Commit 33f1de69 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw:
  GFS2: Whitespace fixes
  GFS2: Remove unused sysfs file
  GFS2: Be extra careful about deallocating inodes
  GFS2: Remove no_formal_ino generating code
  GFS2: Rename eattr.[ch] as xattr.[ch]
  GFS2: Clean up of extended attribute support
  GFS2: Add explanation of extended attr on-disk format
  GFS2: Add "-o errors=panic|withdraw" mount options
  GFS2: jumping to wrong label?
  GFS2: free disk inode which is deleted by remote node -V2
  GFS2: Add a document explaining GFS2's uevents
  GFS2: Add sysfs link to device
  GFS2: Replace assertion with proper error handling
  GFS2: Improve error handling in inode allocation
  GFS2: Add some more info to uevents
  GFS2: Add online uevent to GFS2
parents 041d6d0b 86d00636
uevents and GFS2
==================
During the lifetime of a GFS2 mount, a number of uevents are generated.
This document explains what the events are and what they are used
for (by gfs_controld in gfs2-utils).
A list of GFS2 uevents
-----------------------
1. ADD
The ADD event occurs at mount time. It will always be the first
uevent generated by the newly created filesystem. If the mount
is successful, an ONLINE uevent will follow. If it is not successful
then a REMOVE uevent will follow.
The ADD uevent has two environment variables: SPECTATOR=[0|1]
and RDONLY=[0|1] that specify the spectator status (a read-only mount
with no journal assigned), and read-only (with journal assigned) status
of the filesystem respectively.
2. ONLINE
The ONLINE uevent is generated after a successful mount or remount. It
has the same environment variables as the ADD uevent. The ONLINE
uevent, along with the two environment variables for spectator and
RDONLY are a relatively recent addition (2.6.32-rc+) and will not
be generated by older kernels.
3. CHANGE
The CHANGE uevent is used in two places. One is when reporting the
successful mount of the filesystem by the first node (FIRSTMOUNT=Done).
This is used as a signal by gfs_controld that it is then ok for other
nodes in the cluster to mount the filesystem.
The other CHANGE uevent is used to inform of the completion
of journal recovery for one of the filesystems journals. It has
two environment variables, JID= which specifies the journal id which
has just been recovered, and RECOVERY=[Done|Failed] to indicate the
success (or otherwise) of the operation. These uevents are generated
for every journal recovered, whether it is during the initial mount
process or as the result of gfs_controld requesting a specific journal
recovery via the /sys/fs/gfs2/<fsname>/lock_module/recovery file.
Because the CHANGE uevent was used (in early versions of gfs_controld)
without checking the environment variables to discover the state, we
cannot add any more functions to it without running the risk of
someone using an older version of the user tools and breaking their
cluster. For this reason the ONLINE uevent was used when adding a new
uevent for a successful mount or remount.
4. OFFLINE
The OFFLINE uevent is only generated due to filesystem errors and is used
as part of the "withdraw" mechanism. Currently this doesn't give any
information about what the error is, which is something that needs to
be fixed.
5. REMOVE
The REMOVE uevent is generated at the end of an unsuccessful mount
or at the end of a umount of the filesystem. All REMOVE uevents will
have been preceeded by at least an ADD uevent for the same fileystem,
and unlike the other uevents is generated automatically by the kernel's
kobject subsystem.
Information common to all GFS2 uevents (uevent environment variables)
----------------------------------------------------------------------
1. LOCKTABLE=
The LOCKTABLE is a string, as supplied on the mount command
line (locktable=) or via fstab. It is used as a filesystem label
as well as providing the information for a lock_dlm mount to be
able to join the cluster.
2. LOCKPROTO=
The LOCKPROTO is a string, and its value depends on what is set
on the mount command line, or via fstab. It will be either
lock_nolock or lock_dlm. In the future other lock managers
may be supported.
3. JOURNALID=
If a journal is in use by the filesystem (journals are not
assigned for spectator mounts) then this will give the
numeric journal id in all GFS2 uevents.
4. UUID=
With recent versions of gfs2-utils, mkfs.gfs2 writes a UUID
into the filesystem superblock. If it exists, this will
be included in every uevent relating to the filesystem.
EXTRA_CFLAGS := -I$(src)
obj-$(CONFIG_GFS2_FS) += gfs2.o
gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \
gfs2-y := acl.o bmap.o dir.o xattr.o glock.o \
glops.o inode.o log.o lops.o main.o meta_io.o \
aops.o dentry.o export.o file.o \
ops_fstype.o ops_inode.o quota.o \
......
......@@ -19,8 +19,7 @@
#include "gfs2.h"
#include "incore.h"
#include "acl.h"
#include "eaops.h"
#include "eattr.h"
#include "xattr.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
......@@ -31,8 +30,7 @@
#define ACL_DEFAULT 0
int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
struct gfs2_ea_request *er,
int *remove, mode_t *mode)
struct gfs2_ea_request *er, int *remove, mode_t *mode)
{
struct posix_acl *acl;
int error;
......@@ -83,30 +81,20 @@ int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access)
return 0;
}
static int acl_get(struct gfs2_inode *ip, int access, struct posix_acl **acl,
struct gfs2_ea_location *el, char **data, unsigned int *len)
static int acl_get(struct gfs2_inode *ip, const char *name,
struct posix_acl **acl, struct gfs2_ea_location *el,
char **datap, unsigned int *lenp)
{
struct gfs2_ea_request er;
struct gfs2_ea_location el_this;
char *data;
unsigned int len;
int error;
el->el_bh = NULL;
if (!ip->i_eattr)
return 0;
memset(&er, 0, sizeof(struct gfs2_ea_request));
if (access) {
er.er_name = GFS2_POSIX_ACL_ACCESS;
er.er_name_len = GFS2_POSIX_ACL_ACCESS_LEN;
} else {
er.er_name = GFS2_POSIX_ACL_DEFAULT;
er.er_name_len = GFS2_POSIX_ACL_DEFAULT_LEN;
}
er.er_type = GFS2_EATYPE_SYS;
if (!el)
el = &el_this;
error = gfs2_ea_find(ip, &er, el);
error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, name, el);
if (error)
return error;
if (!el->el_ea)
......@@ -114,32 +102,31 @@ static int acl_get(struct gfs2_inode *ip, int access, struct posix_acl **acl,
if (!GFS2_EA_DATA_LEN(el->el_ea))
goto out;
er.er_data_len = GFS2_EA_DATA_LEN(el->el_ea);
er.er_data = kmalloc(er.er_data_len, GFP_NOFS);
len = GFS2_EA_DATA_LEN(el->el_ea);
data = kmalloc(len, GFP_NOFS);
error = -ENOMEM;
if (!er.er_data)
if (!data)
goto out;
error = gfs2_ea_get_copy(ip, el, er.er_data);
if (error)
error = gfs2_ea_get_copy(ip, el, data, len);
if (error < 0)
goto out_kfree;
error = 0;
if (acl) {
*acl = posix_acl_from_xattr(er.er_data, er.er_data_len);
*acl = posix_acl_from_xattr(data, len);
if (IS_ERR(*acl))
error = PTR_ERR(*acl);
}
out_kfree:
if (error || !data)
kfree(er.er_data);
else {
*data = er.er_data;
*len = er.er_data_len;
if (error || !datap) {
kfree(data);
} else {
*datap = data;
*lenp = len;
}
out:
if (error || el == &el_this)
brelse(el->el_bh);
return error;
}
......@@ -153,10 +140,12 @@ out:
int gfs2_check_acl(struct inode *inode, int mask)
{
struct gfs2_ea_location el;
struct posix_acl *acl = NULL;
int error;
error = acl_get(GFS2_I(inode), ACL_ACCESS, &acl, NULL, NULL, NULL);
error = acl_get(GFS2_I(inode), GFS2_POSIX_ACL_ACCESS, &acl, &el, NULL, NULL);
brelse(el.el_bh);
if (error)
return error;
......@@ -196,10 +185,12 @@ static int munge_mode(struct gfs2_inode *ip, mode_t mode)
int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
{
struct gfs2_ea_location el;
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct posix_acl *acl = NULL, *clone;
struct gfs2_ea_request er;
mode_t mode = ip->i_inode.i_mode;
char *data = NULL;
unsigned int len;
int error;
if (!sdp->sd_args.ar_posix_acl)
......@@ -207,11 +198,8 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
if (S_ISLNK(ip->i_inode.i_mode))
return 0;
memset(&er, 0, sizeof(struct gfs2_ea_request));
er.er_type = GFS2_EATYPE_SYS;
error = acl_get(dip, ACL_DEFAULT, &acl, NULL,
&er.er_data, &er.er_data_len);
error = acl_get(dip, GFS2_POSIX_ACL_DEFAULT, &acl, &el, &data, &len);
brelse(el.el_bh);
if (error)
return error;
if (!acl) {
......@@ -229,9 +217,8 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
acl = clone;
if (S_ISDIR(ip->i_inode.i_mode)) {
er.er_name = GFS2_POSIX_ACL_DEFAULT;
er.er_name_len = GFS2_POSIX_ACL_DEFAULT_LEN;
error = gfs2_system_eaops.eo_set(ip, &er);
error = gfs2_xattr_set(&ip->i_inode, GFS2_EATYPE_SYS,
GFS2_POSIX_ACL_DEFAULT, data, len, 0);
if (error)
goto out;
}
......@@ -239,21 +226,19 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
error = posix_acl_create_masq(acl, &mode);
if (error < 0)
goto out;
if (error > 0) {
er.er_name = GFS2_POSIX_ACL_ACCESS;
er.er_name_len = GFS2_POSIX_ACL_ACCESS_LEN;
posix_acl_to_xattr(acl, er.er_data, er.er_data_len);
er.er_mode = mode;
er.er_flags = GFS2_ERF_MODE;
error = gfs2_system_eaops.eo_set(ip, &er);
if (error)
goto out;
} else
munge_mode(ip, mode);
if (error == 0)
goto munge;
posix_acl_to_xattr(acl, data, len);
error = gfs2_xattr_set(&ip->i_inode, GFS2_EATYPE_SYS,
GFS2_POSIX_ACL_ACCESS, data, len, 0);
if (error)
goto out;
munge:
error = munge_mode(ip, mode);
out:
posix_acl_release(acl);
kfree(er.er_data);
kfree(data);
return error;
}
......@@ -265,9 +250,9 @@ int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
unsigned int len;
int error;
error = acl_get(ip, ACL_ACCESS, &acl, &el, &data, &len);
error = acl_get(ip, GFS2_POSIX_ACL_ACCESS, &acl, &el, &data, &len);
if (error)
return error;
goto out_brelse;
if (!acl)
return gfs2_setattr_simple(ip, attr);
......@@ -286,8 +271,9 @@ int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
out:
posix_acl_release(acl);
brelse(el.el_bh);
kfree(data);
out_brelse:
brelse(el.el_bh);
return error;
}
......@@ -107,8 +107,26 @@ static int gfs2_dhash(struct dentry *dentry, struct qstr *str)
return 0;
}
static int gfs2_dentry_delete(struct dentry *dentry)
{
struct gfs2_inode *ginode;
if (!dentry->d_inode)
return 0;
ginode = GFS2_I(dentry->d_inode);
if (!ginode->i_iopen_gh.gh_gl)
return 0;
if (test_bit(GLF_DEMOTE, &ginode->i_iopen_gh.gh_gl->gl_flags))
return 1;
return 0;
}
const struct dentry_operations gfs2_dops = {
.d_revalidate = gfs2_drevalidate,
.d_hash = gfs2_dhash,
.d_delete = gfs2_dentry_delete,
};
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2006 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/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/capability.h>
#include <linux/xattr.h>
#include <linux/gfs2_ondisk.h>
#include <asm/uaccess.h>
#include "gfs2.h"
#include "incore.h"
#include "acl.h"
#include "eaops.h"
#include "eattr.h"
#include "util.h"
/**
* gfs2_ea_name2type - get the type of the ea, and truncate type from the name
* @namep: ea name, possibly with type appended
*
* Returns: GFS2_EATYPE_XXX
*/
unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name)
{
unsigned int type;
if (strncmp(name, "system.", 7) == 0) {
type = GFS2_EATYPE_SYS;
if (truncated_name)
*truncated_name = name + sizeof("system.") - 1;
} else if (strncmp(name, "user.", 5) == 0) {
type = GFS2_EATYPE_USR;
if (truncated_name)
*truncated_name = name + sizeof("user.") - 1;
} else if (strncmp(name, "security.", 9) == 0) {
type = GFS2_EATYPE_SECURITY;
if (truncated_name)
*truncated_name = name + sizeof("security.") - 1;
} else {
type = GFS2_EATYPE_UNUSED;
if (truncated_name)
*truncated_name = NULL;
}
return type;
}
static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
{
if (!GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) &&
!GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
if (GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl == 0 &&
(GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) ||
GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)))
return -EOPNOTSUPP;
return gfs2_ea_get_i(ip, er);
}
static int system_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
{
int remove = 0;
int error;
if (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len)) {
if (!(er->er_flags & GFS2_ERF_MODE)) {
er->er_mode = ip->i_inode.i_mode;
er->er_flags |= GFS2_ERF_MODE;
}
error = gfs2_acl_validate_set(ip, 1, er,
&remove, &er->er_mode);
if (error)
return error;
error = gfs2_ea_set_i(ip, er);
if (error)
return error;
if (remove)
gfs2_ea_remove_i(ip, er);
return 0;
} else if (GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)) {
error = gfs2_acl_validate_set(ip, 0, er,
&remove, NULL);
if (error)
return error;
if (!remove)
error = gfs2_ea_set_i(ip, er);
else {
error = gfs2_ea_remove_i(ip, er);
if (error == -ENODATA)
error = 0;
}
return error;
}
return -EPERM;
}
static int system_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
{
if (GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len)) {
int error = gfs2_acl_validate_remove(ip, 1);
if (error)
return error;
} else if (GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)) {
int error = gfs2_acl_validate_remove(ip, 0);
if (error)
return error;
} else
return -EPERM;
return gfs2_ea_remove_i(ip, er);
}
static const struct gfs2_eattr_operations gfs2_user_eaops = {
.eo_get = gfs2_ea_get_i,
.eo_set = gfs2_ea_set_i,
.eo_remove = gfs2_ea_remove_i,
.eo_name = "user",
};
const struct gfs2_eattr_operations gfs2_system_eaops = {
.eo_get = system_eo_get,
.eo_set = system_eo_set,
.eo_remove = system_eo_remove,
.eo_name = "system",
};
static const struct gfs2_eattr_operations gfs2_security_eaops = {
.eo_get = gfs2_ea_get_i,
.eo_set = gfs2_ea_set_i,
.eo_remove = gfs2_ea_remove_i,
.eo_name = "security",
};
const struct gfs2_eattr_operations *gfs2_ea_ops[] = {
NULL,
&gfs2_user_eaops,
&gfs2_system_eaops,
&gfs2_security_eaops,
};
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2006 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.
*/
#ifndef __EAOPS_DOT_H__
#define __EAOPS_DOT_H__
struct gfs2_ea_request;
struct gfs2_inode;
struct gfs2_eattr_operations {
int (*eo_get) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
int (*eo_set) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
int (*eo_remove) (struct gfs2_inode *ip, struct gfs2_ea_request *er);
char *eo_name;
};
unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name);
extern const struct gfs2_eattr_operations gfs2_system_eaops;
extern const struct gfs2_eattr_operations *gfs2_ea_ops[];
#endif /* __EAOPS_DOT_H__ */
......@@ -143,17 +143,14 @@ static struct dentry *gfs2_get_parent(struct dentry *child)
}
static struct dentry *gfs2_get_dentry(struct super_block *sb,
struct gfs2_inum_host *inum)
struct gfs2_inum_host *inum)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_holder i_gh, ri_gh, rgd_gh;
struct gfs2_rgrpd *rgd;
struct gfs2_holder i_gh;
struct inode *inode;
struct dentry *dentry;
int error;
/* System files? */
inode = gfs2_ilookup(sb, inum->no_addr);
if (inode) {
if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
......@@ -168,29 +165,11 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
if (error)
return ERR_PTR(error);
error = gfs2_rindex_hold(sdp, &ri_gh);
error = gfs2_check_blk_type(sdp, inum->no_addr, GFS2_BLKST_DINODE);
if (error)
goto fail;
error = -EINVAL;
rgd = gfs2_blk2rgrpd(sdp, inum->no_addr);
if (!rgd)
goto fail_rindex;
error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
if (error)
goto fail_rindex;
error = -ESTALE;
if (gfs2_get_block_type(rgd, inum->no_addr) != GFS2_BLKST_DINODE)
goto fail_rgd;
gfs2_glock_dq_uninit(&rgd_gh);
gfs2_glock_dq_uninit(&ri_gh);
inode = gfs2_inode_lookup(sb, DT_UNKNOWN,
inum->no_addr,
0, 0);
inode = gfs2_inode_lookup(sb, DT_UNKNOWN, inum->no_addr, 0, 0);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
goto fail;
......@@ -224,13 +203,6 @@ out_inode:
if (!IS_ERR(dentry))
dentry->d_op = &gfs2_dops;
return dentry;
fail_rgd:
gfs2_glock_dq_uninit(&rgd_gh);
fail_rindex:
gfs2_glock_dq_uninit(&ri_gh);
fail:
gfs2_glock_dq_uninit(&i_gh);
return ERR_PTR(error);
......
......@@ -38,7 +38,6 @@
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "eaops.h"
/**
* gfs2_llseek - seek to a location in a file
......
......@@ -406,6 +406,12 @@ struct gfs2_statfs_change_host {
#define GFS2_DATA_WRITEBACK 1
#define GFS2_DATA_ORDERED 2
#define GFS2_ERRORS_DEFAULT GFS2_ERRORS_WITHDRAW
#define GFS2_ERRORS_WITHDRAW 0
#define GFS2_ERRORS_CONTINUE 1 /* place holder for future feature */
#define GFS2_ERRORS_RO 2 /* place holder for future feature */
#define GFS2_ERRORS_PANIC 3
struct gfs2_args {
char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */
char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */
......@@ -422,6 +428,7 @@ struct gfs2_args {
unsigned int ar_data:2; /* ordered/writeback */