Ocfs2 devel - Jun 2015 - [PATCH 1/4] ocfs2: export ocfs2_kset for online file check

When there are errors in the ocfs2 filesystem,
they are usually accompanied by the inode number which caused the error.
This inode number would be the input to fixing the file.
One of these options could be considered:
A file in the sys filesytem which would accept inode numbers.
This could be used to communication back what has to be fixed or is fixed.
You could write:
$# echo "CHECK <inode>" > /sys/fs/ocfs2/devname/filecheck
or
$# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck

Gang He (4):
  ocfs2: export ocfs2_kset for online file check
  ocfs2: sysfile interfaces for online file check
  ocfs2: create/remove sysfile for online file check
  ocfs2: check/fix inode block for online file check

 fs/ocfs2/Makefile      |   3 +-
 fs/ocfs2/filecheck.c   | 569 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/filecheck.h   |  48 +++++
 fs/ocfs2/inode.c       | 196 ++++++++++++++++-
 fs/ocfs2/inode.h       |   3 +
 fs/ocfs2/ocfs2_trace.h |   2 +
 fs/ocfs2/stackglue.c   |   3 +-
 fs/ocfs2/stackglue.h   |   2 +
 fs/ocfs2/super.c       |   5 +
 9 files changed, 823 insertions(+), 8 deletions(-)
 create mode 100644 fs/ocfs2/filecheck.c
 create mode 100644 fs/ocfs2/filecheck.h

-- 
2.1.2

Export ocfs2_kset object from ocfs2_stackglue kernel module,
then online file check code will create the related sysfiles
under ocfs2_kset object.

Signed-off-by: Gang He <ghe at suse.com>
Reviewed-by: Goldwyn Rodrigues <rgoldwyn at suse.de>
---
 fs/ocfs2/stackglue.c | 3 ++-
 fs/ocfs2/stackglue.h | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 5d965e8..13219ed 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -629,7 +629,8 @@ static struct attribute_group ocfs2_attr_group = {
 	.attrs = ocfs2_attrs,
 };
 
-static struct kset *ocfs2_kset;
+struct kset *ocfs2_kset;
+EXPORT_SYMBOL_GPL(ocfs2_kset);
 
 static void ocfs2_sysfs_exit(void)
 {
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 66334a3..f2dce10 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,4 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct
ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+extern struct kset *ocfs2_kset;
+
 #endif  /* STACKGLUE_H */
-- 
2.1.2

Implement online file check sysfile interfaces, e.g.
how to create the related sysfile according to device name,
how to display/handle file check request from the sysfile.

Signed-off-by: Gang He <ghe at suse.com>
Reviewed-by: Goldwyn Rodrigues <rgoldwyn at suse.de>
---
 fs/ocfs2/Makefile    |   3 +-
 fs/ocfs2/filecheck.c | 569 +++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/filecheck.h |  48 +++++
 fs/ocfs2/inode.h     |   3 +
 4 files changed, 622 insertions(+), 1 deletion(-)
 create mode 100644 fs/ocfs2/filecheck.c
 create mode 100644 fs/ocfs2/filecheck.h

diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index ce210d4..e27e652 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -41,7 +41,8 @@ ocfs2-objs := \
 	quota_local.o		\
 	quota_global.o		\
 	xattr.o			\
-	acl.o
+	acl.o	\
+	filecheck.o
 
 ocfs2_stackglue-objs := stackglue.o
 ocfs2_stack_o2cb-objs := stack_o2cb.o
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
new file mode 100644
index 0000000..3e68112
--- /dev/null
+++ b/fs/ocfs2/filecheck.c
@@ -0,0 +1,569 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.c
+ *
+ * Code which implements online file check.
+ *
+ * Copyright (C) 2007, 2009 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/sysctl.h>
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "ocfs2_fs.h"
+#include "stackglue.h"
+#include "inode.h"
+
+#include "filecheck.h"
+
+
+/* File check error strings,
+ * must correspond with error number in header file.
+ */
+static const char * const ocfs2_filecheck_errs[] = {
+	"SUCCESS",
+	"FAILED",
+	"INPROGRESS",
+	"READONLY",
+	"INVALIDINO",
+	"BLOCKECC",
+	"BLOCKNO",
+	"VALIDFLAG",
+	"GENERATION",
+	"UNSUPPORTED"
+};
+
+static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
+static LIST_HEAD(ocfs2_filecheck_sysfs_list);
+
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* File check entries are done in list */
+};
+
+struct ocfs2_filecheck_sysfs_entry {
+	struct list_head fs_list;
+	atomic_t fs_count;
+	struct super_block *fs_sb;
+	struct kset *fs_kset;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set file check options */
+};
+
+struct ocfs2_filecheck_entry {
+	struct list_head fe_list;
+	unsigned long fe_ino;
+	unsigned int fe_type;
+	unsigned short fe_done:1;
+	unsigned short fe_status:15;
+};
+
+struct ocfs2_filecheck_args {
+	unsigned int fa_type;
+	union {
+		unsigned long fa_ino;
+		unsigned int fa_len;
+	};
+};
+
+static const char *
+ocfs2_filecheck_error(int errno)
+{
+	if (!errno)
+		return ocfs2_filecheck_errs[errno];
+
+	BUG_ON(errno < OCFS2_FILECHECK_ERR_START ||
+			errno > OCFS2_FILECHECK_ERR_END);
+	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf);
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count);
+static struct kobj_attribute ocfs2_attr_filecheck +					__ATTR(filecheck,
S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+
+static int ocfs2_filecheck_sysfs_wait(atomic_t *p)
+{
+	schedule();
+	return 0;
+}
+
+static void
+ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	if (!atomic_dec_and_test(&entry->fs_count))
+		wait_on_atomic_t(&entry->fs_count, ocfs2_filecheck_sysfs_wait,
+						TASK_UNINTERRUPTIBLE);
+
+	spin_lock(&entry->fs_fcheck->fc_lock);
+	while (!list_empty(&entry->fs_fcheck->fc_head)) {
+		p = list_first_entry(&entry->fs_fcheck->fc_head,
+				struct ocfs2_filecheck_entry, fe_list);
+		list_del(&p->fe_list);
+		BUG_ON(!p->fe_done); /* To free a undone file check entry */
+		kfree(p);
+	}
+	spin_unlock(&entry->fs_fcheck->fc_lock);
+
+	kset_unregister(entry->fs_kset);
+	kfree(entry->fs_fcheck);
+	kfree(entry);
+}
+
+static void
+ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+}
+
+static int ocfs2_filecheck_sysfs_del(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			list_del(&p->fs_list);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			ocfs2_filecheck_sysfs_free(p);
+			return 0;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return 1;
+}
+
+static void
+ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	if (atomic_dec_and_test(&entry->fs_count))
+		wake_up_atomic_t(&entry->fs_count);
+}
+
+static struct ocfs2_filecheck_sysfs_entry *
+ocfs2_filecheck_sysfs_get(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p = NULL;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			atomic_inc(&p->fs_count);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			return p;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return NULL;
+}
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb)
+{
+	int ret = 0;
+	struct kset *ocfs2_filecheck_kset = NULL;
+	struct ocfs2_filecheck *fcheck = NULL;
+	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
+	struct attribute **attrs = NULL;
+	struct attribute_group attrgp;
+
+	if (!ocfs2_kset)
+		return -ENOMEM;
+
+	attrs = kmalloc(sizeof(struct attribute *) * 2, GFP_NOFS);
+	if (!attrs) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		attrs[0] = &ocfs2_attr_filecheck.attr;
+		attrs[1] = NULL;
+		memset(&attrgp, 0, sizeof(attrgp));
+		attrgp.attrs = attrs;
+	}
+
+	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
+	if (!fcheck) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		INIT_LIST_HEAD(&fcheck->fc_head);
+		spin_lock_init(&fcheck->fc_lock);
+		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+		fcheck->fc_size = 0;
+		fcheck->fc_done = 0;
+	}
+
+	if (strlen(sb->s_id) <= 0) {
+		mlog(ML_ERROR,
+		"Cannot get device basename when create filecheck sysfs\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	ocfs2_filecheck_kset = kset_create_and_add(sb->s_id, NULL,
+						&ocfs2_kset->kobj);
+	if (!ocfs2_filecheck_kset) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = sysfs_create_group(&ocfs2_filecheck_kset->kobj, &attrgp);
+	if (ret)
+		goto error;
+
+	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		atomic_set(&entry->fs_count, 1);
+		entry->fs_sb = sb;
+		entry->fs_kset = ocfs2_filecheck_kset;
+		entry->fs_fcheck = fcheck;
+		ocfs2_filecheck_sysfs_add(entry);
+	}
+
+	kfree(attrs);
+	return 0;
+
+error:
+	kfree(attrs);
+	kfree(entry);
+	kfree(fcheck);
+	kset_unregister(ocfs2_filecheck_kset);
+	return ret;
+}
+
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+{
+	return ocfs2_filecheck_sysfs_del(sb->s_id);
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned int count);
+static int
+ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned int len)
+{
+	int ret;
+
+	if ((len < OCFS2_FILECHECK_MINSIZE) || (len > OCFS2_FILECHECK_MAXSIZE))
+		return -EINVAL;
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done))
{
+		mlog(ML_ERROR,
+		"Cannot set online file check maximum entry number "
+		"to %u due to too much pending entries(%u)\n",
+		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
+		ret = -EBUSY;
+	} else {
+		if (len < ent->fs_fcheck->fc_size)
+			BUG_ON(!ocfs2_filecheck_erase_entries(ent,
+				ent->fs_fcheck->fc_size - len));
+
+		ent->fs_fcheck->fc_max = len;
+		ret = 0;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	return ret;
+}
+
+#define OCFS2_FILECHECK_ARGS_LEN	32
+static int
+ocfs2_filecheck_args_get_long(const char *buf, size_t count,
+				unsigned long *val)
+{
+	char buffer[OCFS2_FILECHECK_ARGS_LEN];
+
+	if (count < 1)
+		return 1;
+
+	memcpy(buffer, buf, count);
+	buffer[count] = '\0';
+
+	if (kstrtoul(buffer, 0, val))
+		return 1;
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_args_parse(const char *buf, size_t count,
+				struct ocfs2_filecheck_args *args)
+{
+	unsigned long val = 0;
+
+	/* too short/long args length */
+	if ((count < 5) || (count > OCFS2_FILECHECK_ARGS_LEN))
+		return 1;
+
+	if ((strncmp(buf, "FIX ", 4) == 0) ||
+		(strncmp(buf, "fix ", 4) == 0)) {
+		if (ocfs2_filecheck_args_get_long(buf + 4, count - 4, &val))
+			return 1;
+
+		args->fa_type = OCFS2_FILECHECK_TYPE_FIX;
+		args->fa_ino = val;
+		return 0;
+	} else if ((strncmp(buf, "CHECK ", 6) == 0) ||
+		(strncmp(buf, "check ", 6) == 0)) {
+		if (ocfs2_filecheck_args_get_long(buf + 6, count - 6, &val))
+			return 1;
+
+		args->fa_type = OCFS2_FILECHECK_TYPE_CHK;
+		args->fa_ino = val;
+		return 0;
+	} else if ((strncmp(buf, "SET ", 4) == 0) ||
+		(strncmp(buf, "set ", 4) == 0)) {
+		if (ocfs2_filecheck_args_get_long(buf + 4, count - 4, &val))
+			return 1;
+
+		args->fa_type = OCFS2_FILECHECK_TYPE_SET;
+		args->fa_len = (unsigned int)val;
+		return 0;
+	} else { /* invalid args */
+		return 1;
+	}
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf)
+{
+
+	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
+	struct ocfs2_filecheck_entry *p;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->name);
+		return -ENODEV;
+	}
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	ret = snprintf(buf, remain, "INO\t\tTYPE\tDONE\tERROR\n");
+	total += ret;
+	remain -= ret;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		ret = snprintf(buf + total, remain, "%lu\t\t%u\t%u\t%s\n",
+			p->fe_ino, p->fe_type, p->fe_done,
+			ocfs2_filecheck_error(p->fe_status));
+		if (ret < 0) {
+			total = ret;
+			break;
+		}
+		if (ret == remain) {
+			/* snprintf() didn't fit */
+			total = -E2BIG;
+			break;
+		}
+		total += ret;
+		remain -= ret;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	ocfs2_filecheck_sysfs_put(ent);
+	return total;
+}
+
+static int
+ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (p->fe_done) {
+			list_del(&p->fe_list);
+			kfree(p);
+			ent->fs_fcheck->fc_size--;
+			ent->fs_fcheck->fc_done--;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned int count)
+{
+	unsigned int i = 0;
+	unsigned int ret = 0;
+
+	while (i++ < count) {
+		if (ocfs2_filecheck_erase_entry(ent))
+			ret++;
+		else
+			break;
+	}
+
+	return (ret == count ? 1 : 0);
+}
+
+static void
+ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				struct ocfs2_filecheck_entry *entry)
+{
+	entry->fe_done = 1;
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	ent->fs_fcheck->fc_done++;
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+}
+
+static unsigned short
+ocfs2_filecheck_handle(struct super_block *sb,
+				unsigned long ino, unsigned int flags)
+{
+	unsigned short ret = OCFS2_FILECHECK_ERR_SUCCESS;
+	struct inode *inode = NULL;
+	int rc;
+
+	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	if (IS_ERR(inode)) {
+		rc = (int)(-(long)inode);
+		if (rc >= OCFS2_FILECHECK_ERR_START &&
+			rc < OCFS2_FILECHECK_ERR_END)
+			ret = rc;
+		else
+			ret = OCFS2_FILECHECK_ERR_FAILED;
+	} else
+		iput(inode);
+
+	return ret;
+}
+
+static void
+ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				struct ocfs2_filecheck_entry *entry)
+{
+	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
+	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
+	else
+		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
+
+	ocfs2_filecheck_done_entry(ent, entry);
+}
+
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct ocfs2_filecheck_args args;
+	struct ocfs2_filecheck_entry *entry = NULL;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+	ssize_t ret = 0;
+
+	if (count == 0)
+		return count;
+
+	if (ocfs2_filecheck_args_parse(buf, count, &args)) {
+		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+		return -EINVAL;
+	}
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->name);
+		return -ENODEV;
+	}
+
+	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
+		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
+		ocfs2_filecheck_sysfs_put(ent);
+		return (!ret ? count : ret);
+	}
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max)
&&
+		(ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_ERROR,
+		"Online file check queue(%u) is full\n",
+		ent->fs_fcheck->fc_max);
+		ret = -EBUSY;
+	} else {
+		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max)
&&
+			(ent->fs_fcheck->fc_done > 0)) {
+			/* Delete the oldest entry which was done,
+			 * make sure the entry size in list does
+			 * not exceed maximum value
+			 */
+			BUG_ON(!ocfs2_filecheck_erase_entry(ent));
+		}
+
+		entry = kmalloc(sizeof(struct ocfs2_filecheck_entry), GFP_NOFS);
+		if (entry) {
+			entry->fe_ino = args.fa_ino;
+			entry->fe_type = args.fa_type;
+			entry->fe_done = 0;
+			entry->fe_status = OCFS2_FILECHECK_ERR_INPROGRESS;
+			list_add_tail(&entry->fe_list,
+					&ent->fs_fcheck->fc_head);
+
+			ent->fs_fcheck->fc_size++;
+			ret = count;
+		} else {
+			ret = -ENOMEM;
+		}
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	if (entry)
+		ocfs2_filecheck_handle_entry(ent, entry);
+
+	ocfs2_filecheck_sysfs_put(ent);
+	return ret;
+}
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
new file mode 100644
index 0000000..c65fee9
--- /dev/null
+++ b/fs/ocfs2/filecheck.h
@@ -0,0 +1,48 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.h
+ *
+ * Online file check.
+ *
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+
+#ifndef FILECHECK_H
+#define FILECHECK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+
+/* File check errno */
+enum {
+	OCFS2_FILECHECK_ERR_SUCCESS = 0,	/* Success */
+	OCFS2_FILECHECK_ERR_FAILED = 1000,	/* Other failure */
+	OCFS2_FILECHECK_ERR_INPROGRESS,		/* In progress */
+	OCFS2_FILECHECK_ERR_READONLY,		/* Read only */
+	OCFS2_FILECHECK_ERR_INVALIDINO,		/* Invalid ino */
+	OCFS2_FILECHECK_ERR_BLOCKECC,		/* Block ecc */
+	OCFS2_FILECHECK_ERR_BLOCKNO,		/* Block number */
+	OCFS2_FILECHECK_ERR_VALIDFLAG,		/* Inode valid flag */
+	OCFS2_FILECHECK_ERR_GENERATION,		/* Inode generation */
+	OCFS2_FILECHECK_ERR_UNSUPPORTED		/* Unsupported */
+};
+
+#define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
+#define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb);
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+
+#endif  /* FILECHECK_H */
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 5e86b24..abd1018 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -139,6 +139,9 @@ int ocfs2_drop_inode(struct inode *inode);
 /* Flags for ocfs2_iget() */
 #define OCFS2_FI_FLAG_SYSFILE		0x1
 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY	0x2
+#define OCFS2_FI_FLAG_FILECHECK_CHK	0x4
+#define OCFS2_FI_FLAG_FILECHECK_FIX	0x8
+
 struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
-- 
2.1.2

Create online file check sysfile when ocfs2 mount,
remove the related sysfile when ocfs2 umount.

Signed-off-by: Gang He <ghe at suse.com>
Reviewed-by: Goldwyn Rodrigues <rgoldwyn at suse.de>
---
 fs/ocfs2/super.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 403c566..7213a94 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -74,6 +74,7 @@
 #include "suballoc.h"
 
 #include "buffer_head_io.h"
+#include "filecheck.h"
 
 static struct kmem_cache *ocfs2_inode_cachep;
 struct kmem_cache *ocfs2_dquot_cachep;
@@ -1202,6 +1203,9 @@ static int ocfs2_fill_super(struct super_block *sb, void
*data, int silent)
 	/* Start this when the mount is almost sure of being successful */
 	ocfs2_orphan_scan_start(osb);
 
+	/* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */
+	ocfs2_filecheck_create_sysfs(sb);
+
 	return status;
 
 read_super_error:
@@ -1658,6 +1662,7 @@ static void ocfs2_put_super(struct super_block *sb)
 
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
+	ocfs2_filecheck_remove_sysfs(sb);
 }
 
 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
-- 
2.1.2

Implement online check or fix inode block during
reading a inode block to memory.

Signed-off-by: Gang He <ghe at suse.com>
Reviewed-by: Goldwyn Rodrigues <rgoldwyn at suse.de>
---
 fs/ocfs2/inode.c       | 196 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/ocfs2/ocfs2_trace.h |   2 +
 2 files changed, 192 insertions(+), 6 deletions(-)

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index b254416..d811698 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -53,6 +53,7 @@
 #include "xattr.h"
 #include "refcounttree.h"
 #include "ocfs2_trace.h"
+#include "filecheck.h"
 
 #include "buffer_head_io.h"
 
@@ -74,6 +75,13 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 				    struct inode *inode,
 				    struct buffer_head *fe_bh);
 
+static int ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+			struct buffer_head **bh, int flags, int type);
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+			struct buffer_head *bh);
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+			struct buffer_head *bh);
+
 void ocfs2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = OCFS2_I(inode)->ip_attr;
@@ -127,6 +135,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64
blkno)
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 			 int sysfile_type)
 {
+	int rc = 0;
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
@@ -161,12 +170,17 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64
blkno, unsigned flags,
 	}
 	trace_ocfs2_iget5_locked(inode->i_state);
 	if (inode->i_state & I_NEW) {
-		ocfs2_read_locked_inode(inode, &args);
+		rc = ocfs2_read_locked_inode(inode, &args);
 		unlock_new_inode(inode);
 	}
 	if (is_bad_inode(inode)) {
 		iput(inode);
-		inode = ERR_PTR(-ESTALE);
+		if ((flags & OCFS2_FI_FLAG_FILECHECK_CHK) ||
+			(flags & OCFS2_FI_FLAG_FILECHECK_FIX))
+			/* Return OCFS2_FILECHECK_ERR_XXX related errno */
+			inode = ERR_PTR(rc);
+		else
+			inode = ERR_PTR(-ESTALE);
 		goto bail;
 	}
 
@@ -494,16 +508,32 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 	}
 
 	if (can_lock) {
-		status = ocfs2_read_inode_block_full(inode, &bh,
-						     OCFS2_BH_IGNORE_CACHE);
+		if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 0);
+		else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 1);
+		else
+			status = ocfs2_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE);
 	} else {
 		status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
 		/*
 		 * If buffer is in jbd, then its checksum may not have been
 		 * computed as yet.
 		 */
-		if (!status && !buffer_jbd(bh))
-			status = ocfs2_validate_inode_block(osb->sb, bh);
+		if (!status && !buffer_jbd(bh)) {
+			if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+				status = ocfs2_filecheck_validate_inode_block(
+								osb->sb, bh);
+			else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+				status = ocfs2_filecheck_repair_inode_block(
+								osb->sb, bh);
+			else
+				status = ocfs2_validate_inode_block(
+								osb->sb, bh);
+		}
 	}
 	if (status < 0) {
 		mlog_errno(status);
@@ -531,6 +561,14 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 
 	BUG_ON(args->fi_blkno != le64_to_cpu(fe->i_blkno));
 
+	if (buffer_dirty(bh)) {
+		status = ocfs2_write_block(osb, bh, INODE_CACHE(inode));
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = 0;
 
 bail:
@@ -1385,6 +1423,152 @@ bail:
 	return rc;
 }
 
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+			       struct buffer_head *bh)
+{
+	int rc = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	trace_ocfs2_filecheck_validate_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	if (!OCFS2_IS_VALID_DINODE(di)) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: signature = %.*s\n",
+			(unsigned long long)bh->b_blocknr, 7, di->i_signature);
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
+		goto bail;
+	}
+
+	rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
+	if (rc) {
+		mlog(ML_ERROR,
+			"Filecheck: checksum failed for dinode %llu\n",
+			(unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_BLOCKECC;
+		goto bail;
+	}
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: i_blkno is %llu\n",
+			(unsigned long long)bh->b_blocknr,
+			(unsigned long long)le64_to_cpu(di->i_blkno));
+		rc = -OCFS2_FILECHECK_ERR_BLOCKNO;
+		goto bail;
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: OCFS2_VALID_FL not set\n",
+			(unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_VALIDFLAG;
+		goto bail;
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !+	    OCFS2_SB(sb)->fs_generation)
{
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: fs_generation is %u\n",
+			(unsigned long long)bh->b_blocknr,
+			le32_to_cpu(di->i_fs_generation));
+		rc = -OCFS2_FILECHECK_ERR_GENERATION;
+		goto bail;
+	}
+
+bail:
+	return rc;
+}
+
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+			       struct buffer_head *bh)
+{
+	int rc;
+	int changed = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	rc = ocfs2_filecheck_validate_inode_block(sb, bh);
+	/* Can't fix invalid inode block */
+	if (!rc || rc == -OCFS2_FILECHECK_ERR_INVALIDINO)
+		return rc;
+
+	trace_ocfs2_filecheck_repair_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	if (ocfs2_is_hard_readonly(OCFS2_SB(sb)) ||
+		ocfs2_is_soft_readonly(OCFS2_SB(sb))) {
+		mlog(ML_ERROR,
+			"Filecheck: try to repair dinode #%llu on readonly filesystem\n",
+			(unsigned long long)bh->b_blocknr);
+		return -OCFS2_FILECHECK_ERR_READONLY;
+	}
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		di->i_blkno = cpu_to_le64(bh->b_blocknr);
+		changed = 1;
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: i_blkno to %llu\n",
+			(unsigned long long)bh->b_blocknr,
+			(unsigned long long)le64_to_cpu(di->i_blkno));
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		di->i_flags |= cpu_to_le32(OCFS2_VALID_FL);
+		changed = 1;
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: OCFS2_VALID_FL is set\n",
+			(unsigned long long)bh->b_blocknr);
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !+	    OCFS2_SB(sb)->fs_generation)
{
+		di->i_fs_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+		changed = 1;
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: fs_generation to %u\n",
+			(unsigned long long)bh->b_blocknr,
+			le32_to_cpu(di->i_fs_generation));
+	}
+
+	if (changed ||
+		ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check)) {
+		ocfs2_compute_meta_ecc(sb, bh->b_data, &di->i_check);
+		mark_buffer_dirty(bh);
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: compute meta ecc\n",
+			(unsigned long long)bh->b_blocknr);
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+		struct buffer_head **bh, int flags, int type)
+{
+	int rc;
+	struct buffer_head *tmp = *bh;
+
+	if (!type) /* Check inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_validate_inode_block);
+	else /* Repair inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_repair_inode_block);
+
+	/* If ocfs2_read_blocks() got us a new bh, pass it up. */
+	if (!rc && !*bh)
+		*bh = tmp;
+
+	return rc;
+}
+
 int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh,
 				int flags)
 {
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b..d9205e0 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1540,6 +1540,8 @@ DEFINE_OCFS2_ULL_INT_EVENT(ocfs2_read_locked_inode);
 DEFINE_OCFS2_INT_INT_EVENT(ocfs2_check_orphan_recovery_state);
 
 DEFINE_OCFS2_ULL_EVENT(ocfs2_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_repair_inode_block);
 
 TRACE_EVENT(ocfs2_inode_is_valid_to_delete,
 	TP_PROTO(void *task, void *dc_task, unsigned long long ino,
-- 
2.1.2

Hi Gang,
Thank you and Goldwyn for posting this feature as well as its framework.
This patch set tries to fix inode related errors such as block no, valid
flag, generation, metaecc, etc. I think it may fit some cases but not all.
For example, valid flag not set readonly may be caused by an inode with
two entries, so I think it is not right to just reset it.
Moreover, in our environment, most readonly cases we have encountered are
related gd and entent tree/block. So do you have any consideration about
these cases?
For more details about gd and entent tree/block readonly cases, please
refer the previous mails:
https://oss.oracle.com/pipermail/ocfs2-devel/2015-April/010768.html
https://oss.oracle.com/pipermail/ocfs2-devel/2015-June/010873.html

Thanks,
Joseph

On 2015/6/24 13:24, Gang He wrote:
> When there are errors in the ocfs2 filesystem,
> they are usually accompanied by the inode number which caused the error.
> This inode number would be the input to fixing the file.
> One of these options could be considered:
> A file in the sys filesytem which would accept inode numbers.
> This could be used to communication back what has to be fixed or is fixed.
> You could write:
> $# echo "CHECK <inode>" >
/sys/fs/ocfs2/devname/filecheck
> or
> $# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck
> 
> Gang He (4):
>   ocfs2: export ocfs2_kset for online file check
>   ocfs2: sysfile interfaces for online file check
>   ocfs2: create/remove sysfile for online file check
>   ocfs2: check/fix inode block for online file check
> 
>  fs/ocfs2/Makefile      |   3 +-
>  fs/ocfs2/filecheck.c   | 569
+++++++++++++++++++++++++++++++++++++++++++++++++
>  fs/ocfs2/filecheck.h   |  48 +++++
>  fs/ocfs2/inode.c       | 196 ++++++++++++++++-
>  fs/ocfs2/inode.h       |   3 +
>  fs/ocfs2/ocfs2_trace.h |   2 +
>  fs/ocfs2/stackglue.c   |   3 +-
>  fs/ocfs2/stackglue.h   |   2 +
>  fs/ocfs2/super.c       |   5 +
>  9 files changed, 823 insertions(+), 8 deletions(-)
>  create mode 100644 fs/ocfs2/filecheck.c
>  create mode 100644 fs/ocfs2/filecheck.h
>

On Wed, 24 Jun 2015 13:24:17 +0800 Gang He <ghe at suse.com> wrote:
> When there are errors in the ocfs2 filesystem,
> they are usually accompanied by the inode number which caused the error.
> This inode number would be the input to fixing the file.
> One of these options could be considered:
> A file in the sys filesytem which would accept inode numbers.
> This could be used to communication back what has to be fixed or is fixed.
> You could write:
> $# echo "CHECK <inode>" >
/sys/fs/ocfs2/devname/filecheck
> or
> $# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck
This is a userspace feature so it should have user documentation. 
Documentation/filesystems/ocfs2.txt is presumably the appropriate
place.

And the availability of the complete user documentation will make the
review of this patchset more productive.