glock.c

linux 内核源代码

/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 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 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/kallsyms.h>
#include <linux/gfs2_ondisk.h>
#include <linux/list.h>
#include <linux/lm_interface.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 "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"

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             */
};

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 DECLARE_RWSEM(gfs2_umount_flush_sem);
static struct dentry *gfs2_root;
static struct task_struct *scand_process;
static unsigned int scand_secs = 5;
static struct workqueue_struct *glock_workqueue;

#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)

static struct gfs2_gl_hash_bucket gl_hash_table[GFS2_GL_HASH_SIZE];
static struct dentry *gfs2_root;

/*
 * 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

/**
 * 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
 *
 * Returns: The number of the corresponding hash bucket
 */

static unsigned int gl_hash(const struct gfs2_sbd *sdp,
			    const struct lm_lockname *name)
{
	unsigned int h;

	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;
}

/**
 * glock_free() - Perform a few checks and then release struct gfs2_glock
 * @gl: The glock to release
 *
 * Also calls lock module to release its internal structure for this glock.
 *
 */

static void glock_free(struct gfs2_glock *gl)
{
	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);
}

/**
 * gfs2_glock_hold() - increment reference count on glock
 * @gl: The glock to hold
 *
 */

void gfs2_glock_hold(struct gfs2_glock *gl)
{
	atomic_inc(&gl->gl_ref);
}

/**
 * gfs2_glock_put() - Decrement reference count on glock
 * @gl: The glock to put
 *
 */

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));
		BUG_ON(spin_is_locked(&gl->gl_spin));
		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_free(gl);
		rv = 1;
		goto out;
	}
	write_unlock(gl_lock_addr(gl->gl_hash));
out:
	return rv;
}

/**
 * search_bucket() - Find struct gfs2_glock by lock number
 * @bucket: the bucket to search
 * @name: The lock name
 *
 * Returns: NULL, or the struct gfs2_glock with the requested number
 */

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;

	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;

		atomic_inc(&gl->gl_ref);

		return gl;
	}

	return NULL;
}

/**
 * gfs2_glock_find() - Find glock by lock number
 * @sdp: The GFS2 superblock
 * @name: The lock name
 *
 * Returns: NULL, or the struct gfs2_glock with the requested number
 */

static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp,
					  const struct lm_lockname *name)
{
	unsigned int hash = gl_hash(sdp, name);
	struct gfs2_glock *gl;

	read_lock(gl_lock_addr(hash));
	gl = search_bucket(hash, sdp, name);
	read_unlock(gl_lock_addr(hash));

	return gl;
}

static void glock_work_func(struct work_struct *work)
{
	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);

	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);
	spin_unlock(&gl->gl_spin);
	gfs2_glock_put(gl);
}

/**
 * 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
 */

int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
		   const struct gfs2_glock_operations *glops, int create,
		   struct gfs2_glock **glp)
{
	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;

	read_lock(gl_lock_addr(hash));
	gl = search_bucket(hash, sdp, &name);
	read_unlock(gl_lock_addr(hash));

	if (gl || !create) {
		*glp = gl;
		return 0;
	}

	gl = kmem_cache_alloc(gfs2_glock_cachep, GFP_KERNEL);
	if (!gl)
		return -ENOMEM;

	gl->gl_flags = 0;
	gl->gl_name = name;
	atomic_set(&gl->gl_ref, 1);
	gl->gl_state = LM_ST_UNLOCKED;
	gl->gl_demote_state = LM_ST_EXCLUSIVE;
	gl->gl_hash = hash;
	gl->gl_owner_pid = 0;
	gl->gl_ip = 0;
	gl->gl_ops = glops;
	gl->gl_req_gh = NULL;
	gl->gl_req_bh = NULL;
	gl->gl_vn = 0;
	gl->gl_stamp = jiffies;
	gl->gl_tchange = jiffies;
	gl->gl_object = NULL;
	gl->gl_sbd = sdp;
	gl->gl_aspace = NULL;
	lops_init_le(&gl->gl_le, &gfs2_glock_lops);
	INIT_DELAYED_WORK(&gl->gl_work, glock_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;
		}
	}

	error = gfs2_lm_get_lock(sdp, &name, &gl->gl_lock);
	if (error)
		goto fail_aspace;

	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 {
		hlist_add_head(&gl->gl_list, &gl_hash_table[hash].hb_list);
		write_unlock(gl_lock_addr(hash));
	}

	*glp = gl;

	return 0;

fail_aspace:
	if (gl->gl_aspace)
		gfs2_aspace_put(gl->gl_aspace);
fail:
	kmem_cache_free(gfs2_glock_cachep, gl);
	return error;
}

/**
 * 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
 *
 */

void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
		      struct gfs2_holder *gh)
{
	INIT_LIST_HEAD(&gh->gh_list);
	gh->gh_gl = gl;
	gh->gh_ip = (unsigned long)__builtin_return_address(0);
	gh->gh_owner_pid = current->pid;
	gh->gh_state = state;
	gh->gh_flags = flags;
	gh->gh_error = 0;
	gh->gh_iflags = 0;
	gfs2_glock_hold(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)
{
	gh->gh_state = state;
	gh->gh_flags = flags;
	gh->gh_iflags = 0;
	gh->gh_ip = (unsigned long)__builtin_return_address(0);
}

/**
 * gfs2_holder_uninit - uninitialize a holder structure (drop glock reference)
 * @gh: the holder structure
 *
 */

void gfs2_holder_uninit(struct gfs2_holder *gh)
{
	gfs2_glock_put(gh->gh_gl);
	gh->gh_gl = NULL;
	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();
        return 0;
}

static void wait_on_holder(struct gfs2_holder *gh)
{
	might_sleep();
	wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
}

static void gfs2_demote_wake(struct gfs2_glock *gl)
{
	BUG_ON(!spin_is_locked(&gl->gl_spin));
	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();
	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE);
}

/**
 * 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;
	struct gfs2_sbd *sdp = gl->gl_sbd;

	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);
			}

			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;