1 files changed, 102 insertions, 217 deletions

diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 9410abdef3ce..adc231892b0d 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -16,6 +16,8 @@
 static int __remove_xattr(struct ceph_inode_info *ci,
 			  struct ceph_inode_xattr *xattr);
 
+const struct xattr_handler ceph_other_xattr_handler;
+
 /*
  * List of handlers for synthetic system.* attributes. Other
  * attributes are handled directly.
@@ -25,6 +27,7 @@ const struct xattr_handler *ceph_xattr_handlers[] = {
 	&posix_acl_access_xattr_handler,
 	&posix_acl_default_xattr_handler,
 #endif
+	&ceph_other_xattr_handler,
 	NULL,
 };
 
@@ -33,7 +36,6 @@ 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);
 }
@@ -55,81 +57,88 @@ struct ceph_vxattr {
 
 static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
 {
-	size_t s;
-	char *p = (char *)&ci->i_layout;
-
-	for (s = 0; s < sizeof(ci->i_layout); s++, p++)
-		if (*p)
-			return true;
-	return false;
+	struct ceph_file_layout *fl = &ci->i_layout;
+	return (fl->stripe_unit > 0 || fl->stripe_count > 0 ||
+		fl->object_size > 0 || fl->pool_id >= 0 ||
+		rcu_dereference_raw(fl->pool_ns) != NULL);
 }
 
 static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 				   size_t size)
 {
-	int ret;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
-	s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+	struct ceph_string *pool_ns;
+	s64 pool = ci->i_layout.pool_id;
 	const char *pool_name;
+	const char *ns_field = " pool_namespace=";
 	char buf[128];
+	size_t len, total_len = 0;
+	int ret;
+
+	pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
 
 	dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
-	down_read(&osdc->map_sem);
+	down_read(&osdc->lock);
 	pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
 	if (pool_name) {
-		size_t len = strlen(pool_name);
-		ret = snprintf(buf, sizeof(buf),
-		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=",
-		(unsigned long long)ceph_file_layout_su(ci->i_layout),
-		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
-	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
-		if (!size) {
-			ret += len;
-		} else if (ret + len > size) {
-			ret = -ERANGE;
-		} else {
-			memcpy(val, buf, ret);
+		len = snprintf(buf, sizeof(buf),
+		"stripe_unit=%u stripe_count=%u object_size=%u pool=",
+		ci->i_layout.stripe_unit, ci->i_layout.stripe_count,
+	        ci->i_layout.object_size);
+		total_len = len + strlen(pool_name);
+	} else {
+		len = snprintf(buf, sizeof(buf),
+		"stripe_unit=%u stripe_count=%u object_size=%u pool=%lld",
+		ci->i_layout.stripe_unit, ci->i_layout.stripe_count,
+	        ci->i_layout.object_size, (unsigned long long)pool);
+		total_len = len;
+	}
+
+	if (pool_ns)
+		total_len += strlen(ns_field) + pool_ns->len;
+
+	if (!size) {
+		ret = total_len;
+	} else if (total_len > size) {
+		ret = -ERANGE;
+	} else {
+		memcpy(val, buf, len);
+		ret = len;
+		if (pool_name) {
+			len = strlen(pool_name);
 			memcpy(val + ret, pool_name, len);
 			ret += len;
 		}
-	} else {
-		ret = snprintf(buf, sizeof(buf),
-		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%lld",
-		(unsigned long long)ceph_file_layout_su(ci->i_layout),
-		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
-	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
-		(unsigned long long)pool);
-		if (size) {
-			if (ret <= size)
-				memcpy(val, buf, ret);
-			else
-				ret = -ERANGE;
+		if (pool_ns) {
+			len = strlen(ns_field);
+			memcpy(val + ret, ns_field, len);
+			ret += len;
+			memcpy(val + ret, pool_ns->str, pool_ns->len);
+			ret += pool_ns->len;
 		}
 	}
-	up_read(&osdc->map_sem);
+	up_read(&osdc->lock);
+	ceph_put_string(pool_ns);
 	return ret;
 }
 
 static size_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci,
 					       char *val, size_t size)
 {
-	return snprintf(val, size, "%lld",
-			(unsigned long long)ceph_file_layout_su(ci->i_layout));
+	return snprintf(val, size, "%u", ci->i_layout.stripe_unit);
 }
 
 static size_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci,
 						char *val, size_t size)
 {
-	return snprintf(val, size, "%lld",
-	       (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout));
+	return snprintf(val, size, "%u", ci->i_layout.stripe_count);
 }
 
 static size_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci,
 					       char *val, size_t size)
 {
-	return snprintf(val, size, "%lld",
-	       (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
+	return snprintf(val, size, "%u", ci->i_layout.object_size);
 }
 
 static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
@@ -138,16 +147,28 @@ static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
 	int ret;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
-	s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+	s64 pool = ci->i_layout.pool_id;
 	const char *pool_name;
 
-	down_read(&osdc->map_sem);
+	down_read(&osdc->lock);
 	pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
 	if (pool_name)
 		ret = snprintf(val, size, "%s", pool_name);
 	else
 		ret = snprintf(val, size, "%lld", (unsigned long long)pool);
-	up_read(&osdc->map_sem);
+	up_read(&osdc->lock);
+	return ret;
+}
+
+static size_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci,
+						  char *val, size_t size)
+{
+	int ret = 0;
+	struct ceph_string *ns = ceph_try_get_string(ci->i_layout.pool_ns);
+	if (ns) {
+		ret = snprintf(val, size, "%.*s", (int)ns->len, ns->str);
+		ceph_put_string(ns);
+	}
 	return ret;
 }
 
@@ -239,6 +260,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
 	XATTR_LAYOUT_FIELD(dir, layout, stripe_count),
 	XATTR_LAYOUT_FIELD(dir, layout, object_size),
 	XATTR_LAYOUT_FIELD(dir, layout, pool),
+	XATTR_LAYOUT_FIELD(dir, layout, pool_namespace),
 	XATTR_NAME_CEPH(dir, entries),
 	XATTR_NAME_CEPH(dir, files),
 	XATTR_NAME_CEPH(dir, subdirs),
@@ -266,6 +288,7 @@ static struct ceph_vxattr ceph_file_vxattrs[] = {
 	XATTR_LAYOUT_FIELD(file, layout, stripe_count),
 	XATTR_LAYOUT_FIELD(file, layout, object_size),
 	XATTR_LAYOUT_FIELD(file, layout, pool),
+	XATTR_LAYOUT_FIELD(file, layout, pool_namespace),
 	{ .name = NULL, 0 }	/* Required table terminator */
 };
 static size_t ceph_file_vxattrs_name_size;	/* total size of all names */
@@ -496,19 +519,6 @@ static int __remove_xattr(struct ceph_inode_info *ci,
 	return 0;
 }
 
-static int __remove_xattr_by_name(struct ceph_inode_info *ci,
-			   const char *name)
-{
-	struct rb_node **p;
-	struct ceph_inode_xattr *xattr;
-	int err;
-
-	p = &ci->i_xattrs.index.rb_node;
-	xattr = __get_xattr(ci, name);
-	err = __remove_xattr(ci, xattr);
-	return err;
-}
-
 static char *__copy_xattr_names(struct ceph_inode_info *ci,
 				char *dest)
 {
@@ -740,9 +750,6 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 	int req_mask;
 	int err;
 
-	if (!ceph_is_valid_xattr(name))
-		return -ENODATA;
-
 	/* let's see if a virtual xattr was requested */
 	vxattr = ceph_match_vxattr(inode, name);
 	if (vxattr) {
@@ -804,15 +811,6 @@ out:
 	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(d_inode(dentry), name, value, size);
-}
-
 ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
 {
 	struct inode *inode = d_inode(dentry);
@@ -877,15 +875,15 @@ out:
 	return err;
 }
 
-static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
+static int ceph_sync_setxattr(struct inode *inode, const char *name,
 			      const char *value, size_t size, int flags)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
-	struct inode *inode = d_inode(dentry);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_pagelist *pagelist = NULL;
+	int op = CEPH_MDS_OP_SETXATTR;
 	int err;
 
 	if (size > 0) {
@@ -899,20 +897,21 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 		if (err)
 			goto out;
 	} else if (!value) {
-		flags |= CEPH_XATTR_REMOVE;
+		if (flags & CEPH_XATTR_REPLACE)
+			op = CEPH_MDS_OP_RMXATTR;
+		else
+			flags |= CEPH_XATTR_REMOVE;
 	}
 
 	dout("setxattr value=%.*s\n", (int)size, value);
 
 	/* do request */
-	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
-				       USE_AUTH_MDS);
+	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
 	}
 
-	req->r_args.setxattr.flags = cpu_to_le32(flags);
 	req->r_path2 = kstrdup(name, GFP_NOFS);
 	if (!req->r_path2) {
 		ceph_mdsc_put_request(req);
@@ -920,8 +919,11 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 		goto out;
 	}
 
-	req->r_pagelist = pagelist;
-	pagelist = NULL;
+	if (op == CEPH_MDS_OP_SETXATTR) {
+		req->r_args.setxattr.flags = cpu_to_le32(flags);
+		req->r_pagelist = pagelist;
+		pagelist = NULL;
+	}
 
 	req->r_inode = inode;
 	ihold(inode);
@@ -939,13 +941,12 @@ out:
 	return err;
 }
 
-int __ceph_setxattr(struct dentry *dentry, const char *name,
+int __ceph_setxattr(struct inode *inode, const char *name,
 			const void *value, size_t size, int flags)
 {
-	struct inode *inode = d_inode(dentry);
 	struct ceph_vxattr *vxattr;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_cap_flush *prealloc_cf = NULL;
 	int issued;
 	int err;
@@ -958,8 +959,8 @@ int __ceph_setxattr(struct dentry *dentry, const char *name,
 	int required_blob_size;
 	bool lock_snap_rwsem = false;
 
-	if (!ceph_is_valid_xattr(name))
-		return -EOPNOTSUPP;
+	if (ceph_snap(inode) != CEPH_NOSNAP)
+		return -EROFS;
 
 	vxattr = ceph_match_vxattr(inode, name);
 	if (vxattr && vxattr->readonly)
@@ -1056,7 +1057,7 @@ do_sync_unlocked:
 				    "during filling trace\n", inode);
 		err = -EBUSY;
 	} else {
-		err = ceph_sync_setxattr(dentry, name, value, size, flags);
+		err = ceph_sync_setxattr(inode, name, value, size, flags);
 	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
@@ -1066,146 +1067,30 @@ out:
 	return err;
 }
 
-int ceph_setxattr(struct dentry *dentry, const char *name,
-		  const void *value, size_t size, int flags)
+static int ceph_get_xattr_handler(const struct xattr_handler *handler,
+				  struct dentry *dentry, struct inode *inode,
+				  const char *name, void *value, size_t size)
 {
-	if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
-		return -EROFS;
-
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_setxattr(dentry, name, value, size, flags);
-
-	if (size == 0)
-		value = "";  /* empty EA, do not remove */
-
-	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);
-	struct ceph_mds_client *mdsc = fsc->mdsc;
-	struct inode *inode = d_inode(dentry);
-	struct ceph_mds_request *req;
-	int err;
-
-	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RMXATTR,
-				       USE_AUTH_MDS);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-	req->r_path2 = kstrdup(name, GFP_NOFS);
-	if (!req->r_path2)
-		return -ENOMEM;
-
-	req->r_inode = inode;
-	ihold(inode);
-	req->r_num_caps = 1;
-	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
-	err = ceph_mdsc_do_request(mdsc, NULL, req);
-	ceph_mdsc_put_request(req);
-	return err;
+	if (!ceph_is_valid_xattr(name))
+		return -EOPNOTSUPP;
+	return __ceph_getxattr(inode, name, value, size);
 }
 
-int __ceph_removexattr(struct dentry *dentry, const char *name)
+static int ceph_set_xattr_handler(const struct xattr_handler *handler,
+				  struct dentry *unused, struct inode *inode,
+				  const char *name, const void *value,
+				  size_t size, int flags)
 {
-	struct inode *inode = d_inode(dentry);
-	struct ceph_vxattr *vxattr;
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
-	struct ceph_cap_flush *prealloc_cf = NULL;
-	int issued;
-	int err;
-	int required_blob_size;
-	int dirty;
-	bool lock_snap_rwsem = false;
-
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
-
-	vxattr = ceph_match_vxattr(inode, name);
-	if (vxattr && vxattr->readonly)
-		return -EOPNOTSUPP;
-
-	/* pass any unhandled ceph.* xattrs through to the MDS */
-	if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
-		goto do_sync_unlocked;
-
-	prealloc_cf = ceph_alloc_cap_flush();
-	if (!prealloc_cf)
-		return -ENOMEM;
-
-	err = -ENOMEM;
-	spin_lock(&ci->i_ceph_lock);
-retry:
-	issued = __ceph_caps_issued(ci, NULL);
-	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
-		goto do_sync;
-
-	if (!lock_snap_rwsem && !ci->i_head_snapc) {
-		lock_snap_rwsem = true;
-		if (!down_read_trylock(&mdsc->snap_rwsem)) {
-			spin_unlock(&ci->i_ceph_lock);
-			down_read(&mdsc->snap_rwsem);
-			spin_lock(&ci->i_ceph_lock);
-			goto retry;
-		}
-	}
-
-	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
-
-	__build_xattrs(inode);
-
-	required_blob_size = __get_required_blob_size(ci, 0, 0);
-
-	if (!ci->i_xattrs.prealloc_blob ||
-	    required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
-		struct ceph_buffer *blob;
-
-		spin_unlock(&ci->i_ceph_lock);
-		dout(" preaallocating new blob size=%d\n", required_blob_size);
-		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
-		if (!blob)
-			goto do_sync_unlocked;
-		spin_lock(&ci->i_ceph_lock);
-		if (ci->i_xattrs.prealloc_blob)
-			ceph_buffer_put(ci->i_xattrs.prealloc_blob);
-		ci->i_xattrs.prealloc_blob = blob;
-		goto retry;
-	}
-
-	err = __remove_xattr_by_name(ceph_inode(inode), name);
-
-	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
-				       &prealloc_cf);
-	ci->i_xattrs.dirty = true;
-	inode->i_ctime = current_fs_time(inode->i_sb);
-	spin_unlock(&ci->i_ceph_lock);
-	if (lock_snap_rwsem)
-		up_read(&mdsc->snap_rwsem);
-	if (dirty)
-		__mark_inode_dirty(inode, dirty);
-	ceph_free_cap_flush(prealloc_cf);
-	return err;
-do_sync:
-	spin_unlock(&ci->i_ceph_lock);
-do_sync_unlocked:
-	if (lock_snap_rwsem)
-		up_read(&mdsc->snap_rwsem);
-	ceph_free_cap_flush(prealloc_cf);
-	err = ceph_send_removexattr(dentry, name);
-	return err;
+	return __ceph_setxattr(inode, name, value, size, flags);
 }
 
-int ceph_removexattr(struct dentry *dentry, const char *name)
-{
-	if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
-		return -EROFS;
-
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_removexattr(dentry, name);
-
-	return __ceph_removexattr(dentry, name);
-}
+const struct xattr_handler ceph_other_xattr_handler = {
+	.prefix = "",  /* match any name => handlers called with full name */
+	.get = ceph_get_xattr_handler,
+	.set = ceph_set_xattr_handler,
+};
 
 #ifdef CONFIG_SECURITY
 bool ceph_security_xattr_wanted(struct inode *in)