Merge branch 'akpm' (incoming fixes from Andrew)

Merge misc fixes from Andrew Morton:
 "The audit fixes have been floating around for a while - Al and Eric
  aren't responding to either myself or Kees so I asked Kees to
  re-review them and here they are."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (22 commits)
  lib/rbtree.c: avoid the use of non-static __always_inline
  MAINTAINERS: Omar had moved
  mm: compaction: partially revert capture of suitable high-order page
  linux/audit.h: move ptrace.h include to kernel header
  kernel/audit.c: avoid negative sleep durations
  audit: catch possible NULL audit buffers
  audit: create explicit AUDIT_SECCOMP event type
  MAINTAINERS: fix a status pattern
  MAINTAINERS: fix arch/arm/plat-omap/include/plat/omap_hwmod.h
  mm: thp: acquire the anon_vma rwsem for write during split
  mm: mmap: annotate vm_lock_anon_vma locking properly for lockdep
  lockdep, rwsem: provide down_write_nest_lock()
  arch/mn10300/Kconfig: select CONFIG_GENERIC_ATOMIC64
  mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment
  mm: use aligned zone start for pfn_to_bitidx calculation
  fs/exec.c: work around icc miscompilation
  mm: compaction: fix echo 1 > compact_memory return error issue
  mm: memblock: fix wrong memmove size in memblock_merge_regions()
  drivers/video/ssd1307fb.c: fix bit order bug in the byte translation function
  mm: migrate: check page_count of THP before migrating
  ...

7 files changed, 50 insertions, 16 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 1324cd7..b93376c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -185,10 +185,23 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 	while (start < end) {
 		unsigned long *map, idx, vec;
+		unsigned shift;
 
 		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
+		shift = idx & (BITS_PER_LONG - 1);
+		/*
+		 * vec holds at most BITS_PER_LONG map bits,
+		 * bit 0 corresponds to start.
+		 */
 		vec = ~map[idx / BITS_PER_LONG];
+
+		if (shift) {
+			vec >>= shift;
+			if (end - start >= BITS_PER_LONG)
+				vec |= ~map[idx / BITS_PER_LONG + 1] <<
+					(BITS_PER_LONG - shift);
+		}
 		/*
 		 * If we have a properly aligned and fully unreserved
 		 * BITS_PER_LONG block of pages in front of us, free
@@ -201,19 +214,18 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 			count += BITS_PER_LONG;
 			start += BITS_PER_LONG;
 		} else {
-			unsigned long off = 0;
+			unsigned long cur = start;
 
-			vec >>= start & (BITS_PER_LONG - 1);
-			while (vec) {
+			start = ALIGN(start + 1, BITS_PER_LONG);
+			while (vec && cur != start) {
 				if (vec & 1) {
-					page = pfn_to_page(start + off);
+					page = pfn_to_page(cur);
 					__free_pages_bootmem(page, 0);
 					count++;
 				}
 				vec >>= 1;
-				off++;
+				++cur;
 			}
-			start = ALIGN(start + 1, BITS_PER_LONG);
 		}
 	}
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 2c57043..c62bd06 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1144,7 +1144,7 @@ static int compact_node(int nid)
 }
 
 /* Compact all nodes in the system */
-static int compact_nodes(void)
+static void compact_nodes(void)
 {
 	int nid;
 
@@ -1153,8 +1153,6 @@ static int compact_nodes(void)
 
 	for_each_online_node(nid)
 		compact_node(nid);
-
-	return COMPACT_COMPLETE;
 }
 
 /* The written value is actually unused, all memory is compacted */
@@ -1165,7 +1163,7 @@ int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
-		return compact_nodes();
+		compact_nodes();
 
 	return 0;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9e894ed..6001ee6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1819,9 +1819,19 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(is_huge_zero_pfn(page_to_pfn(page)));
 	BUG_ON(!PageAnon(page));
-	anon_vma = page_lock_anon_vma_read(page);
+
+	/*
+	 * The caller does not necessarily hold an mmap_sem that would prevent
+	 * the anon_vma disappearing so we first we take a reference to it
+	 * and then lock the anon_vma for write. This is similar to
+	 * page_lock_anon_vma_read except the write lock is taken to serialise
+	 * against parallel split or collapse operations.
+	 */
+	anon_vma = page_get_anon_vma(page);
 	if (!anon_vma)
 		goto out;
+	anon_vma_lock_write(anon_vma);
+
 	ret = 0;
 	if (!PageCompound(page))
 		goto out_unlock;
@@ -1832,7 +1842,8 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	page_unlock_anon_vma_read(anon_vma);
+	anon_vma_unlock(anon_vma);
+	put_anon_vma(anon_vma);
 out:
 	return ret;
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index 6259055..88adc8a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -314,7 +314,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
 		}
 
 		this->size += next->size;
-		memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next));
+		/* move forward from next + 1, index of which is i + 2 */
+		memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
 		type->cnt--;
 	}
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 3b676b0..c387786 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1679,9 +1679,21 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	page_xchg_last_nid(new_page, page_last_nid(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
-	if (!isolated) {
+
+	/*
+	 * Failing to isolate or a GUP pin prevents migration. The expected
+	 * page count is 2. 1 for anonymous pages without a mapping and 1
+	 * for the callers pin. If the page was isolated, the page will
+	 * need to be put back on the LRU.
+	 */
+	if (!isolated || page_count(page) != 2) {
 		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 		put_page(new_page);
+		if (isolated) {
+			putback_lru_page(page);
+			isolated = 0;
+			goto out;
+		}
 		goto out_keep_locked;
 	}
 
diff --git a/mm/mmap.c b/mm/mmap.c
index f54b235..35730ee 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2886,7 +2886,7 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		down_write(&anon_vma->root->rwsem);
+		down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
 		 * anon_vma->root->rwsem. If some other vma in this mm shares
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ece7b8e..df2022f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5585,7 +5585,7 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
 	pfn &= (PAGES_PER_SECTION-1);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #else
-	pfn = pfn - zone->zone_start_pfn;
+	pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #endif /* CONFIG_SPARSEMEM */
 }