summaryrefslogtreecommitdiffstats
path: root/fs/dlm
diff options
context:
space:
mode:
Diffstat (limited to 'fs/dlm')
-rw-r--r--fs/dlm/lock.c53
-rw-r--r--fs/dlm/netlink.c2
-rw-r--r--fs/dlm/plock.c185
-rw-r--r--fs/dlm/recover.c39
4 files changed, 160 insertions, 119 deletions
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index d4e204473..0864481d8 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1858,7 +1858,7 @@ static void del_timeout(struct dlm_lkb *lkb)
void dlm_scan_timeout(struct dlm_ls *ls)
{
struct dlm_rsb *r;
- struct dlm_lkb *lkb;
+ struct dlm_lkb *lkb = NULL, *iter;
int do_cancel, do_warn;
s64 wait_us;
@@ -1869,27 +1869,28 @@ void dlm_scan_timeout(struct dlm_ls *ls)
do_cancel = 0;
do_warn = 0;
mutex_lock(&ls->ls_timeout_mutex);
- list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) {
+ list_for_each_entry(iter, &ls->ls_timeout, lkb_time_list) {
wait_us = ktime_to_us(ktime_sub(ktime_get(),
- lkb->lkb_timestamp));
+ iter->lkb_timestamp));
- if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) &&
- wait_us >= (lkb->lkb_timeout_cs * 10000))
+ if ((iter->lkb_exflags & DLM_LKF_TIMEOUT) &&
+ wait_us >= (iter->lkb_timeout_cs * 10000))
do_cancel = 1;
- if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) &&
+ if ((iter->lkb_flags & DLM_IFL_WATCH_TIMEWARN) &&
wait_us >= dlm_config.ci_timewarn_cs * 10000)
do_warn = 1;
if (!do_cancel && !do_warn)
continue;
- hold_lkb(lkb);
+ hold_lkb(iter);
+ lkb = iter;
break;
}
mutex_unlock(&ls->ls_timeout_mutex);
- if (!do_cancel && !do_warn)
+ if (!lkb)
break;
r = lkb->lkb_resource;
@@ -5243,21 +5244,18 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls)
{
- struct dlm_lkb *lkb;
- int found = 0;
+ struct dlm_lkb *lkb = NULL, *iter;
mutex_lock(&ls->ls_waiters_mutex);
- list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
- if (lkb->lkb_flags & DLM_IFL_RESEND) {
- hold_lkb(lkb);
- found = 1;
+ list_for_each_entry(iter, &ls->ls_waiters, lkb_wait_reply) {
+ if (iter->lkb_flags & DLM_IFL_RESEND) {
+ hold_lkb(iter);
+ lkb = iter;
break;
}
}
mutex_unlock(&ls->ls_waiters_mutex);
- if (!found)
- lkb = NULL;
return lkb;
}
@@ -5916,37 +5914,36 @@ int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, void *name, unsigned int namelen,
unsigned long timeout_cs, uint32_t *lkid)
{
- struct dlm_lkb *lkb;
+ struct dlm_lkb *lkb = NULL, *iter;
struct dlm_user_args *ua;
int found_other_mode = 0;
- int found = 0;
int rv = 0;
mutex_lock(&ls->ls_orphans_mutex);
- list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) {
- if (lkb->lkb_resource->res_length != namelen)
+ list_for_each_entry(iter, &ls->ls_orphans, lkb_ownqueue) {
+ if (iter->lkb_resource->res_length != namelen)
continue;
- if (memcmp(lkb->lkb_resource->res_name, name, namelen))
+ if (memcmp(iter->lkb_resource->res_name, name, namelen))
continue;
- if (lkb->lkb_grmode != mode) {
+ if (iter->lkb_grmode != mode) {
found_other_mode = 1;
continue;
}
- found = 1;
- list_del_init(&lkb->lkb_ownqueue);
- lkb->lkb_flags &= ~DLM_IFL_ORPHAN;
- *lkid = lkb->lkb_id;
+ lkb = iter;
+ list_del_init(&iter->lkb_ownqueue);
+ iter->lkb_flags &= ~DLM_IFL_ORPHAN;
+ *lkid = iter->lkb_id;
break;
}
mutex_unlock(&ls->ls_orphans_mutex);
- if (!found && found_other_mode) {
+ if (!lkb && found_other_mode) {
rv = -EAGAIN;
goto out;
}
- if (!found) {
+ if (!lkb) {
rv = -ENOENT;
goto out;
}
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index 43a96c330..ea50f5961 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -115,7 +115,7 @@ static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb)
void dlm_timeout_warn(struct dlm_lkb *lkb)
{
- struct sk_buff *uninitialized_var(send_skb);
+ struct sk_buff *send_skb;
struct dlm_lock_data *data;
size_t size;
int rv;
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index e0c05e08d..c6079f6c6 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -22,20 +22,20 @@ static struct list_head recv_list;
static wait_queue_head_t send_wq;
static wait_queue_head_t recv_wq;
-struct plock_op {
- struct list_head list;
- int done;
- struct dlm_plock_info info;
- int (*callback)(struct file_lock *fl, int result);
-};
-
-struct plock_xop {
- struct plock_op xop;
+struct plock_async_data {
void *fl;
void *file;
struct file_lock flc;
+ int (*callback)(struct file_lock *fl, int result);
};
+struct plock_op {
+ struct list_head list;
+ int done;
+ struct dlm_plock_info info;
+ /* if set indicates async handling */
+ struct plock_async_data *data;
+};
static inline void set_version(struct dlm_plock_info *info)
{
@@ -61,6 +61,12 @@ static int check_version(struct dlm_plock_info *info)
return 0;
}
+static void dlm_release_plock_op(struct plock_op *op)
+{
+ kfree(op->data);
+ kfree(op);
+}
+
static void send_op(struct plock_op *op)
{
set_version(&op->info);
@@ -77,8 +83,7 @@ static void send_op(struct plock_op *op)
abandoned waiter. So, we have to insert the unlock-close when the
lock call is interrupted. */
-static void do_unlock_close(struct dlm_ls *ls, u64 number,
- struct file *file, struct file_lock *fl)
+static void do_unlock_close(const struct dlm_plock_info *info)
{
struct plock_op *op;
@@ -87,15 +92,12 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number,
return;
op->info.optype = DLM_PLOCK_OP_UNLOCK;
- op->info.pid = fl->fl_pid;
- op->info.fsid = ls->ls_global_id;
- op->info.number = number;
+ op->info.pid = info->pid;
+ op->info.fsid = info->fsid;
+ op->info.number = info->number;
op->info.start = 0;
op->info.end = OFFSET_MAX;
- if (fl->fl_lmops && fl->fl_lmops->lm_grant)
- op->info.owner = (__u64) fl->fl_pid;
- else
- op->info.owner = (__u64)(long) fl->fl_owner;
+ op->info.owner = info->owner;
op->info.flags |= DLM_PLOCK_FL_CLOSE;
send_op(op);
@@ -104,22 +106,21 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number,
int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
int cmd, struct file_lock *fl)
{
+ struct plock_async_data *op_data;
struct dlm_ls *ls;
struct plock_op *op;
- struct plock_xop *xop;
int rv;
ls = dlm_find_lockspace_local(lockspace);
if (!ls)
return -EINVAL;
- xop = kzalloc(sizeof(*xop), GFP_NOFS);
- if (!xop) {
+ op = kzalloc(sizeof(*op), GFP_NOFS);
+ if (!op) {
rv = -ENOMEM;
goto out;
}
- op = &xop->xop;
op->info.optype = DLM_PLOCK_OP_LOCK;
op->info.pid = fl->fl_pid;
op->info.ex = (fl->fl_type == F_WRLCK);
@@ -128,35 +129,45 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
op->info.number = number;
op->info.start = fl->fl_start;
op->info.end = fl->fl_end;
+ /* async handling */
if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
+ op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
+ if (!op_data) {
+ dlm_release_plock_op(op);
+ rv = -ENOMEM;
+ goto out;
+ }
+
/* fl_owner is lockd which doesn't distinguish
processes on the nfs client */
op->info.owner = (__u64) fl->fl_pid;
- op->callback = fl->fl_lmops->lm_grant;
- locks_init_lock(&xop->flc);
- locks_copy_lock(&xop->flc, fl);
- xop->fl = fl;
- xop->file = file;
+ op_data->callback = fl->fl_lmops->lm_grant;
+ locks_init_lock(&op_data->flc);
+ locks_copy_lock(&op_data->flc, fl);
+ op_data->fl = fl;
+ op_data->file = file;
+
+ op->data = op_data;
+
+ send_op(op);
+ rv = FILE_LOCK_DEFERRED;
+ goto out;
} else {
op->info.owner = (__u64)(long) fl->fl_owner;
}
send_op(op);
- if (!op->callback) {
- rv = wait_event_interruptible(recv_wq, (op->done != 0));
- if (rv == -ERESTARTSYS) {
- log_debug(ls, "dlm_posix_lock: wait killed %llx",
- (unsigned long long)number);
- spin_lock(&ops_lock);
- list_del(&op->list);
- spin_unlock(&ops_lock);
- kfree(xop);
- do_unlock_close(ls, number, file, fl);
- goto out;
- }
- } else {
- rv = FILE_LOCK_DEFERRED;
+ rv = wait_event_killable(recv_wq, (op->done != 0));
+ if (rv == -ERESTARTSYS) {
+ spin_lock(&ops_lock);
+ list_del(&op->list);
+ spin_unlock(&ops_lock);
+ log_debug(ls, "%s: wait interrupted %x %llx pid %d",
+ __func__, ls->ls_global_id,
+ (unsigned long long)number, op->info.pid);
+ dlm_release_plock_op(op);
+ do_unlock_close(&op->info);
goto out;
}
@@ -176,7 +187,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
(unsigned long long)number);
}
- kfree(xop);
+ dlm_release_plock_op(op);
out:
dlm_put_lockspace(ls);
return rv;
@@ -186,11 +197,11 @@ EXPORT_SYMBOL_GPL(dlm_posix_lock);
/* Returns failure iff a successful lock operation should be canceled */
static int dlm_plock_callback(struct plock_op *op)
{
+ struct plock_async_data *op_data = op->data;
struct file *file;
struct file_lock *fl;
struct file_lock *flc;
int (*notify)(struct file_lock *fl, int result) = NULL;
- struct plock_xop *xop = (struct plock_xop *)op;
int rv = 0;
spin_lock(&ops_lock);
@@ -202,10 +213,10 @@ static int dlm_plock_callback(struct plock_op *op)
spin_unlock(&ops_lock);
/* check if the following 2 are still valid or make a copy */
- file = xop->file;
- flc = &xop->flc;
- fl = xop->fl;
- notify = op->callback;
+ file = op_data->file;
+ flc = &op_data->flc;
+ fl = op_data->fl;
+ notify = op_data->callback;
if (op->info.rv) {
notify(fl, op->info.rv);
@@ -236,7 +247,7 @@ static int dlm_plock_callback(struct plock_op *op)
}
out:
- kfree(xop);
+ dlm_release_plock_op(op);
return rv;
}
@@ -306,7 +317,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
rv = 0;
out_free:
- kfree(op);
+ dlm_release_plock_op(op);
out:
dlm_put_lockspace(ls);
fl->fl_flags = fl_flags;
@@ -366,13 +377,15 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
locks_init_lock(fl);
fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
fl->fl_flags = FL_POSIX;
- fl->fl_pid = -op->info.pid;
+ fl->fl_pid = op->info.pid;
+ if (op->info.nodeid != dlm_our_nodeid())
+ fl->fl_pid = -fl->fl_pid;
fl->fl_start = op->info.start;
fl->fl_end = op->info.end;
rv = 0;
}
- kfree(op);
+ dlm_release_plock_op(op);
out:
dlm_put_lockspace(ls);
return rv;
@@ -395,7 +408,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
list_del(&op->list);
else
- list_move(&op->list, &recv_list);
+ list_move_tail(&op->list, &recv_list);
memcpy(&info, &op->info, sizeof(info));
}
spin_unlock(&ops_lock);
@@ -408,7 +421,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
(the process did not make an unlock call). */
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
- kfree(op);
+ dlm_release_plock_op(op);
if (copy_to_user(u, &info, sizeof(info)))
return -EFAULT;
@@ -420,9 +433,9 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
loff_t *ppos)
{
+ struct plock_op *op = NULL, *iter;
struct dlm_plock_info info;
- struct plock_op *op;
- int found = 0, do_callback = 0;
+ int do_callback = 0;
if (count != sizeof(info))
return -EINVAL;
@@ -433,31 +446,63 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
if (check_version(&info))
return -EINVAL;
+ /*
+ * The results for waiting ops (SETLKW) can be returned in any
+ * order, so match all fields to find the op. The results for
+ * non-waiting ops are returned in the order that they were sent
+ * to userspace, so match the result with the first non-waiting op.
+ */
spin_lock(&ops_lock);
- list_for_each_entry(op, &recv_list, list) {
- if (op->info.fsid == info.fsid &&
- op->info.number == info.number &&
- op->info.owner == info.owner) {
- list_del_init(&op->list);
- memcpy(&op->info, &info, sizeof(info));
- if (op->callback)
- do_callback = 1;
- else
- op->done = 1;
- found = 1;
- break;
+ if (info.wait) {
+ list_for_each_entry(iter, &recv_list, list) {
+ if (iter->info.fsid == info.fsid &&
+ iter->info.number == info.number &&
+ iter->info.owner == info.owner &&
+ iter->info.pid == info.pid &&
+ iter->info.start == info.start &&
+ iter->info.end == info.end &&
+ iter->info.ex == info.ex &&
+ iter->info.wait) {
+ op = iter;
+ break;
+ }
}
+ } else {
+ list_for_each_entry(iter, &recv_list, list) {
+ if (!iter->info.wait &&
+ iter->info.fsid == info.fsid) {
+ op = iter;
+ break;
+ }
+ }
+ }
+
+ if (op) {
+ /* Sanity check that op and info match. */
+ if (info.wait)
+ WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK);
+ else
+ WARN_ON(op->info.number != info.number ||
+ op->info.owner != info.owner ||
+ op->info.optype != info.optype);
+
+ list_del_init(&op->list);
+ memcpy(&op->info, &info, sizeof(info));
+ if (op->data)
+ do_callback = 1;
+ else
+ op->done = 1;
}
spin_unlock(&ops_lock);
- if (found) {
+ if (op) {
if (do_callback)
dlm_plock_callback(op);
else
wake_up(&recv_wq);
} else
- log_print("dev_write no op %x %llx", info.fsid,
- (unsigned long long)info.number);
+ log_print("%s: no op %x %llx", __func__,
+ info.fsid, (unsigned long long)info.number);
return count;
}
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index ce2aa54ca..98b710cc9 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -734,10 +734,9 @@ void dlm_recovered_lock(struct dlm_rsb *r)
static void recover_lvb(struct dlm_rsb *r)
{
- struct dlm_lkb *lkb, *high_lkb = NULL;
+ struct dlm_lkb *big_lkb = NULL, *iter, *high_lkb = NULL;
uint32_t high_seq = 0;
int lock_lvb_exists = 0;
- int big_lock_exists = 0;
int lvblen = r->res_ls->ls_lvblen;
if (!rsb_flag(r, RSB_NEW_MASTER2) &&
@@ -753,37 +752,37 @@ static void recover_lvb(struct dlm_rsb *r)
/* we are the new master, so figure out if VALNOTVALID should
be set, and set the rsb lvb from the best lkb available. */
- list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
- if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+ list_for_each_entry(iter, &r->res_grantqueue, lkb_statequeue) {
+ if (!(iter->lkb_exflags & DLM_LKF_VALBLK))
continue;
lock_lvb_exists = 1;
- if (lkb->lkb_grmode > DLM_LOCK_CR) {
- big_lock_exists = 1;
+ if (iter->lkb_grmode > DLM_LOCK_CR) {
+ big_lkb = iter;
goto setflag;
}
- if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
- high_lkb = lkb;
- high_seq = lkb->lkb_lvbseq;
+ if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) {
+ high_lkb = iter;
+ high_seq = iter->lkb_lvbseq;
}
}
- list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
- if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+ list_for_each_entry(iter, &r->res_convertqueue, lkb_statequeue) {
+ if (!(iter->lkb_exflags & DLM_LKF_VALBLK))
continue;
lock_lvb_exists = 1;
- if (lkb->lkb_grmode > DLM_LOCK_CR) {
- big_lock_exists = 1;
+ if (iter->lkb_grmode > DLM_LOCK_CR) {
+ big_lkb = iter;
goto setflag;
}
- if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
- high_lkb = lkb;
- high_seq = lkb->lkb_lvbseq;
+ if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) {
+ high_lkb = iter;
+ high_seq = iter->lkb_lvbseq;
}
}
@@ -792,7 +791,7 @@ static void recover_lvb(struct dlm_rsb *r)
goto out;
/* lvb is invalidated if only NL/CR locks remain */
- if (!big_lock_exists)
+ if (!big_lkb)
rsb_set_flag(r, RSB_VALNOTVALID);
if (!r->res_lvbptr) {
@@ -801,9 +800,9 @@ static void recover_lvb(struct dlm_rsb *r)
goto out;
}
- if (big_lock_exists) {
- r->res_lvbseq = lkb->lkb_lvbseq;
- memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen);
+ if (big_lkb) {
+ r->res_lvbseq = big_lkb->lkb_lvbseq;
+ memcpy(r->res_lvbptr, big_lkb->lkb_lvbptr, lvblen);
} else if (high_lkb) {
r->res_lvbseq = high_lkb->lkb_lvbseq;
memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen);