summaryrefslogtreecommitdiffstats
path: root/fs/ceph/caps.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph/caps.c')
-rw-r--r--fs/ceph/caps.c251
1 files changed, 204 insertions, 47 deletions
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 8f537f1d9d1d..5c14ef04e474 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1188,11 +1188,11 @@ void ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
lockdep_assert_held(&ci->i_ceph_lock);
- fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ fsc = ceph_inode_to_client(&ci->vfs_inode);
WARN_ON_ONCE(ci->i_auth_cap == cap &&
!list_empty(&ci->i_dirty_item) &&
!fsc->blocklisted &&
- READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN);
+ !ceph_inode_is_shutdown(&ci->vfs_inode));
__ceph_remove_cap(cap, queue_release);
}
@@ -1856,7 +1856,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
u32 invalidating_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
- ceph_fscache_invalidate(inode);
+ ceph_fscache_invalidate(inode, false);
invalidate_mapping_pages(&inode->i_data, 0, -1);
spin_lock(&ci->i_ceph_lock);
@@ -1915,6 +1915,13 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
ceph_get_mds_session(session);
spin_lock(&ci->i_ceph_lock);
+ if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) {
+ /* Don't send messages until we get async create reply */
+ spin_unlock(&ci->i_ceph_lock);
+ ceph_put_mds_session(session);
+ return;
+ }
+
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
retry:
@@ -1968,8 +1975,8 @@ retry:
}
}
- dout("check_caps %p file_want %s used %s dirty %s flushing %s"
- " issued %s revoking %s retain %s %s%s\n", inode,
+ dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s"
+ " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode),
ceph_cap_string(file_wanted),
ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
ceph_cap_string(ci->i_flushing_caps),
@@ -1990,7 +1997,8 @@ retry:
(revoking & (CEPH_CAP_FILE_CACHE|
CEPH_CAP_FILE_LAZYIO)) && /* or revoking cache */
!tried_invalidate) {
- dout("check_caps trying to invalidate on %p\n", inode);
+ dout("check_caps trying to invalidate on %llx.%llx\n",
+ ceph_vinop(inode));
if (try_nonblocking_invalidate(inode) < 0) {
dout("check_caps queuing invalidate\n");
queue_invalidate = true;
@@ -2217,6 +2225,7 @@ static int unsafe_request_wait(struct inode *inode)
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req1 = NULL, *req2 = NULL;
+ unsigned int max_sessions;
int ret, err = 0;
spin_lock(&ci->i_unsafe_lock);
@@ -2235,36 +2244,46 @@ static int unsafe_request_wait(struct inode *inode)
spin_unlock(&ci->i_unsafe_lock);
/*
+ * The mdsc->max_sessions is unlikely to be changed
+ * mostly, here we will retry it by reallocating the
+ * sessions array memory to get rid of the mdsc->mutex
+ * lock.
+ */
+retry:
+ max_sessions = mdsc->max_sessions;
+
+ /*
* Trigger to flush the journal logs in all the relevant MDSes
* manually, or in the worst case we must wait at most 5 seconds
* to wait the journal logs to be flushed by the MDSes periodically.
*/
- if (req1 || req2) {
+ if ((req1 || req2) && likely(max_sessions)) {
struct ceph_mds_session **sessions = NULL;
struct ceph_mds_session *s;
struct ceph_mds_request *req;
- unsigned int max;
int i;
- /*
- * The mdsc->max_sessions is unlikely to be changed
- * mostly, here we will retry it by reallocating the
- * sessions arrary memory to get rid of the mdsc->mutex
- * lock.
- */
-retry:
- max = mdsc->max_sessions;
- sessions = krealloc(sessions, max * sizeof(s), __GFP_ZERO);
- if (!sessions)
- return -ENOMEM;
+ sessions = kzalloc(max_sessions * sizeof(s), GFP_KERNEL);
+ if (!sessions) {
+ err = -ENOMEM;
+ goto out;
+ }
spin_lock(&ci->i_unsafe_lock);
if (req1) {
list_for_each_entry(req, &ci->i_unsafe_dirops,
r_unsafe_dir_item) {
s = req->r_session;
- if (unlikely(s->s_mds >= max)) {
+ if (!s)
+ continue;
+ if (unlikely(s->s_mds >= max_sessions)) {
spin_unlock(&ci->i_unsafe_lock);
+ for (i = 0; i < max_sessions; i++) {
+ s = sessions[i];
+ if (s)
+ ceph_put_mds_session(s);
+ }
+ kfree(sessions);
goto retry;
}
if (!sessions[s->s_mds]) {
@@ -2277,8 +2296,16 @@ retry:
list_for_each_entry(req, &ci->i_unsafe_iops,
r_unsafe_target_item) {
s = req->r_session;
- if (unlikely(s->s_mds >= max)) {
+ if (!s)
+ continue;
+ if (unlikely(s->s_mds >= max_sessions)) {
spin_unlock(&ci->i_unsafe_lock);
+ for (i = 0; i < max_sessions; i++) {
+ s = sessions[i];
+ if (s)
+ ceph_put_mds_session(s);
+ }
+ kfree(sessions);
goto retry;
}
if (!sessions[s->s_mds]) {
@@ -2299,7 +2326,7 @@ retry:
spin_unlock(&ci->i_ceph_lock);
/* send flush mdlog request to MDSes */
- for (i = 0; i < max; i++) {
+ for (i = 0; i < max_sessions; i++) {
s = sessions[i];
if (s) {
send_flush_mdlog(s);
@@ -2316,15 +2343,19 @@ retry:
ceph_timeout_jiffies(req1->r_timeout));
if (ret)
err = -EIO;
- ceph_mdsc_put_request(req1);
}
if (req2) {
ret = !wait_for_completion_timeout(&req2->r_safe_completion,
ceph_timeout_jiffies(req2->r_timeout));
if (ret)
err = -EIO;
- ceph_mdsc_put_request(req2);
}
+
+out:
+ if (req1)
+ ceph_mdsc_put_request(req1);
+ if (req2)
+ ceph_mdsc_put_request(req2);
return err;
}
@@ -2387,7 +2418,11 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync);
dout("write_inode %p wait=%d\n", inode, wait);
+ ceph_fscache_unpin_writeback(inode, wbc);
if (wait) {
+ err = ceph_wait_on_async_create(inode);
+ if (err)
+ return err;
dirty = try_flush_caps(inode, &flush_tid);
if (dirty)
err = wait_event_interruptible(ci->i_cap_wq,
@@ -2418,6 +2453,10 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
u64 first_tid = 0;
u64 last_snap_flush = 0;
+ /* Don't do anything until create reply comes in */
+ if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE)
+ return;
+
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
list_for_each_entry_reverse(cf, &ci->i_cap_flush_list, i_list) {
@@ -2629,9 +2668,9 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
*
* Returns 0 if caps were not able to be acquired (yet), 1 if succeed,
* or a negative error code. There are 3 speical error codes:
- * -EAGAIN: need to sleep but non-blocking is specified
- * -EFBIG: ask caller to call check_max_size() and try again.
- * -ESTALE: ask caller to call ceph_renew_caps() and try again.
+ * -EAGAIN: need to sleep but non-blocking is specified
+ * -EFBIG: ask caller to call check_max_size() and try again.
+ * -EUCLEAN: ask caller to call ceph_renew_caps() and try again.
*/
enum {
/* first 8 bits are reserved for CEPH_FILE_MODE_FOO */
@@ -2679,7 +2718,7 @@ again:
dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
inode, endoff, ci->i_max_size);
if (endoff > ci->i_requested_max_size)
- ret = ci->i_auth_cap ? -EFBIG : -ESTALE;
+ ret = ci->i_auth_cap ? -EFBIG : -EUCLEAN;
goto out_unlock;
}
/*
@@ -2749,9 +2788,9 @@ again:
goto out_unlock;
}
- if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
- dout("get_cap_refs %p forced umount\n", inode);
- ret = -EIO;
+ if (ceph_inode_is_shutdown(inode)) {
+ dout("get_cap_refs %p inode is shutdown\n", inode);
+ ret = -ESTALE;
goto out_unlock;
}
mds_wanted = __ceph_caps_mds_wanted(ci, false);
@@ -2759,7 +2798,7 @@ again:
dout("get_cap_refs %p need %s > mds_wanted %s\n",
inode, ceph_cap_string(need),
ceph_cap_string(mds_wanted));
- ret = -ESTALE;
+ ret = -EUCLEAN;
goto out_unlock;
}
@@ -2843,7 +2882,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
ret = try_get_cap_refs(inode, need, want, 0, flags, got);
/* three special error codes */
- if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE)
+ if (ret == -EAGAIN || ret == -EFBIG || ret == -EUCLEAN)
ret = 0;
return ret;
}
@@ -2926,7 +2965,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
}
if (ret < 0) {
- if (ret == -EFBIG || ret == -ESTALE) {
+ if (ret == -EFBIG || ret == -EUCLEAN) {
int ret2 = ceph_wait_on_async_create(inode);
if (ret2 < 0)
return ret2;
@@ -2935,7 +2974,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
check_max_size(inode, endoff);
continue;
}
- if (ret == -ESTALE) {
+ if (ret == -EUCLEAN) {
/* session was killed, try renew caps */
ret = ceph_renew_caps(inode, flags);
if (ret == 0)
@@ -3374,8 +3413,7 @@ static void handle_cap_grant(struct inode *inode,
if ((newcaps & CEPH_CAP_LINK_SHARED) &&
(extra_info->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)))
+ if (inode->i_nlink == 0)
deleted_inode = true;
}
@@ -3836,6 +3874,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
dout("handle_cap_export inode %p ci %p mds%d mseq %d target %d\n",
inode, ci, mds, mseq, target);
retry:
+ down_read(&mdsc->snap_rwsem);
spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
@@ -3899,6 +3938,7 @@ retry:
}
spin_unlock(&ci->i_ceph_lock);
+ up_read(&mdsc->snap_rwsem);
mutex_unlock(&session->s_mutex);
/* open target session */
@@ -3924,6 +3964,7 @@ retry:
out_unlock:
spin_unlock(&ci->i_ceph_lock);
+ up_read(&mdsc->snap_rwsem);
mutex_unlock(&session->s_mutex);
if (tsession) {
mutex_unlock(&tsession->s_mutex);
@@ -4132,7 +4173,6 @@ void ceph_handle_caps(struct ceph_mds_session *session,
/* lookup ino */
inode = ceph_find_inode(mdsc->fsc->sb, vino);
- ci = ceph_inode(inode);
dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
vino.snap, inode);
@@ -4158,6 +4198,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
}
goto flush_cap_releases;
}
+ ci = ceph_inode(inode);
/* these will work even if we don't have a cap yet */
switch (op) {
@@ -4315,7 +4356,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s)
i_dirty_item);
inode = &ci->vfs_inode;
ihold(inode);
- dout("flush_dirty_caps %p\n", inode);
+ dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode));
spin_unlock(&mdsc->cap_dirty_lock);
ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
iput(inode);
@@ -4349,7 +4390,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
int bits = (fmode << 1) | 1;
- bool is_opened = false;
+ bool already_opened = false;
int i;
if (count == 1)
@@ -4357,19 +4398,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
spin_lock(&ci->i_ceph_lock);
for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
- if (bits & (1 << i))
- ci->i_nr_by_mode[i] += count;
-
/*
- * If any of the mode ref is larger than 1,
+ * If any of the mode ref is larger than 0,
* that means it has been already opened by
* others. Just skip checking the PIN ref.
*/
- if (i && ci->i_nr_by_mode[i] > 1)
- is_opened = true;
+ if (i && ci->i_nr_by_mode[i])
+ already_opened = true;
+
+ if (bits & (1 << i))
+ ci->i_nr_by_mode[i] += count;
}
- if (!is_opened)
+ if (!already_opened)
percpu_counter_inc(&mdsc->metric.opened_inodes);
spin_unlock(&ci->i_ceph_lock);
}
@@ -4560,3 +4601,119 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
spin_unlock(&dentry->d_lock);
return ret;
}
+
+static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_cap_snap *capsnap;
+ int capsnap_release = 0;
+
+ lockdep_assert_held(&ci->i_ceph_lock);
+
+ dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode);
+
+ while (!list_empty(&ci->i_cap_snaps)) {
+ capsnap = list_first_entry(&ci->i_cap_snaps,
+ struct ceph_cap_snap, ci_item);
+ __ceph_remove_capsnap(inode, capsnap, NULL, NULL);
+ ceph_put_snap_context(capsnap->context);
+ ceph_put_cap_snap(capsnap);
+ capsnap_release++;
+ }
+ wake_up_all(&ci->i_cap_wq);
+ wake_up_all(&mdsc->cap_flushing_wq);
+ return capsnap_release;
+}
+
+int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate)
+{
+ struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+ struct ceph_mds_client *mdsc = fsc->mdsc;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ bool is_auth;
+ bool dirty_dropped = false;
+ int iputs = 0;
+
+ lockdep_assert_held(&ci->i_ceph_lock);
+
+ dout("removing cap %p, ci is %p, inode is %p\n",
+ cap, ci, &ci->vfs_inode);
+
+ is_auth = (cap == ci->i_auth_cap);
+ __ceph_remove_cap(cap, false);
+ if (is_auth) {
+ struct ceph_cap_flush *cf;
+
+ if (ceph_inode_is_shutdown(inode)) {
+ if (inode->i_data.nrpages > 0)
+ *invalidate = true;
+ if (ci->i_wrbuffer_ref > 0)
+ mapping_set_error(&inode->i_data, -EIO);
+ }
+
+ spin_lock(&mdsc->cap_dirty_lock);
+
+ /* trash all of the cap flushes for this inode */
+ while (!list_empty(&ci->i_cap_flush_list)) {
+ cf = list_first_entry(&ci->i_cap_flush_list,
+ struct ceph_cap_flush, i_list);
+ list_del_init(&cf->g_list);
+ list_del_init(&cf->i_list);
+ if (!cf->is_capsnap)
+ ceph_free_cap_flush(cf);
+ }
+
+ if (!list_empty(&ci->i_dirty_item)) {
+ pr_warn_ratelimited(
+ " dropping dirty %s state for %p %lld\n",
+ ceph_cap_string(ci->i_dirty_caps),
+ inode, ceph_ino(inode));
+ ci->i_dirty_caps = 0;
+ list_del_init(&ci->i_dirty_item);
+ dirty_dropped = true;
+ }
+ if (!list_empty(&ci->i_flushing_item)) {
+ pr_warn_ratelimited(
+ " dropping dirty+flushing %s state for %p %lld\n",
+ ceph_cap_string(ci->i_flushing_caps),
+ inode, ceph_ino(inode));
+ ci->i_flushing_caps = 0;
+ list_del_init(&ci->i_flushing_item);
+ mdsc->num_cap_flushing--;
+ dirty_dropped = true;
+ }
+ spin_unlock(&mdsc->cap_dirty_lock);
+
+ if (dirty_dropped) {
+ mapping_set_error(inode->i_mapping, -EIO);
+
+ if (ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ceph_put_snap_context(ci->i_head_snapc);
+ ci->i_head_snapc = NULL;
+ }
+ }
+
+ if (atomic_read(&ci->i_filelock_ref) > 0) {
+ /* make further file lock syscall return -EIO */
+ ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK;
+ pr_warn_ratelimited(" dropping file locks for %p %lld\n",
+ inode, ceph_ino(inode));
+ }
+
+ if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) {
+ cf = ci->i_prealloc_cap_flush;
+ ci->i_prealloc_cap_flush = NULL;
+ if (!cf->is_capsnap)
+ ceph_free_cap_flush(cf);
+ }
+
+ if (!list_empty(&ci->i_cap_snaps))
+ iputs = remove_capsnaps(mdsc, inode);
+ }
+ if (dirty_dropped)
+ ++iputs;
+ return iputs;
+}
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-01 03:51:40 +0100