From 091806edd458486af13ad83c9802f5b8b54d6d19 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Tue, 29 Apr 2008 12:35:48 -0500 Subject: [GFS2] filesystem consistency error from do_strip This patch fixes a GFS2 filesystem consistency error reported from function do_strip. The problem was caused by a timing window that allowed two vfs inodes to be created in memory that point to the same file. The problem is fixed by making the vfs's iget_test, iget_set mechanism check and set a new bit in the in-core gfs2_inode structure while the vfs inode spin_lock is held. Signed-off-by: Bob Peterson Signed-off-by: Steven Whitehouse --- fs/gfs2/ops_super.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'fs/gfs2/ops_super.c') diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 2278c68b7e3..0b7cc920eb8 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 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 @@ -52,7 +52,7 @@ static int gfs2_write_inode(struct inode *inode, int sync) struct gfs2_inode *ip = GFS2_I(inode); /* Check this is a "normal" inode */ - if (inode->i_private) { + if (test_bit(GIF_USER, &ip->i_flags)) { if (current->flags & PF_MEMALLOC) return 0; if (sync) @@ -297,8 +297,9 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) */ static void gfs2_drop_inode(struct inode *inode) { - if (inode->i_private && inode->i_nlink) { - struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_inode *ip = GFS2_I(inode); + + if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) { struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags)) clear_nlink(inode); @@ -314,12 +315,13 @@ static void gfs2_drop_inode(struct inode *inode) static void gfs2_clear_inode(struct inode *inode) { + struct gfs2_inode *ip = GFS2_I(inode); + /* This tells us its a "real" inode and not one which only * serves to contain an address space (see rgrp.c, meta_io.c) * which therefore doesn't have its own glocks. */ - if (inode->i_private) { - struct gfs2_inode *ip = GFS2_I(inode); + if (test_bit(GIF_USER, &ip->i_flags)) { ip->i_gl->gl_object = NULL; gfs2_glock_schedule_for_reclaim(ip->i_gl); gfs2_glock_put(ip->i_gl); @@ -419,7 +421,7 @@ static void gfs2_delete_inode(struct inode *inode) struct gfs2_holder gh; int error; - if (!inode->i_private) + if (!test_bit(GIF_USER, &ip->i_flags)) goto out; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); -- cgit v1.2.3-70-g09d2 From 9171f5a991e7613cbee816874ad8c9515dcab50f Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Mon, 9 Jun 2008 12:08:23 -0500 Subject: [GFS2] kernel panic mounting volume This patch fixes Red Hat bugzilla bug 450156. This started with a not-too-improbable mount failure because the locking protocol was never set back to its proper "lock_dlm" after the system was rebooted in the middle of a gfs2_fsck. That left a (purposely) invalid locking protocol in the superblock, which caused an error when the file system was mounted the next time. When there's an error mounting, vfs calls DQUOT_OFF, which calls vfs_quota_off which calls gfs2_sync_fs. Next, gfs2_sync_fs calls gfs2_log_flush passing s_fs_info. But due to the error, s_fs_info had been previously set to NULL, and so we have the kernel oops. My solution in this patch is to test for the NULL value before passing it. I tested this patch and it fixes the problem. Signed-off-by: Bob Peterson Signed-off-by: Steven Whitehouse --- fs/gfs2/ops_super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/gfs2/ops_super.c') diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 0b7cc920eb8..66907922109 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -155,7 +155,7 @@ static void gfs2_write_super(struct super_block *sb) static int gfs2_sync_fs(struct super_block *sb, int wait) { sb->s_dirt = 0; - if (wait) + if (wait && sb->s_fs_info) gfs2_log_flush(sb->s_fs_info, NULL); return 0; } -- cgit v1.2.3-70-g09d2 From 1bdad606338debc6384b2844f1b53cc436b3ac90 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 3 Jun 2008 14:09:53 +0100 Subject: [GFS2] Remove remote lock dropping code There are several reasons why this is undesirable: 1. It never happens during normal operation anyway 2. If it does happen it causes performance to be very, very poor 3. It isn't likely to solve the original problem (memory shortage on remote DLM node) it was supposed to solve 4. It uses a bunch of arbitrary constants which are unlikely to be correct for any particular situation and for which the tuning seems to be a black art. 5. In an N node cluster, only 1/N of the dropped locked will actually contribute to solving the problem on average. So all in all we are better off without it. This also makes merging the lock_dlm module into GFS2 a bit easier. Signed-off-by: Steven Whitehouse --- fs/gfs2/gfs2.h | 5 ----- fs/gfs2/glock.c | 12 +++--------- fs/gfs2/glock.h | 2 +- fs/gfs2/locking/dlm/lock_dlm.h | 3 --- fs/gfs2/locking/dlm/mount.c | 3 --- fs/gfs2/locking/dlm/sysfs.c | 13 ------------- fs/gfs2/locking/dlm/thread.c | 19 ------------------- fs/gfs2/ops_fstype.c | 2 +- fs/gfs2/ops_super.c | 2 +- fs/gfs2/sys.c | 14 -------------- include/linux/lm_interface.h | 4 ---- 11 files changed, 6 insertions(+), 73 deletions(-) (limited to 'fs/gfs2/ops_super.c') diff --git a/fs/gfs2/gfs2.h b/fs/gfs2/gfs2.h index 3bb11c0f8b5..ef606e3a5cf 100644 --- a/fs/gfs2/gfs2.h +++ b/fs/gfs2/gfs2.h @@ -15,11 +15,6 @@ enum { CREATE = 1, }; -enum { - NO_WAIT = 0, - WAIT = 1, -}; - enum { NO_FORCE = 0, FORCE = 1, diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index be7ed503f01..8d5450f3c3e 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1316,11 +1316,6 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data) 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; @@ -1508,11 +1503,10 @@ static void clear_glock(struct gfs2_glock *gl) * @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; @@ -1527,7 +1521,7 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait) cont = 1; } - if (!wait || !cont) + if (!cont) break; if (time_after_eq(jiffies, diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 7389f8ef0a3..971d92af70f 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -132,7 +132,7 @@ void gfs2_lvb_unhold(struct gfs2_glock *gl); void gfs2_glock_cb(void *cb_data, unsigned int type, void *data); void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl); void gfs2_reclaim_glock(struct gfs2_sbd *sdp); -void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait); +void gfs2_gl_hash_clear(struct gfs2_sbd *sdp); int __init gfs2_glock_init(void); void gfs2_glock_exit(void); diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h index ad944c64eab..845a27fd303 100644 --- a/fs/gfs2/locking/dlm/lock_dlm.h +++ b/fs/gfs2/locking/dlm/lock_dlm.h @@ -79,9 +79,6 @@ struct gdlm_ls { wait_queue_head_t wait_control; struct task_struct *thread; wait_queue_head_t thread_wait; - unsigned long drop_time; - int drop_locks_count; - int drop_locks_period; }; enum { diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c index 0628520a445..fa31c54c2e6 100644 --- a/fs/gfs2/locking/dlm/mount.c +++ b/fs/gfs2/locking/dlm/mount.c @@ -22,8 +22,6 @@ static struct gdlm_ls *init_gdlm(lm_callback_t cb, struct gfs2_sbd *sdp, if (!ls) return NULL; - ls->drop_locks_count = GDLM_DROP_COUNT; - ls->drop_locks_period = GDLM_DROP_PERIOD; ls->fscb = cb; ls->sdp = sdp; ls->fsflags = flags; @@ -33,7 +31,6 @@ static struct gdlm_ls *init_gdlm(lm_callback_t cb, struct gfs2_sbd *sdp, INIT_LIST_HEAD(&ls->all_locks); init_waitqueue_head(&ls->thread_wait); init_waitqueue_head(&ls->wait_control); - ls->drop_time = jiffies; ls->jid = -1; strncpy(buf, table_name, 256); diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c index a4ff271df9e..4ec571c3d8a 100644 --- a/fs/gfs2/locking/dlm/sysfs.c +++ b/fs/gfs2/locking/dlm/sysfs.c @@ -114,17 +114,6 @@ static ssize_t recover_status_show(struct gdlm_ls *ls, char *buf) return sprintf(buf, "%d\n", ls->recover_jid_status); } -static ssize_t drop_count_show(struct gdlm_ls *ls, char *buf) -{ - return sprintf(buf, "%d\n", ls->drop_locks_count); -} - -static ssize_t drop_count_store(struct gdlm_ls *ls, const char *buf, size_t len) -{ - ls->drop_locks_count = simple_strtol(buf, NULL, 0); - return len; -} - struct gdlm_attr { struct attribute attr; ssize_t (*show)(struct gdlm_ls *, char *); @@ -144,7 +133,6 @@ GDLM_ATTR(first_done, 0444, first_done_show, NULL); GDLM_ATTR(recover, 0644, recover_show, recover_store); GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); -GDLM_ATTR(drop_count, 0644, drop_count_show, drop_count_store); static struct attribute *gdlm_attrs[] = { &gdlm_attr_proto_name.attr, @@ -157,7 +145,6 @@ static struct attribute *gdlm_attrs[] = { &gdlm_attr_recover.attr, &gdlm_attr_recover_done.attr, &gdlm_attr_recover_status.attr, - &gdlm_attr_drop_count.attr, NULL, }; diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c index f30350abd62..38823efd698 100644 --- a/fs/gfs2/locking/dlm/thread.c +++ b/fs/gfs2/locking/dlm/thread.c @@ -20,19 +20,6 @@ static inline int no_work(struct gdlm_ls *ls) return ret; } -static inline int check_drop(struct gdlm_ls *ls) -{ - if (!ls->drop_locks_count) - return 0; - - if (time_after(jiffies, ls->drop_time + ls->drop_locks_period * HZ)) { - ls->drop_time = jiffies; - if (ls->all_locks_count >= ls->drop_locks_count) - return 1; - } - return 0; -} - static int gdlm_thread(void *data) { struct gdlm_ls *ls = (struct gdlm_ls *) data; @@ -52,12 +39,6 @@ static int gdlm_thread(void *data) gdlm_do_lock(lp); spin_lock(&ls->async_lock); } - /* Does this ever happen these days? I hope not anyway */ - if (check_drop(ls)) { - spin_unlock(&ls->async_lock); - ls->fscb(ls->sdp, LM_CB_DROPLOCKS, NULL); - spin_lock(&ls->async_lock); - } spin_unlock(&ls->async_lock); } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 9bd97c5543b..6ba69dd1a72 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -874,7 +874,7 @@ fail_sb: fail_locking: init_locking(sdp, &mount_gh, UNDO); fail_lm: - gfs2_gl_hash_clear(sdp, WAIT); + gfs2_gl_hash_clear(sdp); gfs2_lm_unmount(sdp); while (invalidate_inodes(sb)) yield(); diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 66907922109..f66ea0f7a35 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -126,7 +126,7 @@ static void gfs2_put_super(struct super_block *sb) gfs2_clear_rgrpd(sdp); gfs2_jindex_free(sdp); /* Take apart glock structures and buffer lists */ - gfs2_gl_hash_clear(sdp, WAIT); + gfs2_gl_hash_clear(sdp); /* Unmount the locking protocol */ gfs2_lm_unmount(sdp); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 9ab9fc85ecd..6f7e2e5858e 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -110,18 +110,6 @@ static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf, return len; } -static ssize_t shrink_store(struct gfs2_sbd *sdp, const char *buf, size_t len) -{ - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - - if (simple_strtol(buf, NULL, 0) != 1) - return -EINVAL; - - gfs2_gl_hash_clear(sdp, NO_WAIT); - return len; -} - static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { @@ -175,7 +163,6 @@ static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store) GFS2_ATTR(id, 0444, id_show, NULL); GFS2_ATTR(fsname, 0444, fsname_show, NULL); GFS2_ATTR(freeze, 0644, freeze_show, freeze_store); -GFS2_ATTR(shrink, 0200, NULL, shrink_store); GFS2_ATTR(withdraw, 0644, withdraw_show, withdraw_store); GFS2_ATTR(statfs_sync, 0200, NULL, statfs_sync_store); GFS2_ATTR(quota_sync, 0200, NULL, quota_sync_store); @@ -186,7 +173,6 @@ static struct attribute *gfs2_attrs[] = { &gfs2_attr_id.attr, &gfs2_attr_fsname.attr, &gfs2_attr_freeze.attr, - &gfs2_attr_shrink.attr, &gfs2_attr_withdraw.attr, &gfs2_attr_statfs_sync.attr, &gfs2_attr_quota_sync.attr, diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h index f274997bc28..d0a7112b971 100644 --- a/include/linux/lm_interface.h +++ b/include/linux/lm_interface.h @@ -138,9 +138,6 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); * LM_CB_NEED_RECOVERY * The given journal needs to be recovered. * - * LM_CB_DROPLOCKS - * Reduce the number of cached locks. - * * LM_CB_ASYNC * The given lock has been granted. */ @@ -149,7 +146,6 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); #define LM_CB_NEED_D 258 #define LM_CB_NEED_S 259 #define LM_CB_NEED_RECOVERY 260 -#define LM_CB_DROPLOCKS 261 #define LM_CB_ASYNC 262 /* -- cgit v1.2.3-70-g09d2