Merge branch 'akpm' (second patch-bomb from Andrew)

Merge second patchbomb from Andrew Morton:
 - the rest of MM
 - misc fs fixes
 - add execveat() syscall
 - new ratelimit feature for fault-injection
 - decompressor updates
 - ipc/ updates
 - fallocate feature creep
 - fsnotify cleanups
 - a few other misc things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (99 commits)
  cgroups: Documentation: fix trivial typos and wrong paragraph numberings
  parisc: percpu: update comments referring to __get_cpu_var
  percpu: update local_ops.txt to reflect this_cpu operations
  percpu: remove __get_cpu_var and __raw_get_cpu_var macros
  fsnotify: remove destroy_list from fsnotify_mark
  fsnotify: unify inode and mount marks handling
  fallocate: create FAN_MODIFY and IN_MODIFY events
  mm/cma: make kmemleak ignore CMA regions
  slub: fix cpuset check in get_any_partial
  slab: fix cpuset check in fallback_alloc
  shmdt: use i_size_read() instead of ->i_size
  ipc/shm.c: fix overly aggressive shmdt() when calls span multiple segments
  ipc/msg: increase MSGMNI, remove scaling
  ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM
  ipc/sem.c: change memory barrier in sem_lock() to smp_rmb()
  lib/decompress.c: consistency of compress formats for kernel image
  decompress_bunzip2: off by one in get_next_block()
  usr/Kconfig: make initrd compression algorithm selection not expert
  fault-inject: add ratelimit option
  ratelimit: add initialization macro
  ...

1 files changed, 19 insertions, 31 deletions

diff --git a/mm/nommu.c b/mm/nommu.c
index bd1808e194a7..b51eadf6d952 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -722,11 +722,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
 
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		flush_dcache_mmap_lock(mapping);
 		vma_interval_tree_insert(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 	}
 
 	/* add the VMA to the tree */
@@ -795,11 +795,11 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
 
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		flush_dcache_mmap_lock(mapping);
 		vma_interval_tree_remove(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 	}
 
 	/* remove from the MM's tree and list */
@@ -1149,8 +1149,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 			   unsigned long len,
 			   unsigned long capabilities)
 {
-	struct page *pages;
-	unsigned long total, point, n;
+	unsigned long total, point;
 	void *base;
 	int ret, order;
 
@@ -1182,33 +1181,23 @@ static int do_mmap_private(struct vm_area_struct *vma,
 	order = get_order(len);
 	kdebug("alloc order %d for %lx", order, len);
 
-	pages = alloc_pages(GFP_KERNEL, order);
-	if (!pages)
-		goto enomem;
-
 	total = 1 << order;
-	atomic_long_add(total, &mmap_pages_allocated);
-
 	point = len >> PAGE_SHIFT;
 
-	/* we allocated a power-of-2 sized page set, so we may want to trim off
-	 * the excess */
+	/* we don't want to allocate a power-of-2 sized page set */
 	if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) {
-		while (total > point) {
-			order = ilog2(total - point);
-			n = 1 << order;
-			kdebug("shave %lu/%lu @%lu", n, total - point, total);
-			atomic_long_sub(n, &mmap_pages_allocated);
-			total -= n;
-			set_page_refcounted(pages + total);
-			__free_pages(pages + total, order);
-		}
+		total = point;
+		kdebug("try to alloc exact %lu pages", total);
+		base = alloc_pages_exact(len, GFP_KERNEL);
+	} else {
+		base = (void *)__get_free_pages(GFP_KERNEL, order);
 	}
 
-	for (point = 1; point < total; point++)
-		set_page_refcounted(&pages[point]);
+	if (!base)
+		goto enomem;
+
+	atomic_long_add(total, &mmap_pages_allocated);
 
-	base = page_address(pages);
 	region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY;
 	region->vm_start = (unsigned long) base;
 	region->vm_end   = region->vm_start + len;
@@ -2094,14 +2083,14 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 	high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	down_write(&nommu_region_sem);
-	mutex_lock(&inode->i_mapping->i_mmap_mutex);
+	i_mmap_lock_read(inode->i_mapping);
 
 	/* search for VMAs that fall within the dead zone */
 	vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) {
 		/* found one - only interested if it's shared out of the page
 		 * cache */
 		if (vma->vm_flags & VM_SHARED) {
-			mutex_unlock(&inode->i_mapping->i_mmap_mutex);
+			i_mmap_unlock_read(inode->i_mapping);
 			up_write(&nommu_region_sem);
 			return -ETXTBSY; /* not quite true, but near enough */
 		}
@@ -2113,8 +2102,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 	 * we don't check for any regions that start beyond the EOF as there
 	 * shouldn't be any
 	 */
-	vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap,
-				  0, ULONG_MAX) {
+	vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, 0, ULONG_MAX) {
 		if (!(vma->vm_flags & VM_SHARED))
 			continue;
 
@@ -2129,7 +2117,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 		}
 	}
 
-	mutex_unlock(&inode->i_mapping->i_mmap_mutex);
+	i_mmap_unlock_read(inode->i_mapping);
 	up_write(&nommu_region_sem);
 	return 0;
 }