1 files changed, 181 insertions, 133 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 2afcdbbdb685..440e2a7e6c1c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -360,6 +360,87 @@ static int shmem_free_swap(struct address_space *mapping,
 }
 
 /*
+ * Determine (in bytes) how many of the shmem object's pages mapped by the
+ * given offsets are swapped out.
+ *
+ * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU,
+ * as long as the inode doesn't go away and racy results are not a problem.
+ */
+unsigned long shmem_partial_swap_usage(struct address_space *mapping,
+						pgoff_t start, pgoff_t end)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	struct page *page;
+	unsigned long swapped = 0;
+
+	rcu_read_lock();
+
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		if (iter.index >= end)
+			break;
+
+		page = radix_tree_deref_slot(slot);
+
+		/*
+		 * This should only be possible to happen at index 0, so we
+		 * don't need to reset the counter, nor do we risk infinite
+		 * restarts.
+		 */
+		if (radix_tree_deref_retry(page))
+			goto restart;
+
+		if (radix_tree_exceptional_entry(page))
+			swapped++;
+
+		if (need_resched()) {
+			cond_resched_rcu();
+			start = iter.index + 1;
+			goto restart;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return swapped << PAGE_SHIFT;
+}
+
+/*
+ * Determine (in bytes) how many of the shmem object's pages mapped by the
+ * given vma is swapped out.
+ *
+ * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU,
+ * as long as the inode doesn't go away and racy results are not a problem.
+ */
+unsigned long shmem_swap_usage(struct vm_area_struct *vma)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long swapped;
+
+	/* Be careful as we don't hold info->lock */
+	swapped = READ_ONCE(info->swapped);
+
+	/*
+	 * The easier cases are when the shmem object has nothing in swap, or
+	 * the vma maps it whole. Then we can simply use the stats that we
+	 * already track.
+	 */
+	if (!swapped)
+		return 0;
+
+	if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size)
+		return swapped << PAGE_SHIFT;
+
+	/* Here comes the more involved part */
+	return shmem_partial_swap_usage(mapping,
+			linear_page_index(vma, vma->vm_start),
+			linear_page_index(vma, vma->vm_end));
+}
+
+/*
  * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
  */
 void shmem_unlock_mapping(struct address_space *mapping)
@@ -620,8 +701,7 @@ static void shmem_evict_inode(struct inode *inode)
 			list_del_init(&info->swaplist);
 			mutex_unlock(&shmem_swaplist_mutex);
 		}
-	} else
-		kfree(info->symlink);
+	}
 
 	simple_xattrs_free(&info->xattrs);
 	WARN_ON(inode->i_blocks);
@@ -729,7 +809,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg);
+	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg,
+			false);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -752,9 +833,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	if (error) {
 		if (error != -ENOMEM)
 			error = 0;
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, false);
 	} else
-		mem_cgroup_commit_charge(page, memcg, true);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -830,6 +911,9 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	if (!swap.val)
 		goto redirty;
 
+	if (mem_cgroup_try_charge_swap(page, swap))
+		goto free_swap;
+
 	/*
 	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
 	 * if it's not already there.  Do it now before the page is
@@ -858,6 +942,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
+free_swap:
 	swapcache_free(swap);
 redirty:
 	set_page_dirty(page);
@@ -1004,7 +1089,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	copy_highpage(newpage, oldpage);
 	flush_dcache_page(newpage);
 
-	__set_page_locked(newpage);
+	__SetPageLocked(newpage);
 	SetPageUptodate(newpage);
 	SetPageSwapBacked(newpage);
 	set_page_private(newpage, swap_index);
@@ -1137,7 +1222,8 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg,
+				false);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 						swp_to_radix_entry(swap));
@@ -1154,14 +1240,14 @@ repeat:
 			 * "repeat": reading a hole and writing should succeed.
 			 */
 			if (error) {
-				mem_cgroup_cancel_charge(page, memcg);
+				mem_cgroup_cancel_charge(page, memcg, false);
 				delete_from_swap_cache(page);
 			}
 		}
 		if (error)
 			goto failed;
 
-		mem_cgroup_commit_charge(page, memcg, true);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 
 		spin_lock(&info->lock);
 		info->swapped--;
@@ -1196,11 +1282,12 @@ repeat:
 		}
 
 		__SetPageSwapBacked(page);
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
+		error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg,
+				false);
 		if (error)
 			goto decused;
 		error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
@@ -1210,10 +1297,10 @@ repeat:
 			radix_tree_preload_end();
 		}
 		if (error) {
-			mem_cgroup_cancel_charge(page, memcg);
+			mem_cgroup_cancel_charge(page, memcg, false);
 			goto decused;
 		}
-		mem_cgroup_commit_charge(page, memcg, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_anon(page);
 
 		spin_lock(&info->lock);
@@ -1814,7 +1901,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	if (whence != SEEK_DATA && whence != SEEK_HOLE)
 		return generic_file_llseek_size(file, offset, whence,
 					MAX_LFS_FILESIZE, i_size_read(inode));
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	/* We're holding i_mutex so we can access i_size directly */
 
 	if (offset < 0)
@@ -1838,7 +1925,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 
 	if (offset >= 0)
 		offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return offset;
 }
 
@@ -2003,7 +2090,7 @@ int shmem_add_seals(struct file *file, unsigned int seals)
 	if (seals & ~(unsigned int)F_ALL_SEALS)
 		return -EINVAL;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if (info->seals & F_SEAL_SEAL) {
 		error = -EPERM;
@@ -2026,7 +2113,7 @@ int shmem_add_seals(struct file *file, unsigned int seals)
 	error = 0;
 
 unlock:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return error;
 }
 EXPORT_SYMBOL_GPL(shmem_add_seals);
@@ -2076,7 +2163,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		struct address_space *mapping = file->f_mapping;
@@ -2189,7 +2276,7 @@ undone:
 	inode->i_private = NULL;
 	spin_unlock(&inode->i_lock);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return error;
 }
 
@@ -2438,7 +2525,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	int len;
 	struct inode *inode;
 	struct page *page;
-	char *kaddr;
 	struct shmem_inode_info *info;
 
 	len = strlen(symname) + 1;
@@ -2462,14 +2548,14 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	info = SHMEM_I(inode);
 	inode->i_size = len-1;
 	if (len <= SHORT_SYMLINK_LEN) {
-		info->symlink = kmemdup(symname, len, GFP_KERNEL);
-		if (!info->symlink) {
+		inode->i_link = kmemdup(symname, len, GFP_KERNEL);
+		if (!inode->i_link) {
 			iput(inode);
 			return -ENOMEM;
 		}
 		inode->i_op = &shmem_short_symlink_operations;
-		inode->i_link = info->symlink;
 	} else {
+		inode_nohighmem(inode);
 		error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
 		if (error) {
 			iput(inode);
@@ -2477,9 +2563,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 		}
 		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_op = &shmem_symlink_inode_operations;
-		kaddr = kmap_atomic(page);
-		memcpy(kaddr, symname, len);
-		kunmap_atomic(kaddr);
+		memcpy(page_address(page), symname, len);
 		SetPageUptodate(page);
 		set_page_dirty(page);
 		unlock_page(page);
@@ -2492,23 +2576,34 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	return 0;
 }
 
-static const char *shmem_follow_link(struct dentry *dentry, void **cookie)
+static void shmem_put_link(void *arg)
 {
-	struct page *page = NULL;
-	int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL);
-	if (error)
-		return ERR_PTR(error);
-	unlock_page(page);
-	*cookie = page;
-	return kmap(page);
+	mark_page_accessed(arg);
+	put_page(arg);
 }
 
-static void shmem_put_link(struct inode *unused, void *cookie)
+static const char *shmem_get_link(struct dentry *dentry,
+				  struct inode *inode,
+				  struct delayed_call *done)
 {
-	struct page *page = cookie;
-	kunmap(page);
-	mark_page_accessed(page);
-	page_cache_release(page);
+	struct page *page = NULL;
+	int error;
+	if (!dentry) {
+		page = find_get_page(inode->i_mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		error = shmem_getpage(inode, 0, &page, SGP_READ, NULL);
+		if (error)
+			return ERR_PTR(error);
+		unlock_page(page);
+	}
+	set_delayed_call(done, shmem_put_link, page);
+	return page_address(page);
 }
 
 #ifdef CONFIG_TMPFS_XATTR
@@ -2555,122 +2650,74 @@ static int shmem_initxattrs(struct inode *inode,
 	return 0;
 }
 
-static const struct xattr_handler *shmem_xattr_handlers[] = {
-#ifdef CONFIG_TMPFS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
-	NULL
-};
-
-static int shmem_xattr_validate(const char *name)
-{
-	struct { const char *prefix; size_t len; } arr[] = {
-		{ XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN },
-		{ XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN }
-	};
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(arr); i++) {
-		size_t preflen = arr[i].len;
-		if (strncmp(name, arr[i].prefix, preflen) == 0) {
-			if (!name[preflen])
-				return -EINVAL;
-			return 0;
-		}
-	}
-	return -EOPNOTSUPP;
-}
-
-static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
-			      void *buffer, size_t size)
+static int shmem_xattr_handler_get(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
 {
 	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	int err;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_getxattr(dentry, name, buffer, size);
-
-	err = shmem_xattr_validate(name);
-	if (err)
-		return err;
 
+	name = xattr_full_name(handler, name);
 	return simple_xattr_get(&info->xattrs, name, buffer, size);
 }
 
-static int shmem_setxattr(struct dentry *dentry, const char *name,
-			  const void *value, size_t size, int flags)
+static int shmem_xattr_handler_set(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *value, size_t size, int flags)
 {
 	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	int err;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_setxattr(dentry, name, value, size, flags);
-
-	err = shmem_xattr_validate(name);
-	if (err)
-		return err;
 
+	name = xattr_full_name(handler, name);
 	return simple_xattr_set(&info->xattrs, name, value, size, flags);
 }
 
-static int shmem_removexattr(struct dentry *dentry, const char *name)
-{
-	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	int err;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_removexattr(dentry, name);
+static const struct xattr_handler shmem_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = shmem_xattr_handler_get,
+	.set = shmem_xattr_handler_set,
+};
 
-	err = shmem_xattr_validate(name);
-	if (err)
-		return err;
+static const struct xattr_handler shmem_trusted_xattr_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = shmem_xattr_handler_get,
+	.set = shmem_xattr_handler_set,
+};
 
-	return simple_xattr_remove(&info->xattrs, name);
-}
+static const struct xattr_handler *shmem_xattr_handlers[] = {
+#ifdef CONFIG_TMPFS_POSIX_ACL
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+#endif
+	&shmem_security_xattr_handler,
+	&shmem_trusted_xattr_handler,
+	NULL
+};
 
 static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
 	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
-	return simple_xattr_list(&info->xattrs, buffer, size);
+	return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size);
 }
 #endif /* CONFIG_TMPFS_XATTR */
 
 static const struct inode_operations shmem_short_symlink_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
+	.get_link	= simple_get_link,
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 };
 
 static const struct inode_operations shmem_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= shmem_follow_link,
-	.put_link	= shmem_put_link,
+	.get_link	= shmem_get_link,
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 };
 
@@ -3083,6 +3130,7 @@ static struct inode *shmem_alloc_inode(struct super_block *sb)
 static void shmem_destroy_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
+	kfree(inode->i_link);
 	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
 }
 
@@ -3103,7 +3151,7 @@ static int shmem_init_inodecache(void)
 {
 	shmem_inode_cachep = kmem_cache_create("shmem_inode_cache",
 				sizeof(struct shmem_inode_info),
-				0, SLAB_PANIC, shmem_init_inode);
+				0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode);
 	return 0;
 }
 
@@ -3142,10 +3190,10 @@ static const struct inode_operations shmem_inode_operations = {
 	.getattr	= shmem_getattr,
 	.setattr	= shmem_setattr,
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 	.set_acl	= simple_set_acl,
 #endif
 };
@@ -3164,10 +3212,10 @@ static const struct inode_operations shmem_dir_inode_operations = {
 	.tmpfile	= shmem_tmpfile,
 #endif
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	.setattr	= shmem_setattr,
@@ -3177,10 +3225,10 @@ static const struct inode_operations shmem_dir_inode_operations = {
 
 static const struct inode_operations shmem_special_inode_operations = {
 #ifdef CONFIG_TMPFS_XATTR
-	.setxattr	= shmem_setxattr,
-	.getxattr	= shmem_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= shmem_listxattr,
-	.removexattr	= shmem_removexattr,
+	.removexattr	= generic_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	.setattr	= shmem_setattr,