aboutsummaryrefslogtreecommitdiff
path: root/fs/ceph/xattr.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph/xattr.c')
-rw-r--r--fs/ceph/xattr.c348
1 files changed, 269 insertions, 79 deletions
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 2c2ae5be990..c9c2b887381 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -6,16 +6,33 @@
#include <linux/ceph/decode.h>
#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
#include <linux/slab.h>
#define XATTR_CEPH_PREFIX "ceph."
#define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
+static int __remove_xattr(struct ceph_inode_info *ci,
+ struct ceph_inode_xattr *xattr);
+
+/*
+ * 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
+ &posix_acl_access_xattr_handler,
+ &posix_acl_default_xattr_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);
}
@@ -29,9 +46,110 @@ struct ceph_vxattr {
size_t name_size; /* strlen(name) + 1 (for '\0') */
size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
- bool readonly;
+ bool readonly, hidden;
+ bool (*exists_cb)(struct ceph_inode_info *ci);
};
+/* layouts */
+
+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;
+}
+
+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);
+ const char *pool_name;
+ char buf[128];
+
+ dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
+ down_read(&osdc->map_sem);
+ 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);
+ 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;
+ }
+ }
+ up_read(&osdc->map_sem);
+ 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));
+}
+
+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));
+}
+
+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));
+}
+
+static size_t ceph_vxattrcb_layout_pool(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);
+ const char *pool_name;
+
+ down_read(&osdc->map_sem);
+ 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);
+ return ret;
+}
+
/* directories */
static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
@@ -83,17 +201,43 @@ static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
(long)ci->i_rctime.tv_nsec);
}
-#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
-#define XATTR_NAME_CEPH(_type, _name) \
- { \
- .name = CEPH_XATTR_NAME(_type, _name), \
- .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
- .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
- .readonly = true, \
- }
+#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
+#define CEPH_XATTR_NAME2(_type, _name, _name2) \
+ XATTR_CEPH_PREFIX #_type "." #_name "." #_name2
+
+#define XATTR_NAME_CEPH(_type, _name) \
+ { \
+ .name = CEPH_XATTR_NAME(_type, _name), \
+ .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
+ .readonly = true, \
+ .hidden = false, \
+ .exists_cb = NULL, \
+ }
+#define XATTR_LAYOUT_FIELD(_type, _name, _field) \
+ { \
+ .name = CEPH_XATTR_NAME2(_type, _name, _field), \
+ .name_size = sizeof (CEPH_XATTR_NAME2(_type, _name, _field)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _name ## _ ## _field, \
+ .readonly = false, \
+ .hidden = true, \
+ .exists_cb = ceph_vxattrcb_layout_exists, \
+ }
static struct ceph_vxattr ceph_dir_vxattrs[] = {
+ {
+ .name = "ceph.dir.layout",
+ .name_size = sizeof("ceph.dir.layout"),
+ .getxattr_cb = ceph_vxattrcb_layout,
+ .readonly = false,
+ .hidden = true,
+ .exists_cb = ceph_vxattrcb_layout_exists,
+ },
+ XATTR_LAYOUT_FIELD(dir, layout, stripe_unit),
+ XATTR_LAYOUT_FIELD(dir, layout, stripe_count),
+ XATTR_LAYOUT_FIELD(dir, layout, object_size),
+ XATTR_LAYOUT_FIELD(dir, layout, pool),
XATTR_NAME_CEPH(dir, entries),
XATTR_NAME_CEPH(dir, files),
XATTR_NAME_CEPH(dir, subdirs),
@@ -102,35 +246,26 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
XATTR_NAME_CEPH(dir, rsubdirs),
XATTR_NAME_CEPH(dir, rbytes),
XATTR_NAME_CEPH(dir, rctime),
- { 0 } /* Required table terminator */
+ { .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_dir_vxattrs_name_size; /* total size of all names */
/* files */
-static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
- size_t size)
-{
- int ret;
-
- ret = snprintf(val, size,
- "chunk_bytes=%lld\nstripe_count=%lld\nobject_size=%lld\n",
- (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));
- return ret;
-}
-
static struct ceph_vxattr ceph_file_vxattrs[] = {
- XATTR_NAME_CEPH(file, layout),
- /* The following extended attribute name is deprecated */
{
- .name = XATTR_CEPH_PREFIX "layout",
- .name_size = sizeof (XATTR_CEPH_PREFIX "layout"),
- .getxattr_cb = ceph_vxattrcb_file_layout,
- .readonly = true,
+ .name = "ceph.file.layout",
+ .name_size = sizeof("ceph.file.layout"),
+ .getxattr_cb = ceph_vxattrcb_layout,
+ .readonly = false,
+ .hidden = true,
+ .exists_cb = ceph_vxattrcb_layout_exists,
},
- { 0 } /* Required table terminator */
+ XATTR_LAYOUT_FIELD(file, layout, stripe_unit),
+ XATTR_LAYOUT_FIELD(file, layout, stripe_count),
+ XATTR_LAYOUT_FIELD(file, layout, object_size),
+ XATTR_LAYOUT_FIELD(file, layout, pool),
+ { .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_file_vxattrs_name_size; /* total size of all names */
@@ -164,7 +299,8 @@ static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs)
size_t size = 0;
for (vxattr = vxattrs; vxattr->name; vxattr++)
- size += vxattr->name_size;
+ if (!vxattr->hidden)
+ size += vxattr->name_size;
return size;
}
@@ -202,8 +338,7 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
static int __set_xattr(struct ceph_inode_info *ci,
const char *name, int name_len,
const char *val, int val_len,
- int dirty,
- int should_free_name, int should_free_val,
+ int flags, int update_xattr,
struct ceph_inode_xattr **newxattr)
{
struct rb_node **p;
@@ -232,12 +367,31 @@ static int __set_xattr(struct ceph_inode_info *ci,
xattr = NULL;
}
+ if (update_xattr) {
+ int err = 0;
+ if (xattr && (flags & XATTR_CREATE))
+ err = -EEXIST;
+ else if (!xattr && (flags & XATTR_REPLACE))
+ err = -ENODATA;
+ if (err) {
+ kfree(name);
+ kfree(val);
+ return err;
+ }
+ if (update_xattr < 0) {
+ if (xattr)
+ __remove_xattr(ci, xattr);
+ kfree(name);
+ return 0;
+ }
+ }
+
if (!xattr) {
new = 1;
xattr = *newxattr;
xattr->name = name;
xattr->name_len = name_len;
- xattr->should_free_name = should_free_name;
+ xattr->should_free_name = update_xattr;
ci->i_xattrs.count++;
dout("__set_xattr count=%d\n", ci->i_xattrs.count);
@@ -247,7 +401,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
if (xattr->should_free_val)
kfree((void *)xattr->val);
- if (should_free_name) {
+ if (update_xattr) {
kfree((void *)name);
name = xattr->name;
}
@@ -262,8 +416,8 @@ static int __set_xattr(struct ceph_inode_info *ci,
xattr->val = "";
xattr->val_len = val_len;
- xattr->dirty = dirty;
- xattr->should_free_val = (val && should_free_val);
+ xattr->dirty = update_xattr;
+ xattr->should_free_val = (val && update_xattr);
if (new) {
rb_link_node(&xattr->node, parent, p);
@@ -325,7 +479,7 @@ static int __remove_xattr(struct ceph_inode_info *ci,
struct ceph_inode_xattr *xattr)
{
if (!xattr)
- return -EOPNOTSUPP;
+ return -ENODATA;
rb_erase(&xattr->node, &ci->i_xattrs.index);
@@ -471,7 +625,7 @@ start:
p += len;
err = __set_xattr(ci, name, namelen, val, len,
- 0, 0, 0, &xattrs[numattr]);
+ 0, 0, &xattrs[numattr]);
if (err < 0)
goto bad;
@@ -560,10 +714,9 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
}
}
-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;
@@ -574,6 +727,10 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
/* let's see if a virtual xattr was requested */
vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && !(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
+ err = vxattr->getxattr_cb(ci, value, size);
+ return err;
+ }
spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
@@ -592,11 +749,6 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
spin_lock(&ci->i_ceph_lock);
- if (vxattr && vxattr->readonly) {
- err = vxattr->getxattr_cb(ci, value, size);
- goto out;
- }
-
err = __build_xattrs(inode);
if (err < 0)
goto out;
@@ -604,11 +756,8 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
get_xattr:
err = -ENODATA; /* == ENOATTR */
xattr = __get_xattr(ci, name);
- if (!xattr) {
- if (vxattr)
- err = vxattr->getxattr_cb(ci, value, size);
+ if (!xattr)
goto out;
- }
err = -ERANGE;
if (size && size < xattr->val_len)
@@ -625,6 +774,15 @@ 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(dentry->d_inode, name, value, size);
+}
+
ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
{
struct inode *inode = dentry->d_inode;
@@ -664,23 +822,30 @@ list_xattr:
vir_namelen = ceph_vxattrs_name_size(vxattrs);
/* adding 1 byte per each variable due to the null termination */
- namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
+ namelen = ci->i_xattrs.names_size + ci->i_xattrs.count;
err = -ERANGE;
- if (size && namelen > size)
+ if (size && vir_namelen + namelen > size)
goto out;
- err = namelen;
+ err = namelen + vir_namelen;
if (size == 0)
goto out;
names = __copy_xattr_names(ci, names);
/* virtual xattr names, too */
- if (vxattrs)
+ err = namelen;
+ if (vxattrs) {
for (i = 0; vxattrs[i].name; i++) {
- len = sprintf(names, "%s", vxattrs[i].name);
- names += len + 1;
+ if (!vxattrs[i].hidden &&
+ !(vxattrs[i].exists_cb &&
+ !vxattrs[i].exists_cb(ci))) {
+ len = sprintf(names, "%s", vxattrs[i].name);
+ names += len + 1;
+ err += len + 1;
+ }
}
+ }
out:
spin_unlock(&ci->i_ceph_lock);
@@ -693,7 +858,6 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
struct inode *inode = dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct inode *parent_inode;
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = fsc->mdsc;
int err;
@@ -722,6 +886,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
dout("setxattr value=%.*s\n", (int)size, value);
+ if (!value)
+ flags |= CEPH_XATTR_REMOVE;
+
/* do request */
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
USE_AUTH_MDS);
@@ -741,9 +908,7 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
req->r_data_len = size;
dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
- parent_inode = ceph_get_dentry_parent_inode(dentry);
- err = ceph_mdsc_do_request(mdsc, parent_inode, req);
- iput(parent_inode);
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
dout("xattr.ver (after): %lld\n", ci->i_xattrs.version);
@@ -756,15 +921,15 @@ out:
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;
struct ceph_inode_info *ci = ceph_inode(inode);
int issued;
int err;
- int dirty;
+ int dirty = 0;
int name_len = strlen(name);
int val_len = size;
char *newname = NULL;
@@ -772,9 +937,6 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
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;
@@ -782,6 +944,10 @@ int ceph_setxattr(struct dentry *dentry, const char *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;
+
/* preallocate memory for xattr name, value, index node */
err = -ENOMEM;
newname = kmemdup(name, name_len + 1, GFP_NOFS);
@@ -824,12 +990,14 @@ retry:
goto retry;
}
- err = __set_xattr(ci, newname, name_len, newval,
- val_len, 1, 1, 1, &xattr);
+ err = __set_xattr(ci, newname, name_len, newval, val_len,
+ flags, value ? 1 : -1, &xattr);
- dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
- ci->i_xattrs.dirty = true;
- inode->i_ctime = CURRENT_TIME;
+ if (!err) {
+ dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+ ci->i_xattrs.dirty = true;
+ inode->i_ctime = CURRENT_TIME;
+ }
spin_unlock(&ci->i_ceph_lock);
if (dirty)
@@ -838,6 +1006,7 @@ retry:
do_sync:
spin_unlock(&ci->i_ceph_lock);
+do_sync_unlocked:
err = ceph_sync_setxattr(dentry, name, value, size, flags);
out:
kfree(newname);
@@ -846,12 +1015,23 @@ out:
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);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct inode *inode = dentry->d_inode;
- struct inode *parent_inode;
struct ceph_mds_request *req;
int err;
@@ -865,14 +1045,12 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
req->r_num_caps = 1;
req->r_path2 = kstrdup(name, GFP_NOFS);
- parent_inode = ceph_get_dentry_parent_inode(dentry);
- err = ceph_mdsc_do_request(mdsc, parent_inode, req);
- iput(parent_inode);
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
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;
@@ -882,9 +1060,6 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
int required_blob_size;
int dirty;
- if (ceph_snap(inode) != CEPH_NOSNAP)
- return -EROFS;
-
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
@@ -892,6 +1067,10 @@ int ceph_removexattr(struct dentry *dentry, const char *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;
+
err = -ENOMEM;
spin_lock(&ci->i_ceph_lock);
retry:
@@ -931,8 +1110,19 @@ retry:
return err;
do_sync:
spin_unlock(&ci->i_ceph_lock);
+do_sync_unlocked:
err = ceph_send_removexattr(dentry, name);
out:
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);
+}