Merge branch 'akpm' (Andrew's patchbomb)

Merge misc updates from Andrew Morton:
 "About half of most of MM.  Going very early this time due to
  uncertainty over the coreautounifiednumasched things.  I'll send the
  other half of most of MM tomorrow.  The rest of MM awaits a slab merge
  from Pekka."

* emailed patches from Andrew Morton: (71 commits)
  memory_hotplug: ensure every online node has NORMAL memory
  memory_hotplug: handle empty zone when online_movable/online_kernel
  mm, memory-hotplug: dynamic configure movable memory and portion memory
  drivers/base/node.c: cleanup node_state_attr[]
  bootmem: fix wrong call parameter for free_bootmem()
  avr32, kconfig: remove HAVE_ARCH_BOOTMEM
  mm: cma: remove watermark hacks
  mm: cma: skip watermarks check for already isolated blocks in split_free_page()
  mm, oom: fix race when specifying a thread as the oom origin
  mm, oom: change type of oom_score_adj to short
  mm: cleanup register_node()
  mm, mempolicy: remove duplicate code
  mm/vmscan.c: try_to_freeze() returns boolean
  mm: introduce putback_movable_pages()
  virtio_balloon: introduce migration primitives to balloon pages
  mm: introduce compaction and migration for ballooned pages
  mm: introduce a common interface for balloon pages mobility
  mm: redefine address_space.assoc_mapping
  mm: adjust address_space_operations.migratepage() return code
  arch/sparc/kernel/sys_sparc_64.c: s/COLOUR/COLOR/
  ...

5 files changed, 61 insertions, 231 deletions

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 5939f44fe0c..9c999c1674f 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -354,12 +354,10 @@ static inline int mmap_is_ia32(void)
 	return 0;
 }
 
-/* The first two values are special, do not change. See align_addr() */
+/* Do not change the values. See get_align_mask() */
 enum align_flags {
 	ALIGN_VA_32	= BIT(0),
 	ALIGN_VA_64	= BIT(1),
-	ALIGN_VDSO	= BIT(2),
-	ALIGN_TOPDOWN	= BIT(3),
 };
 
 struct va_alignment {
@@ -368,5 +366,5 @@ struct va_alignment {
 } ____cacheline_aligned;
 
 extern struct va_alignment va_align;
-extern unsigned long align_addr(unsigned long, struct file *, enum align_flags);
+extern unsigned long align_vdso_addr(unsigned long);
 #endif /* _ASM_X86_ELF_H */
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 593e51d4643..513b05f15bb 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -3,6 +3,9 @@
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
+#define MAP_HUGE_2MB    (21 << MAP_HUGE_SHIFT)
+#define MAP_HUGE_1GB    (30 << MAP_HUGE_SHIFT)
+
 #include <asm-generic/mman.h>
 
 #endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index b4d3c3927dd..97ef74b88e0 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -21,37 +21,23 @@
 
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
- *
- * @flags denotes the allocation direction - bottomup or topdown -
- * or vDSO; see call sites below.
  */
-unsigned long align_addr(unsigned long addr, struct file *filp,
-			 enum align_flags flags)
+static unsigned long get_align_mask(void)
 {
-	unsigned long tmp_addr;
-
 	/* handle 32- and 64-bit case with a single conditional */
 	if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
-		return addr;
+		return 0;
 
 	if (!(current->flags & PF_RANDOMIZE))
-		return addr;
-
-	if (!((flags & ALIGN_VDSO) || filp))
-		return addr;
-
-	tmp_addr = addr;
-
-	/*
-	 * We need an address which is <= than the original
-	 * one only when in topdown direction.
-	 */
-	if (!(flags & ALIGN_TOPDOWN))
-		tmp_addr += va_align.mask;
+		return 0;
 
-	tmp_addr &= ~va_align.mask;
+	return va_align.mask;
+}
 
-	return tmp_addr;
+unsigned long align_vdso_addr(unsigned long addr)
+{
+	unsigned long align_mask = get_align_mask();
+	return (addr + align_mask) & ~align_mask;
 }
 
 static int __init control_va_addr_alignment(char *str)
@@ -126,7 +112,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	struct vm_unmapped_area_info info;
 	unsigned long begin, end;
 
 	if (flags & MAP_FIXED)
@@ -144,50 +130,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
-	if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
-	    && len <= mm->cached_hole_size) {
-		mm->cached_hole_size = 0;
-		mm->free_area_cache = begin;
-	}
-	addr = mm->free_area_cache;
-	if (addr < begin)
-		addr = begin;
-	start_addr = addr;
-
-full_search:
-
-	addr = align_addr(addr, filp, 0);
-
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
-		/* At this point:  (!vma || addr < vma->vm_end). */
-		if (end - len < addr) {
-			/*
-			 * Start a new search - just in case we missed
-			 * some holes.
-			 */
-			if (start_addr != begin) {
-				start_addr = addr = begin;
-				mm->cached_hole_size = 0;
-				goto full_search;
-			}
-			return -ENOMEM;
-		}
-		if (!vma || addr + len <= vma->vm_start) {
-			/*
-			 * Remember the place where we stopped the search:
-			 */
-			mm->free_area_cache = addr + len;
-			return addr;
-		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-			mm->cached_hole_size = vma->vm_start - addr;
 
-		addr = vma->vm_end;
-		addr = align_addr(addr, filp, 0);
-	}
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = begin;
+	info.high_limit = end;
+	info.align_mask = filp ? get_align_mask() : 0;
+	info.align_offset = pgoff << PAGE_SHIFT;
+	return vm_unmapped_area(&info);
 }
 
-
 unsigned long
 arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			  const unsigned long len, const unsigned long pgoff,
@@ -195,7 +147,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0, start_addr;
+	unsigned long addr = addr0;
+	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
@@ -217,51 +170,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			return addr;
 	}
 
-	/* check if free_area_cache is useful for us */
-	if (len <= mm->cached_hole_size) {
-		mm->cached_hole_size = 0;
-		mm->free_area_cache = mm->mmap_base;
-	}
-
-try_again:
-	/* either no address requested or can't fit in requested address hole */
-	start_addr = addr = mm->free_area_cache;
-
-	if (addr < len)
-		goto fail;
-
-	addr -= len;
-	do {
-		addr = align_addr(addr, filp, ALIGN_TOPDOWN);
-
-		/*
-		 * Lookup failure means no vma is above this address,
-		 * else if new region fits below vma->vm_start,
-		 * return with success:
-		 */
-		vma = find_vma(mm, addr);
-		if (!vma || addr+len <= vma->vm_start)
-			/* remember the address as a hint for next time */
-			return mm->free_area_cache = addr;
-
-		/* remember the largest hole we saw so far */
-		if (addr + mm->cached_hole_size < vma->vm_start)
-			mm->cached_hole_size = vma->vm_start - addr;
-
-		/* try just below the current vma->vm_start */
-		addr = vma->vm_start-len;
-	} while (len < vma->vm_start);
-
-fail:
-	/*
-	 * if hint left us with no space for the requested
-	 * mapping then try again:
-	 */
-	if (start_addr != mm->mmap_base) {
-		mm->free_area_cache = mm->mmap_base;
-		mm->cached_hole_size = 0;
-		goto try_again;
-	}
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = PAGE_SIZE;
+	info.high_limit = mm->mmap_base;
+	info.align_mask = filp ? get_align_mask() : 0;
+	info.align_offset = pgoff << PAGE_SHIFT;
+	addr = vm_unmapped_area(&info);
+	if (!(addr & ~PAGE_MASK))
+		return addr;
+	VM_BUG_ON(addr != -ENOMEM);
 
 bottomup:
 	/*
@@ -270,14 +188,5 @@ bottomup:
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	mm->cached_hole_size = ~0UL;
-	mm->free_area_cache = TASK_UNMAPPED_BASE;
-	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
-	/*
-	 * Restore the topdown base:
-	 */
-	mm->free_area_cache = mm->mmap_base;
-	mm->cached_hole_size = ~0UL;
-
-	return addr;
+	return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
 }
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 937bff5cdaa..ae1aa71d011 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -274,42 +274,15 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long pgoff, unsigned long flags)
 {
 	struct hstate *h = hstate_file(file);
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long start_addr;
-
-	if (len > mm->cached_hole_size) {
-	        start_addr = mm->free_area_cache;
-	} else {
-	        start_addr = TASK_UNMAPPED_BASE;
-	        mm->cached_hole_size = 0;
-	}
-
-full_search:
-	addr = ALIGN(start_addr, huge_page_size(h));
-
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
-		/* At this point:  (!vma || addr < vma->vm_end). */
-		if (TASK_SIZE - len < addr) {
-			/*
-			 * Start a new search - just in case we missed
-			 * some holes.
-			 */
-			if (start_addr != TASK_UNMAPPED_BASE) {
-				start_addr = TASK_UNMAPPED_BASE;
-				mm->cached_hole_size = 0;
-				goto full_search;
-			}
-			return -ENOMEM;
-		}
-		if (!vma || addr + len <= vma->vm_start) {
-			mm->free_area_cache = addr + len;
-			return addr;
-		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
-		addr = ALIGN(vma->vm_end, huge_page_size(h));
-	}
+	struct vm_unmapped_area_info info;
+
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = TASK_UNMAPPED_BASE;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	return vm_unmapped_area(&info);
 }
 
 static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
@@ -317,83 +290,30 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		unsigned long pgoff, unsigned long flags)
 {
 	struct hstate *h = hstate_file(file);
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long base = mm->mmap_base;
-	unsigned long addr = addr0;
-	unsigned long largest_hole = mm->cached_hole_size;
-	unsigned long start_addr;
-
-	/* don't allow allocations above current base */
-	if (mm->free_area_cache > base)
-		mm->free_area_cache = base;
-
-	if (len <= largest_hole) {
-	        largest_hole = 0;
-		mm->free_area_cache  = base;
-	}
-try_again:
-	start_addr = mm->free_area_cache;
-
-	/* make sure it can fit in the remaining address space */
-	if (mm->free_area_cache < len)
-		goto fail;
-
-	/* either no address requested or can't fit in requested address hole */
-	addr = (mm->free_area_cache - len) & huge_page_mask(h);
-	do {
-		/*
-		 * Lookup failure means no vma is above this address,
-		 * i.e. return with success:
-		 */
-		vma = find_vma(mm, addr);
-		if (!vma)
-			return addr;
+	struct vm_unmapped_area_info info;
+	unsigned long addr;
 
-		if (addr + len <= vma->vm_start) {
-			/* remember the address as a hint for next time */
-		        mm->cached_hole_size = largest_hole;
-		        return (mm->free_area_cache = addr);
-		} else if (mm->free_area_cache == vma->vm_end) {
-			/* pull free_area_cache down to the first hole */
-			mm->free_area_cache = vma->vm_start;
-			mm->cached_hole_size = largest_hole;
-		}
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = PAGE_SIZE;
+	info.high_limit = current->mm->mmap_base;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	addr = vm_unmapped_area(&info);
 
-		/* remember the largest hole we saw so far */
-		if (addr + largest_hole < vma->vm_start)
-		        largest_hole = vma->vm_start - addr;
-
-		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start - len) & huge_page_mask(h);
-	} while (len <= vma->vm_start);
-
-fail:
-	/*
-	 * if hint left us with no space for the requested
-	 * mapping then try again:
-	 */
-	if (start_addr != base) {
-		mm->free_area_cache = base;
-		largest_hole = 0;
-		goto try_again;
-	}
 	/*
 	 * A failed mmap() very likely causes application failure,
 	 * so fall back to the bottom-up function here. This scenario
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	mm->free_area_cache = TASK_UNMAPPED_BASE;
-	mm->cached_hole_size = ~0UL;
-	addr = hugetlb_get_unmapped_area_bottomup(file, addr0,
-			len, pgoff, flags);
-
-	/*
-	 * Restore the topdown base:
-	 */
-	mm->free_area_cache = base;
-	mm->cached_hole_size = ~0UL;
+	if (addr & ~PAGE_MASK) {
+		VM_BUG_ON(addr != -ENOMEM);
+		info.flags = 0;
+		info.low_limit = TASK_UNMAPPED_BASE;
+		info.high_limit = TASK_SIZE;
+		addr = vm_unmapped_area(&info);
+	}
 
 	return addr;
 }
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 00aaf047b39..431e8754441 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -141,7 +141,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 	 * unaligned here as a result of stack start randomization.
 	 */
 	addr = PAGE_ALIGN(addr);
-	addr = align_addr(addr, NULL, ALIGN_VDSO);
+	addr = align_vdso_addr(addr);
 
 	return addr;
 }