From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp

---
 kernel/fs/gfs2/super.c |  920 +++++++++++++++++++++------------------------------------
 1 files changed, 339 insertions(+), 581 deletions(-)

diff --git a/kernel/fs/gfs2/super.c b/kernel/fs/gfs2/super.c
index 3cc2237..d14b98a 100644
--- a/kernel/fs/gfs2/super.c
+++ b/kernel/fs/gfs2/super.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
  * Copyright (C) 2004-2007 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.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -45,258 +42,13 @@
 #include "util.h"
 #include "sys.h"
 #include "xattr.h"
+#include "lops.h"
 
-#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
-
-enum {
-	Opt_lockproto,
-	Opt_locktable,
-	Opt_hostdata,
-	Opt_spectator,
-	Opt_ignore_local_fs,
-	Opt_localflocks,
-	Opt_localcaching,
-	Opt_debug,
-	Opt_nodebug,
-	Opt_upgrade,
-	Opt_acl,
-	Opt_noacl,
-	Opt_quota_off,
-	Opt_quota_account,
-	Opt_quota_on,
-	Opt_quota,
-	Opt_noquota,
-	Opt_suiddir,
-	Opt_nosuiddir,
-	Opt_data_writeback,
-	Opt_data_ordered,
-	Opt_meta,
-	Opt_discard,
-	Opt_nodiscard,
-	Opt_commit,
-	Opt_err_withdraw,
-	Opt_err_panic,
-	Opt_statfs_quantum,
-	Opt_statfs_percent,
-	Opt_quota_quantum,
-	Opt_barrier,
-	Opt_nobarrier,
-	Opt_rgrplvb,
-	Opt_norgrplvb,
-	Opt_loccookie,
-	Opt_noloccookie,
-	Opt_error,
+enum dinode_demise {
+	SHOULD_DELETE_DINODE,
+	SHOULD_NOT_DELETE_DINODE,
+	SHOULD_DEFER_EVICTION,
 };
-
-static const match_table_t tokens = {
-	{Opt_lockproto, "lockproto=%s"},
-	{Opt_locktable, "locktable=%s"},
-	{Opt_hostdata, "hostdata=%s"},
-	{Opt_spectator, "spectator"},
-	{Opt_spectator, "norecovery"},
-	{Opt_ignore_local_fs, "ignore_local_fs"},
-	{Opt_localflocks, "localflocks"},
-	{Opt_localcaching, "localcaching"},
-	{Opt_debug, "debug"},
-	{Opt_nodebug, "nodebug"},
-	{Opt_upgrade, "upgrade"},
-	{Opt_acl, "acl"},
-	{Opt_noacl, "noacl"},
-	{Opt_quota_off, "quota=off"},
-	{Opt_quota_account, "quota=account"},
-	{Opt_quota_on, "quota=on"},
-	{Opt_quota, "quota"},
-	{Opt_noquota, "noquota"},
-	{Opt_suiddir, "suiddir"},
-	{Opt_nosuiddir, "nosuiddir"},
-	{Opt_data_writeback, "data=writeback"},
-	{Opt_data_ordered, "data=ordered"},
-	{Opt_meta, "meta"},
-	{Opt_discard, "discard"},
-	{Opt_nodiscard, "nodiscard"},
-	{Opt_commit, "commit=%d"},
-	{Opt_err_withdraw, "errors=withdraw"},
-	{Opt_err_panic, "errors=panic"},
-	{Opt_statfs_quantum, "statfs_quantum=%d"},
-	{Opt_statfs_percent, "statfs_percent=%d"},
-	{Opt_quota_quantum, "quota_quantum=%d"},
-	{Opt_barrier, "barrier"},
-	{Opt_nobarrier, "nobarrier"},
-	{Opt_rgrplvb, "rgrplvb"},
-	{Opt_norgrplvb, "norgrplvb"},
-	{Opt_loccookie, "loccookie"},
-	{Opt_noloccookie, "noloccookie"},
-	{Opt_error, NULL}
-};
-
-/**
- * gfs2_mount_args - Parse mount options
- * @args: The structure into which the parsed options will be written
- * @options: The options to parse
- *
- * Return: errno
- */
-
-int gfs2_mount_args(struct gfs2_args *args, char *options)
-{
-	char *o;
-	int token;
-	substring_t tmp[MAX_OPT_ARGS];
-	int rv;
-
-	/* Split the options into tokens with the "," character and
-	   process them */
-
-	while (1) {
-		o = strsep(&options, ",");
-		if (o == NULL)
-			break;
-		if (*o == '\0')
-			continue;
-
-		token = match_token(o, tokens, tmp);
-		switch (token) {
-		case Opt_lockproto:
-			match_strlcpy(args->ar_lockproto, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_locktable:
-			match_strlcpy(args->ar_locktable, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_hostdata:
-			match_strlcpy(args->ar_hostdata, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_spectator:
-			args->ar_spectator = 1;
-			break;
-		case Opt_ignore_local_fs:
-			/* Retained for backwards compat only */
-			break;
-		case Opt_localflocks:
-			args->ar_localflocks = 1;
-			break;
-		case Opt_localcaching:
-			/* Retained for backwards compat only */
-			break;
-		case Opt_debug:
-			if (args->ar_errors == GFS2_ERRORS_PANIC) {
-				pr_warn("-o debug and -o errors=panic are mutually exclusive\n");
-				return -EINVAL;
-			}
-			args->ar_debug = 1;
-			break;
-		case Opt_nodebug:
-			args->ar_debug = 0;
-			break;
-		case Opt_upgrade:
-			/* Retained for backwards compat only */
-			break;
-		case Opt_acl:
-			args->ar_posix_acl = 1;
-			break;
-		case Opt_noacl:
-			args->ar_posix_acl = 0;
-			break;
-		case Opt_quota_off:
-		case Opt_noquota:
-			args->ar_quota = GFS2_QUOTA_OFF;
-			break;
-		case Opt_quota_account:
-			args->ar_quota = GFS2_QUOTA_ACCOUNT;
-			break;
-		case Opt_quota_on:
-		case Opt_quota:
-			args->ar_quota = GFS2_QUOTA_ON;
-			break;
-		case Opt_suiddir:
-			args->ar_suiddir = 1;
-			break;
-		case Opt_nosuiddir:
-			args->ar_suiddir = 0;
-			break;
-		case Opt_data_writeback:
-			args->ar_data = GFS2_DATA_WRITEBACK;
-			break;
-		case Opt_data_ordered:
-			args->ar_data = GFS2_DATA_ORDERED;
-			break;
-		case Opt_meta:
-			args->ar_meta = 1;
-			break;
-		case Opt_discard:
-			args->ar_discard = 1;
-			break;
-		case Opt_nodiscard:
-			args->ar_discard = 0;
-			break;
-		case Opt_commit:
-			rv = match_int(&tmp[0], &args->ar_commit);
-			if (rv || args->ar_commit <= 0) {
-				pr_warn("commit mount option requires a positive numeric argument\n");
-				return rv ? rv : -EINVAL;
-			}
-			break;
-		case Opt_statfs_quantum:
-			rv = match_int(&tmp[0], &args->ar_statfs_quantum);
-			if (rv || args->ar_statfs_quantum < 0) {
-				pr_warn("statfs_quantum mount option requires a non-negative numeric argument\n");
-				return rv ? rv : -EINVAL;
-			}
-			break;
-		case Opt_quota_quantum:
-			rv = match_int(&tmp[0], &args->ar_quota_quantum);
-			if (rv || args->ar_quota_quantum <= 0) {
-				pr_warn("quota_quantum mount option requires a positive numeric argument\n");
-				return rv ? rv : -EINVAL;
-			}
-			break;
-		case Opt_statfs_percent:
-			rv = match_int(&tmp[0], &args->ar_statfs_percent);
-			if (rv || args->ar_statfs_percent < 0 ||
-			    args->ar_statfs_percent > 100) {
-				pr_warn("statfs_percent mount option requires a numeric argument between 0 and 100\n");
-				return rv ? rv : -EINVAL;
-			}
-			break;
-		case Opt_err_withdraw:
-			args->ar_errors = GFS2_ERRORS_WITHDRAW;
-			break;
-		case Opt_err_panic:
-			if (args->ar_debug) {
-				pr_warn("-o debug and -o errors=panic are mutually exclusive\n");
-				return -EINVAL;
-			}
-			args->ar_errors = GFS2_ERRORS_PANIC;
-			break;
-		case Opt_barrier:
-			args->ar_nobarrier = 0;
-			break;
-		case Opt_nobarrier:
-			args->ar_nobarrier = 1;
-			break;
-		case Opt_rgrplvb:
-			args->ar_rgrplvb = 1;
-			break;
-		case Opt_norgrplvb:
-			args->ar_rgrplvb = 0;
-			break;
-		case Opt_loccookie:
-			args->ar_loccookie = 1;
-			break;
-		case Opt_noloccookie:
-			args->ar_loccookie = 0;
-			break;
-		case Opt_error:
-		default:
-			pr_warn("invalid mount option: %s\n", o);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
 
 /**
  * gfs2_jindex_free - Clear all the journal index information
@@ -315,11 +67,13 @@
 	sdp->sd_journals = 0;
 	spin_unlock(&sdp->sd_jindex_spin);
 
+	sdp->sd_jdesc = NULL;
 	while (!list_empty(&list)) {
-		jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
+		jd = list_first_entry(&list, struct gfs2_jdesc, jd_list);
 		gfs2_free_journal_extents(jd);
 		list_del(&jd->jd_list);
 		iput(jd->jd_inode);
+		jd->jd_inode = NULL;
 		kfree(jd);
 	}
 }
@@ -372,33 +126,6 @@
 	return 0;
 }
 
-static int init_threads(struct gfs2_sbd *sdp)
-{
-	struct task_struct *p;
-	int error = 0;
-
-	p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
-	if (IS_ERR(p)) {
-		error = PTR_ERR(p);
-		fs_err(sdp, "can't start logd thread: %d\n", error);
-		return error;
-	}
-	sdp->sd_logd_process = p;
-
-	p = kthread_run(gfs2_quotad, sdp, "gfs2_quotad");
-	if (IS_ERR(p)) {
-		error = PTR_ERR(p);
-		fs_err(sdp, "can't start quotad thread: %d\n", error);
-		goto fail;
-	}
-	sdp->sd_quotad_process = p;
-	return 0;
-
-fail:
-	kthread_stop(sdp->sd_logd_process);
-	return error;
-}
-
 /**
  * gfs2_make_fs_rw - Turn a Read-Only FS into a Read-Write one
  * @sdp: the filesystem
@@ -410,29 +137,20 @@
 {
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 	struct gfs2_glock *j_gl = ip->i_gl;
-	struct gfs2_holder freeze_gh;
 	struct gfs2_log_header_host head;
 	int error;
 
-	error = init_threads(sdp);
-	if (error)
-		return error;
-
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
-				   &freeze_gh);
-	if (error)
-		goto fail_threads;
-
 	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
+	if (gfs2_withdrawn(sdp))
+		return -EIO;
 
-	error = gfs2_find_jhead(sdp->sd_jdesc, &head);
-	if (error)
-		goto fail;
+	error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
+	if (error || gfs2_withdrawn(sdp))
+		return error;
 
 	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
 		gfs2_consist(sdp);
-		error = -EIO;
-		goto fail;
+		return -EIO;
 	}
 
 	/*  Initialize some head of the log stuff  */
@@ -440,21 +158,8 @@
 	gfs2_log_pointers_init(sdp, head.lh_blkno);
 
 	error = gfs2_quota_init(sdp);
-	if (error)
-		goto fail;
-
-	set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-
-	gfs2_glock_dq_uninit(&freeze_gh);
-
-	return 0;
-
-fail:
-	freeze_gh.gh_flags |= GL_NOCACHE;
-	gfs2_glock_dq_uninit(&freeze_gh);
-fail_threads:
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
+	if (!error && !gfs2_withdrawn(sdp))
+		set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 	return error;
 }
 
@@ -467,7 +172,7 @@
 	sc->sc_dinodes = be64_to_cpu(str->sc_dinodes);
 }
 
-static void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf)
+void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf)
 {
 	struct gfs2_statfs_change *str = buf;
 
@@ -648,8 +353,7 @@
  * Returns: errno
  */
 
-static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
-				    struct gfs2_holder *freeze_gh)
+static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip;
 	struct gfs2_jdesc *jd;
@@ -674,13 +378,15 @@
 	}
 
 	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE,
-				   GL_NOCACHE, freeze_gh);
+				   LM_FLAG_NOEXP, &sdp->sd_freeze_gh);
+	if (error)
+		goto out;
 
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		error = gfs2_jdesc_check(jd);
 		if (error)
 			break;
-		error = gfs2_find_jhead(jd, &lh);
+		error = gfs2_find_jhead(jd, &lh, false);
 		if (error)
 			break;
 		if (!(lh.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
@@ -690,11 +396,11 @@
 	}
 
 	if (error)
-		gfs2_glock_dq_uninit(freeze_gh);
+		gfs2_freeze_unlock(&sdp->sd_freeze_gh);
 
 out:
 	while (!list_empty(&list)) {
-		lfcc = list_entry(list.next, struct lfcc, list);
+		lfcc = list_first_entry(&list, struct lfcc, list);
 		list_del(&lfcc->list);
 		gfs2_glock_dq_uninit(&lfcc->gh);
 		kfree(lfcc);
@@ -802,12 +508,13 @@
 
 	if (!(flags & I_DIRTY_INODE))
 		return;
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		return;
 	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
 		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 		if (ret) {
 			fs_err(sdp, "dirty_inode: glock %d\n", ret);
+			gfs2_dump_glock(NULL, ip->i_gl, true);
 			return;
 		}
 		need_unlock = 1;
@@ -844,32 +551,43 @@
  * Returns: errno
  */
 
-static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 {
-	struct gfs2_holder freeze_gh;
-	int error;
+	int error = 0;
+	int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
-				   &freeze_gh);
-	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return error;
+	gfs2_flush_delete_work(sdp);
+	if (!log_write_allowed && current == sdp->sd_quotad_process)
+		fs_warn(sdp, "The quotad daemon is withdrawing.\n");
+	else if (sdp->sd_quotad_process)
+		kthread_stop(sdp->sd_quotad_process);
+	sdp->sd_quotad_process = NULL;
 
-	flush_workqueue(gfs2_delete_workqueue);
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
+	if (!log_write_allowed && current == sdp->sd_logd_process)
+		fs_warn(sdp, "The logd daemon is withdrawing.\n");
+	else if (sdp->sd_logd_process)
+		kthread_stop(sdp->sd_logd_process);
+	sdp->sd_logd_process = NULL;
 
-	gfs2_quota_sync(sdp->sd_vfs, 0);
-	gfs2_statfs_sync(sdp->sd_vfs, 0);
+	if (log_write_allowed) {
+		gfs2_quota_sync(sdp->sd_vfs, 0);
+		gfs2_statfs_sync(sdp->sd_vfs, 0);
 
-	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
-		       GFS2_LFC_MAKE_FS_RO);
-	wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0);
-	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
-
-	if (gfs2_holder_initialized(&freeze_gh))
-		gfs2_glock_dq_uninit(&freeze_gh);
-
+		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
+			       GFS2_LFC_MAKE_FS_RO);
+		wait_event(sdp->sd_reserving_log_wait,
+			   atomic_read(&sdp->sd_reserving_log) == 0);
+		gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) ==
+				 sdp->sd_jdesc->jd_blocks);
+	} else {
+		wait_event_timeout(sdp->sd_reserving_log_wait,
+				   atomic_read(&sdp->sd_reserving_log) == 0,
+				   HZ * 5);
+	}
 	gfs2_quota_cleanup(sdp);
+
+	if (!log_write_allowed)
+		sdp->sd_vfs->s_flags |= SB_RDONLY;
 
 	return error;
 }
@@ -908,6 +626,8 @@
 		if (error)
 			gfs2_io_error(sdp);
 	}
+	WARN_ON(gfs2_withdrawing(sdp));
+
 	/*  At this point, we're through modifying the disk  */
 
 	/*  Release stuff  */
@@ -921,11 +641,13 @@
 	gfs2_glock_put(sdp->sd_freeze_gl);
 
 	if (!sdp->sd_args.ar_spectator) {
-		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		if (gfs2_holder_initialized(&sdp->sd_journal_gh))
+			gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		if (gfs2_holder_initialized(&sdp->sd_jinode_gh))
+			gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
 		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
 		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
-		iput(sdp->sd_sc_inode);
+		free_local_statfs_inodes(sdp);
 		iput(sdp->sd_qc_inode);
 	}
 
@@ -941,6 +663,7 @@
 
 	/*  At this point, we're through participating in the lockspace  */
 	gfs2_sys_fs_del(sdp);
+	free_sbd(sdp);
 }
 
 /**
@@ -969,25 +692,22 @@
 	struct super_block *sb = sdp->sd_vfs;
 
 	atomic_inc(&sb->s_active);
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0,
-				   &freeze_gh);
+	error = gfs2_freeze_lock(sdp, &freeze_gh, 0);
 	if (error) {
-		printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error);
 		gfs2_assert_withdraw(sdp, 0);
-	}
-	else {
+	} else {
 		atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN);
 		error = thaw_super(sb);
 		if (error) {
-			printk(KERN_INFO "GFS2: couldn't thaw filesystem: %d\n",
-			       error);
+			fs_info(sdp, "GFS2: couldn't thaw filesystem: %d\n",
+				error);
 			gfs2_assert_withdraw(sdp, 0);
 		}
-		if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
-			freeze_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&freeze_gh);
+		gfs2_freeze_unlock(&freeze_gh);
 	}
 	deactivate_super(sb);
+	clear_bit_unlock(SDF_FS_FROZEN, &sdp->sd_flags);
+	wake_up_bit(&sdp->sd_flags, SDF_FS_FROZEN);
 	return;
 }
 
@@ -1008,30 +728,29 @@
 		goto out;
 	}
 
-	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
-		error = -EINVAL;
-		goto out;
-	}
-
 	for (;;) {
-		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
+		if (gfs2_withdrawn(sdp)) {
+			error = -EINVAL;
+			goto out;
+		}
+
+		error = gfs2_lock_fs_check_clean(sdp);
 		if (!error)
 			break;
 
-		switch (error) {
-		case -EBUSY:
+		if (error == -EBUSY)
 			fs_err(sdp, "waiting for recovery before freeze\n");
-			break;
-
-		default:
+		else if (error == -EIO) {
+			fs_err(sdp, "Fatal IO error: cannot freeze gfs2 due "
+			       "to recovery error.\n");
+			goto out;
+		} else {
 			fs_err(sdp, "error freezing FS: %d\n", error);
-			break;
 		}
-
 		fs_err(sdp, "retrying...\n");
 		msleep(1000);
 	}
-	error = 0;
+	set_bit(SDF_FS_FROZEN, &sdp->sd_flags);
 out:
 	mutex_unlock(&sdp->sd_freeze_mutex);
 	return error;
@@ -1054,9 +773,9 @@
 		return -EINVAL;
 	}
 
-	gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	gfs2_freeze_unlock(&sdp->sd_freeze_gh);
 	mutex_unlock(&sdp->sd_freeze_mutex);
-	return 0;
+	return wait_on_bit(&sdp->sd_flags, SDF_FS_FROZEN, TASK_INTERRUPTIBLE);
 }
 
 /**
@@ -1227,86 +946,6 @@
 }
 
 /**
- * gfs2_remount_fs - called when the FS is remounted
- * @sb:  the filesystem
- * @flags:  the remount flags
- * @data:  extra data passed in (not used right now)
- *
- * Returns: errno
- */
-
-static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
-	struct gfs2_tune *gt = &sdp->sd_tune;
-	int error;
-
-	sync_filesystem(sb);
-
-	spin_lock(&gt->gt_spin);
-	args.ar_commit = gt->gt_logd_secs;
-	args.ar_quota_quantum = gt->gt_quota_quantum;
-	if (gt->gt_statfs_slow)
-		args.ar_statfs_quantum = 0;
-	else
-		args.ar_statfs_quantum = gt->gt_statfs_quantum;
-	spin_unlock(&gt->gt_spin);
-	error = gfs2_mount_args(&args, data);
-	if (error)
-		return error;
-
-	/* Not allowed to change locking details */
-	if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) ||
-	    strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) ||
-	    strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata))
-		return -EINVAL;
-
-	/* Some flags must not be changed */
-	if (args_neq(&args, &sdp->sd_args, spectator) ||
-	    args_neq(&args, &sdp->sd_args, localflocks) ||
-	    args_neq(&args, &sdp->sd_args, meta))
-		return -EINVAL;
-
-	if (sdp->sd_args.ar_spectator)
-		*flags |= SB_RDONLY;
-
-	if ((sb->s_flags ^ *flags) & SB_RDONLY) {
-		if (*flags & SB_RDONLY)
-			error = gfs2_make_fs_ro(sdp);
-		else
-			error = gfs2_make_fs_rw(sdp);
-		if (error)
-			return error;
-	}
-
-	sdp->sd_args = args;
-	if (sdp->sd_args.ar_posix_acl)
-		sb->s_flags |= SB_POSIXACL;
-	else
-		sb->s_flags &= ~SB_POSIXACL;
-	if (sdp->sd_args.ar_nobarrier)
-		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
-	else
-		clear_bit(SDF_NOBARRIERS, &sdp->sd_flags);
-	spin_lock(&gt->gt_spin);
-	gt->gt_logd_secs = args.ar_commit;
-	gt->gt_quota_quantum = args.ar_quota_quantum;
-	if (args.ar_statfs_quantum) {
-		gt->gt_statfs_slow = 0;
-		gt->gt_statfs_quantum = args.ar_statfs_quantum;
-	}
-	else {
-		gt->gt_statfs_slow = 1;
-		gt->gt_statfs_quantum = 30;
-	}
-	spin_unlock(&gt->gt_spin);
-
-	gfs2_online_uevent(sdp);
-	return 0;
-}
-
-/**
  * gfs2_drop_inode - Drop an inode (test for remote unlink)
  * @inode: The inode to drop
  *
@@ -1344,7 +983,7 @@
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
 
 		gfs2_glock_hold(gl);
-		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
+		if (!gfs2_queue_delete_work(gl, 0))
 			gfs2_glock_queue_put(gl);
 		return false;
 	}
@@ -1548,6 +1187,194 @@
 		gfs2_glock_put(gl);
 }
 
+static bool gfs2_upgrade_iopen_glock(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder *gh = &ip->i_iopen_gh;
+	long timeout = 5 * HZ;
+	int error;
+
+	gh->gh_flags |= GL_NOCACHE;
+	gfs2_glock_dq_wait(gh);
+
+	/*
+	 * If there are no other lock holders, we'll get the lock immediately.
+	 * Otherwise, the other nodes holding the lock will be notified about
+	 * our locking request.  If they don't have the inode open, they'll
+	 * evict the cached inode and release the lock.  Otherwise, if they
+	 * poke the inode glock, we'll take this as an indication that they
+	 * still need the iopen glock and that they'll take care of deleting
+	 * the inode when they're done.  As a last resort, if another node
+	 * keeps holding the iopen glock without showing any activity on the
+	 * inode glock, we'll eventually time out.
+	 *
+	 * Note that we're passing the LM_FLAG_TRY_1CB flag to the first
+	 * locking request as an optimization to notify lock holders as soon as
+	 * possible.  Without that flag, they'd be notified implicitly by the
+	 * second locking request.
+	 */
+
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, gh);
+	error = gfs2_glock_nq(gh);
+	if (error != GLR_TRYFAILED)
+		return !error;
+
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, GL_ASYNC | GL_NOCACHE, gh);
+	error = gfs2_glock_nq(gh);
+	if (error)
+		return false;
+
+	timeout = wait_event_interruptible_timeout(sdp->sd_async_glock_wait,
+		!test_bit(HIF_WAIT, &gh->gh_iflags) ||
+		test_bit(GLF_DEMOTE, &ip->i_gl->gl_flags),
+		timeout);
+	if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) {
+		gfs2_glock_dq(gh);
+		return false;
+	}
+	return true;
+}
+
+/**
+ * evict_should_delete - determine whether the inode is eligible for deletion
+ * @inode: The inode to evict
+ *
+ * This function determines whether the evicted inode is eligible to be deleted
+ * and locks the inode glock.
+ *
+ * Returns: the fate of the dinode
+ */
+static enum dinode_demise evict_should_delete(struct inode *inode,
+					      struct gfs2_holder *gh)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int ret;
+
+	if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
+		BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl));
+		goto should_delete;
+	}
+
+	if (test_bit(GIF_DEFERRED_DELETE, &ip->i_flags))
+		return SHOULD_DEFER_EVICTION;
+
+	/* Deletes should never happen under memory pressure anymore.  */
+	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
+		return SHOULD_DEFER_EVICTION;
+
+	/* Must not read inode block until block type has been verified */
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, gh);
+	if (unlikely(ret)) {
+		glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
+		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		return SHOULD_DEFER_EVICTION;
+	}
+
+	if (gfs2_inode_already_deleted(ip->i_gl, ip->i_no_formal_ino))
+		return SHOULD_NOT_DELETE_DINODE;
+	ret = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+	if (ret)
+		return SHOULD_NOT_DELETE_DINODE;
+
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		ret = gfs2_inode_refresh(ip);
+		if (ret)
+			return SHOULD_NOT_DELETE_DINODE;
+	}
+
+	/*
+	 * The inode may have been recreated in the meantime.
+	 */
+	if (inode->i_nlink)
+		return SHOULD_NOT_DELETE_DINODE;
+
+should_delete:
+	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
+	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+		if (!gfs2_upgrade_iopen_glock(inode)) {
+			gfs2_holder_uninit(&ip->i_iopen_gh);
+			return SHOULD_NOT_DELETE_DINODE;
+		}
+	}
+	return SHOULD_DELETE_DINODE;
+}
+
+/**
+ * evict_unlinked_inode - delete the pieces of an unlinked evicted inode
+ * @inode: The inode to evict
+ */
+static int evict_unlinked_inode(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int ret;
+
+	if (S_ISDIR(inode->i_mode) &&
+	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
+		ret = gfs2_dir_exhash_dealloc(ip);
+		if (ret)
+			goto out;
+	}
+
+	if (ip->i_eattr) {
+		ret = gfs2_ea_dealloc(ip);
+		if (ret)
+			goto out;
+	}
+
+	if (!gfs2_is_stuffed(ip)) {
+		ret = gfs2_file_dealloc(ip);
+		if (ret)
+			goto out;
+	}
+
+	/* We're about to clear the bitmap for the dinode, but as soon as we
+	   do, gfs2_create_inode can create another inode at the same block
+	   location and try to set gl_object again. We clear gl_object here so
+	   that subsequent inode creates don't see an old gl_object. */
+	glock_clear_object(ip->i_gl, ip);
+	ret = gfs2_dinode_dealloc(ip);
+	gfs2_inode_remember_delete(ip->i_gl, ip->i_no_formal_ino);
+out:
+	return ret;
+}
+
+/*
+ * evict_linked_inode - evict an inode whose dinode has not been unlinked
+ * @inode: The inode to evict
+ */
+static int evict_linked_inode(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct address_space *metamapping;
+	int ret;
+
+	gfs2_log_flush(sdp, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
+		       GFS2_LFC_EVICT_INODE);
+	metamapping = gfs2_glock2aspace(ip->i_gl);
+	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
+		filemap_fdatawrite(metamapping);
+		filemap_fdatawait(metamapping);
+	}
+	write_inode_now(inode, 1);
+	gfs2_ail_flush(ip->i_gl, 0);
+
+	ret = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+	if (ret)
+		return ret;
+
+	/* Needs to be done before glock release & also in a transaction */
+	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(metamapping, 0);
+	gfs2_trans_end(sdp);
+	return 0;
+}
+
 /**
  * gfs2_evict_inode - Remove an inode from cache
  * @inode: The inode to evict
@@ -1575,8 +1402,7 @@
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
-	struct address_space *metamapping;
-	int error;
+	int ret;
 
 	if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) {
 		clear_inode(inode);
@@ -1586,141 +1412,50 @@
 	if (inode->i_nlink || sb_rdonly(sb))
 		goto out;
 
-	if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
-		BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl));
-		gfs2_holder_mark_uninitialized(&gh);
-		goto alloc_failed;
-	}
-
-	/* Deletes should never happen under memory pressure anymore.  */
-	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
+	gfs2_holder_mark_uninitialized(&gh);
+	ret = evict_should_delete(inode, &gh);
+	if (ret == SHOULD_DEFER_EVICTION)
 		goto out;
+	if (ret == SHOULD_DELETE_DINODE)
+		ret = evict_unlinked_inode(inode);
+	else
+		ret = evict_linked_inode(inode);
 
-	/* Must not read inode block until block type has been verified */
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
-	if (unlikely(error)) {
-		glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
-		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-		goto out;
-	}
-
-	error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
-	if (error)
-		goto out_truncate;
-
-	if (test_bit(GIF_INVALID, &ip->i_flags)) {
-		error = gfs2_inode_refresh(ip);
-		if (error)
-			goto out_truncate;
-	}
-
-	/*
-	 * The inode may have been recreated in the meantime.
-	 */
-	if (inode->i_nlink)
-		goto out_truncate;
-
-alloc_failed:
-	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
-	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
-		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_wait(&ip->i_iopen_gh);
-		gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE,
-				   &ip->i_iopen_gh);
-		error = gfs2_glock_nq(&ip->i_iopen_gh);
-		if (error)
-			goto out_truncate;
-	}
-
-	/* Case 1 starts here */
-
-	if (S_ISDIR(inode->i_mode) &&
-	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
-		error = gfs2_dir_exhash_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	if (ip->i_eattr) {
-		error = gfs2_ea_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	if (!gfs2_is_stuffed(ip)) {
-		error = gfs2_file_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	/* We're about to clear the bitmap for the dinode, but as soon as we
-	   do, gfs2_create_inode can create another inode at the same block
-	   location and try to set gl_object again. We clear gl_object here so
-	   that subsequent inode creates don't see an old gl_object. */
-	glock_clear_object(ip->i_gl, ip);
-	error = gfs2_dinode_dealloc(ip);
-	goto out_unlock;
-
-out_truncate:
-	gfs2_log_flush(sdp, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
-		       GFS2_LFC_EVICT_INODE);
-	metamapping = gfs2_glock2aspace(ip->i_gl);
-	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
-		filemap_fdatawrite(metamapping);
-		filemap_fdatawait(metamapping);
-	}
-	write_inode_now(inode, 1);
-	gfs2_ail_flush(ip->i_gl, 0);
-
-	/* Case 2 starts here */
-	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
-	if (error)
-		goto out_unlock;
-	/* Needs to be done before glock release & also in a transaction */
-	truncate_inode_pages(&inode->i_data, 0);
-	truncate_inode_pages(metamapping, 0);
-	gfs2_trans_end(sdp);
-
-out_unlock:
-	/* Error path for case 1 */
 	if (gfs2_rs_active(&ip->i_res))
 		gfs2_rs_deltree(&ip->i_res);
 
-	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
-		glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
-		if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
-			ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-			gfs2_glock_dq(&ip->i_iopen_gh);
-		}
-		gfs2_holder_uninit(&ip->i_iopen_gh);
-	}
 	if (gfs2_holder_initialized(&gh)) {
 		glock_clear_object(ip->i_gl, ip);
 		gfs2_glock_dq_uninit(&gh);
 	}
-	if (error && error != GLR_TRYFAILED && error != -EROFS)
-		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
+	if (ret && ret != GLR_TRYFAILED && ret != -EROFS)
+		fs_warn(sdp, "gfs2_evict_inode: %d\n", ret);
 out:
-	/* Case 3 starts here */
 	truncate_inode_pages_final(&inode->i_data);
-	gfs2_rsqa_delete(ip, NULL);
+	if (ip->i_qadata)
+		gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0);
+	gfs2_rs_deltree(&ip->i_res);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
-	glock_clear_object(ip->i_gl, ip);
-	wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
-	gfs2_glock_add_to_lru(ip->i_gl);
-	gfs2_glock_put_eventually(ip->i_gl);
-	ip->i_gl = NULL;
 	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
 
 		glock_clear_object(gl, ip);
-		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+		if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+			ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+			gfs2_glock_dq(&ip->i_iopen_gh);
+		}
 		gfs2_glock_hold(gl);
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 		gfs2_glock_put_eventually(gl);
+	}
+	if (ip->i_gl) {
+		glock_clear_object(ip->i_gl, ip);
+		wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
+		gfs2_glock_add_to_lru(ip->i_gl);
+		gfs2_glock_put_eventually(ip->i_gl);
+		ip->i_gl = NULL;
 	}
 }
 
@@ -1729,30 +1464,54 @@
 	struct gfs2_inode *ip;
 
 	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
-	if (ip) {
-		ip->i_flags = 0;
-		ip->i_gl = NULL;
-		memset(&ip->i_res, 0, sizeof(ip->i_res));
-		RB_CLEAR_NODE(&ip->i_res.rs_node);
-		ip->i_rahead = 0;
-	}
+	if (!ip)
+		return NULL;
+	ip->i_flags = 0;
+	ip->i_gl = NULL;
+	gfs2_holder_mark_uninitialized(&ip->i_iopen_gh);
+	memset(&ip->i_res, 0, sizeof(ip->i_res));
+	RB_CLEAR_NODE(&ip->i_res.rs_node);
+	ip->i_rahead = 0;
 	return &ip->i_inode;
 }
 
-static void gfs2_i_callback(struct rcu_head *head)
+static void gfs2_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
-	kmem_cache_free(gfs2_inode_cachep, inode);
+	kmem_cache_free(gfs2_inode_cachep, GFS2_I(inode));
 }
 
-static void gfs2_destroy_inode(struct inode *inode)
+extern void free_local_statfs_inodes(struct gfs2_sbd *sdp)
 {
-	call_rcu(&inode->i_rcu, gfs2_i_callback);
+	struct local_statfs_inode *lsi, *safe;
+
+	/* Run through the statfs inodes list to iput and free memory */
+	list_for_each_entry_safe(lsi, safe, &sdp->sd_sc_inodes_list, si_list) {
+		if (lsi->si_jid == sdp->sd_jdesc->jd_jid)
+			sdp->sd_sc_inode = NULL; /* belongs to this node */
+		if (lsi->si_sc_inode)
+			iput(lsi->si_sc_inode);
+		list_del(&lsi->si_list);
+		kfree(lsi);
+	}
+}
+
+extern struct inode *find_local_statfs_inode(struct gfs2_sbd *sdp,
+					     unsigned int index)
+{
+	struct local_statfs_inode *lsi;
+
+	/* Return the local (per node) statfs inode in the
+	 * sdp->sd_sc_inodes_list corresponding to the 'index'. */
+	list_for_each_entry(lsi, &sdp->sd_sc_inodes_list, si_list) {
+		if (lsi->si_jid == index)
+			return lsi->si_sc_inode;
+	}
+	return NULL;
 }
 
 const struct super_operations gfs2_super_ops = {
 	.alloc_inode		= gfs2_alloc_inode,
-	.destroy_inode		= gfs2_destroy_inode,
+	.free_inode		= gfs2_free_inode,
 	.write_inode		= gfs2_write_inode,
 	.dirty_inode		= gfs2_dirty_inode,
 	.evict_inode		= gfs2_evict_inode,
@@ -1761,7 +1520,6 @@
 	.freeze_super		= gfs2_freeze,
 	.thaw_super		= gfs2_unfreeze,
 	.statfs			= gfs2_statfs,
-	.remount_fs		= gfs2_remount_fs,
 	.drop_inode		= gfs2_drop_inode,
 	.show_options		= gfs2_show_options,
 };

--
Gitblit v1.6.2