ceph: add acl for cephfs

Signed-off-by: Guangliang Zhao <[e-mail]>
Reviewed-by: Li Wang <[e-mail]>
Reviewed-by: Zheng Yan <[e-mail]>

fs/ceph/Kconfig

···
 	  caching support for Ceph clients using FS-Cache
 
 endif
+
+config CEPH_FS_POSIX_ACL
+	bool "Ceph POSIX Access Control Lists"
+	depends on CEPH_FS
+	select FS_POSIX_ACL
+	help
+	  POSIX Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the POSIX ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N

fs/ceph/Makefile

···
 	debugfs.o
 
 ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
+ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o

fs/ceph/acl.c

···
+/*
+ * linux/fs/ceph/acl.c
+ *
+ * Copyright (C) 2013 Guangliang Zhao, <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include "super.h"
+
+static inline void ceph_set_cached_acl(struct inode *inode,
+					int type, struct posix_acl *acl)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
+		set_cached_acl(inode, type, acl);
+	spin_unlock(&ci->i_ceph_lock);
+}
+
+static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode,
+							int type)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct posix_acl *acl = ACL_NOT_CACHED;
+
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
+		acl = get_cached_acl(inode, type);
+	spin_unlock(&ci->i_ceph_lock);
+
+	return acl;
+}
+
+void ceph_forget_all_cached_acls(struct inode *inode)
+{
+	forget_all_cached_acls(inode);
+}
+
+struct posix_acl *ceph_get_acl(struct inode *inode, int type)
+{
+	int size;
+	const char *name;
+	char *value = NULL;
+	struct posix_acl *acl;
+
+	if (!IS_POSIXACL(inode))
+		return NULL;
+
+	acl = ceph_get_cached_acl(inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+
+	size = __ceph_getxattr(inode, name, "", 0);
+	if (size > 0) {
+		value = kzalloc(size, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		size = __ceph_getxattr(inode, name, value, size);
+	}
+
+	if (size > 0)
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+	else if (size == -ERANGE || size == -ENODATA || size == 0)
+		acl = NULL;
+	else
+		acl = ERR_PTR(-EIO);
+
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		ceph_set_cached_acl(inode, type, acl);
+
+	return acl;
+}
+
+static int ceph_set_acl(struct dentry *dentry, struct inode *inode,
+				struct posix_acl *acl, int type)
+{
+	int ret = 0, size = 0;
+	const char *name = NULL;
+	char *value = NULL;
+	struct iattr newattrs;
+	umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
+
+	if (acl) {
+		ret = posix_acl_valid(acl);
+		if (ret < 0)
+			goto out;
+	}
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		if (acl) {
+			ret = posix_acl_equiv_mode(acl, &new_mode);
+			if (ret < 0)
+				goto out;
+			if (ret == 0)
+				acl = NULL;
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		if (!S_ISDIR(inode->i_mode)) {
+			ret = acl ? -EINVAL : 0;
+			goto out;
+		}
+		name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (acl) {
+		size = posix_acl_xattr_size(acl->a_count);
+		value = kmalloc(size, GFP_NOFS);
+		if (!value) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+		if (ret < 0)
+			goto out_free;
+	}
+
+	if (new_mode != old_mode) {
+		newattrs.ia_mode = new_mode;
+		newattrs.ia_valid = ATTR_MODE;
+		ret = ceph_setattr(dentry, &newattrs);
+		if (ret)
+			goto out_free;
+	}
+
+	if (value)
+		ret = __ceph_setxattr(dentry, name, value, size, 0);
+	else
+		ret = __ceph_removexattr(dentry, name);
+
+	if (ret) {
+		if (new_mode != old_mode) {
+			newattrs.ia_mode = old_mode;
+			newattrs.ia_valid = ATTR_MODE;
+			ceph_setattr(dentry, &newattrs);
+		}
+		goto out_free;
+	}
+
+	ceph_set_cached_acl(inode, type, acl);
+
+out_free:
+	kfree(value);
+out:
+	return ret;
+}
+
+int ceph_init_acl(struct dentry *dentry, struct inode *inode, struct inode *dir)
+{
+	struct posix_acl *acl = NULL;
+	int ret = 0;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (IS_POSIXACL(dir)) {
+			acl = ceph_get_acl(dir, ACL_TYPE_DEFAULT);
+			if (IS_ERR(acl)) {
+				ret = PTR_ERR(acl);
+				goto out;
+			}
+		}
+
+		if (!acl)
+			inode->i_mode &= ~current_umask();
+	}
+
+	if (IS_POSIXACL(dir) && acl) {
+		if (S_ISDIR(inode->i_mode)) {
+			ret = ceph_set_acl(dentry, inode, acl,
+						ACL_TYPE_DEFAULT);
+			if (ret)
+				goto out_release;
+		}
+		ret = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
+		if (ret < 0)
+			goto out;
+		else if (ret > 0)
+			ret = ceph_set_acl(dentry, inode, acl, ACL_TYPE_ACCESS);
+		else
+			cache_no_acl(inode);
+	} else {
+		cache_no_acl(inode);
+	}
+
+out_release:
+	posix_acl_release(acl);
+out:
+	return ret;
+}
+
+int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
+{
+	struct posix_acl *acl;
+	int ret = 0;
+
+	if (S_ISLNK(inode->i_mode)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (!IS_POSIXACL(inode))
+		goto out;
+
+	acl = ceph_get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR_OR_NULL(acl)) {
+		ret = PTR_ERR(acl);
+		goto out;
+	}
+
+	ret = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+	if (ret)
+		goto out;
+	ret = ceph_set_acl(dentry, inode, acl, ACL_TYPE_ACCESS);
+	posix_acl_release(acl);
+out:
+	return ret;
+}
+
+static int ceph_xattr_acl_get(struct dentry *dentry, const char *name,
+				void *value, size_t size, int type)
+{
+	struct posix_acl *acl;
+	int ret = 0;
+
+	if (!IS_POSIXACL(dentry->d_inode))
+		return -EOPNOTSUPP;
+
+	acl = ceph_get_acl(dentry->d_inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+
+	ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+	posix_acl_release(acl);
+
+	return ret;
+}
+
+static int ceph_xattr_acl_set(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags, int type)
+{
+	int ret = 0;
+	struct posix_acl *acl = NULL;
+
+	if (!inode_owner_or_capable(dentry->d_inode)) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (!IS_POSIXACL(dentry->d_inode)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (value) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		if (IS_ERR(acl)) {
+			ret = PTR_ERR(acl);
+			goto out;
+		}
+
+		if (acl) {
+			ret = posix_acl_valid(acl);
+			if (ret)
+				goto out_release;
+		}
+	}
+
+	ret = ceph_set_acl(dentry, dentry->d_inode, acl, type);
+
+out_release:
+	posix_acl_release(acl);
+out:
+	return ret;
+}
+
+const struct xattr_handler ceph_xattr_acl_default_handler = {
+	.prefix = POSIX_ACL_XATTR_DEFAULT,
+	.flags  = ACL_TYPE_DEFAULT,
+	.get    = ceph_xattr_acl_get,
+	.set    = ceph_xattr_acl_set,
+};
+
+const struct xattr_handler ceph_xattr_acl_access_handler = {
+	.prefix = POSIX_ACL_XATTR_ACCESS,
+	.flags  = ACL_TYPE_ACCESS,
+	.get    = ceph_xattr_acl_get,
+	.set    = ceph_xattr_acl_set,
+};

fs/ceph/caps.c

···
 				ceph_buffer_put(ci->i_xattrs.blob);
 			ci->i_xattrs.blob = ceph_buffer_get(xattr_buf);
 			ci->i_xattrs.version = version;
+			ceph_forget_all_cached_acls(inode);
 		}
 	}
 

fs/ceph/dir.c

···
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
+
+	if (!err)
+		err = ceph_init_acl(dentry, dentry->d_inode, dir);
+
 	if (err)
 		d_drop(dentry);
 	return err;
···
 	.getxattr = ceph_getxattr,
 	.listxattr = ceph_listxattr,
 	.removexattr = ceph_removexattr,
+	.get_acl = ceph_get_acl,
 	.mknod = ceph_mknod,
 	.symlink = ceph_symlink,
 	.mkdir = ceph_mkdir,

fs/ceph/inode.c

···
 	.getxattr = ceph_getxattr,
 	.listxattr = ceph_listxattr,
 	.removexattr = ceph_removexattr,
+	.get_acl = ceph_get_acl,
 };
 
 
···
 			memcpy(ci->i_xattrs.blob->vec.iov_base,
 			       iinfo->xattr_data, iinfo->xattr_len);
 		ci->i_xattrs.version = le64_to_cpu(info->xattr_version);
+		ceph_forget_all_cached_acls(inode);
 		xattr_blob = NULL;
 	}
 
···
 	.getxattr = ceph_getxattr,
 	.listxattr = ceph_listxattr,
 	.removexattr = ceph_removexattr,
+	.get_acl = ceph_get_acl,
 };
 
 /*
···
 			dirtied |= CEPH_CAP_AUTH_EXCL;
 		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
 			   attr->ia_mode != inode->i_mode) {
+			inode->i_mode = attr->ia_mode;
 			req->r_args.setattr.mode = cpu_to_le32(attr->ia_mode);
 			mask |= CEPH_SETATTR_MODE;
 			release |= CEPH_CAP_AUTH_SHARED;
···
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
+	if (ia_valid & ATTR_MODE) {
+		err = ceph_acl_chmod(dentry, inode);
+		if (err)
+			goto out_put;
+	}
+
 	if (mask) {
 		req->r_inode = inode;
 		ihold(inode);
···
 	return err;
 out:
 	spin_unlock(&ci->i_ceph_lock);
+out_put:
 	ceph_mdsc_put_request(req);
 	return err;
 }

fs/ceph/super.c

···
 
 	s->s_flags = fsc->mount_options->sb_flags;
 	s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	s->s_flags |= MS_POSIXACL;
+#endif
 
+	s->s_xattr = ceph_xattr_handlers;
 	s->s_fs_info = fsc;
 	fsc->sb = s;
 

fs/ceph/super.h

···
 	u32 i_fscache_gen; /* sequence, for delayed fscache validate */
 	struct work_struct i_revalidate_work;
 #endif
-
 	struct inode vfs_inode; /* at end */
 };
 
···
 /* xattr.c */
 extern int ceph_setxattr(struct dentry *, const char *, const void *,
 			 size_t, int);
+int __ceph_setxattr(struct dentry *, const char *, const void *, size_t, int);
+ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
+int __ceph_removexattr(struct dentry *, const char *);
 extern ssize_t ceph_getxattr(struct dentry *, const char *, void *, size_t);
 extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
 extern int ceph_removexattr(struct dentry *, const char *);
···
 extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
 extern void __init ceph_xattr_init(void);
 extern void ceph_xattr_exit(void);
+
+/* acl.c */
+extern const struct xattr_handler ceph_xattr_acl_access_handler;
+extern const struct xattr_handler ceph_xattr_acl_default_handler;
+extern const struct xattr_handler *ceph_xattr_handlers[];
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+
+struct posix_acl *ceph_get_acl(struct inode *, int);
+int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
+int ceph_acl_chmod(struct dentry *, struct inode *);
+void ceph_forget_all_cached_acls(struct inode *inode);
+
+#else
+
+#define ceph_get_acl NULL
+
+static inline int ceph_init_acl(struct dentry *dentry, struct inode *inode,
+				struct inode *dir)
+{
+	return 0;
+}
+
+static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
+{
+	return 0;
+}
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+}
+
+#endif
 
 /* caps.c */
 extern const char *ceph_cap_string(int c);

fs/ceph/xattr.c

···
 #define XATTR_CEPH_PREFIX "ceph."
 #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
 
+/*
+ * List of handlers for synthetic system.* attributes. Other
+ * attributes are handled directly.
+ */
+const struct xattr_handler *ceph_xattr_handlers[] = {
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+	&ceph_xattr_acl_access_handler,
+	&ceph_xattr_acl_default_handler,
+#endif
+	NULL,
+};
+
 static bool ceph_is_valid_xattr(const char *name)
 {
 	return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) ||
 	       !strncmp(name, XATTR_SECURITY_PREFIX,
 			XATTR_SECURITY_PREFIX_LEN) ||
+	       !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) ||
 	       !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
 	       !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
 }
···
 	}
 }
 
-ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
+ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 		      size_t size)
 {
-	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int err;
 	struct ceph_inode_xattr *xattr;
···
 
 	if (!ceph_is_valid_xattr(name))
 		return -ENODATA;
-
 
 	/* let's see if a virtual xattr was requested */
 	vxattr = ceph_match_vxattr(inode, name);
···
 out:
 	spin_unlock(&ci->i_ceph_lock);
 	return err;
+}
+
+ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
+		      size_t size)
+{
+	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+		return generic_getxattr(dentry, name, value, size);
+
+	return __ceph_getxattr(dentry->d_inode, name, value, size);
 }
 
 ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
···
 	return err;
 }
 
-int ceph_setxattr(struct dentry *dentry, const char *name,
-		  const void *value, size_t size, int flags)
+int __ceph_setxattr(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags)
 {
 	struct inode *inode = dentry->d_inode;
 	struct ceph_vxattr *vxattr;
···
 	char *newval = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
 	int required_blob_size;
-
-	if (ceph_snap(inode) != CEPH_NOSNAP)
-		return -EROFS;
 
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
···
 	return err;
 }
 
+int ceph_setxattr(struct dentry *dentry, const char *name,
+		  const void *value, size_t size, int flags)
+{
+	if (ceph_snap(dentry->d_inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+		return generic_setxattr(dentry, name, value, size, flags);
+
+	return __ceph_setxattr(dentry, name, value, size, flags);
+}
+
 static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
···
 	return err;
 }
 
-int ceph_removexattr(struct dentry *dentry, const char *name)
+int __ceph_removexattr(struct dentry *dentry, const char *name)
 {
 	struct inode *inode = dentry->d_inode;
 	struct ceph_vxattr *vxattr;
···
 	int err;
 	int required_blob_size;
 	int dirty;
-
-	if (ceph_snap(inode) != CEPH_NOSNAP)
-		return -EROFS;
 
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
···
 	return err;
 }
 
+int ceph_removexattr(struct dentry *dentry, const char *name)
+{
+	if (ceph_snap(dentry->d_inode) != CEPH_NOSNAP)
+		return -EROFS;
+
+	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+		return generic_removexattr(dentry, name);
+
+	return __ceph_removexattr(dentry, name);
+}