summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/inode.c11
-rw-r--r--fs/ceph/mds_client.c7
-rw-r--r--fs/ceph/snap.c2
-rw-r--r--fs/ceph/super.c19
-rw-r--r--fs/ceph/super.h4
-rw-r--r--fs/ceph/xattr.c202
6 files changed, 163 insertions, 82 deletions
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2c489378b4cd..9fff9f3b17e4 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -677,18 +677,19 @@ static int fill_inode(struct inode *inode,
case S_IFLNK:
inode->i_op = &ceph_symlink_iops;
if (!ci->i_symlink) {
- int symlen = iinfo->symlink_len;
+ u32 symlen = iinfo->symlink_len;
char *sym;
- BUG_ON(symlen != inode->i_size);
spin_unlock(&ci->i_ceph_lock);
+ err = -EINVAL;
+ if (WARN_ON(symlen != inode->i_size))
+ goto out;
+
err = -ENOMEM;
- sym = kmalloc(symlen+1, GFP_NOFS);
+ sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
if (!sym)
goto out;
- memcpy(sym, iinfo->symlink, symlen);
- sym[symlen] = 0;
spin_lock(&ci->i_ceph_lock);
if (!ci->i_symlink)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 866e8d7ca37d..89971e137aab 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -402,7 +402,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
spin_lock_init(&s->s_gen_ttl_lock);
s->s_cap_gen = 0;
- s->s_cap_ttl = 0;
+ s->s_cap_ttl = jiffies - 1;
spin_lock_init(&s->s_cap_lock);
s->s_renew_requested = 0;
@@ -1083,8 +1083,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
int wake = 0;
spin_lock(&session->s_cap_lock);
- was_stale = is_renew && (session->s_cap_ttl == 0 ||
- time_after_eq(jiffies, session->s_cap_ttl));
+ was_stale = is_renew && time_after_eq(jiffies, session->s_cap_ttl);
session->s_cap_ttl = session->s_renew_requested +
mdsc->mdsmap->m_session_timeout*HZ;
@@ -2332,7 +2331,7 @@ static void handle_session(struct ceph_mds_session *session,
session->s_mds);
spin_lock(&session->s_gen_ttl_lock);
session->s_cap_gen++;
- session->s_cap_ttl = 0;
+ session->s_cap_ttl = jiffies - 1;
spin_unlock(&session->s_gen_ttl_lock);
send_renew_caps(mdsc, session);
break;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index a559c80f127a..f04c0961f993 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
/* alloc new snap context */
err = -ENOMEM;
- if (num > ULONG_MAX / sizeof(u64) - sizeof(*snapc))
+ if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64))
goto fail;
snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
if (!snapc)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 256f85221926..1e67dd7305a4 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -130,10 +130,12 @@ enum {
Opt_nodirstat,
Opt_rbytes,
Opt_norbytes,
+ Opt_asyncreaddir,
Opt_noasyncreaddir,
Opt_dcache,
Opt_nodcache,
Opt_ino32,
+ Opt_noino32,
};
static match_table_t fsopt_tokens = {
@@ -153,10 +155,12 @@ static match_table_t fsopt_tokens = {
{Opt_nodirstat, "nodirstat"},
{Opt_rbytes, "rbytes"},
{Opt_norbytes, "norbytes"},
+ {Opt_asyncreaddir, "asyncreaddir"},
{Opt_noasyncreaddir, "noasyncreaddir"},
{Opt_dcache, "dcache"},
{Opt_nodcache, "nodcache"},
{Opt_ino32, "ino32"},
+ {Opt_noino32, "noino32"},
{-1, NULL}
};
@@ -232,6 +236,9 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_norbytes:
fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
break;
+ case Opt_asyncreaddir:
+ fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR;
+ break;
case Opt_noasyncreaddir:
fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
break;
@@ -244,6 +251,9 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_ino32:
fsopt->flags |= CEPH_MOUNT_OPT_INO32;
break;
+ case Opt_noino32:
+ fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
+ break;
default:
BUG_ON(token);
}
@@ -334,10 +344,12 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
*path += 2;
dout("server path '%s'\n", *path);
- err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+ *popt = ceph_parse_options(options, dev_name, dev_name_end,
parse_fsopt_token, (void *)fsopt);
- if (err)
+ if (IS_ERR(*popt)) {
+ err = PTR_ERR(*popt);
goto out;
+ }
/* success */
*pfsopt = fsopt;
@@ -926,6 +938,7 @@ static int __init init_ceph(void)
if (ret)
goto out;
+ ceph_xattr_init();
ret = register_filesystem(&ceph_fs_type);
if (ret)
goto out_icache;
@@ -935,6 +948,7 @@ static int __init init_ceph(void)
return 0;
out_icache:
+ ceph_xattr_exit();
destroy_caches();
out:
return ret;
@@ -944,6 +958,7 @@ static void __exit exit_ceph(void)
{
dout("exit_ceph\n");
unregister_filesystem(&ceph_fs_type);
+ ceph_xattr_exit();
destroy_caches();
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1421f3d875a2..fc35036d258d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -367,7 +367,7 @@ static inline u32 ceph_ino_to_ino32(__u64 vino)
u32 ino = vino & 0xffffffff;
ino ^= vino >> 32;
if (!ino)
- ino = 1;
+ ino = 2;
return ino;
}
@@ -733,6 +733,8 @@ extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
extern int ceph_removexattr(struct dentry *, const char *);
extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
+extern void __init ceph_xattr_init(void);
+extern void ceph_xattr_exit(void);
/* caps.c */
extern const char *ceph_cap_string(int c);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index a76f697303d9..35b86331d8a5 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -8,9 +8,12 @@
#include <linux/xattr.h>
#include <linux/slab.h>
+#define XATTR_CEPH_PREFIX "ceph."
+#define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
+
static bool ceph_is_valid_xattr(const char *name)
{
- return !strncmp(name, "ceph.", 5) ||
+ return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) ||
!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
@@ -21,79 +24,91 @@ static bool ceph_is_valid_xattr(const char *name)
* These define virtual xattrs exposing the recursive directory
* statistics and layout metadata.
*/
-struct ceph_vxattr_cb {
- bool readonly;
+struct ceph_vxattr {
char *name;
+ 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;
};
/* directories */
-static size_t ceph_vxattrcb_entries(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs);
}
-static size_t ceph_vxattrcb_files(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_files);
}
-static size_t ceph_vxattrcb_subdirs(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_subdirs);
}
-static size_t ceph_vxattrcb_rentries(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs);
}
-static size_t ceph_vxattrcb_rfiles(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rfiles);
}
-static size_t ceph_vxattrcb_rsubdirs(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rsubdirs);
}
-static size_t ceph_vxattrcb_rbytes(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rbytes);
}
-static size_t ceph_vxattrcb_rctime(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
size_t size)
{
- return snprintf(val, size, "%ld.%ld", (long)ci->i_rctime.tv_sec,
+ return snprintf(val, size, "%ld.09%ld", (long)ci->i_rctime.tv_sec,
(long)ci->i_rctime.tv_nsec);
}
-static struct ceph_vxattr_cb ceph_dir_vxattrs[] = {
- { true, "ceph.dir.entries", ceph_vxattrcb_entries},
- { true, "ceph.dir.files", ceph_vxattrcb_files},
- { true, "ceph.dir.subdirs", ceph_vxattrcb_subdirs},
- { true, "ceph.dir.rentries", ceph_vxattrcb_rentries},
- { true, "ceph.dir.rfiles", ceph_vxattrcb_rfiles},
- { true, "ceph.dir.rsubdirs", ceph_vxattrcb_rsubdirs},
- { true, "ceph.dir.rbytes", ceph_vxattrcb_rbytes},
- { true, "ceph.dir.rctime", ceph_vxattrcb_rctime},
- { true, NULL, NULL }
+#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, \
+ }
+
+static struct ceph_vxattr ceph_dir_vxattrs[] = {
+ XATTR_NAME_CEPH(dir, entries),
+ XATTR_NAME_CEPH(dir, files),
+ XATTR_NAME_CEPH(dir, subdirs),
+ XATTR_NAME_CEPH(dir, rentries),
+ XATTR_NAME_CEPH(dir, rfiles),
+ XATTR_NAME_CEPH(dir, rsubdirs),
+ XATTR_NAME_CEPH(dir, rbytes),
+ XATTR_NAME_CEPH(dir, rctime),
+ { 0 } /* Required table terminator */
};
+static size_t ceph_dir_vxattrs_name_size; /* total size of all names */
/* files */
-static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
+static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
size_t size)
{
int ret;
@@ -103,21 +118,32 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
(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 (ceph_file_layout_pg_preferred(ci->i_layout))
- ret += snprintf(val + ret, size, "preferred_osd=%lld\n",
+
+ if (ceph_file_layout_pg_preferred(ci->i_layout) >= 0) {
+ val += ret;
+ size -= ret;
+ ret += snprintf(val, size, "preferred_osd=%lld\n",
(unsigned long long)ceph_file_layout_pg_preferred(
ci->i_layout));
+ }
+
return ret;
}
-static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
- { true, "ceph.file.layout", ceph_vxattrcb_layout},
+static struct ceph_vxattr ceph_file_vxattrs[] = {
+ XATTR_NAME_CEPH(file, layout),
/* The following extended attribute name is deprecated */
- { true, "ceph.layout", ceph_vxattrcb_layout},
- { true, NULL, NULL }
+ {
+ .name = XATTR_CEPH_PREFIX "layout",
+ .name_size = sizeof (XATTR_CEPH_PREFIX "layout"),
+ .getxattr_cb = ceph_vxattrcb_file_layout,
+ .readonly = true,
+ },
+ { 0 } /* Required table terminator */
};
+static size_t ceph_file_vxattrs_name_size; /* total size of all names */
-static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
+static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode)
{
if (S_ISDIR(inode->i_mode))
return ceph_dir_vxattrs;
@@ -126,14 +152,59 @@ static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
return NULL;
}
-static struct ceph_vxattr_cb *ceph_match_vxattr(struct ceph_vxattr_cb *vxattr,
+static size_t ceph_vxattrs_name_size(struct ceph_vxattr *vxattrs)
+{
+ if (vxattrs == ceph_dir_vxattrs)
+ return ceph_dir_vxattrs_name_size;
+ if (vxattrs == ceph_file_vxattrs)
+ return ceph_file_vxattrs_name_size;
+ BUG();
+
+ return 0;
+}
+
+/*
+ * Compute the aggregate size (including terminating '\0') of all
+ * virtual extended attribute names in the given vxattr table.
+ */
+static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs)
+{
+ struct ceph_vxattr *vxattr;
+ size_t size = 0;
+
+ for (vxattr = vxattrs; vxattr->name; vxattr++)
+ size += vxattr->name_size;
+
+ return size;
+}
+
+/* Routines called at initialization and exit time */
+
+void __init ceph_xattr_init(void)
+{
+ ceph_dir_vxattrs_name_size = vxattrs_name_size(ceph_dir_vxattrs);
+ ceph_file_vxattrs_name_size = vxattrs_name_size(ceph_file_vxattrs);
+}
+
+void ceph_xattr_exit(void)
+{
+ ceph_dir_vxattrs_name_size = 0;
+ ceph_file_vxattrs_name_size = 0;
+}
+
+static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
const char *name)
{
- do {
- if (strcmp(vxattr->name, name) == 0)
- return vxattr;
- vxattr++;
- } while (vxattr->name);
+ struct ceph_vxattr *vxattr = ceph_inode_vxattrs(inode);
+
+ if (vxattr) {
+ while (vxattr->name) {
+ if (!strcmp(vxattr->name, name))
+ return vxattr;
+ vxattr++;
+ }
+ }
+
return NULL;
}
@@ -502,17 +573,15 @@ ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value,
{
struct inode *inode = dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
int err;
struct ceph_inode_xattr *xattr;
- struct ceph_vxattr_cb *vxattr = NULL;
+ struct ceph_vxattr *vxattr = NULL;
if (!ceph_is_valid_xattr(name))
return -ENODATA;
/* let's see if a virtual xattr was requested */
- if (vxattrs)
- vxattr = ceph_match_vxattr(vxattrs, name);
+ vxattr = ceph_match_vxattr(inode, name);
spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
@@ -568,7 +637,7 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
{
struct inode *inode = dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+ struct ceph_vxattr *vxattrs = ceph_inode_vxattrs(inode);
u32 vir_namelen = 0;
u32 namelen;
int err;
@@ -596,11 +665,12 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
goto out;
list_xattr:
- vir_namelen = 0;
- /* include virtual dir xattrs */
- if (vxattrs)
- for (i = 0; vxattrs[i].name; i++)
- vir_namelen += strlen(vxattrs[i].name) + 1;
+ /*
+ * Start with virtual dir xattr names (if any) (including
+ * terminating '\0' characters for each).
+ */
+ 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;
err = -ERANGE;
@@ -698,17 +768,17 @@ 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);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
+ int issued;
int err;
+ int dirty;
int name_len = strlen(name);
int val_len = size;
char *newname = NULL;
char *newval = NULL;
struct ceph_inode_xattr *xattr = NULL;
- int issued;
int required_blob_size;
- int dirty;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
@@ -716,12 +786,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
- if (vxattrs) {
- struct ceph_vxattr_cb *vxattr =
- ceph_match_vxattr(vxattrs, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
- }
+ vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && vxattr->readonly)
+ return -EOPNOTSUPP;
/* preallocate memory for xattr name, value, index node */
err = -ENOMEM;
@@ -730,11 +797,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
goto out;
if (val_len) {
- newval = kmalloc(val_len + 1, GFP_NOFS);
+ newval = kmemdup(value, val_len, GFP_NOFS);
if (!newval)
goto out;
- memcpy(newval, value, val_len);
- newval[val_len] = '\0';
}
xattr = kmalloc(sizeof(struct ceph_inode_xattr), GFP_NOFS);
@@ -744,6 +809,7 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
spin_lock(&ci->i_ceph_lock);
retry:
issued = __ceph_caps_issued(ci, NULL);
+ dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
if (!(issued & CEPH_CAP_XATTR_EXCL))
goto do_sync;
__build_xattrs(inode);
@@ -752,7 +818,7 @@ retry:
if (!ci->i_xattrs.prealloc_blob ||
required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
- struct ceph_buffer *blob = NULL;
+ struct ceph_buffer *blob;
spin_unlock(&ci->i_ceph_lock);
dout(" preaallocating new blob size=%d\n", required_blob_size);
@@ -766,12 +832,13 @@ retry:
goto retry;
}
- dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
err = __set_xattr(ci, newname, name_len, newval,
val_len, 1, 1, 1, &xattr);
+
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)
__mark_inode_dirty(inode, dirty);
@@ -816,8 +883,8 @@ static int ceph_send_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;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
int issued;
int err;
int required_blob_size;
@@ -829,22 +896,19 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
if (!ceph_is_valid_xattr(name))
return -EOPNOTSUPP;
- if (vxattrs) {
- struct ceph_vxattr_cb *vxattr =
- ceph_match_vxattr(vxattrs, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
- }
+ vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && vxattr->readonly)
+ return -EOPNOTSUPP;
err = -ENOMEM;
spin_lock(&ci->i_ceph_lock);
- __build_xattrs(inode);
retry:
issued = __ceph_caps_issued(ci, NULL);
dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
if (!(issued & CEPH_CAP_XATTR_EXCL))
goto do_sync;
+ __build_xattrs(inode);
required_blob_size = __get_required_blob_size(ci, 0, 0);
@@ -865,10 +929,10 @@ retry:
}
err = __remove_xattr_by_name(ceph_inode(inode), name);
+
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)
__mark_inode_dirty(inode, dirty);