[PATCH 01/18] [GFS2] Clean up the glock core

From: swhiteho
Date: Fri Jul 11 2008 - 07:01:55 EST


From: Steven Whitehouse <swhiteho@xxxxxxxxxx>

This patch implements a number of cleanups to the core of the
GFS2 glock code. As a result a lot of code is removed. It looks
like a really big change, but actually a large part of this patch
is either removing or moving existing code.

There are some new bits too though, such as the new run_queue()
function which is considerably streamlined. Highlights of this
patch include:

o Fixes a cluster coherency bug during SH -> EX lock conversions
o Removes the "glmutex" code in favour of a single bit lock
o Removes the ->go_xmote_bh() for inodes since it was duplicating
->go_lock()
o We now only use the ->lm_lock() function for both locks and
unlocks (i.e. unlock is a lock with target mode LM_ST_UNLOCKED)
o The fast path is considerably shortly, giving performance gains
especially with lock_nolock
o The glock_workqueue is now used for all the callbacks from the DLM
which allows us to simplify the lock_dlm module (see following patch)
o The way is now open to make further changes such as eliminating the two
threads (gfs2_glockd and gfs2_scand) in favour of a more efficient
scheme.

This patch has undergone extensive testing with various test suites
so it should be pretty stable by now.

Signed-off-by: Steven Whitehouse <swhiteho@xxxxxxxxxx>
Cc: Bob Peterson <rpeterso@xxxxxxxxxx>

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d636b3e..519a54c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -45,21 +45,19 @@ struct gfs2_gl_hash_bucket {
struct hlist_head hb_list;
};

-struct glock_iter {
- int hash; /* hash bucket index */
- struct gfs2_sbd *sdp; /* incore superblock */
- struct gfs2_glock *gl; /* current glock struct */
- struct seq_file *seq; /* sequence file for debugfs */
- char string[512]; /* scratch space */
+struct gfs2_glock_iter {
+ int hash; /* hash bucket index */
+ struct gfs2_sbd *sdp; /* incore superblock */
+ struct gfs2_glock *gl; /* current glock struct */
+ char string[512]; /* scratch space */
};

typedef void (*glock_examiner) (struct gfs2_glock * gl);

static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
-static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
-static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
-static void gfs2_glock_drop_th(struct gfs2_glock *gl);
-static void run_queue(struct gfs2_glock *gl);
+static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl);
+#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { __dump_glock(NULL, gl); BUG(); } } while(0)
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);

static DECLARE_RWSEM(gfs2_umount_flush_sem);
static struct dentry *gfs2_root;
@@ -123,33 +121,6 @@ static inline rwlock_t *gl_lock_addr(unsigned int x)
#endif

/**
- * relaxed_state_ok - is a requested lock compatible with the current lock mode?
- * @actual: the current state of the lock
- * @requested: the lock state that was requested by the caller
- * @flags: the modifier flags passed in by the caller
- *
- * Returns: 1 if the locks are compatible, 0 otherwise
- */
-
-static inline int relaxed_state_ok(unsigned int actual, unsigned requested,
- int flags)
-{
- if (actual == requested)
- return 1;
-
- if (flags & GL_EXACT)
- return 0;
-
- if (actual == LM_ST_EXCLUSIVE && requested == LM_ST_SHARED)
- return 1;
-
- if (actual != LM_ST_UNLOCKED && (flags & LM_FLAG_ANY))
- return 1;
-
- return 0;
-}
-
-/**
* gl_hash() - Turn glock number into hash bucket number
* @lock: The glock number
*
@@ -211,17 +182,14 @@ static void gfs2_glock_hold(struct gfs2_glock *gl)
int gfs2_glock_put(struct gfs2_glock *gl)
{
int rv = 0;
- struct gfs2_sbd *sdp = gl->gl_sbd;

write_lock(gl_lock_addr(gl->gl_hash));
if (atomic_dec_and_test(&gl->gl_ref)) {
hlist_del(&gl->gl_list);
write_unlock(gl_lock_addr(gl->gl_hash));
- gfs2_assert(sdp, gl->gl_state == LM_ST_UNLOCKED);
- gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
- gfs2_assert(sdp, list_empty(&gl->gl_holders));
- gfs2_assert(sdp, list_empty(&gl->gl_waiters1));
- gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
+ GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_UNLOCKED);
+ GLOCK_BUG_ON(gl, !list_empty(&gl->gl_reclaim));
+ GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
glock_free(gl);
rv = 1;
goto out;
@@ -281,16 +249,382 @@ static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp,
return gl;
}

+/**
+ * may_grant - check if its ok to grant a new lock
+ * @gl: The glock
+ * @gh: The lock request which we wish to grant
+ *
+ * Returns: true if its ok to grant the lock
+ */
+
+static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
+{
+ const struct gfs2_holder *gh_head = list_entry(gl->gl_holders.next, const struct gfs2_holder, gh_list);
+ if ((gh->gh_state == LM_ST_EXCLUSIVE ||
+ gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
+ return 0;
+ if (gl->gl_state == gh->gh_state)
+ return 1;
+ if (gh->gh_flags & GL_EXACT)
+ return 0;
+ if (gh->gh_state == LM_ST_SHARED && gl->gl_state == LM_ST_EXCLUSIVE)
+ return 1;
+ if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
+ return 1;
+ return 0;
+}
+
+static void gfs2_holder_wake(struct gfs2_holder *gh)
+{
+ clear_bit(HIF_WAIT, &gh->gh_iflags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&gh->gh_iflags, HIF_WAIT);
+}
+
+/**
+ * do_promote - promote as many requests as possible on the current queue
+ * @gl: The glock
+ *
+ * Returns: true if there is a blocked holder at the head of the list
+ */
+
+static int do_promote(struct gfs2_glock *gl)
+{
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_holder *gh, *tmp;
+ int ret;
+
+restart:
+ list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ continue;
+ if (may_grant(gl, gh)) {
+ if (gh->gh_list.prev == &gl->gl_holders &&
+ glops->go_lock) {
+ spin_unlock(&gl->gl_spin);
+ /* FIXME: eliminate this eventually */
+ ret = glops->go_lock(gh);
+ spin_lock(&gl->gl_spin);
+ if (ret) {
+ gh->gh_error = ret;
+ list_del_init(&gh->gh_list);
+ gfs2_holder_wake(gh);
+ goto restart;
+ }
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ gfs2_holder_wake(gh);
+ goto restart;
+ }
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ gfs2_holder_wake(gh);
+ continue;
+ }
+ if (gh->gh_list.prev == &gl->gl_holders)
+ return 1;
+ break;
+ }
+ return 0;
+}
+
+/**
+ * do_error - Something unexpected has happened during a lock request
+ *
+ */
+
+static inline void do_error(struct gfs2_glock *gl, const int ret)
+{
+ struct gfs2_holder *gh, *tmp;
+
+ list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ continue;
+ if (ret & LM_OUT_ERROR)
+ gh->gh_error = -EIO;
+ else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+ gh->gh_error = GLR_TRYFAILED;
+ else
+ continue;
+ list_del_init(&gh->gh_list);
+ gfs2_holder_wake(gh);
+ }
+}
+
+/**
+ * find_first_waiter - find the first gh that's waiting for the glock
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
+{
+ struct gfs2_holder *gh;
+
+ list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+ return gh;
+ }
+ return NULL;
+}
+
+/**
+ * state_change - record that the glock is now in a different state
+ * @gl: the glock
+ * @new_state the new state
+ *
+ */
+
+static void state_change(struct gfs2_glock *gl, unsigned int new_state)
+{
+ int held1, held2;
+
+ held1 = (gl->gl_state != LM_ST_UNLOCKED);
+ held2 = (new_state != LM_ST_UNLOCKED);
+
+ if (held1 != held2) {
+ if (held2)
+ gfs2_glock_hold(gl);
+ else
+ gfs2_glock_put(gl);
+ }
+
+ gl->gl_state = new_state;
+ gl->gl_tchange = jiffies;
+}
+
+static void gfs2_demote_wake(struct gfs2_glock *gl)
+{
+ gl->gl_demote_state = LM_ST_EXCLUSIVE;
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
+}
+
+/**
+ * finish_xmote - The DLM has replied to one of our lock requests
+ * @gl: The glock
+ * @ret: The status from the DLM
+ *
+ */
+
+static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
+{
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_holder *gh;
+ unsigned state = ret & LM_OUT_ST_MASK;
+
+ spin_lock(&gl->gl_spin);
+ state_change(gl, state);
+ gh = find_first_waiter(gl);
+
+ /* Demote to UN request arrived during demote to SH or DF */
+ if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
+ state != LM_ST_UNLOCKED && gl->gl_demote_state == LM_ST_UNLOCKED)
+ gl->gl_target = LM_ST_UNLOCKED;
+
+ /* Check for state != intended state */
+ if (unlikely(state != gl->gl_target)) {
+ if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) {
+ /* move to back of queue and try next entry */
+ if (ret & LM_OUT_CANCELED) {
+ if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
+ list_move_tail(&gh->gh_list, &gl->gl_holders);
+ gh = find_first_waiter(gl);
+ gl->gl_target = gh->gh_state;
+ goto retry;
+ }
+ /* Some error or failed "try lock" - report it */
+ if ((ret & LM_OUT_ERROR) ||
+ (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
+ gl->gl_target = gl->gl_state;
+ do_error(gl, ret);
+ goto out;
+ }
+ }
+ switch(state) {
+ /* Unlocked due to conversion deadlock, try again */
+ case LM_ST_UNLOCKED:
+retry:
+ do_xmote(gl, gh, gl->gl_target);
+ break;
+ /* Conversion fails, unlock and try again */
+ case LM_ST_SHARED:
+ case LM_ST_DEFERRED:
+ do_xmote(gl, gh, LM_ST_UNLOCKED);
+ break;
+ default: /* Everything else */
+ printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
+ GLOCK_BUG_ON(gl, 1);
+ }
+ spin_unlock(&gl->gl_spin);
+ gfs2_glock_put(gl);
+ return;
+ }
+
+ /* Fast path - we got what we asked for */
+ if (test_and_clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
+ gfs2_demote_wake(gl);
+ if (state != LM_ST_UNLOCKED) {
+ if (glops->go_xmote_bh) {
+ int rv;
+ spin_unlock(&gl->gl_spin);
+ rv = glops->go_xmote_bh(gl, gh);
+ if (rv == -EAGAIN)
+ return;
+ spin_lock(&gl->gl_spin);
+ if (rv) {
+ do_error(gl, rv);
+ goto out;
+ }
+ }
+ do_promote(gl);
+ }
+out:
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+ spin_unlock(&gl->gl_spin);
+ gfs2_glock_put(gl);
+}
+
+static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+ unsigned int cur_state, unsigned int req_state,
+ unsigned int flags)
+{
+ int ret = LM_OUT_ERROR;
+ if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
+ req_state, flags);
+ return ret;
+}
+
+/**
+ * do_xmote - Calls the DLM to change the state of a lock
+ * @gl: The lock state
+ * @gh: The holder (only for promotes)
+ * @target: The target lock state
+ *
+ */
+
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
+{
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ unsigned int lck_flags = gh ? gh->gh_flags : 0;
+ int ret;
+
+ lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
+ LM_FLAG_PRIORITY);
+ BUG_ON(gl->gl_state == target);
+ BUG_ON(gl->gl_state == gl->gl_target);
+ if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
+ glops->go_inval) {
+ set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+ do_error(gl, 0); /* Fail queued try locks */
+ }
+ spin_unlock(&gl->gl_spin);
+ if (glops->go_xmote_th)
+ glops->go_xmote_th(gl);
+ if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
+ glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
+ clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+
+ gfs2_glock_hold(gl);
+ if (target != LM_ST_UNLOCKED && (gl->gl_state == LM_ST_SHARED ||
+ gl->gl_state == LM_ST_DEFERRED) &&
+ !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
+ lck_flags |= LM_FLAG_TRY_1CB;
+ ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, target, lck_flags);
+
+ if (!(ret & LM_OUT_ASYNC)) {
+ finish_xmote(gl, ret);
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
+ } else {
+ GLOCK_BUG_ON(gl, ret != LM_OUT_ASYNC);
+ }
+ spin_lock(&gl->gl_spin);
+}
+
+/**
+ * find_first_holder - find the first "holder" gh
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
+{
+ struct gfs2_holder *gh;
+
+ if (!list_empty(&gl->gl_holders)) {
+ gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ return gh;
+ }
+ return NULL;
+}
+
+/**
+ * run_queue - do all outstanding tasks related to a glock
+ * @gl: The glock in question
+ * @nonblock: True if we must not block in run_queue
+ *
+ */
+
+static void run_queue(struct gfs2_glock *gl, const int nonblock)
+{
+ struct gfs2_holder *gh = NULL;
+
+ if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
+ return;
+
+ GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags));
+
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags) &&
+ gl->gl_demote_state != gl->gl_state) {
+ if (find_first_holder(gl))
+ goto out;
+ if (nonblock)
+ goto out_sched;
+ set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
+ gl->gl_target = gl->gl_demote_state;
+ } else {
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags))
+ gfs2_demote_wake(gl);
+ if (do_promote(gl) == 0)
+ goto out;
+ gh = find_first_waiter(gl);
+ gl->gl_target = gh->gh_state;
+ if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
+ do_error(gl, 0); /* Fail queued try locks */
+ }
+ do_xmote(gl, gh, gl->gl_target);
+ return;
+
+out_sched:
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
+out:
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+}
+
static void glock_work_func(struct work_struct *work)
{
+ unsigned long delay = 0;
struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);

+ if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+ finish_xmote(gl, gl->gl_reply);
spin_lock(&gl->gl_spin);
- if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags))
- set_bit(GLF_DEMOTE, &gl->gl_flags);
- run_queue(gl);
+ if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags)) {
+ unsigned long holdtime, now = jiffies;
+ holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+ if (time_before(now, holdtime))
+ delay = holdtime - now;
+ set_bit(delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE, &gl->gl_flags);
+ }
+ run_queue(gl, 0);
spin_unlock(&gl->gl_spin);
- gfs2_glock_put(gl);
+ if (!delay ||
+ queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+ gfs2_glock_put(gl);
}

static int gfs2_lm_get_lock(struct gfs2_sbd *sdp, struct lm_lockname *name,
@@ -342,12 +676,10 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
gl->gl_name = name;
atomic_set(&gl->gl_ref, 1);
gl->gl_state = LM_ST_UNLOCKED;
+ gl->gl_target = LM_ST_UNLOCKED;
gl->gl_demote_state = LM_ST_EXCLUSIVE;
gl->gl_hash = hash;
- gl->gl_owner_pid = NULL;
- gl->gl_ip = 0;
gl->gl_ops = glops;
- gl->gl_req_gh = NULL;
gl->gl_stamp = jiffies;
gl->gl_tchange = jiffies;
gl->gl_object = NULL;
@@ -447,13 +779,6 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
gh->gh_ip = 0;
}

-static void gfs2_holder_wake(struct gfs2_holder *gh)
-{
- clear_bit(HIF_WAIT, &gh->gh_iflags);
- smp_mb__after_clear_bit();
- wake_up_bit(&gh->gh_iflags, HIF_WAIT);
-}
-
static int just_schedule(void *word)
{
schedule();
@@ -466,14 +791,6 @@ static void wait_on_holder(struct gfs2_holder *gh)
wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
}

-static void gfs2_demote_wake(struct gfs2_glock *gl)
-{
- gl->gl_demote_state = LM_ST_EXCLUSIVE;
- clear_bit(GLF_DEMOTE, &gl->gl_flags);
- smp_mb__after_clear_bit();
- wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
-}
-
static void wait_on_demote(struct gfs2_glock *gl)
{
might_sleep();
@@ -481,217 +798,6 @@ static void wait_on_demote(struct gfs2_glock *gl)
}

/**
- * rq_mutex - process a mutex request in the queue
- * @gh: the glock holder
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_mutex(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
-
- list_del_init(&gh->gh_list);
- /* gh->gh_error never examined. */
- set_bit(GLF_LOCK, &gl->gl_flags);
- clear_bit(HIF_WAIT, &gh->gh_iflags);
- smp_mb();
- wake_up_bit(&gh->gh_iflags, HIF_WAIT);
-
- return 1;
-}
-
-/**
- * rq_promote - process a promote request in the queue
- * @gh: the glock holder
- *
- * Acquire a new inter-node lock, or change a lock state to more restrictive.
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_promote(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
-
- if (!relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
- if (list_empty(&gl->gl_holders)) {
- gl->gl_req_gh = gh;
- set_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_xmote_th(gh->gh_gl, gh);
- spin_lock(&gl->gl_spin);
- }
- return 1;
- }
-
- if (list_empty(&gl->gl_holders)) {
- set_bit(HIF_FIRST, &gh->gh_iflags);
- set_bit(GLF_LOCK, &gl->gl_flags);
- } else {
- struct gfs2_holder *next_gh;
- if (gh->gh_state == LM_ST_EXCLUSIVE)
- return 1;
- next_gh = list_entry(gl->gl_holders.next, struct gfs2_holder,
- gh_list);
- if (next_gh->gh_state == LM_ST_EXCLUSIVE)
- return 1;
- }
-
- list_move_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
-
- gfs2_holder_wake(gh);
-
- return 0;
-}
-
-/**
- * rq_demote - process a demote request in the queue
- * @gh: the glock holder
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_demote(struct gfs2_glock *gl)
-{
- if (!list_empty(&gl->gl_holders))
- return 1;
-
- if (gl->gl_state == gl->gl_demote_state ||
- gl->gl_state == LM_ST_UNLOCKED) {
- gfs2_demote_wake(gl);
- return 0;
- }
-
- set_bit(GLF_LOCK, &gl->gl_flags);
- set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
-
- if (gl->gl_demote_state == LM_ST_UNLOCKED ||
- gl->gl_state != LM_ST_EXCLUSIVE) {
- spin_unlock(&gl->gl_spin);
- gfs2_glock_drop_th(gl);
- } else {
- spin_unlock(&gl->gl_spin);
- gfs2_glock_xmote_th(gl, NULL);
- }
-
- spin_lock(&gl->gl_spin);
- clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
-
- return 0;
-}
-
-/**
- * run_queue - process holder structures on a glock
- * @gl: the glock
- *
- */
-static void run_queue(struct gfs2_glock *gl)
-{
- struct gfs2_holder *gh;
- int blocked = 1;
-
- for (;;) {
- if (test_bit(GLF_LOCK, &gl->gl_flags))
- break;
-
- if (!list_empty(&gl->gl_waiters1)) {
- gh = list_entry(gl->gl_waiters1.next,
- struct gfs2_holder, gh_list);
- blocked = rq_mutex(gh);
- } else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
- blocked = rq_demote(gl);
- if (test_bit(GLF_WAITERS2, &gl->gl_flags) &&
- !blocked) {
- set_bit(GLF_DEMOTE, &gl->gl_flags);
- gl->gl_demote_state = LM_ST_UNLOCKED;
- }
- clear_bit(GLF_WAITERS2, &gl->gl_flags);
- } else if (!list_empty(&gl->gl_waiters3)) {
- gh = list_entry(gl->gl_waiters3.next,
- struct gfs2_holder, gh_list);
- blocked = rq_promote(gh);
- } else
- break;
-
- if (blocked)
- break;
- }
-}
-
-/**
- * gfs2_glmutex_lock - acquire a local lock on a glock
- * @gl: the glock
- *
- * Gives caller exclusive access to manipulate a glock structure.
- */
-
-static void gfs2_glmutex_lock(struct gfs2_glock *gl)
-{
- spin_lock(&gl->gl_spin);
- if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
- struct gfs2_holder gh;
-
- gfs2_holder_init(gl, 0, 0, &gh);
- set_bit(HIF_WAIT, &gh.gh_iflags);
- list_add_tail(&gh.gh_list, &gl->gl_waiters1);
- spin_unlock(&gl->gl_spin);
- wait_on_holder(&gh);
- gfs2_holder_uninit(&gh);
- } else {
- gl->gl_owner_pid = get_pid(task_pid(current));
- gl->gl_ip = (unsigned long)__builtin_return_address(0);
- spin_unlock(&gl->gl_spin);
- }
-}
-
-/**
- * gfs2_glmutex_trylock - try to acquire a local lock on a glock
- * @gl: the glock
- *
- * Returns: 1 if the glock is acquired
- */
-
-static int gfs2_glmutex_trylock(struct gfs2_glock *gl)
-{
- int acquired = 1;
-
- spin_lock(&gl->gl_spin);
- if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
- acquired = 0;
- } else {
- gl->gl_owner_pid = get_pid(task_pid(current));
- gl->gl_ip = (unsigned long)__builtin_return_address(0);
- }
- spin_unlock(&gl->gl_spin);
-
- return acquired;
-}
-
-/**
- * gfs2_glmutex_unlock - release a local lock on a glock
- * @gl: the glock
- *
- */
-
-static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
-{
- struct pid *pid;
-
- spin_lock(&gl->gl_spin);
- clear_bit(GLF_LOCK, &gl->gl_flags);
- pid = gl->gl_owner_pid;
- gl->gl_owner_pid = NULL;
- gl->gl_ip = 0;
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
-
- put_pid(pid);
-}
-
-/**
* handle_callback - process a demote request
* @gl: the glock
* @state: the state the caller wants us to change to
@@ -705,398 +811,45 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
{
int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;

- spin_lock(&gl->gl_spin);
set_bit(bit, &gl->gl_flags);
if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
gl->gl_demote_state = state;
gl->gl_demote_time = jiffies;
if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&
- gl->gl_object) {
+ gl->gl_object)
gfs2_glock_schedule_for_reclaim(gl);
- spin_unlock(&gl->gl_spin);
- return;
- }
} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
gl->gl_demote_state != state) {
- if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
- set_bit(GLF_WAITERS2, &gl->gl_flags);
- else
- gl->gl_demote_state = LM_ST_UNLOCKED;
+ gl->gl_demote_state = LM_ST_UNLOCKED;
}
- spin_unlock(&gl->gl_spin);
}

/**
- * state_change - record that the glock is now in a different state
- * @gl: the glock
- * @new_state the new state
- *
- */
-
-static void state_change(struct gfs2_glock *gl, unsigned int new_state)
-{
- int held1, held2;
-
- held1 = (gl->gl_state != LM_ST_UNLOCKED);
- held2 = (new_state != LM_ST_UNLOCKED);
-
- if (held1 != held2) {
- if (held2)
- gfs2_glock_hold(gl);
- else
- gfs2_glock_put(gl);
- }
-
- gl->gl_state = new_state;
- gl->gl_tchange = jiffies;
-}
-
-/**
- * drop_bh - Called after a lock module unlock completes
- * @gl: the glock
- * @ret: the return status
- *
- * Doesn't wake up the process waiting on the struct gfs2_holder (if any)
- * Doesn't drop the reference on the glock the top half took out
- *
- */
-
-static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_holder *gh = gl->gl_req_gh;
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, !ret);
-
- state_change(gl, LM_ST_UNLOCKED);
-
- if (test_and_clear_bit(GLF_CONV_DEADLK, &gl->gl_flags)) {
- spin_lock(&gl->gl_spin);
- gh->gh_error = 0;
- spin_unlock(&gl->gl_spin);
- gfs2_glock_xmote_th(gl, gl->gl_req_gh);
- gfs2_glock_put(gl);
- return;
- }
-
- spin_lock(&gl->gl_spin);
- gfs2_demote_wake(gl);
- clear_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_put(gl);
-}
-
-/**
- * xmote_bh - Called after the lock module is done acquiring a lock
- * @gl: The glock in question
- * @ret: the int returned from the lock module
- *
- */
-
-static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
- struct gfs2_holder *gh = gl->gl_req_gh;
- int op_done = 1;
-
- if (!gh && (ret & LM_OUT_ST_MASK) == LM_ST_UNLOCKED) {
- drop_bh(gl, ret);
- return;
- }
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, !(ret & LM_OUT_ASYNC));
-
- state_change(gl, ret & LM_OUT_ST_MASK);
-
- /* Deal with each possible exit condition */
-
- if (!gh) {
- gl->gl_stamp = jiffies;
- if (ret & LM_OUT_CANCELED) {
- op_done = 0;
- } else {
- spin_lock(&gl->gl_spin);
- if (gl->gl_state != gl->gl_demote_state) {
- spin_unlock(&gl->gl_spin);
- gfs2_glock_drop_th(gl);
- gfs2_glock_put(gl);
- return;
- }
- gfs2_demote_wake(gl);
- spin_unlock(&gl->gl_spin);
- }
- } else {
- spin_lock(&gl->gl_spin);
- if (ret & LM_OUT_CONV_DEADLK) {
- gh->gh_error = 0;
- set_bit(GLF_CONV_DEADLK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_drop_th(gl);
- gfs2_glock_put(gl);
- return;
- }
- list_del_init(&gh->gh_list);
- gh->gh_error = -EIO;
- if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- goto out;
- gh->gh_error = GLR_CANCELED;
- if (ret & LM_OUT_CANCELED)
- goto out;
- if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
- list_add_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
- set_bit(HIF_FIRST, &gh->gh_iflags);
- op_done = 0;
- goto out;
- }
- gh->gh_error = GLR_TRYFAILED;
- if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
- goto out;
- gh->gh_error = -EINVAL;
- if (gfs2_assert_withdraw(sdp, 0) == -1)
- fs_err(sdp, "ret = 0x%.8X\n", ret);
-out:
- spin_unlock(&gl->gl_spin);
- }
-
- if (glops->go_xmote_bh)
- glops->go_xmote_bh(gl);
-
- if (op_done) {
- spin_lock(&gl->gl_spin);
- gl->gl_req_gh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- }
-
- gfs2_glock_put(gl);
-
- if (gh)
- gfs2_holder_wake(gh);
-}
-
-static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
- unsigned int cur_state, unsigned int req_state,
- unsigned int flags)
-{
- int ret = 0;
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock, cur_state,
- req_state, flags);
- return ret;
-}
-
-/**
- * gfs2_glock_xmote_th - Call into the lock module to acquire or change a glock
- * @gl: The glock in question
- * @state: the requested state
- * @flags: modifier flags to the lock call
- *
- */
-
-static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- int flags = gh ? gh->gh_flags : 0;
- unsigned state = gh ? gh->gh_state : gl->gl_demote_state;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
- int lck_flags = flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB |
- LM_FLAG_NOEXP | LM_FLAG_ANY |
- LM_FLAG_PRIORITY);
- unsigned int lck_ret;
-
- if (glops->go_xmote_th)
- glops->go_xmote_th(gl);
- if (state == LM_ST_DEFERRED && glops->go_inval)
- glops->go_inval(gl, DIO_METADATA);
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, state != LM_ST_UNLOCKED);
- gfs2_assert_warn(sdp, state != gl->gl_state);
-
- gfs2_glock_hold(gl);
-
- lck_ret = gfs2_lm_lock(sdp, gl->gl_lock, gl->gl_state, state, lck_flags);
-
- if (gfs2_assert_withdraw(sdp, !(lck_ret & LM_OUT_ERROR)))
- return;
-
- if (lck_ret & LM_OUT_ASYNC)
- gfs2_assert_warn(sdp, lck_ret == LM_OUT_ASYNC);
- else
- xmote_bh(gl, lck_ret);
-}
-
-static unsigned int gfs2_lm_unlock(struct gfs2_sbd *sdp, void *lock,
- unsigned int cur_state)
-{
- int ret = 0;
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- ret = sdp->sd_lockstruct.ls_ops->lm_unlock(lock, cur_state);
- return ret;
-}
-
-/**
- * gfs2_glock_drop_th - call into the lock module to unlock a lock
- * @gl: the glock
- *
- */
-
-static void gfs2_glock_drop_th(struct gfs2_glock *gl)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
- unsigned int ret;
-
- if (glops->go_xmote_th)
- glops->go_xmote_th(gl);
- if (glops->go_inval)
- glops->go_inval(gl, DIO_METADATA);
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
- gfs2_assert_warn(sdp, gl->gl_state != LM_ST_UNLOCKED);
-
- gfs2_glock_hold(gl);
-
- ret = gfs2_lm_unlock(sdp, gl->gl_lock, gl->gl_state);
-
- if (gfs2_assert_withdraw(sdp, !(ret & LM_OUT_ERROR)))
- return;
-
- if (!ret)
- drop_bh(gl, ret);
- else
- gfs2_assert_warn(sdp, ret == LM_OUT_ASYNC);
-}
-
-/**
- * do_cancels - cancel requests for locks stuck waiting on an expire flag
- * @gh: the LM_FLAG_PRIORITY holder waiting to acquire the lock
- *
- * Don't cancel GL_NOCANCEL requests.
- */
-
-static void do_cancels(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_sbd *sdp = gl->gl_sbd;
-
- spin_lock(&gl->gl_spin);
-
- while (gl->gl_req_gh != gh &&
- !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
- !list_empty(&gh->gh_list)) {
- if (!(gl->gl_req_gh && (gl->gl_req_gh->gh_flags & GL_NOCANCEL))) {
- spin_unlock(&gl->gl_spin);
- if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
- sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock);
- msleep(100);
- spin_lock(&gl->gl_spin);
- } else {
- spin_unlock(&gl->gl_spin);
- msleep(100);
- spin_lock(&gl->gl_spin);
- }
- }
-
- spin_unlock(&gl->gl_spin);
-}
-
-/**
- * glock_wait_internal - wait on a glock acquisition
+ * gfs2_glock_wait - wait on a glock acquisition
* @gh: the glock holder
*
* Returns: 0 on success
*/

-static int glock_wait_internal(struct gfs2_holder *gh)
+int gfs2_glock_wait(struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_sbd *sdp = gl->gl_sbd;
- const struct gfs2_glock_operations *glops = gl->gl_ops;
-
- if (test_bit(HIF_ABORTED, &gh->gh_iflags))
- return -EIO;
-
- if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
- spin_lock(&gl->gl_spin);
- if (gl->gl_req_gh != gh &&
- !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
- !list_empty(&gh->gh_list)) {
- list_del_init(&gh->gh_list);
- gh->gh_error = GLR_TRYFAILED;
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- return gh->gh_error;
- }
- spin_unlock(&gl->gl_spin);
- }
-
- if (gh->gh_flags & LM_FLAG_PRIORITY)
- do_cancels(gh);
-
wait_on_holder(gh);
- if (gh->gh_error)
- return gh->gh_error;
-
- gfs2_assert_withdraw(sdp, test_bit(HIF_HOLDER, &gh->gh_iflags));
- gfs2_assert_withdraw(sdp, relaxed_state_ok(gl->gl_state, gh->gh_state,
- gh->gh_flags));
-
- if (test_bit(HIF_FIRST, &gh->gh_iflags)) {
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
-
- if (glops->go_lock) {
- gh->gh_error = glops->go_lock(gh);
- if (gh->gh_error) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- spin_unlock(&gl->gl_spin);
- }
- }
-
- spin_lock(&gl->gl_spin);
- gl->gl_req_gh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- }
-
return gh->gh_error;
}

-static inline struct gfs2_holder *
-find_holder_by_owner(struct list_head *head, struct pid *pid)
-{
- struct gfs2_holder *gh;
-
- list_for_each_entry(gh, head, gh_list) {
- if (gh->gh_owner_pid == pid)
- return gh;
- }
-
- return NULL;
-}
-
-static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
{
va_list args;

va_start(args, fmt);
- if (gi) {
+ if (seq) {
+ struct gfs2_glock_iter *gi = seq->private;
vsprintf(gi->string, fmt, args);
- seq_printf(gi->seq, gi->string);
- }
- else
+ seq_printf(seq, gi->string);
+ } else {
+ printk(KERN_ERR " ");
vprintk(fmt, args);
+ }
va_end(args);
}

@@ -1104,50 +857,75 @@ static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
* add_to_queue - Add a holder to the wait queue (but look for recursion)
* @gh: the holder structure to add
*
+ * Eventually we should move the recursive locking trap to a
+ * debugging option or something like that. This is the fast
+ * path and needs to have the minimum number of distractions.
+ *
*/

-static void add_to_queue(struct gfs2_holder *gh)
+static inline void add_to_queue(struct gfs2_holder *gh)
{
struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_holder *existing;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct list_head *insert_pt = NULL;
+ struct gfs2_holder *gh2;
+ int try_lock = 0;

BUG_ON(gh->gh_owner_pid == NULL);
if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
BUG();

- if (!(gh->gh_flags & GL_FLOCK)) {
- existing = find_holder_by_owner(&gl->gl_holders,
- gh->gh_owner_pid);
- if (existing) {
- print_symbol(KERN_WARNING "original: %s\n",
- existing->gh_ip);
- printk(KERN_INFO "pid : %d\n",
- pid_nr(existing->gh_owner_pid));
- printk(KERN_INFO "lock type : %d lock state : %d\n",
- existing->gh_gl->gl_name.ln_type,
- existing->gh_gl->gl_state);
- print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- printk(KERN_INFO "pid : %d\n",
- pid_nr(gh->gh_owner_pid));
- printk(KERN_INFO "lock type : %d lock state : %d\n",
- gl->gl_name.ln_type, gl->gl_state);
- BUG();
- }
-
- existing = find_holder_by_owner(&gl->gl_waiters3,
- gh->gh_owner_pid);
- if (existing) {
- print_symbol(KERN_WARNING "original: %s\n",
- existing->gh_ip);
- print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- BUG();
+ if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
+ if (test_bit(GLF_LOCK, &gl->gl_flags))
+ try_lock = 1;
+ if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
+ goto fail;
+ }
+
+ list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
+ if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
+ (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
+ goto trap_recursive;
+ if (try_lock &&
+ !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) &&
+ !may_grant(gl, gh)) {
+fail:
+ gh->gh_error = GLR_TRYFAILED;
+ gfs2_holder_wake(gh);
+ return;
}
+ if (test_bit(HIF_HOLDER, &gh2->gh_iflags))
+ continue;
+ if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
+ insert_pt = &gh2->gh_list;
+ }
+ if (likely(insert_pt == NULL)) {
+ list_add_tail(&gh->gh_list, &gl->gl_holders);
+ if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
+ goto do_cancel;
+ return;
}
+ list_add_tail(&gh->gh_list, insert_pt);
+do_cancel:
+ gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+ if (!(gh->gh_flags & LM_FLAG_PRIORITY)) {
+ spin_unlock(&gl->gl_spin);
+ sdp->sd_lockstruct.ls_ops->lm_cancel(gl->gl_lock);
+ spin_lock(&gl->gl_spin);
+ }
+ return;

- if (gh->gh_flags & LM_FLAG_PRIORITY)
- list_add(&gh->gh_list, &gl->gl_waiters3);
- else
- list_add_tail(&gh->gh_list, &gl->gl_waiters3);
+trap_recursive:
+ print_symbol(KERN_ERR "original: %s\n", gh2->gh_ip);
+ printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
+ printk(KERN_ERR "lock type: %d req lock state : %d\n",
+ gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
+ print_symbol(KERN_ERR "new: %s\n", gh->gh_ip);
+ printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
+ printk(KERN_ERR "lock type: %d req lock state : %d\n",
+ gh->gh_gl->gl_name.ln_type, gh->gh_state);
+ __dump_glock(NULL, gl);
+ BUG();
}

/**
@@ -1165,24 +943,16 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
struct gfs2_sbd *sdp = gl->gl_sbd;
int error = 0;

-restart:
- if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
- set_bit(HIF_ABORTED, &gh->gh_iflags);
+ if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
return -EIO;
- }

spin_lock(&gl->gl_spin);
add_to_queue(gh);
- run_queue(gl);
+ run_queue(gl, 1);
spin_unlock(&gl->gl_spin);

- if (!(gh->gh_flags & GL_ASYNC)) {
- error = glock_wait_internal(gh);
- if (error == GLR_CANCELED) {
- msleep(100);
- goto restart;
- }
- }
+ if (!(gh->gh_flags & GL_ASYNC))
+ error = gfs2_glock_wait(gh);

return error;
}
@@ -1196,48 +966,7 @@ restart:

int gfs2_glock_poll(struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = gh->gh_gl;
- int ready = 0;
-
- spin_lock(&gl->gl_spin);
-
- if (test_bit(HIF_HOLDER, &gh->gh_iflags))
- ready = 1;
- else if (list_empty(&gh->gh_list)) {
- if (gh->gh_error == GLR_CANCELED) {
- spin_unlock(&gl->gl_spin);
- msleep(100);
- if (gfs2_glock_nq(gh))
- return 1;
- return 0;
- } else
- ready = 1;
- }
-
- spin_unlock(&gl->gl_spin);
-
- return ready;
-}
-
-/**
- * gfs2_glock_wait - wait for a lock acquisition that ended in a GLR_ASYNC
- * @gh: the holder structure
- *
- * Returns: 0, GLR_TRYFAILED, or errno on failure
- */
-
-int gfs2_glock_wait(struct gfs2_holder *gh)
-{
- int error;
-
- error = glock_wait_internal(gh);
- if (error == GLR_CANCELED) {
- msleep(100);
- gh->gh_flags &= ~GL_ASYNC;
- error = gfs2_glock_nq(gh);
- }
-
- return error;
+ return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
}

/**
@@ -1251,26 +980,30 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
struct gfs2_glock *gl = gh->gh_gl;
const struct gfs2_glock_operations *glops = gl->gl_ops;
unsigned delay = 0;
+ int fast_path = 0;

+ spin_lock(&gl->gl_spin);
if (gh->gh_flags & GL_NOCACHE)
handle_callback(gl, LM_ST_UNLOCKED, 0, 0);

- gfs2_glmutex_lock(gl);
-
- spin_lock(&gl->gl_spin);
list_del_init(&gh->gh_list);
-
- if (list_empty(&gl->gl_holders)) {
+ if (find_first_holder(gl) == NULL) {
if (glops->go_unlock) {
+ GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags));
spin_unlock(&gl->gl_spin);
glops->go_unlock(gh);
spin_lock(&gl->gl_spin);
+ clear_bit(GLF_LOCK, &gl->gl_flags);
}
gl->gl_stamp = jiffies;
+ if (list_empty(&gl->gl_holders) &&
+ !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+ !test_bit(GLF_DEMOTE, &gl->gl_flags))
+ fast_path = 1;
}
-
- clear_bit(GLF_LOCK, &gl->gl_flags);
spin_unlock(&gl->gl_spin);
+ if (likely(fast_path))
+ return;

gfs2_glock_hold(gl);
if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
@@ -1469,20 +1202,14 @@ int gfs2_lvb_hold(struct gfs2_glock *gl)
{
int error;

- gfs2_glmutex_lock(gl);
-
if (!atomic_read(&gl->gl_lvb_count)) {
error = gfs2_lm_hold_lvb(gl->gl_sbd, gl->gl_lock, &gl->gl_lvb);
- if (error) {
- gfs2_glmutex_unlock(gl);
+ if (error)
return error;
- }
gfs2_glock_hold(gl);
}
atomic_inc(&gl->gl_lvb_count);

- gfs2_glmutex_unlock(gl);
-
return 0;
}

@@ -1497,8 +1224,6 @@ void gfs2_lvb_unhold(struct gfs2_glock *gl)
struct gfs2_sbd *sdp = gl->gl_sbd;

gfs2_glock_hold(gl);
- gfs2_glmutex_lock(gl);
-
gfs2_assert(gl->gl_sbd, atomic_read(&gl->gl_lvb_count) > 0);
if (atomic_dec_and_test(&gl->gl_lvb_count)) {
if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
@@ -1506,8 +1231,6 @@ void gfs2_lvb_unhold(struct gfs2_glock *gl)
gl->gl_lvb = NULL;
gfs2_glock_put(gl);
}
-
- gfs2_glmutex_unlock(gl);
gfs2_glock_put(gl);
}

@@ -1527,7 +1250,9 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
if (time_before(now, holdtime))
delay = holdtime - now;

+ spin_lock(&gl->gl_spin);
handle_callback(gl, state, 1, delay);
+ spin_unlock(&gl->gl_spin);
if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
gfs2_glock_put(gl);
}
@@ -1568,7 +1293,8 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
gl = gfs2_glock_find(sdp, &async->lc_name);
if (gfs2_assert_warn(sdp, gl))
return;
- xmote_bh(gl, async->lc_ret);
+ gl->gl_reply = async->lc_ret;
+ set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
gfs2_glock_put(gl);
up_read(&gfs2_umount_flush_sem);
@@ -1646,6 +1372,7 @@ void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
{
struct gfs2_glock *gl;
+ int done_callback = 0;

spin_lock(&sdp->sd_reclaim_lock);
if (list_empty(&sdp->sd_reclaim_list)) {
@@ -1660,14 +1387,16 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
atomic_dec(&sdp->sd_reclaim_count);
atomic_inc(&sdp->sd_reclaimed);

- if (gfs2_glmutex_trylock(gl)) {
- if (list_empty(&gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
- handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
- gfs2_glmutex_unlock(gl);
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL &&
+ gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl)) {
+ handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
+ done_callback = 1;
}
-
- gfs2_glock_put(gl);
+ spin_unlock(&gl->gl_spin);
+ if (!done_callback ||
+ queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
}

/**
@@ -1724,18 +1453,14 @@ static void scan_glock(struct gfs2_glock *gl)
{
if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object)
return;
+ if (test_bit(GLF_LOCK, &gl->gl_flags))
+ return;

- if (gfs2_glmutex_trylock(gl)) {
- if (list_empty(&gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
- goto out_schedule;
- gfs2_glmutex_unlock(gl);
- }
- return;
-
-out_schedule:
- gfs2_glmutex_unlock(gl);
- gfs2_glock_schedule_for_reclaim(gl);
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL &&
+ gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
+ gfs2_glock_schedule_for_reclaim(gl);
+ spin_unlock(&gl->gl_spin);
}

/**
@@ -1760,12 +1485,13 @@ static void clear_glock(struct gfs2_glock *gl)
spin_unlock(&sdp->sd_reclaim_lock);
}

- if (gfs2_glmutex_trylock(gl)) {
- if (list_empty(&gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED)
- handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
- gfs2_glmutex_unlock(gl);
- }
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL && gl->gl_state != LM_ST_UNLOCKED)
+ handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
+ spin_unlock(&gl->gl_spin);
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
}

/**
@@ -1810,180 +1536,164 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
}
}

-/*
- * Diagnostic routines to help debug distributed deadlock
- */
-
-static void gfs2_print_symbol(struct glock_iter *gi, const char *fmt,
- unsigned long address)
+static const char *state2str(unsigned state)
{
- char buffer[KSYM_SYMBOL_LEN];
-
- sprint_symbol(buffer, address);
- print_dbg(gi, fmt, buffer);
+ switch(state) {
+ case LM_ST_UNLOCKED:
+ return "UN";
+ case LM_ST_SHARED:
+ return "SH";
+ case LM_ST_DEFERRED:
+ return "DF";
+ case LM_ST_EXCLUSIVE:
+ return "EX";
+ }
+ return "??";
+}
+
+static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
+{
+ char *p = buf;
+ if (flags & LM_FLAG_TRY)
+ *p++ = 't';
+ if (flags & LM_FLAG_TRY_1CB)
+ *p++ = 'T';
+ if (flags & LM_FLAG_NOEXP)
+ *p++ = 'e';
+ if (flags & LM_FLAG_ANY)
+ *p++ = 'a';
+ if (flags & LM_FLAG_PRIORITY)
+ *p++ = 'p';
+ if (flags & GL_ASYNC)
+ *p++ = 'a';
+ if (flags & GL_EXACT)
+ *p++ = 'E';
+ if (flags & GL_ATIME)
+ *p++ = 'a';
+ if (flags & GL_NOCACHE)
+ *p++ = 'c';
+ if (test_bit(HIF_HOLDER, &iflags))
+ *p++ = 'H';
+ if (test_bit(HIF_WAIT, &iflags))
+ *p++ = 'W';
+ if (test_bit(HIF_FIRST, &iflags))
+ *p++ = 'F';
+ *p = 0;
+ return buf;
}

/**
* dump_holder - print information about a glock holder
- * @str: a string naming the type of holder
+ * @seq: the seq_file struct
* @gh: the glock holder
*
* Returns: 0 on success, -ENOBUFS when we run out of space
*/

-static int dump_holder(struct glock_iter *gi, char *str,
- struct gfs2_holder *gh)
+static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
{
- unsigned int x;
- struct task_struct *gh_owner;
+ struct task_struct *gh_owner = NULL;
+ char buffer[KSYM_SYMBOL_LEN];
+ char flags_buf[32];

- print_dbg(gi, " %s\n", str);
- if (gh->gh_owner_pid) {
- print_dbg(gi, " owner = %ld ",
- (long)pid_nr(gh->gh_owner_pid));
+ sprint_symbol(buffer, gh->gh_ip);
+ if (gh->gh_owner_pid)
gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
- if (gh_owner)
- print_dbg(gi, "(%s)\n", gh_owner->comm);
- else
- print_dbg(gi, "(ended)\n");
- } else
- print_dbg(gi, " owner = -1\n");
- print_dbg(gi, " gh_state = %u\n", gh->gh_state);
- print_dbg(gi, " gh_flags =");
- for (x = 0; x < 32; x++)
- if (gh->gh_flags & (1 << x))
- print_dbg(gi, " %u", x);
- print_dbg(gi, " \n");
- print_dbg(gi, " error = %d\n", gh->gh_error);
- print_dbg(gi, " gh_iflags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &gh->gh_iflags))
- print_dbg(gi, " %u", x);
- print_dbg(gi, " \n");
- gfs2_print_symbol(gi, " initialized at: %s\n", gh->gh_ip);
-
+ gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %s\n",
+ state2str(gh->gh_state),
+ hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
+ gh->gh_error,
+ gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
+ gh_owner ? gh_owner->comm : "(ended)", buffer);
return 0;
}

-/**
- * dump_inode - print information about an inode
- * @ip: the inode
- *
- * Returns: 0 on success, -ENOBUFS when we run out of space
- */
-
-static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip)
-{
- unsigned int x;
-
- print_dbg(gi, " Inode:\n");
- print_dbg(gi, " num = %llu/%llu\n",
- (unsigned long long)ip->i_no_formal_ino,
- (unsigned long long)ip->i_no_addr);
- print_dbg(gi, " type = %u\n", IF2DT(ip->i_inode.i_mode));
- print_dbg(gi, " i_flags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &ip->i_flags))
- print_dbg(gi, " %u", x);
- print_dbg(gi, " \n");
- return 0;
+static const char *gflags2str(char *buf, const unsigned long *gflags)
+{
+ char *p = buf;
+ if (test_bit(GLF_LOCK, gflags))
+ *p++ = 'l';
+ if (test_bit(GLF_STICKY, gflags))
+ *p++ = 's';
+ if (test_bit(GLF_DEMOTE, gflags))
+ *p++ = 'D';
+ if (test_bit(GLF_PENDING_DEMOTE, gflags))
+ *p++ = 'd';
+ if (test_bit(GLF_DEMOTE_IN_PROGRESS, gflags))
+ *p++ = 'p';
+ if (test_bit(GLF_DIRTY, gflags))
+ *p++ = 'y';
+ if (test_bit(GLF_LFLUSH, gflags))
+ *p++ = 'f';
+ if (test_bit(GLF_INVALIDATE_IN_PROGRESS, gflags))
+ *p++ = 'i';
+ if (test_bit(GLF_REPLY_PENDING, gflags))
+ *p++ = 'r';
+ *p = 0;
+ return buf;
}

/**
- * dump_glock - print information about a glock
+ * __dump_glock - print information about a glock
+ * @seq: The seq_file struct
* @gl: the glock
- * @count: where we are in the buffer
+ *
+ * The file format is as follows:
+ * One line per object, capital letters are used to indicate objects
+ * G = glock, I = Inode, R = rgrp, H = holder. Glocks are not indented,
+ * other objects are indented by a single space and follow the glock to
+ * which they are related. Fields are indicated by lower case letters
+ * followed by a colon and the field value, except for strings which are in
+ * [] so that its possible to see if they are composed of spaces for
+ * example. The field's are n = number (id of the object), f = flags,
+ * t = type, s = state, r = refcount, e = error, p = pid.
*
* Returns: 0 on success, -ENOBUFS when we run out of space
*/

-static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
+static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl)
{
- struct gfs2_holder *gh;
- unsigned int x;
- int error = -ENOBUFS;
- struct task_struct *gl_owner;
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ unsigned long long dtime;
+ const struct gfs2_holder *gh;
+ char gflags_buf[32];
+ int error = 0;

- spin_lock(&gl->gl_spin);
+ dtime = jiffies - gl->gl_demote_time;
+ dtime *= 1000000/HZ; /* demote time in uSec */
+ if (!test_bit(GLF_DEMOTE, &gl->gl_flags))
+ dtime = 0;
+ gfs2_print_dbg(seq, "G: s:%s n:%u/%llu f:%s t:%s d:%s/%llu l:%d a:%d r:%d\n",
+ state2str(gl->gl_state),
+ gl->gl_name.ln_type,
+ (unsigned long long)gl->gl_name.ln_number,
+ gflags2str(gflags_buf, &gl->gl_flags),
+ state2str(gl->gl_target),
+ state2str(gl->gl_demote_state), dtime,
+ atomic_read(&gl->gl_lvb_count),
+ atomic_read(&gl->gl_ail_count),
+ atomic_read(&gl->gl_ref));

- print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type,
- (unsigned long long)gl->gl_name.ln_number);
- print_dbg(gi, " gl_flags =");
- for (x = 0; x < 32; x++) {
- if (test_bit(x, &gl->gl_flags))
- print_dbg(gi, " %u", x);
- }
- if (!test_bit(GLF_LOCK, &gl->gl_flags))
- print_dbg(gi, " (unlocked)");
- print_dbg(gi, " \n");
- print_dbg(gi, " gl_ref = %d\n", atomic_read(&gl->gl_ref));
- print_dbg(gi, " gl_state = %u\n", gl->gl_state);
- if (gl->gl_owner_pid) {
- gl_owner = pid_task(gl->gl_owner_pid, PIDTYPE_PID);
- if (gl_owner)
- print_dbg(gi, " gl_owner = pid %d (%s)\n",
- pid_nr(gl->gl_owner_pid), gl_owner->comm);
- else
- print_dbg(gi, " gl_owner = %d (ended)\n",
- pid_nr(gl->gl_owner_pid));
- } else
- print_dbg(gi, " gl_owner = -1\n");
- print_dbg(gi, " gl_ip = %lu\n", gl->gl_ip);
- print_dbg(gi, " req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
- print_dbg(gi, " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
- print_dbg(gi, " object = %s\n", (gl->gl_object) ? "yes" : "no");
- print_dbg(gi, " reclaim = %s\n",
- (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
- if (gl->gl_aspace)
- print_dbg(gi, " aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
- gl->gl_aspace->i_mapping->nrpages);
- else
- print_dbg(gi, " aspace = no\n");
- print_dbg(gi, " ail = %d\n", atomic_read(&gl->gl_ail_count));
- if (gl->gl_req_gh) {
- error = dump_holder(gi, "Request", gl->gl_req_gh);
- if (error)
- goto out;
- }
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- error = dump_holder(gi, "Holder", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
- error = dump_holder(gi, "Waiter1", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
- error = dump_holder(gi, "Waiter3", gh);
+ error = dump_holder(seq, gh);
if (error)
goto out;
}
- if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
- print_dbg(gi, " Demotion req to state %u (%llu uS ago)\n",
- gl->gl_demote_state, (unsigned long long)
- (jiffies - gl->gl_demote_time)*(1000000/HZ));
- }
- if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) {
- if (!test_bit(GLF_LOCK, &gl->gl_flags) &&
- list_empty(&gl->gl_holders)) {
- error = dump_inode(gi, gl->gl_object);
- if (error)
- goto out;
- } else {
- error = -ENOBUFS;
- print_dbg(gi, " Inode: busy\n");
- }
- }
-
- error = 0;
-
+ if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump)
+ error = glops->go_dump(seq, gl);
out:
- spin_unlock(&gl->gl_spin);
return error;
}

+static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
+{
+ int ret;
+ spin_lock(&gl->gl_spin);
+ ret = __dump_glock(seq, gl);
+ spin_unlock(&gl->gl_spin);
+ return ret;
+}
+
/**
* gfs2_dump_lockstate - print out the current lockstate
* @sdp: the filesystem
@@ -2086,7 +1796,7 @@ void gfs2_glock_exit(void)
module_param(scand_secs, uint, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(scand_secs, "The number of seconds between scand runs");

-static int gfs2_glock_iter_next(struct glock_iter *gi)
+static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
{
struct gfs2_glock *gl;

@@ -2104,7 +1814,7 @@ restart:
gfs2_glock_put(gl);
if (gl && gi->gl == NULL)
gi->hash++;
- while(gi->gl == NULL) {
+ while (gi->gl == NULL) {
if (gi->hash >= GFS2_GL_HASH_SIZE)
return 1;
read_lock(gl_lock_addr(gi->hash));
@@ -2122,58 +1832,34 @@ restart:
return 0;
}

-static void gfs2_glock_iter_free(struct glock_iter *gi)
+static void gfs2_glock_iter_free(struct gfs2_glock_iter *gi)
{
if (gi->gl)
gfs2_glock_put(gi->gl);
- kfree(gi);
-}
-
-static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
-{
- struct glock_iter *gi;
-
- gi = kmalloc(sizeof (*gi), GFP_KERNEL);
- if (!gi)
- return NULL;
-
- gi->sdp = sdp;
- gi->hash = 0;
- gi->seq = NULL;
gi->gl = NULL;
- memset(gi->string, 0, sizeof(gi->string));
-
- if (gfs2_glock_iter_next(gi)) {
- gfs2_glock_iter_free(gi);
- return NULL;
- }
-
- return gi;
}

-static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
+static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct glock_iter *gi;
+ struct gfs2_glock_iter *gi = seq->private;
loff_t n = *pos;

- gi = gfs2_glock_iter_init(file->private);
- if (!gi)
- return NULL;
+ gi->hash = 0;

- while(n--) {
+ do {
if (gfs2_glock_iter_next(gi)) {
gfs2_glock_iter_free(gi);
return NULL;
}
- }
+ } while (n--);

- return gi;
+ return gi->gl;
}

-static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
+static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
loff_t *pos)
{
- struct glock_iter *gi = iter_ptr;
+ struct gfs2_glock_iter *gi = seq->private;

(*pos)++;

@@ -2182,24 +1868,18 @@ static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
return NULL;
}

- return gi;
+ return gi->gl;
}

-static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
+static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
{
- struct glock_iter *gi = iter_ptr;
- if (gi)
- gfs2_glock_iter_free(gi);
+ struct gfs2_glock_iter *gi = seq->private;
+ gfs2_glock_iter_free(gi);
}

-static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
+static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
{
- struct glock_iter *gi = iter_ptr;
-
- gi->seq = file;
- dump_glock(gi, gi->gl);
-
- return 0;
+ return dump_glock(seq, iter_ptr);
}

static const struct seq_operations gfs2_glock_seq_ops = {
@@ -2211,17 +1891,14 @@ static const struct seq_operations gfs2_glock_seq_ops = {

static int gfs2_debugfs_open(struct inode *inode, struct file *file)
{
- struct seq_file *seq;
- int ret;
-
- ret = seq_open(file, &gfs2_glock_seq_ops);
- if (ret)
- return ret;
-
- seq = file->private_data;
- seq->private = inode->i_private;
-
- return 0;
+ int ret = seq_open_private(file, &gfs2_glock_seq_ops,
+ sizeof(struct gfs2_glock_iter));
+ if (ret == 0) {
+ struct seq_file *seq = file->private_data;
+ struct gfs2_glock_iter *gi = seq->private;
+ gi->sdp = inode->i_private;
+ }
+ return ret;
}

static const struct file_operations gfs2_debug_fops = {
@@ -2229,7 +1906,7 @@ static const struct file_operations gfs2_debug_fops = {
.open = gfs2_debugfs_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release
+ .release = seq_release_private,
};

int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index cdad3e6..7389f8e 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -26,11 +26,8 @@
#define GL_SKIP 0x00000100
#define GL_ATIME 0x00000200
#define GL_NOCACHE 0x00000400
-#define GL_FLOCK 0x00000800
-#define GL_NOCANCEL 0x00001000

#define GLR_TRYFAILED 13
-#define GLR_CANCELED 14

static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
{
@@ -41,6 +38,8 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
spin_lock(&gl->gl_spin);
pid = task_pid(current);
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+ break;
if (gh->gh_owner_pid == pid)
goto out;
}
@@ -70,7 +69,7 @@ static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
{
int ret;
spin_lock(&gl->gl_spin);
- ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
+ ret = test_bit(GLF_DEMOTE, &gl->gl_flags);
spin_unlock(&gl->gl_spin);
return ret;
}
@@ -98,6 +97,7 @@ int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);

/**
* gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
@@ -130,7 +130,6 @@ int gfs2_lvb_hold(struct gfs2_glock *gl);
void gfs2_lvb_unhold(struct gfs2_glock *gl);

void gfs2_glock_cb(void *cb_data, unsigned int type, void *data);
-
void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl);
void gfs2_reclaim_glock(struct gfs2_sbd *sdp);
void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 07d84d1..c6c318c 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -13,6 +13,7 @@
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>
+#include <linux/bio.h>

#include "gfs2.h"
#include "incore.h"
@@ -172,26 +173,6 @@ static void inode_go_sync(struct gfs2_glock *gl)
}

/**
- * inode_go_xmote_bh - After promoting/demoting a glock
- * @gl: the glock
- *
- */
-
-static void inode_go_xmote_bh(struct gfs2_glock *gl)
-{
- struct gfs2_holder *gh = gl->gl_req_gh;
- struct buffer_head *bh;
- int error;
-
- if (gl->gl_state != LM_ST_UNLOCKED &&
- (!gh || !(gh->gh_flags & GL_SKIP))) {
- error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
- if (!error)
- brelse(bh);
- }
-}
-
-/**
* inode_go_inval - prepare a inode glock to be released
* @gl: the glock
* @flags:
@@ -267,6 +248,26 @@ static int inode_go_lock(struct gfs2_holder *gh)
}

/**
+ * inode_go_dump - print information about an inode
+ * @seq: The iterator
+ * @ip: the inode
+ *
+ * Returns: 0 on success, -ENOBUFS when we run out of space
+ */
+
+static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+ const struct gfs2_inode *ip = gl->gl_object;
+ if (ip == NULL)
+ return 0;
+ gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%08lx\n",
+ (unsigned long long)ip->i_no_formal_ino,
+ (unsigned long long)ip->i_no_addr,
+ IF2DT(ip->i_inode.i_mode), ip->i_flags);
+ return 0;
+}
+
+/**
* rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
* @gl: the glock
*
@@ -306,6 +307,22 @@ static void rgrp_go_unlock(struct gfs2_holder *gh)
}

/**
+ * rgrp_go_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
+ *
+ */
+
+static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+ const struct gfs2_rgrpd *rgd = gl->gl_object;
+ if (rgd == NULL)
+ return 0;
+ gfs2_print_dbg(seq, " R: n:%llu\n", (unsigned long long)rgd->rd_addr);
+ return 0;
+}
+
+/**
* trans_go_sync - promote/demote the transaction glock
* @gl: the glock
* @state: the requested state
@@ -330,7 +347,7 @@ static void trans_go_sync(struct gfs2_glock *gl)
*
*/

-static void trans_go_xmote_bh(struct gfs2_glock *gl)
+static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
@@ -338,8 +355,7 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl)
struct gfs2_log_header_host head;
int error;

- if (gl->gl_state != LM_ST_UNLOCKED &&
- test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+ if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);

error = gfs2_find_jhead(sdp->sd_jdesc, &head);
@@ -354,6 +370,7 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl)
gfs2_log_pointers_init(sdp, head.lh_blkno);
}
}
+ return 0;
}

/**
@@ -375,12 +392,12 @@ const struct gfs2_glock_operations gfs2_meta_glops = {

const struct gfs2_glock_operations gfs2_inode_glops = {
.go_xmote_th = inode_go_sync,
- .go_xmote_bh = inode_go_xmote_bh,
.go_inval = inode_go_inval,
.go_demote_ok = inode_go_demote_ok,
.go_lock = inode_go_lock,
+ .go_dump = inode_go_dump,
.go_type = LM_TYPE_INODE,
- .go_min_hold_time = HZ / 10,
+ .go_min_hold_time = HZ / 5,
};

const struct gfs2_glock_operations gfs2_rgrp_glops = {
@@ -389,8 +406,9 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
.go_demote_ok = rgrp_go_demote_ok,
.go_lock = rgrp_go_lock,
.go_unlock = rgrp_go_unlock,
+ .go_dump = rgrp_go_dump,
.go_type = LM_TYPE_RGRP,
- .go_min_hold_time = HZ / 10,
+ .go_min_hold_time = HZ / 5,
};

const struct gfs2_glock_operations gfs2_trans_glops = {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index eabe5ea..4b734c6 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -128,20 +128,20 @@ struct gfs2_bufdata {

struct gfs2_glock_operations {
void (*go_xmote_th) (struct gfs2_glock *gl);
- void (*go_xmote_bh) (struct gfs2_glock *gl);
+ int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
void (*go_inval) (struct gfs2_glock *gl, int flags);
int (*go_demote_ok) (struct gfs2_glock *gl);
int (*go_lock) (struct gfs2_holder *gh);
void (*go_unlock) (struct gfs2_holder *gh);
+ int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
const int go_type;
const unsigned long go_min_hold_time;
};

enum {
/* States */
- HIF_HOLDER = 6,
+ HIF_HOLDER = 6, /* Set for gh that "holds" the glock */
HIF_FIRST = 7,
- HIF_ABORTED = 9,
HIF_WAIT = 10,
};

@@ -154,20 +154,20 @@ struct gfs2_holder {
unsigned gh_flags;

int gh_error;
- unsigned long gh_iflags;
+ unsigned long gh_iflags; /* HIF_... */
unsigned long gh_ip;
};

enum {
- GLF_LOCK = 1,
- GLF_STICKY = 2,
- GLF_DEMOTE = 3,
- GLF_PENDING_DEMOTE = 4,
- GLF_DIRTY = 5,
- GLF_DEMOTE_IN_PROGRESS = 6,
- GLF_LFLUSH = 7,
- GLF_WAITERS2 = 8,
- GLF_CONV_DEADLK = 9,
+ GLF_LOCK = 1,
+ GLF_STICKY = 2,
+ GLF_DEMOTE = 3,
+ GLF_PENDING_DEMOTE = 4,
+ GLF_DEMOTE_IN_PROGRESS = 5,
+ GLF_DIRTY = 6,
+ GLF_LFLUSH = 7,
+ GLF_INVALIDATE_IN_PROGRESS = 8,
+ GLF_REPLY_PENDING = 9,
};

struct gfs2_glock {
@@ -179,19 +179,14 @@ struct gfs2_glock {
spinlock_t gl_spin;

unsigned int gl_state;
+ unsigned int gl_target;
+ unsigned int gl_reply;
unsigned int gl_hash;
unsigned int gl_demote_state; /* state requested by remote node */
unsigned long gl_demote_time; /* time of first demote request */
- struct pid *gl_owner_pid;
- unsigned long gl_ip;
struct list_head gl_holders;
- struct list_head gl_waiters1; /* HIF_MUTEX */
- struct list_head gl_waiters3; /* HIF_PROMOTE */

const struct gfs2_glock_operations *gl_ops;
-
- struct gfs2_holder *gl_req_gh;
-
void *gl_lock;
char *gl_lvb;
atomic_t gl_lvb_count;
diff --git a/fs/gfs2/locking/dlm/lock.c b/fs/gfs2/locking/dlm/lock.c
index cf7ea8a..fed9a67 100644
--- a/fs/gfs2/locking/dlm/lock.c
+++ b/fs/gfs2/locking/dlm/lock.c
@@ -308,6 +308,9 @@ unsigned int gdlm_lock(void *lock, unsigned int cur_state,
{
struct gdlm_lock *lp = lock;

+ if (req_state == LM_ST_UNLOCKED)
+ return gdlm_unlock(lock, cur_state);
+
clear_bit(LFL_DLM_CANCEL, &lp->flags);
if (flags & LM_FLAG_NOEXP)
set_bit(LFL_NOBLOCK, &lp->flags);
diff --git a/fs/gfs2/locking/nolock/main.c b/fs/gfs2/locking/nolock/main.c
index 284a5ec..627bfb7 100644
--- a/fs/gfs2/locking/nolock/main.c
+++ b/fs/gfs2/locking/nolock/main.c
@@ -107,6 +107,8 @@ static void nolock_put_lock(void *lock)
static unsigned int nolock_lock(void *lock, unsigned int cur_state,
unsigned int req_state, unsigned int flags)
{
+ if (req_state == LM_ST_UNLOCKED)
+ return 0;
return req_state | LM_OUT_CACHEABLE;
}

diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 053e2eb..bcc668d 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -40,8 +40,6 @@ static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo)
INIT_HLIST_NODE(&gl->gl_list);
spin_lock_init(&gl->gl_spin);
INIT_LIST_HEAD(&gl->gl_holders);
- INIT_LIST_HEAD(&gl->gl_waiters1);
- INIT_LIST_HEAD(&gl->gl_waiters3);
gl->gl_lvb = NULL;
atomic_set(&gl->gl_lvb_count, 0);
INIT_LIST_HEAD(&gl->gl_reclaim);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 78d75f8..0985362 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -129,7 +129,7 @@ void gfs2_meta_sync(struct gfs2_glock *gl)
}

/**
- * getbuf - Get a buffer with a given address space
+ * gfs2_getbuf - Get a buffer with a given address space
* @gl: the glock
* @blkno: the block number (filesystem scope)
* @create: 1 if the buffer should be created
@@ -137,7 +137,7 @@ void gfs2_meta_sync(struct gfs2_glock *gl)
* Returns: the buffer
*/

-static struct buffer_head *getbuf(struct gfs2_glock *gl, u64 blkno, int create)
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
{
struct address_space *mapping = gl->gl_aspace->i_mapping;
struct gfs2_sbd *sdp = gl->gl_sbd;
@@ -205,7 +205,7 @@ static void meta_prep_new(struct buffer_head *bh)
struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
{
struct buffer_head *bh;
- bh = getbuf(gl, blkno, CREATE);
+ bh = gfs2_getbuf(gl, blkno, CREATE);
meta_prep_new(bh);
return bh;
}
@@ -223,7 +223,7 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
struct buffer_head **bhp)
{
- *bhp = getbuf(gl, blkno, CREATE);
+ *bhp = gfs2_getbuf(gl, blkno, CREATE);
if (!buffer_uptodate(*bhp)) {
ll_rw_block(READ_META, 1, bhp);
if (flags & DIO_WAIT) {
@@ -346,7 +346,7 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
struct buffer_head *bh;

while (blen) {
- bh = getbuf(ip->i_gl, bstart, NO_CREATE);
+ bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
if (bh) {
lock_buffer(bh);
gfs2_log_lock(sdp);
@@ -421,7 +421,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
if (extlen > max_ra)
extlen = max_ra;

- first_bh = getbuf(gl, dblock, CREATE);
+ first_bh = gfs2_getbuf(gl, dblock, CREATE);

if (buffer_uptodate(first_bh))
goto out;
@@ -432,7 +432,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
extlen--;

while (extlen) {
- bh = getbuf(gl, dblock, CREATE);
+ bh = gfs2_getbuf(gl, dblock, CREATE);

if (!buffer_uptodate(bh) && !buffer_locked(bh))
ll_rw_block(READA, 1, &bh);
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 73e3b1c..b1a5f36 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -47,6 +47,7 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno,
int flags, struct buffer_head **bhp);
int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create);

void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
int meta);
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index f55394e..2b556dd 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -507,26 +507,23 @@ static int __gfs2_readpage(void *file, struct page *page)
static int gfs2_readpage(struct file *file, struct page *page)
{
struct gfs2_inode *ip = GFS2_I(page->mapping->host);
- struct gfs2_holder *gh;
+ struct gfs2_holder gh;
int error;

- gh = gfs2_glock_is_locked_by_me(ip->i_gl);
- if (!gh) {
- gh = kmalloc(sizeof(struct gfs2_holder), GFP_NOFS);
- if (!gh)
- return -ENOBUFS;
- gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, gh);
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
+ error = gfs2_glock_nq_atime(&gh);
+ if (unlikely(error)) {
unlock_page(page);
- error = gfs2_glock_nq_atime(gh);
- if (likely(error != 0))
- goto out;
- return AOP_TRUNCATED_PAGE;
+ goto out;
}
error = __gfs2_readpage(file, page);
- gfs2_glock_dq(gh);
+ gfs2_glock_dq(&gh);
out:
- gfs2_holder_uninit(gh);
- kfree(gh);
+ gfs2_holder_uninit(&gh);
+ if (error == GLR_TRYFAILED) {
+ yield();
+ return AOP_TRUNCATED_PAGE;
+ }
return error;
}

diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index e1b7d52..0ff512a 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -669,8 +669,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
int error = 0;

state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
- flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE
- | GL_FLOCK;
+ flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;

mutex_lock(&fp->f_fl_mutex);

@@ -683,9 +682,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
gfs2_glock_dq_wait(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {
- error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
- ip->i_no_addr, &gfs2_flock_glops,
- CREATE, &gl);
+ error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
+ &gfs2_flock_glops, CREATE, &gl);
if (error)
goto out;
gfs2_holder_init(gl, state, flags, fl_gh);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 2888e4b..fdd3f0f 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -505,7 +505,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)

error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
- GL_NOCANCEL | GL_NOCACHE, &t_gh);
+ GL_NOCACHE, &t_gh);
if (error)
goto fail_gunlock_ji;

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 7aeacbc..12fe38f 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -941,8 +941,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
}

error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
- LM_FLAG_PRIORITY | GL_NOCACHE,
- t_gh);
+ GL_NOCACHE, t_gh);

list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
error = gfs2_jdesc_check(jd);
--
1.5.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/