[GFS2] The core of GFS2

This patch contains all the core files for GFS2.

Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

79 files changed, 28772 insertions, 0 deletions

diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
new file mode 100644
index 00000000000..17cb44bea1c
--- /dev/null
+++ b/fs/gfs2/Kconfig
@@ -0,0 +1,46 @@
+config GFS2_FS
+        tristate "GFS2 file system support"
+	default m
+	depends on EXPERIMENTAL
+        select FS_POSIX_ACL
+        select SYSFS
+        help
+        A cluster filesystem.
+
+        Allows a cluster of computers to simultaneously use a block device
+        that is shared between them (with FC, iSCSI, NBD, etc...).  GFS reads
+        and writes to the block device like a local filesystem, but also uses
+        a lock module to allow the computers coordinate their I/O so
+        filesystem consistency is maintained.  One of the nifty features of
+        GFS is perfect consistency -- changes made to the filesystem on one
+        machine show up immediately on all other machines in the cluster.
+
+	To use the GFS2 filesystem, you will need to enable one or more of
+	the below locking modules. Documentation and utilities for GFS2 can
+	be found here: http://sources.redhat.com/cluster/gfs/
+
+config GFS2_FS_LOCKING_NOLOCK
+	tristate "GFS2 \"nolock\" locking module"
+	depends on GFS2_FS
+	help
+	Single node locking module for GFS2.
+
+	Use this module if you want to use GFS2 on a single node without
+	its clustering features. You can still take advantage of the
+	large file support, and upgrade to running a full cluster later on
+	if required.
+
+	If you will only be using GFS2 in cluster mode, you do not need this
+	module.
+
+config GFS2_FS_LOCKING_DLM
+	tristate "GFS2 DLM locking module"
+	depends on GFS2_FS
+	select DLM
+	help
+	Multiple node locking module for GFS2
+
+	Most users of GFS2 will require this module. It provides the locking
+	interface between GFS2 and the DLM, which is required to use GFS2
+	in a cluster environment.
+
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
new file mode 100644
index 00000000000..b1bac4f199d
--- /dev/null
+++ b/fs/gfs2/Makefile
@@ -0,0 +1,44 @@
+obj-$(CONFIG_GFS2_FS) += gfs2.o
+gfs2-y := \
+	acl.o \
+	bits.o \
+	bmap.o \
+	daemon.o \
+	dir.o \
+	eaops.o \
+	eattr.o \
+	glock.o \
+	glops.o \
+	inode.o \
+	jdata.o \
+	lm.o \
+	log.o \
+	lops.o \
+	locking.o \
+	lvb.o \
+	main.o \
+	meta_io.o \
+	mount.o \
+	ondisk.o \
+	ops_address.o \
+	ops_dentry.o \
+	ops_export.o \
+	ops_file.o \
+	ops_fstype.o \
+	ops_inode.o \
+	ops_super.o \
+	ops_vm.o \
+	page.o \
+	quota.o \
+	resize.o \
+	recovery.o \
+	rgrp.o \
+	super.o \
+	sys.o \
+	trans.o \
+	unlinked.o \
+	util.o
+
+obj-$(CONFIG_GFS2_LOCKING_NOLOCK) += locking/nolock/
+obj-$(CONFIG_GFS2_LOCKING_DLM) += locking/dlm/
+
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
new file mode 100644
index 00000000000..33c465a2ab5
--- /dev/null
+++ b/fs/gfs2/acl.c
@@ -0,0 +1,312 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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 v.2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <asm/semaphore.h>
+
+#include "gfs2.h"
+#include "acl.h"
+#include "eaops.h"
+#include "eattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "trans.h"
+
+#define ACL_ACCESS 1
+#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 posix_acl *acl;
+	int error;
+
+	error = gfs2_acl_validate_remove(ip, access);
+	if (error)
+		return error;
+
+	if (!er->er_data)
+		return -EINVAL;
+
+	acl = posix_acl_from_xattr(er->er_data, er->er_data_len);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (!acl) {
+		*remove = 1;
+		return 0;
+	}
+
+	error = posix_acl_valid(acl);
+	if (error)
+		goto out;
+
+	if (access) {
+		error = posix_acl_equiv_mode(acl, mode);
+		if (!error)
+			*remove = 1;
+		else if (error > 0)
+			error = 0;
+	}
+
+ out:
+	posix_acl_release(acl);
+
+	return error;
+}
+
+int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access)
+{
+	if (!ip->i_sbd->sd_args.ar_posix_acl)
+		return -EOPNOTSUPP;
+	if (current->fsuid != ip->i_di.di_uid && !capable(CAP_FOWNER))
+		return -EPERM;
+	if (S_ISLNK(ip->i_di.di_mode))
+		return -EOPNOTSUPP;
+	if (!access && !S_ISDIR(ip->i_di.di_mode))
+		return -EACCES;
+
+	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)
+{
+	struct gfs2_ea_request er;
+	struct gfs2_ea_location el_this;
+	int error;
+
+	if (!ip->i_di.di_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);
+	if (error)
+		return error;
+	if (!el->el_ea)
+		return 0;
+	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_KERNEL);
+	error = -ENOMEM;
+	if (!er.er_data)
+		goto out;
+
+	error = gfs2_ea_get_copy(ip, el, er.er_data);
+	if (error)
+		goto out_kfree;
+
+	if (acl) {
+		*acl = posix_acl_from_xattr(er.er_data, er.er_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;
+	}
+
+ out:
+	if (error || el == &el_this)
+		brelse(el->el_bh);
+
+	return error;
+}
+
+/**
+ * gfs2_check_acl_locked - Check an ACL to see if we're allowed to do something
+ * @inode: the file we want to do something to
+ * @mask: what we want to do
+ *
+ * Returns: errno
+ */
+
+int gfs2_check_acl_locked(struct inode *inode, int mask)
+{
+	struct posix_acl *acl = NULL;
+	int error;
+
+	error = acl_get(get_v2ip(inode), ACL_ACCESS, &acl, NULL, NULL, NULL);
+	if (error)
+		return error;
+
+	if (acl) {
+		error = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return error;
+	}
+
+	return -EAGAIN;
+}
+
+int gfs2_check_acl(struct inode *inode, int mask)
+{
+	struct gfs2_inode *ip = get_v2ip(inode);
+	struct gfs2_holder i_gh;
+	int error;
+
+	error = gfs2_glock_nq_init(ip->i_gl,
+				   LM_ST_SHARED, LM_FLAG_ANY,
+				   &i_gh);
+	if (!error) {
+		error = gfs2_check_acl_locked(inode, mask);
+		gfs2_glock_dq_uninit(&i_gh);
+	}
+	
+	return error;
+}
+
+static int munge_mode(struct gfs2_inode *ip, mode_t mode)
+{
+	struct gfs2_sbd *sdp = ip->i_sbd;
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		return error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (!error) {
+		gfs2_assert_withdraw(sdp,
+				(ip->i_di.di_mode & S_IFMT) == (mode & S_IFMT));
+		ip->i_di.di_mode = mode;
+		gfs2_trans_add_bh(ip->i_gl, dibh);
+		gfs2_dinode_out(&ip->i_di, dibh->b_data);
+		brelse(dibh);
+	}
+
+	gfs2_trans_end(sdp);
+
+	return 0;
+}
+
+int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = dip->i_sbd;
+	struct posix_acl *acl = NULL, *clone;
+	struct gfs2_ea_request er;
+	mode_t mode = ip->i_di.di_mode;
+	int error;
+
+	if (!sdp->sd_args.ar_posix_acl)
+		return 0;
+	if (S_ISLNK(ip->i_di.di_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);
+	if (error)
+		return error;
+	if (!acl) {
+		mode &= ~current->fs->umask;
+		if (mode != ip->i_di.di_mode)
+			error = munge_mode(ip, mode);
+		return error;
+	}
+
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	if (S_ISDIR(ip->i_di.di_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);
+		if (error)
+			goto out;
+	}
+
+	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);
+
+ out:
+	posix_acl_release(acl);
+	kfree(er.er_data);
+	return error;
+}
+
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
+{
+	struct posix_acl *acl = NULL, *clone;
+	struct gfs2_ea_location el;
+	char *data;
+	unsigned int len;
+	int error;
+
+	error = acl_get(ip, ACL_ACCESS, &acl, &el, &data, &len);
+	if (error)
+		return error;
+	if (!acl)
+		return gfs2_setattr_simple(ip, attr);
+
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	error = -ENOMEM;
+	if (!clone)
+		goto out;
+	posix_acl_release(acl);
+	acl = clone;
+
+	error = posix_acl_chmod_masq(acl, attr->ia_mode);
+	if (!error) {
+		posix_acl_to_xattr(acl, data, len);
+		error = gfs2_ea_acl_chmod(ip, &el, attr, data);
+	}
+
+ out:
+	posix_acl_release(acl);
+	brelse(el.el_bh);
+	kfree(data);
+
+	return error;
+}
+
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
new file mode 100644
index 00000000000..a174b4f6bcc
--- /dev/null
+++ b/fs/gfs2/acl.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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 v.2.
+ */
+
+#ifndef __ACL_DOT_H__
+#define __ACL_DOT_H__
+
+#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
+#define GFS2_POSIX_ACL_ACCESS_LEN	16
+#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
+#define GFS2_POSIX_ACL_DEFAULT_LEN	17
+
+#define GFS2_ACL_IS_ACCESS(name, len) \
+         ((len) == GFS2_POSIX_ACL_ACCESS_LEN && \
+         !memcmp(GFS2_POSIX_ACL_ACCESS, (name), (len)))
+
+#define GFS2_ACL_IS_DEFAULT(name, len) \
+         ((len) == GFS2_POSIX_ACL_DEFAULT_LEN && \
+         !memcmp(GFS2_POSIX_ACL_DEFAULT, (name), (len)))
+
+struct gfs2_ea_request;
+
+int gfs2_acl_validate_set(struct gfs2_inode *ip, int access,
+			  struct gfs2_ea_request *er,
+			  int *remove, mode_t *mode);
+int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access);
+int gfs2_check_acl_locked(struct inode *inode, int mask);
+int gfs2_check_acl(struct inode *inode, int mask);
+int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip);
+int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
+
+#endif /* __ACL_DOT_H__ */
diff --git a/fs/gfs2/bits.c b/fs/gfs2/bits.c
new file mode 100644
index 00000000000..57d420a86ad
--- /dev/null
+++ b/fs/gfs2/bits.c
@@ -0,0 +1,178 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2005 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 v.2.
+ */
+
+/*
+ * These routines are used by the resource group routines (rgrp.c)
+ * to keep track of block allocation.  Each block is represented by two
+ * bits.  One bit indicates whether or not the block is used.  (1=used,
+ * 0=free)  The other bit indicates whether or not the block contains a
+ * dinode or not.  (1=dinode, 0=not-dinode) So, each byte represents
+ * GFS2_NBBY (i.e. 4) blocks.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <asm/semaphore.h>
+
+#include "gfs2.h"
+#include "bits.h"
+
+static const char valid_change[16] = {
+	        /* current */
+	/* n */ 0, 1, 0, 1,
+	/* e */ 1, 0, 0, 0,
+	/* w */ 0, 0, 0, 0,
+	        1, 0, 0, 0
+};
+
+/**
+ * gfs2_setbit - Set a bit in the bitmaps
+ * @buffer: the buffer that holds the bitmaps
+ * @buflen: the length (in bytes) of the buffer
+ * @block: the block to set
+ * @new_state: the new state of the block
+ *
+ */
+
+void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
+		 unsigned int buflen, uint32_t block, unsigned char new_state)
+{
+	unsigned char *byte, *end, cur_state;
+	unsigned int bit;
+
+	byte = buffer + (block / GFS2_NBBY);
+	bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
+	end = buffer + buflen;
+
+	gfs2_assert(rgd->rd_sbd, byte < end);
+
+	cur_state = (*byte >> bit) & GFS2_BIT_MASK;
+
+	if (valid_change[new_state * 4 + cur_state]) {
+		*byte ^= cur_state << bit;
+		*byte |= new_state << bit;
+	} else
+		gfs2_consist_rgrpd(rgd);
+}
+
+/**
+ * gfs2_testbit - test a bit in the bitmaps
+ * @buffer: the buffer that holds the bitmaps
+ * @buflen: the length (in bytes) of the buffer
+ * @block: the block to read
+ *
+ */
+
+unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
+			   unsigned int buflen, uint32_t block)
+{
+	unsigned char *byte, *end, cur_state;
+	unsigned int bit;
+
+	byte = buffer + (block / GFS2_NBBY);
+	bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
+	end = buffer + buflen;
+
+	gfs2_assert(rgd->rd_sbd, byte < end);
+
+	cur_state = (*byte >> bit) & GFS2_BIT_MASK;
+
+	return cur_state;
+}
+
+/**
+ * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing
+ *       a block in a given allocation state.
+ * @buffer: the buffer that holds the bitmaps
+ * @buflen: the length (in bytes) of the buffer
+ * @goal: start search at this block's bit-pair (within @buffer)
+ * @old_state: GFS2_BLKST_XXX the state of the block we're looking for;
+ *       bit 0 = alloc(1)/free(0), bit 1 = meta(1)/data(0)
+ *
+ * Scope of @goal and returned block number is only within this bitmap buffer,
+ * not entire rgrp or filesystem.  @buffer will be offset from the actual
+ * beginning of a bitmap block buffer, skipping any head