From e636c8d336489bf3eed5878299e6cc045bbad077 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:17:29 +0000
Subject: [PATCH] debug lk
---
kernel/fs/gfs2/glops.c | 326 ++++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 252 insertions(+), 74 deletions(-)
diff --git a/kernel/fs/gfs2/glops.c b/kernel/fs/gfs2/glops.c
index 20f08f4..87f8110 100644
--- a/kernel/fs/gfs2/glops.c
+++ b/kernel/fs/gfs2/glops.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 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 version 2.
*/
#include <linux/spinlock.h>
@@ -28,8 +25,11 @@
#include "util.h"
#include "trans.h"
#include "dir.h"
+#include "lops.h"
struct workqueue_struct *gfs2_freeze_wq;
+
+extern struct workqueue_struct *gfs2_control_wq;
static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
{
@@ -41,7 +41,8 @@
fs_err(gl->gl_name.ln_sbd, "AIL glock %u:%llu mapping %p\n",
gl->gl_name.ln_type, gl->gl_name.ln_number,
gfs2_glock2aspace(gl));
- gfs2_lm_withdraw(gl->gl_name.ln_sbd, "AIL error\n");
+ gfs2_lm(gl->gl_name.ln_sbd, "AIL error\n");
+ gfs2_withdraw(gl->gl_name.ln_sbd);
}
/**
@@ -81,10 +82,11 @@
}
-static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_trans tr;
+ int ret;
memset(&tr, 0, sizeof(tr));
INIT_LIST_HEAD(&tr.tr_buf);
@@ -93,24 +95,51 @@
INIT_LIST_HEAD(&tr.tr_ail2_list);
tr.tr_revokes = atomic_read(&gl->gl_ail_count);
- if (!tr.tr_revokes)
- return;
+ if (!tr.tr_revokes) {
+ bool have_revokes;
+ bool log_in_flight;
+
+ /*
+ * We have nothing on the ail, but there could be revokes on
+ * the sdp revoke queue, in which case, we still want to flush
+ * the log and wait for it to finish.
+ *
+ * If the sdp revoke list is empty too, we might still have an
+ * io outstanding for writing revokes, so we should wait for
+ * it before returning.
+ *
+ * If none of these conditions are true, our revokes are all
+ * flushed and we can return.
+ */
+ gfs2_log_lock(sdp);
+ have_revokes = !list_empty(&sdp->sd_log_revokes);
+ log_in_flight = atomic_read(&sdp->sd_log_in_flight);
+ gfs2_log_unlock(sdp);
+ if (have_revokes)
+ goto flush;
+ if (log_in_flight)
+ log_flush_wait(sdp);
+ return 0;
+ }
/* A shortened, inline version of gfs2_trans_begin()
* tr->alloced is not set since the transaction structure is
* on the stack */
- tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
+ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes);
tr.tr_ip = _RET_IP_;
- if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0)
- return;
+ ret = gfs2_log_reserve(sdp, tr.tr_reserved);
+ if (ret < 0)
+ return ret;
WARN_ON_ONCE(current->journal_info);
current->journal_info = &tr;
__gfs2_ail_flush(gl, 0, tr.tr_revokes);
gfs2_trans_end(sdp);
+flush:
gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_AIL_EMPTY_GL);
+ return 0;
}
void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
@@ -136,6 +165,31 @@
}
/**
+ * gfs2_rgrp_metasync - sync out the metadata of a resource group
+ * @gl: the glock protecting the resource group
+ *
+ */
+
+static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct address_space *metamapping = &sdp->sd_aspace;
+ struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+ const unsigned bsize = sdp->sd_sb.sb_bsize;
+ loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+ loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+ int error;
+
+ filemap_fdatawrite_range(metamapping, start, end);
+ error = filemap_fdatawait_range(metamapping, start, end);
+ WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+ mapping_set_error(metamapping, error);
+ if (error)
+ gfs2_io_error(sdp);
+ return error;
+}
+
+/**
* rgrp_go_sync - sync out the metadata for this glock
* @gl: the glock
*
@@ -144,35 +198,23 @@
* return to caller to demote/unlock the glock until I/O is complete.
*/
-static void rgrp_go_sync(struct gfs2_glock *gl)
+static int rgrp_go_sync(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *mapping = &sdp->sd_aspace;
- struct gfs2_rgrpd *rgd;
+ struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
int error;
- spin_lock(&gl->gl_lockref.lock);
- rgd = gl->gl_object;
- if (rgd)
- gfs2_rgrp_brelse(rgd);
- spin_unlock(&gl->gl_lockref.lock);
-
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
- return;
+ return 0;
GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_RGRP_GO_SYNC);
- filemap_fdatawrite_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
- error = filemap_fdatawait_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
- mapping_set_error(mapping, error);
- gfs2_ail_empty_gl(gl);
-
- spin_lock(&gl->gl_lockref.lock);
- rgd = gl->gl_object;
- if (rgd)
- gfs2_free_clones(rgd);
- spin_unlock(&gl->gl_lockref.lock);
+ error = gfs2_rgrp_metasync(gl);
+ if (!error)
+ error = gfs2_ail_empty_gl(gl);
+ gfs2_free_clones(rgd);
+ return error;
}
/**
@@ -190,16 +232,23 @@
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct address_space *mapping = &sdp->sd_aspace;
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+ const unsigned bsize = sdp->sd_sb.sb_bsize;
+ loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+ loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
- if (rgd)
- gfs2_rgrp_brelse(rgd);
-
+ gfs2_rgrp_brelse(rgd);
WARN_ON_ONCE(!(flags & DIO_METADATA));
- gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
- truncate_inode_pages_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
+ truncate_inode_pages_range(mapping, start, end);
+ rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+}
+
+static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
+ const char *fs_id_buf)
+{
+ struct gfs2_rgrpd *rgd = gl->gl_object;
if (rgd)
- rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+ gfs2_rgrp_dump(seq, rgd, fs_id_buf);
}
static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl)
@@ -235,17 +284,34 @@
}
/**
- * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * gfs2_inode_metasync - sync out the metadata of an inode
+ * @gl: the glock protecting the inode
+ *
+ */
+int gfs2_inode_metasync(struct gfs2_glock *gl)
+{
+ struct address_space *metamapping = gfs2_glock2aspace(gl);
+ int error;
+
+ filemap_fdatawrite(metamapping);
+ error = filemap_fdatawait(metamapping);
+ if (error)
+ gfs2_io_error(gl->gl_name.ln_sbd);
+ return error;
+}
+
+/**
+ * inode_go_sync - Sync the dirty metadata of an inode
* @gl: the glock protecting the inode
*
*/
-static void inode_go_sync(struct gfs2_glock *gl)
+static int inode_go_sync(struct gfs2_glock *gl)
{
struct gfs2_inode *ip = gfs2_glock2inode(gl);
int isreg = ip && S_ISREG(ip->i_inode.i_mode);
struct address_space *metamapping = gfs2_glock2aspace(gl);
- int error;
+ int error = 0, ret;
if (isreg) {
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
@@ -266,8 +332,9 @@
error = filemap_fdatawait(mapping);
mapping_set_error(mapping, error);
}
- error = filemap_fdatawait(metamapping);
- mapping_set_error(metamapping, error);
+ ret = gfs2_inode_metasync(gl);
+ if (!error)
+ error = ret;
gfs2_ail_empty_gl(gl);
/*
* Writeback of the data mapping may cause the dirty flag to be set
@@ -278,6 +345,7 @@
out:
gfs2_clear_glop_pending(ip);
+ return error;
}
/**
@@ -294,8 +362,6 @@
static void inode_go_inval(struct gfs2_glock *gl, int flags)
{
struct gfs2_inode *ip = gfs2_glock2inode(gl);
-
- gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count));
if (flags & DIO_METADATA) {
struct address_space *mapping = gfs2_glock2aspace(gl);
@@ -339,6 +405,7 @@
static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
const struct gfs2_dinode *str = buf;
struct timespec64 atime;
u16 height, depth;
@@ -354,7 +421,7 @@
ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
be32_to_cpu(str->di_minor));
break;
- };
+ }
i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid));
@@ -378,7 +445,7 @@
/* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */
gfs2_set_inode_flags(&ip->i_inode);
height = be16_to_cpu(str->di_height);
- if (unlikely(height > GFS2_MAX_META_HEIGHT))
+ if (unlikely(height > sdp->sd_max_height))
goto corrupt;
ip->i_height = (u8)height;
@@ -387,6 +454,9 @@
goto corrupt;
ip->i_depth = (u8)depth;
ip->i_entries = be32_to_cpu(str->di_entries);
+
+ if (gfs2_is_stuffed(ip) && ip->i_inode.i_size > gfs2_max_stuffed_size(ip))
+ goto corrupt;
if (S_ISREG(ip->i_inode.i_mode))
gfs2_set_aops(&ip->i_inode);
@@ -465,20 +535,31 @@
* inode_go_dump - print information about an inode
* @seq: The iterator
* @ip: the inode
+ * @fs_id_buf: file system id (may be empty)
*
*/
-static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
+ const char *fs_id_buf)
{
- const struct gfs2_inode *ip = gl->gl_object;
+ struct gfs2_inode *ip = gl->gl_object;
+ struct inode *inode = &ip->i_inode;
+ unsigned long nrpages;
+
if (ip == NULL)
return;
- gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n",
+
+ xa_lock_irq(&inode->i_data.i_pages);
+ nrpages = inode->i_data.nrpages;
+ xa_unlock_irq(&inode->i_data.i_pages);
+
+ gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu "
+ "p:%lu\n", fs_id_buf,
(unsigned long long)ip->i_no_formal_ino,
(unsigned long long)ip->i_no_addr,
IF2DT(ip->i_inode.i_mode), ip->i_flags,
(unsigned int)ip->i_diskflags,
- (unsigned long long)i_size_read(&ip->i_inode));
+ (unsigned long long)i_size_read(inode), nrpages);
}
/**
@@ -489,23 +570,43 @@
*
*/
-static void freeze_go_sync(struct gfs2_glock *gl)
+static int freeze_go_sync(struct gfs2_glock *gl)
{
int error = 0;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- if (gl->gl_state == LM_ST_SHARED &&
- test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+ /*
+ * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
+ * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
+ * all the nodes should have the freeze glock in SH mode and they all
+ * call do_xmote: One for EX and the others for UN. They ALL must
+ * freeze locally, and they ALL must queue freeze work. The freeze_work
+ * calls freeze_func, which tries to reacquire the freeze glock in SH,
+ * effectively waiting for the thaw on the node who holds it in EX.
+ * Once thawed, the work func acquires the freeze glock in
+ * SH and everybody goes back to thawed.
+ */
+ if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) &&
+ !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) {
atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
error = freeze_super(sdp->sd_vfs);
if (error) {
- printk(KERN_INFO "GFS2: couldn't freeze filesystem: %d\n", error);
+ fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
+ error);
+ if (gfs2_withdrawn(sdp)) {
+ atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN);
+ return 0;
+ }
gfs2_assert_withdraw(sdp, 0);
}
queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work);
- gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
- GFS2_LFC_FREEZE_GO_SYNC);
+ if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+ gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
+ GFS2_LFC_FREEZE_GO_SYNC);
+ else /* read-only mounts */
+ atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
}
+ return 0;
}
/**
@@ -525,17 +626,14 @@
if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
- error = gfs2_find_jhead(sdp->sd_jdesc, &head);
- if (error)
- gfs2_consist(sdp);
- if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
- gfs2_consist(sdp);
-
- /* Initialize some head of the log stuff */
- if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
- sdp->sd_log_sequence = head.lh_sequence + 1;
- gfs2_log_pointers_init(sdp, head.lh_blkno);
- }
+ error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
+ if (gfs2_assert_withdraw_delayed(sdp, !error))
+ return error;
+ if (gfs2_assert_withdraw_delayed(sdp, head.lh_flags &
+ GFS2_LOG_HEAD_UNMOUNT))
+ return -EIO;
+ sdp->sd_log_sequence = head.lh_sequence + 1;
+ gfs2_log_pointers_init(sdp, head.lh_blkno);
}
return 0;
}
@@ -569,13 +667,87 @@
if (gl->gl_demote_state == LM_ST_UNLOCKED &&
gl->gl_state == LM_ST_SHARED && ip) {
gl->gl_lockref.count++;
- if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
+ if (!queue_delayed_work(gfs2_delete_workqueue,
+ &gl->gl_delete, 0))
gl->gl_lockref.count--;
}
}
+static int iopen_go_demote_ok(const struct gfs2_glock *gl)
+{
+ return !gfs2_delete_work_queued(gl);
+}
+
+/**
+ * inode_go_free - wake up anyone waiting for dlm's unlock ast to free it
+ * @gl: glock being freed
+ *
+ * For now, this is only used for the journal inode glock. In withdraw
+ * situations, we need to wait for the glock to be freed so that we know
+ * other nodes may proceed with recovery / journal replay.
+ */
+static void inode_go_free(struct gfs2_glock *gl)
+{
+ /* Note that we cannot reference gl_object because it's already set
+ * to NULL by this point in its lifecycle. */
+ if (!test_bit(GLF_FREEING, &gl->gl_flags))
+ return;
+ clear_bit_unlock(GLF_FREEING, &gl->gl_flags);
+ wake_up_bit(&gl->gl_flags, GLF_FREEING);
+}
+
+/**
+ * nondisk_go_callback - used to signal when a node did a withdraw
+ * @gl: the nondisk glock
+ * @remote: true if this came from a different cluster node
+ *
+ */
+static void nondisk_go_callback(struct gfs2_glock *gl, bool remote)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+ /* Ignore the callback unless it's from another node, and it's the
+ live lock. */
+ if (!remote || gl->gl_name.ln_number != GFS2_LIVE_LOCK)
+ return;
+
+ /* First order of business is to cancel the demote request. We don't
+ * really want to demote a nondisk glock. At best it's just to inform
+ * us of another node's withdraw. We'll keep it in SH mode. */
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
+
+ /* Ignore the unlock if we're withdrawn, unmounting, or in recovery. */
+ if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) ||
+ test_bit(SDF_WITHDRAWN, &sdp->sd_flags) ||
+ test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags))
+ return;
+
+ /* We only care when a node wants us to unlock, because that means
+ * they want a journal recovered. */
+ if (gl->gl_demote_state != LM_ST_UNLOCKED)
+ return;
+
+ if (sdp->sd_args.ar_spectator) {
+ fs_warn(sdp, "Spectator node cannot recover journals.\n");
+ return;
+ }
+
+ fs_warn(sdp, "Some node has withdrawn; checking for recovery.\n");
+ set_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags);
+ /*
+ * We can't call remote_withdraw directly here or gfs2_recover_journal
+ * because this is called from the glock unlock function and the
+ * remote_withdraw needs to enqueue and dequeue the same "live" glock
+ * we were called from. So we queue it to the control work queue in
+ * lock_dlm.
+ */
+ queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
+}
+
const struct gfs2_glock_operations gfs2_meta_glops = {
.go_type = LM_TYPE_META,
+ .go_flags = GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_inode_glops = {
@@ -585,15 +757,15 @@
.go_lock = inode_go_lock,
.go_dump = inode_go_dump,
.go_type = LM_TYPE_INODE,
- .go_flags = GLOF_ASPACE | GLOF_LRU,
+ .go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB,
+ .go_free = inode_go_free,
};
const struct gfs2_glock_operations gfs2_rgrp_glops = {
.go_sync = rgrp_go_sync,
.go_inval = rgrp_go_inval,
.go_lock = gfs2_rgrp_go_lock,
- .go_unlock = gfs2_rgrp_go_unlock,
- .go_dump = gfs2_rgrp_dump,
+ .go_dump = gfs2_rgrp_go_dump,
.go_type = LM_TYPE_RGRP,
.go_flags = GLOF_LVB,
};
@@ -603,30 +775,36 @@
.go_xmote_bh = freeze_go_xmote_bh,
.go_demote_ok = freeze_go_demote_ok,
.go_type = LM_TYPE_NONDISK,
+ .go_flags = GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_iopen_glops = {
.go_type = LM_TYPE_IOPEN,
.go_callback = iopen_go_callback,
- .go_flags = GLOF_LRU,
+ .go_demote_ok = iopen_go_demote_ok,
+ .go_flags = GLOF_LRU | GLOF_NONDISK,
+ .go_subclass = 1,
};
const struct gfs2_glock_operations gfs2_flock_glops = {
.go_type = LM_TYPE_FLOCK,
- .go_flags = GLOF_LRU,
+ .go_flags = GLOF_LRU | GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_nondisk_glops = {
.go_type = LM_TYPE_NONDISK,
+ .go_flags = GLOF_NONDISK,
+ .go_callback = nondisk_go_callback,
};
const struct gfs2_glock_operations gfs2_quota_glops = {
.go_type = LM_TYPE_QUOTA,
- .go_flags = GLOF_LVB | GLOF_LRU,
+ .go_flags = GLOF_LVB | GLOF_LRU | GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_journal_glops = {
.go_type = LM_TYPE_JOURNAL,
+ .go_flags = GLOF_NONDISK,
};
const struct gfs2_glock_operations *gfs2_glops_list[] = {
--
Gitblit v1.6.2