/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License v.2.
+ * of the GNU General Public License version 2.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
-#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/delay.h>
#include <linux/sort.h>
#include <linux/jhash.h>
-#include <linux/kref.h>
#include <linux/kallsyms.h>
#include <linux/gfs2_ondisk.h>
-#include <asm/semaphore.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+#include <linux/module.h>
+#include <linux/rwsem.h>
#include <asm/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
#include "gfs2.h"
-#include "lm_interface.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
-#include "lm.h"
#include "lops.h"
#include "meta_io.h"
#include "quota.h"
#include "super.h"
#include "util.h"
+#include "bmap.h"
+#define CREATE_TRACE_POINTS
+#include "trace_gfs2.h"
-/* Must be kept in sync with the beginning of struct gfs2_glock */
-struct glock_plug {
- struct list_head gl_list;
- unsigned long gl_flags;
+struct gfs2_gl_hash_bucket {
+ struct hlist_head hb_list;
};
-struct greedy {
- struct gfs2_holder gr_gh;
- struct work_struct gr_work;
+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 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);
-/**
- * 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;
+static DECLARE_RWSEM(gfs2_umount_flush_sem);
+static struct dentry *gfs2_root;
+static struct workqueue_struct *glock_workqueue;
+struct workqueue_struct *gfs2_delete_workqueue;
+static LIST_HEAD(lru_list);
+static atomic_t lru_count = ATOMIC_INIT(0);
+static DEFINE_SPINLOCK(lru_lock);
- if (actual == LM_ST_EXCLUSIVE && requested == LM_ST_SHARED)
- return 1;
+#define GFS2_GL_HASH_SHIFT 15
+#define GFS2_GL_HASH_SIZE (1 << GFS2_GL_HASH_SHIFT)
+#define GFS2_GL_HASH_MASK (GFS2_GL_HASH_SIZE - 1)
- if (actual != LM_ST_UNLOCKED && (flags & LM_FLAG_ANY))
- return 1;
+static struct gfs2_gl_hash_bucket gl_hash_table[GFS2_GL_HASH_SIZE];
+static struct dentry *gfs2_root;
- return 0;
+/*
+ * Despite what you might think, the numbers below are not arbitrary :-)
+ * They are taken from the ipv4 routing hash code, which is well tested
+ * and thus should be nearly optimal. Later on we might tweek the numbers
+ * but for now this should be fine.
+ *
+ * The reason for putting the locks in a separate array from the list heads
+ * is that we can have fewer locks than list heads and save memory. We use
+ * the same hash function for both, but with a different hash mask.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
+ defined(CONFIG_PROVE_LOCKING)
+
+#ifdef CONFIG_LOCKDEP
+# define GL_HASH_LOCK_SZ 256
+#else
+# if NR_CPUS >= 32
+# define GL_HASH_LOCK_SZ 4096
+# elif NR_CPUS >= 16
+# define GL_HASH_LOCK_SZ 2048
+# elif NR_CPUS >= 8
+# define GL_HASH_LOCK_SZ 1024
+# elif NR_CPUS >= 4
+# define GL_HASH_LOCK_SZ 512
+# else
+# define GL_HASH_LOCK_SZ 256
+# endif
+#endif
+
+/* We never want more locks than chains */
+#if GFS2_GL_HASH_SIZE < GL_HASH_LOCK_SZ
+# undef GL_HASH_LOCK_SZ
+# define GL_HASH_LOCK_SZ GFS2_GL_HASH_SIZE
+#endif
+
+static rwlock_t gl_hash_locks[GL_HASH_LOCK_SZ];
+
+static inline rwlock_t *gl_lock_addr(unsigned int x)
+{
+ return &gl_hash_locks[x & (GL_HASH_LOCK_SZ-1)];
+}
+#else /* not SMP, so no spinlocks required */
+static inline rwlock_t *gl_lock_addr(unsigned int x)
+{
+ return NULL;
}
+#endif
/**
* gl_hash() - Turn glock number into hash bucket number
* Returns: The number of the corresponding hash bucket
*/
-static unsigned int gl_hash(struct lm_lockname *name)
+static unsigned int gl_hash(const struct gfs2_sbd *sdp,
+ const struct lm_lockname *name)
{
unsigned int h;
- h = jhash(&name->ln_number, sizeof(uint64_t), 0);
+ h = jhash(&name->ln_number, sizeof(u64), 0);
h = jhash(&name->ln_type, sizeof(unsigned int), h);
+ h = jhash(&sdp, sizeof(struct gfs2_sbd *), h);
h &= GFS2_GL_HASH_MASK;
return h;
struct gfs2_sbd *sdp = gl->gl_sbd;
struct inode *aspace = gl->gl_aspace;
- gfs2_lm_put_lock(sdp, gl->gl_lock);
-
if (aspace)
gfs2_aspace_put(aspace);
-
- kmem_cache_free(gfs2_glock_cachep, gl);
+ trace_gfs2_glock_put(gl);
+ sdp->sd_lockstruct.ls_ops->lm_put_lock(gfs2_glock_cachep, gl);
}
/**
void gfs2_glock_hold(struct gfs2_glock *gl)
{
- kref_get(&gl->gl_ref);
+ GLOCK_BUG_ON(gl, atomic_read(&gl->gl_ref) == 0);
+ atomic_inc(&gl->gl_ref);
}
-/* All work is done after the return from kref_put() so we
- can release the write_lock before the free. */
+/**
+ * demote_ok - Check to see if it's ok to unlock a glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
-static void kill_glock(struct kref *kref)
+static int demote_ok(const struct gfs2_glock *gl)
{
- struct gfs2_glock *gl = container_of(kref, struct gfs2_glock, gl_ref);
- struct gfs2_sbd *sdp = gl->gl_sbd;
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
- 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_waiters2));
- gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
+ if (gl->gl_state == LM_ST_UNLOCKED)
+ return 0;
+ if (!list_empty(&gl->gl_holders))
+ return 0;
+ if (glops->go_demote_ok)
+ return glops->go_demote_ok(gl);
+ return 1;
}
/**
- * gfs2_glock_put() - Decrement reference count on glock
- * @gl: The glock to put
+ * gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
+ * @gl: the glock
*
*/
-int gfs2_glock_put(struct gfs2_glock *gl)
+static void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_gl_hash_bucket *bucket = gl->gl_bucket;
- int rv = 0;
-
- mutex_lock(&sdp->sd_invalidate_inodes_mutex);
-
- write_lock(&bucket->hb_lock);
- if (kref_put(&gl->gl_ref, kill_glock)) {
- list_del_init(&gl->gl_list);
- write_unlock(&bucket->hb_lock);
- BUG_ON(spin_is_locked(&gl->gl_spin));
- glock_free(gl);
- rv = 1;
- goto out;
+ int may_reclaim;
+ may_reclaim = (demote_ok(gl) &&
+ (atomic_read(&gl->gl_ref) == 1 ||
+ (gl->gl_name.ln_type == LM_TYPE_INODE &&
+ atomic_read(&gl->gl_ref) <= 2)));
+ spin_lock(&lru_lock);
+ if (list_empty(&gl->gl_lru) && may_reclaim) {
+ list_add_tail(&gl->gl_lru, &lru_list);
+ atomic_inc(&lru_count);
}
- write_unlock(&bucket->hb_lock);
- out:
- mutex_unlock(&sdp->sd_invalidate_inodes_mutex);
- return rv;
+ spin_unlock(&lru_lock);
}
/**
- * queue_empty - check to see if a glock's queue is empty
- * @gl: the glock
- * @head: the head of the queue to check
+ * gfs2_glock_put_nolock() - Decrement reference count on glock
+ * @gl: The glock to put
*
- * This function protects the list in the event that a process already
- * has a holder on the list and is adding a second holder for itself.
- * The glmutex lock is what generally prevents processes from working
- * on the same glock at once, but the special case of adding a second
- * holder for yourself ("recursive" locking) doesn't involve locking
- * glmutex, making the spin lock necessary.
+ * This function should only be used if the caller has its own reference
+ * to the glock, in addition to the one it is dropping.
+ */
+
+void gfs2_glock_put_nolock(struct gfs2_glock *gl)
+{
+ if (atomic_dec_and_test(&gl->gl_ref))
+ GLOCK_BUG_ON(gl, 1);
+ gfs2_glock_schedule_for_reclaim(gl);
+}
+
+/**
+ * gfs2_glock_put() - Decrement reference count on glock
+ * @gl: The glock to put
*
- * Returns: 1 if the queue is empty
*/
-static inline int queue_empty(struct gfs2_glock *gl, struct list_head *head)
+int gfs2_glock_put(struct gfs2_glock *gl)
{
- int empty;
+ int rv = 0;
+
+ 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));
+ spin_lock(&lru_lock);
+ if (!list_empty(&gl->gl_lru)) {
+ list_del_init(&gl->gl_lru);
+ atomic_dec(&lru_count);
+ }
+ spin_unlock(&lru_lock);
+ GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
+ glock_free(gl);
+ rv = 1;
+ goto out;
+ }
spin_lock(&gl->gl_spin);
- empty = list_empty(head);
+ gfs2_glock_schedule_for_reclaim(gl);
spin_unlock(&gl->gl_spin);
- return empty;
+ write_unlock(gl_lock_addr(gl->gl_hash));
+out:
+ return rv;
}
/**
* Returns: NULL, or the struct gfs2_glock with the requested number
*/
-static struct gfs2_glock *search_bucket(struct gfs2_gl_hash_bucket *bucket,
- struct lm_lockname *name)
+static struct gfs2_glock *search_bucket(unsigned int hash,
+ const struct gfs2_sbd *sdp,
+ const struct lm_lockname *name)
{
struct gfs2_glock *gl;
+ struct hlist_node *h;
- list_for_each_entry(gl, &bucket->hb_list, gl_list) {
- if (test_bit(GLF_PLUG, &gl->gl_flags))
- continue;
+ hlist_for_each_entry(gl, h, &gl_hash_table[hash].hb_list, gl_list) {
if (!lm_name_equal(&gl->gl_name, name))
continue;
+ if (gl->gl_sbd != sdp)
+ continue;
- kref_get(&gl->gl_ref);
+ atomic_inc(&gl->gl_ref);
return gl;
}
}
/**
- * gfs2_glock_find() - Find glock by lock number
- * @sdp: The GFS2 superblock
- * @name: The lock name
+ * may_grant - check if its ok to grant a new lock
+ * @gl: The glock
+ * @gh: The lock request which we wish to grant
*
- * Returns: NULL, or the struct gfs2_glock with the requested number
+ * Returns: true if its ok to grant the lock
*/
-static struct gfs2_glock *gfs2_glock_find(struct gfs2_sbd *sdp,
- struct lm_lockname *name)
+static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
{
- struct gfs2_gl_hash_bucket *bucket = &sdp->sd_gl_hash[gl_hash(name)];
- struct gfs2_glock *gl;
-
- read_lock(&bucket->hb_lock);
- gl = search_bucket(bucket, name);
- read_unlock(&bucket->hb_lock);
+ 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 (gl->gl_state == LM_ST_EXCLUSIVE) {
+ if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
+ return 1;
+ if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
+ return 1;
+ }
+ if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
+ return 1;
+ return 0;
+}
- return gl;
+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);
}
/**
- * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
- * @sdp: The GFS2 superblock
- * @number: the lock number
- * @glops: The glock_operations to use
- * @create: If 0, don't create the glock if it doesn't exist
- * @glp: the glock is returned here
- *
- * This does not lock a glock, just finds/creates structures for one.
- *
- * Returns: errno
+ * do_promote - promote as many requests as possible on the current queue
+ * @gl: The glock
+ *
+ * Returns: 1 if there is a blocked holder at the head of the list, or 2
+ * if a type specific operation is underway.
*/
-int gfs2_glock_get(struct gfs2_sbd *sdp, uint64_t number,
- struct gfs2_glock_operations *glops, int create,
- struct gfs2_glock **glp)
+static int do_promote(struct gfs2_glock *gl)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
{
- struct lm_lockname name;
- struct gfs2_glock *gl, *tmp;
- struct gfs2_gl_hash_bucket *bucket;
- int error;
-
- name.ln_number = number;
- name.ln_type = glops->go_type;
- bucket = &sdp->sd_gl_hash[gl_hash(&name)];
-
- read_lock(&bucket->hb_lock);
- gl = search_bucket(bucket, &name);
- read_unlock(&bucket->hb_lock);
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_holder *gh, *tmp;
+ int ret;
- if (gl || !create) {
- *glp = gl;
- return 0;
+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) {
+ if (ret == 1)
+ return 2;
+ gh->gh_error = ret;
+ list_del_init(&gh->gh_list);
+ trace_gfs2_glock_queue(gh, 0);
+ gfs2_holder_wake(gh);
+ goto restart;
+ }
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ trace_gfs2_promote(gh, 1);
+ gfs2_holder_wake(gh);
+ goto restart;
+ }
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ trace_gfs2_promote(gh, 0);
+ gfs2_holder_wake(gh);
+ continue;
+ }
+ if (gh->gh_list.prev == &gl->gl_holders)
+ return 1;
+ break;
}
+ return 0;
+}
- gl = kmem_cache_alloc(gfs2_glock_cachep, GFP_KERNEL);
- if (!gl)
- return -ENOMEM;
-
- memset(gl, 0, sizeof(struct gfs2_glock));
-
- INIT_LIST_HEAD(&gl->gl_list);
- gl->gl_name = name;
- kref_init(&gl->gl_ref);
-
- spin_lock_init(&gl->gl_spin);
-
- gl->gl_state = LM_ST_UNLOCKED;
- INIT_LIST_HEAD(&gl->gl_holders);
- INIT_LIST_HEAD(&gl->gl_waiters1);
- INIT_LIST_HEAD(&gl->gl_waiters2);
- INIT_LIST_HEAD(&gl->gl_waiters3);
+/**
+ * do_error - Something unexpected has happened during a lock request
+ *
+ */
- gl->gl_ops = glops;
+static inline void do_error(struct gfs2_glock *gl, const int ret)
+{
+ struct gfs2_holder *gh, *tmp;
- gl->gl_bucket = bucket;
- INIT_LIST_HEAD(&gl->gl_reclaim);
+ 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);
+ trace_gfs2_glock_queue(gh, 0);
+ gfs2_holder_wake(gh);
+ }
+}
- gl->gl_sbd = sdp;
+/**
+ * find_first_waiter - find the first gh that's waiting for the glock
+ * @gl: the glock
+ */
- lops_init_le(&gl->gl_le, &gfs2_glock_lops);
- INIT_LIST_HEAD(&gl->gl_ail_list);
+static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
+{
+ struct gfs2_holder *gh;
- /* If this glock protects actual on-disk data or metadata blocks,
- create a VFS inode to manage the pages/buffers holding them. */
- if (glops == &gfs2_inode_glops ||
- glops == &gfs2_rgrp_glops ||
- glops == &gfs2_meta_glops) {
- gl->gl_aspace = gfs2_aspace_get(sdp);
- if (!gl->gl_aspace) {
- error = -ENOMEM;
- goto fail;
- }
+ list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+ return gh;
}
+ return NULL;
+}
- error = gfs2_lm_get_lock(sdp, &name, &gl->gl_lock);
- if (error)
- goto fail_aspace;
-
- write_lock(&bucket->hb_lock);
- tmp = search_bucket(bucket, &name);
- if (tmp) {
- write_unlock(&bucket->hb_lock);
- glock_free(gl);
- gl = tmp;
- } else {
- list_add_tail(&gl->gl_list, &bucket->hb_list);
- write_unlock(&bucket->hb_lock);
- }
+/**
+ * state_change - record that the glock is now in a different state
+ * @gl: the glock
+ * @new_state the new state
+ *
+ */
- *glp = gl;
+static void state_change(struct gfs2_glock *gl, unsigned int new_state)
+{
+ int held1, held2;
- return 0;
+ held1 = (gl->gl_state != LM_ST_UNLOCKED);
+ held2 = (new_state != LM_ST_UNLOCKED);
- fail_aspace:
- if (gl->gl_aspace)
- gfs2_aspace_put(gl->gl_aspace);
+ if (held1 != held2) {
+ if (held2)
+ gfs2_glock_hold(gl);
+ else
+ gfs2_glock_put_nolock(gl);
+ }
- fail:
- kmem_cache_free(gfs2_glock_cachep, gl);
+ gl->gl_state = new_state;
+ gl->gl_tchange = jiffies;
+}
- return error;
+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);
}
/**
- * gfs2_holder_init - initialize a struct gfs2_holder in the default way
- * @gl: the glock
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gh: the holder structure
+ * finish_xmote - The DLM has replied to one of our lock requests
+ * @gl: The glock
+ * @ret: The status from the DLM
*
*/
-void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
- struct gfs2_holder *gh)
+static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
{
- INIT_LIST_HEAD(&gh->gh_list);
- gh->gh_gl = gl;
- gh->gh_ip = (unsigned long)__builtin_return_address(0);
- gh->gh_owner = current;
- gh->gh_state = state;
- gh->gh_flags = flags;
- gh->gh_error = 0;
- gh->gh_iflags = 0;
- init_completion(&gh->gh_wait);
+ const struct gfs2_glock_operations *glops = gl->gl_ops;
+ struct gfs2_holder *gh;
+ unsigned state = ret & LM_OUT_ST_MASK;
+ int rv;
- if (gh->gh_state == LM_ST_EXCLUSIVE)
- gh->gh_flags |= GL_LOCAL_EXCL;
+ spin_lock(&gl->gl_spin);
+ trace_gfs2_glock_state_change(gl, state);
+ 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;
+ }
- gfs2_glock_hold(gl);
+ /* 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) {
+ 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;
+ }
+ }
+ rv = do_promote(gl);
+ if (rv == 2)
+ goto out_locked;
+ }
+out:
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+out_locked:
+ spin_unlock(&gl->gl_spin);
+ gfs2_glock_put(gl);
}
-/**
- * gfs2_holder_reinit - reinitialize a struct gfs2_holder so we can requeue it
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gh: the holder structure
- *
- * Don't mess with the glock.
- *
- */
-
-void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
+static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
+ unsigned int req_state,
+ unsigned int flags)
{
- gh->gh_state = state;
- gh->gh_flags = flags;
- if (gh->gh_state == LM_ST_EXCLUSIVE)
- gh->gh_flags |= GL_LOCAL_EXCL;
+ int ret = LM_OUT_ERROR;
- gh->gh_iflags &= 1 << HIF_ALLOCED;
- gh->gh_ip = (unsigned long)__builtin_return_address(0);
+ if (!sdp->sd_lockstruct.ls_ops->lm_lock)
+ return req_state == LM_ST_UNLOCKED ? 0 : req_state;
+
+ if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock,
+ req_state, flags);
+ return ret;
}
/**
- * gfs2_holder_uninit - uninitialize a holder structure (drop glock reference)
- * @gh: the holder structure
+ * 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
*
*/
-void gfs2_holder_uninit(struct gfs2_holder *gh)
+static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
{
- gfs2_glock_put(gh->gh_gl);
- gh->gh_gl = NULL;
- gh->gh_ip = 0;
+ 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, 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);
}
/**
- * gfs2_holder_get - get a struct gfs2_holder structure
+ * find_first_holder - find the first "holder" gh
* @gl: the glock
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gfp_flags: __GFP_NOFAIL
- *
- * Figure out how big an impact this function has. Either:
- * 1) Replace it with a cache of structures hanging off the struct gfs2_sbd
- * 2) Leave it like it is
- *
- * Returns: the holder structure, NULL on ENOMEM
*/
-static struct gfs2_holder *gfs2_holder_get(struct gfs2_glock *gl,
- unsigned int state,
- int flags, gfp_t gfp_flags)
+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
{
struct gfs2_holder *gh;
- gh = kmalloc(sizeof(struct gfs2_holder), gfp_flags);
- if (!gh)
- return NULL;
-
- gfs2_holder_init(gl, state, flags, gh);
- set_bit(HIF_ALLOCED, &gh->gh_iflags);
- gh->gh_ip = (unsigned long)__builtin_return_address(0);
- return 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;
}
/**
- * gfs2_holder_put - get rid of a struct gfs2_holder structure
- * @gh: the holder structure
+ * 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 gfs2_holder_put(struct gfs2_holder *gh)
+static void run_queue(struct gfs2_glock *gl, const int nonblock)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
{
- gfs2_holder_uninit(gh);
- kfree(gh);
-}
+ struct gfs2_holder *gh = NULL;
+ int ret;
-/**
- * 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);
- complete(&gh->gh_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;
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_glock_operations *glops = gl->gl_ops;
-
- 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);
-
- if (atomic_read(&sdp->sd_reclaim_count) >
- gfs2_tune_get(sdp, gt_reclaim_limit) &&
- !(gh->gh_flags & LM_FLAG_PRIORITY)) {
- gfs2_reclaim_glock(sdp);
- gfs2_reclaim_glock(sdp);
- }
-
- glops->go_xmote_th(gl, gh->gh_state,
- gh->gh_flags);
-
- 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_flags & GL_LOCAL_EXCL)
- return 1;
- next_gh = list_entry(gl->gl_holders.next, struct gfs2_holder,
- gh_list);
- if (next_gh->gh_flags & GL_LOCAL_EXCL)
- return 1;
- }
-
- list_move_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
-
- complete(&gh->gh_wait);
-
- 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_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_glock_operations *glops = gl->gl_ops;
-
- if (!list_empty(&gl->gl_holders))
- return 1;
+ if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
+ return;
- if (gl->gl_state == gh->gh_state || gl->gl_state == LM_ST_UNLOCKED) {
- list_del_init(&gh->gh_list);
- gh->gh_error = 0;
- spin_unlock(&gl->gl_spin);
- if (test_bit(HIF_DEALLOC, &gh->gh_iflags))
- gfs2_holder_put(gh);
- else
- complete(&gh->gh_wait);
- spin_lock(&gl->gl_spin);
+ 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_unlock;
+ if (nonblock)
+ goto out_sched;
+ set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
+ GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
+ gl->gl_target = gl->gl_demote_state;
} else {
- gl->gl_req_gh = gh;
- set_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
-
- if (gh->gh_state == LM_ST_UNLOCKED ||
- gl->gl_state != LM_ST_EXCLUSIVE)
- glops->go_drop_th(gl);
- else
- glops->go_xmote_th(gl, gh->gh_state, gh->gh_flags);
-
- spin_lock(&gl->gl_spin);
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags))
+ gfs2_demote_wake(gl);
+ ret = do_promote(gl);
+ if (ret == 0)
+ goto out_unlock;
+ if (ret == 2)
+ 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);
+out:
+ return;
- return 0;
+out_sched:
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put_nolock(gl);
+out_unlock:
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+ goto out;
}
-/**
- * rq_greedy - process a queued request to drop greedy status
- * @gh: the glock holder
- *
- * Returns: 1 if the queue is blocked
- */
-
-static int rq_greedy(struct gfs2_holder *gh)
+static void delete_work_func(struct work_struct *work)
{
- struct gfs2_glock *gl = gh->gh_gl;
+ struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete);
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct gfs2_inode *ip = NULL;
+ struct inode *inode;
+ u64 no_addr = 0;
- list_del_init(&gh->gh_list);
- /* gh->gh_error never examined. */
- clear_bit(GLF_GREEDY, &gl->gl_flags);
+ spin_lock(&gl->gl_spin);
+ ip = (struct gfs2_inode *)gl->gl_object;
+ if (ip)
+ no_addr = ip->i_no_addr;
spin_unlock(&gl->gl_spin);
-
- gfs2_holder_uninit(gh);
- kfree(container_of(gh, struct greedy, gr_gh));
-
- spin_lock(&gl->gl_spin);
-
- 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);
-
- if (test_bit(HIF_MUTEX, &gh->gh_iflags))
- blocked = rq_mutex(gh);
- else
- gfs2_assert_warn(gl->gl_sbd, 0);
-
- } else if (!list_empty(&gl->gl_waiters2) &&
- !test_bit(GLF_SKIP_WAITERS2, &gl->gl_flags)) {
- gh = list_entry(gl->gl_waiters2.next,
- struct gfs2_holder, gh_list);
-
- if (test_bit(HIF_DEMOTE, &gh->gh_iflags))
- blocked = rq_demote(gh);
- else if (test_bit(HIF_GREEDY, &gh->gh_iflags))
- blocked = rq_greedy(gh);
- else
- gfs2_assert_warn(gl->gl_sbd, 0);
-
- } else if (!list_empty(&gl->gl_waiters3)) {
- gh = list_entry(gl->gl_waiters3.next,
- struct gfs2_holder, gh_list);
-
- if (test_bit(HIF_PROMOTE, &gh->gh_iflags))
- blocked = rq_promote(gh);
- else
- gfs2_assert_warn(gl->gl_sbd, 0);
-
- } else
- break;
-
- if (blocked)
- break;
+ if (ip) {
+ inode = gfs2_ilookup(sdp->sd_vfs, no_addr);
+ if (inode) {
+ d_prune_aliases(inode);
+ iput(inode);
+ }
}
+ gfs2_glock_put(gl);
}
-/**
- * gfs2_glmutex_lock - acquire a local lock on a glock
- * @gl: the glock
- *
- * Gives caller exclusive access to manipulate a glock structure.
- */
-
-void gfs2_glmutex_lock(struct gfs2_glock *gl)
+static void glock_work_func(struct work_struct *work)
{
- struct gfs2_holder gh;
-
- gfs2_holder_init(gl, 0, 0, &gh);
- set_bit(HIF_MUTEX, &gh.gh_iflags);
+ 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);
+ down_read(&gfs2_umount_flush_sem);
spin_lock(&gl->gl_spin);
- if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
- list_add_tail(&gh.gh_list, &gl->gl_waiters1);
- else
- complete(&gh.gh_wait);
+ if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+ gl->gl_state != LM_ST_UNLOCKED &&
+ gl->gl_demote_state != LM_ST_EXCLUSIVE) {
+ 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);
-
- wait_for_completion(&gh.gh_wait);
- gfs2_holder_uninit(&gh);
+ up_read(&gfs2_umount_flush_sem);
+ if (!delay ||
+ queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+ gfs2_glock_put(gl);
}
/**
- * gfs2_glmutex_trylock - try to acquire a local lock on a glock
- * @gl: the glock
+ * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
+ * @sdp: The GFS2 superblock
+ * @number: the lock number
+ * @glops: The glock_operations to use
+ * @create: If 0, don't create the glock if it doesn't exist
+ * @glp: the glock is returned here
*
- * 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;
- spin_unlock(&gl->gl_spin);
-
- return acquired;
-}
-
-/**
- * gfs2_glmutex_unlock - release a local lock on a glock
- * @gl: the glock
+ * This does not lock a glock, just finds/creates structures for one.
*
+ * Returns: errno
*/
-void gfs2_glmutex_unlock(struct gfs2_glock *gl)
+int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
+ const struct gfs2_glock_operations *glops, int create,
+ struct gfs2_glock **glp)
{
- spin_lock(&gl->gl_spin);
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- BUG_ON(!spin_is_locked(&gl->gl_spin));
- spin_unlock(&gl->gl_spin);
-}
+ struct lm_lockname name = { .ln_number = number, .ln_type = glops->go_type };
+ struct gfs2_glock *gl, *tmp;
+ unsigned int hash = gl_hash(sdp, &name);
+ int error;
-/**
- * handle_callback - add a demote request to a lock's queue
- * @gl: the glock
- * @state: the state the caller wants us to change to
- *
- */
+ read_lock(gl_lock_addr(hash));
+ gl = search_bucket(hash, sdp, &name);
+ read_unlock(gl_lock_addr(hash));
-static void handle_callback(struct gfs2_glock *gl, unsigned int state)
-{
- struct gfs2_holder *gh, *new_gh = NULL;
+ *glp = gl;
+ if (gl)
+ return 0;
+ if (!create)
+ return -ENOENT;
- restart:
- spin_lock(&gl->gl_spin);
+ gl = kmem_cache_alloc(gfs2_glock_cachep, GFP_KERNEL);
+ if (!gl)
+ return -ENOMEM;
- list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
- if (test_bit(HIF_DEMOTE, &gh->gh_iflags) &&
- gl->gl_req_gh != gh) {
- if (gh->gh_state != state)
- gh->gh_state = LM_ST_UNLOCKED;
- goto out;
+ gl->gl_flags = 0;
+ 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_ops = glops;
+ snprintf(gl->gl_strname, GDLM_STRNAME_BYTES, "%8x%16llx", name.ln_type, (unsigned long long)number);
+ memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
+ gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
+ gl->gl_tchange = jiffies;
+ gl->gl_object = NULL;
+ gl->gl_sbd = sdp;
+ gl->gl_aspace = NULL;
+ INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
+ INIT_WORK(&gl->gl_delete, delete_work_func);
+
+ /* If this glock protects actual on-disk data or metadata blocks,
+ create a VFS inode to manage the pages/buffers holding them. */
+ if (glops == &gfs2_inode_glops || glops == &gfs2_rgrp_glops) {
+ gl->gl_aspace = gfs2_aspace_get(sdp);
+ if (!gl->gl_aspace) {
+ error = -ENOMEM;
+ goto fail;
}
}
- if (new_gh) {
- list_add_tail(&new_gh->gh_list, &gl->gl_waiters2);
- new_gh = NULL;
+ write_lock(gl_lock_addr(hash));
+ tmp = search_bucket(hash, sdp, &name);
+ if (tmp) {
+ write_unlock(gl_lock_addr(hash));
+ glock_free(gl);
+ gl = tmp;
} else {
- spin_unlock(&gl->gl_spin);
-
- new_gh = gfs2_holder_get(gl, state, LM_FLAG_TRY,
- GFP_KERNEL | __GFP_NOFAIL),
- set_bit(HIF_DEMOTE, &new_gh->gh_iflags);
- set_bit(HIF_DEALLOC, &new_gh->gh_iflags);
-
- goto restart;
+ hlist_add_head(&gl->gl_list, &gl_hash_table[hash].hb_list);
+ write_unlock(gl_lock_addr(hash));
}
- out:
- spin_unlock(&gl->gl_spin);
+ *glp = gl;
- if (new_gh)
- gfs2_holder_put(new_gh);
+ return 0;
+
+fail:
+ kmem_cache_free(gfs2_glock_cachep, gl);
+ return error;
}
/**
- * state_change - record that the glock is now in a different state
+ * gfs2_holder_init - initialize a struct gfs2_holder in the default way
* @gl: the glock
- * @new_state the new state
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
*
*/
-static void state_change(struct gfs2_glock *gl, unsigned int new_state)
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+ struct gfs2_holder *gh)
{
- 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;
+ INIT_LIST_HEAD(&gh->gh_list);
+ gh->gh_gl = gl;
+ gh->gh_ip = (unsigned long)__builtin_return_address(0);
+ gh->gh_owner_pid = get_pid(task_pid(current));
+ gh->gh_state = state;
+ gh->gh_flags = flags;
+ gh->gh_error = 0;
+ gh->gh_iflags = 0;
+ gfs2_glock_hold(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
+ * gfs2_holder_reinit - reinitialize a struct gfs2_holder so we can requeue it
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ * Don't mess with the glock.
*
*/
-static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
+void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_glock_operations *glops = gl->gl_ops;
- struct gfs2_holder *gh = gl->gl_req_gh;
- int prev_state = gl->gl_state;
- int op_done = 1;
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
- gfs2_assert_warn(sdp, !(ret & LM_OUT_ASYNC));
-
- state_change(gl, ret & LM_OUT_ST_MASK);
-
- if (prev_state != LM_ST_UNLOCKED && !(ret & LM_OUT_CACHEABLE)) {
- if (glops->go_inval)
- glops->go_inval(gl, DIO_METADATA | DIO_DATA);
- } else if (gl->gl_state == LM_ST_DEFERRED) {
- /* We might not want to do this here.
- Look at moving to the inode glops. */
- if (glops->go_inval)
- glops->go_inval(gl, DIO_DATA);
- }
-
- /* Deal with each possible exit condition */
-
- if (!gh)
- gl->gl_stamp = jiffies;
-
- else if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- gh->gh_error = -EIO;
- spin_unlock(&gl->gl_spin);
-
- } else if (test_bit(HIF_DEMOTE, &gh->gh_iflags)) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- if (gl->gl_state == gh->gh_state ||
- gl->gl_state == LM_ST_UNLOCKED)
- gh->gh_error = 0;
- else {
- if (gfs2_assert_warn(sdp, gh->gh_flags &
- (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) == -1)
- fs_warn(sdp, "ret = 0x%.8X\n", ret);
- gh->gh_error = GLR_TRYFAILED;
- }
- spin_unlock(&gl->gl_spin);
-
- if (ret & LM_OUT_CANCELED)
- handle_callback(gl, LM_ST_UNLOCKED); /* Lame */
-
- } else if (ret & LM_OUT_CANCELED) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- gh->gh_error = GLR_CANCELED;
- spin_unlock(&gl->gl_spin);
-
- } else if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
- spin_lock(&gl->gl_spin);
- list_move_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
- spin_unlock(&gl->gl_spin);
-
- set_bit(HIF_FIRST, &gh->gh_iflags);
-
- op_done = 0;
-
- } else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- gh->gh_error = GLR_TRYFAILED;
- spin_unlock(&gl->gl_spin);
-
- } else {
- if (gfs2_assert_withdraw(sdp, 0) == -1)
- fs_err(sdp, "ret = 0x%.8X\n", ret);
- }
-
- if (glops->go_xmote_bh)
- glops->go_xmote_bh(gl);
-
- if (op_done) {
- spin_lock(&gl->gl_spin);
- gl->gl_req_gh = NULL;
- gl->gl_req_bh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- }
-
- gfs2_glock_put(gl);
-
- if (gh) {
- if (test_bit(HIF_DEALLOC, &gh->gh_iflags))
- gfs2_holder_put(gh);
- else
- complete(&gh->gh_wait);
- }
+ gh->gh_state = state;
+ gh->gh_flags = flags;
+ gh->gh_iflags = 0;
+ gh->gh_ip = (unsigned long)__builtin_return_address(0);
}
/**
- * 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
+ * gfs2_holder_uninit - uninitialize a holder structure (drop glock reference)
+ * @gh: the holder structure
*
*/
-void gfs2_glock_xmote_th(struct gfs2_glock *gl, unsigned int state, int flags)
+void gfs2_holder_uninit(struct gfs2_holder *gh)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- 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;
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
- gfs2_assert_warn(sdp, state != LM_ST_UNLOCKED);
- gfs2_assert_warn(sdp, state != gl->gl_state);
-
- if (gl->gl_state == LM_ST_EXCLUSIVE) {
- if (glops->go_sync)
- glops->go_sync(gl,
- DIO_METADATA | DIO_DATA | DIO_RELEASE);
- }
-
- gfs2_glock_hold(gl);
- gl->gl_req_bh = xmote_bh;
-
- 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);
+ put_pid(gh->gh_owner_pid);
+ gfs2_glock_put(gh->gh_gl);
+ gh->gh_gl = NULL;
+ gh->gh_ip = 0;
}
/**
- * 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
+ * gfs2_glock_holder_wait
+ * @word: unused
*
+ * This function and gfs2_glock_demote_wait both show up in the WCHAN
+ * field. Thus I've separated these otherwise identical functions in
+ * order to be more informative to the user.
*/
-static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
+static int gfs2_glock_holder_wait(void *word)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_glock_operations *glops = gl->gl_ops;
- struct gfs2_holder *gh = gl->gl_req_gh;
-
- clear_bit(GLF_PREFETCH, &gl->gl_flags);
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
- gfs2_assert_warn(sdp, !ret);
-
- state_change(gl, LM_ST_UNLOCKED);
-
- if (glops->go_inval)
- glops->go_inval(gl, DIO_METADATA | DIO_DATA);
-
- if (gh) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- gh->gh_error = 0;
- spin_unlock(&gl->gl_spin);
- }
-
- if (glops->go_drop_bh)
- glops->go_drop_bh(gl);
-
- spin_lock(&gl->gl_spin);
- gl->gl_req_gh = NULL;
- gl->gl_req_bh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
-
- gfs2_glock_put(gl);
-
- if (gh) {
- if (test_bit(HIF_DEALLOC, &gh->gh_iflags))
- gfs2_holder_put(gh);
- else
- complete(&gh->gh_wait);
- }
+ schedule();
+ return 0;
}
-/**
- * gfs2_glock_drop_th - call into the lock module to unlock a lock
- * @gl: the glock
- *
- */
-
-void gfs2_glock_drop_th(struct gfs2_glock *gl)
+static int gfs2_glock_demote_wait(void *word)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_glock_operations *glops = gl->gl_ops;
- unsigned int ret;
-
- gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
- gfs2_assert_warn(sdp, queue_empty(gl, &gl->gl_holders));
- gfs2_assert_warn(sdp, gl->gl_state != LM_ST_UNLOCKED);
-
- if (gl->gl_state == LM_ST_EXCLUSIVE) {
- if (glops->go_sync)
- glops->go_sync(gl,
- DIO_METADATA | DIO_DATA | DIO_RELEASE);
- }
-
- gfs2_glock_hold(gl);
- gl->gl_req_bh = drop_bh;
-
- ret = gfs2_lm_unlock(sdp, gl->gl_lock, gl->gl_state);
+ schedule();
+ return 0;
+}
- if (gfs2_assert_withdraw(sdp, !(ret & LM_OUT_ERROR)))
- return;
+static void wait_on_holder(struct gfs2_holder *gh)
+{
+ might_sleep();
+ wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE);
+}
- if (!ret)
- drop_bh(gl, ret);
- else
- gfs2_assert_warn(sdp, ret == LM_OUT_ASYNC);
+static void wait_on_demote(struct gfs2_glock *gl)
+{
+ might_sleep();
+ wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE);
}
/**
- * do_cancels - cancel requests for locks stuck waiting on an expire flag
- * @gh: the LM_FLAG_PRIORITY holder waiting to acquire the lock
+ * handle_callback - process a demote request
+ * @gl: the glock
+ * @state: the state the caller wants us to change to
*
- * Don't cancel GL_NOCANCEL requests.
+ * There are only two requests that we are going to see in actual
+ * practise: LM_ST_SHARED and LM_ST_UNLOCKED
*/
-static void do_cancels(struct gfs2_holder *gh)
+static void handle_callback(struct gfs2_glock *gl, unsigned int state,
+ unsigned long delay)
{
- struct gfs2_glock *gl = gh->gh_gl;
-
- spin_lock(&gl->gl_spin);
+ int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
- while (gl->gl_req_gh != gh &&
- !test_bit(HIF_HOLDER, &gh->gh_iflags) &&
- !list_empty(&gh->gh_list)) {
- if (gl->gl_req_bh &&
- !(gl->gl_req_gh &&
- (gl->gl_req_gh->gh_flags & GL_NOCANCEL))) {
- spin_unlock(&gl->gl_spin);
- gfs2_lm_cancel(gl->gl_sbd, gl->gl_lock);
- msleep(100);
- spin_lock(&gl->gl_spin);
- } else {
- spin_unlock(&gl->gl_spin);
- msleep(100);
- 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;
+ } else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
+ gl->gl_demote_state != state) {
+ gl->gl_demote_state = LM_ST_UNLOCKED;
}
-
- spin_unlock(&gl->gl_spin);
+ if (gl->gl_ops->go_callback)
+ gl->gl_ops->go_callback(gl);
+ trace_gfs2_demote_rq(gl);
}
/**
- * 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;
- 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_for_completion(&gh->gh_wait);
-
- 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;
- gl->gl_req_bh = NULL;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- }
-
+ wait_on_holder(gh);
return gh->gh_error;
}
-static inline struct gfs2_holder *
-find_holder_by_owner(struct list_head *head, struct task_struct *owner)
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
{
- struct gfs2_holder *gh;
+ va_list args;
- list_for_each_entry(gh, head, gh_list) {
- if (gh->gh_owner == owner)
- return gh;
+ va_start(args, fmt);
+ if (seq) {
+ struct gfs2_glock_iter *gi = seq->private;
+ vsprintf(gi->string, fmt, args);
+ seq_printf(seq, gi->string);
+ } else {
+ printk(KERN_ERR " ");
+ vprintk(fmt, args);
}
-
- return NULL;
+ va_end(args);
}
/**
* 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)
+__releases(&gl->gl_spin)
+__acquires(&gl->gl_spin)
{
struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_holder *existing;
-
- BUG_ON(!gh->gh_owner);
-
- existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner);
- if (existing) {
- print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
- print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- BUG();
- }
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct list_head *insert_pt = NULL;
+ struct gfs2_holder *gh2;
+ int try_lock = 0;
- existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner);
- if (existing) {
- print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
- print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+ BUG_ON(gh->gh_owner_pid == NULL);
+ if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
BUG();
- }
-
- 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);
-}
-
-/**
- * gfs2_glock_nq - enqueue a struct gfs2_holder onto a glock (acquire a glock)
- * @gh: the holder structure
- *
- * if (gh->gh_flags & GL_ASYNC), this never returns an error
- *
- * Returns: 0, GLR_TRYFAILED, or errno on failure
- */
-int gfs2_glock_nq(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
- 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);
- return -EIO;
+ 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;
}
- set_bit(HIF_PROMOTE, &gh->gh_iflags);
-
- spin_lock(&gl->gl_spin);
- add_to_queue(gh);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
-
- if (!(gh->gh_flags & GL_ASYNC)) {
- error = glock_wait_internal(gh);
- if (error == GLR_CANCELED) {
- msleep(100);
- goto restart;
+ 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;
}
-
- clear_bit(GLF_PREFETCH, &gl->gl_flags);
-
- return error;
-}
-
-/**
- * gfs2_glock_poll - poll to see if an async request has been completed
- * @gh: the holder
- *
- * Returns: 1 if the request is ready to be gfs2_glock_wait()ed on
- */
-
-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;
-}
-
-/**
- * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
- * @gh: the glock holder
- *
- */
-
-void gfs2_glock_dq(struct gfs2_holder *gh)
-{
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_glock_operations *glops = gl->gl_ops;
-
- if (gh->gh_flags & GL_SYNC)
- set_bit(GLF_SYNC, &gl->gl_flags);
-
- if (gh->gh_flags & GL_NOCACHE)
- handle_callback(gl, LM_ST_UNLOCKED);
-
- gfs2_glmutex_lock(gl);
-
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
-
- if (list_empty(&gl->gl_holders)) {
- spin_unlock(&gl->gl_spin);
-
- if (glops->go_unlock)
- glops->go_unlock(gh);
-
- if (test_bit(GLF_SYNC, &gl->gl_flags)) {
- if (glops->go_sync)
- glops->go_sync(gl, DIO_METADATA | DIO_DATA);
- }
-
- gl->gl_stamp = jiffies;
-
+ 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;
+ }
+ trace_gfs2_glock_queue(gh, 1);
+ 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);
+ if (sdp->sd_lockstruct.ls_ops->lm_cancel)
+ sdp->sd_lockstruct.ls_ops->lm_cancel(gl);
spin_lock(&gl->gl_spin);
}
+ return;
- clear_bit(GLF_LOCK, &gl->gl_flags);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
+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();
}
/**
- * gfs2_glock_prefetch - Try to prefetch a glock
- * @gl: the glock
- * @state: the state to prefetch in
- * @flags: flags passed to go_xmote_th()
+ * gfs2_glock_nq - enqueue a struct gfs2_holder onto a glock (acquire a glock)
+ * @gh: the holder structure
*
+ * if (gh->gh_flags & GL_ASYNC), this never returns an error
+ *
+ * Returns: 0, GLR_TRYFAILED, or errno on failure
*/
-static void gfs2_glock_prefetch(struct gfs2_glock *gl, unsigned int state,
- int flags)
+int gfs2_glock_nq(struct gfs2_holder *gh)
{
- struct gfs2_glock_operations *glops = gl->gl_ops;
-
- spin_lock(&gl->gl_spin);
+ struct gfs2_glock *gl = gh->gh_gl;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ int error = 0;
- if (test_bit(GLF_LOCK, &gl->gl_flags) ||
- !list_empty(&gl->gl_holders) ||
- !list_empty(&gl->gl_waiters1) ||
- !list_empty(&gl->gl_waiters2) ||
- !list_empty(&gl->gl_waiters3) ||
- relaxed_state_ok(gl->gl_state, state, flags)) {
- spin_unlock(&gl->gl_spin);
- return;
- }
+ if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ return -EIO;
- set_bit(GLF_PREFETCH, &gl->gl_flags);
- set_bit(GLF_LOCK, &gl->gl_flags);
+ spin_lock(&gl->gl_spin);
+ add_to_queue(gh);
+ run_queue(gl, 1);
spin_unlock(&gl->gl_spin);
- glops->go_xmote_th(gl, state, flags);
-}
-
-static void greedy_work(void *data)
-{
- struct greedy *gr = data;
- struct gfs2_holder *gh = &gr->gr_gh;
- struct gfs2_glock *gl = gh->gh_gl;
- struct gfs2_glock_operations *glops = gl->gl_ops;
-
- clear_bit(GLF_SKIP_WAITERS2, &gl->gl_flags);
+ if (!(gh->gh_flags & GL_ASYNC))
+ error = gfs2_glock_wait(gh);
- if (glops->go_greedy)
- glops->go_greedy(gl);
+ return error;
+}
- spin_lock(&gl->gl_spin);
+/**
+ * gfs2_glock_poll - poll to see if an async request has been completed
+ * @gh: the holder
+ *
+ * Returns: 1 if the request is ready to be gfs2_glock_wait()ed on
+ */
- if (list_empty(&gl->gl_waiters2)) {
- clear_bit(GLF_GREEDY, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- gfs2_holder_uninit(gh);
- kfree(gr);
- } else {
- gfs2_glock_hold(gl);
- list_add_tail(&gh->gh_list, &gl->gl_waiters2);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
- gfs2_glock_put(gl);
- }
+int gfs2_glock_poll(struct gfs2_holder *gh)
+{
+ return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
}
/**
- * gfs2_glock_be_greedy -
- * @gl:
- * @time:
+ * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
+ * @gh: the glock holder
*
- * Returns: 0 if go_greedy will be called, 1 otherwise
*/
-int gfs2_glock_be_greedy(struct gfs2_glock *gl, unsigned int time)
+void gfs2_glock_dq(struct gfs2_holder *gh)
{
- struct greedy *gr;
- 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;
- if (!time ||
- gl->gl_sbd->sd_args.ar_localcaching ||
- test_and_set_bit(GLF_GREEDY, &gl->gl_flags))
- return 1;
+ spin_lock(&gl->gl_spin);
+ if (gh->gh_flags & GL_NOCACHE)
+ handle_callback(gl, LM_ST_UNLOCKED, 0);
- gr = kmalloc(sizeof(struct greedy), GFP_KERNEL);
- if (!gr) {
- clear_bit(GLF_GREEDY, &gl->gl_flags);
- return 1;
+ list_del_init(&gh->gh_list);
+ 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);
+ }
+ if (list_empty(&gl->gl_holders) &&
+ !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+ !test_bit(GLF_DEMOTE, &gl->gl_flags))
+ fast_path = 1;
}
- gh = &gr->gr_gh;
-
- gfs2_holder_init(gl, 0, 0, gh);
- set_bit(HIF_GREEDY, &gh->gh_iflags);
- INIT_WORK(&gr->gr_work, greedy_work, gr);
+ trace_gfs2_glock_queue(gh, 0);
+ spin_unlock(&gl->gl_spin);
+ if (likely(fast_path))
+ return;
- set_bit(GLF_SKIP_WAITERS2, &gl->gl_flags);
- schedule_delayed_work(&gr->gr_work, time);
+ gfs2_glock_hold(gl);
+ if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+ !test_bit(GLF_DEMOTE, &gl->gl_flags))
+ delay = gl->gl_ops->go_min_hold_time;
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+ gfs2_glock_put(gl);
+}
- return 0;
+void gfs2_glock_dq_wait(struct gfs2_holder *gh)
+{
+ struct gfs2_glock *gl = gh->gh_gl;
+ gfs2_glock_dq(gh);
+ wait_on_demote(gl);
}
/**
* Returns: errno
*/
-int gfs2_glock_nq_num(struct gfs2_sbd *sdp, uint64_t number,
- struct gfs2_glock_operations *glops, unsigned int state,
- int flags, struct gfs2_holder *gh)
+int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
+ const struct gfs2_glock_operations *glops,
+ unsigned int state, int flags, struct gfs2_holder *gh)
{
struct gfs2_glock *gl;
int error;
static int glock_compare(const void *arg_a, const void *arg_b)
{
- struct gfs2_holder *gh_a = *(struct gfs2_holder **)arg_a;
- struct gfs2_holder *gh_b = *(struct gfs2_holder **)arg_b;
- struct lm_lockname *a = &gh_a->gh_gl->gl_name;
- struct lm_lockname *b = &gh_b->gh_gl->gl_name;
- int ret = 0;
+ const struct gfs2_holder *gh_a = *(const struct gfs2_holder **)arg_a;
+ const struct gfs2_holder *gh_b = *(const struct gfs2_holder **)arg_b;
+ const struct lm_lockname *a = &gh_a->gh_gl->gl_name;
+ const struct lm_lockname *b = &gh_b->gh_gl->gl_name;
if (a->ln_number > b->ln_number)
- ret = 1;
- else if (a->ln_number < b->ln_number)
- ret = -1;
- else {
- if (gh_a->gh_state == LM_ST_SHARED &&
- gh_b->gh_state == LM_ST_EXCLUSIVE)
- ret = 1;
- else if (!(gh_a->gh_flags & GL_LOCAL_EXCL) &&
- (gh_b->gh_flags & GL_LOCAL_EXCL))
- ret = 1;
- }
-
- return ret;
+ return 1;
+ if (a->ln_number < b->ln_number)
+ return -1;
+ BUG_ON(gh_a->gh_gl->gl_ops->go_type == gh_b->gh_gl->gl_ops->go_type);
+ return 0;
}
/**
* @num_gh: the number of structures
* @ghs: an array of struct gfs2_holder structures
*
- * Figure out how big an impact this function has. Either:
- * 1) Replace this code with code that calls gfs2_glock_prefetch()
- * 2) Forget async stuff and just call nq_m_sync()
- * 3) Leave it like it is
*
* Returns: 0 on success (all glocks acquired),
* errno on failure (no glocks acquired)
int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
- int *e;
- unsigned int x;
- int borked = 0, serious = 0;
+ struct gfs2_holder *tmp[4];
+ struct gfs2_holder **pph = tmp;
int error = 0;
- if (!num_gh)
+ switch(num_gh) {
+ case 0:
return 0;
-
- if (num_gh == 1) {
+ case 1:
ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC);
return gfs2_glock_nq(ghs);
- }
-
- e = kcalloc(num_gh, sizeof(struct gfs2_holder *), GFP_KERNEL);
- if (!e)
- return -ENOMEM;
-
- for (x = 0; x < num_gh; x++) {
- ghs[x].gh_flags |= LM_FLAG_TRY | GL_ASYNC;
- error = gfs2_glock_nq(&ghs[x]);
- if (error) {
- borked = 1;
- serious = error;
- num_gh = x;
- break;
- }
- }
-
- for (x = 0; x < num_gh; x++) {
- error = e[x] = glock_wait_internal(&ghs[x]);
- if (error) {
- borked = 1;
- if (error != GLR_TRYFAILED && error != GLR_CANCELED)
- serious = error;
- }
- }
-
- if (!borked) {
- kfree(e);
- return 0;
- }
-
- for (x = 0; x < num_gh; x++)
- if (!e[x])
- gfs2_glock_dq(&ghs[x]);
-
- if (serious)
- error = serious;
- else {
- for (x = 0; x < num_gh; x++)
- gfs2_holder_reinit(ghs[x].gh_state, ghs[x].gh_flags,
- &ghs[x]);
- error = nq_m_sync(num_gh, ghs, (struct gfs2_holder **)e);
- }
-
- kfree(e);
-
- return error;
-}
-
-/**
- * gfs2_glock_dq_m - release multiple glocks
- * @num_gh: the number of structures
- * @ghs: an array of struct gfs2_holder structures
- *
- */
-
-void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
-{
- unsigned int x;
-
- for (x = 0; x < num_gh; x++)
- gfs2_glock_dq(&ghs[x]);
-}
-
-/**
- * gfs2_glock_dq_uninit_m - release multiple glocks
- * @num_gh: the number of structures
- * @ghs: an array of struct gfs2_holder structures
- *
- */
-
-void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
-{
- unsigned int x;
-
- for (x = 0; x < num_gh; x++)
- gfs2_glock_dq_uninit(&ghs[x]);
-}
-
-/**
- * gfs2_glock_prefetch_num - prefetch a glock based on lock number
- * @sdp: the filesystem
- * @number: the lock number
- * @glops: the glock operations for the type of glock
- * @state: the state to acquire the glock in
- * @flags: modifier flags for the aquisition
- *
- * Returns: errno
- */
-
-void gfs2_glock_prefetch_num(struct gfs2_sbd *sdp, uint64_t number,
- struct gfs2_glock_operations *glops,
- unsigned int state, int flags)
-{
- struct gfs2_glock *gl;
- int error;
-
- if (atomic_read(&sdp->sd_reclaim_count) <
- gfs2_tune_get(sdp, gt_reclaim_limit)) {
- error = gfs2_glock_get(sdp, number, glops, CREATE, &gl);
- if (!error) {
- gfs2_glock_prefetch(gl, state, flags);
- gfs2_glock_put(gl);
- }
- }
-}
-
-/**
- * gfs2_lvb_hold - attach a LVB from a glock
- * @gl: The glock in question
- *
- */
-
-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);
- return error;
- }
- gfs2_glock_hold(gl);
- }
- atomic_inc(&gl->gl_lvb_count);
-
- gfs2_glmutex_unlock(gl);
-
- return 0;
-}
-
-/**
- * gfs2_lvb_unhold - detach a LVB from a glock
- * @gl: The glock in question
- *
- */
-
-void gfs2_lvb_unhold(struct gfs2_glock *gl)
-{
- 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)) {
- gfs2_lm_unhold_lvb(gl->gl_sbd, gl->gl_lock, gl->gl_lvb);
- gl->gl_lvb = NULL;
- gfs2_glock_put(gl);
- }
-
- gfs2_glmutex_unlock(gl);
- gfs2_glock_put(gl);
-}
-
-#if 0
-void gfs2_lvb_sync(struct gfs2_glock *gl)
-{
- gfs2_glmutex_lock(gl);
-
- gfs2_assert(gl->gl_sbd, atomic_read(&gl->gl_lvb_count));
- if (!gfs2_assert_warn(gl->gl_sbd, gfs2_glock_is_held_excl(gl)))
- gfs2_lm_sync_lvb(gl->gl_sbd, gl->gl_lock, gl->gl_lvb);
-
- gfs2_glmutex_unlock(gl);
-}
-#endif /* 0 */
-
-static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
- unsigned int state)
-{
- struct gfs2_glock *gl;
-
- gl = gfs2_glock_find(sdp, name);
- if (!gl)
- return;
-
- if (gl->gl_ops->go_callback)
- gl->gl_ops->go_callback(gl, state);
- handle_callback(gl, state);
-
- spin_lock(&gl->gl_spin);
- run_queue(gl);
- spin_unlock(&gl->gl_spin);
-
- gfs2_glock_put(gl);
-}
-
-/**
- * gfs2_glock_cb - Callback used by locking module
- * @fsdata: Pointer to the superblock
- * @type: Type of callback
- * @data: Type dependent data pointer
- *
- * Called by the locking module when it wants to tell us something.
- * Either we need to drop a lock, one of our ASYNC requests completed, or
- * a journal from another client needs to be recovered.
- */
-
-void gfs2_glock_cb(lm_fsdata_t *fsdata, unsigned int type, void *data)
-{
- struct gfs2_sbd *sdp = (struct gfs2_sbd *)fsdata;
-
- switch (type) {
- case LM_CB_NEED_E:
- blocking_cb(sdp, data, LM_ST_UNLOCKED);
- return;
-
- case LM_CB_NEED_D:
- blocking_cb(sdp, data, LM_ST_DEFERRED);
- return;
-
- case LM_CB_NEED_S:
- blocking_cb(sdp, data, LM_ST_SHARED);
- return;
-
- case LM_CB_ASYNC: {
- struct lm_async_cb *async = data;
- struct gfs2_glock *gl;
-
- gl = gfs2_glock_find(sdp, &async->lc_name);
- if (gfs2_assert_warn(sdp, gl))
- return;
- if (!gfs2_assert_warn(sdp, gl->gl_req_bh))
- gl->gl_req_bh(gl, async->lc_ret);
- gfs2_glock_put(gl);
- return;
- }
-
- case LM_CB_NEED_RECOVERY:
- gfs2_jdesc_make_dirty(sdp, *(unsigned int *)data);
- if (sdp->sd_recoverd_process)
- wake_up_process(sdp->sd_recoverd_process);
- return;
-
- case LM_CB_DROPLOCKS:
- gfs2_gl_hash_clear(sdp, NO_WAIT);
- gfs2_quota_scan(sdp);
- return;
-
default:
- gfs2_assert_warn(sdp, 0);
- return;
- }
-}
-
-/**
- * gfs2_try_toss_inode - try to remove a particular inode struct from cache
- * sdp: the filesystem
- * inum: the inode number
- *
- */
-
-void gfs2_try_toss_inode(struct gfs2_sbd *sdp, struct gfs2_inum *inum)
-{
- struct gfs2_glock *gl;
- struct gfs2_inode *ip;
- int error;
-
- error = gfs2_glock_get(sdp, inum->no_addr, &gfs2_inode_glops,
- NO_CREATE, &gl);
- if (error || !gl)
- return;
-
- if (!gfs2_glmutex_trylock(gl))
- goto out;
-
- ip = gl->gl_object;
- if (!ip)
- goto out_unlock;
-
- if (atomic_read(&ip->i_count))
- goto out_unlock;
-
- gfs2_inode_destroy(ip, 1);
-
- out_unlock:
- gfs2_glmutex_unlock(gl);
-
- out:
- gfs2_glock_put(gl);
-}
-
-/**
- * gfs2_iopen_go_callback - Try to kick the inode/vnode associated with an
- * iopen glock from memory
- * @io_gl: the iopen glock
- * @state: the state into which the glock should be put
- *
- */
-
-void gfs2_iopen_go_callback(struct gfs2_glock *io_gl, unsigned int state)
-{
- struct gfs2_glock *i_gl;
-
- if (state != LM_ST_UNLOCKED)
- return;
-
- spin_lock(&io_gl->gl_spin);
- i_gl = io_gl->gl_object;
- if (i_gl) {
- gfs2_glock_hold(i_gl);
- spin_unlock(&io_gl->gl_spin);
- } else {
- spin_unlock(&io_gl->gl_spin);
- return;
+ if (num_gh <= 4)
+ break;
+ pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS);
+ if (!pph)
+ return -ENOMEM;
}
- if (gfs2_glmutex_trylock(i_gl)) {
- struct gfs2_inode *ip = i_gl->gl_object;
- if (ip) {
- gfs2_try_toss_vnode(ip);
- gfs2_glmutex_unlock(i_gl);
- gfs2_glock_schedule_for_reclaim(i_gl);
- goto out;
- }
- gfs2_glmutex_unlock(i_gl);
- }
+ error = nq_m_sync(num_gh, ghs, pph);
- out:
- gfs2_glock_put(i_gl);
+ if (pph != tmp)
+ kfree(pph);
+
+ return error;
}
/**
- * demote_ok - Check to see if it's ok to unlock a glock
- * @gl: the glock
+ * gfs2_glock_dq_m - release multiple glocks
+ * @num_gh: the number of structures
+ * @ghs: an array of struct gfs2_holder structures
*
- * Returns: 1 if it's ok
*/
-static int demote_ok(struct gfs2_glock *gl)
+void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- struct gfs2_glock_operations *glops = gl->gl_ops;
- int demote = 1;
-
- if (test_bit(GLF_STICKY, &gl->gl_flags))
- demote = 0;
- else if (test_bit(GLF_PREFETCH, &gl->gl_flags))
- demote = time_after_eq(jiffies,
- gl->gl_stamp +
- gfs2_tune_get(sdp, gt_prefetch_secs) * HZ);
- else if (glops->go_demote_ok)
- demote = glops->go_demote_ok(gl);
+ unsigned int x;
- return demote;
+ for (x = 0; x < num_gh; x++)
+ gfs2_glock_dq(&ghs[x]);
}
/**
- * gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
- * @gl: the glock
+ * gfs2_glock_dq_uninit_m - release multiple glocks
+ * @num_gh: the number of structures
+ * @ghs: an array of struct gfs2_holder structures
*
*/
-void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
+void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
-
- spin_lock(&sdp->sd_reclaim_lock);
- if (list_empty(&gl->gl_reclaim)) {
- gfs2_glock_hold(gl);
- list_add(&gl->gl_reclaim, &sdp->sd_reclaim_list);
- atomic_inc(&sdp->sd_reclaim_count);
- }
- spin_unlock(&sdp->sd_reclaim_lock);
+ unsigned int x;
- wake_up(&sdp->sd_reclaim_wq);
+ for (x = 0; x < num_gh; x++)
+ gfs2_glock_dq_uninit(&ghs[x]);
}
-/**
- * gfs2_reclaim_glock - process the next glock on the filesystem's reclaim list
- * @sdp: the filesystem
- *
- * Called from gfs2_glockd() glock reclaim daemon, or when promoting a
- * different glock and we notice that there are a lot of glocks in the
- * reclaim list.
- *
- */
-
-void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
+void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
{
- struct gfs2_glock *gl;
+ unsigned long delay = 0;
+ unsigned long holdtime;
+ unsigned long now = jiffies;
- spin_lock(&sdp->sd_reclaim_lock);
- if (list_empty(&sdp->sd_reclaim_list)) {
- spin_unlock(&sdp->sd_reclaim_lock);
- return;
- }
- gl = list_entry(sdp->sd_reclaim_list.next,
- struct gfs2_glock, gl_reclaim);
- list_del_init(&gl->gl_reclaim);
- spin_unlock(&sdp->sd_reclaim_lock);
-
- atomic_dec(&sdp->sd_reclaim_count);
- atomic_inc(&sdp->sd_reclaimed);
-
- if (gfs2_glmutex_trylock(gl)) {
- if (gl->gl_ops == &gfs2_inode_glops) {
- struct gfs2_inode *ip = gl->gl_object;
- if (ip && !atomic_read(&ip->i_count))
- gfs2_inode_destroy(ip, 1);
- }
- if (queue_empty(gl, &gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED &&
- demote_ok(gl))
- handle_callback(gl, LM_ST_UNLOCKED);
- gfs2_glmutex_unlock(gl);
- }
+ gfs2_glock_hold(gl);
+ holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+ if (time_before(now, holdtime))
+ delay = holdtime - now;
+ if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+ delay = gl->gl_ops->go_min_hold_time;
- gfs2_glock_put(gl);
+ spin_lock(&gl->gl_spin);
+ handle_callback(gl, state, delay);
+ spin_unlock(&gl->gl_spin);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+ gfs2_glock_put(gl);
}
/**
- * examine_bucket - Call a function for glock in a hash bucket
- * @examiner: the function
- * @sdp: the filesystem
- * @bucket: the bucket
+ * gfs2_glock_complete - Callback used by locking
+ * @gl: Pointer to the glock
+ * @ret: The return value from the dlm
*
- * Returns: 1 if the bucket has entries
*/
-static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
- struct gfs2_gl_hash_bucket *bucket)
+void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
{
- struct glock_plug plug;
- struct list_head *tmp;
- struct gfs2_glock *gl;
- int entries;
-
- /* Add "plug" to end of bucket list, work back up list from there */
- memset(&plug.gl_flags, 0, sizeof(unsigned long));
- set_bit(GLF_PLUG, &plug.gl_flags);
+ struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+ gl->gl_reply = ret;
+ if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))) {
+ struct gfs2_holder *gh;
+ spin_lock(&gl->gl_spin);
+ gh = find_first_waiter(gl);
+ if ((!(gh && (gh->gh_flags & LM_FLAG_NOEXP)) &&
+ (gl->gl_target != LM_ST_UNLOCKED)) ||
+ ((ret & ~LM_OUT_ST_MASK) != 0))
+ set_bit(GLF_FROZEN, &gl->gl_flags);
+ spin_unlock(&gl->gl_spin);
+ if (test_bit(GLF_FROZEN, &gl->gl_flags))
+ return;
+ }
+ set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
+}
- write_lock(&bucket->hb_lock);
- list_add(&plug.gl_list, &bucket->hb_list);
- write_unlock(&bucket->hb_lock);
- for (;;) {
- write_lock(&bucket->hb_lock);
+static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask)
+{
+ struct gfs2_glock *gl;
+ int may_demote;
+ int nr_skipped = 0;
+ LIST_HEAD(skipped);
- for (;;) {
- tmp = plug.gl_list.next;
+ if (nr == 0)
+ goto out;
- if (tmp == &bucket->hb_list) {
- list_del(&plug.gl_list);
- entries = !list_empty(&bucket->hb_list);
- write_unlock(&bucket->hb_lock);
- return entries;
- }
- gl = list_entry(tmp, struct gfs2_glock, gl_list);
+ if (!(gfp_mask & __GFP_FS))
+ return -1;
- /* Move plug up list */
- list_move(&plug.gl_list, &gl->gl_list);
+ spin_lock(&lru_lock);
+ while(nr && !list_empty(&lru_list)) {
+ gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
+ list_del_init(&gl->gl_lru);
+ atomic_dec(&lru_count);
- if (test_bit(GLF_PLUG, &gl->gl_flags))
- continue;
+ /* Check if glock is about to be freed */
+ if (atomic_read(&gl->gl_ref) == 0)
+ continue;
- /* examiner() must glock_put() */
+ /* Test for being demotable */
+ if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
gfs2_glock_hold(gl);
-
- break;
+ spin_unlock(&lru_lock);
+ spin_lock(&gl->gl_spin);
+ may_demote = demote_ok(gl);
+ if (may_demote) {
+ handle_callback(gl, LM_ST_UNLOCKED, 0);
+ nr--;
+ }
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put_nolock(gl);
+ spin_unlock(&gl->gl_spin);
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+ spin_lock(&lru_lock);
+ continue;
}
-
- write_unlock(&bucket->hb_lock);
-
- examiner(gl);
+ nr_skipped++;
+ list_add(&gl->gl_lru, &skipped);
}
+ list_splice(&skipped, &lru_list);
+ atomic_add(nr_skipped, &lru_count);
+ spin_unlock(&lru_lock);
+out:
+ return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
}
+static struct shrinker glock_shrinker = {
+ .shrink = gfs2_shrink_glock_memory,
+ .seeks = DEFAULT_SEEKS,
+};
+
/**
- * scan_glock - look at a glock and see if we can reclaim it
- * @gl: the glock to look at
+ * examine_bucket - Call a function for glock in a hash bucket
+ * @examiner: the function
+ * @sdp: the filesystem
+ * @bucket: the bucket
*
+ * Returns: 1 if the bucket has entries
*/
-static void scan_glock(struct gfs2_glock *gl)
+static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
+ unsigned int hash)
{
- if (gfs2_glmutex_trylock(gl)) {
- if (gl->gl_ops == &gfs2_inode_glops) {
- struct gfs2_inode *ip = gl->gl_object;
- if (ip && !atomic_read(&ip->i_count))
- goto out_schedule;
- }
- if (queue_empty(gl, &gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED &&
- demote_ok(gl))
- goto out_schedule;
+ struct gfs2_glock *gl, *prev = NULL;
+ int has_entries = 0;
+ struct hlist_head *head = &gl_hash_table[hash].hb_list;
- gfs2_glmutex_unlock(gl);
+ read_lock(gl_lock_addr(hash));
+ /* Can't use hlist_for_each_entry - don't want prefetch here */
+ if (hlist_empty(head))
+ goto out;
+ gl = list_entry(head->first, struct gfs2_glock, gl_list);
+ while(1) {
+ if (!sdp || gl->gl_sbd == sdp) {
+ gfs2_glock_hold(gl);
+ read_unlock(gl_lock_addr(hash));
+ if (prev)
+ gfs2_glock_put(prev);
+ prev = gl;
+ examiner(gl);
+ has_entries = 1;
+ read_lock(gl_lock_addr(hash));
+ }
+ if (gl->gl_list.next == NULL)
+ break;
+ gl = list_entry(gl->gl_list.next, struct gfs2_glock, gl_list);
}
-
- gfs2_glock_put(gl);
-
- return;
-
- out_schedule:
- gfs2_glmutex_unlock(gl);
- gfs2_glock_schedule_for_reclaim(gl);
- gfs2_glock_put(gl);
+out:
+ read_unlock(gl_lock_addr(hash));
+ if (prev)
+ gfs2_glock_put(prev);
+ cond_resched();
+ return has_entries;
}
+
/**
- * gfs2_scand_internal - Look for glocks and inodes to toss from memory
- * @sdp: the filesystem
+ * thaw_glock - thaw out a glock which has an unprocessed reply waiting
+ * @gl: The glock to thaw
*
+ * N.B. When we freeze a glock, we leave a ref to the glock outstanding,
+ * so this has to result in the ref count being dropped by one.
*/
-void gfs2_scand_internal(struct gfs2_sbd *sdp)
+static void thaw_glock(struct gfs2_glock *gl)
{
- unsigned int x;
-
- for (x = 0; x < GFS2_GL_HASH_SIZE; x++) {
- examine_bucket(scan_glock, sdp, &sdp->sd_gl_hash[x]);
- cond_resched();
- }
+ if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+ return;
+ set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+ gfs2_glock_hold(gl);
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put(gl);
}
/**
static void clear_glock(struct gfs2_glock *gl)
{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- int released;
-
- spin_lock(&sdp->sd_reclaim_lock);
- if (!list_empty(&gl->gl_reclaim)) {
- list_del_init(&gl->gl_reclaim);
- atomic_dec(&sdp->sd_reclaim_count);
- spin_unlock(&sdp->sd_reclaim_lock);
- released = gfs2_glock_put(gl);
- gfs2_assert(sdp, !released);
- } else {
- spin_unlock(&sdp->sd_reclaim_lock);
+ spin_lock(&lru_lock);
+ if (!list_empty(&gl->gl_lru)) {
+ list_del_init(&gl->gl_lru);
+ atomic_dec(&lru_count);
}
+ spin_unlock(&lru_lock);
- if (gfs2_glmutex_trylock(gl)) {
- if (gl->gl_ops == &gfs2_inode_glops) {
- struct gfs2_inode *ip = gl->gl_object;
- if (ip && !atomic_read(&ip->i_count))
- gfs2_inode_destroy(ip, 1);
- }
- if (queue_empty(gl, &gl->gl_holders) &&
- gl->gl_state != LM_ST_UNLOCKED)
- handle_callback(gl, LM_ST_UNLOCKED);
+ spin_lock(&gl->gl_spin);
+ if (find_first_holder(gl) == NULL && gl->gl_state != LM_ST_UNLOCKED)
+ handle_callback(gl, LM_ST_UNLOCKED, 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);
+}
- gfs2_glmutex_unlock(gl);
- }
+/**
+ * gfs2_glock_thaw - Thaw any frozen glocks
+ * @sdp: The super block
+ *
+ */
- gfs2_glock_put(gl);
+void gfs2_glock_thaw(struct gfs2_sbd *sdp)
+{
+ unsigned x;
+
+ for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+ examine_bucket(thaw_glock, sdp, x);
}
/**
* @sdp: the filesystem
* @wait: wait until it's all gone
*
- * Called when unmounting the filesystem, or when inter-node lock manager
- * requests DROPLOCKS because it is running out of capacity.
+ * Called when unmounting the filesystem.
*/
-void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
+void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
{
unsigned long t;
unsigned int x;
for (;;) {
cont = 0;
-
- for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
- if (examine_bucket(clear_glock, sdp,
- &sdp->sd_gl_hash[x]))
+ for (x = 0; x < GFS2_GL_HASH_SIZE; x++) {
+ if (examine_bucket(clear_glock, sdp, x))
cont = 1;
+ }
- if (!wait || !cont)
+ if (!cont)
break;
if (time_after_eq(jiffies,
t = jiffies;
}
- /* invalidate_inodes() requires that the sb inodes list
- not change, but an async completion callback for an
- unlock can occur which does glock_put() which
- can call iput() which will change the sb inodes list.
- invalidate_inodes_mutex prevents glock_put()'s during
- an invalidate_inodes() */
-
- mutex_lock(&sdp->sd_invalidate_inodes_mutex);
+ down_write(&gfs2_umount_flush_sem);
invalidate_inodes(sdp->sd_vfs);
- mutex_unlock(&sdp->sd_invalidate_inodes_mutex);
- yield();
+ up_write(&gfs2_umount_flush_sem);
+ msleep(10);
}
}
-/*
- * Diagnostic routines to help debug distributed deadlock
- */
+void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
+{
+ struct gfs2_glock *gl = ip->i_gl;
+ int ret;
-/**
- * dump_holder - print information about a glock holder
- * @str: a string naming the type of holder
- * @gh: the glock holder
- *
- * Returns: 0 on success, -ENOBUFS when we run out of space
- */
+ ret = gfs2_truncatei_resume(ip);
+ gfs2_assert_withdraw(gl->gl_sbd, ret == 0);
-static int dump_holder(char *str, struct gfs2_holder *gh)
-{
- unsigned int x;
- int error = -ENOBUFS;
-
- printk(KERN_INFO " %s\n", str);
- printk(KERN_INFO " owner = %ld\n",
- (gh->gh_owner) ? (long)gh->gh_owner->pid : -1);
- printk(KERN_INFO " gh_state = %u\n", gh->gh_state);
- printk(KERN_INFO " gh_flags =");
- for (x = 0; x < 32; x++)
- if (gh->gh_flags & (1 << x))
- printk(" %u", x);
- printk(" \n");
- printk(KERN_INFO " error = %d\n", gh->gh_error);
- printk(KERN_INFO " gh_iflags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &gh->gh_iflags))
- printk(" %u", x);
- printk(" \n");
- print_symbol(KERN_INFO " initialized at: %s\n", gh->gh_ip);
-
- error = 0;
+ spin_lock(&gl->gl_spin);
+ clear_bit(GLF_LOCK, &gl->gl_flags);
+ run_queue(gl, 1);
+ spin_unlock(&gl->gl_spin);
+}
- return error;
+static const char *state2str(unsigned state)
+{
+ 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_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_inode - print information about an inode
- * @ip: the inode
+ * dump_holder - print information about a glock holder
+ * @seq: the seq_file struct
+ * @gh: the glock holder
*
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_inode(struct gfs2_inode *ip)
+static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
{
- unsigned int x;
- int error = -ENOBUFS;
-
- printk(KERN_INFO " Inode:\n");
- printk(KERN_INFO " num = %llu %llu\n",
- ip->i_num.no_formal_ino, ip->i_num.no_addr);
- printk(KERN_INFO " type = %u\n", IF2DT(ip->i_di.di_mode));
- printk(KERN_INFO " i_count = %d\n", atomic_read(&ip->i_count));
- printk(KERN_INFO " i_flags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &ip->i_flags))
- printk(" %u", x);
- printk(" \n");
- printk(KERN_INFO " vnode = %s\n", (ip->i_vnode) ? "yes" : "no");
-
- error = 0;
+ struct task_struct *gh_owner = NULL;
+ char buffer[KSYM_SYMBOL_LEN];
+ char flags_buf[32];
- return error;
+ sprint_symbol(buffer, gh->gh_ip);
+ if (gh->gh_owner_pid)
+ gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
+ 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;
+}
+
+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_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';
+ if (test_bit(GLF_INITIAL, gflags))
+ *p++ = 'I';
+ if (test_bit(GLF_FROZEN, gflags))
+ *p++ = 'F';
+ *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 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;
+ 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 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_ail_count),
+ atomic_read(&gl->gl_ref));
- printk(KERN_INFO "Glock (%u, %llu)\n",
- gl->gl_name.ln_type,
- gl->gl_name.ln_number);
- printk(KERN_INFO " gl_flags =");
- for (x = 0; x < 32; x++)
- if (test_bit(x, &gl->gl_flags))
- printk(" %u", x);
- printk(" \n");
- printk(KERN_INFO " gl_ref = %d\n", atomic_read(&gl->gl_ref.refcount));
- printk(KERN_INFO " gl_state = %u\n", gl->gl_state);
- printk(KERN_INFO " req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
- printk(KERN_INFO " req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
- printk(KERN_INFO " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
- printk(KERN_INFO " object = %s\n", (gl->gl_object) ? "yes" : "no");
- printk(KERN_INFO " le = %s\n",
- (list_empty(&gl->gl_le.le_list)) ? "no" : "yes");
- printk(KERN_INFO " reclaim = %s\n",
- (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
- if (gl->gl_aspace)
- printk(KERN_INFO " aspace = %lu\n",
- gl->gl_aspace->i_mapping->nrpages);
- else
- printk(KERN_INFO " aspace = no\n");
- printk(KERN_INFO " ail = %d\n", atomic_read(&gl->gl_ail_count));
- if (gl->gl_req_gh) {
- error = dump_holder("Request", gl->gl_req_gh);
- if (error)
- goto out;
- }
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- error = dump_holder("Holder", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
- error = dump_holder("Waiter1", gh);
+ error = dump_holder(seq, gh);
if (error)
goto out;
}
- list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
- error = dump_holder("Waiter2", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
- error = dump_holder("Waiter3", gh);
- if (error)
- goto out;
- }
- 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(gl->gl_object);
- if (error)
- goto out;
- } else {
- error = -ENOBUFS;
- printk(KERN_INFO " Inode: busy\n");
- }
- }
-
- error = 0;
+ if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump)
+ error = glops->go_dump(seq, gl);
+out:
+ return error;
+}
- out:
+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 error;
+ return ret;
}
/**
static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
{
- struct gfs2_gl_hash_bucket *bucket;
struct gfs2_glock *gl;
+ struct hlist_node *h;
unsigned int x;
int error = 0;
for (x = 0; x < GFS2_GL_HASH_SIZE; x++) {
- bucket = &sdp->sd_gl_hash[x];
- read_lock(&bucket->hb_lock);
+ read_lock(gl_lock_addr(x));
- list_for_each_entry(gl, &bucket->hb_list, gl_list) {
- if (test_bit(GLF_PLUG, &gl->gl_flags))
+ hlist_for_each_entry(gl, h, &gl_hash_table[x].hb_list, gl_list) {
+ if (gl->gl_sbd != sdp)
continue;
- error = dump_glock(gl);
+ error = dump_glock(NULL, gl);
if (error)
break;
}
- read_unlock(&bucket->hb_lock);
+ read_unlock(gl_lock_addr(x));
if (error)
break;
return error;
}
+
+int __init gfs2_glock_init(void)
+{
+ unsigned i;
+ for(i = 0; i < GFS2_GL_HASH_SIZE; i++) {
+ INIT_HLIST_HEAD(&gl_hash_table[i].hb_list);
+ }
+#ifdef GL_HASH_LOCK_SZ
+ for(i = 0; i < GL_HASH_LOCK_SZ; i++) {
+ rwlock_init(&gl_hash_locks[i]);
+ }
+#endif
+
+ glock_workqueue = create_workqueue("glock_workqueue");
+ if (IS_ERR(glock_workqueue))
+ return PTR_ERR(glock_workqueue);
+ gfs2_delete_workqueue = create_workqueue("delete_workqueue");
+ if (IS_ERR(gfs2_delete_workqueue)) {
+ destroy_workqueue(glock_workqueue);
+ return PTR_ERR(gfs2_delete_workqueue);
+ }
+
+ register_shrinker(&glock_shrinker);
+
+ return 0;
+}
+
+void gfs2_glock_exit(void)
+{
+ unregister_shrinker(&glock_shrinker);
+ destroy_workqueue(glock_workqueue);
+ destroy_workqueue(gfs2_delete_workqueue);
+}
+
+static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
+{
+ struct gfs2_glock *gl;
+
+restart:
+ read_lock(gl_lock_addr(gi->hash));
+ gl = gi->gl;
+ if (gl) {
+ gi->gl = hlist_entry(gl->gl_list.next,
+ struct gfs2_glock, gl_list);
+ } else {
+ gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+ struct gfs2_glock, gl_list);
+ }
+ if (gi->gl)
+ gfs2_glock_hold(gi->gl);
+ read_unlock(gl_lock_addr(gi->hash));
+ if (gl)
+ gfs2_glock_put(gl);
+ while (gi->gl == NULL) {
+ gi->hash++;
+ if (gi->hash >= GFS2_GL_HASH_SIZE)
+ return 1;
+ read_lock(gl_lock_addr(gi->hash));
+ gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+ struct gfs2_glock, gl_list);
+ if (gi->gl)
+ gfs2_glock_hold(gi->gl);
+ read_unlock(gl_lock_addr(gi->hash));
+ }
+
+ if (gi->sdp != gi->gl->gl_sbd)
+ goto restart;
+
+ return 0;
+}
+
+static void gfs2_glock_iter_free(struct gfs2_glock_iter *gi)
+{
+ if (gi->gl)
+ gfs2_glock_put(gi->gl);
+ gi->gl = NULL;
+}
+
+static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ struct gfs2_glock_iter *gi = seq->private;
+ loff_t n = *pos;
+
+ gi->hash = 0;
+
+ do {
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+ } while (n--);
+
+ return gi->gl;
+}
+
+static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
+ loff_t *pos)
+{
+ struct gfs2_glock_iter *gi = seq->private;
+
+ (*pos)++;
+
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+
+ return gi->gl;
+}
+
+static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
+{
+ struct gfs2_glock_iter *gi = seq->private;
+ gfs2_glock_iter_free(gi);
+}
+
+static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
+{
+ return dump_glock(seq, iter_ptr);
+}
+
+static const struct seq_operations gfs2_glock_seq_ops = {
+ .start = gfs2_glock_seq_start,
+ .next = gfs2_glock_seq_next,
+ .stop = gfs2_glock_seq_stop,
+ .show = gfs2_glock_seq_show,
+};
+
+static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+{
+ 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 = {
+ .owner = THIS_MODULE,
+ .open = gfs2_debugfs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
+{
+ sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root);
+ if (!sdp->debugfs_dir)
+ return -ENOMEM;
+ sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
+ S_IFREG | S_IRUGO,
+ sdp->debugfs_dir, sdp,
+ &gfs2_debug_fops);
+ if (!sdp->debugfs_dentry_glocks)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
+{
+ if (sdp && sdp->debugfs_dir) {
+ if (sdp->debugfs_dentry_glocks) {
+ debugfs_remove(sdp->debugfs_dentry_glocks);
+ sdp->debugfs_dentry_glocks = NULL;
+ }
+ debugfs_remove(sdp->debugfs_dir);
+ sdp->debugfs_dir = NULL;
+ }
+}
+
+int gfs2_register_debugfs(void)
+{
+ gfs2_root = debugfs_create_dir("gfs2", NULL);
+ return gfs2_root ? 0 : -ENOMEM;
+}
+
+void gfs2_unregister_debugfs(void)
+{
+ debugfs_remove(gfs2_root);
+ gfs2_root = NULL;
+}