCCESS, p, pfn);
 
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d649e..98b58fecede 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3185,7 +3185,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 		 * with threads.
 		 */
 		if (flags & FAULT_FLAG_WRITE)
-			flush_tlb_page(vma, address);
+			flush_tlb_fix_spurious_fault(vma, address);
 	}
 unlock:
 	pte_unmap_unlock(pte, ptl);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dd186c1a5d5..d4e940a2694 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -840,7 +840,6 @@ repeat:
 	ret = 0;
 	if (drain) {
 		lru_add_drain_all();
-		flush_scheduled_work();
 		cond_resched();
 		drain_all_pages();
 	}
@@ -862,7 +861,6 @@ repeat:
 	}
 	/* drain all zone's lru pagevec, this is asyncronous... */
 	lru_add_drain_all();
-	flush_scheduled_work();
 	yield();
 	/* drain pcp pages , this is synchrouns. */
 	drain_all_pages();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a8cfa9cc6e8..2a362c52fdf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -21,6 +21,7 @@
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
@@ -3636,6 +3637,41 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+
+	/* Need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		u64 addr;
+		u64 ei_start, ei_last;
+		u64 final_start, final_end;
+
+		ei_last = early_node_map[i].end_pfn;
+		ei_last <<= PAGE_SHIFT;
+		ei_start = early_node_map[i].start_pfn;
+		ei_start <<= PAGE_SHIFT;
+
+		final_start = max(ei_start, goal);
+		final_end = min(ei_last, limit);
+
+		if (final_start >= final_end)
+			continue;
+
+		addr = memblock_find_in_range(final_start, final_end, size, align);
+
+		if (addr == MEMBLOCK_ERROR)
+			continue;
+
+		return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+#endif
+
 int __init add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid)
 {
@@ -3655,46 +3691,26 @@ int __init add_from_early_node_map(struct range *range, int az,
 void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
-	int i;
 	void *ptr;
+	u64 addr;
 
-	if (limit > get_max_mapped())
-		limit = get_max_mapped();
-
-	/* need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		ei_last = early_node_map[i].end_pfn;
-		ei_last <<= PAGE_SHIFT;
-		ei_start = early_node_map[i].start_pfn;
-		ei_start <<= PAGE_SHIFT;
-		addr = find_early_area(ei_start, ei_last,
-					 goal, limit, size, align);
-
-		if (addr == -1ULL)
-			continue;
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
 
-#if 0
-		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
-				nid,
-				ei_start, ei_last, goal, limit, size,
-				align, addr);
-#endif
+	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		/*
-		 * The min_count is set to 0 so that bootmem allocated blocks
-		 * are never reported as leaks.
-		 */
-		kmemleak_alloc(ptr, size, 0, 0);
-		return ptr;
-	}
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
 
-	return NULL;
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
 }
 #endif
 
@@ -5182,9 +5198,9 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (!table)
 		panic("Failed to allocate %s hash table\n", tablename);
 
-	printk(KERN_INFO "%s hash table entries: %d (order: %d, %lu bytes)\n",
+	printk(KERN_INFO "%s hash table entries: %ld (order: %d, %lu bytes)\n",
 	       tablename,
-	       (1U << log2qty),
+	       (1UL << log2qty),
 	       ilog2(size) - PAGE_SHIFT,
 	       size);
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 9734b184aaa..6fc9015534f 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -826,8 +826,8 @@ fail_unlock_mutex:
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align.  Might
- * sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align.
+ * Might sleep.  Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -846,9 +846,10 @@ EXPORT_SYMBOL_GPL(__alloc_percpu);
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align from reserved
- * percpu area if arch has set it up; otherwise, allocation is served
- * from the same dynamic area.  Might sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align
+ * from reserved percpu area if arch has set it up; otherwise,
+ * allocation is served from the same dynamic area.  Might sleep.
+ * Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -1075,165 +1076,6 @@ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
 	free_bootmem(__pa(ai), ai->__ai_size);
 }
 
-#if defined(CONFIG_SMP) && (defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
-			    defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK))
-/**
- * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
- * @reserved_size: the size of reserved percpu area in bytes
- * @dyn_size: minimum free size for dynamic allocation in bytes
- * @atom_size: allocation atom size
- * @cpu_distance_fn: callback to determine distance between cpus, optional
- *
- * This function determines grouping of units, their mappings to cpus
- * and other parameters considering needed percpu size, allocation
- * atom size and distances between CPUs.
- *
- * Groups are always mutliples of atom size and CPUs which are of
- * LOCAL_DISTANCE both ways are grouped together and share space for
- * units in the same group.  The returned configuration is guaranteed
- * to have CPUs on different nodes on different groups and >=75% usage
- * of allocated virtual address space.
- *
- * RETURNS:
- * On success, pointer to the new allocation_info is returned.  On
- * failure, ERR_PTR value is returned.
- */
-static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
-				size_t reserved_size, size_t dyn_size,
-				size_t atom_size,
-				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
-{
-	static int group_map[NR_CPUS] __initdata;
-	static int group_cnt[NR_CPUS] __initdata;
-	const size_t static_size = __per_cpu_end - __per_cpu_start;
-	int nr_groups = 1, nr_units = 0;
-	size_t size_sum, min_unit_size, alloc_size;
-	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
-	int last_allocs, group, unit;
-	unsigned int cpu, tcpu;
-	struct pcpu_alloc_info *ai;
-	unsigned int *cpu_map;
-
-	/* this function may be called multiple times */
-	memset(group_map, 0, sizeof(group_map));
-	memset(group_cnt, 0, sizeof(group_cnt));
-
-	/* calculate size_sum and ensure dyn_size is enough for early alloc */
-	size_sum = PFN_ALIGN(static_size + reserved_size +
-			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
-	dyn_size = size_sum - static_size - reserved_size;
-
-	/*
-	 * Determine min_unit_size, alloc_size and max_upa such that
-	 * alloc_size is multiple of atom_size and is the smallest
-	 * which can accomodate 4k aligned segments which are equal to
-	 * or larger than min_unit_size.
-	 */
-	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
-
-	alloc_size = roundup(min_unit_size, atom_size);
-	upa = alloc_size / min_unit_size;
-	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
-		upa--;
-	max_upa = upa;
-
-	/* group cpus according to their proximity */
-	for_each_possible_cpu(cpu) {
-		group = 0;
-	next_group:
-		for_each_possible_cpu(tcpu) {
-			if (cpu == tcpu)
-				break;
-			if (group_map[tcpu] == group && cpu_distance_fn &&
-			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
-			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
-				group++;
-				nr_groups = max(nr_groups, group + 1);
-				goto next_group;
-			}
-		}
-		group_map[cpu] = group;
-		group_cnt[group]++;
-	}
-
-	/*
-	 * Expand unit size until address space usage goes over 75%
-	 * and then as much as possible without using more address
-	 * space.
-	 */
-	last_allocs = INT_MAX;
-	for (upa = max_upa; upa; upa--) {
-		int allocs = 0, wasted = 0;
-
-		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
-			continue;
-
-		for (group = 0; group < nr_groups; group++) {
-			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
-			allocs += this_allocs;
-			wasted += this_allocs * upa - group_cnt[group];
-		}
-
-		/*
-		 * Don't accept if wastage is over 1/3.  The
-		 * greater-than comparison ensures upa==1 always
-		 * passes the following check.
-		 */
-		if (wasted > num_possible_cpus() / 3)
-			continue;
-
-		/* and then don't consume more memory */
-		if (allocs > last_allocs)
-			break;
-		last_allocs = allocs;
-		best_upa = upa;
-	}
-	upa = best_upa;
-
-	/* allocate and fill alloc_info */
-	for (group = 0; group < nr_groups; group++)
-		nr_units += roundup(group_cnt[group], upa);
-
-	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
-	if (!ai)
-		return ERR_PTR(-ENOMEM);
-	cpu_map = ai->groups[0].cpu_map;
-
-	for (group = 0; group < nr_groups; group++) {
-		ai->groups[group].cpu_map = cpu_map;
-		cpu_map += roundup(group_cnt[group], upa);
-	}
-
-	ai->static_size = static_size;
-	ai->reserved_size = reserved_size;
-	ai->dyn_size = dyn_size;
-	ai->unit_size = alloc_size / upa;
-	ai->atom_size = atom_size;
-	ai->alloc_size = alloc_size;
-
-	for (group = 0, unit = 0; group_cnt[group]; group++) {
-		struct pcpu_group_info *gi = &ai->groups[group];
-
-		/*
-		 * Initialize base_offset as if all groups are located
-		 * back-to-back.  The caller should update this to
-		 * reflect actual allocation.
-		 */
-		gi->base_offset = unit * ai->unit_size;
-
-		for_each_possible_cpu(cpu)
-			if (group_map[cpu] == group)
-				gi->cpu_map[gi->nr_units++] = cpu;
-		gi->nr_units = roundup(gi->nr_units, upa);
-		unit += gi->nr_units;
-	}
-	BUG_ON(unit != nr_units);
-
-	return ai;
-}
-#endif	/* CONFIG_SMP && (CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
-			  CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) */
-
 /**
  * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
  * @lvl: loglevel
@@ -1532,8 +1374,180 @@ static int __init percpu_alloc_setup(char *str)
 }
 early_param("percpu_alloc", percpu_alloc_setup);
 
+/*
+ * pcpu_embed_first_chunk() is used by the generic percpu setup.
+ * Build it if needed by the arch config or the generic setup is going
+ * to be used.
+ */
 #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
 	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
+#define BUILD_EMBED_FIRST_CHUNK
+#endif
+
+/* build pcpu_page_first_chunk() iff needed by the arch config */
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
+#define BUILD_PAGE_FIRST_CHUNK
+#endif
+
+/* pcpu_build_alloc_info() is used by both embed and page first chunk */
+#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
+/**
+ * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
+ * @reserved_size: the size of reserved percpu area in bytes
+ * @dyn_size: minimum free size for dynamic allocation in bytes
+ * @atom_size: allocation atom size
+ * @cpu_distance_fn: callback to determine distance between cpus, optional
+ *
+ * This function determines grouping of units, their mappings to cpus
+ * and other parameters considering needed percpu size, allocation
+ * atom size and distances between CPUs.
+ *
+ * Groups are always mutliples of atom size and CPUs which are of
+ * LOCAL_DISTANCE both ways are grouped together and share space for
+ * units in the same group.  The returned configuration is guaranteed
+ * to have CPUs on different nodes on different groups and >=75% usage
+ * of allocated virtual address space.
+ *
+ * RETURNS:
+ * On success, pointer to the new allocation_info is returned.  On
+ * failure, ERR_PTR value is returned.
+ */
+static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
+				size_t reserved_size, size_t dyn_size,
+				size_t atom_size,
+				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
+{
+	static int group_map[NR_CPUS] __initdata;
+	static int group_cnt[NR_CPUS] __initdata;
+	const size_t static_size = __per_cpu_end - __per_cpu_start;
+	int nr_groups = 1, nr_units = 0;
+	size_t size_sum, min_unit_size, alloc_size;
+	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
+	int last_allocs, group, unit;
+	unsigned int cpu, tcpu;
+	struct pcpu_alloc_info *ai;
+	unsigned int *cpu_map;
+
+	/* this function may be called multiple times */
+	memset(group_map, 0, sizeof(group_map));
+	memset(group_cnt, 0, sizeof(group_cnt));
+
+	/* calculate size_sum and ensure dyn_size is enough for early alloc */
+	size_sum = PFN_ALIGN(static_size + reserved_size +
+			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
+	dyn_size = size_sum - static_size - reserved_size;
+
+	/*
+	 * Determine min_unit_size, alloc_size and max_upa such that
+	 * alloc_size is multiple of atom_size and is the smallest
+	 * which can accomodate 4k aligned segments which are equal to
+	 * or larger than min_unit_size.
+	 */
+	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
+
+	alloc_size = roundup(min_unit_size, atom_size);
+	upa = alloc_size / min_unit_size;
+	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+		upa--;
+	max_upa = upa;
+
+	/* group cpus according to their proximity */
+	for_each_possible_cpu(cpu) {
+		group = 0;
+	next_group:
+		for_each_possible_cpu(tcpu) {
+			if (cpu == tcpu)
+				break;
+			if (group_map[tcpu] == group && cpu_distance_fn &&
+			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
+			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
+				group++;
+				nr_groups = max(nr_groups, group + 1);
+				goto next_group;
+			}
+		}
+		group_map[cpu] = group;
+		group_cnt[group]++;
+	}
+
+	/*
+	 * Expand unit size until address space usage goes over 75%
+	 * and then as much as possible without using more address
+	 * space.
+	 */
+	last_allocs = INT_MAX;
+	for (upa = max_upa; upa; upa--) {
+		int allocs = 0, wasted = 0;
+
+		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+			continue;
+
+		for (group = 0; group < nr_groups; group++) {
+			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
+			allocs += this_allocs;
+			wasted += this_allocs * upa - group_cnt[group];
+		}
+
+		/*
+		 * Don't accept if wastage is over 1/3.  The
+		 * greater-than comparison ensures upa==1 always
+		 * passes the following check.
+		 */
+		if (wasted > num_possible_cpus() / 3)
+			continue;
+
+		/* and then don't consume more memory */
+		if (allocs > last_allocs)
+			break;
+		last_allocs = allocs;
+		best_upa = upa;
+	}
+	upa = best_upa;
+
+	/* allocate and fill alloc_info */
+	for (group = 0; group < nr_groups; group++)
+		nr_units += roundup(group_cnt[group], upa);
+
+	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
+	if (!ai)
+		return ERR_PTR(-ENOMEM);
+	cpu_map = ai->groups[0].cpu_map;
+
+	for (group = 0; group < nr_groups; group++) {
+		ai->groups[group].cpu_map = cpu_map;
+		cpu_map += roundup(group_cnt[group], upa);
+	}
+
+	ai->static_size = static_size;
+	ai->reserved_size = reserved_size;
+	ai->dyn_size = dyn_size;
+	ai->unit_size = alloc_size / upa;
+	ai->atom_size = atom_size;
+	ai->alloc_size = alloc_size;
+
+	for (group = 0, unit = 0; group_cnt[group]; group++) {
+		struct pcpu_group_info *gi = &ai->groups[group];
+
+		/*
+		 * Initialize base_offset as if all groups are located
+		 * back-to-back.  The caller should update this to
+		 * reflect actual allocation.
+		 */
+		gi->base_offset = unit * ai->unit_size;
+
+		for_each_possible_cpu(cpu)
+			if (group_map[cpu] == group)
+				gi->cpu_map[gi->nr_units++] = cpu;
+		gi->nr_units = roundup(gi->nr_units, upa);
+		unit += gi->nr_units;
+	}
+	BUG_ON(unit != nr_units);
+
+	return ai;
+}
+#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
+
+#if defined(BUILD_EMBED_FIRST_CHUNK)
 /**
  * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1662,10 +1676,9 @@ out_free:
 		free_bootmem(__pa(areas), areas_size);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
-	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif /* BUILD_EMBED_FIRST_CHUNK */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#ifdef BUILD_PAGE_FIRST_CHUNK
 /**
  * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1773,7 +1786,7 @@ out_free_ar:
 	pcpu_free_alloc_info(ai);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */
+#endif /* BUILD_PAGE_FIRST_CHUNK */
 
 #ifndef	CONFIG_HAVE_SETUP_PER_CPU_AREA
 /*
diff --git a/mm/rmap.c b/mm/rmap.c
index 9d2ba01bd4f..92e6757f196 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -381,7 +381,13 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
 	if (PageAnon(page)) {
-		if (vma->anon_vma->root != page_anon_vma(page)->root)
+		struct anon_vma *page__anon_vma = page_anon_vma(page);
+		/*
+		 * Note: swapoff's unuse_vma() is more efficient with this
+		 * check, and needs it to match anon_vma when KSM is active.
+		 */
+		if (!vma->anon_vma || !page__anon_vma ||
+		    vma->anon_vma->root != page__anon_vma->root)
 			return -EFAULT;
 	} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
 		if (!vma->vm_file ||
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index aa33fd67fa4..29d6cbffb28 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -220,18 +220,7 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-#ifdef CONFIG_NO_BOOTMEM
-		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
-		if (vmemmap_buf_start < vmemmap_buf) {
-			char name[15];
-
-			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
-			reserve_early_without_check(__pa(vmemmap_buf_start),
-						    __pa(vmemmap_buf), name);
-		}
-#else
 		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
-#endif
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7c703ff2f36..9fc7bac7db0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -139,7 +139,7 @@ static int discard_swap(struct swap_info_struct *si)
 	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
 	if (nr_blocks) {
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
+				nr_blocks, GFP_KERNEL, 0);
 		if (err)
 			return err;
 		cond_resched();
@@ -150,7 +150,7 @@ static int discard_swap(struct swap_info_struct *si)
 		nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
+				nr_blocks, GFP_KERNEL, 0);
 		if (err)
 			break;
 
@@ -189,7 +189,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 			start_block <<= PAGE_SHIFT - 9;
 			nr_blocks <<= PAGE_SHIFT - 9;
 			if (blkdev_issue_discard(si->bdev, start_block,
-				    nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT))
+				    nr_blocks, GFP_NOIO, 0))
 				break;
 		}
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c623e0ce3f0..9f909622a25 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -517,6 +517,15 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
 static void purge_fragmented_blocks_allcpus(void);
 
 /*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
+/*
  * Purges all lazily-freed vmap areas.
  *
  * If sync is 0 then don't purge if there is already a purge in progress.