summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/caps.c22
-rw-r--r--fs/ceph/inode.c16
-rw-r--r--fs/ceph/locks.c3
-rw-r--r--fs/ceph/mds_client.c4
-rw-r--r--fs/ceph/snap.c4
-rw-r--r--fs/ceph/super.c11
-rw-r--r--fs/ceph/super.h9
-rw-r--r--fs/ceph/xattr.c33
8 files changed, 70 insertions, 32 deletions
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 92eb9c3052ee..c3a3ee74e2d8 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -935,6 +935,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
+ /* remove from inode's cap rbtree, and clear auth cap */
+ rb_erase(&cap->ci_node, &ci->i_caps);
+ if (ci->i_auth_cap == cap)
+ ci->i_auth_cap = NULL;
+
/* remove from session list */
spin_lock(&session->s_cap_lock);
if (session->s_cap_iterator == cap) {
@@ -970,11 +975,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
spin_unlock(&session->s_cap_lock);
- /* remove from inode list */
- rb_erase(&cap->ci_node, &ci->i_caps);
- if (ci->i_auth_cap == cap)
- ci->i_auth_cap = NULL;
-
if (removed)
ceph_put_cap(mdsc, cap);
@@ -1119,20 +1119,23 @@ static int send_cap_msg(struct cap_msg_args *arg)
}
/*
- * Queue cap releases when an inode is dropped from our cache. Since
- * inode is about to be destroyed, there is no need for i_ceph_lock.
+ * Queue cap releases when an inode is dropped from our cache.
*/
void ceph_queue_caps_release(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct rb_node *p;
+ /* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU)
+ * may call __ceph_caps_issued_mask() on a freeing inode. */
+ spin_lock(&ci->i_ceph_lock);
p = rb_first(&ci->i_caps);
while (p) {
struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
p = rb_next(p);
__ceph_remove_cap(cap, true);
}
+ spin_unlock(&ci->i_ceph_lock);
}
/*
@@ -1159,6 +1162,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
{
struct ceph_inode_info *ci = cap->ci;
struct inode *inode = &ci->vfs_inode;
+ struct ceph_buffer *old_blob = NULL;
struct cap_msg_args arg;
int held, revoking, dropping;
int wake = 0;
@@ -1224,7 +1228,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
ci->i_requested_max_size = arg.max_size;
if (flushing & CEPH_CAP_XATTR_EXCL) {
- __ceph_build_xattrs_blob(ci);
+ old_blob = __ceph_build_xattrs_blob(ci);
arg.xattr_version = ci->i_xattrs.version;
arg.xattr_buf = ci->i_xattrs.blob;
} else {
@@ -1259,6 +1263,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
+
ret = send_cap_msg(&arg);
if (ret < 0) {
dout("error sending cap msg, must requeue %p\n", inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f2b722f0df5d..5999d806de78 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -730,6 +730,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
int issued = 0, implemented, new_issued;
struct timespec mtime, atime, ctime;
struct ceph_buffer *xattr_blob = NULL;
+ struct ceph_buffer *old_blob = NULL;
struct ceph_string *pool_ns = NULL;
struct ceph_cap *new_cap = NULL;
int err = 0;
@@ -788,7 +789,12 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
ci->i_version = le64_to_cpu(info->version);
inode->i_version++;
inode->i_rdev = le32_to_cpu(info->rdev);
- inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+ /* directories have fl_stripe_unit set to zero */
+ if (le32_to_cpu(info->layout.fl_stripe_unit))
+ inode->i_blkbits =
+ fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+ else
+ inode->i_blkbits = CEPH_BLOCK_SHIFT;
if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
(issued & CEPH_CAP_AUTH_EXCL) == 0) {
@@ -847,7 +853,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) &&
le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
if (ci->i_xattrs.blob)
- ceph_buffer_put(ci->i_xattrs.blob);
+ old_blob = ci->i_xattrs.blob;
ci->i_xattrs.blob = xattr_blob;
if (xattr_blob)
memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -993,8 +999,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
out:
if (new_cap)
ceph_put_cap(mdsc, new_cap);
- if (xattr_blob)
- ceph_buffer_put(xattr_blob);
+ ceph_buffer_put(old_blob);
+ ceph_buffer_put(xattr_blob);
ceph_put_string(pool_ns);
return err;
}
@@ -1341,6 +1347,7 @@ retry_lookup:
dout(" final dn %p\n", dn);
} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
req->r_op == CEPH_MDS_OP_MKSNAP) &&
+ test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
struct dentry *dn = req->r_dentry;
struct inode *dir = req->r_parent;
@@ -1624,7 +1631,6 @@ retry_lookup:
if (IS_ERR(realdn)) {
err = PTR_ERR(realdn);
d_drop(dn);
- dn = NULL;
goto next_item;
}
dn = realdn;
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index e7cce412f2cf..cb647c8c7b68 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -78,8 +78,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
req->r_wait_for_completion = ceph_lock_wait_for_completion;
err = ceph_mdsc_do_request(mdsc, inode, req);
-
- if (operation == CEPH_MDS_OP_GETFILELOCK) {
+ if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index e1ded4bd6115..b968334f841e 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3543,7 +3543,9 @@ static void delayed_work(struct work_struct *work)
pr_info("mds%d hung\n", s->s_mds);
}
}
- if (s->s_state < CEPH_MDS_SESSION_OPEN) {
+ if (s->s_state == CEPH_MDS_SESSION_NEW ||
+ s->s_state == CEPH_MDS_SESSION_RESTARTING ||
+ s->s_state == CEPH_MDS_SESSION_REJECTED) {
/* this mds is failed or recovering, just wait */
ceph_put_mds_session(s);
continue;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index a7e763dac038..29ed1688a1d3 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -460,6 +460,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
struct inode *inode = &ci->vfs_inode;
struct ceph_cap_snap *capsnap;
struct ceph_snap_context *old_snapc, *new_snapc;
+ struct ceph_buffer *old_blob = NULL;
int used, dirty;
capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
@@ -536,7 +537,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
capsnap->gid = inode->i_gid;
if (dirty & CEPH_CAP_XATTR_EXCL) {
- __ceph_build_xattrs_blob(ci);
+ old_blob = __ceph_build_xattrs_blob(ci);
capsnap->xattr_blob =
ceph_buffer_get(ci->i_xattrs.blob);
capsnap->xattr_version = ci->i_xattrs.version;
@@ -579,6 +580,7 @@ update_snapc:
}
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
kfree(capsnap);
ceph_put_snap_context(old_snapc);
}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index f0694293b31a..088c4488b449 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -232,6 +232,7 @@ static int parse_fsopt_token(char *c, void *private)
return -ENOMEM;
break;
case Opt_fscache_uniq:
+#ifdef CONFIG_CEPH_FSCACHE
kfree(fsopt->fscache_uniq);
fsopt->fscache_uniq = kstrndup(argstr[0].from,
argstr[0].to-argstr[0].from,
@@ -240,7 +241,10 @@ static int parse_fsopt_token(char *c, void *private)
return -ENOMEM;
fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
break;
- /* misc */
+#else
+ pr_err("fscache support is disabled\n");
+ return -EINVAL;
+#endif
case Opt_wsize:
if (intval < PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
return -EINVAL;
@@ -312,8 +316,13 @@ static int parse_fsopt_token(char *c, void *private)
fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
break;
case Opt_fscache:
+#ifdef CONFIG_CEPH_FSCACHE
fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
break;
+#else
+ pr_err("fscache support is disabled\n");
+ return -EINVAL;
+#endif
case Opt_nofscache:
fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
break;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3e27a28aa44a..46f600107cb5 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -517,7 +517,12 @@ static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
long long release_count,
long long ordered_count)
{
- smp_mb__before_atomic();
+ /*
+ * Makes sure operations that setup readdir cache (update page
+ * cache and i_size) are strongly ordered w.r.t. the following
+ * atomic64_set() operations.
+ */
+ smp_mb();
atomic64_set(&ci->i_complete_seq[0], release_count);
atomic64_set(&ci->i_complete_seq[1], ordered_count);
}
@@ -830,7 +835,7 @@ extern int ceph_getattr(const struct path *path, struct kstat *stat,
int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
-extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
+extern struct ceph_buffer *__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);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index e1c4e0b12b4c..3a166f860b6c 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -75,7 +75,7 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
const char *ns_field = " pool_namespace=";
char buf[128];
size_t len, total_len = 0;
- int ret;
+ ssize_t ret;
pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
@@ -99,11 +99,8 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
if (pool_ns)
total_len += strlen(ns_field) + pool_ns->len;
- if (!size) {
- ret = total_len;
- } else if (total_len > size) {
- ret = -ERANGE;
- } else {
+ ret = total_len;
+ if (size >= total_len) {
memcpy(val, buf, len);
ret = len;
if (pool_name) {
@@ -684,12 +681,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
/*
* If there are dirty xattrs, reencode xattrs into the prealloc_blob
- * and swap into place.
+ * and swap into place. It returns the old i_xattrs.blob (or NULL) so
+ * that it can be freed by the caller as the i_ceph_lock is likely to be
+ * held.
*/
-void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
{
struct rb_node *p;
struct ceph_inode_xattr *xattr = NULL;
+ struct ceph_buffer *old_blob = NULL;
void *dest;
dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
@@ -720,12 +720,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
if (ci->i_xattrs.blob)
- ceph_buffer_put(ci->i_xattrs.blob);
+ old_blob = ci->i_xattrs.blob;
ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = NULL;
ci->i_xattrs.dirty = false;
ci->i_xattrs.version++;
}
+
+ return old_blob;
}
static inline int __get_request_mask(struct inode *in) {
@@ -761,8 +763,11 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
if (err)
return err;
err = -ENODATA;
- if (!(vxattr->exists_cb && !vxattr->exists_cb(ci)))
+ if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
err = vxattr->getxattr_cb(ci, value, size);
+ if (size && size < err)
+ err = -ERANGE;
+ }
return err;
}
@@ -955,6 +960,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_cap_flush *prealloc_cf = NULL;
+ struct ceph_buffer *old_blob = NULL;
int issued;
int err;
int dirty = 0;
@@ -1023,13 +1029,15 @@ retry:
struct ceph_buffer *blob;
spin_unlock(&ci->i_ceph_lock);
- dout(" preaallocating new blob size=%d\n", required_blob_size);
+ ceph_buffer_put(old_blob); /* Shouldn't be required */
+ dout(" pre-allocating 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);
+ /* prealloc_blob can't be released while holding i_ceph_lock */
if (ci->i_xattrs.prealloc_blob)
- ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+ old_blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = blob;
goto retry;
}
@@ -1045,6 +1053,7 @@ retry:
}
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
if (lock_snap_rwsem)
up_read(&mdsc->snap_rwsem);
if (dirty)
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-19 03:17:33 +0000