Merge branch 'akpm' (patches from Andrew Morton)

Merge a bunch of fixes from Andrew Morton.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  fs/proc/task_mmu.c: fix buffer overflow in add_page_map()
  arch: *: Kconfig: add "kernel/Kconfig.freezer" to "arch/*/Kconfig"
  ocfs2: fix null pointer dereference in ocfs2_dir_foreach_blk_id()
  x86 get_unmapped_area(): use proper mmap base for bottom-up direction
  ocfs2: fix NULL pointer dereference in ocfs2_duplicate_clusters_by_page
  ocfs2: Revert 40bd62e to avoid regression in extended allocation
  drivers/rtc/rtc-stmp3xxx.c: provide timeout for potentially endless loop polling a HW bit
  hugetlb: fix lockdep splat caused by pmd sharing
  aoe: adjust ref of head for compound page tails
  microblaze: fix clone syscall
  mm: save soft-dirty bits on file pages
  mm: save soft-dirty bits on swapped pages
  memcg: don't initialize kmem-cache destroying work for root caches

9 files changed, 49 insertions, 67 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a3f868a..3442397 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -463,6 +463,14 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 	return inode;
 }
 
+/*
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * be taken from reclaim -- unlike regular filesystems. This needs an
+ * annotation because huge_pmd_share() does an allocation under
+ * i_mmap_mutex.
+ */
+struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					struct inode *dir,
 					umode_t mode, dev_t dev)
@@ -474,6 +482,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
+		lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
+				&hugetlbfs_i_mmap_mutex_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 79736a2..2abf97b 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1757,7 +1757,7 @@ try_again:
 		goto out;
 	} else if (ret == 1) {
 		clusters_need = wc->w_clen;
-		ret = ocfs2_refcount_cow(inode, filp, di_bh,
+		ret = ocfs2_refcount_cow(inode, di_bh,
 					 wc->w_cpos, wc->w_clen, UINT_MAX);
 		if (ret) {
 			mlog_errno(ret);
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index eb760d8..30544ce 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2153,11 +2153,9 @@ int ocfs2_empty_dir(struct inode *inode)
 {
 	int ret;
 	struct ocfs2_empty_dir_priv priv = {
-		.ctx.actor = ocfs2_empty_dir_filldir
+		.ctx.actor = ocfs2_empty_dir_filldir,
 	};
 
-	memset(&priv, 0, sizeof(priv));
-
 	if (ocfs2_dir_indexed(inode)) {
 		ret = ocfs2_empty_dir_dx(inode, &priv);
 		if (ret)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 41000f2..3261d71 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -370,7 +370,7 @@ static int ocfs2_cow_file_pos(struct inode *inode,
 	if (!(ext_flags & OCFS2_EXT_REFCOUNTED))
 		goto out;
 
-	return ocfs2_refcount_cow(inode, NULL, fe_bh, cpos, 1, cpos+1);
+	return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1);
 
 out:
 	return status;
@@ -899,7 +899,7 @@ static int ocfs2_zero_extend_get_range(struct inode *inode,
 		zero_clusters = last_cpos - zero_cpos;
 
 	if (needs_cow) {
-		rc = ocfs2_refcount_cow(inode, NULL, di_bh, zero_cpos,
+		rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos,
 					zero_clusters, UINT_MAX);
 		if (rc) {
 			mlog_errno(rc);
@@ -2078,7 +2078,7 @@ static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
 
 	*meta_level = 1;
 
-	ret = ocfs2_refcount_cow(inode, file, di_bh, cpos, clusters, UINT_MAX);
+	ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
 	if (ret)
 		mlog_errno(ret);
 out:
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 96f9ac2..0a99273 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -537,7 +537,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb,
 	extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth);
 
 	return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks +
-	       ocfs2_quota_trans_credits(sb) + bits_wanted;
+	       ocfs2_quota_trans_credits(sb);
 }
 
 static inline int ocfs2_calc_symlink_credits(struct super_block *sb)
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index f1fc172..452068b 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -69,7 +69,7 @@ static int __ocfs2_move_extent(handle_t *handle,
 	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
 	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
 
-	ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
+	ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos,
 					       p_cpos, new_p_cpos, len);
 	if (ret) {
 		mlog_errno(ret);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 9f6b96a..a70d604 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -49,7 +49,6 @@
 
 struct ocfs2_cow_context {
 	struct inode *inode;
-	struct file *file;
 	u32 cow_start;
 	u32 cow_len;
 	struct ocfs2_extent_tree data_et;
@@ -66,7 +65,7 @@ struct ocfs2_cow_context {
 			    u32 *num_clusters,
 			    unsigned int *extent_flags);
 	int (*cow_duplicate_clusters)(handle_t *handle,
-				      struct file *file,
+				      struct inode *inode,
 				      u32 cpos, u32 old_cluster,
 				      u32 new_cluster, u32 new_len);
 };
@@ -2922,14 +2921,12 @@ static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh)
 }
 
 int ocfs2_duplicate_clusters_by_page(handle_t *handle,
-				     struct file *file,
+				     struct inode *inode,
 				     u32 cpos, u32 old_cluster,
 				     u32 new_cluster, u32 new_len)
 {
 	int ret = 0, partial;
-	struct inode *inode = file_inode(file);
-	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
-	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+	struct super_block *sb = inode->i_sb;
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
@@ -2978,13 +2975,6 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
 			BUG_ON(PageDirty(page));
 
-		if (PageReadahead(page)) {
-			page_cache_async_readahead(mapping,
-						   &file->f_ra, file,
-						   page, page_index,
-						   readahead_pages);
-		}
-
 		if (!PageUptodate(page)) {
 			ret = block_read_full_page(page, ocfs2_get_block);
 			if (ret) {
@@ -3004,7 +2994,8 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 			}
 		}
 
-		ocfs2_map_and_dirty_page(inode, handle, from, to,
+		ocfs2_map_and_dirty_page(inode,
+					 handle, from, to,
 					 page, 0, &new_block);
 		mark_page_accessed(page);
 unlock:
@@ -3020,12 +3011,11 @@ unlock:
 }
 
 int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
-				    struct file *file,
+				    struct inode *inode,
 				    u32 cpos, u32 old_cluster,
 				    u32 new_cluster, u32 new_len)
 {
 	int ret = 0;
-	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
 	struct ocfs2_caching_info *ci = INODE_CACHE(inode);
 	int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
@@ -3150,7 +3140,7 @@ static int ocfs2_replace_clusters(handle_t *handle,
 
 	/*If the old clusters is unwritten, no need to duplicate. */
 	if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-		ret = context->cow_duplicate_clusters(handle, context->file,
+		ret = context->cow_duplicate_clusters(handle, context->inode,
 						      cpos, old, new, len);
 		if (ret) {
 			mlog_errno(ret);
@@ -3428,35 +3418,12 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
 	return ret;
 }
 
-static void ocfs2_readahead_for_cow(struct inode *inode,
-				    struct file *file,
-				    u32 start, u32 len)
-{
-	struct address_space *mapping;
-	pgoff_t index;
-	unsigned long num_pages;
-	int cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
-
-	if (!file)
-		return;
-
-	mapping = file->f_mapping;
-	num_pages = (len << cs_bits) >> PAGE_CACHE_SHIFT;
-	if (!num_pages)
-		num_pages = 1;
-
-	index = ((loff_t)start << cs_bits) >> PAGE_CACHE_SHIFT;
-	page_cache_sync_readahead(mapping, &file->f_ra, file,
-				  index, num_pages);
-}
-
 /*
  * Starting at cpos, try to CoW write_len clusters.  Don't CoW
  * past max_cpos.  This will stop when it runs into a hole or an
  * unrefcounted extent.
  */
 static int ocfs2_refcount_cow_hunk(struct inode *inode,
-				   struct file *file,
 				   struct buffer_head *di_bh,
 				   u32 cpos, u32 write_len, u32 max_cpos)
 {
@@ -3485,8 +3452,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
 
 	BUG_ON(cow_len == 0);
 
-	ocfs2_readahead_for_cow(inode, file, cow_start, cow_len);
-
 	context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS);
 	if (!context) {
 		ret = -ENOMEM;
@@ -3508,7 +3473,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
 	context->ref_root_bh = ref_root_bh;
 	context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page;
 	context->get_clusters = ocfs2_di_get_clusters;
-	context->file = file;
 
 	ocfs2_init_dinode_extent_tree(&context->data_et,
 				      INODE_CACHE(inode), di_bh);
@@ -3537,7 +3501,6 @@ out:
  * clusters between cpos and cpos+write_len are safe to modify.
  */
 int ocfs2_refcount_cow(struct inode *inode,
-		       struct file *file,
 		       struct buffer_head *di_bh,
 		       u32 cpos, u32 write_len, u32 max_cpos)
 {
@@ -3557,7 +3520,7 @@ int ocfs2_refcount_cow(struct inode *inode,
 			num_clusters = write_len;
 
 		if (ext_flags & OCFS2_EXT_REFCOUNTED) {
-			ret = ocfs2_refcount_cow_hunk(inode, file, di_bh, cpos,
+			ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos,
 						      num_clusters, max_cpos);
 			if (ret) {
 				mlog_errno(ret);
diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h
index 7754608..6422bbc 100644
--- a/fs/ocfs2/refcounttree.h
+++ b/fs/ocfs2/refcounttree.h
@@ -53,7 +53,7 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode,
 					  int *credits,
 					  int *ref_blocks);
 int ocfs2_refcount_cow(struct inode *inode,
-		       struct file *filep, struct buffer_head *di_bh,
+		       struct buffer_head *di_bh,
 		       u32 cpos, u32 write_len, u32 max_cpos);
 
 typedef int (ocfs2_post_refcount_func)(struct inode *inode,
@@ -85,11 +85,11 @@ int ocfs2_refcount_cow_xattr(struct inode *inode,
 			     u32 cpos, u32 write_len,
 			     struct ocfs2_post_refcount *post);
 int ocfs2_duplicate_clusters_by_page(handle_t *handle,
-				     struct file *file,
+				     struct inode *inode,
 				     u32 cpos, u32 old_cluster,
 				     u32 new_cluster, u32 new_len);
 int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
-				    struct file *file,
+				    struct inode *inode,
 				    u32 cpos, u32 old_cluster,
 				    u32 new_cluster, u32 new_len);
 int ocfs2_cow_sync_writeback(struct super_block *sb,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dbf61f6..107d026 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -730,8 +730,16 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	 * of how soft-dirty works.
 	 */
 	pte_t ptent = *pte;
-	ptent = pte_wrprotect(ptent);
-	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+	if (pte_present(ptent)) {
+		ptent = pte_wrprotect(ptent);
+		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+	} else if (is_swap_pte(ptent)) {
+		ptent = pte_swp_clear_soft_dirty(ptent);
+	} else if (pte_file(ptent)) {
+		ptent = pte_file_clear_soft_dirty(ptent);
+	}
+
 	set_pte_at(vma->vm_mm, addr, pte, ptent);
 #endif
 }
@@ -752,14 +760,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
-		if (!pte_present(ptent))
-			continue;
 
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty(vma, addr, pte);
 			continue;
 		}
 
+		if (!pte_present(ptent))
+			continue;
+
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
@@ -859,7 +868,7 @@ typedef struct {
 } pagemap_entry_t;
 
 struct pagemapread {
-	int pos, len;
+	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
 	pagemap_entry_t *buffer;
 	bool v2;
 };
@@ -867,7 +876,7 @@ struct pagemapread {
 #define PAGEMAP_WALK_SIZE	(PMD_SIZE)
 #define PAGEMAP_WALK_MASK	(PMD_MASK)
 
-#define PM_ENTRY_BYTES      sizeof(u64)
+#define PM_ENTRY_BYTES      sizeof(pagemap_entry_t)
 #define PM_STATUS_BITS      3
 #define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
 #define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
@@ -930,8 +939,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 		flags = PM_PRESENT;
 		page = vm_normal_page(vma, addr, pte);
 	} else if (is_swap_pte(pte)) {
-		swp_entry_t entry = pte_to_swp_entry(pte);
-
+		swp_entry_t entry;
+		if (pte_swp_soft_dirty(pte))
+			flags2 |= __PM_SOFT_DIRTY;
+		entry = pte_to_swp_entry(pte);
 		frame = swp_type(entry) |
 			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
 		flags = PM_SWAP;
@@ -1116,8 +1127,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		goto out_task;
 
 	pm.v2 = soft_dirty_cleared;
-	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
-	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+	pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+	pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
 	ret = -ENOMEM;
 	if (!pm.buffer)
 		goto out_task;