summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-09-14 14:35:56 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-09-14 14:35:56 -0700
commit33f1de69312432baecb997a570b7d77c4d02d1ed (patch)
tree24e9e7487ec3b892e120409aa2ac1b1263794373
parent041d6d0be82bed7e0b87181dba5d10b8ab14afd9 (diff)
parent86d006365610fe6cda243d89b67d5047dca44656 (diff)
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
-rw-r--r--Documentation/filesystems/gfs2-uevents.txt100
-rw-r--r--fs/gfs2/Makefile2
-rw-r--r--fs/gfs2/acl.c106
-rw-r--r--fs/gfs2/dentry.c18
-rw-r--r--fs/gfs2/eaops.c157
-rw-r--r--fs/gfs2/eaops.h30
-rw-r--r--fs/gfs2/export.c36
-rw-r--r--fs/gfs2/file.c1
-rw-r--r--fs/gfs2/incore.h15
-rw-r--r--fs/gfs2/inode.c159
-rw-r--r--fs/gfs2/ops_fstype.c66
-rw-r--r--fs/gfs2/ops_inode.c82
-rw-r--r--fs/gfs2/rgrp.c82
-rw-r--r--fs/gfs2/rgrp.h6
-rw-r--r--fs/gfs2/super.c46
-rw-r--r--fs/gfs2/super.h5
-rw-r--r--fs/gfs2/sys.c31
-rw-r--r--fs/gfs2/util.c41
-rw-r--r--fs/gfs2/xattr.c (renamed from fs/gfs2/eattr.c)425
-rw-r--r--fs/gfs2/xattr.h (renamed from fs/gfs2/eattr.h)54
-rw-r--r--include/linux/gfs2_ondisk.h22
21 files changed, 678 insertions, 806 deletions
diff --git a/Documentation/filesystems/gfs2-uevents.txt b/Documentation/filesystems/gfs2-uevents.txt
new file mode 100644
index 000000000000..fd966dc9979a
--- /dev/null
+++ b/Documentation/filesystems/gfs2-uevents.txt
@@ -0,0 +1,100 @@
+ 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.
+
+
+
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index 3da2f1f4f738..21f7e46da4c0 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,6 +1,6 @@
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 \
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index fa881bdc3d85..3fc4e3ac7d84 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -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;
}
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 022c66cd5606..91beddadd388 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -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,
};
diff --git a/fs/gfs2/eaops.c b/fs/gfs2/eaops.c
deleted file mode 100644
index dee9b03e5b37..000000000000
--- a/fs/gfs2/eaops.c
+++ /dev/null
@@ -1,157 +0,0 @@
-/*
- * 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,
-};
-
diff --git a/fs/gfs2/eaops.h b/fs/gfs2/eaops.h
deleted file mode 100644
index da2f7fbbb40d..000000000000
--- a/fs/gfs2/eaops.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * 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__ */
-
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 9200ef221716..d15876e9aa26 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -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);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 73318a3ce6f1..166f38fbd246 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -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
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 61801ada36f0..6edb423f90b3 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -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 */
unsigned int ar_meta:1; /* mount metafs */
unsigned int ar_discard:1; /* discard requests */
+ unsigned int ar_errors:2; /* errors=withdraw | panic */
int ar_commit; /* Commit interval */
};
@@ -489,7 +496,6 @@ struct gfs2_sb_host {
*/
struct lm_lockstruct {
- u32 ls_id;
unsigned int ls_jid;
unsigned int ls_first;
unsigned int ls_first_done;
@@ -541,18 +547,12 @@ struct gfs2_sbd {
struct dentry *sd_root_dir;
struct inode *sd_jindex;
- struct inode *sd_inum_inode;
struct inode *sd_statfs_inode;
- struct inode *sd_ir_inode;
struct inode *sd_sc_inode;
struct inode *sd_qc_inode;
struct inode *sd_rindex;
struct inode *sd_quota_inode;
- /* Inum stuff */
-
- struct mutex sd_inum_mutex;
-
/* StatFS stuff */
spinlock_t sd_statfs_spin;
@@ -580,7 +580,6 @@ struct gfs2_sbd {
struct gfs2_holder sd_journal_gh;
struct gfs2_holder sd_jinode_gh;
- struct gfs2_holder sd_ir_gh;
struct gfs2_holder sd_sc_gh;
struct gfs2_holder sd_qc_gh;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 2f94bd723698..fb15d3b1f409 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -24,7 +24,7 @@
#include "acl.h"
#include "bmap.h"
#include "dir.h"
-#include "eattr.h"
+#include "xattr.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
@@ -519,139 +519,6 @@ out:
return inode ? inode : ERR_PTR(error);
}
-static void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf)
-{
- const struct gfs2_inum_range *str = buf;
-
- ir->ir_start = be64_to_cpu(str->ir_start);
- ir->ir_length = be64_to_cpu(str->ir_length);
-}
-
-static void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf)
-{
- struct gfs2_inum_range *str = buf;
-
- str->ir_start = cpu_to_be64(ir->ir_start);
- str->ir_length = cpu_to_be64(ir->ir_length);
-}
-
-static int pick_formal_ino_1(struct gfs2_sbd *sdp, u64 *formal_ino)
-{
- struct gfs2_inode *ip = GFS2_I(sdp->sd_ir_inode);
- struct buffer_head *bh;
- struct gfs2_inum_range_host ir;
- int error;
-
- error = gfs2_trans_begin(sdp, RES_DINODE, 0);
- if (error)
- return error;
- mutex_lock(&sdp->sd_inum_mutex);
-
- error = gfs2_meta_inode_buffer(ip, &bh);
- if (error) {
- mutex_unlock(&sdp->sd_inum_mutex);
- gfs2_trans_end(sdp);
- return error;
- }
-
- gfs2_inum_range_in(&ir, bh->b_data + sizeof(struct gfs2_dinode));
-
- if (ir.ir_length) {
- *formal_ino = ir.ir_start++;
- ir.ir_length--;
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
- gfs2_inum_range_out(&ir,
- bh->b_data + sizeof(struct gfs2_dinode));
- brelse(bh);
- mutex_unlock(&sdp->sd_inum_mutex);
- gfs2_trans_end(sdp);
- return 0;
- }
-
- brelse(bh);
-
- mutex_unlock(&sdp->sd_inum_mutex);
- gfs2_trans_end(sdp);
-
- return 1;
-}
-
-static int pick_formal_ino_2(struct gfs2_sbd *sdp, u64 *formal_ino)
-{
- struct gfs2_inode *ip = GFS2_I(sdp->sd_ir_inode);
- struct gfs2_inode *m_ip = GFS2_I(sdp->sd_inum_inode);
- struct gfs2_holder gh;
- struct buffer_head *bh;
- struct gfs2_inum_range_host ir;
- int error;
-
- error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
- if (error)
- return error;
-
- error = gfs2_trans_begin(sdp, 2 * RES_DINODE, 0);
- if (error)
- goto out;
- mutex_lock(&sdp->sd_inum_mutex);
-
- error = gfs2_meta_inode_buffer(ip, &bh);
- if (error)
- goto out_end_trans;
-
- gfs2_inum_range_in(&ir, bh->b_data + sizeof(struct gfs2_dinode));
-
- if (!ir.ir_length) {
- struct buffer_head *m_bh;
- u64 x, y;
- __be64 z;
-
- error = gfs2_meta_inode_buffer(m_ip, &m_bh);
- if (error)
- goto out_brelse;
-
- z = *(__be64 *)(m_bh->b_data + sizeof(struct gfs2_dinode));
- x = y = be64_to_cpu(z);
- ir.ir_start = x;
- ir.ir_length = GFS2_INUM_QUANTUM;
- x += GFS2_INUM_QUANTUM;
- if (x < y)
- gfs2_consist_inode(m_ip);
- z = cpu_to_be64(x);
- gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
- *(__be64 *)(m_bh->b_data + sizeof(struct gfs2_dinode)) = z;
-
- brelse(m_bh);
- }
-
- *formal_ino = ir.ir_start++;
- ir.ir_length--;
-
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
- gfs2_inum_range_out(&ir, bh->b_data + sizeof(struct gfs2_dinode));
-
-out_brelse:
- brelse(bh);
-out_end_trans:
- mutex_unlock(&sdp->sd_inum_mutex);
- gfs2_trans_end(sdp);
-out:
- gfs2_glock_dq_uninit(&gh);
- return error;
-}
-
-static int pick_formal_ino(struct gfs2_sbd *sdp, u64 *inum)
-{
- int error;
-
- error = pick_formal_ino_1(sdp, inum);
- if (error <= 0)
- return error;
-
- error = pick_formal_ino_2(sdp, inum);
-
- return error;
-}
-
/**
* create_ok - OK to create a new on-disk inode here?
* @dip: Directory in which dinode is to be created
@@ -731,7 +598,7 @@ static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
if (error)
goto out_ipreserv;
- *no_addr = gfs2_alloc_di(dip, generation);
+ error = gfs2_alloc_di(dip, no_addr, generation);
gfs2_trans_end(sdp);
@@ -924,7 +791,6 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
size_t len;
void *value;
char *name;
- struct gfs2_ea_request er;
err = security_inode_init_security(&ip->i_inode, &dip->i_inode,
&name, &value, &len);
@@ -935,16 +801,7 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
return err;
}
- memset(&er, 0, sizeof(struct gfs2_ea_request));
-
- er.er_type = GFS2_EATYPE_SECURITY;
- er.er_name = name;
- er.er_data = value;
- er.er_name_len = strlen(name);
- er.er_data_len = len;
-
- err = gfs2_ea_set_i(ip, &er);
-
+ err = gfs2_xattr_set(&ip->i_inode, GFS2_EATYPE_SECURITY, name, value, len, 0);
kfree(value);
kfree(name);
@@ -991,13 +848,10 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
if (error)
goto fail_gunlock;
- error = pick_formal_ino(sdp, &inum.no_formal_ino);
- if (error)
- goto fail_gunlock;
-
error = alloc_dinode(dip, &inum.no_addr, &generation);
if (error)
goto fail_gunlock;
+ inum.no_formal_ino = generation;
error = gfs2_glock_nq_num(sdp, inum.no_addr, &gfs2_inode_glops,
LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
@@ -1008,9 +862,8 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
if (error)
goto fail_gunlock2;
- inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode),
- inum.no_addr,
- inum.no_formal_ino, 0);
+ inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
+ inum.no_formal_ino, 0);
if (IS_ERR(inode))
goto fail_gunlock2;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 7bc3c45cd676..52fb6c048981 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -84,7 +84,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
gfs2_tune_init(&sdp->sd_tune);
- mutex_init(&sdp->sd_inum_mutex);
spin_lock_init(&sdp->sd_statfs_spin);
spin_lock_init(&sdp->sd_rindex_spin);
@@ -833,21 +832,12 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
if (error)
goto fail;
- /* Read in the master inode number inode */
- sdp->sd_inum_inode = gfs2_lookup_simple(master, "inum");
- if (IS_ERR(sdp->sd_inum_inode)) {
- error = PTR_ERR(sdp->sd_inum_inode);
- fs_err(sdp, "can't read in inum inode: %d\n", error);
- goto fail_journal;
- }
-
-
/* Read in the master statfs inode */
sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
if (IS_ERR(sdp->sd_statfs_inode)) {
error = PTR_ERR(sdp->sd_statfs_inode);
fs_err(sdp, "can't read in statfs inode: %d\n", error);
- goto fail_inum;
+ goto fail_journal;
}
/* Read in the resource index inode */
@@ -876,8 +866,6 @@ fail_rindex:
iput(sdp->sd_rindex);
fail_statfs:
iput(sdp->sd_statfs_inode);
-fail_inum:
- iput(sdp->sd_inum_inode);
fail_journal:
init_journal(sdp, UNDO);
fail:
@@ -905,20 +893,12 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
return error;
}
- sprintf(buf, "inum_range%u", sdp->sd_jdesc->jd_jid);
- sdp->sd_ir_inode = gfs2_lookup_simple(pn, buf);
- if (IS_ERR(sdp->sd_ir_inode)) {
- error = PTR_ERR(sdp->sd_ir_inode);
- fs_err(sdp, "can't find local \"ir\" file: %d\n", error);
- goto fail;
- }
-
sprintf(buf, "statfs_change%u", sdp->sd_jdesc->jd_jid);
sdp->sd_sc_inode = gfs2_lookup_simple(pn, buf);
if (IS_ERR(sdp->sd_sc_inode)) {
error = PTR_ERR(sdp->sd_sc_inode);
fs_err(sdp, "can't find local \"sc\" file: %d\n", error);
- goto fail_ir_i;
+ goto fail;
}
sprintf(buf, "quota_change%u", sdp->sd_jdesc->jd_jid);
@@ -932,27 +912,16 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
iput(pn);
pn = NULL;
- ip = GFS2_I(sdp->sd_ir_inode);
- error = gfs2_glock_nq_init(ip->i_gl,
- LM_ST_EXCLUSIVE, 0,
- &sdp->sd_ir_gh);
- if (error) {
- fs_err(sdp, "can't lock local \"ir\" file: %d\n", error);
- goto fail_qc_i;
- }
-
ip = GFS2_I(sdp->sd_sc_inode);
- error = gfs2_glock_nq_init(ip->i_gl,
- LM_ST_EXCLUSIVE, 0,
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
&sdp->sd_sc_gh);
if (error) {
fs_err(sdp, "can't lock local \"sc\" file: %d\n", error);
- goto fail_ir_gh;
+ goto fail_qc_i;
}
ip = GFS2_I(sdp->sd_qc_inode);
- error = gfs2_glock_nq_init(ip->i_gl,
- LM_ST_EXCLUSIVE, 0,
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0,
&sdp->sd_qc_gh);
if (error) {
fs_err(sdp, "can't lock local \"qc\" file: %d\n", error);
@@ -965,14 +934,10 @@ fail_qc_gh:
gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
fail_ut_gh:
gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
-fail_ir_gh:
- gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
fail_qc_i:
iput(sdp->sd_qc_inode);
fail_ut_i:
iput(sdp->sd_sc_inode);
-fail_ir_i:
- iput(sdp->sd_ir_inode);
fail:
if (pn)
iput(pn);
@@ -1063,7 +1028,6 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
ls->ls_ops = lm;
ls->ls_first = 1;
- ls->ls_id = 0;
for (options = args->ar_hostdata; (o = strsep(&options, ":")); ) {
substring_t tmp[MAX_OPT_ARGS];
@@ -1081,10 +1045,7 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
ls->ls_jid = option;
break;
case Opt_id:
- ret = match_int(&tmp[0], &option);
- if (ret)
- goto hostdata_error;
- ls->ls_id = option;
+ /* Obsolete, but left for backward compat purposes */
break;
case Opt_first:
ret = match_int(&tmp[0], &option);
@@ -1133,6 +1094,17 @@ void gfs2_lm_unmount(struct gfs2_sbd *sdp)
lm->lm_unmount(sdp);
}
+void gfs2_online_uevent(struct gfs2_sbd *sdp)
+{
+ struct super_block *sb = sdp->sd_vfs;
+ char ro[20];
+ char spectator[20];
+ char *envp[] = { ro, spectator, NULL };
+ sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
+ sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);
+ kobject_uevent_env(&sdp->sd_kobj, KOBJ_ONLINE, envp);
+}
+
/**
* fill_super - Read in superblock
* @sb: The VFS superblock
@@ -1157,6 +1129,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT;
sdp->sd_args.ar_data = GFS2_DATA_DEFAULT;
sdp->sd_args.ar_commit = 60;
+ sdp->sd_args.ar_errors = GFS2_ERRORS_DEFAULT;
error = gfs2_mount_args(sdp, &sdp->sd_args, data);
if (error) {
@@ -1174,6 +1147,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
sb->s_magic = GFS2_MAGIC;
sb->s_op = &gfs2_super_ops;
sb->s_export_op = &gfs2_export_ops;
+ sb->s_xattr = gfs2_xattr_handlers;
sb->s_time_gran = 1;
sb->s_maxbytes = MAX_LFS_FILESIZE;
@@ -1236,7 +1210,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
}
gfs2_glock_dq_uninit(&mount_gh);
-
+ gfs2_online_uevent(sdp);
return 0;
fail_threads:
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index f8bd20baf99c..c3ac18054057 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -26,8 +26,7 @@
#include "acl.h"
#include "bmap.h"
#include "dir.h"
-#include "eaops.h"
-#include "eattr.h"
+#include "xattr.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
@@ -349,7 +348,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
if (error)
- goto out_rgrp;
+ goto out_gunlock;
error = gfs2_dir_del(dip, &dentry->d_name);
if (error)
@@ -1302,60 +1301,53 @@ static int gfs2_setxattr(struct dentry *dentry, const char *name,
const void *data, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
- struct gfs2_ea_request er;
-
- memset(&er, 0, sizeof(struct gfs2_ea_request));
- er.er_type = gfs2_ea_name2type(name, &er.er_name);
- if (er.er_type == GFS2_EATYPE_UNUSED)
- return -EOPNOTSUPP;
- er.er_data = (char *)data;
- er.er_name_len = strlen(er.er_name);
- er.er_data_len = size;
- er.er_flags = flags;
-
- gfs2_assert_warn(GFS2_SB(inode), !(er.er_flags & GFS2_ERF_MODE));
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
- return gfs2_ea_set(GFS2_I(inode), &er);
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (ret == 0) {
+ ret = generic_setxattr(dentry, name, data, size, flags);
+ gfs2_glock_dq(&gh);
+ }
+ gfs2_holder_uninit(&gh);
+ return ret;
}
static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
void *data, size_t size)
{
- struct gfs2_ea_request er;
-
- memset(&er, 0, sizeof(struct gfs2_ea_request));
- er.er_type = gfs2_ea_name2type(name, &er.er_name);
- if (er.er_type == GFS2_EATYPE_UNUSED)
- return -EOPNOTSUPP;
- er.er_data = data;
- er.er_name_len = strlen(er.er_name);
- er.er_data_len = size;
-
- return gfs2_ea_get(GFS2_I(dentry->d_inode), &er);
-}
-
-static ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
- struct gfs2_ea_request er;
-
- memset(&er, 0, sizeof(struct gfs2_ea_request));
- er.er_data = (size) ? buffer : NULL;
- er.er_data_len = size;
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
- return gfs2_ea_list(GFS2_I(dentry->d_inode), &er);
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (ret == 0) {
+ ret = generic_getxattr(dentry, name, data, size);
+ gfs2_glock_dq(&gh);
+ }
+ gfs2_holder_uninit(&gh);
+ return ret;
}
static int gfs2_removexattr(struct dentry *dentry, const char *name)
{
- struct gfs2_ea_request er;
-
- memset(&er, 0, sizeof(struct gfs2_ea_request));
- er.er_type = gfs2_ea_name2type(name, &er.er_name);
- if (er.er_type == GFS2_EATYPE_UNUSED)
- return -EOPNOTSUPP;
- er.er_name_len = strlen(er.er_name);
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
- return gfs2_ea_remove(GFS2_I(dentry->d_inode), &er);
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (ret == 0) {
+ ret = generic_removexattr(dentry, name);
+ gfs2_glock_dq(&gh);
+ }
+ gfs2_holder_uninit(&gh);
+ return ret;
}
static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index fba795798d3a..18d3a28554ac 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1256,7 +1256,7 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
* Returns: The block type (GFS2_BLKST_*)
*/
-unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block)
+static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block)
{
struct gfs2_bitmap *bi = NULL;
u32 length, rgrp_block, buf_block;
@@ -1459,6 +1459,16 @@ int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl)
return 0;
}
+static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd)
+{
+ struct gfs2_sbd *sdp = rgd->rd_sbd;
+ fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
+ (unsigned long long)rgd->rd_addr);
+ fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
+ gfs2_rgrp_dump(NULL, rgd->rd_gl);
+ rgd->rd_flags |= GFS2_RDF_ERROR;
+}
+
/**
* gfs2_alloc_block - Allocate one or more blocks
* @ip: the inode to allocate the block for
@@ -1520,22 +1530,20 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
return 0;
rgrp_error:
- fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
- (unsigned long long)rgd->rd_addr);
- fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
- gfs2_rgrp_dump(NULL, rgd->rd_gl);
- rgd->rd_flags |= GFS2_RDF_ERROR;
+ gfs2_rgrp_error(rgd);
return -EIO;
}
/**
* gfs2_alloc_di - Allocate a dinode
* @dip: the directory that the inode is going in
+ * @bn: the block number which is allocated
+ * @generation: the generation number of the inode
*
- * Returns: the block allocated
+ * Returns: 0 on success or error
*/
-u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
+int gfs2_alloc_di(struct gfs2_inode *dip, u64 *bn, u64 *generation)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_alloc *al = dip->i_alloc;
@@ -1546,16 +1554,21 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
blk = rgblk_search(rgd, rgd->rd_last_alloc,
GFS2_BLKST_FREE, GFS2_BLKST_DINODE, &n);
- BUG_ON(blk == BFITNOENT);
- rgd->rd_last_alloc = blk;
+ /* Since all blocks are reserved in advance, this shouldn't happen */
+ if (blk == BFITNOENT)
+ goto rgrp_error;
+ rgd->rd_last_alloc = blk;
block = rgd->rd_data0 + blk;
+ if (rgd->rd_free == 0)
+ goto rgrp_error;
- gfs2_assert_withdraw(sdp, rgd->rd_free);
rgd->rd_free--;
rgd->rd_dinodes++;
*generation = rgd->rd_igeneration++;
+ if (*generation == 0)
+ *generation = rgd->rd_igeneration++;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
@@ -1568,7 +1581,12 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
rgd->rd_free_clone--;
spin_unlock(&sdp->sd_rindex_spin);
trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE);
- return block;
+ *bn = block;
+ return 0;
+
+rgrp_error:
+ gfs2_rgrp_error(rgd);
+ return -EIO;
}
/**
@@ -1676,6 +1694,46 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
}
/**
+ * gfs2_check_blk_type - Check the type of a block
+ * @sdp: The superblock
+ * @no_addr: The block number to check
+ * @type: The block type we are looking for
+ *
+ * Returns: 0 if the block type matches the expected type
+ * -ESTALE if it doesn't match
+ * or -ve errno if something went wrong while checking
+ */
+
+int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
+{
+ struct gfs2_rgrpd *rgd;
+ struct gfs2_holder ri_gh, rgd_gh;
+ int error;
+
+ error = gfs2_rindex_hold(sdp, &ri_gh);
+ if (error)
+ goto fail;
+
+ error = -EINVAL;
+ rgd = gfs2_blk2rgrpd(sdp, 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;
+
+ if (gfs2_get_block_type(rgd, no_addr) != type)
+ error = -ESTALE;
+
+ gfs2_glock_dq_uninit(&rgd_gh);
+fail_rindex:
+ gfs2_glock_dq_uninit(&ri_gh);
+fail:
+ return error;
+}
+
+/**
* gfs2_rlist_add - add a RG to a list of RGs
* @sdp: the filesystem
* @rlist: the list of resource groups
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 1e76ff0f3e00..b4106ddaaa98 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -44,15 +44,15 @@ gfs2_inplace_reserve_i((ip), __FILE__, __LINE__)
extern void gfs2_inplace_release(struct gfs2_inode *ip);
-extern unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block);
-
extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
-extern u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation);
+extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);
extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
extern void gfs2_unlink_di(struct inode *inode);
+extern int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr,
+ unsigned int type);
struct gfs2_rgrp_list {
unsigned int rl_rgrps;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index f522bb017973..0ec3ec672de1 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -38,7 +38,7 @@
#include "trans.h"
#include "util.h"
#include "sys.h"
-#include "eattr.h"
+#include "xattr.h"
#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
@@ -68,6 +68,8 @@ enum {
Opt_discard,
Opt_nodiscard,
Opt_commit,
+ Opt_err_withdraw,
+ Opt_err_panic,
Opt_error,
};
@@ -97,6 +99,8 @@ static const match_table_t tokens = {
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_commit, "commit=%d"},
+ {Opt_err_withdraw, "errors=withdraw"},
+ {Opt_err_panic, "errors=panic"},
{Opt_error, NULL}
};
@@ -152,6 +156,11 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
args->ar_localcaching = 1;
break;
case Opt_debug:
+ if (args->ar_errors == GFS2_ERRORS_PANIC) {
+ fs_info(sdp, "-o debug and -o errors=panic "
+ "are mutually exclusive.\n");
+ return -EINVAL;
+ }
args->ar_debug = 1;
break;
case Opt_nodebug:
@@ -205,6 +214,17 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
return rv ? rv : -EINVAL;
}
break;
+ case Opt_err_withdraw:
+ args->ar_errors = GFS2_ERRORS_WITHDRAW;
+ break;
+ case Opt_err_panic:
+ if (args->ar_debug) {
+ fs_info(sdp, "-o debug and -o errors=panic "
+ "are mutually exclusive.\n");
+ return -EINVAL;
+ }
+ args->ar_errors = GFS2_ERRORS_PANIC;
+ break;
case Opt_error:
default:
fs_info(sdp, "invalid mount option: %s\n", o);
@@ -768,7 +788,6 @@ restart:
/* Release stuff */
iput(sdp->sd_jindex);
- iput(sdp->sd_inum_inode);
iput(sdp->sd_statfs_inode);
iput(sdp->sd_rindex);
iput(sdp->sd_quota_inode);
@@ -779,10 +798,8 @@ restart:
if (!sdp->sd_args.ar_spectator) {
gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
- gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
- iput(sdp->sd_ir_inode);
iput(sdp->sd_sc_inode);
iput(sdp->sd_qc_inode);
}
@@ -1084,6 +1101,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
gt->gt_log_flush_secs = args.ar_commit;
spin_unlock(&gt->gt_spin);
+ gfs2_online_uevent(sdp);
return 0;
}
@@ -1225,6 +1243,22 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
lfsecs = sdp->sd_tune.gt_log_flush_secs;
if (lfsecs != 60)
seq_printf(s, ",commit=%d", lfsecs);
+ if (args->ar_errors != GFS2_ERRORS_DEFAULT) {
+ const char *state;
+
+ switch (args->ar_errors) {
+ case GFS2_ERRORS_WITHDRAW:
+ state = "withdraw";
+ break;
+ case GFS2_ERRORS_PANIC:
+ state = "panic";
+ break;
+ default:
+ state = "unknown";
+ break;
+ }
+ seq_printf(s, ",errors=%s", state);
+ }
return 0;
}
@@ -1252,6 +1286,10 @@ static void gfs2_delete_inode(struct inode *inode)
goto out;
}
+ error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+ if (error)
+ goto out_truncate;
+
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);
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 22e0417ed996..235db3682885 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -25,7 +25,7 @@ static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
return x;
}
-void gfs2_jindex_free(struct gfs2_sbd *sdp);
+extern void gfs2_jindex_free(struct gfs2_sbd *sdp);
extern int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *data);
@@ -36,7 +36,7 @@ extern int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
struct gfs2_inode **ipp);
extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
-
+extern void gfs2_online_uevent(struct gfs2_sbd *sdp);
extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
s64 dinodes);
@@ -54,6 +54,7 @@ extern struct file_system_type gfs2meta_fs_type;
extern const struct export_operations gfs2_export_ops;
extern const struct super_operations gfs2_super_ops;
extern const struct dentry_operations gfs2_dops;
+extern struct xattr_handler *gfs2_xattr_handlers[];
#endif /* __SUPER_DOT_H__ */
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index a7cbfbd340c7..446329728d52 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -16,6 +16,7 @@
#include <linux/kobject.h>
#include <asm/uaccess.h>
#include <linux/gfs2_ondisk.h>
+#include <linux/genhd.h>
#include "gfs2.h"
#include "incore.h"
@@ -319,12 +320,6 @@ static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
return ret;
}
-static ssize_t lkid_show(struct gfs2_sbd *sdp, char *buf)
-{
- struct lm_lockstruct *ls = &sdp->sd_lockstruct;
- return sprintf(buf, "%u\n", ls->ls_id);
-}
-
static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf)
{
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
@@ -389,7 +384,6 @@ static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
GDLM_ATTR(proto_name, 0444, proto_name_show, NULL);
GDLM_ATTR(block, 0644, block_show, block_store);
GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store);
-GDLM_ATTR(id, 0444, lkid_show, NULL);
GDLM_ATTR(jid, 0444, jid_show, NULL);
GDLM_ATTR(first, 0444, lkfirst_show, NULL);
GDLM_ATTR(first_done, 0444, first_done_show, NULL);
@@ -401,7 +395,6 @@ static struct attribute *lock_module_attrs[] = {
&gdlm_attr_proto_name.attr,
&gdlm_attr_block.attr,
&gdlm_attr_withdraw.attr,
- &gdlm_attr_id.attr,
&gdlm_attr_jid.attr,
&gdlm_attr_first.attr,
&gdlm_attr_first_done.attr,
@@ -519,7 +512,14 @@ static struct attribute_group lock_module_group = {
int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
{
+ struct super_block *sb = sdp->sd_vfs;
int error;
+ char ro[20];
+ char spectator[20];
+ char *envp[] = { ro, spectator, NULL };
+
+ sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
+ sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);
sdp->sd_kobj.kset = gfs2_kset;
error = kobject_init_and_add(&sdp->sd_kobj, &gfs2_ktype, NULL,
@@ -535,9 +535,17 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
if (error)
goto fail_tune;
- kobject_uevent(&sdp->sd_kobj, KOBJ_ADD);
+ error = sysfs_create_link(&sdp->sd_kobj,
+ &disk_to_dev(sb->s_bdev->bd_disk)->kobj,
+ "device");
+ if (error)
+ goto fail_lock_module;
+
+ kobject_uevent_env(&sdp->sd_kobj, KOBJ_ADD, envp);
return 0;
+fail_lock_module:
+ sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
fail_tune:
sysfs_remove_group(&sdp->sd_kobj, &tune_group);
fail_reg:
@@ -549,12 +557,12 @@ fail:
void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
{
+ sysfs_remove_link(&sdp->sd_kobj, "device");
sysfs_remove_group(&sdp->sd_kobj, &tune_group);
sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
kobject_put(&sdp->sd_kobj);
}
-
static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
struct kobj_uevent_env *env)
{
@@ -563,6 +571,8 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
+ if (!sdp->sd_args.ar_spectator)
+ add_uevent_var(env, "JOURNALID=%u", sdp->sd_lockstruct.ls_jid);
if (gfs2_uuid_valid(uuid)) {
add_uevent_var(env, "UUID=%02X%02X%02X%02X-%02X%02X-%02X%02X-"
"%02X%02X-%02X%02X%02X%02X%02X%02X",
@@ -578,7 +588,6 @@ static struct kset_uevent_ops gfs2_uevent_ops = {
.uevent = gfs2_uevent,
};
-
int gfs2_sys_init(void)
{
gfs2_kset = kset_create_and_add("gfs2", &gfs2_uevent_ops, fs_kobj);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 9d12b1118ba0..f6a7efa34eb9 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -38,24 +38,30 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, char *fmt, ...)
const struct lm_lockops *lm = ls->ls_ops;
va_list args;
- if (test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+ if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
+ test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
return 0;
va_start(args, fmt);
vprintk(fmt, args);
va_end(args);
- fs_err(sdp, "about to withdraw this file system\n");
- BUG_ON(sdp->sd_args.ar_debug);
+ if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
+ fs_err(sdp, "about to withdraw this file system\n");
+ BUG_ON(sdp->sd_args.ar_debug);
- kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE);
+ kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE);
- if (lm->lm_unmount) {
- fs_err(sdp, "telling LM to unmount\n");
- lm->lm_unmount(sdp);
+ if (lm->lm_unmount) {
+ fs_err(sdp, "telling LM to unmount\n");
+ lm->lm_unmount(sdp);
+ }
+ fs_err(sdp, "withdrawn\n");
+ dump_stack();
}
- fs_err(sdp, "withdrawn\n");
- dump_stack();
+
+ if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
+ panic("GFS2: fsid=%s: panic requested.\n", sdp->sd_fsname);
return -1;
}
@@ -93,17 +99,24 @@ int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
gfs2_tune_get(sdp, gt_complain_secs) * HZ))
return -2;
- printk(KERN_WARNING
- "GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
- "GFS2: fsid=%s: function = %s, file = %s, line = %u\n",
- sdp->sd_fsname, assertion,
- sdp->sd_fsname, function, file, line);
+ if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW)
+ printk(KERN_WARNING
+ "GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
+ "GFS2: fsid=%s: function = %s, file = %s, line = %u\n",
+ sdp->sd_fsname, assertion,
+ sdp->sd_fsname, function, file, line);
if (sdp->sd_args.ar_debug)
BUG();
else
dump_stack();
+ if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
+ panic("GFS2: fsid=%s: warning: assertion \"%s\" failed\n"
+ "GFS2: fsid=%s: function = %s, file = %s, line = %u\n",
+ sdp->sd_fsname, assertion,
+ sdp->sd_fsname, function, file, line);
+
sdp->sd_last_warning = jiffies;
return -1;
diff --git a/fs/gfs2/eattr.c b/fs/gfs2/xattr.c
index 07ea9529adda..8a0f8ef6ee27 100644
--- a/fs/gfs2/eattr.c
+++ b/fs/gfs2/xattr.c
@@ -18,8 +18,7 @@
#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"
@@ -38,26 +37,32 @@
* Returns: 1 if the EA should be stuffed
*/
-static int ea_calc_size(struct gfs2_sbd *sdp, struct gfs2_ea_request *er,
+static int ea_calc_size(struct gfs2_sbd *sdp, unsigned int nsize, size_t dsize,
unsigned int *size)
{
- *size = GFS2_EAREQ_SIZE_STUFFED(er);
- if (*size <= sdp->sd_jbsize)
+ unsigned int jbsize = sdp->sd_jbsize;
+
+ /* Stuffed */
+ *size = ALIGN(sizeof(struct gfs2_ea_header) + nsize + dsize, 8);
+
+ if (*size <= jbsize)
return 1;
- *size = GFS2_EAREQ_SIZE_UNSTUFFED(sdp, er);
+ /* Unstuffed */
+ *size = ALIGN(sizeof(struct gfs2_ea_header) + nsize +
+ (sizeof(__be64) * DIV_ROUND_UP(dsize, jbsize)), 8);
return 0;
}
-static int ea_check_size(struct gfs2_sbd *sdp, struct gfs2_ea_request *er)
+static int ea_check_size(struct gfs2_sbd *sdp, unsigned int nsize, size_t dsize)
{
unsigned int size;
- if (er->er_data_len > GFS2_EA_MAX_DATA_LEN)
+ if (dsize > GFS2_EA_MAX_DATA_LEN)
return -ERANGE;
- ea_calc_size(sdp, er, &size);
+ ea_calc_size(sdp, nsize, dsize, &size);
/* This can only happen with 512 byte blocks */
if (size > sdp->sd_jbsize)
@@ -151,7 +156,9 @@ out:
}
struct ea_find {
- struct gfs2_ea_request *ef_er;
+ int type;
+ const char *name;
+ size_t namel;
struct gfs2_ea_location *ef_el;
};
@@ -160,14 +167,13 @@ static int ea_find_i(struct gfs2_inode *ip, struct buffer_head *bh,
void *private)
{
struct ea_find *ef = private;
- struct gfs2_ea_request *er = ef->ef_er;
if (ea->ea_type == GFS2_EATYPE_UNUSED)
return 0;
- if (ea->ea_type == er->er_type) {
- if (ea->ea_name_len == er->er_name_len &&
- !memcmp(GFS2_EA2NAME(ea), er->er_name, ea->ea_name_len)) {
+ if (ea->ea_type == ef->type) {
+ if (ea->ea_name_len == ef->namel &&
+ !memcmp(GFS2_EA2NAME(ea), ef->name, ea->ea_name_len)) {
struct gfs2_ea_location *el = ef->ef_el;
get_bh(bh);
el->el_bh = bh;
@@ -180,13 +186,15 @@ static int ea_find_i(struct gfs2_inode *ip, struct buffer_head *bh,
return 0;
}
-int gfs2_ea_find(struct gfs2_inode *ip, struct gfs2_ea_request *er,
+int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name,
struct gfs2_ea_location *el)
{
struct ea_find ef;
int error;
- ef.ef_er = er;
+ ef.type = type;
+ ef.name = name;
+ ef.namel = strlen(name);
ef.ef_el = el;
memset(el, 0, sizeof(struct gfs2_ea_location));
@@ -344,6 +352,20 @@ struct ea_list {
unsigned int ei_size;
};
+static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
+{
+ switch (ea->ea_type) {
+ case GFS2_EATYPE_USR:
+ return 5 + ea->ea_name_len + 1;
+ case GFS2_EATYPE_SYS:
+ return 7 + ea->ea_name_len + 1;
+ case GFS2_EATYPE_SECURITY:
+ return 9 + ea->ea_name_len + 1;
+ default:
+ return 0;
+ }
+}
+
static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh,
struct gfs2_ea_header *ea, struct gfs2_ea_header *prev,
void *private)
@@ -392,21 +414,25 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh,
}
/**
- * gfs2_ea_list -
- * @ip:
- * @er:
+ * gfs2_listxattr - List gfs2 extended attributes
+ * @dentry: The dentry whose inode we are interested in
+ * @buffer: The buffer to write the results
+ * @size: The size of the buffer
*
* Returns: actual size of data on success, -errno on error
*/
-int gfs2_ea_list(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
+ struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+ struct gfs2_ea_request er;
struct gfs2_holder i_gh;
int error;
- if (!er->er_data || !er->er_data_len) {
- er->er_data = NULL;
- er->er_data_len = 0;
+ memset(&er, 0, sizeof(struct gfs2_ea_request));
+ if (size) {
+ er.er_data = buffer;
+ er.er_data_len = size;
}
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
@@ -414,7 +440,7 @@ int gfs2_ea_list(struct gfs2_inode *ip, struct gfs2_ea_request *er)
return error;
if (ip->i_eattr) {
- struct ea_list ei = { .ei_er = er, .ei_size = 0 };
+ struct ea_list ei = { .ei_er = &er, .ei_size = 0 };
error = ea_foreach(ip, ea_list_i, &ei);
if (!error)
@@ -491,84 +517,61 @@ out:
}
int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el,
- char *data)
+ char *data, size_t size)
{
+ int ret;
+ size_t len = GFS2_EA_DATA_LEN(el->el_ea);
+ if (len > size)
+ return -ERANGE;
+
if (GFS2_EA_IS_STUFFED(el->el_ea)) {
- memcpy(data, GFS2_EA2DATA(el->el_ea), GFS2_EA_DATA_LEN(el->el_ea));
- return 0;
- } else
- return ea_get_unstuffed(ip, el->el_ea, data);
+ memcpy(data, GFS2_EA2DATA(el->el_ea), len);
+ return len;
+ }
+ ret = ea_get_unstuffed(ip, el->el_ea, data);
+ if (ret < 0)
+ return ret;
+ return len;
}
/**
- * gfs2_ea_get_i -
- * @ip: The GFS2 inode
- * @er: The request structure
+ * gfs2_xattr_get - Get a GFS2 extended attribute
+ * @inode: The inode
+ * @type: The type of extended attribute
+ * @name: The name of the extended attribute
+ * @buffer: The buffer to write the result into
+ * @size: The size of the buffer
*
* Returns: actual size of data on success, -errno on error
*/
-int gfs2_ea_get_i(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+int gfs2_xattr_get(struct inode *inode, int type, const char *name,
+ void *buffer, size_t size)
{
+ struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_ea_location el;
int error;
if (!ip->i_eattr)
return -ENODATA;
+ if (strlen(name) > GFS2_EA_MAX_NAME_LEN)
+ return -EINVAL;
- error = gfs2_ea_find(ip, er, &el);
+ error = gfs2_ea_find(ip, type, name, &el);
if (error)
return error;
if (!el.el_ea)
return -ENODATA;
-
- if (er->er_data_len) {
- if (GFS2_EA_DATA_LEN(el.el_ea) > er->er_data_len)
- error = -ERANGE;
- else
- error = gfs2_ea_get_copy(ip, &el, er->er_data);
- }
- if (!error)
+ if (size)
+ error = gfs2_ea_get_copy(ip, &el, buffer, size);
+ else
error = GFS2_EA_DATA_LEN(el.el_ea);
-
brelse(el.el_bh);
return error;
}
/**
- * gfs2_ea_get -
- * @ip: The GFS2 inode
- * @er: The request structure
- *
- * Returns: actual size of data on success, -errno on error
- */
-
-int gfs2_ea_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
- struct gfs2_holder i_gh;
- int error;
-
- if (!er->er_name_len ||
- er->er_name_len > GFS2_EA_MAX_NAME_LEN)
- return -EINVAL;
- if (!er->er_data || !er->er_data_len) {
- er->er_data = NULL;
- er->er_data_len = 0;
- }
-
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
- if (error)
- return error;
-
- error = gfs2_ea_ops[er->er_type]->eo_get(ip, er);
-
- gfs2_glock_dq_uninit(&i_gh);
-
- return error;
-}
-
-/**
* ea_alloc_blk - allocates a new block for extended attributes.
* @ip: A pointer to the inode that's getting extended attributes
* @bhp: Pointer to pointer to a struct buffer_head
@@ -713,12 +716,6 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er,
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
- if (er->er_flags & GFS2_ERF_MODE) {
- gfs2_assert_withdraw(GFS2_SB(&ip->i_inode),
- (ip->i_inode.i_mode & S_IFMT) ==
- (er->er_mode & S_IFMT));
- ip->i_inode.i_mode = er->er_mode;
- }
ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
@@ -762,15 +759,23 @@ static int ea_init_i(struct gfs2_inode *ip, struct gfs2_ea_request *er,
* Returns: errno
*/
-static int ea_init(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+static int ea_init(struct gfs2_inode *ip, int type, const char *name,
+ const void *data, size_t size)
{
+ struct gfs2_ea_request er;
unsigned int jbsize = GFS2_SB(&ip->i_inode)->sd_jbsize;
unsigned int blks = 1;
- if (GFS2_EAREQ_SIZE_STUFFED(er) > jbsize)
- blks += DIV_ROUND_UP(er->er_data_len, jbsize);
+ er.er_type = type;
+ er.er_name = name;
+ er.er_name_len = strlen(name);
+ er.er_data = (void *)data;
+ er.er_data_len = size;
+
+ if (GFS2_EAREQ_SIZE_STUFFED(&er) > jbsize)
+ blks += DIV_ROUND_UP(er.er_data_len, jbsize);
- return ea_alloc_skeleton(ip, er, blks, ea_init_i, NULL);
+ return ea_alloc_skeleton(ip, &er, blks, ea_init_i, NULL);
}
static struct gfs2_ea_header *ea_split_ea(struct gfs2_ea_header *ea)
@@ -848,12 +853,6 @@ static int ea_set_simple_noalloc(struct gfs2_inode *ip, struct buffer_head *bh,
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out;
-
- if (er->er_flags & GFS2_ERF_MODE) {
- gfs2_assert_withdraw(GFS2_SB(&ip->i_inode),
- (ip->i_inode.i_mode & S_IFMT) == (er->er_mode & S_IFMT));
- ip->i_inode.i_mode = er->er_mode;
- }
ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
@@ -894,7 +893,8 @@ static int ea_set_simple(struct gfs2_inode *ip, struct buffer_head *bh,
int stuffed;
int error;
- stuffed = ea_calc_size(GFS2_SB(&ip->i_inode), es->es_er, &size);
+ stuffed = ea_calc_size(GFS2_SB(&ip->i_inode), es->es_er->er_name_len,
+ es->es_er->er_data_len, &size);
if (ea->ea_type == GFS2_EATYPE_UNUSED) {
if (GFS2_EA_REC_LEN(ea) < size)
@@ -1005,15 +1005,22 @@ out:
return error;
}
-static int ea_set_i(struct gfs2_inode *ip, struct gfs2_ea_request *er,
- struct gfs2_ea_location *el)
+static int ea_set_i(struct gfs2_inode *ip, int type, const char *name,
+ const void *value, size_t size, struct gfs2_ea_location *el)
{
+ struct gfs2_ea_request er;
struct ea_set es;
unsigned int blks = 2;
int error;
+ er.er_type = type;
+ er.er_name = name;
+ er.er_data = (void *)value;
+ er.er_name_len = strlen(name);
+ er.er_data_len = size;
+
memset(&es, 0, sizeof(struct ea_set));
- es.es_er = er;
+ es.es_er = &er;
es.es_el = el;
error = ea_foreach(ip, ea_set_simple, &es);
@@ -1024,10 +1031,10 @@ static int ea_set_i(struct gfs2_inode *ip, struct gfs2_ea_request *er,
if (!(ip->i_diskflags & GFS2_DIF_EA_INDIRECT))
blks++;
- if (GFS2_EAREQ_SIZE_STUFFED(er) > GFS2_SB(&ip->i_inode)->sd_jbsize)
- blks += DIV_ROUND_UP(er->er_data_len, GFS2_SB(&ip->i_inode)->sd_jbsize);
+ if (GFS2_EAREQ_SIZE_STUFFED(&er) > GFS2_SB(&ip->i_inode)->sd_jbsize)
+ blks += DIV_ROUND_UP(er.er_data_len, GFS2_SB(&ip->i_inode)->sd_jbsize);
- return ea_alloc_skeleton(ip, er, blks, ea_set_block, el);
+ return ea_alloc_skeleton(ip, &er, blks, ea_set_block, el);
}
static int ea_set_remove_unstuffed(struct gfs2_inode *ip,
@@ -1039,75 +1046,7 @@ static int ea_set_remove_unstuffed(struct gfs2_inode *ip,
GFS2_EA2NEXT(el->el_prev) == el->el_ea);
}
- return ea_remove_unstuffed(ip, el->el_bh, el->el_ea, el->el_prev,0);
-}
-
-int gfs2_ea_set_i(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
- struct gfs2_ea_location el;
- int error;
-
- if (!ip->i_eattr) {
- if (er->er_flags & XATTR_REPLACE)
- return -ENODATA;
- return ea_init(ip, er);
- }
-
- error = gfs2_ea_find(ip, er, &el);
- if (error)
- return error;
-
- if (el.el_ea) {
- if (ip->i_diskflags & GFS2_DIF_APPENDONLY) {
- brelse(el.el_bh);
- return -EPERM;
- }
-
- error = -EEXIST;
- if (!(er->er_flags & XATTR_CREATE)) {
- int unstuffed = !GFS2_EA_IS_STUFFED(el.el_ea);
- error = ea_set_i(ip, er, &el);
- if (!error && unstuffed)
- ea_set_remove_unstuffed(ip, &el);
- }
-
- brelse(el.el_bh);
- } else {
- error = -ENODATA;
- if (!(er->er_flags & XATTR_REPLACE))
- error = ea_set_i(ip, er, NULL);
- }
-
- return error;
-}
-
-int gfs2_ea_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
- struct gfs2_holder i_gh;
- int error;
-
- if (!er->er_name_len || er->er_name_len > GFS2_EA_MAX_NAME_LEN)
- return -EINVAL;
- if (!er->er_data || !er->er_data_len) {
- er->er_data = NULL;
- er->er_data_len = 0;
- }
- error = ea_check_size(GFS2_SB(&ip->i_inode), er);
- if (error)
- return error;
-
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
- if (error)
- return error;
-
- if (IS_IMMUTABLE(&ip->i_inode))
- error = -EPERM;
- else
- error = gfs2_ea_ops[er->er_type]->eo_set(ip, er);
-
- gfs2_glock_dq_uninit(&i_gh);
-
- return error;
+ return ea_remove_unstuffed(ip, el->el_bh, el->el_ea, el->el_prev, 0);
}
static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el)
@@ -1131,8 +1070,9 @@ static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el)
if (GFS2_EA_IS_LAST(ea))
prev->ea_flags |= GFS2_EAFLAG_LAST;
- } else
+ } else {
ea->ea_type = GFS2_EATYPE_UNUSED;
+ }
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
@@ -1147,15 +1087,29 @@ static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el)
return error;
}
-int gfs2_ea_remove_i(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+/**
+ * gfs2_xattr_remove - Remove a GFS2 extended attribute
+ * @inode: The inode
+ * @type: The type of the extended attribute
+ * @name: The name of the extended attribute
+ *
+ * This is not called directly by the VFS since we use the (common)
+ * scheme of making a "set with NULL data" mean a remove request. Note
+ * that this is different from a set with zero length data.
+ *
+ * Returns: 0, or errno on failure
+ */
+
+static int gfs2_xattr_remove(struct inode *inode, int type, const char *name)
{
+ struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_ea_location el;
int error;
if (!ip->i_eattr)
return -ENODATA;
- error = gfs2_ea_find(ip, er, &el);
+ error = gfs2_ea_find(ip, type, name, &el);
if (error)
return error;
if (!el.el_ea)
@@ -1164,8 +1118,7 @@ int gfs2_ea_remove_i(struct gfs2_inode *ip, struct gfs2_ea_request *er)
if (GFS2_EA_IS_STUFFED(el.el_ea))
error = ea_remove_stuffed(ip, &el);
else
- error = ea_remove_unstuffed(ip, el.el_bh, el.el_ea, el.el_prev,
- 0);
+ error = ea_remove_unstuffed(ip, el.el_bh, el.el_ea, el.el_prev, 0);
brelse(el.el_bh);
@@ -1173,31 +1126,70 @@ int gfs2_ea_remove_i(struct gfs2_inode *ip, struct gfs2_ea_request *er)
}
/**
- * gfs2_ea_remove - sets (or creates or replaces) an extended attribute
- * @ip: pointer to the inode of the target file
- * @er: request information
+ * gfs2_xattr_set - Set (or remove) a GFS2 extended attribute
+ * @inode: The inode
+ * @type: The type of the extended attribute
+ * @name: The name of the extended attribute
+ * @value: The value of the extended attribute (NULL for remove)
+ * @size: The size of the @value argument
+ * @flags: Create or Replace
*
- * Returns: errno
+ * See gfs2_xattr_remove() for details of the removal of xattrs.
+ *
+ * Returns: 0 or errno on failure
*/
-int gfs2_ea_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
+int gfs2_xattr_set(struct inode *inode, int type, const char *name,
+ const void *value, size_t size, int flags)
{
- struct gfs2_holder i_gh;
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_ea_location el;
+ unsigned int namel = strlen(name);
int error;
- if (!er->er_name_len || er->er_name_len > GFS2_EA_MAX_NAME_LEN)
- return -EINVAL;
+ if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+ return -EPERM;
+ if (namel > GFS2_EA_MAX_NAME_LEN)
+ return -ERANGE;
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+ if (value == NULL)
+ return gfs2_xattr_remove(inode, type, name);
+
+ if (ea_check_size(sdp, namel, size))
+ return -ERANGE;
+
+ if (!ip->i_eattr) {
+ if (flags & XATTR_REPLACE)
+ return -ENODATA;
+ return ea_init(ip, type, name, value, size);
+ }
+
+ error = gfs2_ea_find(ip, type, name, &el);
if (error)
return error;
- if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
- error = -EPERM;
- else
- error = gfs2_ea_ops[er->er_type]->eo_remove(ip, er);
+ if (el.el_ea) {
+ if (ip->i_diskflags & GFS2_DIF_APPENDONLY) {
+ brelse(el.el_bh);
+ return -EPERM;
+ }
- gfs2_glock_dq_uninit(&i_gh);
+ error = -EEXIST;
+ if (!(flags & XATTR_CREATE)) {
+ int unstuffed = !GFS2_EA_IS_STUFFED(el.el_ea);
+ error = ea_set_i(ip, type, name, value, size, &el);
+ if (!error && unstuffed)
+ ea_set_remove_unstuffed(ip, &el);
+ }
+
+ brelse(el.el_bh);
+ return error;
+ }
+
+ error = -ENODATA;
+ if (!(flags & XATTR_REPLACE))
+ error = ea_set_i(ip, type, name, value, size, NULL);
return error;
}
@@ -1503,3 +1495,64 @@ out_alloc:
return error;
}
+static int gfs2_xattr_user_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ return gfs2_xattr_get(inode, GFS2_EATYPE_USR, name, buffer, size);
+}
+
+static int gfs2_xattr_user_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ return gfs2_xattr_set(inode, GFS2_EATYPE_USR, name, value, size, flags);
+}
+
+static int gfs2_xattr_system_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ return gfs2_xattr_get(inode, GFS2_EATYPE_SYS, name, buffer, size);
+}
+
+static int gfs2_xattr_system_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ return gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, value, size, flags);
+}
+
+static int gfs2_xattr_security_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ return gfs2_xattr_get(inode, GFS2_EATYPE_SECURITY, name, buffer, size);
+}
+
+static int gfs2_xattr_security_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ return gfs2_xattr_set(inode, GFS2_EATYPE_SECURITY, name, value, size, flags);
+}
+
+static struct xattr_handler gfs2_xattr_user_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .get = gfs2_xattr_user_get,
+ .set = gfs2_xattr_user_set,
+};
+
+static struct xattr_handler gfs2_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .get = gfs2_xattr_security_get,
+ .set = gfs2_xattr_security_set,
+};
+
+static struct xattr_handler gfs2_xattr_system_handler = {
+ .prefix = XATTR_SYSTEM_PREFIX,
+ .get = gfs2_xattr_system_get,
+ .set = gfs2_xattr_system_set,
+};
+
+struct xattr_handler *gfs2_xattr_handlers[] = {
+ &gfs2_xattr_user_handler,
+ &gfs2_xattr_security_handler,
+ &gfs2_xattr_system_handler,
+ NULL,
+};
+
diff --git a/fs/gfs2/eattr.h b/fs/gfs2/xattr.h
index c82dbe01d713..cbdfd7743733 100644
--- a/fs/gfs2/eattr.h
+++ b/fs/gfs2/xattr.h
@@ -19,7 +19,7 @@ struct iattr;
#define GFS2_EA_SIZE(ea) \
ALIGN(sizeof(struct gfs2_ea_header) + (ea)->ea_name_len + \
((GFS2_EA_IS_STUFFED(ea)) ? GFS2_EA_DATA_LEN(ea) : \
- (sizeof(__be64) * (ea)->ea_num_ptrs)), 8)
+ (sizeof(__be64) * (ea)->ea_num_ptrs)), 8)
#define GFS2_EA_IS_STUFFED(ea) (!(ea)->ea_num_ptrs)
#define GFS2_EA_IS_LAST(ea) ((ea)->ea_flags & GFS2_EAFLAG_LAST)
@@ -27,10 +27,6 @@ ALIGN(sizeof(struct gfs2_ea_header) + (ea)->ea_name_len + \
#define GFS2_EAREQ_SIZE_STUFFED(er) \
ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + (er)->er_data_len, 8)
-#define GFS2_EAREQ_SIZE_UNSTUFFED(sdp, er) \
-ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + \
- sizeof(__be64) * DIV_ROUND_UP((er)->er_data_len, (sdp)->sd_jbsize), 8)
-
#define GFS2_EA2NAME(ea) ((char *)((struct gfs2_ea_header *)(ea) + 1))
#define GFS2_EA2DATA(ea) (GFS2_EA2NAME(ea) + (ea)->ea_name_len)
@@ -43,16 +39,12 @@ ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + \
#define GFS2_EA_BH2FIRST(bh) \
((struct gfs2_ea_header *)((bh)->b_data + sizeof(struct gfs2_meta_header)))
-#define GFS2_ERF_MODE 0x80000000
-
struct gfs2_ea_request {
const char *er_name;
char *er_data;
unsigned int er_name_len;
unsigned int er_data_len;
unsigned int er_type; /* GFS2_EATYPE_... */
- int er_flags;
- mode_t er_mode;
};
struct gfs2_ea_location {
@@ -61,40 +53,20 @@ struct gfs2_ea_location {
struct gfs2_ea_header *el_prev;
};
-int gfs2_ea_get_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-int gfs2_ea_set_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-int gfs2_ea_remove_i(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-
-int gfs2_ea_list(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-int gfs2_ea_get(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-int gfs2_ea_set(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-int gfs2_ea_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er);
-
-int gfs2_ea_dealloc(struct gfs2_inode *ip);
+extern int gfs2_xattr_get(struct inode *inode, int type, const char *name,
+ void *buffer, size_t size);
+extern int gfs2_xattr_set(struct inode *inode, int type, const char *name,
+ const void *value, size_t size, int flags);
+extern ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size);
+extern int gfs2_ea_dealloc(struct gfs2_inode *ip);
/* Exported to acl.c */
-int gfs2_ea_find(struct gfs2_inode *ip,
- struct gfs2_ea_request *er,
- struct gfs2_ea_location *el);
-int gfs2_ea_get_copy(struct gfs2_inode *ip,
- struct gfs2_ea_location *el,
- char *data);
-int gfs2_ea_acl_chmod(struct gfs2_inode *ip, struct gfs2_ea_location *el,
- struct iattr *attr, char *data);
-
-static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
-{
- switch (ea->ea_type) {
- case GFS2_EATYPE_USR:
- return 5 + ea->ea_name_len + 1;
- case GFS2_EATYPE_SYS:
- return 7 + ea->ea_name_len + 1;
- case GFS2_EATYPE_SECURITY:
- return 9 + ea->ea_name_len + 1;
- default:
- return 0;
- }
-}
+extern int gfs2_ea_find(struct gfs2_inode *ip, int type, const char *name,
+ struct gfs2_ea_location *el);
+extern int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el,
+ char *data, size_t size);
+extern int gfs2_ea_acl_chmod(struct gfs2_inode *ip, struct gfs2_ea_location *el,
+ struct iattr *attr, char *data);
#endif /* __EATTR_DOT_H__ */
diff --git a/include/linux/gfs2_ondisk.h b/include/linux/gfs2_ondisk.h
index c56b4bce56d0..b80c88dedbbb 100644
--- a/include/linux/gfs2_ondisk.h
+++ b/include/linux/gfs2_ondisk.h
@@ -333,6 +333,28 @@ struct gfs2_leaf {
/*
* Extended attribute header format
+ *
+ * This works in a similar way to dirents. There is a fixed size header
+ * followed by a variable length section made up of the name and the
+ * associated data. In the case of a "stuffed" entry, the value is
+ * inline directly after the name, the ea_num_ptrs entry will be
+ * zero in that case. For non-"stuffed" entries, there will be
+ * a set of pointers (aligned to 8 byte boundary) to the block(s)
+ * containing the value.
+ *
+ * The blocks containing the values and the blocks containing the
+ * extended attribute headers themselves all start with the common
+ * metadata header. Each inode, if it has extended attributes, will
+ * have either a single block containing the extended attribute headers
+ * or a single indirect block pointing to blocks containing the
+ * extended attribure headers.
+ *
+ * The maximim size of the data part of an extended attribute is 64k
+ * so the number of blocks required depends upon block size. Since the
+ * block size also determines the number of pointers in an indirect
+ * block, its a fairly complicated calculation to work out the maximum
+ * number of blocks that an inode may have relating to extended attributes.
+ *
*/
#define GFS2_EA_MAX_NAME_LEN 255