summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ocfs2')
-rw-r--r--fs/ocfs2/alloc.c6
-rw-r--r--fs/ocfs2/aops.c7
-rw-r--r--fs/ocfs2/cluster/heartbeat.c2
-rw-r--r--fs/ocfs2/cluster/tcp.c33
-rw-r--r--fs/ocfs2/dlm/dlmcommon.h5
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c2
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c14
-rw-r--r--fs/ocfs2/dlm/dlmlock.c2
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c71
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c13
-rw-r--r--fs/ocfs2/dlm/dlmthread.c13
-rw-r--r--fs/ocfs2/dlm/dlmunlock.c18
-rw-r--r--fs/ocfs2/dlmglue.c5
-rw-r--r--fs/ocfs2/file.c140
-rw-r--r--fs/ocfs2/ioctl.c81
-rw-r--r--fs/ocfs2/journal.c17
-rw-r--r--fs/ocfs2/namei.c145
-rw-r--r--fs/ocfs2/ocfs2.h1
-rw-r--r--fs/ocfs2/ocfs2_trace.h2
-rw-r--r--fs/ocfs2/refcounttree.c15
-rw-r--r--fs/ocfs2/resize.c10
-rw-r--r--fs/ocfs2/stackglue.c2
-rw-r--r--fs/ocfs2/super.c16
-rw-r--r--fs/ocfs2/uptodate.c2
24 files changed, 386 insertions, 236 deletions
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b4deb5f750d9..9d8fcf2f3b94 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6046,7 +6046,8 @@ static void ocfs2_truncate_log_worker(struct work_struct *work)
void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
int cancel)
{
- if (osb->osb_tl_inode) {
+ if (osb->osb_tl_inode &&
+ atomic_read(&osb->osb_tl_disable) == 0) {
/* We want to push off log flushes while truncates are
* still running. */
if (cancel)
@@ -6223,6 +6224,8 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb)
int status;
struct inode *tl_inode = osb->osb_tl_inode;
+ atomic_set(&osb->osb_tl_disable, 1);
+
if (tl_inode) {
cancel_delayed_work(&osb->osb_truncate_log_wq);
flush_workqueue(ocfs2_wq);
@@ -6254,6 +6257,7 @@ int ocfs2_truncate_log_init(struct ocfs2_super *osb)
* until we're sure all is well. */
INIT_DELAYED_WORK(&osb->osb_truncate_log_wq,
ocfs2_truncate_log_worker);
+ atomic_set(&osb->osb_tl_disable, 0);
osb->osb_tl_bh = tl_bh;
osb->osb_tl_inode = tl_inode;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index d310d12a9adc..4a231a166cf8 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -599,9 +599,8 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
static ssize_t ocfs2_direct_IO(int rw,
struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file)->i_mapping->host;
@@ -618,7 +617,7 @@ static ssize_t ocfs2_direct_IO(int rw,
return 0;
return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
- iov, offset, nr_segs,
+ iter, offset,
ocfs2_direct_IO_get_blocks,
ocfs2_dio_end_io, NULL, 0);
}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index bf482dfed14f..73039295d0d1 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1107,7 +1107,7 @@ static int o2hb_thread(void *data)
mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread running\n");
- set_user_nice(current, -20);
+ set_user_nice(current, MIN_NICE);
/* Pin node */
o2nm_depend_this_node();
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index c6b90e670389..681691bc233a 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -108,7 +108,7 @@ static struct rb_root o2net_handler_tree = RB_ROOT;
static struct o2net_node o2net_nodes[O2NM_MAX_NODES];
/* XXX someday we'll need better accounting */
-static struct socket *o2net_listen_sock = NULL;
+static struct socket *o2net_listen_sock;
/*
* listen work is only queued by the listening socket callbacks on the
@@ -1799,7 +1799,7 @@ int o2net_register_hb_callbacks(void)
/* ------------------------------------------------------------ */
-static int o2net_accept_one(struct socket *sock)
+static int o2net_accept_one(struct socket *sock, int *more)
{
int ret, slen;
struct sockaddr_in sin;
@@ -1810,6 +1810,7 @@ static int o2net_accept_one(struct socket *sock)
struct o2net_node *nn;
BUG_ON(sock == NULL);
+ *more = 0;
ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type,
sock->sk->sk_protocol, &new_sock);
if (ret)
@@ -1821,6 +1822,7 @@ static int o2net_accept_one(struct socket *sock)
if (ret < 0)
goto out;
+ *more = 1;
new_sock->sk->sk_allocation = GFP_ATOMIC;
ret = o2net_set_nodelay(new_sock);
@@ -1919,11 +1921,36 @@ out:
return ret;
}
+/*
+ * This function is invoked in response to one or more
+ * pending accepts at softIRQ level. We must drain the
+ * entire que before returning.
+ */
+
static void o2net_accept_many(struct work_struct *work)
{
struct socket *sock = o2net_listen_sock;
- while (o2net_accept_one(sock) == 0)
+ int more;
+ int err;
+
+ /*
+ * It is critical to note that due to interrupt moderation
+ * at the network driver level, we can't assume to get a
+ * softIRQ for every single conn since tcp SYN packets
+ * can arrive back-to-back, and therefore many pending
+ * accepts may result in just 1 softIRQ. If we terminate
+ * the o2net_accept_one() loop upon seeing an err, what happens
+ * to the rest of the conns in the queue? If no new SYN
+ * arrives for hours, no softIRQ will be delivered,
+ * and the connections will just sit in the queue.
+ */
+
+ for (;;) {
+ err = o2net_accept_one(sock, &more);
+ if (!more)
+ break;
cond_resched();
+ }
}
static void o2net_listen_data_ready(struct sock *sk)
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e0517762fcc0..fae17c640df3 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -108,7 +108,6 @@ static inline int dlm_is_recovery_lock(const char *lock_name, int name_len)
struct dlm_recovery_ctxt
{
struct list_head resources;
- struct list_head received;
struct list_head node_data;
u8 new_master;
u8 dead_node;
@@ -332,6 +331,7 @@ struct dlm_lock_resource
u16 state;
char lvb[DLM_LVB_LEN];
unsigned int inflight_locks;
+ unsigned int inflight_assert_workers;
unsigned long refmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
};
@@ -911,6 +911,9 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
struct dlm_lock_resource *res);
+void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res);
+
void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index e33cd7a3c582..18f13c2e4a10 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -338,7 +338,7 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle)
#ifdef CONFIG_DEBUG_FS
-static struct dentry *dlm_debugfs_root = NULL;
+static struct dentry *dlm_debugfs_root;
#define DLM_DEBUGFS_DIR "o2dlm"
#define DLM_DEBUGFS_DLM_STATE "dlm_state"
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index c973690dc0bc..39efc5057a36 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -959,6 +959,14 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data,
* domain. Set him in the map and clean up our
* leftover join state. */
BUG_ON(dlm->joining_node != assert->node_idx);
+
+ if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+ mlog(0, "dlm recovery is ongoing, disallow join\n");
+ spin_unlock(&dlm->spinlock);
+ spin_unlock(&dlm_domain_lock);
+ return -EAGAIN;
+ }
+
set_bit(assert->node_idx, dlm->domain_map);
clear_bit(assert->node_idx, dlm->exit_domain_map);
__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
@@ -1517,6 +1525,7 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm,
unsigned int node)
{
int status;
+ int ret;
struct dlm_assert_joined assert_msg;
mlog(0, "Sending join assert to node %u\n", node);
@@ -1528,11 +1537,13 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm,
status = o2net_send_message(DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY,
&assert_msg, sizeof(assert_msg), node,
- NULL);
+ &ret);
if (status < 0)
mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
"node %u\n", status, DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY,
node);
+ else
+ status = ret;
return status;
}
@@ -2023,7 +2034,6 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
INIT_LIST_HEAD(&dlm->list);
INIT_LIST_HEAD(&dlm->dirty_list);
INIT_LIST_HEAD(&dlm->reco.resources);
- INIT_LIST_HEAD(&dlm->reco.received);
INIT_LIST_HEAD(&dlm->reco.node_data);
INIT_LIST_HEAD(&dlm->purge_list);
INIT_LIST_HEAD(&dlm->dlm_domain_handlers);
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 5d32f7511f74..66c2a491f68d 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -52,7 +52,7 @@
#define MLOG_MASK_PREFIX ML_DLM
#include "cluster/masklog.h"
-static struct kmem_cache *dlm_lock_cache = NULL;
+static struct kmem_cache *dlm_lock_cache;
static DEFINE_SPINLOCK(dlm_cookie_lock);
static u64 dlm_next_cookie = 1;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index af3f7aa73e13..82abf0cc9a12 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -82,9 +82,9 @@ static inline int dlm_mle_equal(struct dlm_ctxt *dlm,
return 1;
}
-static struct kmem_cache *dlm_lockres_cache = NULL;
-static struct kmem_cache *dlm_lockname_cache = NULL;
-static struct kmem_cache *dlm_mle_cache = NULL;
+static struct kmem_cache *dlm_lockres_cache;
+static struct kmem_cache *dlm_lockname_cache;
+static struct kmem_cache *dlm_mle_cache;
static void dlm_mle_release(struct kref *kref);
static void dlm_init_mle(struct dlm_master_list_entry *mle,
@@ -472,11 +472,15 @@ bail:
void dlm_destroy_master_caches(void)
{
- if (dlm_lockname_cache)
+ if (dlm_lockname_cache) {
kmem_cache_destroy(dlm_lockname_cache);
+ dlm_lockname_cache = NULL;
+ }
- if (dlm_lockres_cache)
+ if (dlm_lockres_cache) {
kmem_cache_destroy(dlm_lockres_cache);
+ dlm_lockres_cache = NULL;
+ }
}
static void dlm_lockres_release(struct kref *kref)
@@ -577,6 +581,7 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
atomic_set(&res->asts_reserved, 0);
res->migration_pending = 0;
res->inflight_locks = 0;
+ res->inflight_assert_workers = 0;
res->dlm = dlm;
@@ -679,6 +684,43 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
wake_up(&res->wq);
}
+void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ assert_spin_locked(&res->spinlock);
+ res->inflight_assert_workers++;
+ mlog(0, "%s:%.*s: inflight assert worker++: now %u\n",
+ dlm->name, res->lockname.len, res->lockname.name,
+ res->inflight_assert_workers);
+}
+
+static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ spin_lock(&res->spinlock);
+ __dlm_lockres_grab_inflight_worker(dlm, res);
+ spin_unlock(&res->spinlock);
+}
+
+static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ assert_spin_locked(&res->spinlock);
+ BUG_ON(res->inflight_assert_workers == 0);
+ res->inflight_assert_workers--;
+ mlog(0, "%s:%.*s: inflight assert worker--: now %u\n",
+ dlm->name, res->lockname.len, res->lockname.name,
+ res->inflight_assert_workers);
+}
+
+static void dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ spin_lock(&res->spinlock);
+ __dlm_lockres_drop_inflight_worker(dlm, res);
+ spin_unlock(&res->spinlock);
+}
+
/*
* lookup a lock resource by name.
* may already exist in the hashtable.
@@ -1599,7 +1641,8 @@ send_response:
mlog(ML_ERROR, "failed to dispatch assert master work\n");
response = DLM_MASTER_RESP_ERROR;
dlm_lockres_put(res);
- }
+ } else
+ dlm_lockres_grab_inflight_worker(dlm, res);
} else {
if (res)
dlm_lockres_put(res);
@@ -2114,6 +2157,8 @@ static void dlm_assert_master_worker(struct dlm_work_item *item, void *data)
dlm_lockres_release_ast(dlm, res);
put:
+ dlm_lockres_drop_inflight_worker(dlm, res);
+
dlm_lockres_put(res);
mlog(0, "finished with dlm_assert_master_worker\n");
@@ -3084,11 +3129,15 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
/* remove it so that only one mle will be found */
__dlm_unlink_mle(dlm, tmp);
__dlm_mle_detach_hb_events(dlm, tmp);
- ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
- mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
- "telling master to get ref for cleared out mle "
- "during migration\n", dlm->name, namelen, name,
- master, new_master);
+ if (tmp->type == DLM_MLE_MASTER) {
+ ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
+ mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
+ "telling master to get ref "
+ "for cleared out mle during "
+ "migration\n", dlm->name,
+ namelen, name, master,
+ new_master);
+ }
}
spin_unlock(&tmp->spinlock);
}
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index fe29f7978f81..45067faf5695 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1708,7 +1708,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
mlog_errno(-ENOMEM);
/* retry!? */
BUG();
- }
+ } else
+ __dlm_lockres_grab_inflight_worker(dlm, res);
} else /* put.. incase we are not the master */
dlm_lockres_put(res);
spin_unlock(&res->spinlock);
@@ -1986,7 +1987,15 @@ skip_lvb:
}
if (!bad) {
dlm_lock_get(newlock);
- list_add_tail(&newlock->list, queue);
+ if (mres->flags & DLM_MRES_RECOVERY &&
+ ml->list == DLM_CONVERTING_LIST &&
+ newlock->ml.type >
+ newlock->ml.convert_type) {
+ /* newlock is doing downconvert, add it to the
+ * head of converting list */
+ list_add(&newlock->list, queue);
+ } else
+ list_add_tail(&newlock->list, queue);
mlog(0, "%s:%.*s: added lock for node %u, "
"setting refmap bit\n", dlm->name,
res->lockname.len, res->lockname.name, ml->node);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 9db869de829d..69aac6f088ad 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -259,12 +259,15 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
* refs on it. */
unused = __dlm_lockres_unused(lockres);
if (!unused ||
- (lockres->state & DLM_LOCK_RES_MIGRATING)) {
+ (lockres->state & DLM_LOCK_RES_MIGRATING) ||
+ (lockres->inflight_assert_workers != 0)) {
mlog(0, "%s: res %.*s is in use or being remastered, "
- "used %d, state %d\n", dlm->name,
- lockres->lockname.len, lockres->lockname.name,
- !unused, lockres->state);
- list_move_tail(&dlm->purge_list, &lockres->purge);
+ "used %d, state %d, assert master workers %u\n",
+ dlm->name, lockres->lockname.len,
+ lockres->lockname.name,
+ !unused, lockres->state,
+ lockres->inflight_assert_workers);
+ list_move_tail(&lockres->purge, &dlm->purge_list);
spin_unlock(&lockres->spinlock);
continue;
}
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 5698b52cf5c9..2e3c9dbab68c 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -191,7 +191,9 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
DLM_UNLOCK_CLEAR_CONVERT_TYPE);
} else if (status == DLM_RECOVERING ||
status == DLM_MIGRATING ||
- status == DLM_FORWARD) {
+ status == DLM_FORWARD ||
+ status == DLM_NOLOCKMGR
+ ) {
/* must clear the actions because this unlock
* is about to be retried. cannot free or do
* any list manipulation. */
@@ -200,7 +202,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
res->lockname.name,
status==DLM_RECOVERING?"recovering":
(status==DLM_MIGRATING?"migrating":
- "forward"));
+ (status == DLM_FORWARD ? "forward" :
+ "nolockmanager")));
actions = 0;
}
if (flags & LKM_CANCEL)
@@ -364,7 +367,10 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
* updated state to the recovery master. this thread
* just needs to finish out the operation and call
* the unlockast. */
- ret = DLM_NORMAL;
+ if (dlm_is_node_dead(dlm, owner))
+ ret = DLM_NORMAL;
+ else
+ ret = DLM_NOLOCKMGR;
} else {
/* something bad. this will BUG in ocfs2 */
ret = dlm_err_to_dlm_status(tmpret);
@@ -638,7 +644,9 @@ retry:
if (status == DLM_RECOVERING ||
status == DLM_MIGRATING ||
- status == DLM_FORWARD) {
+ status == DLM_FORWARD ||
+ status == DLM_NOLOCKMGR) {
+
/* We want to go away for a tiny bit to allow recovery
* / migration to complete on this resource. I don't
* know of any wait queue we could sleep on as this
@@ -650,7 +658,7 @@ retry:
msleep(50);
mlog(0, "retrying unlock due to pending recovery/"
- "migration/in-progress\n");
+ "migration/in-progress/reconnect\n");
goto retry;
}
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6bd690b5a061..52cfe99ae056 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2544,11 +2544,6 @@ int ocfs2_super_lock(struct ocfs2_super *osb,
* refreshed, so we do it here. Of course, making sense of
* everything is up to the caller :) */
status = ocfs2_should_refresh_lock_res(lockres);
- if (status < 0) {
- ocfs2_cluster_unlock(osb, lockres, level);
- mlog_errno(status);
- goto bail;
- }
if (status) {
status = ocfs2_refresh_slot_info(osb);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8970dcf74de5..2930e231f3f9 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -828,7 +828,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
/*
* fs-writeback will release the dirty pages without page lock
* whose offset are over inode size, the release happens at
- * block_write_full_page_endio().
+ * block_write_full_page().
*/
i_size_write(inode, abs_to);
inode->i_blocks = ocfs2_inode_sector_count(inode);
@@ -2233,16 +2233,13 @@ out:
return ret;
}
-static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
- const struct iovec *iov,
- unsigned long nr_segs,
- loff_t pos)
+static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
+ struct iov_iter *from)
{
int ret, direct_io, appending, rw_level, have_alloc_sem = 0;
int can_do_direct, has_refcount = 0;
ssize_t written = 0;
- size_t ocount; /* original count */
- size_t count; /* after file limit checks */
+ size_t count = iov_iter_count(from);
loff_t old_size, *ppos = &iocb->ki_pos;
u32 old_clusters;
struct file *file = iocb->ki_filp;
@@ -2256,7 +2253,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
file->f_path.dentry->d_name.len,
file->f_path.dentry->d_name.name,
- (unsigned int)nr_segs);
+ (unsigned int)from->nr_segs); /* GRRRRR */
if (iocb->ki_nbytes == 0)
return 0;
@@ -2354,29 +2351,21 @@ relock:
/* communicate with ocfs2_dio_end_io */
ocfs2_iocb_set_rw_locked(iocb, rw_level);
- ret = generic_segment_checks(iov, &nr_segs, &ocount,
- VERIFY_READ);
- if (ret)
- goto out_dio;
-
- count = ocount;
ret = generic_write_checks(file, ppos, &count,
S_ISBLK(inode->i_mode));
if (ret)
goto out_dio;
+ iov_iter_truncate(from, count);
if (direct_io) {
- written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
- count, ocount);
+ written = generic_file_direct_write(iocb, from, *ppos);
if (written < 0) {
ret = written;
goto out_dio;
}
} else {
- struct iov_iter from;
- iov_iter_init(&from, iov, nr_segs, count, 0);
current->backing_dev_info = file->f_mapping->backing_dev_info;
- written = generic_perform_write(file, &from, *ppos);
+ written = generic_perform_write(file, from, *ppos);
if (likely(written >= 0))
iocb->ki_pos = *ppos + written;
current->backing_dev_info = NULL;
@@ -2441,84 +2430,6 @@ out_sems:
return ret;
}
-static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
- struct file *out,
- struct splice_desc *sd)
-{
- int ret;
-
- ret = ocfs2_prepare_inode_for_write(out, &sd->pos,
- sd->total_len, 0, NULL, NULL);
- if (ret < 0) {
- mlog_errno(ret);
- return ret;
- }
-
- return splice_from_pipe_feed(pipe, sd, pipe_to_file);
-}
-
-static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
- struct file *out,
- loff_t *ppos,
- size_t len,
- unsigned int flags)
-{
- int ret;
- struct address_space *mapping = out->f_mapping;
- struct inode *inode = mapping->host;
- struct splice_desc sd = {
- .total_len = len,
- .flags = flags,
- .pos = *ppos,
- .u.file = out,
- };
-
-
- trace_ocfs2_file_splice_write(inode, out, out->f_path.dentry,
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- out->f_path.dentry->d_name.len,
- out->f_path.dentry->d_name.name, len);
-
- pipe_lock(pipe);
-
- splice_from_pipe_begin(&sd);
- do {
- ret = splice_from_pipe_next(pipe, &sd);
- if (ret <= 0)
- break;
-
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
- ret = ocfs2_rw_lock(inode, 1);
- if (ret < 0)
- mlog_errno(ret);
- else {
- ret = ocfs2_splice_to_file(pipe, out, &sd);
- ocfs2_rw_unlock(inode, 1);
- }
- mutex_unlock(&inode->i_mutex);
- } while (ret > 0);
- splice_from_pipe_end(pipe, &sd);
-
- pipe_unlock(pipe);
-
- if (sd.num_spliced)
- ret = sd.num_spliced;
-
- if (ret > 0) {
- int err;
-
- err = generic_write_sync(out, *ppos, ret);
- if (err)
- ret = err;
- else
- *ppos += ret;
-
- balance_dirty_pages_ratelimited(mapping);
- }
-
- return ret;
-}
-
static ssize_t ocfs2_file_splice_read(struct file *in,
loff_t *ppos,
struct pipe_inode_info *pipe,
@@ -2534,7 +2445,7 @@ static ssize_t ocfs2_file_splice_read(struct file *in,
in->f_path.dentry->d_name.name, len);
/*
- * See the comment in ocfs2_file_aio_read()
+ * See the comment in ocfs2_file_read_iter()
*/
ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
if (ret < 0) {
@@ -2549,10 +2460,8 @@ bail:
return ret;
}
-static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
- const struct iovec *iov,
- unsigned long nr_segs,
- loff_t pos)
+static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
+ struct iov_iter *to)
{
int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
struct file *filp = iocb->ki_filp;
@@ -2561,7 +2470,8 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
filp->f_path.dentry->d_name.len,
- filp->f_path.dentry->d_name.name, nr_segs);
+ filp->f_path.dentry->d_name.name,
+ to->nr_segs); /* GRRRRR */
if (!inode) {
@@ -2606,13 +2516,13 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
}
ocfs2_inode_unlock(inode, lock_level);
- ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
+ ret = generic_file_read_iter(iocb, to);
trace_generic_file_aio_read_ret(ret);
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
- /* see ocfs2_file_aio_write */
+ /* see ocfs2_file_write_iter */
if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
rw_level = -1;
have_alloc_sem = 0;
@@ -2705,14 +2615,14 @@ const struct inode_operations ocfs2_special_file_iops = {
*/
const struct file_operations ocfs2_fops = {
.llseek = ocfs2_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
.mmap = ocfs2_mmap,
.fsync = ocfs2_sync_file,
.release = ocfs2_file_release,
.open = ocfs2_file_open,
- .aio_read = ocfs2_file_aio_read,
- .aio_write = ocfs2_file_aio_write,
+ .read_iter = ocfs2_file_read_iter,
+ .write_iter = ocfs2_file_write_iter,
.unlocked_ioctl = ocfs2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ocfs2_compat_ioctl,
@@ -2720,7 +2630,7 @@ const struct file_operations ocfs2_fops = {
.lock = ocfs2_lock,
.flock = ocfs2_flock,
.splice_read = ocfs2_file_splice_read,
- .splice_write = ocfs2_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
@@ -2753,21 +2663,21 @@ const struct file_operations ocfs2_dops = {
*/
const struct file_operations ocfs2_fops_no_plocks = {
.llseek = ocfs2_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
.mmap = ocfs2_mmap,
.fsync = ocfs2_sync_file,
.release = ocfs2_file_release,
.open = ocfs2_file_open,
- .aio_read = ocfs2_file_aio_read,
- .aio_write = ocfs2_file_aio_write,
+ .read_iter = ocfs2_file_read_iter,
+ .write_iter = ocfs2_file_write_iter,
.unlocked_ioctl = ocfs2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ocfs2_compat_ioctl,
#endif
.flock = ocfs2_flock,
.splice_read = ocfs2_file_splice_read,
- .splice_write = ocfs2_file_splice_write,
+ .splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 490229f43731..6f66b3751ace 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -143,8 +143,8 @@ bail:
return status;
}
-int ocfs2_info_handle_blocksize(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_blocksize(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_blocksize oib;
@@ -167,8 +167,8 @@ bail:
return status;
}
-int ocfs2_info_handle_clustersize(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_clustersize(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_clustersize oic;
@@ -192,8 +192,8 @@ bail:
return status;
}
-int ocfs2_info_handle_maxslots(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_maxslots(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_maxslots oim;
@@ -217,8 +217,8 @@ bail:
return status;
}
-int ocfs2_info_handle_label(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_label(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_label oil;
@@ -242,8 +242,8 @@ bail:
return status;
}
-int ocfs2_info_handle_uuid(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_uuid(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_uuid oiu;
@@ -267,8 +267,8 @@ bail:
return status;
}
-int ocfs2_info_handle_fs_features(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_fs_features(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_fs_features oif;
@@ -294,8 +294,8 @@ bail:
return status;
}
-int ocfs2_info_handle_journal_size(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_journal_size(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_journal_size oij;
@@ -319,9 +319,10 @@ bail:
return status;
}
-int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
- struct inode *inode_alloc, u64 blkno,
- struct ocfs2_info_freeinode *fi, u32 slot)
+static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
+ struct inode *inode_alloc, u64 blkno,
+ struct ocfs2_info_freeinode *fi,
+ u32 slot)
{
int status = 0, unlock = 0;
@@ -366,8 +367,8 @@ bail:
return status;
}
-int ocfs2_info_handle_freeinode(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_freeinode(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
u32 i;
u64 blkno = -1;
@@ -462,19 +463,19 @@ static void o2ffg_update_stats(struct ocfs2_info_freefrag_stats *stats,
stats->ffs_free_chunks_real++;
}
-void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg,
- unsigned int chunksize)
+static void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg,
+ unsigned int chunksize)
{
o2ffg_update_histogram(&(ffg->iff_ffs.ffs_fc_hist), chunksize);
o2ffg_update_stats(&(ffg->iff_ffs), chunksize);
}
-int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb,
- struct inode *gb_inode,
- struct ocfs2_dinode *gb_dinode,
- struct ocfs2_chain_rec *rec,
- struct ocfs2_info_freefrag *ffg,
- u32 chunks_in_group)
+static int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb,
+ struct inode *gb_inode,
+ struct ocfs2_dinode *gb_dinode,
+ struct ocfs2_chain_rec *rec,
+ struct ocfs2_info_freefrag *ffg,
+ u32 chunks_in_group)
{
int status = 0, used;
u64 blkno;
@@ -572,9 +573,9 @@ bail:
return status;
}
-int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb,
- struct inode *gb_inode, u64 blkno,
- struct ocfs2_info_freefrag *ffg)
+static int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb,
+ struct inode *gb_inode, u64 blkno,
+ struct ocfs2_info_freefrag *ffg)
{
u32 chunks_in_group;
int status = 0, unlock = 0, i;
@@ -652,8 +653,8 @@ bail:
return status;
}
-int ocfs2_info_handle_freefrag(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_freefrag(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
u64 blkno = -1;
char namebuf[40];
@@ -723,8 +724,8 @@ out_err:
return status;
}
-int ocfs2_info_handle_unknown(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_unknown(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_request oir;
@@ -752,8 +753,8 @@ bail:
* - distinguish different requests.
* - validate size of different requests.
*/
-int ocfs2_info_handle_request(struct inode *inode,
- struct ocfs2_info_request __user *req)
+static int ocfs2_info_handle_request(struct inode *inode,
+ struct ocfs2_info_request __user *req)
{
int status = -EFAULT;
struct ocfs2_info_request oir;
@@ -811,8 +812,8 @@ bail:
return status;
}
-int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx,
- u64 *req_addr, int compat_flag)
+static int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx,
+ u64 *req_addr, int compat_flag)
{
int status = -EFAULT;
u64 __user *bp = NULL;
@@ -849,8 +850,8 @@ bail:
* a better backward&forward compatibility, since a small piece of
* request will be less likely to be broken if disk layout get changed.
*/
-int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info,
- int compat_flag)
+static int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info,
+ int compat_flag)
{
int i, status = 0;
u64 req_addr;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 03ea9314fecd..4b0c68849b36 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -30,6 +30,7 @@
#include <linux/kthread.h>
#include <linux/time.h>
#include <linux/random.h>
+#include <linux/delay.h>
#include <cluster/masklog.h>
@@ -2185,8 +2186,20 @@ static int ocfs2_commit_thread(void *arg)
|| kthread_should_stop());
status = ocfs2_commit_cache(osb);
- if (status < 0)
- mlog_errno(status);
+ if (status < 0) {
+ static unsigned long abort_warn_time;
+
+ /* Warn about this once per minute */
+ if (printk_timed_ratelimit(&abort_warn_time, 60*HZ))
+ mlog(ML_ERROR, "status = %d, journal is "
+ "already aborted.\n", status);
+ /*
+ * After ocfs2_commit_cache() fails, j_num_trans has a
+ * non-zero value. Sleep here to avoid a busy-wait
+ * loop.
+ */
+ msleep_interruptible(1000);
+ }
if (kthread_should_stop() && atomic_read(&journal->j_num_trans)){
mlog(ML_KTHREAD,
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 2060fc398445..8add6f1030d7 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -205,6 +205,21 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
return inode;
}
+static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb,
+ struct dentry *dentry, struct inode *inode)
+{
+ struct ocfs2_dentry_lock *dl = dentry->d_fsdata;
+
+ ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
+ ocfs2_lock_res_free(&dl->dl_lockres);
+ BUG_ON(dl->dl_count != 1);
+ spin_lock(&dentry_attach_lock);
+ dentry->d_fsdata = NULL;
+ spin_unlock(&dentry_attach_lock);
+ kfree(dl);
+ iput(inode);
+}
+
static int ocfs2_mknod(struct inode *dir,
struct dentry *dentry,
umode_t mode,
@@ -231,6 +246,7 @@ static int ocfs2_mknod(struct inode *dir,
sigset_t oldset;
int did_block_signals = 0;
struct posix_acl *default_acl = NULL, *acl = NULL;
+ struct ocfs2_dentry_lock *dl = NULL;
trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
(unsigned long long)OCFS2_I(dir)->ip_blkno,
@@ -423,6 +439,8 @@ static int ocfs2_mknod(struct inode *dir,
goto leave;
}
+ dl = dentry->d_fsdata;
+
status = ocfs2_add_entry(handle, dentry, inode,
OCFS2_I(inode)->ip_blkno, parent_fe_bh,
&lookup);
@@ -469,6 +487,9 @@ leave:
* ocfs2_delete_inode will mutex_lock again.
*/
if ((status < 0) && inode) {
+ if (dl)
+ ocfs2_cleanup_add_entry_failure(osb, dentry, inode);
+
OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
clear_nlink(inode);
iput(inode);
@@ -991,6 +1012,65 @@ leave:
return status;
}
+static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
+ u64 src_inode_no, u64 dest_inode_no)
+{
+ int ret = 0, i = 0;
+ u64 parent_inode_no = 0;
+ u64 child_inode_no = src_inode_no;
+ struct inode *child_inode;
+
+#define MAX_LOOKUP_TIMES 32
+ while (1) {
+ child_inode = ocfs2_iget(osb, child_inode_no, 0, 0);
+ if (IS_ERR(child_inode)) {
+ ret = PTR_ERR(child_inode);
+ break;
+ }
+
+ ret = ocfs2_inode_lock(child_inode, NULL, 0);
+ if (ret < 0) {
+ iput(child_inode);
+ if (ret != -ENOENT)
+ mlog_errno(ret);
+ break;
+ }
+
+ ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2,
+ &parent_inode_no);
+ ocfs2_inode_unlock(child_inode, 0);
+ iput(child_inode);
+ if (ret < 0) {
+ ret = -ENOENT;
+ break;
+ }
+
+ if (parent_inode_no == dest_inode_no) {
+ ret = 1;
+ break;
+ }
+
+ if (parent_inode_no == osb->root_inode->i_ino) {
+ ret = 0;
+ break;
+ }
+
+ child_inode_no = parent_inode_no;
+
+ if (++i >= MAX_LOOKUP_TIMES) {
+ mlog(ML_NOTICE, "max lookup times reached, filesystem "
+ "may have nested directories, "
+ "src inode: %llu, dest inode: %llu.\n",
+ (unsigned long long)src_inode_no,
+ (unsigned long long)dest_inode_no);
+ ret = 0;
+ break;
+ }
+ }
+
+ return ret;
+}
+
/*
* The only place this should be used is rename!
* if they have the same id, then the 1st one is the only one locked.
@@ -1002,6 +1082,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
struct inode *inode2)
{
int status;
+ int inode1_is_ancestor, inode2_is_ancestor;
struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
struct ocfs2_inode_info *oi2 = OCFS2_I(inode2);
struct buffer_head **tmpbh;
@@ -1015,9 +1096,26 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
if (*bh2)
*bh2 = NULL;
- /* we always want to lock the one with the lower lockid first. */
+ /* we always want to lock the one with the lower lockid first.
+ * and if they are nested, we lock ancestor first */
if (oi1->ip_blkno != oi2->ip_blkno) {
- if (oi1->ip_blkno < oi2->ip_blkno) {
+ inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno,
+ oi1->ip_blkno);
+ if (inode1_is_ancestor < 0) {
+ status = inode1_is_ancestor;
+ goto bail;
+ }
+
+ inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno,
+ oi2->ip_blkno);
+ if (inode2_is_ancestor < 0) {
+ status = inode2_is_ancestor;
+ goto bail;
+ }
+
+ if ((inode1_is_ancestor == 1) ||
+ (oi1->ip_blkno < oi2->ip_blkno &&
+ inode2_is_ancestor == 0)) {
/* switch id1 and id2 around */
tmpbh = bh2;
bh2 = bh1;
@@ -1098,6 +1196,7 @@ static int ocfs2_rename(struct inode *old_dir,
struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, };
struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
struct ocfs2_dir_lookup_result target_insert = { NULL, };
+ bool should_add_orphan = false;
/* At some point it might be nice to break this function up a
* bit. */
@@ -1134,6 +1233,21 @@ static int ocfs2_rename(struct inode *old_dir,
goto bail;
}
rename_lock = 1;
+
+ /* here we cannot guarantee the inodes haven't just been
+ * changed, so check if they are nested again */
+ status = ocfs2_check_if_ancestor(osb, new_dir->i_ino,
+ old_inode->i_ino);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ } else if (status == 1) {
+ status = -EPERM;
+ trace_ocfs2_rename_not_permitted(
+ (unsigned long long)old_inode->i_ino,
+ (unsigned long long)new_dir->i_ino);
+ goto bail;
+ }
}
/* if old and new are the same, this'll just do one lock. */
@@ -1304,6 +1418,7 @@ static int ocfs2_rename(struct inode *old_dir,
mlog_errno(status);
goto bail;
}
+ should_add_orphan = true;
}
} else {
BUG_ON(new_dentry->d_parent->d_inode != new_dir);
@@ -1348,17 +1463,6 @@ static int ocfs2_rename(struct inode *old_dir,
goto bail;
}
- if (S_ISDIR(new_inode->i_mode) ||
- (ocfs2_read_links_count(newfe) == 1)) {
- status = ocfs2_orphan_add(osb, handle, new_inode,
- newfe_bh, orphan_name,
- &orphan_insert, orphan_dir);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
- }
-
/* change the dirent to point to the correct inode */
status = ocfs2_update_entry(new_dir, handle, &target_lookup_res,
old_inode);
@@ -1373,6 +1477,15 @@ static int ocfs2_rename(struct inode *old_dir,
else
ocfs2_add_links_count(newfe, -1);
ocfs2_journal_dirty(handle, newfe_bh);
+ if (should_add_orphan) {
+ status = ocfs2_orphan_add(osb, handle, new_inode,
+ newfe_bh, orphan_name,
+ &orphan_insert, orphan_dir);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
+ }
} else {
/* if the name was not found in new_dir, add it now */
status = ocfs2_add_entry(handle, new_dentry, old_inode,
@@ -1642,6 +1755,7 @@ static int ocfs2_symlink(struct inode *dir,
struct ocfs2_dir_lookup_result lookup = { NULL, };
sigset_t oldset;
int did_block_signals = 0;
+ struct ocfs2_dentry_lock *dl = NULL;
trace_ocfs2_symlink_begin(dir, dentry, symname,
dentry->d_name.len, dentry->d_name.name);
@@ -1830,6 +1944,8 @@ static int ocfs2_symlink(struct inode *dir,
goto bail;
}
+ dl = dentry->d_fsdata;
+
status = ocfs2_add_entry(handle, dentry, inode,
le64_to_cpu(fe->i_blkno), parent_fe_bh,
&lookup);
@@ -1864,6 +1980,9 @@ bail:
if (xattr_ac)
ocfs2_free_alloc_context(xattr_ac);
if ((status < 0) && inode) {
+ if (dl)
+ ocfs2_cleanup_add_entry_failure(osb, dentry, inode);
+
OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
clear_nlink(inode);
iput(inode);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 8d64a97a9d5e..bbec539230fd 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -422,6 +422,7 @@ struct ocfs2_super
struct inode *osb_tl_inode;
struct buffer_head *osb_tl_bh;
struct delayed_work osb_truncate_log_wq;
+ atomic_t osb_tl_disable;
/*
* How many clusters in our truncate log.
* It must be protected by osb_tl_inode->i_mutex.
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 1b60c62aa9d6..6cb019b7c6a8 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2292,6 +2292,8 @@ TRACE_EVENT(ocfs2_rename,
__entry->new_len, __get_str(new_name))
);
+DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_rename_not_permitted);
+
TRACE_EVENT(ocfs2_rename_target_exists,
TP_PROTO(int new_len, const char *new_name),
TP_ARGS(new_len, new_name),
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 6ba4bcbc4796..636aab69ead5 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -1408,10 +1408,9 @@ static void swap_refcount_rec(void *a, void *b, int size)
{
struct ocfs2_refcount_rec *l = a, *r = b, tmp;
- tmp = *(struct ocfs2_refcount_rec *)l;
- *(struct ocfs2_refcount_rec *)l =
- *(struct ocfs2_refcount_rec *)r;
- *(struct ocfs2_refcount_rec *)r = tmp;
+ tmp = *l;
+ *l = *r;
+ *r = tmp;
}
/*
@@ -4289,9 +4288,16 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
goto out;
}
+ error = ocfs2_rw_lock(inode, 1);
+ if (error) {
+ mlog_errno(error);
+ goto out;
+ }
+
error = ocfs2_inode_lock(inode, &old_bh, 1);
if (error) {
mlog_errno(error);
+ ocfs2_rw_unlock(inode, 1);
goto out;
}
@@ -4303,6 +4309,7 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
up_write(&OCFS2_I(inode)->ip_xattr_sem);
ocfs2_inode_unlock(inode, 1);
+ ocfs2_rw_unlock(inode, 1);
brelse(old_bh);
if (error) {
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index 822ebc10f281..d5da6f624142 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -53,8 +53,6 @@
*/
static u16 ocfs2_calc_new_backup_super(struct inode *inode,
struct ocfs2_group_desc *gd,
- int new_clusters,
- u32 first_new_cluster,
u16 cl_cpg,
int set)
{
@@ -127,8 +125,6 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
OCFS2_FEATURE_COMPAT_BACKUP_SB)) {
backups = ocfs2_calc_new_backup_super(bm_inode,
group,
- new_clusters,
- first_new_cluster,
cl_cpg, 1);
le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
}
@@ -157,7 +153,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
spin_lock(&OCFS2_I(bm_inode)->ip_lock);
OCFS2_I(bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
- le64_add_cpu(&fe->i_size, new_clusters << osb->s_clustersize_bits);
+ le64_add_cpu(&fe->i_size, (u64)new_clusters << osb->s_clustersize_bits);
spin_unlock(&OCFS2_I(bm_inode)->ip_lock);
i_size_write(bm_inode, le64_to_cpu(fe->i_size));
@@ -167,8 +163,6 @@ out_rollback:
if (ret < 0) {
ocfs2_calc_new_backup_super(bm_inode,
group,
- new_clusters,
- first_new_cluster,
cl_cpg, 0);
le16_add_cpu(&group->bg_free_bits_count, backups);
le16_add_cpu(&group->bg_bits, -1 * num_bits);
@@ -569,7 +563,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input)
spin_lock(&OCFS2_I(main_bm_inode)->ip_lock);
OCFS2_I(main_bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
- le64_add_cpu(&fe->i_size, input->clusters << osb->s_clustersize_bits);
+ le64_add_cpu(&fe->i_size, (u64)input->clusters << osb->s_clustersize_bits);
spin_unlock(&OCFS2_I(main_bm_inode)->ip_lock);
i_size_write(main_bm_inode, le64_to_cpu(fe->i_size));
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 83f1a665ae97..5d965e83bd43 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -709,7 +709,7 @@ static struct ctl_table ocfs2_root_table[] = {
{ }
};
-static struct ctl_table_header *ocfs2_table_header = NULL;
+static struct ctl_table_header *ocfs2_table_header;
/*
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a7cdd56f4c79..ddb662b32447 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -75,7 +75,7 @@
#include "buffer_head_io.h"
-static struct kmem_cache *ocfs2_inode_cachep = NULL;
+static struct kmem_cache *ocfs2_inode_cachep;
struct kmem_cache *ocfs2_dquot_cachep;
struct kmem_cache *ocfs2_qf_chunk_cachep;
@@ -85,7 +85,7 @@ struct kmem_cache *ocfs2_qf_chunk_cachep;
* workqueue and schedule on our own. */
struct workqueue_struct *ocfs2_wq = NULL;
-static struct dentry *ocfs2_debugfs_root = NULL;
+static struct dentry *ocfs2_debugfs_root;
MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");
@@ -1925,15 +1925,11 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
ocfs2_shutdown_local_alloc(osb);
+ ocfs2_truncate_log_shutdown(osb);
+
/* This will disable recovery and flush any recovery work. */
ocfs2_recovery_exit(osb);
- /*
- * During dismount, when it recovers another node it will call
- * ocfs2_recover_orphans and queue delayed work osb_truncate_log_wq.
- */
- ocfs2_truncate_log_shutdown(osb);
-
ocfs2_journal_shutdown(osb);
ocfs2_sync_blockdev(sb);
@@ -2292,8 +2288,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
- osb->vol_label[63] = '\0';
+ strlcpy(osb->vol_label, di->id2.i_super.s_label,
+ OCFS2_MAX_VOL_LABEL_LEN);
osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno);
osb->system_dir_blkno = le64_to_cpu(di->id2.i_super.s_system_dir_blkno);
osb->first_cluster_group_blkno =
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 52eaf33d346f..82e17b076ce7 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -67,7 +67,7 @@ struct ocfs2_meta_cache_item {
sector_t c_block;
};
-static struct kmem_cache *ocfs2_uptodate_cachep = NULL;
+static struct kmem_cache *ocfs2_uptodate_cachep;
u64 ocfs2_metadata_cache_owner(struct ocfs2_caching_info *ci)
{
OpenPOWER on IntegriCloud