summaryrefslogtreecommitdiff
path: root/fs/gfs2
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@woody.linux-foundation.org>2007-05-07 12:26:27 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-05-07 12:26:27 -0700
commit5cefcab3db2b13093480f2a42bf081574dd72d3d (patch)
treec3755a241553436a1b84d65ad3c00f77ce6d02ad /fs/gfs2
parent5f757f91e70a97eda8f0cc13bddc853209b2d173 (diff)
parent37fde8ca6c60ea61f5e9d7cb877c25ac60e74167 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw
* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw: (34 commits) [GFS2] Uncomment sprintf_symbol calling code [DLM] lowcomms style [GFS2] printk warning fixes [GFS2] Patch to fix mmap of stuffed files [GFS2] use lib/parser for parsing mount options [DLM] Lowcomms nodeid range & initialisation fixes [DLM] Fix dlm_lowcoms_stop hang [DLM] fix mode munging [GFS2] lockdump improvements [GFS2] Patch to detect corrupt number of dir entries in leaf and/or inode blocks [GFS2] bz 236008: Kernel gpf doing cat /debugfs/gfs2/xxx (lock dump) [DLM] fs/dlm/ast.c should #include "ast.h" [DLM] Consolidate transport protocols [DLM] Remove redundant assignment [GFS2] Fix bz 234168 (ignoring rgrp flags) [DLM] change lkid format [DLM] interface for purge (2/2) [DLM] add orphan purging code (1/2) [DLM] split create_message function [GFS2] Set drop_count to 0 (off) by default ...
Diffstat (limited to 'fs/gfs2')
-rw-r--r--fs/gfs2/dir.c38
-rw-r--r--fs/gfs2/glock.c619
-rw-r--r--fs/gfs2/glock.h8
-rw-r--r--fs/gfs2/incore.h14
-rw-r--r--fs/gfs2/locking/dlm/lock.c14
-rw-r--r--fs/gfs2/locking/dlm/lock_dlm.h3
-rw-r--r--fs/gfs2/lops.c20
-rw-r--r--fs/gfs2/main.c4
-rw-r--r--fs/gfs2/mount.c239
-rw-r--r--fs/gfs2/ops_address.c21
-rw-r--r--fs/gfs2/ops_fstype.c4
-rw-r--r--fs/gfs2/ops_super.c28
-rw-r--r--fs/gfs2/rgrp.c12
13 files changed, 642 insertions, 382 deletions
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 82a1ac7895a2..a96fa07b3f3b 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1262,9 +1262,10 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
u64 leaf_no)
{
struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
struct gfs2_leaf *lf;
- unsigned entries = 0;
+ unsigned entries = 0, entries2 = 0;
unsigned leaves = 0;
const struct gfs2_dirent **darr, *dent;
struct dirent_gather g;
@@ -1290,7 +1291,13 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
return 0;
error = -ENOMEM;
- larr = vmalloc((leaves + entries) * sizeof(void *));
+ /*
+ * The extra 99 entries are not normally used, but are a buffer
+ * zone in case the number of entries in the leaf is corrupt.
+ * 99 is the maximum number of entries that can fit in a single
+ * leaf block.
+ */
+ larr = vmalloc((leaves + entries + 99) * sizeof(void *));
if (!larr)
goto out;
darr = (const struct gfs2_dirent **)(larr + leaves);
@@ -1305,10 +1312,20 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
lf = (struct gfs2_leaf *)bh->b_data;
lfn = be64_to_cpu(lf->lf_next);
if (lf->lf_entries) {
+ entries2 += be16_to_cpu(lf->lf_entries);
dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
gfs2_dirent_gather, NULL, &g);
error = PTR_ERR(dent);
- if (IS_ERR(dent)) {
+ if (IS_ERR(dent))
+ goto out_kfree;
+ if (entries2 != g.offset) {
+ fs_warn(sdp, "Number of entries corrupt in dir "
+ "leaf %llu, entries2 (%u) != "
+ "g.offset (%u)\n",
+ (unsigned long long)bh->b_blocknr,
+ entries2, g.offset);
+
+ error = -EIO;
goto out_kfree;
}
error = 0;
@@ -1318,6 +1335,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
}
} while(lfn);
+ BUG_ON(entries2 != entries);
error = do_filldir_main(ip, offset, opaque, filldir, darr,
entries, copied);
out_kfree:
@@ -1401,6 +1419,7 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
filldir_t filldir)
{
struct gfs2_inode *dip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
struct dirent_gather g;
const struct gfs2_dirent **darr, *dent;
struct buffer_head *dibh;
@@ -1423,8 +1442,8 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
return error;
error = -ENOMEM;
- darr = kmalloc(dip->i_di.di_entries * sizeof(struct gfs2_dirent *),
- GFP_KERNEL);
+ /* 96 is max number of dirents which can be stuffed into an inode */
+ darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_KERNEL);
if (darr) {
g.pdent = darr;
g.offset = 0;
@@ -1434,6 +1453,15 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
error = PTR_ERR(dent);
goto out;
}
+ if (dip->i_di.di_entries != g.offset) {
+ fs_warn(sdp, "Number of entries corrupt in dir %llu, "
+ "ip->i_di.di_entries (%u) != g.offset (%u)\n",
+ (unsigned long long)dip->i_num.no_addr,
+ dip->i_di.di_entries,
+ g.offset);
+ error = -EIO;
+ goto out;
+ }
error = do_filldir_main(dip, offset, opaque, filldir, darr,
dip->i_di.di_entries, &copied);
out:
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 12accb08fe02..1815429a2978 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -23,6 +23,10 @@
#include <linux/module.h>
#include <linux/rwsem.h>
#include <asm/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
#include "gfs2.h"
#include "incore.h"
@@ -40,20 +44,30 @@ 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 hlist_head *hb_list; /* current hash bucket ptr */
+ 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 gfs2_glock *gl);
-static int dump_inode(struct gfs2_inode *ip);
-static void gfs2_glock_xmote_th(struct gfs2_holder *gh);
+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 DECLARE_RWSEM(gfs2_umount_flush_sem);
+static struct dentry *gfs2_root;
#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 :-)
@@ -202,7 +216,6 @@ int gfs2_glock_put(struct gfs2_glock *gl)
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));
glock_free(gl);
rv = 1;
@@ -303,7 +316,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
atomic_set(&gl->gl_ref, 1);
gl->gl_state = LM_ST_UNLOCKED;
gl->gl_hash = hash;
- gl->gl_owner = NULL;
+ gl->gl_owner_pid = 0;
gl->gl_ip = 0;
gl->gl_ops = glops;
gl->gl_req_gh = NULL;
@@ -367,7 +380,7 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
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_owner_pid = current->pid;
gh->gh_state = state;
gh->gh_flags = flags;
gh->gh_error = 0;
@@ -389,7 +402,7 @@ void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *
{
gh->gh_state = state;
gh->gh_flags = flags;
- gh->gh_iflags &= 1 << HIF_ALLOCED;
+ gh->gh_iflags = 0;
gh->gh_ip = (unsigned long)__builtin_return_address(0);
}
@@ -406,54 +419,8 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
gh->gh_ip = 0;
}
-/**
- * gfs2_holder_get - get a struct gfs2_holder structure
- * @gl: the glock
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gfp_flags:
- *
- * 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)
-{
- 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;
-}
-
-/**
- * gfs2_holder_put - get rid of a struct gfs2_holder structure
- * @gh: the holder structure
- *
- */
-
-static void gfs2_holder_put(struct gfs2_holder *gh)
+static void gfs2_holder_wake(struct gfs2_holder *gh)
{
- gfs2_holder_uninit(gh);
- kfree(gh);
-}
-
-static void gfs2_holder_dispose_or_wake(struct gfs2_holder *gh)
-{
- if (test_bit(HIF_DEALLOC, &gh->gh_iflags)) {
- gfs2_holder_put(gh);
- return;
- }
clear_bit(HIF_WAIT, &gh->gh_iflags);
smp_mb();
wake_up_bit(&gh->gh_iflags, HIF_WAIT);
@@ -519,7 +486,7 @@ static int rq_promote(struct gfs2_holder *gh)
gfs2_reclaim_glock(sdp);
}
- gfs2_glock_xmote_th(gh);
+ gfs2_glock_xmote_th(gh->gh_gl, gh);
spin_lock(&gl->gl_spin);
}
return 1;
@@ -542,7 +509,7 @@ static int rq_promote(struct gfs2_holder *gh)
gh->gh_error = 0;
set_bit(HIF_HOLDER, &gh->gh_iflags);
- gfs2_holder_dispose_or_wake(gh);
+ gfs2_holder_wake(gh);
return 0;
}
@@ -554,32 +521,24 @@ static int rq_promote(struct gfs2_holder *gh)
* Returns: 1 if the queue is blocked
*/
-static int rq_demote(struct gfs2_holder *gh)
+static int rq_demote(struct gfs2_glock *gl)
{
- struct gfs2_glock *gl = gh->gh_gl;
-
if (!list_empty(&gl->gl_holders))
return 1;
- 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);
- gfs2_holder_dispose_or_wake(gh);
- spin_lock(&gl->gl_spin);
- } 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)
- gfs2_glock_drop_th(gl);
- else
- gfs2_glock_xmote_th(gh);
-
- spin_lock(&gl->gl_spin);
+ if (gl->gl_state == gl->gl_demote_state ||
+ gl->gl_state == LM_ST_UNLOCKED) {
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ return 0;
}
+ set_bit(GLF_LOCK, &gl->gl_flags);
+ spin_unlock(&gl->gl_spin);
+ if (gl->gl_demote_state == LM_ST_UNLOCKED ||
+ gl->gl_state != LM_ST_EXCLUSIVE)
+ gfs2_glock_drop_th(gl);
+ else
+ gfs2_glock_xmote_th(gl, NULL);
+ spin_lock(&gl->gl_spin);
return 0;
}
@@ -607,16 +566,8 @@ static void run_queue(struct gfs2_glock *gl)
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
- gfs2_assert_warn(gl->gl_sbd, 0);
-
+ } else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+ blocked = rq_demote(gl);
} else if (!list_empty(&gl->gl_waiters3)) {
gh = list_entry(gl->gl_waiters3.next,
struct gfs2_holder, gh_list);
@@ -654,7 +605,7 @@ static void gfs2_glmutex_lock(struct gfs2_glock *gl)
if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
list_add_tail(&gh.gh_list, &gl->gl_waiters1);
} else {
- gl->gl_owner = current;
+ gl->gl_owner_pid = current->pid;
gl->gl_ip = (unsigned long)__builtin_return_address(0);
clear_bit(HIF_WAIT, &gh.gh_iflags);
smp_mb();
@@ -681,7 +632,7 @@ static int gfs2_glmutex_trylock(struct gfs2_glock *gl)
if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
acquired = 0;
} else {
- gl->gl_owner = current;
+ gl->gl_owner_pid = current->pid;
gl->gl_ip = (unsigned long)__builtin_return_address(0);
}
spin_unlock(&gl->gl_spin);
@@ -699,7 +650,7 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
{
spin_lock(&gl->gl_spin);
clear_bit(GLF_LOCK, &gl->gl_flags);
- gl->gl_owner = NULL;
+ gl->gl_owner_pid = 0;
gl->gl_ip = 0;
run_queue(gl);
BUG_ON(!spin_is_locked(&gl->gl_spin));
@@ -707,50 +658,24 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
}
/**
- * handle_callback - add a demote request to a lock's queue
+ * handle_callback - process a demote request
* @gl: the glock
* @state: the state the caller wants us to change to
*
- * Note: This may fail sliently if we are out of memory.
+ * There are only two requests that we are going to see in actual
+ * practise: LM_ST_SHARED and LM_ST_UNLOCKED
*/
static void handle_callback(struct gfs2_glock *gl, unsigned int state)
{
- struct gfs2_holder *gh, *new_gh = NULL;
-
-restart:
spin_lock(&gl->gl_spin);
-
- 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;
- }
- }
-
- if (new_gh) {
- list_add_tail(&new_gh->gh_list, &gl->gl_waiters2);
- new_gh = NULL;
- } else {
- spin_unlock(&gl->gl_spin);
-
- new_gh = gfs2_holder_get(gl, state, LM_FLAG_TRY, GFP_NOFS);
- if (!new_gh)
- return;
- set_bit(HIF_DEMOTE, &new_gh->gh_iflags);
- set_bit(HIF_DEALLOC, &new_gh->gh_iflags);
- set_bit(HIF_WAIT, &new_gh->gh_iflags);
-
- goto restart;
+ if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) {
+ gl->gl_demote_state = state;
+ gl->gl_demote_time = jiffies;
+ } else if (gl->gl_demote_state != LM_ST_UNLOCKED) {
+ gl->gl_demote_state = state;
}
-
-out:
spin_unlock(&gl->gl_spin);
-
- if (new_gh)
- gfs2_holder_put(new_gh);
}
/**
@@ -810,56 +735,37 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
/* Deal with each possible exit condition */
- if (!gh)
+ if (!gh) {
gl->gl_stamp = jiffies;
- else if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+ if (ret & LM_OUT_CANCELED)
+ op_done = 0;
+ else
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ } else {
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) {
+ if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ goto out;
+ gh->gh_error = GLR_CANCELED;
+ if (ret & LM_OUT_CANCELED)
+ goto out;
+ if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
+ list_add_tail(&gh->gh_list, &gl->gl_holders);
gh->gh_error = 0;
- } 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;
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ set_bit(HIF_FIRST, &gh->gh_iflags);
+ op_done = 0;
+ goto out;
}
- spin_unlock(&gl->gl_spin);
-
- if (ret & LM_OUT_CANCELED)
- handle_callback(gl, LM_ST_UNLOCKED);
-
- } 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 (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+ goto out;
+ gh->gh_error = -EINVAL;
if (gfs2_assert_withdraw(sdp, 0) == -1)
fs_err(sdp, "ret = 0x%.8X\n", ret);
+out:
+ spin_unlock(&gl->gl_spin);
}
if (glops->go_xmote_bh)
@@ -877,7 +783,7 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
gfs2_glock_put(gl);
if (gh)
- gfs2_holder_dispose_or_wake(gh);
+ gfs2_holder_wake(gh);
}
/**
@@ -888,12 +794,11 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
*
*/
-void gfs2_glock_xmote_th(struct gfs2_holder *gh)
+void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = gh->gh_gl;
struct gfs2_sbd *sdp = gl->gl_sbd;
- int flags = gh->gh_flags;
- unsigned state = gh->gh_state;
+ int flags = gh ? gh->gh_flags : 0;
+ unsigned state = gh ? gh->gh_state : gl->gl_demote_state;
const struct gfs2_glock_operations *glops = gl->gl_ops;
int lck_flags = flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB |
LM_FLAG_NOEXP | LM_FLAG_ANY |
@@ -943,6 +848,7 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
gfs2_assert_warn(sdp, !ret);
state_change(gl, LM_ST_UNLOCKED);
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
if (glops->go_inval)
glops->go_inval(gl, DIO_METADATA);
@@ -964,7 +870,7 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
gfs2_glock_put(gl);
if (gh)
- gfs2_holder_dispose_or_wake(gh);
+ gfs2_holder_wake(gh);
}
/**
@@ -1097,18 +1003,32 @@ static int glock_wait_internal(struct gfs2_holder *gh)
}
static inline struct gfs2_holder *
-find_holder_by_owner(struct list_head *head, struct task_struct *owner)
+find_holder_by_owner(struct list_head *head, pid_t pid)
{
struct gfs2_holder *gh;
list_for_each_entry(gh, head, gh_list) {
- if (gh->gh_owner == owner)
+ if (gh->gh_owner_pid == pid)
return gh;
}
return NULL;
}
+static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ if (gi) {
+ vsprintf(gi->string, fmt, args);
+ seq_printf(gi->seq, gi->string);
+ }
+ else
+ vprintk(fmt, args);
+ va_end(args);
+}
+
/**
* add_to_queue - Add a holder to the wait queue (but look for recursion)
* @gh: the holder structure to add
@@ -1120,24 +1040,24 @@ static void add_to_queue(struct gfs2_holder *gh)
struct gfs2_glock *gl = gh->gh_gl;
struct gfs2_holder *existing;
- BUG_ON(!gh->gh_owner);
+ BUG_ON(!gh->gh_owner_pid);
if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
BUG();
- existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner);
+ existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner_pid);
if (existing) {
print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
- printk(KERN_INFO "pid : %d\n", existing->gh_owner->pid);
+ printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
printk(KERN_INFO "lock type : %d lock state : %d\n",
existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state);
print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- printk(KERN_INFO "pid : %d\n", gh->gh_owner->pid);
+ printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
printk(KERN_INFO "lock type : %d lock state : %d\n",
gl->gl_name.ln_type, gl->gl_state);
BUG();
}
- existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner);
+ existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner_pid);
if (existing) {
print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
@@ -1267,9 +1187,8 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
if (glops->go_unlock)
glops->go_unlock(gh);
- gl->gl_stamp = jiffies;
-
spin_lock(&gl->gl_spin);
+ gl->gl_stamp = jiffies;
}
clear_bit(GLF_LOCK, &gl->gl_flags);
@@ -1841,6 +1760,15 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
* Diagnostic routines to help debug distributed deadlock
*/
+static void gfs2_print_symbol(struct glock_iter *gi, const char *fmt,
+ unsigned long address)
+{
+ char buffer[KSYM_SYMBOL_LEN];
+
+ sprint_symbol(buffer, address);
+ print_dbg(gi, fmt, buffer);
+}
+
/**
* dump_holder - print information about a glock holder
* @str: a string naming the type of holder
@@ -1849,31 +1777,37 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait)
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_holder(char *str, struct gfs2_holder *gh)
+static int dump_holder(struct glock_iter *gi, 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 =");
+ struct task_struct *gh_owner;
+
+ print_dbg(gi, " %s\n", str);
+ if (gh->gh_owner_pid) {
+ print_dbg(gi, " owner = %ld ", (long)gh->gh_owner_pid);
+ gh_owner = find_task_by_pid(gh->gh_owner_pid);
+ if (gh_owner)
+ print_dbg(gi, "(%s)\n", gh_owner->comm);
+ else
+ print_dbg(gi, "(ended)\n");
+ } else
+ print_dbg(gi, " owner = -1\n");
+ print_dbg(gi, " gh_state = %u\n", gh->gh_state);
+ print_dbg(gi, " gh_flags =");
for (x = 0; x < 32; x++)
if (gh->gh_flags & (1 << x))
- printk(" %u", x);
- printk(" \n");
- printk(KERN_INFO " error = %d\n", gh->gh_error);
- printk(KERN_INFO " gh_iflags =");
+ print_dbg(gi, " %u", x);
+ print_dbg(gi, " \n");
+ print_dbg(gi, " error = %d\n", gh->gh_error);
+ print_dbg(gi, " gh_iflags =");
for (x = 0; x < 32; x++)
if (test_bit(x, &gh->gh_iflags))
- printk(" %u", x);
- printk(" \n");
- print_symbol(KERN_INFO " initialized at: %s\n", gh->gh_ip);
-
- error = 0;
+ print_dbg(gi, " %u", x);
+ print_dbg(gi, " \n");
+ gfs2_print_symbol(gi, " initialized at: %s\n", gh->gh_ip);
- return error;
+ return 0;
}
/**
@@ -1883,25 +1817,20 @@ static int dump_holder(char *str, struct gfs2_holder *gh)
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_inode(struct gfs2_inode *ip)
+static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip)
{
unsigned int x;
- int error = -ENOBUFS;
- printk(KERN_INFO " Inode:\n");
- printk(KERN_INFO " num = %llu %llu\n",
- (unsigned long long)ip->i_num.no_formal_ino,
- (unsigned long long)ip->i_num.no_addr);
- printk(KERN_INFO " type = %u\n", IF2DT(ip->i_inode.i_mode));
- printk(KERN_INFO " i_flags =");
+ print_dbg(gi, " Inode:\n");
+ print_dbg(gi, " num = %llu/%llu\n",
+ ip->i_num.no_formal_ino, ip->i_num.no_addr);
+ print_dbg(gi, " type = %u\n", IF2DT(ip->i_inode.i_mode));
+ print_dbg(gi, " i_flags =");
for (x = 0; x < 32; x++)
if (test_bit(x, &ip->i_flags))
- printk(" %u", x);
- printk(" \n");
-
- error = 0;
-
- return error;
+ print_dbg(gi, " %u", x);
+ print_dbg(gi, " \n");
+ return 0;
}
/**
@@ -1912,74 +1841,86 @@ static int dump_inode(struct gfs2_inode *ip)
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_glock(struct gfs2_glock *gl)
+static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
{
struct gfs2_holder *gh;
unsigned int x;
int error = -ENOBUFS;
+ struct task_struct *gl_owner;
spin_lock(&gl->gl_spin);
- printk(KERN_INFO "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
- (unsigned long long)gl->gl_name.ln_number);
- printk(KERN_INFO " gl_flags =");
+ print_dbg(gi, "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
+ (unsigned long long)gl->gl_name.ln_number);
+ print_dbg(gi, " gl_flags =");
for (x = 0; x < 32; x++) {
if (test_bit(x, &gl->gl_flags))
- printk(" %u", x);
+ print_dbg(gi, " %u", x);
}
- printk(" \n");
- printk(KERN_INFO " gl_ref = %d\n", atomic_read(&gl->gl_ref));
- printk(KERN_INFO " gl_state = %u\n", gl->gl_state);
- printk(KERN_INFO " gl_owner = %s\n", gl->gl_owner->comm);
- print_symbol(KERN_INFO " gl_ip = %s\n", gl->gl_ip);
- 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",
+ if (!test_bit(GLF_LOCK, &gl->gl_flags))
+ print_dbg(gi, " (unlocked)");
+ print_dbg(gi, " \n");
+ print_dbg(gi, " gl_ref = %d\n", atomic_read(&gl->gl_ref));
+ print_dbg(gi, " gl_state = %u\n", gl->gl_state);
+ if (gl->gl_owner_pid) {
+ gl_owner = find_task_by_pid(gl->gl_owner_pid);
+ if (gl_owner)
+ print_dbg(gi, " gl_owner = pid %d (%s)\n",
+ gl->gl_owner_pid, gl_owner->comm);
+ else
+ print_dbg(gi, " gl_owner = %d (ended)\n",
+ gl->gl_owner_pid);
+ } else
+ print_dbg(gi, " gl_owner = -1\n");
+ print_dbg(gi, " gl_ip = %lu\n", gl->gl_ip);
+ print_dbg(gi, " req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
+ print_dbg(gi, " req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
+ print_dbg(gi, " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
+ print_dbg(gi, " object = %s\n", (gl->gl_object) ? "yes" : "no");
+ print_dbg(gi, " 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");
+ print_dbg(gi, " reclaim = %s\n",
+ (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
if (gl->gl_aspace)
- printk(KERN_INFO " aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
- gl->gl_aspace->i_mapping->nrpages);
+ print_dbg(gi, " aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
+ 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));
+ print_dbg(gi, " aspace = no\n");
+ print_dbg(gi, " ail = %d\n", atomic_read(&gl->gl_ail_count));
if (gl->gl_req_gh) {
- error = dump_holder("Request", gl->gl_req_gh);
+ error = dump_holder(gi, "Request", gl->gl_req_gh);
if (error)
goto out;
}
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- error = dump_holder("Holder", gh);
+ error = dump_holder(gi, "Holder", gh);
if (error)
goto out;
}
list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
- error = dump_holder("Waiter1", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
- error = dump_holder("Waiter2", gh);
+ error = dump_holder(gi, "Waiter1", gh);
if (error)
goto out;
}
list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
- error = dump_holder("Waiter3", gh);
+ error = dump_holder(gi, "Waiter3", gh);
if (error)
goto out;
}
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+ print_dbg(gi, " Demotion req to state %u (%llu uS ago)\n",
+ gl->gl_demote_state,
+ (u64)(jiffies - gl->gl_demote_time)*(1000000/HZ));
+ }
if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) {
if (!test_bit(GLF_LOCK, &gl->gl_flags) &&
- list_empty(&gl->gl_holders)) {
- error = dump_inode(gl->gl_object);
+ list_empty(&gl->gl_holders)) {
+ error = dump_inode(gi, gl->gl_object);
if (error)
goto out;
} else {
error = -ENOBUFS;
- printk(KERN_INFO " Inode: busy\n");
+ print_dbg(gi, " Inode: busy\n");
}
}
@@ -2014,7 +1955,7 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
if (gl->gl_sbd != sdp)
continue;
- error = dump_glock(gl);
+ error = dump_glock(NULL, gl);
if (error)
break;
}
@@ -2043,3 +1984,189 @@ int __init gfs2_glock_init(void)
return 0;
}
+static int gfs2_glock_iter_next(struct glock_iter *gi)
+{
+ read_lock(gl_lock_addr(gi->hash));
+ while (1) {
+ if (!gi->hb_list) { /* If we don't have a hash bucket yet */
+ gi->hb_list = &gl_hash_table[gi->hash].hb_list;
+ if (hlist_empty(gi->hb_list)) {
+ read_unlock(gl_lock_addr(gi->hash));
+ gi->hash++;
+ read_lock(gl_lock_addr(gi->hash));
+ gi->hb_list = NULL;
+ if (gi->hash >= GFS2_GL_HASH_SIZE) {
+ read_unlock(gl_lock_addr(gi->hash));
+ return 1;
+ }
+ else
+ continue;
+ }
+ if (!hlist_empty(gi->hb_list)) {
+ gi->gl = list_entry(gi->hb_list->first,
+ struct gfs2_glock,
+ gl_list);
+ }
+ } else {
+ if (gi->gl->gl_list.next == NULL) {
+ read_unlock(gl_lock_addr(gi->hash));
+ gi->hash++;
+ read_lock(gl_lock_addr(gi->hash));
+ gi->hb_list = NULL;
+ continue;
+ }
+ gi->gl = list_entry(gi->gl->gl_list.next,
+ struct gfs2_glock, gl_list);
+ }
+ if (gi->gl)
+ break;
+ }
+ read_unlock(gl_lock_addr(gi->hash));
+ return 0;
+}
+
+static void gfs2_glock_iter_free(struct glock_iter *gi)
+{
+ kfree(gi);
+}
+
+static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
+{
+ struct glock_iter *gi;
+
+ gi = kmalloc(sizeof (*gi), GFP_KERNEL);
+ if (!gi)
+ return NULL;
+
+ gi->sdp = sdp;
+ gi->hash = 0;
+ gi->gl = NULL;
+ gi->hb_list = NULL;
+ gi->seq = NULL;
+ memset(gi->string, 0, sizeof(gi->string));
+
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+
+ return gi;
+}
+
+static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
+{
+ struct glock_iter *gi;
+ loff_t n = *pos;
+
+ gi = gfs2_glock_iter_init(file->private);
+ if (!gi)
+ return NULL;
+
+ while (n--) {
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+ }
+
+ return gi;
+}
+
+static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
+ loff_t *pos)
+{
+ struct glock_iter *gi = iter_ptr;
+
+ (*pos)++;
+
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+
+ return gi;
+}
+
+static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
+{
+ /* nothing for now */
+}
+
+static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
+{
+ struct glock_iter *gi = iter_ptr;
+
+ gi->seq = file;
+ dump_glock(gi, gi->gl);
+
+ return 0;
+}
+
+static 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)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &gfs2_glock_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private;
+
+ return 0;
+}
+
+static const struct file_operations gfs2_debug_fops = {
+ .owner = THIS_MODULE,
+ .open = gfs2_debugfs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release
+};
+
+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;
+}
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index f50e40ceca43..11477ca3a3c0 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -38,7 +38,7 @@ static inline int gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
/* Look in glock's list of holders for one with current task as owner */
spin_lock(&gl->gl_spin);
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- if (gh->gh_owner == current) {
+ if (gh->gh_owner_pid == current->pid) {
locked = 1;
break;
}
@@ -67,7 +67,7 @@ static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
{
int ret;
spin_lock(&gl->gl_spin);
- ret = !list_empty(&gl->gl_waiters2) || !list_empty(&gl->gl_waiters3);
+ ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
spin_unlock(&gl->gl_spin);
return ret;
}
@@ -135,5 +135,9 @@ void gfs2_scand_internal(struct gfs2_sbd *sdp);
void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
int __init gfs2_glock_init(void);
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
+int gfs2_register_debugfs(void);
+void gfs2_unregister_debugfs(void);
#endif /* __GLOCK_DOT_H__ */
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 49f0dbf40d86..d995441373ab 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -115,11 +115,8 @@ enum {
/* Actions */
HIF_MUTEX = 0,
HIF_PROMOTE = 1,
- HIF_DEMOTE = 2,
/* States */
- HIF_ALLOCED = 4,
- HIF_DEALLOC = 5,
HIF_HOLDER = 6,
HIF_FIRST = 7,
HIF_ABORTED = 9,
@@ -130,7 +127,7 @@ struct gfs2_holder {
struct list_head gh_list;
struct gfs2_glock *gh_gl;
- struct task_struct *gh_owner;
+ pid_t gh_owner_pid;
unsigned int gh_state;
unsigned gh_flags;
@@ -142,8 +139,8 @@ struct gfs2_holder {
enum {
GLF_LOCK = 1,
GLF_STICKY = 2,
+ GLF_DEMOTE = 3,
GLF_DIRTY = 5,
- GLF_SKIP_WAITERS2 = 6,
};
struct gfs2_glock {
@@ -156,11 +153,12 @@ struct gfs2_glock {
unsigned int gl_state;
unsigned int gl_hash;
- struct task_struct *gl_owner;
+ unsigned int gl_demote_state; /* state requested by remote node */
+ unsigned long gl_demote_time; /* time of first demote request */
+ pid_t gl_owner_pid;
unsigned long gl_ip;
struct list_head gl_holders;
struct list_head gl_waiters1; /* HIF_MUTEX */
- struct list_head gl_waiters2; /* HIF_DEMOTE */
struct list_head gl_waiters3; /* HIF_PROMOTE */
const struct gfs2_glock_operations *gl_ops;
@@ -611,6 +609,8 @@ struct gfs2_sbd {
unsigned long sd_last_warning;
struct vfsmount *sd_gfs2mnt;
+ struct dentry *debugfs_dir; /* debugfs directory */
+ struct dentry *debugfs_dentry_glocks; /* for debugfs */
};
#endif /* __INCORE_DOT_H__ */
diff --git a/fs/gfs2/locking/dlm/lock.c b/fs/gfs2/locking/dlm/lock.c
index b167addf9fd1..c305255bfe8a 100644
--- a/fs/gfs2/locking/dlm/lock.c
+++ b/fs/gfs2/locking/dlm/lock.c
@@ -151,7 +151,7 @@ static inline unsigned int make_flags(struct gdlm_lock *lp,
/* make_strname - convert GFS lock numbers to a string */
-static inline void make_strname(struct lm_lockname *lockname,
+static inline void make_strname(const struct lm_lockname *lockname,
struct gdlm_strname *str)
{
sprintf(str->name, "%8x%16llx", lockname->ln_type,
@@ -169,6 +169,7 @@ static int gdlm_create_lp(struct gdlm_ls *ls, struct lm_lockname *name,
return -ENOMEM;
lp->lockname = *name;
+ make_strname(name, &lp->strname);
lp->ls = ls;
lp->cur = DLM_LOCK_IV;
lp->lvb = NULL;
@@ -227,7 +228,6 @@ void gdlm_put_lock(void *lock)
unsigned int gdlm_do_lock(struct gdlm_lock *lp)
{
struct gdlm_ls *ls = lp->ls;
- struct gdlm_strname str;
int error, bast = 1;
/*
@@ -249,8 +249,6 @@ unsigned int gdlm_do_lock(struct gdlm_lock *lp)
if (test_bit(LFL_NOBAST, &lp->flags))
bast = 0;
- make_strname(&lp->lockname, &str);
-
set_bit(LFL_ACTIVE, &lp->flags);
log_debug("lk %x,%llx id %x %d,%d %x", lp->lockname.ln_type,
@@ -258,8 +256,8 @@ unsigned int gdlm_do_lock(struct gdlm_lock *lp)
lp->cur, lp->req, lp->lkf);
error = dlm_lock(ls->dlm_lockspace, lp->req, &lp->lksb, lp->lkf,
- str.name, str.namelen, 0, gdlm_ast, lp,
- bast ? gdlm_bast : NULL);
+ lp->strname.name, lp->strname.namelen, 0, gdlm_ast,
+ lp, bast ? gdlm_bast : NULL);
if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) {
lp->lksb.sb_status = -EAGAIN;
@@ -268,7 +266,7 @@ unsigned int gdlm_do_lock(struct gdlm_lock *lp)
}
if (error) {
- log_debug("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
+ log_error("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
"flags=%lx", ls->fsname, lp->lockname.ln_type,
(unsigned long long)lp->lockname.ln_number, error,
lp->cur, lp->req, lp->lkf, lp->flags);
@@ -296,7 +294,7 @@ static unsigned int gdlm_do_unlock(struct gdlm_lock *lp)
error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, lkf, NULL, lp);
if (error) {
- log_debug("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x "
+ log_error("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x "
"flags=%lx", ls->fsname, lp->lockname.ln_type,
(unsigned long long)lp->lockname.ln_number, error,
lp->cur, lp->req, lp->lkf, lp->flags);
diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h
index a87c7bf3c568..d074c6e6f9bf 100644
--- a/fs/gfs2/locking/dlm/lock_dlm.h
+++ b/fs/gfs2/locking/dlm/lock_dlm.h
@@ -36,7 +36,7 @@
#define GDLM_STRNAME_BYTES 24
#define GDLM_LVB_SIZE 32
-#define GDLM_DROP_COUNT 200000
+#define GDLM_DROP_COUNT 0
#define GDLM_DROP_PERIOD 60
#define GDLM_NAME_LEN 128
@@ -106,6 +106,7 @@ enum {
struct gdlm_lock {
struct gdlm_ls *ls;
struct lm_lockname lockname;
+ struct gdlm_strname strname;
char *lvb;
struct dlm_lksb lksb;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 16bb4b4561ae..f82d84d05d23 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -33,16 +33,17 @@ static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
tr->tr_touched = 1;
- if (!list_empty(&le->le_list))
- return;
-
gl = container_of(le, struct gfs2_glock, gl_le);
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
return;
- gfs2_glock_hold(gl);
- set_bit(GLF_DIRTY, &gl->gl_flags);
gfs2_log_lock(sdp);
+ if (!list_empty(&le->le_list)){
+ gfs2_log_unlock(sdp);
+ return;
+ }
+ gfs2_glock_hold(gl);
+ set_bit(GLF_DIRTY, &gl->gl_flags);
sdp->sd_log_num_gl++;
list_add(&le->le_list, &sdp->sd_log_le_gl);
gfs2_log_unlock(sdp);
@@ -415,13 +416,14 @@ static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
tr->tr_touched = 1;
- if (!list_empty(&le->le_list))
- return;
-
rgd = container_of(le, struct gfs2_rgrpd, rd_le);
- gfs2_rgrp_bh_hold(rgd);
gfs2_log_lock(sdp);
+ if (!list_empty(&le->le_list)){
+ gfs2_log_unlock(sdp);
+ return;
+ }
+ gfs2_rgrp_bh_hold(rgd);
sdp->sd_log_num_rg++;
list_add(&le->le_list, &sdp->sd_log_le_rg);
gfs2_log_unlock(sdp);
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index e2bffae683cc..e460487c0557 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -43,7 +43,6 @@ static void gfs2_init_glock_once(void *foo, struct kmem_cache *cachep, unsigned
spin_lock_init(&gl->gl_spin);
INIT_LIST_HEAD(&gl->gl_holders);
INIT_LIST_HEAD(&gl->gl_waiters1);
- INIT_LIST_HEAD(&gl->gl_waiters2);
INIT_LIST_HEAD(&gl->gl_waiters3);
gl->gl_lvb = NULL;
atomic_set(&gl->gl_lvb_count, 0);
@@ -101,6 +100,8 @@ static int __init init_gfs2_fs(void)
if (error)
goto fail_unregister;
+ gfs2_register_debugfs();
+
printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
return 0;
@@ -128,6 +129,7 @@ fail:
static void __exit exit_gfs2_fs(void)
{
+ gfs2_unregister_debugfs();
unregister_filesystem(&gfs2_fs_type);
unregister_filesystem(&gfs2meta_fs_type);
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index 32caecd20300..4864659555d4 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -13,6 +13,7 @@
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>
+#include <linux/parser.h>
#include "gfs2.h"
#include "incore.h"
@@ -20,6 +21,52 @@
#include "sys.h"
#include "util.h"
+enum {
+ Opt_lockproto,
+ Opt_locktable,
+ Opt_hostdata,
+ Opt_spectator,
+ Opt_ignore_local_fs,
+ Opt_localflocks,
+ Opt_localcaching,
+ Opt_debug,
+ Opt_nodebug,
+ Opt_upgrade,
+ Opt_num_glockd,
+ Opt_acl,
+ Opt_noacl,
+ Opt_quota_off,
+ Opt_quota_account,
+ Opt_quota_on,
+ Opt_suiddir,
+ Opt_nosuiddir,
+ Opt_data_writeback,
+ Opt_data_ordered,
+};
+
+static match_table_t tokens = {
+ {Opt_lockproto, "lockproto=%s"},
+ {Opt_locktable, "locktable=%s"},
+ {Opt_hostdata, "hostdata=%s"},
+ {Opt_spectator, "spectator"},
+ {Opt_ignore_local_fs, "ignore_local_fs"},
+ {Opt_localflocks, "localflocks"},
+ {Opt_localcaching, "localcaching"},
+ {Opt_debug, "debug"},
+ {Opt_nodebug, "nodebug"},
+ {Opt_upgrade, "upgrade"},
+ {Opt_num_glockd, "num_glockd=%d"},
+ {Opt_acl, "acl"},
+ {Opt_noacl, "noacl"},
+ {Opt_quota_off, "quota=off"},
+ {Opt_quota_account, "quota=account"},
+ {Opt_quota_on, "quota=on"},
+ {Opt_suiddir, "suiddir"},
+ {Opt_nosuiddir, "nosuiddir"},
+ {Opt_data_writeback, "data=writeback"},
+ {Opt_data_ordered, "data=ordered"}
+};
+
/**
* gfs2_mount_args - Parse mount options
* @sdp:
@@ -54,146 +101,150 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
process them */
for (options = data; (o = strsep(&options, ",")); ) {
+ int token, option;
+ substring_t tmp[MAX_OPT_ARGS];
+
if (!*o)
continue;
- v = strchr(o, '=');
- if (v)
- *v++ = 0;
+ token = match_token(o, tokens, tmp);
+ switch (token) {
+ case Opt_lockproto:
+ v = match_strdup(&tmp[0]);
+ if (!v) {
+ fs_info(sdp, "no memory for lockproto\n");
+ error = -ENOMEM;
+ goto out_error;
+ }
- if (!strcmp(o, "lockproto")) {
- if (!v)
- goto need_value;
- if (remount && strcmp(v, args->ar_lockproto))
+ if (remount && strcmp(v, args->ar_lockproto)) {
+ kfree(v);
goto cant_remount;
+ }
+
strncpy(args->ar_lockproto, v, GFS2_LOCKNAME_LEN);
args->ar_lockproto[GFS2_LOCKNAME_LEN - 1] = 0;
- }
+ kfree(v);
+ break;
+ case Opt_locktable:
+ v = match_strdup(&tmp[0]);
+ if (!v) {
+ fs_info(sdp, "no memory for locktable\n");
+ error = -ENOMEM;
+ goto out_error;
+ }
- else if (!strcmp(o, "locktable")) {
- if (!v)
- goto need_value;
- if (remount && strcmp(v, args->ar_locktable))
+ if (remount && strcmp(v, args->ar_locktable)) {
+ kfree(v);
goto cant_remount;
+ }
+
strncpy(args->ar_locktable, v, GFS2_LOCKNAME_LEN);
- args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0;
- }
+ args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0;
+ kfree(v);
+ break;
+ case Opt_hostdata:
+ v = match_strdup(&tmp[0]);
+ if (!v) {
+ fs_info(sdp, "no memory for hostdata\n");
+ error = -ENOMEM;
+ goto out_error;
+ }
- else if (!strcmp(o, "hostdata")) {
- if (!v)
- goto need_value;
- if (remount && strcmp(v, args->ar_hostdata))
+ if (remount && strcmp(v, args->ar_hostdata)) {
+ kfree(v);
goto cant_remount;
+ }
+
strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN);
args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0;
- }
-
- else if (!strcmp(o, "spectator")) {
+ kfree(v);
+ break;
+ case Opt_spectator:
if (remount && !args->ar_spectator)
goto cant_remount;
args->ar_spectator = 1;
sdp->sd_vfs->s_flags |= MS_RDONLY;
- }
-
- else if (!strcmp(o, "ignore_local_fs")) {
+ break;
+ case Opt_ignore_local_fs:
if (remount && !args->ar_ignore_local_fs)
goto cant_remount;
args->ar_ignore_local_fs = 1;
- }
-
- else if (!strcmp(o, "localflocks")) {
+ break;
+ case Opt_localflocks:
if (remount && !args->ar_localflocks)
goto cant_remount;
args->ar_localflocks = 1;
- }
-
- else if (!strcmp(o, "localcaching")) {
+ break;
+ case Opt_localcaching:
if (remount && !args->ar_localcaching)
goto cant_remount;
args->ar_localcaching = 1;
- }
-
- else if (!strcmp(o, "debug"))
+ break;
+ case Opt_debug:
args->ar_debug = 1;
-
- else if (!strcmp(o, "nodebug"))
+ break;
+ case Opt_nodebug:
args->ar_debug = 0;
-
- else if (!strcmp(o, "upgrade")) {
+ break;
+ case Opt_upgrade:
if (remount && !args->ar_upgrade)
goto cant_remount;
args->ar_upgrade = 1;
- }
+ break;
+ case Opt_num_glockd:
+ if ((error = match_int(&tmp[0], &option))) {
+ fs_info(sdp, "problem getting num_glockd\n");
+ goto out_error;
+ }
- else if (!strcmp(o, "num_glockd")) {
- unsigned int x;
- if (!v)
- goto need_value;
- sscanf(v, "%u", &x);
- if (remount && x != args->ar_num_glockd)
+ if (remount && option != args->ar_num_glockd)
goto cant_remount;
- if (!x || x > GFS2_GLOCKD_MAX) {
+ if (!option || option > GFS2_GLOCKD_MAX) {
fs_info(sdp, "0 < num_glockd <= %u (not %u)\n",
- GFS2_GLOCKD_MAX, x);
+ GFS2_GLOCKD_MAX, option);
error = -EINVAL;
- break;
+ goto out_error;
}
- args->ar_num_glockd = x;
- }
-
- else if (!strcmp(o, "acl")) {
+ args->ar_num_glockd = option;
+ break;
+ case Opt_acl:
args->ar_posix_acl = 1;
sdp->sd_vfs->s_flags |= MS_POSIXACL;
- }
-
- else if (!strcmp(o, "noacl")) {
+ break;
+ case Opt_noacl:
args->ar_posix_acl = 0;
sdp->sd_vfs->s_flags &= ~MS_POSIXACL;
- }
-
- else if (!strcmp(o, "quota")) {
- if (!v)
- goto need_value;
- if (!strcmp(v, "off"))
- args->ar_quota = GFS2_QUOTA_OFF;
- else if (!strcmp(v, "account"))
- args->ar_quota = GFS2_QUOTA_ACCOUNT;
- else if (!strcmp(v, "on"))
- args->ar_quota = GFS2_QUOTA_ON;
- else {
- fs_info(sdp, "invalid value for quota\n");
- error = -EINVAL;
- break;
- }
- }
-
- else if (!strcmp(o, "suiddir"))
+ break;
+ case Opt_quota_off:
+ args->ar_quota = GFS2_QUOTA_OFF;
+ break;
+ case Opt_quota_account:
+ args->ar_quota = GFS2_QUOTA_ACCOUNT;
+ break;
+ case Opt_quota_on:
+ args->ar_quota = GFS2_QUOTA_ON;
+ break;
+ case Opt_suiddir:
args->ar_suiddir = 1;
-
- else if (!strcmp(o, "nosuiddir"))
+ break;
+ case Opt_nosuiddir:
args->ar_suiddir = 0;
-
- else if (!strcmp(o, "data")) {
- if (!v)
- goto need_value;
- if (!strcmp(v, "writeback"))
- args->ar_data = GFS2_DATA_WRITEBACK;
- else if (!strcmp(v, "ordered"))
- args->ar_data = GFS2_DATA_ORDERED;
- else {
- fs_info(sdp, "invalid value for data\n");
- error = -EINVAL;
- break;
- }
- }
-
- else {
+ break;
+ case Opt_data_writeback:
+ args->ar_data = GFS2_DATA_WRITEBACK;
+ break;
+ case Opt_data_ordered:
+ args->ar_data = GFS2_DATA_ORDERED;
+ break;
+ default:
fs_info(sdp, "unknown option: %s\n", o);
error = -EINVAL;
- break;
+ goto out_error;
}
}
+out_error:
if (error)
fs_info(sdp, "invalid mount option(s)\n");
@@ -202,10 +253,6 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
return error;
-need_value:
- fs_info(sdp, "need value for option %s\n", o);
- return -EINVAL;
-
cant_remount:
fs_info(sdp, "can't remount with option %s\n", o);
return -EINVAL;
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index b3b7e8475359..30c15622174f 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -197,7 +197,19 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
void *kaddr;
int error;
- BUG_ON(page->index);
+ /*
+ * Due to the order of unstuffing files and ->nopage(), we can be
+ * asked for a zero page in the case of a stuffed file being extended,
+ * so we need to supply one here. It doesn't happen often.
+ */
+ if (unlikely(page->index)) {
+ kaddr = kmap_atomic(page, KM_USER0);
+ memset(kaddr, 0, PAGE_CACHE_SIZE);
+ kunmap_atomic(kaddr, KM_USER0);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ return 0;
+ }
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
@@ -208,9 +220,8 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
ip->i_di.di_size);
memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
kunmap_atomic(kaddr, KM_USER0);
-
+ flush_dcache_page(page);
brelse(dibh);
-
SetPageUptodate(page);
return 0;
@@ -507,7 +518,9 @@ static int gfs2_commit_write(struct file *file, struct page *page,
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
+ unlock_page(page);
gfs2_glock_dq_m(1, &ip->i_gh);
+ lock_page(page);
gfs2_holder_uninit(&ip->i_gh);
return 0;
@@ -520,7 +533,9 @@ fail_endtrans:
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
+ unlock_page(page);
gfs2_glock_dq_m(1, &ip->i_gh);
+ lock_page(page);
gfs2_holder_uninit(&ip->i_gh);
fail_nounlock:
ClearPageUptodate(page);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index ee54cb667083..2c5f8e7def0d 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -690,6 +690,8 @@ static int fill_super(struct super_block *sb, void *data, int silent)
if (error)
goto fail;
+ gfs2_create_debugfs_file(sdp);
+
error = gfs2_sys_fs_add(sdp);
if (error)
goto fail;
@@ -754,6 +756,7 @@ fail_lm:
fail_sys:
gfs2_sys_fs_del(sdp);
fail:
+ gfs2_delete_debugfs_file(sdp);
kfree(sdp);
sb->s_fs_info = NULL;
return error;
@@ -896,6 +899,7 @@ error:
static void gfs2_kill_sb(struct super_block *sb)
{
+ gfs2_delete_debugfs_file(sb->s_fs_info);
kill_block_super(sb);
}
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index b89999d3a767..485ce3d49923 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -284,6 +284,31 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
}
/**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+static void gfs2_drop_inode(struct inode *inode)
+{
+ if (inode->i_private && inode->i_nlink) {
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+ if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+ clear_nlink(inode);
+ }
+ generic_drop_inode(inode);
+}
+
+/**
* gfs2_clear_inode - Deallocate an inode when VFS is done with it
* @inode: The VFS inode
*
@@ -441,7 +466,7 @@ out_unlock:
out_uninit:
gfs2_holder_uninit(&ip->i_iopen_gh);
gfs2_glock_dq_uninit(&gh);
- if (error)
+ if (error && error != GLR_TRYFAILED)
fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
out:
truncate_inode_pages(&inode->i_data, 0);
@@ -481,6 +506,7 @@ const struct super_operations gfs2_super_ops = {
.statfs = gfs2_statfs,
.remount_fs = gfs2_remount_fs,
.clear_inode = gfs2_clear_inode,
+ .drop_inode = gfs2_drop_inode,
.show_options = gfs2_show_options,
};
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 8d9c08b5c4b6..1727f5012efe 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -27,6 +27,7 @@
#include "trans.h"
#include "ops_file.h"
#include "util.h"
+#include "log.h"
#define BFITNOENT ((u32)~0)
@@ -697,8 +698,6 @@ struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
* @al: the struct gfs2_alloc structure describing the reservation
*
* If there's room for the requested blocks to be allocated from the RG:
- * Sets the $al_reserved_data field in @al.
- * Sets the $al_reserved_meta field in @al.
* Sets the $al_rgd field in @al.
*
* Returns: 1 on success (it fits), 0 on failure (it doesn't fit)
@@ -709,6 +708,9 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
struct gfs2_sbd *sdp = rgd->rd_sbd;
int ret = 0;
+ if (rgd->rd_rg.rg_flags & GFS2_RGF_NOALLOC)
+ return 0;
+
spin_lock(&sdp->sd_rindex_spin);
if (rgd->rd_free_clone >= al->al_requested) {
al->al_rgd = rgd;
@@ -941,9 +943,13 @@ static int get_local_rgrp(struct gfs2_inode *ip)
rgd = gfs2_rgrpd_get_first(sdp);
if (rgd == begin) {
- if (++loops >= 2 || !skipped)
+ if (++loops >= 3)
return -ENOSPC;
+ if (!skipped)
+ loops++;
flags = 0;
+ if (loops == 2)
+ gfs2_log_flush(sdp, NULL);
}
}