aboutsummaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/acl.c17
-rw-r--r--fs/ceph/addr.c23
-rw-r--r--fs/ceph/cache.c1
-rw-r--r--fs/ceph/cache.h10
-rw-r--r--fs/ceph/caps.c257
-rw-r--r--fs/ceph/debugfs.c11
-rw-r--r--fs/ceph/dir.c109
-rw-r--r--fs/ceph/export.c267
-rw-r--r--fs/ceph/file.c203
-rw-r--r--fs/ceph/inode.c376
-rw-r--r--fs/ceph/ioctl.c11
-rw-r--r--fs/ceph/locks.c93
-rw-r--r--fs/ceph/mds_client.c112
-rw-r--r--fs/ceph/mds_client.h5
-rw-r--r--fs/ceph/mdsmap.c2
-rw-r--r--fs/ceph/strings.c1
-rw-r--r--fs/ceph/super.c33
-rw-r--r--fs/ceph/super.h24
-rw-r--r--fs/ceph/xattr.c102
19 files changed, 920 insertions, 737 deletions
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 4c2d452c4bf..469f2e8657e 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -54,11 +54,6 @@ static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode,
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;
@@ -109,12 +104,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
struct dentry *dentry;
- if (acl) {
- ret = posix_acl_valid(acl);
- if (ret < 0)
- goto out;
- }
-
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
@@ -160,11 +149,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
goto out_dput;
}
- if (value)
- ret = __ceph_setxattr(dentry, name, value, size, 0);
- else
- ret = __ceph_removexattr(dentry, name);
-
+ ret = __ceph_setxattr(dentry, name, value, size, 0);
if (ret) {
if (new_mode != old_mode) {
newattrs.ia_mode = old_mode;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b53278c9fd9..90b3954d48e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -211,18 +211,15 @@ static int readpage_nounlock(struct file *filp, struct page *page)
SetPageError(page);
ceph_fscache_readpage_cancel(inode, page);
goto out;
- } else {
- if (err < PAGE_CACHE_SIZE) {
- /* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
- } else {
- flush_dcache_page(page);
- }
}
- SetPageUptodate(page);
+ if (err < PAGE_CACHE_SIZE)
+ /* zero fill remainder of page */
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ else
+ flush_dcache_page(page);
- if (err >= 0)
- ceph_readpage_to_fscache(inode, page);
+ SetPageUptodate(page);
+ ceph_readpage_to_fscache(inode, page);
out:
return err < 0 ? err : 0;
@@ -694,7 +691,7 @@ static int ceph_writepages_start(struct address_space *mapping,
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
- pr_warning("writepage_start %p on forced umount\n", inode);
+ pr_warn("writepage_start %p on forced umount\n", inode);
return -EIO; /* we're in a forced umount, don't write! */
}
if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
@@ -1187,8 +1184,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
* never get called.
*/
static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
- const struct iovec *iov,
- loff_t pos, unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t pos)
{
WARN_ON(1);
return -EINVAL;
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 8c44fdd4e1c..834f9f3723f 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -205,6 +205,7 @@ void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
ci->fscache = fscache_acquire_cookie(fsc->fscache,
&ceph_fscache_inode_object_def,
ci, true);
+ fscache_check_consistency(ci->fscache);
done:
mutex_unlock(&inode->i_mutex);
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index da95f61b7a0..5ac591bd012 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -48,6 +48,12 @@ void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
void ceph_queue_revalidate(struct inode *inode);
+static inline void ceph_fscache_update_objectsize(struct inode *inode)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ fscache_attr_changed(ci->fscache);
+}
+
static inline void ceph_fscache_invalidate(struct inode *inode)
{
fscache_invalidate(ceph_inode(inode)->fscache);
@@ -135,6 +141,10 @@ static inline void ceph_readpage_to_fscache(struct inode *inode,
{
}
+static inline void ceph_fscache_update_objectsize(struct inode *inode)
+{
+}
+
static inline void ceph_fscache_invalidate(struct inode *inode)
{
}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 17543383545..1fde164b74b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -221,8 +221,8 @@ int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
return 0;
}
-static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc,
- struct ceph_cap_reservation *ctx)
+struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+ struct ceph_cap_reservation *ctx)
{
struct ceph_cap *cap = NULL;
@@ -508,15 +508,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
* it is < 0. (This is so we can atomically add the cap and add an
* open file reference to it.)
*/
-int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned seq, unsigned mseq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation)
+void ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ int fmode, unsigned issued, unsigned wanted,
+ unsigned seq, unsigned mseq, u64 realmino, int flags,
+ struct ceph_cap **new_cap)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_cap *new_cap = NULL;
struct ceph_cap *cap;
int mds = session->s_mds;
int actual_wanted;
@@ -531,20 +530,10 @@ int ceph_add_cap(struct inode *inode,
if (fmode >= 0)
wanted |= ceph_caps_for_mode(fmode);
-retry:
- spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
- if (new_cap) {
- cap = new_cap;
- new_cap = NULL;
- } else {
- spin_unlock(&ci->i_ceph_lock);
- new_cap = get_cap(mdsc, caps_reservation);
- if (new_cap == NULL)
- return -ENOMEM;
- goto retry;
- }
+ cap = *new_cap;
+ *new_cap = NULL;
cap->issued = 0;
cap->implemented = 0;
@@ -562,9 +551,6 @@ retry:
session->s_nr_caps++;
spin_unlock(&session->s_cap_lock);
} else {
- if (new_cap)
- ceph_put_cap(mdsc, new_cap);
-
/*
* auth mds of the inode changed. we received the cap export
* message, but still haven't received the cap import message.
@@ -622,9 +608,10 @@ retry:
if (flags & CEPH_CAP_FLAG_AUTH) {
if (ci->i_auth_cap == NULL ||
- ceph_seq_cmp(ci->i_auth_cap->mseq, mseq) < 0)
+ ceph_seq_cmp(ci->i_auth_cap->mseq, mseq) < 0) {
ci->i_auth_cap = cap;
- ci->i_cap_exporting_issued = 0;
+ cap->mds_wanted = wanted;
+ }
} else {
WARN_ON(ci->i_auth_cap == cap);
}
@@ -646,9 +633,6 @@ retry:
if (fmode >= 0)
__ceph_get_fmode(ci, fmode);
- spin_unlock(&ci->i_ceph_lock);
- wake_up_all(&ci->i_cap_wq);
- return 0;
}
/*
@@ -683,7 +667,7 @@ static int __cap_is_valid(struct ceph_cap *cap)
*/
int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
{
- int have = ci->i_snap_caps | ci->i_cap_exporting_issued;
+ int have = ci->i_snap_caps;
struct ceph_cap *cap;
struct rb_node *p;
@@ -885,7 +869,10 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
cap = rb_entry(p, struct ceph_cap, ci_node);
if (!__cap_is_valid(cap))
continue;
- mds_wanted |= cap->mds_wanted;
+ if (cap == ci->i_auth_cap)
+ mds_wanted |= cap->mds_wanted;
+ else
+ mds_wanted |= (cap->mds_wanted & ~CEPH_CAP_ANY_FILE_WR);
}
return mds_wanted;
}
@@ -895,7 +882,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
*/
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
- return !RB_EMPTY_ROOT(&ci->i_caps) || ci->i_cap_exporting_issued;
+ return !RB_EMPTY_ROOT(&ci->i_caps);
}
int ceph_is_any_caps(struct inode *inode)
@@ -2392,32 +2379,30 @@ static void invalidate_aliases(struct inode *inode)
* actually be a revocation if it specifies a smaller cap set.)
*
* caller holds s_mutex and i_ceph_lock, we drop both.
- *
- * return value:
- * 0 - ok
- * 1 - check_caps on auth cap only (writeback)
- * 2 - check_caps (ack revoke)
*/
-static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
+static void handle_cap_grant(struct ceph_mds_client *mdsc,
+ struct inode *inode, struct ceph_mds_caps *grant,
+ void *snaptrace, int snaptrace_len,
+ struct ceph_buffer *xattr_buf,
struct ceph_mds_session *session,
- struct ceph_cap *cap,
- struct ceph_buffer *xattr_buf)
- __releases(ci->i_ceph_lock)
+ struct ceph_cap *cap, int issued)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
int seq = le32_to_cpu(grant->seq);
int newcaps = le32_to_cpu(grant->caps);
- int issued, implemented, used, wanted, dirty;
+ int used, wanted, dirty;
u64 size = le64_to_cpu(grant->size);
u64 max_size = le64_to_cpu(grant->max_size);
struct timespec mtime, atime, ctime;
int check_caps = 0;
- int wake = 0;
- int writeback = 0;
- int queue_invalidate = 0;
- int deleted_inode = 0;
- int queue_revalidate = 0;
+ bool wake = 0;
+ bool writeback = 0;
+ bool queue_trunc = 0;
+ bool queue_invalidate = 0;
+ bool queue_revalidate = 0;
+ bool deleted_inode = 0;
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2461,16 +2446,13 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
}
/* side effects now are allowed */
-
- issued = __ceph_caps_issued(ci, &implemented);
- issued |= implemented | __ceph_caps_dirty(ci);
-
cap->cap_gen = session->s_cap_gen;
cap->seq = seq;
__check_cap_issue(ci, cap, newcaps);
- if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+ (issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
@@ -2479,7 +2461,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((issued & CEPH_CAP_LINK_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+ (issued & CEPH_CAP_LINK_EXCL) == 0) {
set_nlink(inode, le32_to_cpu(grant->nlink));
if (inode->i_nlink == 0 &&
(newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
@@ -2506,30 +2489,35 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
queue_revalidate = 1;
- /* size/ctime/mtime/atime? */
- ceph_fill_file_size(inode, issued,
- le32_to_cpu(grant->truncate_seq),
- le64_to_cpu(grant->truncate_size), size);
- ceph_decode_timespec(&mtime, &grant->mtime);
- ceph_decode_timespec(&atime, &grant->atime);
- ceph_decode_timespec(&ctime, &grant->ctime);
- ceph_fill_file_time(inode, issued,
- le32_to_cpu(grant->time_warp_seq), &ctime, &mtime,
- &atime);
-
-
- /* file layout may have changed */
- ci->i_layout = grant->layout;
-
- /* max size increase? */
- if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
- dout("max_size %lld -> %llu\n", ci->i_max_size, max_size);
- ci->i_max_size = max_size;
- if (max_size >= ci->i_wanted_max_size) {
- ci->i_wanted_max_size = 0; /* reset */
- ci->i_requested_max_size = 0;
+ if (newcaps & CEPH_CAP_ANY_RD) {
+ /* ctime/mtime/atime? */
+ ceph_decode_timespec(&mtime, &grant->mtime);
+ ceph_decode_timespec(&atime, &grant->atime);
+ ceph_decode_timespec(&ctime, &grant->ctime);
+ ceph_fill_file_time(inode, issued,
+ le32_to_cpu(grant->time_warp_seq),
+ &ctime, &mtime, &atime);
+ }
+
+ if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
+ /* file layout may have changed */
+ ci->i_layout = grant->layout;
+ /* size/truncate_seq? */
+ queue_trunc = ceph_fill_file_size(inode, issued,
+ le32_to_cpu(grant->truncate_seq),
+ le64_to_cpu(grant->truncate_size),
+ size);
+ /* max size increase? */
+ if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
+ dout("max_size %lld -> %llu\n",
+ ci->i_max_size, max_size);
+ ci->i_max_size = max_size;
+ if (max_size >= ci->i_wanted_max_size) {
+ ci->i_wanted_max_size = 0; /* reset */
+ ci->i_requested_max_size = 0;
+ }
+ wake = 1;
}
- wake = 1;
}
/* check cap bits */
@@ -2590,6 +2578,23 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
spin_unlock(&ci->i_ceph_lock);
+ if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+ down_write(&mdsc->snap_rwsem);
+ ceph_update_snap_trace(mdsc, snaptrace,
+ snaptrace + snaptrace_len, false);
+ downgrade_write(&mdsc->snap_rwsem);
+ kick_flushing_inode_caps(mdsc, session, inode);
+ up_read(&mdsc->snap_rwsem);
+ if (newcaps & ~issued)
+ wake = 1;
+ }
+
+ if (queue_trunc) {
+ ceph_queue_vmtruncate(inode);
+ ceph_queue_revalidate(inode);
+ } else if (queue_revalidate)
+ ceph_queue_revalidate(inode);
+
if (writeback)
/*
* queue inode for writeback: we can't actually call
@@ -2601,8 +2606,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
ceph_queue_invalidate(inode);
if (deleted_inode)
invalidate_aliases(inode);
- if (queue_revalidate)
- ceph_queue_revalidate(inode);
if (wake)
wake_up_all(&ci->i_cap_wq);
@@ -2779,7 +2782,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_session *tsession = NULL;
- struct ceph_cap *cap, *tcap;
+ struct ceph_cap *cap, *tcap, *new_cap = NULL;
struct ceph_inode_info *ci = ceph_inode(inode);
u64 t_cap_id;
unsigned mseq = le32_to_cpu(ex->migrate_seq);
@@ -2802,7 +2805,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
retry:
spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
- if (!cap)
+ if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
goto out_unlock;
if (target < 0) {
@@ -2841,15 +2844,14 @@ retry:
}
__ceph_remove_cap(cap, false);
goto out_unlock;
- }
-
- if (tsession) {
- int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
- spin_unlock(&ci->i_ceph_lock);
+ } else if (tsession) {
/* add placeholder for the export tagert */
+ int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
- t_seq - 1, t_mseq, (u64)-1, flag, NULL);
- goto retry;
+ t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
+
+ __ceph_remove_cap(cap, false);
+ goto out_unlock;
}
spin_unlock(&ci->i_ceph_lock);
@@ -2868,6 +2870,7 @@ retry:
SINGLE_DEPTH_NESTING);
}
ceph_add_cap_releases(mdsc, tsession);
+ new_cap = ceph_get_cap(mdsc, NULL);
} else {
WARN_ON(1);
tsession = NULL;
@@ -2882,24 +2885,27 @@ out_unlock:
mutex_unlock(&tsession->s_mutex);
ceph_put_mds_session(tsession);
}
+ if (new_cap)
+ ceph_put_cap(mdsc, new_cap);
}
/*
- * Handle cap IMPORT. If there are temp bits from an older EXPORT,
- * clean them up.
+ * Handle cap IMPORT.
*
- * caller holds s_mutex.
+ * caller holds s_mutex. acquires i_ceph_lock
*/
static void handle_cap_import(struct ceph_mds_client *mdsc,
struct inode *inode, struct ceph_mds_caps *im,
struct ceph_mds_cap_peer *ph,
struct ceph_mds_session *session,
- void *snaptrace, int snaptrace_len)
+ struct ceph_cap **target_cap, int *old_issued)
+ __acquires(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_cap *cap;
+ struct ceph_cap *cap, *ocap, *new_cap = NULL;
int mds = session->s_mds;
- unsigned issued = le32_to_cpu(im->caps);
+ int issued;
+ unsigned caps = le32_to_cpu(im->caps);
unsigned wanted = le32_to_cpu(im->wanted);
unsigned seq = le32_to_cpu(im->seq);
unsigned mseq = le32_to_cpu(im->migrate_seq);
@@ -2919,40 +2925,52 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
inode, ci, mds, mseq, peer);
+retry:
spin_lock(&ci->i_ceph_lock);
- cap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
- if (cap && cap->cap_id == p_cap_id) {
+ cap = __get_cap_for_mds(ci, mds);
+ if (!cap) {
+ if (!new_cap) {
+ spin_unlock(&ci->i_ceph_lock);
+ new_cap = ceph_get_cap(mdsc, NULL);
+ goto retry;
+ }
+ cap = new_cap;
+ } else {
+ if (new_cap) {
+ ceph_put_cap(mdsc, new_cap);
+ new_cap = NULL;
+ }
+ }
+
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+
+ ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+ realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
+
+ ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
+ if (ocap && ocap->cap_id == p_cap_id) {
dout(" remove export cap %p mds%d flags %d\n",
- cap, peer, ph->flags);
+ ocap, peer, ph->flags);
if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
- (cap->seq != le32_to_cpu(ph->seq) ||
- cap->mseq != le32_to_cpu(ph->mseq))) {
+ (ocap->seq != le32_to_cpu(ph->seq) ||
+ ocap->mseq != le32_to_cpu(ph->mseq))) {
pr_err("handle_cap_import: mismatched seq/mseq: "
"ino (%llx.%llx) mds%d seq %d mseq %d "
"importer mds%d has peer seq %d mseq %d\n",
- ceph_vinop(inode), peer, cap->seq,
- cap->mseq, mds, le32_to_cpu(ph->seq),
+ ceph_vinop(inode), peer, ocap->seq,
+ ocap->mseq, mds, le32_to_cpu(ph->seq),
le32_to_cpu(ph->mseq));
}
- ci->i_cap_exporting_issued = cap->issued;
- __ceph_remove_cap(cap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
+ __ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
}
/* make sure we re-request max_size, if necessary */
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
- spin_unlock(&ci->i_ceph_lock);
-
- down_write(&mdsc->snap_rwsem);
- ceph_update_snap_trace(mdsc, snaptrace, snaptrace+snaptrace_len,
- false);
- downgrade_write(&mdsc->snap_rwsem);
- ceph_add_cap(inode, session, cap_id, -1,
- issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
- NULL /* no caps context */);
- kick_flushing_inode_caps(mdsc, session, inode);
- up_read(&mdsc->snap_rwsem);
+ *old_issued = issued;
+ *target_cap = cap;
}
/*
@@ -2972,7 +2990,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_mds_caps *h;
struct ceph_mds_cap_peer *peer = NULL;
int mds = session->s_mds;
- int op;
+ int op, issued;
u32 seq, mseq;
struct ceph_vino vino;
u64 cap_id;
@@ -3064,7 +3082,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
case CEPH_CAP_OP_IMPORT:
handle_cap_import(mdsc, inode, h, peer, session,
- snaptrace, snaptrace_len);
+ &cap, &issued);
+ handle_cap_grant(mdsc, inode, h, snaptrace, snaptrace_len,
+ msg->middle, session, cap, issued);
+ goto done_unlocked;
}
/* the rest require a cap */
@@ -3081,8 +3102,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
switch (op) {
case CEPH_CAP_OP_REVOKE:
case CEPH_CAP_OP_GRANT:
- case CEPH_CAP_OP_IMPORT:
- handle_cap_grant(inode, h, session, cap, msg->middle);
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+ handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle,
+ session, cap, issued);
goto done_unlocked;
case CEPH_CAP_OP_FLUSH_ACK:
@@ -3256,7 +3279,7 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
rel->seq = cpu_to_le32(cap->seq);
rel->issue_seq = cpu_to_le32(cap->issue_seq),
rel->mseq = cpu_to_le32(cap->mseq);
- rel->caps = cpu_to_le32(cap->issued);
+ rel->caps = cpu_to_le32(cap->implemented);
rel->wanted = cpu_to_le32(cap->mds_wanted);
rel->dname_len = 0;
rel->dname_seq = 0;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6d59006bfa2..5a743ac141a 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -71,9 +71,9 @@ static int mdsc_show(struct seq_file *s, void *p)
seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
if (req->r_got_unsafe)
- seq_printf(s, "\t(unsafe)");
+ seq_puts(s, "\t(unsafe)");
else
- seq_printf(s, "\t");
+ seq_puts(s, "\t");
if (req->r_inode) {
seq_printf(s, " #%llx", ceph_ino(req->r_inode));
@@ -93,6 +93,8 @@ static int mdsc_show(struct seq_file *s, void *p)
} else if (req->r_path1) {
seq_printf(s, " #%llx/%s", req->r_ino1.ino,
req->r_path1);
+ } else {
+ seq_printf(s, " #%llx", req->r_ino1.ino);
}
if (req->r_old_dentry) {
@@ -102,7 +104,8 @@ static int mdsc_show(struct seq_file *s, void *p)
path = NULL;
spin_lock(&req->r_old_dentry->d_lock);
seq_printf(s, " #%llx/%.*s (%s)",
- ceph_ino(req->r_old_dentry_dir),
+ req->r_old_dentry_dir ?
+ ceph_ino(req->r_old_dentry_dir) : 0,
req->r_old_dentry->d_name.len,
req->r_old_dentry->d_name.name,
path ? path : "");
@@ -116,7 +119,7 @@ static int mdsc_show(struct seq_file *s, void *p)
seq_printf(s, " %s", req->r_path2);
}
- seq_printf(s, "\n");
+ seq_puts(s, "\n");
}
mutex_unlock(&mdsc->mutex);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6da4df84ba3..c29d6ae6887 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p)
return p & 0xffffffff;
}
+static int fpos_cmp(loff_t l, loff_t r)
+{
+ int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
+ if (v)
+ return v;
+ return (int)(fpos_off(l) - fpos_off(r));
+}
+
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
@@ -111,7 +119,8 @@ static unsigned fpos_off(loff_t p)
* defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
* the MDS if/when the directory is modified).
*/
-static int __dcache_readdir(struct file *file, struct dir_context *ctx)
+static int __dcache_readdir(struct file *file, struct dir_context *ctx,
+ u32 shared_gen)
{
struct ceph_file_info *fi = file->private_data;
struct dentry *parent = file->f_dentry;
@@ -125,14 +134,14 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx)
last = fi->dentry;
fi->dentry = NULL;
- dout("__dcache_readdir %p at %llu (last %p)\n", dir, ctx->pos,
- last);
+ dout("__dcache_readdir %p v%u at %llu (last %p)\n",
+ dir, shared_gen, ctx->pos, last);
spin_lock(&parent->d_lock);
/* start at beginning? */
if (ctx->pos == 2 || last == NULL ||
- ctx->pos < ceph_dentry(last)->offset) {
+ fpos_cmp(ctx->pos, ceph_dentry(last)->offset) < 0) {
if (list_empty(&parent->d_subdirs))
goto out_unlock;
p = parent->d_subdirs.prev;
@@ -153,10 +162,11 @@ more:
goto out_unlock;
}
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- if (!d_unhashed(dentry) && dentry->d_inode &&
+ if (di->lease_shared_gen == shared_gen &&
+ !d_unhashed(dentry) && dentry->d_inode &&
ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
- ctx->pos <= di->offset)
+ fpos_cmp(ctx->pos, di->offset) <= 0)
break;
dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
dentry->d_name.len, dentry->d_name.name, di->offset,
@@ -172,9 +182,16 @@ more:
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
+ /* make sure a dentry wasn't dropped while we didn't have parent lock */
+ if (!ceph_dir_is_complete(dir)) {
+ dout(" lost dir complete on %p; falling back to mds\n", dir);
+ dput(dentry);
+ err = -EAGAIN;
+ goto out;
+ }
+
dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, ctx->pos,
dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
- ctx->pos = di->offset;
if (!dir_emit(ctx, dentry->d_name.name,
dentry->d_name.len,
ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino),
@@ -182,25 +199,18 @@ more:
if (last) {
/* remember our position */
fi->dentry = last;
- fi->next_offset = di->offset;
+ fi->next_offset = fpos_off(di->offset);
}
dput(dentry);
return 0;
}
+ ctx->pos = di->offset + 1;
+
if (last)
dput(last);
last = dentry;
- ctx->pos++;
-
- /* make sure a dentry wasn't dropped while we didn't have parent lock */
- if (!ceph_dir_is_complete(dir)) {
- dout(" lost dir complete on %p; falling back to mds\n", dir);
- err = -EAGAIN;
- goto out;
- }
-
spin_lock(&parent->d_lock);
p = p->prev; /* advance to next dentry */
goto more;
@@ -244,8 +254,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
int err;
u32 ftype;
struct ceph_mds_reply_info_parsed *rinfo;
- const int max_entries = fsc->mount_options->max_readdir;
- const int max_bytes = fsc->mount_options->max_readdir_bytes;
dout("readdir %p file %p frag %u off %u\n", inode, file, frag, off);
if (fi->flags & CEPH_F_ATEND)
@@ -283,10 +291,13 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
ceph_snap(inode) != CEPH_SNAPDIR &&
__ceph_dir_is_complete(ci) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
+ u32 shared_gen = ci->i_shared_gen;
spin_unlock(&ci->i_ceph_lock);
- err = __dcache_readdir(file, ctx);
+ err = __dcache_readdir(file, ctx, shared_gen);
if (err != -EAGAIN)
return err;
+ frag = fpos_frag(ctx->pos);
+ off = fpos_off(ctx->pos);
} else {
spin_unlock(&ci->i_ceph_lock);
}
@@ -314,14 +325,16 @@ more:
fi->last_readdir = NULL;
}
- /* requery frag tree, as the frag topology may have changed */
- frag = ceph_choose_frag(ceph_inode(inode), frag, NULL, NULL);
-
dout("readdir fetching %llx.%llx frag %x offset '%s'\n",
ceph_vinop(inode), frag, fi->last_name);
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
+ err = ceph_alloc_readdir_reply_buffer(req, inode);
+ if (err) {
+ ceph_mdsc_put_request(req);
+ return err;
+ }
req->r_inode = inode;
ihold(inode);
req->r_dentry = dget(file->f_dentry);
@@ -332,9 +345,6 @@ more:
req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
req->r_readdir_offset = fi->next_offset;
req->r_args.readdir.frag = cpu_to_le32(frag);
- req->r_args.readdir.max_entries = cpu_to_le32(max_entries);
- req->r_args.readdir.max_bytes = cpu_to_le32(max_bytes);
- req->r_num_caps = max_entries + 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err < 0) {
ceph_mdsc_put_request(req);
@@ -361,9 +371,9 @@ more:
fi->next_offset = 0;
off = fi->next_offset;
}
+ fi->frag = frag;
fi->offset = fi->next_offset;
fi->last_readdir = req;
- fi->frag = frag;
if (req->r_reply_info.dir_end) {
kfree(fi->last_name);
@@ -438,7 +448,6 @@ more:
if (atomic_read(&ci->i_release_count) == fi->dir_release_count) {
dout(" marking %p complete\n", inode);
__ceph_dir_set_complete(ci, fi->dir_release_count);
- ci->i_max_offset = ctx->pos;
}
spin_unlock(&ci->i_ceph_lock);
@@ -446,7 +455,7 @@ more:
return 0;
}
-static void reset_readdir(struct ceph_file_info *fi)
+static void reset_readdir(struct ceph_file_info *fi, unsigned frag)
{
if (fi->last_readdir) {
ceph_mdsc_put_request(fi->last_readdir);
@@ -454,7 +463,10 @@ static void reset_readdir(struct ceph_file_info *fi)
}
kfree(fi->last_name);
fi->last_name = NULL;
- fi->next_offset = 2; /* compensate for . and .. */
+ if (ceph_frag_is_leftmost(frag))
+ fi->next_offset = 2; /* compensate for . and .. */
+ else
+ fi->next_offset = 0;
if (fi->dentry) {
dput(fi->dentry);
fi->dentry = NULL;
@@ -466,7 +478,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
{
struct ceph_file_info *fi = file->private_data;
struct inode *inode = file->f_mapping->host;
- loff_t old_offset = offset;
+ loff_t old_offset = ceph_make_fpos(fi->frag, fi->next_offset);
loff_t retval;
mutex_lock(&inode->i_mutex);
@@ -483,7 +495,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
goto out;
}
- if (offset >= 0 && offset <= inode->i_sb->s_maxbytes) {
+ if (offset >= 0) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
@@ -496,14 +508,14 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
* seek to new frag, or seek prior to current chunk.
*/
if (offset == 0 ||
- fpos_frag(offset) != fpos_frag(old_offset) ||
+ fpos_frag(offset) != fi->frag ||
fpos_off(offset) < fi->offset) {
dout("dir_llseek dropping %p content\n", file);
- reset_readdir(fi);
+ reset_readdir(fi, fpos_frag(offset));
}
/* bump dir_release_count if we did a forward seek */
- if (offset > old_offset)
+ if (fpos_cmp(offset, old_offset) > 0)
fi->dir_release_count--;
}
out:
@@ -695,9 +707,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
ceph_mdsc_put_request(req);
if (!err)
- err = ceph_init_acl(dentry, dentry->d_inode, dir);
-
- if (err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -735,7 +746,9 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
- if (err)
+ if (!err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -776,7 +789,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
out:
- if (err < 0)
+ if (!err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -801,8 +816,7 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
}
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
- req->r_old_dentry = dget(old_dentry); /* or inode? hrm. */
- req->r_old_dentry_dir = ceph_get_dentry_parent_inode(old_dentry);
+ req->r_old_dentry = dget(old_dentry);
req->r_locked_dir = dir;
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
@@ -900,10 +914,11 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RENAME, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
+ ihold(old_dir);
req->r_dentry = dget(new_dentry);
req->r_num_caps = 2;
req->r_old_dentry = dget(old_dentry);
- req->r_old_dentry_dir = ceph_get_dentry_parent_inode(old_dentry);
+ req->r_old_dentry_dir = old_dir;
req->r_locked_dir = new_dir;
req->r_old_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_old_dentry_unless = CEPH_CAP_FILE_EXCL;
@@ -921,14 +936,16 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
* to do it here.
*/
- /* d_move screws up d_subdirs order */
- ceph_dir_clear_complete(new_dir);
-
d_move(old_dentry, new_dentry);
/* ensure target dentry is invalidated, despite
rehashing bug in vfs_rename_dir */
ceph_invalidate_dentry_lease(new_dentry);
+
+ /* d_move screws up sibling dentries' offsets */
+ ceph_dir_clear_complete(old_dir);
+ ceph_dir_clear_complete(new_dir);
+
}
ceph_mdsc_put_request(req);
return err;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 16796be53ca..8d7d782f438 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -8,23 +8,6 @@
#include "mds_client.h"
/*
- * NFS export support
- *
- * NFS re-export of a ceph mount is, at present, only semireliable.
- * The basic issue is that the Ceph architectures doesn't lend itself
- * well to generating filehandles that will remain valid forever.
- *
- * So, we do our best. If you're lucky, your inode will be in the
- * client's cache. If it's not, and you have a connectable fh, then
- * the MDS server may be able to find it for you. Otherwise, you get
- * ESTALE.
- *
- * There are ways to this more reliable, but in the non-connectable fh
- * case, we won't every work perfectly, and in the connectable case,
- * some changes are needed on the MDS side to work better.
- */
-
-/*
* Basic fh
*/
struct ceph_nfs_fh {
@@ -32,22 +15,12 @@ struct ceph_nfs_fh {
} __attribute__ ((packed));
/*
- * Larger 'connectable' fh that includes parent ino and name hash.
- * Use this whenever possible, as it works more reliably.
+ * Larger fh that includes parent ino.
*/
struct ceph_nfs_confh {
u64 ino, parent_ino;
- u32 parent_name_hash;
} __attribute__ ((packed));
-/*
- * The presence of @parent_inode here tells us whether NFS wants a
- * connectable file handle. However, we want to make a connectionable
- * file handle unconditionally so that the MDS gets as much of a hint
- * as possible. That means we only use @parent_dentry to indicate
- * whether nfsd wants a connectable fh, and whether we should indicate
- * failure from a too-small @max_len.
- */
static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
struct inode *parent_inode)
{
@@ -56,54 +29,36 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
struct ceph_nfs_confh *cfh = (void *)rawfh;
int connected_handle_length = sizeof(*cfh)/4;
int handle_length = sizeof(*fh)/4;
- struct dentry *dentry;
- struct dentry *parent;
/* don't re-export snaps */
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EINVAL;
- dentry = d_find_alias(inode);
+ if (parent_inode && (*max_len < connected_handle_length)) {
+ *max_len = connected_handle_length;
+ return FILEID_INVALID;
+ } else if (*max_len < handle_length) {
+ *max_len = handle_length;
+ return FILEID_INVALID;
+ }
- /* if we found an alias, generate a connectable fh */
- if (*max_len >= connected_handle_length && dentry) {
- dout("encode_fh %p connectable\n", dentry);
- spin_lock(&dentry->d_lock);
- parent = dentry->d_parent;
+ if (parent_inode) {
+ dout("encode_fh %llx with parent %llx\n",
+ ceph_ino(inode), ceph_ino(parent_inode));
cfh->ino = ceph_ino(inode);
- cfh->parent_ino = ceph_ino(parent->d_inode);
- cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode,
- dentry);
+ cfh->parent_ino = ceph_ino(parent_inode);
*max_len = connected_handle_length;
- type = 2;
- spin_unlock(&dentry->d_lock);
- } else if (*max_len >= handle_length) {
- if (parent_inode) {
- /* nfsd wants connectable */
- *max_len = connected_handle_length;
- type = FILEID_INVALID;
- } else {
- dout("encode_fh %p\n", dentry);
- fh->ino = ceph_ino(inode);
- *max_len = handle_length;
- type = 1;
- }
+ type = FILEID_INO32_GEN_PARENT;
} else {
+ dout("encode_fh %llx\n", ceph_ino(inode));
+ fh->ino = ceph_ino(inode);
*max_len = handle_length;
- type = FILEID_INVALID;
+ type = FILEID_INO32_GEN;
}
- if (dentry)
- dput(dentry);
return type;
}
-/*
- * convert regular fh to dentry
- *
- * FIXME: we should try harder by querying the mds for the ino.
- */
-static struct dentry *__fh_to_dentry(struct super_block *sb,
- struct ceph_nfs_fh *fh, int fh_len)
+static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct inode *inode;
@@ -111,11 +66,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
struct ceph_vino vino;
int err;
- if (fh_len < sizeof(*fh) / 4)
- return ERR_PTR(-ESTALE);
-
- dout("__fh_to_dentry %llx\n", fh->ino);
- vino.ino = fh->ino;
+ vino.ino = ino;
vino.snap = CEPH_NOSNAP;
inode = ceph_find_inode(sb, vino);
if (!inode) {
@@ -139,139 +90,161 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
dentry = d_obtain_alias(inode);
if (IS_ERR(dentry)) {
- pr_err("fh_to_dentry %llx -- inode %p but ENOMEM\n",
- fh->ino, inode);
iput(inode);
return dentry;
}
err = ceph_init_dentry(dentry);
if (err < 0) {
- iput(inode);
+ dput(dentry);
return ERR_PTR(err);
}
- dout("__fh_to_dentry %llx %p dentry %p\n", fh->ino, inode, dentry);
+ dout("__fh_to_dentry %llx %p dentry %p\n", ino, inode, dentry);
return dentry;
}
/*
- * convert connectable fh to dentry
+ * convert regular fh to dentry
*/
-static struct dentry *__cfh_to_dentry(struct super_block *sb,
- struct ceph_nfs_confh *cfh, int fh_len)
+static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
+ struct fid *fid,
+ int fh_len, int fh_type)
+{
+ struct ceph_nfs_fh *fh = (void *)fid->raw;
+
+ if (fh_type != FILEID_INO32_GEN &&
+ fh_type != FILEID_INO32_GEN_PARENT)
+ return NULL;
+ if (fh_len < sizeof(*fh) / 4)
+ return NULL;
+
+ dout("fh_to_dentry %llx\n", fh->ino);
+ return __fh_to_dentry(sb, fh->ino);
+}
+
+static struct dentry *__get_parent(struct super_block *sb,
+ struct dentry *child, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+ struct ceph_mds_request *req;
struct inode *inode;
struct dentry *dentry;
- struct ceph_vino vino;
int err;
- if (fh_len < sizeof(*cfh) / 4)
- return ERR_PTR(-ESTALE);
-
- dout("__cfh_to_dentry %llx (%llx/%x)\n",
- cfh->ino, cfh->parent_ino, cfh->parent_name_hash);
-
- vino.ino = cfh->ino;
- vino.snap = CEPH_NOSNAP;
- inode = ceph_find_inode(sb, vino);
- if (!inode) {
- struct ceph_mds_request *req;
-
- req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPHASH,
- USE_ANY_MDS);
- if (IS_ERR(req))
- return ERR_CAST(req);
+ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
+ USE_ANY_MDS);
+ if (IS_ERR(req))
+ return ERR_CAST(req);
- req->r_ino1 = vino;
- req->r_ino2.ino = cfh->parent_ino;
- req->r_ino2.snap = CEPH_NOSNAP;
- req->r_path2 = kmalloc(16, GFP_NOFS);
- snprintf(req->r_path2, 16, "%d", cfh->parent_name_hash);
- req->r_num_caps = 1;
- err = ceph_mdsc_do_request(mdsc, NULL, req);
- inode = req->r_target_inode;
- if (inode)
- ihold(inode);
- ceph_mdsc_put_request(req);
- if (!inode)
- return ERR_PTR(err ? err : -ESTALE);
+ if (child) {
+ req->r_inode = child->d_inode;
+ ihold(child->d_inode);
+ } else {
+ req->r_ino1 = (struct ceph_vino) {
+ .ino = ino,
+ .snap = CEPH_NOSNAP,
+ };
}
+ req->r_num_caps = 1;
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
+ inode = req->r_target_inode;
+ if (inode)
+ ihold(inode);
+ ceph_mdsc_put_request(req);
+ if (!inode)
+ return ERR_PTR(-ENOENT);
dentry = d_obtain_alias(inode);
if (IS_ERR(dentry)) {
- pr_err("cfh_to_dentry %llx -- inode %p but ENOMEM\n",
- cfh->ino, inode);
iput(inode);
return dentry;
}
err = ceph_init_dentry(dentry);
if (err < 0) {
- iput(inode);
+ dput(dentry);
return ERR_PTR(err);
}
- dout("__cfh_to_dentry %llx %p dentry %p\n", cfh->ino, inode, dentry);
+ dout("__get_parent ino %llx parent %p ino %llx.%llx\n",
+ child ? ceph_ino(child->d_inode) : ino,
+ dentry, ceph_vinop(inode));
return dentry;
}
-static struct dentry *ceph_fh_to_dentry(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type)
+static struct dentry *ceph_get_parent(struct dentry *child)
{
- if (fh_type == 1)
- return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw,
- fh_len);
- else
- return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw,
- fh_len);
+ /* don't re-export snaps */
+ if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
+ return ERR_PTR(-EINVAL);
+
+ dout("get_parent %p ino %llx.%llx\n",
+ child, ceph_vinop(child->d_inode));
+ return __get_parent(child->d_sb, child, 0);
}
/*
- * get parent, if possible.
- *
- * FIXME: we could do better by querying the mds to discover the
- * parent.
+ * convert regular fh to parent
*/
static struct dentry *ceph_fh_to_parent(struct super_block *sb,
- struct fid *fid,
+ struct fid *fid,
int fh_len, int fh_type)
{
struct ceph_nfs_confh *cfh = (void *)fid->raw;
- struct ceph_vino vino;
- struct inode *inode;
struct dentry *dentry;
- int err;
- if (fh_type == 1)
- return ERR_PTR(-ESTALE);
+ if (fh_type != FILEID_INO32_GEN_PARENT)
+ return NULL;
if (fh_len < sizeof(*cfh) / 4)
- return ERR_PTR(-ESTALE);
+ return NULL;
- pr_debug("fh_to_parent %llx/%d\n", cfh->parent_ino,
- cfh->parent_name_hash);
+ dout("fh_to_parent %llx\n", cfh->parent_ino);
+ dentry = __get_parent(sb, NULL, cfh->ino);
+ if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT)
+ dentry = __fh_to_dentry(sb, cfh->parent_ino);
+ return dentry;
+}
- vino.ino = cfh->ino;
- vino.snap = CEPH_NOSNAP;
- inode = ceph_find_inode(sb, vino);
- if (!inode)
- return ERR_PTR(-ESTALE);
+static int ceph_get_name(struct dentry *parent, char *name,
+ struct dentry *child)
+{
+ struct ceph_mds_client *mdsc;
+ struct ceph_mds_request *req;
+ int err;
- dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- pr_err("fh_to_parent %llx -- inode %p but ENOMEM\n",
- cfh->ino, inode);
- iput(inode);
- return dentry;
- }
- err = ceph_init_dentry(dentry);
- if (err < 0) {
- iput(inode);
- return ERR_PTR(err);
+ mdsc = ceph_inode_to_client(child->d_inode)->mdsc;
+ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
+ USE_ANY_MDS);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ mutex_lock(&parent->d_inode->i_mutex);
+
+ req->r_inode = child->d_inode;
+ ihold(child->d_inode);
+ req->r_ino2 = ceph_vino(parent->d_inode);
+ req->r_locked_dir = parent->d_inode;
+ req->r_num_caps = 2;
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
+
+ mutex_unlock(&parent->d_inode->i_mutex);
+
+ if (!err) {
+ struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+ memcpy(name, rinfo->dname, rinfo->dname_len);
+ name[rinfo->dname_len] = 0;
+ dout("get_name %p ino %llx.%llx name %s\n",
+ child, ceph_vinop(child->d_inode), name);
+ } else {
+ dout("get_name %p ino %llx.%llx err %d\n",
+ child, ceph_vinop(child->d_inode), err);
}
- dout("fh_to_parent %llx %p dentry %p\n", cfh->ino, inode, dentry);
- return dentry;
+
+ ceph_mdsc_put_request(req);
+ return err;
}
const struct export_operations ceph_export_ops = {
.encode_fh = ceph_encode_fh,
.fh_to_dentry = ceph_fh_to_dentry,
.fh_to_parent = ceph_fh_to_parent,
+ .get_parent = ceph_get_parent,
+ .get_name = ceph_get_name,
};
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index dfd2ce3419f..302085100c2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -210,7 +210,7 @@ int ceph_open(struct inode *inode, struct file *file)
ihold(inode);
req->r_num_caps = 1;
- if (flags & (O_CREAT|O_TRUNC))
+ if (flags & O_CREAT)
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
iput(parent_inode);
@@ -286,12 +286,14 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+ ceph_init_acl(dentry, dentry->d_inode, dir);
*opened |= FILE_CREATED;
}
err = finish_open(file, dentry, ceph_open, opened);
}
-
out_err:
+ if (!req->r_err && req->r_target_inode)
+ ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
ceph_mdsc_put_request(req);
dout("atomic_open result=%d\n", err);
return err;
@@ -416,7 +418,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
struct page **pages;
u64 off = iocb->ki_pos;
int num_pages, ret;
- size_t len = i->count;
+ size_t len = iov_iter_count(i);
dout("sync_read on file %p %llu~%u %s\n", file, off,
(unsigned)len,
@@ -434,25 +436,26 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
if (file->f_flags & O_DIRECT) {
while (iov_iter_count(i)) {
- void __user *data = i->iov[0].iov_base + i->iov_offset;
- size_t len = i->iov[0].iov_len - i->iov_offset;
+ size_t start;
+ ssize_t n;
+
+ n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start);
+ if (n < 0)
+ return n;
- num_pages = calc_pages_for((unsigned long)data, len);
- pages = ceph_get_direct_page_vector(data,
- num_pages, true);
- if (IS_ERR(pages))
- return PTR_ERR(pages);
+ num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
- ret = striped_read(inode, off, len,
+ ret = striped_read(inode, off, n,
pages, num_pages, checkeof,
- 1, (unsigned long)data & ~PAGE_MASK);
+ 1, start);
+
ceph_put_page_vector(pages, num_pages, true);
if (ret <= 0)
break;
off += ret;
iov_iter_advance(i, ret);
- if (ret < len)
+ if (ret < n)
break;
}
} else {
@@ -464,25 +467,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
num_pages, checkeof, 0, 0);
if (ret > 0) {
int l, k = 0;
- size_t left = len = ret;
+ size_t left = ret;
while (left) {
- void __user *data = i->iov[0].iov_base
- + i->iov_offset;
- l = min(i->iov[0].iov_len - i->iov_offset,
- left);
-
- ret = ceph_copy_page_vector_to_user(&pages[k],
- data, off,
- l);
- if (ret > 0) {
- iov_iter_advance(i, ret);
- left -= ret;
- off += ret;
- k = calc_pages_for(iocb->ki_pos,
- len - left + 1) - 1;
- BUG_ON(k >= num_pages && left);
- } else
+ int copy = min_t(size_t, PAGE_SIZE, left);
+ l = copy_page_to_iter(pages[k++], 0, copy, i);
+ off += l;
+ left -= l;
+ if (l < copy)
break;
}
}
@@ -539,8 +531,7 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
* objects, rollback on failure, etc.)
*/
static ssize_t
-ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, size_t count)
+ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
@@ -554,11 +545,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
int written = 0;
int flags;
int check_caps = 0;
- int page_align;
int ret;
struct timespec mtime = CURRENT_TIME;
loff_t pos = iocb->ki_pos;
- struct iov_iter i;
+ size_t count = iov_iter_count(from);
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
@@ -580,13 +570,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
CEPH_OSD_FLAG_ONDISK |
CEPH_OSD_FLAG_WRITE;
- iov_iter_init(&i, iov, nr_segs, count, 0);
-
- while (iov_iter_count(&i) > 0) {
- void __user *data = i.iov->iov_base + i.iov_offset;
- u64 len = i.iov->iov_len - i.iov_offset;
-
- page_align = (unsigned long)data & ~PAGE_MASK;
+ while (iov_iter_count(from) > 0) {
+ u64 len = iov_iter_single_seg_count(from);
+ size_t start;
+ ssize_t n;
snapc = ci->i_snap_realm->cached_context;
vino = ceph_vino(inode);
@@ -599,23 +586,24 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
- goto out;
+ break;
}
- num_pages = calc_pages_for(page_align, len);
- pages = ceph_get_direct_page_vector(data, num_pages, false);
- if (IS_ERR(pages)) {
- ret = PTR_ERR(pages);
- goto out;
+ n = iov_iter_get_pages_alloc(from, &pages, len, &start);
+ if (unlikely(n < 0)) {
+ ret = n;
+ ceph_osdc_put_request(req);
+ break;
}
+ num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
/*
* throw out any page cache pages in this range. this
* may block.
*/
truncate_inode_pages_range(inode->i_mapping, pos,
- (pos+len) | (PAGE_CACHE_SIZE-1));
- osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
+ (pos+n) | (PAGE_CACHE_SIZE-1));
+ osd_req_op_extent_osd_data_pages(req, 0, pages, n, start,
false, false);
/* BUG_ON(vino.snap != CEPH_NOSNAP); */
@@ -627,22 +615,20 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
ceph_put_page_vector(pages, num_pages, false);
-out:
ceph_osdc_put_request(req);
- if (ret == 0) {
- pos += len;
- written += len;
- iov_iter_advance(&i, (size_t)len);
-
- if (pos > i_size_read(inode)) {
- check_caps = ceph_inode_set_size(inode, pos);
- if (check_caps)
- ceph_check_caps(ceph_inode(inode),
- CHECK_CAPS_AUTHONLY,
- NULL);
- }
- } else
+ if (ret)
break;
+ pos += n;
+ written += n;
+ iov_iter_advance(from, n);
+
+ if (pos > i_size_read(inode)) {
+ check_caps = ceph_inode_set_size(inode, pos);
+ if (check_caps)
+ ceph_check_caps(ceph_inode(inode),
+ CHECK_CAPS_AUTHONLY,
+ NULL);
+ }
}
if (ret != -EOLDSNAPC && written > 0) {
@@ -660,8 +646,7 @@ out:
* correct atomic write, we should e.g. take write locks on all
* objects, rollback on failure, etc.)
*/
-static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, size_t count)
+static ssize_t ceph_sync_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
@@ -679,7 +664,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
int ret;
struct timespec mtime = CURRENT_TIME;
loff_t pos = iocb->ki_pos;
- struct iov_iter i;
+ size_t count = iov_iter_count(from);
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
@@ -701,9 +686,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
CEPH_OSD_FLAG_WRITE |
CEPH_OSD_FLAG_ACK;
- iov_iter_init(&i, iov, nr_segs, count, 0);
-
- while ((len = iov_iter_count(&i)) > 0) {
+ while ((len = iov_iter_count(from)) > 0) {
size_t left;
int n;
@@ -717,7 +700,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
false);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
- goto out;
+ break;
}
/*
@@ -735,13 +718,12 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
left = len;
for (n = 0; n < num_pages; n++) {
size_t plen = min_t(size_t, left, PAGE_SIZE);
- ret = iov_iter_copy_from_user(pages[n], &i, 0, plen);
+ ret = copy_page_from_iter(pages[n], 0, plen, from);
if (ret != plen) {
ret = -EFAULT;
break;
}
left -= ret;
- iov_iter_advance(&i, ret);
}
if (ret < 0) {
@@ -794,8 +776,7 @@ out:
*
* Hmm, the sync read case isn't actually async... should it be?
*/
-static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *filp = iocb->ki_filp;
struct ceph_file_info *fi = filp->private_data;
@@ -821,40 +802,20 @@ again:
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_filp->f_flags & O_DIRECT) ||
(fi->flags & CEPH_F_SYNC)) {
- struct iov_iter i;
dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- if (!read) {
- ret = generic_segment_checks(iov, &nr_segs,
- &len, VERIFY_WRITE);
- if (ret)
- goto out;
- }
-
- iov_iter_init(&i, iov, nr_segs, len, read);
-
/* hmm, this isn't really async... */
- ret = ceph_sync_read(iocb, &i, &checkeof);
+ ret = ceph_sync_read(iocb, to, &checkeof);
} else {
- /*
- * We can't modify the content of iov,
- * so we only read from beginning.
- */
- if (read) {
- iocb->ki_pos = pos;
- len = iocb->ki_nbytes;
- read = 0;
- }
dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
- inode, ceph_vinop(inode), pos, (unsigned)len,
+ inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+ ret = generic_file_read_iter(iocb, to);
}
-out:
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
ceph_put_cap_refs(ci, got);
@@ -870,6 +831,7 @@ out:
", reading more\n", iocb->ki_pos,
inode->i_size);
+ iov_iter_advance(to, ret);
read += ret;
len -= ret;
checkeof = 0;
@@ -893,8 +855,7 @@ out:
*
* If we are near ENOSPC, write synchronously.
*/
-static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct ceph_file_info *fi = file->private_data;
@@ -902,18 +863,15 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
- ssize_t count, written = 0;
+ ssize_t count = iov_iter_count(from), written = 0;
int err, want, got;
+ loff_t pos = iocb->ki_pos;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
mutex_lock(&inode->i_mutex);
- err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
- if (err)
- goto out;
-
/* We can write back this queue in page reclaim */
current->backing_dev_info = file->f_mapping->backing_dev_info;
@@ -923,6 +881,7 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
if (count == 0)
goto out;
+ iov_iter_truncate(from, count);
err = file_remove_suid(file);
if (err)
@@ -954,21 +913,26 @@ retry_snap:
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+ struct iov_iter data;
mutex_unlock(&inode->i_mutex);
+ /* we might need to revert back to that point */
+ data = *from;
if (file->f_flags & O_DIRECT)
- written = ceph_sync_direct_write(iocb, iov,
- nr_segs, count);
+ written = ceph_sync_direct_write(iocb, &data);
else
- written = ceph_sync_write(iocb, iov, nr_segs, count);
+ written = ceph_sync_write(iocb, &data);
if (written == -EOLDSNAPC) {
dout("aio_write %p %llx.%llx %llu~%u"
"got EOLDSNAPC, retrying\n",
inode, ceph_vinop(inode),
- pos, (unsigned)iov->iov_len);
+ pos, (unsigned)count);
mutex_lock(&inode->i_mutex);
goto retry_snap;
}
+ if (written > 0)
+ iov_iter_advance(from, written);
} else {
+ loff_t old_size = inode->i_size;
/*
* No need to acquire the i_truncate_mutex. Because
* the MDS revokes Fwb caps before sending truncate
@@ -976,9 +940,11 @@ retry_snap:
* are pending vmtruncate. So write and vmtruncate
* can not run at the same time
*/
- written = generic_file_buffered_write(iocb, iov, nr_segs,
- pos, &iocb->ki_pos,
- count, 0);
+ written = generic_perform_write(file, from, pos);
+ if (likely(written >= 0))
+ iocb->ki_pos = pos + written;
+ if (inode->i_size > old_size)
+ ceph_fscache_update_objectsize(inode);
mutex_unlock(&inode->i_mutex);
}
@@ -992,7 +958,7 @@ retry_snap:
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
- inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
+ inode, ceph_vinop(inode), pos, (unsigned)count,
ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
@@ -1214,9 +1180,6 @@ static long ceph_fallocate(struct file *file, int mode,
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
- if (IS_SWAPFILE(inode))
- return -ETXTBSY;
-
mutex_lock(&inode->i_mutex);
if (ceph_snap(inode) != CEPH_NOSNAP) {
@@ -1272,16 +1235,16 @@ const struct file_operations ceph_file_fops = {
.open = ceph_open,
.release = ceph_release,
.llseek = ceph_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = ceph_aio_read,
- .aio_write = ceph_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = ceph_read_iter,
+ .write_iter = ceph_write_iter,
.mmap = ceph_mmap,
.fsync = ceph_fsync,
.lock = ceph_lock,
.flock = ceph_flock,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.unlocked_ioctl = ceph_ioctl,
.compat_ioctl = ceph_ioctl,
.fallocate = ceph_fallocate,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 32d519d8a2e..04c89c266ce 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -10,6 +10,7 @@
#include <linux/writeback.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl.h>
+#include <linux/random.h>
#include "super.h"
#include "mds_client.h"
@@ -179,9 +180,8 @@ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
* specified, copy the frag delegation info to the caller if
* it is present.
*/
-u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
- struct ceph_inode_frag *pfrag,
- int *found)
+static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+ struct ceph_inode_frag *pfrag, int *found)
{
u32 t = ceph_frag_make(0, 0);
struct ceph_inode_frag *frag;
@@ -191,7 +191,6 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
if (found)
*found = 0;
- mutex_lock(&ci->i_fragtree_mutex);
while (1) {
WARN_ON(!ceph_frag_contains_value(t, v));
frag = __ceph_find_frag(ci, t);
@@ -220,10 +219,19 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
}
dout("choose_frag(%x) = %x\n", v, t);
- mutex_unlock(&ci->i_fragtree_mutex);
return t;
}
+u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+ struct ceph_inode_frag *pfrag, int *found)
+{
+ u32 ret;
+ mutex_lock(&ci->i_fragtree_mutex);
+ ret = __ceph_choose_frag(ci, v, pfrag, found);
+ mutex_unlock(&ci->i_fragtree_mutex);
+ return ret;
+}
+
/*
* Process dirfrag (delegation) info from the mds. Include leaf
* fragment in tree ONLY if ndist > 0. Otherwise, only
@@ -237,11 +245,17 @@ static int ceph_fill_dirfrag(struct inode *inode,
u32 id = le32_to_cpu(dirinfo->frag);
int mds = le32_to_cpu(dirinfo->auth);
int ndist = le32_to_cpu(dirinfo->ndist);
+ int diri_auth = -1;
int i;
int err = 0;
+ spin_lock(&ci->i_ceph_lock);
+ if (ci->i_auth_cap)
+ diri_auth = ci->i_auth_cap->mds;
+ spin_unlock(&ci->i_ceph_lock);
+
mutex_lock(&ci->i_fragtree_mutex);
- if (ndist == 0) {
+ if (ndist == 0 && mds == diri_auth) {
/* no delegation info needed. */
frag = __ceph_find_frag(ci, id);
if (!frag)
@@ -286,6 +300,75 @@ out:
return err;
}
+static int ceph_fill_fragtree(struct inode *inode,
+ struct ceph_frag_tree_head *fragtree,
+ struct ceph_mds_reply_dirfrag *dirinfo)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_inode_frag *frag;
+ struct rb_node *rb_node;
+ int i;
+ u32 id, nsplits;
+ bool update = false;
+
+ mutex_lock(&ci->i_fragtree_mutex);
+ nsplits = le32_to_cpu(fragtree->nsplits);
+ if (nsplits) {
+ i = prandom_u32() % nsplits;
+ id = le32_to_cpu(fragtree->splits[i].frag);
+ if (!__ceph_find_frag(ci, id))
+ update = true;
+ } else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) {
+ rb_node = rb_first(&ci->i_fragtree);
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node))
+ update = true;
+ }
+ if (!update && dirinfo) {
+ id = le32_to_cpu(dirinfo->frag);
+ if (id != __ceph_choose_frag(ci, id, NULL, NULL))
+ update = true;
+ }
+ if (!update)
+ goto out_unlock;
+
+ dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
+ rb_node = rb_first(&ci->i_fragtree);
+ for (i = 0; i < nsplits; i++) {
+ id = le32_to_cpu(fragtree->splits[i].frag);
+ frag = NULL;
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (ceph_frag_compare(frag->frag, id) >= 0) {
+ if (frag->frag != id)
+ frag = NULL;
+ else
+ rb_node = rb_next(rb_node);
+ break;
+ }
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ frag = NULL;
+ }
+ if (!frag) {
+ frag = __get_or_create_frag(ci, id);
+ if (IS_ERR(frag))
+ continue;
+ }
+ frag->split_by = le32_to_cpu(fragtree->splits[i].by);
+ dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+ }
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ }
+out_unlock:
+ mutex_unlock(&ci->i_fragtree_mutex);
+ return 0;
+}
/*
* initialize a newly allocated inode.
@@ -341,7 +424,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ci->i_cap_snaps);
ci->i_head_snapc = NULL;
ci->i_snap_caps = 0;
- ci->i_cap_exporting_issued = 0;
for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
ci->i_nr_by_mode[i] = 0;
@@ -407,7 +489,7 @@ void ceph_destroy_inode(struct inode *inode)
/*
* we may still have a snap_realm reference if there are stray
- * caps in i_cap_exporting_issued or i_snap_caps.
+ * caps in i_snap_caps.
*/
if (ci->i_snap_realm) {
struct ceph_mds_client *mdsc =
@@ -582,22 +664,26 @@ static int fill_inode(struct inode *inode,
unsigned long ttl_from, int cap_fmode,
struct ceph_cap_reservation *caps_reservation)
{
+ struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_reply_inode *info = iinfo->in;
struct ceph_inode_info *ci = ceph_inode(inode);
- int i;
- int issued = 0, implemented;
+ int issued = 0, implemented, new_issued;
struct timespec mtime, atime, ctime;
- u32 nsplits;
- struct ceph_inode_frag *frag;
- struct rb_node *rb_node;
struct ceph_buffer *xattr_blob = NULL;
+ struct ceph_cap *new_cap = NULL;
int err = 0;
- int queue_trunc = 0;
+ bool wake = false;
+ bool queue_trunc = false;
+ bool new_version = false;
dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
+ /* prealloc new cap struct */
+ if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
+ new_cap = ceph_get_cap(mdsc, caps_reservation);
+
/*
* prealloc xattr data, if it looks like we'll need it. only
* if len > 4 (meaning there are actually xattrs; the first 4
@@ -623,19 +709,23 @@ static int fill_inode(struct inode *inode,
* 3 2 skip
* 3 3 update
*/
- if (le64_to_cpu(info->version) > 0 &&
- (ci->i_version & ~1) >= le64_to_cpu(info->version))
- goto no_change;
-
+ if (ci->i_version == 0 ||
+ ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+ le64_to_cpu(info->version) > (ci->i_version & ~1)))
+ new_version = true;
+
issued = __ceph_caps_issued(ci, &implemented);
issued |= implemented | __ceph_caps_dirty(ci);
+ new_issued = ~issued & le32_to_cpu(info->cap.caps);
/* update inode */
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;
- if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
+ (issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(info->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
@@ -644,31 +734,35 @@ static int fill_inode(struct inode *inode,
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((issued & CEPH_CAP_LINK_EXCL) == 0)
+ if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
+ (issued & CEPH_CAP_LINK_EXCL) == 0)
set_nlink(inode, le32_to_cpu(info->nlink));
- /* be careful with mtime, atime, size */
- ceph_decode_timespec(&atime, &info->atime);
- ceph_decode_timespec(&mtime, &info->mtime);
- ceph_decode_timespec(&ctime, &info->ctime);
- queue_trunc = ceph_fill_file_size(inode, issued,
- le32_to_cpu(info->truncate_seq),
- le64_to_cpu(info->truncate_size),
- le64_to_cpu(info->size));
- ceph_fill_file_time(inode, issued,
- le32_to_cpu(info->time_warp_seq),
- &ctime, &mtime, &atime);
-
- /* only update max_size on auth cap */
- if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
- ci->i_max_size != le64_to_cpu(info->max_size)) {
- dout("max_size %lld -> %llu\n", ci->i_max_size,
- le64_to_cpu(info->max_size));
- ci->i_max_size = le64_to_cpu(info->max_size);
+ if (new_version || (new_issued & CEPH_CAP_ANY_RD)) {
+ /* be careful with mtime, atime, size */
+ ceph_decode_timespec(&atime, &info->atime);
+ ceph_decode_timespec(&mtime, &info->mtime);
+ ceph_decode_timespec(&ctime, &info->ctime);
+ ceph_fill_file_time(inode, issued,
+ le32_to_cpu(info->time_warp_seq),
+ &ctime, &mtime, &atime);
}
- ci->i_layout = info->layout;
- inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+ if (new_version ||
+ (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ ci->i_layout = info->layout;
+ queue_trunc = ceph_fill_file_size(inode, issued,
+ le32_to_cpu(info->truncate_seq),
+ le64_to_cpu(info->truncate_size),
+ le64_to_cpu(info->size));
+ /* only update max_size on auth cap */
+ if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+ ci->i_max_size != le64_to_cpu(info->max_size)) {
+ dout("max_size %lld -> %llu\n", ci->i_max_size,
+ le64_to_cpu(info->max_size));
+ ci->i_max_size = le64_to_cpu(info->max_size);
+ }
+ }
/* xattrs */
/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
@@ -752,52 +846,7 @@ static int fill_inode(struct inode *inode,
!__ceph_dir_is_complete(ci)) {
dout(" marking %p complete (empty)\n", inode);
__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
- ci->i_max_offset = 2;
}
-no_change:
- spin_unlock(&ci->i_ceph_lock);
-
- /* queue truncate if we saw i_size decrease */
- if (queue_trunc)
- ceph_queue_vmtruncate(inode);
-
- /* populate frag tree */
- /* FIXME: move me up, if/when version reflects fragtree changes */
- nsplits = le32_to_cpu(info->fragtree.nsplits);
- mutex_lock(&ci->i_fragtree_mutex);
- rb_node = rb_first(&ci->i_fragtree);
- for (i = 0; i < nsplits; i++) {
- u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
- frag = NULL;
- while (rb_node) {
- frag = rb_entry(rb_node, struct ceph_inode_frag, node);
- if (ceph_frag_compare(frag->frag, id) >= 0) {
- if (frag->frag != id)
- frag = NULL;
- else
- rb_node = rb_next(rb_node);
- break;
- }
- rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
- frag = NULL;
- }
- if (!frag) {
- frag = __get_or_create_frag(ci, id);
- if (IS_ERR(frag))
- continue;
- }
- frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
- dout(" frag %x split by %d\n", frag->frag, frag->split_by);
- }
- while (rb_node) {
- frag = rb_entry(rb_node, struct ceph_inode_frag, node);
- rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
- }
- mutex_unlock(&ci->i_fragtree_mutex);
/* were we issued a capability? */
if (info->cap.caps) {
@@ -810,30 +859,41 @@ no_change:
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
le64_to_cpu(info->cap.realm),
- info->cap.flags,
- caps_reservation);
+ info->cap.flags, &new_cap);
+ wake = true;
} else {
- spin_lock(&ci->i_ceph_lock);
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(le32_to_cpu(info->cap.caps)));
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
- spin_unlock(&ci->i_ceph_lock);
}
} else if (cap_fmode >= 0) {
- pr_warning("mds issued no caps on %llx.%llx\n",
+ pr_warn("mds issued no caps on %llx.%llx\n",
ceph_vinop(inode));
__ceph_get_fmode(ci, cap_fmode);
}
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (wake)
+ wake_up_all(&ci->i_cap_wq);
+
+ /* queue truncate if we saw i_size decrease */
+ if (queue_trunc)
+ ceph_queue_vmtruncate(inode);
+
+ /* populate frag tree */
+ if (S_ISDIR(inode->i_mode))
+ ceph_fill_fragtree(inode, &info->fragtree, dirinfo);
/* update delegation info? */
if (dirinfo)
ceph_fill_dirfrag(inode, dirinfo);
err = 0;
-
out:
+ if (new_cap)
+ ceph_put_cap(mdsc, new_cap);
if (xattr_blob)
ceph_buffer_put(xattr_blob);
return err;
@@ -890,41 +950,6 @@ out_unlock:
}
/*
- * Set dentry's directory position based on the current dir's max, and
- * order it in d_subdirs, so that dcache_readdir behaves.
- *
- * Always called under directory's i_mutex.
- */
-static void ceph_set_dentry_offset(struct dentry *dn)
-{
- struct dentry *dir = dn->d_parent;
- struct inode *inode = dir->d_inode;
- struct ceph_inode_info *ci;
- struct ceph_dentry_info *di;
-
- BUG_ON(!inode);
-
- ci = ceph_inode(inode);
- di = ceph_dentry(dn);
-
- spin_lock(&ci->i_ceph_lock);
- if (!__ceph_dir_is_complete(ci)) {
- spin_unlock(&ci->i_ceph_lock);
- return;
- }
- di->offset = ceph_inode(inode)->i_max_offset++;
- spin_unlock(&ci->i_ceph_lock);
-
- spin_lock(&dir->d_lock);
- spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&dn->d_u.d_child, &dir->d_subdirs);
- dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
- dn->d_u.d_child.prev, dn->d_u.d_child.next);
- spin_unlock(&dn->d_lock);
- spin_unlock(&dir->d_lock);
-}
-
-/*
* splice a dentry to an inode.
* caller must hold directory i_mutex for this to be safe.
*
@@ -933,7 +958,7 @@ static void ceph_set_dentry_offset(struct dentry *dn)
* the caller) if we fail.
*/
static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
- bool *prehash, bool set_offset)
+ bool *prehash)
{
struct dentry *realdn;
@@ -965,8 +990,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
}
if ((!prehash || *prehash) && d_unhashed(dn))
d_rehash(dn);
- if (set_offset)
- ceph_set_dentry_offset(dn);
out:
return dn;
}
@@ -987,7 +1010,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
{
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
struct inode *in = NULL;
- struct ceph_mds_reply_inode *ininfo;
struct ceph_vino vino;
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
int err = 0;
@@ -1044,10 +1066,59 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
session, req->r_request_started, -1,
&req->r_caps_reservation);
if (err < 0)
- return err;
+ goto done;
} else {
WARN_ON_ONCE(1);
}
+
+ if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME) {
+ struct qstr dname;
+ struct dentry *dn, *parent;
+
+ BUG_ON(!rinfo->head->is_target);
+ BUG_ON(req->r_dentry);
+
+ parent = d_find_any_alias(dir);
+ BUG_ON(!parent);
+
+ dname.name = rinfo->dname;
+ dname.len = rinfo->dname_len;
+ dname.hash = full_name_hash(dname.name, dname.len);
+ vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+ vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+retry_lookup:
+ dn = d_lookup(parent, &dname);
+ dout("d_lookup on parent=%p name=%.*s got %p\n",
+ parent, dname.len, dname.name, dn);
+
+ if (!dn) {
+ dn = d_alloc(parent, &dname);
+ dout("d_alloc %p '%.*s' = %p\n", parent,
+ dname.len, dname.name, dn);
+ if (dn == NULL) {
+ dput(parent);
+ err = -ENOMEM;
+ goto done;
+ }
+ err = ceph_init_dentry(dn);
+ if (err < 0) {
+ dput(dn);
+ dput(parent);
+ goto done;
+ }
+ } else if (dn->d_inode &&
+ (ceph_ino(dn->d_inode) != vino.ino ||
+ ceph_snap(dn->d_inode) != vino.snap)) {
+ dout(" dn %p points to wrong inode %p\n",
+ dn, dn->d_inode);
+ d_delete(dn);
+ dput(dn);
+ goto retry_lookup;
+ }
+
+ req->r_dentry = dn;
+ dput(parent);
+ }
}
if (rinfo->head->is_target) {
@@ -1063,7 +1134,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
err = fill_inode(in, &rinfo->targeti, NULL,
session, req->r_request_started,
- (le32_to_cpu(rinfo->head->result) == 0) ?
+ (!req->r_aborted && rinfo->head->result == 0) ?
req->r_fmode : -1,
&req->r_caps_reservation);
if (err < 0) {
@@ -1112,6 +1183,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
/* rename? */
if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) {
+ struct inode *olddir = req->r_old_dentry_dir;
+ BUG_ON(!olddir);
+
dout(" src %p '%.*s' dst %p '%.*s'\n",
req->r_old_dentry,
req->r_old_dentry->d_name.len,
@@ -1131,13 +1205,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
rehashing bug in vfs_rename_dir */
ceph_invalidate_dentry_lease(dn);
- /*
- * d_move() puts the renamed dentry at the end of
- * d_subdirs. We need to assign it an appropriate
- * directory offset so we can behave when dir is
- * complete.
- */
- ceph_set_dentry_offset(req->r_old_dentry);
+ /* d_move screws up sibling dentries' offsets */
+ ceph_dir_clear_complete(dir);
+ ceph_dir_clear_complete(olddir);
+
dout("dn %p gets new offset %lld\n", req->r_old_dentry,
ceph_dentry(req->r_old_dentry)->offset);
@@ -1164,8 +1235,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
/* attach proper inode */
if (!dn->d_inode) {
+ ceph_dir_clear_complete(dir);
ihold(in);
- dn = splice_dentry(dn, in, &have_lease, true);
+ dn = splice_dentry(dn, in, &have_lease);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
goto done;
@@ -1186,17 +1258,16 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
(req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
req->r_op == CEPH_MDS_OP_MKSNAP)) {
struct dentry *dn = req->r_dentry;
+ struct inode *dir = req->r_locked_dir;
/* fill out a snapdir LOOKUPSNAP dentry */
BUG_ON(!dn);
- BUG_ON(!req->r_locked_dir);
- BUG_ON(ceph_snap(req->r_locked_dir) != CEPH_SNAPDIR);
- ininfo = rinfo->targeti.in;
- vino.ino = le64_to_cpu(ininfo->ino);
- vino.snap = le64_to_cpu(ininfo->snapid);
+ BUG_ON(!dir);
+ BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR);
dout(" linking snapped dir %p to dn %p\n", in, dn);
+ ceph_dir_clear_complete(dir);
ihold(in);
- dn = splice_dentry(dn, in, NULL, true);
+ dn = splice_dentry(dn, in, NULL);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
goto done;
@@ -1358,7 +1429,7 @@ retry_lookup:
}
if (!dn->d_inode) {
- dn = splice_dentry(dn, in, NULL, false);
+ dn = splice_dentry(dn, in, NULL);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
dn = NULL;
@@ -1475,7 +1546,7 @@ static void ceph_invalidate_work(struct work_struct *work)
orig_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(inode->i_mapping, 0);
+ truncate_pagecache(inode, 0);
spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
@@ -1578,7 +1649,7 @@ retry:
ci->i_truncate_pending, to);
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(inode->i_mapping, to);
+ truncate_pagecache(inode, to);
spin_lock(&ci->i_ceph_lock);
if (to == ci->i_truncate_size) {
@@ -1616,8 +1687,6 @@ static const struct inode_operations ceph_symlink_iops = {
.getxattr = ceph_getxattr,
.listxattr = ceph_listxattr,
.removexattr = ceph_removexattr,
- .get_acl = ceph_get_acl,
- .set_acl = ceph_set_acl,
};
/*
@@ -1627,7 +1696,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct inode *parent_inode;
const unsigned int ia_valid = attr->ia_valid;
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
@@ -1819,9 +1887,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
req->r_inode_drop = release;
req->r_args.setattr.mask = cpu_to_le32(mask);
req->r_num_caps = 1;
- 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);
}
dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
ceph_cap_string(dirtied), mask);
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index dc66c9e023e..a822a6e5829 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -1,9 +1,8 @@
+#include <linux/ceph/ceph_debug.h>
#include <linux/in.h>
#include "super.h"
#include "mds_client.h"
-#include <linux/ceph/ceph_debug.h>
-
#include "ioctl.h"
@@ -64,7 +63,6 @@ static long __validate_layout(struct ceph_mds_client *mdsc,
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
- struct inode *parent_inode;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
@@ -111,6 +109,8 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
+ req->r_num_caps = 1;
+
req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
req->r_args.setlayout.layout.fl_stripe_unit =
@@ -121,9 +121,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
- parent_inode = ceph_get_dentry_parent_inode(file->f_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;
}
@@ -157,6 +155,7 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
+ req->r_num_caps = 1;
req->r_args.setlayout.layout.fl_stripe_unit =
cpu_to_le32(l.stripe_unit);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ae6d14e82b0..fbc39c47bac 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -2,11 +2,31 @@
#include <linux/file.h>
#include <linux/namei.h>
+#include <linux/random.h>
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/pagelist.h>
+static u64 lock_secret;
+
+static inline u64 secure_addr(void *addr)
+{
+ u64 v = lock_secret ^ (u64)(unsigned long)addr;
+ /*
+ * Set the most significant bit, so that MDS knows the 'owner'
+ * is sufficient to identify the owner of lock. (old code uses
+ * both 'owner' and 'pid')
+ */
+ v |= (1ULL << 63);
+ return v;
+}
+
+void __init ceph_flock_init(void)
+{
+ get_random_bytes(&lock_secret, sizeof(lock_secret));
+}
+
/**
* Implement fcntl and flock locking functions.
*/
@@ -14,17 +34,18 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
int cmd, u8 wait, struct file_lock *fl)
{
struct inode *inode = file_inode(file);
- struct ceph_mds_client *mdsc =
- ceph_sb_to_client(inode->i_sb)->mdsc;
+ struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
int err;
u64 length = 0;
+ u64 owner;
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
+ req->r_num_caps = 1;
/* mds requires start and length rather than start and end */
if (LLONG_MAX == fl->fl_end)
@@ -32,25 +53,24 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
else
length = fl->fl_end - fl->fl_start + 1;
- dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
- "length: %llu, wait: %d, type: %d", (int)lock_type,
- (int)operation, (u64)fl->fl_pid, fl->fl_start,
- length, wait, fl->fl_type);
+ owner = secure_addr(fl->fl_owner);
+
+ dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
+ "start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
+ (int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
+ wait, fl->fl_type);
req->r_args.filelock_change.rule = lock_type;
req->r_args.filelock_change.type = cmd;
+ req->r_args.filelock_change.owner = cpu_to_le64(owner);
req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
- /* This should be adjusted, but I'm not sure if
- namespaces actually get id numbers*/
- req->r_args.filelock_change.pid_namespace =
- cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
req->r_args.filelock_change.length = cpu_to_le64(length);
req->r_args.filelock_change.wait = wait;
err = ceph_mdsc_do_request(mdsc, inode, req);
- if ( operation == CEPH_MDS_OP_GETFILELOCK){
+ if (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;
@@ -87,14 +107,19 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
u8 wait = 0;
u16 op = CEPH_MDS_OP_SETFILELOCK;
- fl->fl_nspid = get_pid(task_tgid(current));
- dout("ceph_lock, fl_pid:%d", fl->fl_pid);
+ if (!(fl->fl_flags & FL_POSIX))
+ return -ENOLCK;
+ /* No mandatory locks */
+ if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
+ return -ENOLCK;
+
+ dout("ceph_lock, fl_owner: %p", fl->fl_owner);
/* set wait bit as appropriate, then make command as Ceph expects it*/
- if (F_SETLKW == cmd)
- wait = 1;
- if (F_GETLK == cmd)
+ if (IS_GETLK(cmd))
op = CEPH_MDS_OP_GETFILELOCK;
+ else if (IS_SETLKW(cmd))
+ wait = 1;
if (F_RDLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_SHARED;
@@ -105,7 +130,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
if (!err) {
- if ( op != CEPH_MDS_OP_GETFILELOCK ){
+ if (op != CEPH_MDS_OP_GETFILELOCK) {
dout("mds locked, locking locally");
err = posix_lock_file(file, fl, NULL);
if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
@@ -131,20 +156,22 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
{
u8 lock_cmd;
int err;
- u8 wait = 1;
-
- fl->fl_nspid = get_pid(task_tgid(current));
- dout("ceph_flock, fl_pid:%d", fl->fl_pid);
-
- /* set wait bit, then clear it out of cmd*/
- if (cmd & LOCK_NB)
- wait = 0;
- cmd = cmd & (LOCK_SH | LOCK_EX | LOCK_UN);
- /* set command sequence that Ceph wants to see:
- shared lock, exclusive lock, or unlock */
- if (LOCK_SH == cmd)
+ u8 wait = 0;
+
+ if (!(fl->fl_flags & FL_FLOCK))
+ return -ENOLCK;
+ /* No mandatory locks */
+ if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
+ return -ENOLCK;
+
+ dout("ceph_flock, fl_file: %p", fl->fl_file);
+
+ if (IS_SETLKW(cmd))
+ wait = 1;
+
+ if (F_RDLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_SHARED;
- else if (LOCK_EX == cmd)
+ else if (F_WRLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_EXCL;
else
lock_cmd = CEPH_LOCK_UNLOCK;
@@ -280,13 +307,11 @@ int lock_to_ceph_filelock(struct file_lock *lock,
struct ceph_filelock *cephlock)
{
int err = 0;
-
cephlock->start = cpu_to_le64(lock->fl_start);
cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
cephlock->client = cpu_to_le64(0);
- cephlock->pid = cpu_to_le64(lock->fl_pid);
- cephlock->pid_namespace =
- cpu_to_le64((u64)(unsigned long)lock->fl_nspid);
+ cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
+ cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
switch (lock->fl_type) {
case F_RDLCK:
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f4f050a69a4..92a2548278f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3,6 +3,7 @@
#include <linux/fs.h>
#include <linux/wait.h>
#include <linux/slab.h>
+#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
@@ -165,21 +166,18 @@ static int parse_reply_info_dir(void **p, void *end,
if (num == 0)
goto done;
- /* alloc large array */
- info->dir_nr = num;
- info->dir_in = kcalloc(num, sizeof(*info->dir_in) +
- sizeof(*info->dir_dname) +
- sizeof(*info->dir_dname_len) +
- sizeof(*info->dir_dlease),
- GFP_NOFS);
- if (info->dir_in == NULL) {
- err = -ENOMEM;
- goto out_bad;
- }
+ BUG_ON(!info->dir_in);
info->dir_dname = (void *)(info->dir_in + num);
info->dir_dname_len = (void *)(info->dir_dname + num);
info->dir_dlease = (void *)(info->dir_dname_len + num);
+ if ((unsigned long)(info->dir_dlease + num) >
+ (unsigned long)info->dir_in + info->dir_buf_size) {
+ pr_err("dir contents are larger than expected\n");
+ WARN_ON(1);
+ goto bad;
+ }
+ info->dir_nr = num;
while (num) {
/* dentry */
ceph_decode_need(p, end, sizeof(u32)*2, bad);
@@ -327,7 +325,9 @@ out_bad:
static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
{
- kfree(info->dir_in);
+ if (!info->dir_in)
+ return;
+ free_pages((unsigned long)info->dir_in, get_order(info->dir_buf_size));
}
@@ -512,12 +512,11 @@ void ceph_mdsc_release_request(struct kref *kref)
struct ceph_mds_request *req = container_of(kref,
struct ceph_mds_request,
r_kref);
+ destroy_reply_info(&req->r_reply_info);
if (req->r_request)
ceph_msg_put(req->r_request);
- if (req->r_reply) {
+ if (req->r_reply)
ceph_msg_put(req->r_reply);
- destroy_reply_info(&req->r_reply_info);
- }
if (req->r_inode) {
ceph_put_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
iput(req->r_inode);
@@ -528,7 +527,9 @@ void ceph_mdsc_release_request(struct kref *kref)
iput(req->r_target_inode);
if (req->r_dentry)
dput(req->r_dentry);
- if (req->r_old_dentry) {
+ if (req->r_old_dentry)
+ dput(req->r_old_dentry);
+ if (req->r_old_dentry_dir) {
/*
* track (and drop pins for) r_old_dentry_dir
* separately, since r_old_dentry's d_parent may have
@@ -537,7 +538,6 @@ void ceph_mdsc_release_request(struct kref *kref)
*/
ceph_put_cap_refs(ceph_inode(req->r_old_dentry_dir),
CEPH_CAP_PIN);
- dput(req->r_old_dentry);
iput(req->r_old_dentry_dir);
}
kfree(req->r_path1);
@@ -1311,6 +1311,9 @@ static int trim_caps(struct ceph_mds_client *mdsc,
trim_caps - session->s_trim_caps);
session->s_trim_caps = 0;
}
+
+ ceph_add_cap_releases(mdsc, session);
+ ceph_send_cap_releases(mdsc, session);
return 0;
}
@@ -1461,15 +1464,18 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
dout("discard_cap_releases mds%d\n", session->s_mds);
- /* zero out the in-progress message */
- msg = list_first_entry(&session->s_cap_releases,
- struct ceph_msg, list_head);
- head = msg->front.iov_base;
- num = le32_to_cpu(head->num);
- dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg, num);
- head->num = cpu_to_le32(0);
- msg->front.iov_len = sizeof(*head);
- session->s_num_cap_releases += num;
+ if (!list_empty(&session->s_cap_releases)) {
+ /* zero out the in-progress message */
+ msg = list_first_entry(&session->s_cap_releases,
+ struct ceph_msg, list_head);
+ head = msg->front.iov_base;
+ num = le32_to_cpu(head->num);
+ dout("discard_cap_releases mds%d %p %u\n",
+ session->s_mds, msg, num);
+ head->num = cpu_to_le32(0);
+ msg->front.iov_len = sizeof(*head);
+ session->s_num_cap_releases += num;
+ }
/* requeue completed messages */
while (!list_empty(&session->s_cap_releases_done)) {
@@ -1492,6 +1498,43 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
* requests
*/
+int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
+ struct inode *dir)
+{
+ struct ceph_inode_info *ci = ceph_inode(dir);
+ struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+ struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options;
+ size_t size = sizeof(*rinfo->dir_in) + sizeof(*rinfo->dir_dname_len) +
+ sizeof(*rinfo->dir_dname) + sizeof(*rinfo->dir_dlease);
+ int order, num_entries;
+
+ spin_lock(&ci->i_ceph_lock);
+ num_entries = ci->i_files + ci->i_subdirs;
+ spin_unlock(&ci->i_ceph_lock);
+ num_entries = max(num_entries, 1);
+ num_entries = min(num_entries, opt->max_readdir);
+
+ order = get_order(size * num_entries);
+ while (order >= 0) {
+ rinfo->dir_in = (void*)__get_free_pages(GFP_NOFS | __GFP_NOWARN,
+ order);
+ if (rinfo->dir_in)
+ break;
+ order--;
+ }
+ if (!rinfo->dir_in)
+ return -ENOMEM;
+
+ num_entries = (PAGE_SIZE << order) / size;
+ num_entries = min(num_entries, opt->max_readdir);
+
+ rinfo->dir_buf_size = PAGE_SIZE << order;
+ req->r_num_caps = num_entries + 1;
+ req->r_args.readdir.max_entries = cpu_to_le32(num_entries);
+ req->r_args.readdir.max_bytes = cpu_to_le32(opt->max_readdir_bytes);
+ return 0;
+}
+
/*
* Create an mds request.
*/
@@ -1515,6 +1558,8 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
init_completion(&req->r_safe_completion);
INIT_LIST_HEAD(&req->r_unsafe_item);
+ req->r_stamp = CURRENT_TIME;
+
req->r_op = op;
req->r_direct_mode = mode;
return req;
@@ -1740,7 +1785,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
}
len = sizeof(*head) +
- pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64));
+ pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
+ sizeof(struct timespec);
/* calculate (max) length for cap releases */
len += sizeof(struct ceph_mds_request_release) *
@@ -1757,6 +1803,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
goto out_free2;
}
+ msg->hdr.version = 2;
msg->hdr.tid = cpu_to_le64(req->r_tid);
head = msg->front.iov_base;
@@ -1793,6 +1840,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
head->num_releases = cpu_to_le16(releases);
+ /* time stamp */
+ ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+
BUG_ON(p > end);
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
@@ -2053,7 +2103,7 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
if (req->r_locked_dir)
ceph_get_cap_refs(ceph_inode(req->r_locked_dir), CEPH_CAP_PIN);
- if (req->r_old_dentry)
+ if (req->r_old_dentry_dir)
ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
CEPH_CAP_PIN);
@@ -2175,13 +2225,13 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
/* dup? */
if ((req->r_got_unsafe && !head->safe) ||
(req->r_got_safe && head->safe)) {
- pr_warning("got a dup %s reply on %llu from mds%d\n",
+ pr_warn("got a dup %s reply on %llu from mds%d\n",
head->safe ? "safe" : "unsafe", tid, mds);
mutex_unlock(&mdsc->mutex);
goto out;
}
if (req->r_got_safe && !head->safe) {
- pr_warning("got unsafe after safe on %llu from mds%d\n",
+ pr_warn("got unsafe after safe on %llu from mds%d\n",
tid, mds);
mutex_unlock(&mdsc->mutex);
goto out;
@@ -3482,7 +3532,7 @@ static void peer_reset(struct ceph_connection *con)
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
- pr_warning("mds%d closed our session\n", s->s_mds);
+ pr_warn("mds%d closed our session\n", s->s_mds);
send_mds_reconnect(mdsc, s);
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 68288917c73..e00737cf523 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -67,6 +67,7 @@ struct ceph_mds_reply_info_parsed {
/* for readdir results */
struct {
struct ceph_mds_reply_dirfrag *dir_dir;
+ size_t dir_buf_size;
int dir_nr;
char **dir_dname;
u32 *dir_dname_len;
@@ -193,6 +194,7 @@ struct ceph_mds_request {
int r_fmode; /* file mode, if expecting cap */
kuid_t r_uid;
kgid_t r_gid;
+ struct timespec r_stamp;
/* for choosing which mds to send this request to */
int r_direct_mode;
@@ -346,7 +348,8 @@ extern void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc,
struct dentry *dn);
extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
-
+extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
+ struct inode *dir);
extern struct ceph_mds_request *
ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 132b64eeecd..261531e55e9 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -62,7 +62,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
ceph_decode_16_safe(p, end, version, bad);
if (version > 3) {
- pr_warning("got mdsmap version %d > 3, failing", version);
+ pr_warn("got mdsmap version %d > 3, failing", version);
goto bad;
}
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index 4440f447fd3..51cc23e4811 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -54,6 +54,7 @@ const char *ceph_mds_op_name(int op)
case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash";
case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent";
case CEPH_MDS_OP_LOOKUPINO: return "lookupino";
+ case CEPH_MDS_OP_LOOKUPNAME: return "lookupname";
case CEPH_MDS_OP_GETATTR: return "getattr";
case CEPH_MDS_OP_SETXATTR: return "setxattr";
case CEPH_MDS_OP_SETATTR: return "setattr";
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2df963f1cf5..06150fd745a 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -144,7 +144,11 @@ enum {
Opt_ino32,
Opt_noino32,
Opt_fscache,
- Opt_nofscache
+ Opt_nofscache,
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ Opt_acl,
+#endif
+ Opt_noacl
};
static match_table_t fsopt_tokens = {
@@ -172,6 +176,10 @@ static match_table_t fsopt_tokens = {
{Opt_noino32, "noino32"},
{Opt_fscache, "fsc"},
{Opt_nofscache, "nofsc"},
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ {Opt_acl, "acl"},
+#endif
+ {Opt_noacl, "noacl"},
{-1, NULL}
};
@@ -271,6 +279,14 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_nofscache:
fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
break;
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ case Opt_acl:
+ fsopt->sb_flags |= MS_POSIXACL;
+ break;
+#endif
+ case Opt_noacl:
+ fsopt->sb_flags &= ~MS_POSIXACL;
+ break;
default:
BUG_ON(token);
}
@@ -438,6 +454,13 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
else
seq_puts(m, ",nofsc");
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ if (fsopt->sb_flags & MS_POSIXACL)
+ seq_puts(m, ",acl");
+ else
+ seq_puts(m, ",noacl");
+#endif
+
if (fsopt->wsize)
seq_printf(m, ",wsize=%d", fsopt->wsize);
if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -819,9 +842,6 @@ static int ceph_set_super(struct super_block *s, void *data)
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;
@@ -911,6 +931,10 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
struct ceph_options *opt = NULL;
dout("ceph_mount\n");
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ flags |= MS_POSIXACL;
+#endif
err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
if (err < 0) {
res = ERR_PTR(err);
@@ -1002,6 +1026,7 @@ static int __init init_ceph(void)
if (ret)
goto out;
+ ceph_flock_init();
ceph_xattr_init();
ret = register_filesystem(&ceph_fs_type);
if (ret)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 19793b56d0a..12b20744e38 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -13,6 +13,7 @@
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
+#include <linux/posix_acl.h>
#include <linux/ceph/libceph.h>
@@ -265,7 +266,6 @@ struct ceph_inode_info {
struct timespec i_rctime;
u64 i_rbytes, i_rfiles, i_rsubdirs;
u64 i_files, i_subdirs;
- u64 i_max_offset; /* largest readdir offset, set with complete dir */
struct rb_root i_fragtree;
struct mutex i_fragtree_mutex;
@@ -292,7 +292,6 @@ struct ceph_inode_info {
struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or
dirty|flushing caps */
unsigned i_snap_caps; /* cap bits for snapped files */
- unsigned i_cap_exporting_issued;
int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */
@@ -576,7 +575,7 @@ struct ceph_file_info {
/* readdir: position within a frag */
unsigned offset; /* offset of last chunk, adjusted for . and .. */
- u64 next_offset; /* offset of next chunk (last_name's + 1) */
+ unsigned next_offset; /* offset of next chunk (last_name's + 1) */
char *last_name; /* last entry in previous chunk */
struct dentry *dentry; /* next dentry (for dcache readdir) */
int dir_release_count;
@@ -743,7 +742,11 @@ extern const struct xattr_handler *ceph_xattr_handlers[];
struct posix_acl *ceph_get_acl(struct inode *, int);
int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
-void ceph_forget_all_cached_acls(struct inode *inode);
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+ forget_all_cached_acls(inode);
+}
#else
@@ -771,11 +774,13 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode)
extern const char *ceph_cap_string(int c);
extern void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_msg *msg);
-extern int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned cap, unsigned seq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation);
+extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+ struct ceph_cap_reservation *ctx);
+extern void ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ int fmode, unsigned issued, unsigned wanted,
+ unsigned cap, unsigned seq, u64 realmino, int flags,
+ struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
@@ -866,6 +871,7 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
extern const struct export_operations ceph_export_ops;
/* locks.c */
+extern __init void ceph_flock_init(void);
extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 898b6565ad3..c9c2b887381 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -12,6 +12,9 @@
#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.
@@ -61,32 +64,48 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
}
static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
- size_t size)
+ 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)
- ret = snprintf(val, size,
- "stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%s",
+ 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),
- pool_name);
- else
- ret = snprintf(val, size,
+ (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;
}
@@ -212,7 +231,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
.name_size = sizeof("ceph.dir.layout"),
.getxattr_cb = ceph_vxattrcb_layout,
.readonly = false,
- .hidden = false,
+ .hidden = true,
.exists_cb = ceph_vxattrcb_layout_exists,
},
XATTR_LAYOUT_FIELD(dir, layout, stripe_unit),
@@ -239,7 +258,7 @@ static struct ceph_vxattr ceph_file_vxattrs[] = {
.name_size = sizeof("ceph.file.layout"),
.getxattr_cb = ceph_vxattrcb_layout,
.readonly = false,
- .hidden = false,
+ .hidden = true,
.exists_cb = ceph_vxattrcb_layout_exists,
},
XATTR_LAYOUT_FIELD(file, layout, stripe_unit),
@@ -319,8 +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;
@@ -349,12 +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);
@@ -364,7 +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;
}
@@ -379,8 +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);
@@ -442,7 +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);
@@ -588,7 +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;
@@ -821,7 +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;
@@ -850,6 +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);
@@ -869,9 +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);
@@ -892,7 +929,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name,
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;
@@ -953,12 +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)
@@ -993,7 +1032,6 @@ 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;
@@ -1007,9 +1045,7 @@ 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;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 18:46:36 +0000