1 files changed, 327 insertions, 83 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index dfc7069102ee..fcedf5464eb7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -99,6 +99,13 @@ static struct vfsmount *shm_mnt;
 /* Pretend that each entry is of this size in directory's i_size */
 #define BOGO_DIRENT_SIZE 20
 
+struct shmem_xattr {
+	struct list_head list;	/* anchored by shmem_inode_info->xattr_list */
+	char *name;		/* xattr name */
+	size_t size;
+	char value[0];
+};
+
 /* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
 enum sgp_type {
 	SGP_READ,	/* don't exceed i_size, don't allocate page */
@@ -532,7 +539,7 @@ static void shmem_free_pages(struct list_head *next)
 	} while (next);
 }
 
-static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long idx;
@@ -555,6 +562,8 @@ static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 	spinlock_t *punch_lock;
 	unsigned long upper_limit;
 
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
 	idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	if (idx >= info->next_index)
@@ -731,16 +740,8 @@ done2:
 		 * lowered next_index.  Also, though shmem_getpage checks
 		 * i_size before adding to cache, no recheck after: so fix the
 		 * narrow window there too.
-		 *
-		 * Recalling truncate_inode_pages_range and unmap_mapping_range
-		 * every time for punch_hole (which never got a chance to clear
-		 * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
-		 * yet hardly ever necessary: try to optimize them out later.
 		 */
 		truncate_inode_pages_range(inode->i_mapping, start, end);
-		if (punch_hole)
-			unmap_mapping_range(inode->i_mapping, start,
-							end - start, 1);
 	}
 
 	spin_lock(&info->lock);
@@ -759,22 +760,23 @@ done2:
 		shmem_free_pages(pages_to_free.next);
 	}
 }
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
-static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
+static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
-	loff_t newsize = attr->ia_size;
 	int error;
 
 	error = inode_change_ok(inode, attr);
 	if (error)
 		return error;
 
-	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
-					&& newsize != inode->i_size) {
+	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
+		loff_t oldsize = inode->i_size;
+		loff_t newsize = attr->ia_size;
 		struct page *page = NULL;
 
-		if (newsize < inode->i_size) {
+		if (newsize < oldsize) {
 			/*
 			 * If truncating down to a partial page, then
 			 * if that page is already allocated, hold it
@@ -803,12 +805,19 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 				spin_unlock(&info->lock);
 			}
 		}
-
-		/* XXX(truncate): truncate_setsize should be called last */
-		truncate_setsize(inode, newsize);
+		if (newsize != oldsize) {
+			i_size_write(inode, newsize);
+			inode->i_ctime = inode->i_mtime = CURRENT_TIME;
+		}
+		if (newsize < oldsize) {
+			loff_t holebegin = round_up(newsize, PAGE_SIZE);
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+			shmem_truncate_range(inode, newsize, (loff_t)-1);
+			/* unmap again to remove racily COWed private pages */
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+		}
 		if (page)
 			page_cache_release(page);
-		shmem_truncate_range(inode, newsize, (loff_t)-1);
 	}
 
 	setattr_copy(inode, attr);
@@ -822,9 +831,9 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 static void shmem_evict_inode(struct inode *inode)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_xattr *xattr, *nxattr;
 
 	if (inode->i_mapping->a_ops == &shmem_aops) {
-		truncate_inode_pages(inode->i_mapping, 0);
 		shmem_unacct_size(info->flags, inode->i_size);
 		inode->i_size = 0;
 		shmem_truncate_range(inode, 0, (loff_t)-1);
@@ -834,6 +843,11 @@ static void shmem_evict_inode(struct inode *inode)
 			mutex_unlock(&shmem_swaplist_mutex);
 		}
 	}
+
+	list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) {
+		kfree(xattr->name);
+		kfree(xattr);
+	}
 	BUG_ON(inode->i_blocks);
 	shmem_free_inode(inode->i_sb);
 	end_writeback(inode);
@@ -916,11 +930,12 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s
 			if (size > ENTRIES_PER_PAGE)
 				size = ENTRIES_PER_PAGE;
 			offset = shmem_find_swp(entry, ptr, ptr+size);
+			shmem_swp_unmap(ptr);
 			if (offset >= 0) {
 				shmem_dir_unmap(dir);
+				ptr = shmem_swp_map(subdir);
 				goto found;
 			}
-			shmem_swp_unmap(ptr);
 		}
 	}
 lost1:
@@ -1100,8 +1115,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		delete_from_page_cache(page);
 		shmem_swp_set(info, entry, swap.val);
 		shmem_swp_unmap(entry);
-		spin_unlock(&info->lock);
 		swap_shmem_alloc(swap);
+		spin_unlock(&info->lock);
 		BUG_ON(page_mapped(page));
 		swap_writepage(page, wbc);
 		return 0;
@@ -1291,12 +1306,10 @@ repeat:
 		swappage = lookup_swap_cache(swap);
 		if (!swappage) {
 			shmem_swp_unmap(entry);
+			spin_unlock(&info->lock);
 			/* here we actually do the io */
-			if (type && !(*type & VM_FAULT_MAJOR)) {
-				__count_vm_event(PGMAJFAULT);
+			if (type)
 				*type |= VM_FAULT_MAJOR;
-			}
-			spin_unlock(&info->lock);
 			swappage = shmem_swapin(swap, gfp, info, idx);
 			if (!swappage) {
 				spin_lock(&info->lock);
@@ -1535,7 +1548,10 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
-
+	if (ret & VM_FAULT_MAJOR) {
+		count_vm_event(PGMAJFAULT);
+		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+	}
 	return ret | VM_FAULT_LOCKED;
 }
 
@@ -1614,6 +1630,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		spin_lock_init(&info->lock);
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
+		INIT_LIST_HEAD(&info->xattr_list);
 		cache_no_acl(inode);
 
 		switch (mode & S_IFMT) {
@@ -2013,9 +2030,9 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 
 	info = SHMEM_I(inode);
 	inode->i_size = len-1;
-	if (len <= (char *)inode - (char *)info) {
+	if (len <= SHMEM_SYMLINK_INLINE_LEN) {
 		/* do it inline */
-		memcpy(info, symname, len);
+		memcpy(info->inline_symlink, symname, len);
 		inode->i_op = &shmem_symlink_inline_operations;
 	} else {
 		error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
@@ -2041,7 +2058,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 
 static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd)
 {
-	nd_set_link(nd, (char *)SHMEM_I(dentry->d_inode));
+	nd_set_link(nd, SHMEM_I(dentry->d_inode)->inline_symlink);
 	return NULL;
 }
 
@@ -2065,63 +2082,253 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co
 	}
 }
 
-static const struct inode_operations shmem_symlink_inline_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= shmem_follow_link_inline,
-};
-
-static const struct inode_operations shmem_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= shmem_follow_link,
-	.put_link	= shmem_put_link,
-};
-
-#ifdef CONFIG_TMPFS_POSIX_ACL
+#ifdef CONFIG_TMPFS_XATTR
 /*
- * Superblocks without xattr inode operations will get security.* xattr
- * support from the VFS "for free". As soon as we have any other xattrs
+ * Superblocks without xattr inode operations may get some security.* xattr
+ * support from the LSM "for free". As soon as we have any other xattrs
  * like ACLs, we also need to implement the security.* handlers at
  * filesystem level, though.
  */
 
-static size_t shmem_xattr_security_list(struct dentry *dentry, char *list,
-					size_t list_len, const char *name,
-					size_t name_len, int handler_flags)
+static int shmem_xattr_get(struct dentry *dentry, const char *name,
+			   void *buffer, size_t size)
 {
-	return security_inode_listsecurity(dentry->d_inode, list, list_len);
-}
+	struct shmem_inode_info *info;
+	struct shmem_xattr *xattr;
+	int ret = -ENODATA;
 
-static int shmem_xattr_security_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int handler_flags)
-{
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-	return xattr_getsecurity(dentry->d_inode, name, buffer, size);
+	info = SHMEM_I(dentry->d_inode);
+
+	spin_lock(&info->lock);
+	list_for_each_entry(xattr, &info->xattr_list, list) {
+		if (strcmp(name, xattr->name))
+			continue;
+
+		ret = xattr->size;
+		if (buffer) {
+			if (size < xattr->size)
+				ret = -ERANGE;
+			else
+				memcpy(buffer, xattr->value, xattr->size);
+		}
+		break;
+	}
+	spin_unlock(&info->lock);
+	return ret;
 }
 
-static int shmem_xattr_security_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int handler_flags)
+static int shmem_xattr_set(struct dentry *dentry, const char *name,
+			   const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-	return security_inode_setsecurity(dentry->d_inode, name, value,
-					  size, flags);
+	struct inode *inode = dentry->d_inode;
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct shmem_xattr *xattr;
+	struct shmem_xattr *new_xattr = NULL;
+	size_t len;
+	int err = 0;
+
+	/* value == NULL means remove */
+	if (value) {
+		/* wrap around? */
+		len = sizeof(*new_xattr) + size;
+		if (len <= sizeof(*new_xattr))
+			return -ENOMEM;
+
+		new_xattr = kmalloc(len, GFP_KERNEL);
+		if (!new_xattr)
+			return -ENOMEM;
+
+		new_xattr->name = kstrdup(name, GFP_KERNEL);
+		if (!new_xattr->name) {
+			kfree(new_xattr);
+			return -ENOMEM;
+		}
+
+		new_xattr->size = size;
+		memcpy(new_xattr->value, value, size);
+	}
+
+	spin_lock(&info->lock);
+	list_for_each_entry(xattr, &info->xattr_list, list) {
+		if (!strcmp(name, xattr->name)) {
+			if (flags & XATTR_CREATE) {
+				xattr = new_xattr;
+				err = -EEXIST;
+			} else if (new_xattr) {
+				list_replace(&xattr->list, &new_xattr->list);
+			} else {
+				list_del(&xattr->list);
+			}
+			goto out;
+		}
+	}
+	if (flags & XATTR_REPLACE) {
+		xattr = new_xattr;
+		err = -ENODATA;
+	} else {
+		list_add(&new_xattr->list, &info->xattr_list);
+		xattr = NULL;
+	}
+out:
+	spin_unlock(&info->lock);
+	if (xattr)
+		kfree(xattr->name);
+	kfree(xattr);
+	return err;
 }
 
-static const struct xattr_handler shmem_xattr_security_handler = {
-	.prefix = XATTR_SECURITY_PREFIX,
-	.list   = shmem_xattr_security_list,
-	.get    = shmem_xattr_security_get,
-	.set    = shmem_xattr_security_set,
-};
 
 static const struct xattr_handler *shmem_xattr_handlers[] = {
+#ifdef CONFIG_TMPFS_POSIX_ACL
 	&generic_acl_access_handler,
 	&generic_acl_default_handler,
-	&shmem_xattr_security_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)
+{
+	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;
+
+	return shmem_xattr_get(dentry, name, buffer, size);
+}
+
+static int shmem_setxattr(struct dentry *dentry, const char *name,
+			  const void *value, size_t size, int flags)
+{
+	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;
+
+	if (size == 0)
+		value = "";  /* empty EA, do not remove */
+
+	return shmem_xattr_set(dentry, name, value, size, flags);
+
+}
+
+static int shmem_removexattr(struct dentry *dentry, const char *name)
+{
+	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);
+
+	err = shmem_xattr_validate(name);
+	if (err)
+		return err;
+
+	return shmem_xattr_set(dentry, name, NULL, 0, XATTR_REPLACE);
+}
+
+static bool xattr_is_trusted(const char *name)
+{
+	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
+}
+
+static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+	bool trusted = capable(CAP_SYS_ADMIN);
+	struct shmem_xattr *xattr;
+	struct shmem_inode_info *info;
+	size_t used = 0;
+
+	info = SHMEM_I(dentry->d_inode);
+
+	spin_lock(&info->lock);
+	list_for_each_entry(xattr, &info->xattr_list, list) {
+		size_t len;
+
+		/* skip "trusted." attributes for unprivileged callers */
+		if (!trusted && xattr_is_trusted(xattr->name))
+			continue;
+
+		len = strlen(xattr->name) + 1;
+		used += len;
+		if (buffer) {
+			if (size < used) {
+				used = -ERANGE;
+				break;
+			}
+			memcpy(buffer, xattr->name, len);
+			buffer += len;
+		}
+	}
+	spin_unlock(&info->lock);
+
+	return used;
+}
+#endif /* CONFIG_TMPFS_XATTR */
+
+static const struct inode_operations shmem_symlink_inline_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= shmem_follow_link_inline,
+#ifdef CONFIG_TMPFS_XATTR
+	.setxattr	= shmem_setxattr,
+	.getxattr	= shmem_getxattr,
+	.listxattr	= shmem_listxattr,
+	.removexattr	= shmem_removexattr,
+#endif
+};
+
+static const struct inode_operations shmem_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= shmem_follow_link,
+	.put_link	= shmem_put_link,
+#ifdef CONFIG_TMPFS_XATTR
+	.setxattr	= shmem_setxattr,
+	.getxattr	= shmem_getxattr,
+	.listxattr	= shmem_listxattr,
+	.removexattr	= shmem_removexattr,
 #endif
+};
 
 static struct dentry *shmem_get_parent(struct dentry *child)
 {
@@ -2401,8 +2608,10 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_magic = TMPFS_MAGIC;
 	sb->s_op = &shmem_ops;
 	sb->s_time_gran = 1;
-#ifdef CONFIG_TMPFS_POSIX_ACL
+#ifdef CONFIG_TMPFS_XATTR
 	sb->s_xattr = shmem_xattr_handlers;
+#endif
+#ifdef CONFIG_TMPFS_POSIX_ACL
 	sb->s_flags |= MS_POSIXACL;
 #endif
 
@@ -2498,13 +2707,15 @@ static const struct file_operations shmem_file_operations = {
 };
 
 static const struct inode_operations shmem_inode_operations = {
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.truncate_range	= shmem_truncate_range,
+#ifdef CONFIG_TMPFS_XATTR
+	.setxattr	= shmem_setxattr,
+	.getxattr	= shmem_getxattr,
+	.listxattr	= shmem_listxattr,
+	.removexattr	= shmem_removexattr,
+#endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
 	.check_acl	= generic_check_acl,
 #endif
 
@@ -2522,23 +2733,27 @@ static const struct inode_operations shmem_dir_inode_operations = {
 	.mknod		= shmem_mknod,
 	.rename		= shmem_rename,
 #endif
+#ifdef CONFIG_TMPFS_XATTR
+	.setxattr	= shmem_setxattr,
+	.getxattr	= shmem_getxattr,
+	.listxattr	= shmem_listxattr,
+	.removexattr	= shmem_removexattr,
+#endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
 
 static const struct inode_operations shmem_special_inode_operations = {
+#ifdef CONFIG_TMPFS_XATTR
+	.setxattr	= shmem_setxattr,
+	.getxattr	= shmem_getxattr,
+	.listxattr	= shmem_listxattr,
+	.removexattr	= shmem_removexattr,
+#endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2694,6 +2909,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	return 0;
 }
 
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+{
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+}
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
+
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 /**
  * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
@@ -2814,3 +3035,26 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
+
+/**
+ * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags.
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @gfp:	the page allocator flags to use if allocating
+ *
+ * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
+ * with any new page allocations done using the specified allocation flags.
+ * But read_cache_page_gfp() uses the ->readpage() method: which does not
+ * suit tmpfs, since it may have pages in swapcache, and needs to find those
+ * for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
+ *
+ * Provide a stub for those callers to start using now, then later
+ * flesh it out to call shmem_getpage() with additional gfp mask, when
+ * shmem_file_splice_read() is added and shmem_readpage() is removed.
+ */
+struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
+					 pgoff_t index, gfp_t gfp)
+{
+	return read_cache_page_gfp(mapping, index, gfp);
+}
+EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp);