1 files changed, 123 insertions, 23 deletions

diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index d0f7a5abd9a9..3d783d80f5da 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -17,12 +17,6 @@
 
 #include "kernfs-internal.h"
 
-static const struct address_space_operations kernfs_aops = {
-	.readpage	= simple_readpage,
-	.write_begin	= simple_write_begin,
-	.write_end	= simple_write_end,
-};
-
 static const struct inode_operations kernfs_iops = {
 	.permission	= kernfs_iop_permission,
 	.setattr	= kernfs_iop_setattr,
@@ -53,6 +47,8 @@ static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc)
 	kn->iattr->ia_ctime = kn->iattr->ia_atime;
 
 	simple_xattrs_init(&kn->iattr->xattrs);
+	atomic_set(&kn->iattr->nr_user_xattrs, 0);
+	atomic_set(&kn->iattr->user_xattr_size, 0);
 out_unlock:
 	ret = kn->iattr;
 	mutex_unlock(&iattr_mutex);
@@ -103,24 +99,28 @@ int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
 int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
 {
 	int ret;
+	struct kernfs_root *root = kernfs_root(kn);
 
-	mutex_lock(&kernfs_mutex);
+	down_write(&root->kernfs_rwsem);
 	ret = __kernfs_setattr(kn, iattr);
-	mutex_unlock(&kernfs_mutex);
+	up_write(&root->kernfs_rwsem);
 	return ret;
 }
 
-int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
+int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		       struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
 	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_root *root;
 	int error;
 
 	if (!kn)
 		return -EINVAL;
 
-	mutex_lock(&kernfs_mutex);
-	error = setattr_prepare(dentry, iattr);
+	root = kernfs_root(kn);
+	down_write(&root->kernfs_rwsem);
+	error = setattr_prepare(&init_user_ns, dentry, iattr);
 	if (error)
 		goto out;
 
@@ -129,10 +129,10 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
 		goto out;
 
 	/* this ignores size changes */
-	setattr_copy(inode, iattr);
+	setattr_copy(&init_user_ns, inode, iattr);
 
 out:
-	mutex_unlock(&kernfs_mutex);
+	up_write(&root->kernfs_rwsem);
 	return error;
 }
 
@@ -181,17 +181,21 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
 		set_nlink(inode, kn->dir.subdirs + 2);
 }
 
-int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+int kernfs_iop_getattr(struct user_namespace *mnt_userns,
+		       const struct path *path, struct kstat *stat,
 		       u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
 	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_root *root = kernfs_root(kn);
 
-	mutex_lock(&kernfs_mutex);
+	down_read(&root->kernfs_rwsem);
+	spin_lock(&inode->i_lock);
 	kernfs_refresh_inode(kn, inode);
-	mutex_unlock(&kernfs_mutex);
+	generic_fillattr(&init_user_ns, inode, stat);
+	spin_unlock(&inode->i_lock);
+	up_read(&root->kernfs_rwsem);
 
-	generic_fillattr(inode, stat);
 	return 0;
 }
 
@@ -199,7 +203,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
 {
 	kernfs_get(kn);
 	inode->i_private = kn;
-	inode->i_mapping->a_ops = &kernfs_aops;
+	inode->i_mapping->a_ops = &ram_aops;
 	inode->i_op = &kernfs_iops;
 	inode->i_generation = kernfs_gen(kn);
 
@@ -270,20 +274,27 @@ void kernfs_evict_inode(struct inode *inode)
 	kernfs_put(kn);
 }
 
-int kernfs_iop_permission(struct inode *inode, int mask)
+int kernfs_iop_permission(struct user_namespace *mnt_userns,
+			  struct inode *inode, int mask)
 {
 	struct kernfs_node *kn;
+	struct kernfs_root *root;
+	int ret;
 
 	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
 	kn = inode->i_private;
+	root = kernfs_root(kn);
 
-	mutex_lock(&kernfs_mutex);
+	down_read(&root->kernfs_rwsem);
+	spin_lock(&inode->i_lock);
 	kernfs_refresh_inode(kn, inode);
-	mutex_unlock(&kernfs_mutex);
+	ret = generic_permission(&init_user_ns, inode, mask);
+	spin_unlock(&inode->i_lock);
+	up_read(&root->kernfs_rwsem);
 
-	return generic_permission(inode, mask);
+	return ret;
 }
 
 int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
@@ -303,7 +314,7 @@ int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_set(&attrs->xattrs, name, value, size, flags);
+	return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL);
 }
 
 static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
@@ -317,6 +328,7 @@ static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
 }
 
 static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
+				struct user_namespace *mnt_userns,
 				struct dentry *unused, struct inode *inode,
 				const char *suffix, const void *value,
 				size_t size, int flags)
@@ -327,6 +339,87 @@ static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
 	return kernfs_xattr_set(kn, name, value, size, flags);
 }
 
+static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,
+				     const char *full_name,
+				     struct simple_xattrs *xattrs,
+				     const void *value, size_t size, int flags)
+{
+	atomic_t *sz = &kn->iattr->user_xattr_size;
+	atomic_t *nr = &kn->iattr->nr_user_xattrs;
+	ssize_t removed_size;
+	int ret;
+
+	if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) {
+		ret = -ENOSPC;
+		goto dec_count_out;
+	}
+
+	if (atomic_add_return(size, sz) > KERNFS_USER_XATTR_SIZE_LIMIT) {
+		ret = -ENOSPC;
+		goto dec_size_out;
+	}
+
+	ret = simple_xattr_set(xattrs, full_name, value, size, flags,
+			       &removed_size);
+
+	if (!ret && removed_size >= 0)
+		size = removed_size;
+	else if (!ret)
+		return 0;
+dec_size_out:
+	atomic_sub(size, sz);
+dec_count_out:
+	atomic_dec(nr);
+	return ret;
+}
+
+static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn,
+				    const char *full_name,
+				    struct simple_xattrs *xattrs,
+				    const void *value, size_t size, int flags)
+{
+	atomic_t *sz = &kn->iattr->user_xattr_size;
+	atomic_t *nr = &kn->iattr->nr_user_xattrs;
+	ssize_t removed_size;
+	int ret;
+
+	ret = simple_xattr_set(xattrs, full_name, value, size, flags,
+			       &removed_size);
+
+	if (removed_size >= 0) {
+		atomic_sub(removed_size, sz);
+		atomic_dec(nr);
+	}
+
+	return ret;
+}
+
+static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
+				     struct user_namespace *mnt_userns,
+				     struct dentry *unused, struct inode *inode,
+				     const char *suffix, const void *value,
+				     size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_iattrs *attrs;
+
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))
+		return -EOPNOTSUPP;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (value)
+		return kernfs_vfs_user_xattr_add(kn, full_name, &attrs->xattrs,
+						 value, size, flags);
+	else
+		return kernfs_vfs_user_xattr_rm(kn, full_name, &attrs->xattrs,
+						value, size, flags);
+
+}
+
 static const struct xattr_handler kernfs_trusted_xattr_handler = {
 	.prefix = XATTR_TRUSTED_PREFIX,
 	.get = kernfs_vfs_xattr_get,
@@ -339,8 +432,15 @@ static const struct xattr_handler kernfs_security_xattr_handler = {
 	.set = kernfs_vfs_xattr_set,
 };
 
+static const struct xattr_handler kernfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_user_xattr_set,
+};
+
 const struct xattr_handler *kernfs_xattr_handlers[] = {
 	&kernfs_trusted_xattr_handler,
 	&kernfs_security_xattr_handler,
+	&kernfs_user_xattr_handler,
 	NULL
 };