Fixed MTP to work with TWRP

fs/gfs2/Kconfig

@@ -0,0 +1,34 @@
+config GFS2_FS
+	tristate "GFS2 file system support"
+	depends on (64BIT || LBDAF)
+	select FS_POSIX_ACL
+	select CRC32
+	select QUOTACTL
+	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 in a cluster, you will need to enable
+	  the locking module below. Documentation and utilities for GFS2 can
+	  be found here: http://sources.redhat.com/cluster
+
+	  The "nolock" lock module is now built in to GFS2 by default. If
+	  you want to use the DLM, be sure to enable IPv4/6 networking.
+
+config GFS2_FS_LOCKING_DLM
+	bool "GFS2 DLM locking"
+	depends on (GFS2_FS!=n) && NET && INET && (IPV6 || IPV6=n) && \
+		CONFIGFS_FS && SYSFS && (DLM=y || DLM=GFS2_FS)
+	help
+	  Multiple node locking module for GFS2
+
+	  Most users of GFS2 will require this. It provides the locking
+	  interface between GFS2 and the DLM, which is required to use GFS2
+	  in a cluster environment.

fs/gfs2/Makefile

@@ -0,0 +1,10 @@
+ccflags-y := -I$(src)
+obj-$(CONFIG_GFS2_FS) += gfs2.o
+gfs2-y := acl.o bmap.o dir.o xattr.o glock.o \
+	glops.o log.o lops.o main.o meta_io.o \
+	aops.o dentry.o export.o file.o \
+	ops_fstype.o inode.o quota.o \
+	recovery.o rgrp.o super.o sys.o trans.o util.o
+
+gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
+

fs/gfs2/acl.c

@@ -0,0 +1,121 @@
+/*
+ * 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/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "xattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+
+static const char *gfs2_acl_name(int type)
+{
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		return GFS2_POSIX_ACL_ACCESS;
+	case ACL_TYPE_DEFAULT:
+		return GFS2_POSIX_ACL_DEFAULT;
+	}
+	return NULL;
+}
+
+struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct posix_acl *acl;
+	const char *name;
+	char *data;
+	int len;
+
+	if (!ip->i_eattr)
+		return NULL;
+
+	name = gfs2_acl_name(type);
+	if (name == NULL)
+		return ERR_PTR(-EINVAL);
+
+	len = gfs2_xattr_acl_get(ip, name, &data);
+	if (len < 0)
+		return ERR_PTR(len);
+	if (len == 0)
+		return NULL;
+
+	acl = posix_acl_from_xattr(&init_user_ns, data, len);
+	kfree(data);
+	return acl;
+}
+
+int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int error;
+	int len;
+	char *data;
+	const char *name = gfs2_acl_name(type);
+
+	BUG_ON(name == NULL);
+
+	if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
+		return -E2BIG;
+
+	if (type == ACL_TYPE_ACCESS) {
+		umode_t mode = inode->i_mode;
+
+		error = posix_acl_equiv_mode(acl, &mode);
+		if (error < 0)
+			return error;
+
+		if (error == 0)
+			acl = NULL;
+
+		if (mode != inode->i_mode) {
+			inode->i_mode = mode;
+			mark_inode_dirty(inode);
+		}
+	}
+
+	if (acl) {
+		len = posix_acl_to_xattr(&init_user_ns, acl, NULL, 0);
+		if (len == 0)
+			return 0;
+		data = kmalloc(len, GFP_NOFS);
+		if (data == NULL)
+			return -ENOMEM;
+		error = posix_acl_to_xattr(&init_user_ns, acl, data, len);
+		if (error < 0)
+			goto out;
+	} else {
+		data = NULL;
+		len = 0;
+	}
+
+	error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS);
+	if (error)
+		goto out;
+
+	if (acl)
+		set_cached_acl(inode, type, acl);
+	else
+		forget_cached_acl(inode, type);
+out:
+	kfree(data);
+	return error;
+}

fs/gfs2/acl.h

@@ -0,0 +1,22 @@
+/*
+ * 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 __ACL_DOT_H__
+#define __ACL_DOT_H__
+
+#include "incore.h"
+
+#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
+#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
+#define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
+
+extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
+extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+
+#endif /* __ACL_DOT_H__ */

fs/gfs2/bmap.h

@@ -0,0 +1,61 @@
+/*
+ * 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 __BMAP_DOT_H__
+#define __BMAP_DOT_H__
+
+#include "inode.h"
+
+struct inode;
+struct gfs2_inode;
+struct page;
+
+
+/**
+ * gfs2_write_calc_reserv - calculate number of blocks needed to write to a file
+ * @ip: the file
+ * @len: the number of bytes to be written to the file
+ * @data_blocks: returns the number of data blocks required
+ * @ind_blocks: returns the number of indirect blocks required
+ *
+ */
+
+static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
+					  unsigned int len,
+					  unsigned int *data_blocks,
+					  unsigned int *ind_blocks)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int tmp;
+
+	BUG_ON(gfs2_is_dir(ip));
+	*data_blocks = (len >> sdp->sd_sb.sb_bsize_shift) + 3;
+	*ind_blocks = 3 * (sdp->sd_max_height - 1);
+
+	for (tmp = *data_blocks; tmp > sdp->sd_diptrs;) {
+		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+		*ind_blocks += tmp;
+	}
+}
+
+extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_block_map(struct inode *inode, sector_t lblock,
+			  struct buffer_head *bh, int create);
+extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
+			   u64 *dblock, unsigned *extlen);
+extern int gfs2_setattr_size(struct inode *inode, u64 size);
+extern void gfs2_trim_blocks(struct inode *inode);
+extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
+extern int gfs2_file_dealloc(struct gfs2_inode *ip);
+extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+				     unsigned int len);
+extern int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
+extern void gfs2_free_journal_extents(struct gfs2_jdesc *jd);
+
+#endif /* __BMAP_DOT_H__ */

fs/gfs2/dentry.c

@@ -0,0 +1,134 @@
+/*
+ * 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/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/namei.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "super.h"
+#include "util.h"
+#include "inode.h"
+
+/**
+ * gfs2_drevalidate - Check directory lookup consistency
+ * @dentry: the mapping to check
+ * @flags: lookup flags
+ *
+ * Check to make sure the lookup necessary to arrive at this inode from its
+ * parent is still good.
+ *
+ * Returns: 1 if the dentry is ok, 0 if it isn't
+ */
+
+static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *parent;
+	struct gfs2_sbd *sdp;
+	struct gfs2_inode *dip;
+	struct inode *inode;
+	struct gfs2_holder d_gh;
+	struct gfs2_inode *ip = NULL;
+	int error;
+	int had_lock = 0;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	parent = dget_parent(dentry);
+	sdp = GFS2_SB(parent->d_inode);
+	dip = GFS2_I(parent->d_inode);
+	inode = dentry->d_inode;
+
+	if (inode) {
+		if (is_bad_inode(inode))
+			goto invalid;
+		ip = GFS2_I(inode);
+	}
+
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		goto valid;
+
+	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
+	if (!had_lock) {
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+		if (error)
+			goto fail;
+	} 
+
+	error = gfs2_dir_check(parent->d_inode, &dentry->d_name, ip);
+	switch (error) {
+	case 0:
+		if (!inode)
+			goto invalid_gunlock;
+		break;
+	case -ENOENT:
+		if (!inode)
+			goto valid_gunlock;
+		goto invalid_gunlock;
+	default:
+		goto fail_gunlock;
+	}
+
+valid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+valid:
+	dput(parent);
+	return 1;
+
+invalid_gunlock:
+	if (!had_lock)
+		gfs2_glock_dq_uninit(&d_gh);
+invalid:
+	dput(parent);
+	return 0;
+
+fail_gunlock:
+	gfs2_glock_dq_uninit(&d_gh);
+fail:
+	dput(parent);
+	return 0;
+}
+
+static int gfs2_dhash(const struct dentry *dentry, struct qstr *str)
+{
+	str->hash = gfs2_disk_hash(str->name, str->len);
+	return 0;
+}
+
+static int gfs2_dentry_delete(const 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,
+};
+

fs/gfs2/dir.h

@@ -0,0 +1,86 @@
+/*
+ * 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 __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+#include <linux/dcache.h>
+#include <linux/crc32.h>
+
+struct inode;
+struct gfs2_inode;
+struct gfs2_inum;
+struct buffer_head;
+struct gfs2_dirent;
+
+struct gfs2_diradd {
+	unsigned nr_blocks;
+	struct gfs2_dirent *dent;
+	struct buffer_head *bh;
+	int save_loc;
+};
+
+extern struct inode *gfs2_dir_search(struct inode *dir,
+				     const struct qstr *filename,
+				     bool fail_on_exist);
+extern int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
+			  const struct gfs2_inode *ip);
+extern int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+			const struct gfs2_inode *ip, struct gfs2_diradd *da);
+static inline void gfs2_dir_no_add(struct gfs2_diradd *da)
+{
+	if (da->bh)
+		brelse(da->bh);
+	da->bh = NULL;
+}
+extern int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry);
+extern int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
+			 struct file_ra_state *f_ra);
+extern int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+			  const struct gfs2_inode *nip, unsigned int new_type);
+
+extern int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+
+extern int gfs2_diradd_alloc_required(struct inode *dir,
+				      const struct qstr *filename,
+				      struct gfs2_diradd *da);
+extern int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+				   struct buffer_head **bhp);
+extern void gfs2_dir_hash_inval(struct gfs2_inode *ip);
+
+static inline u32 gfs2_disk_hash(const char *data, int len)
+{
+        return crc32_le((u32)~0, data, len) ^ (u32)~0;
+}
+
+
+static inline void gfs2_str2qstr(struct qstr *name, const char *fname)
+{
+	name->name = fname;
+	name->len = strlen(fname);
+	name->hash = gfs2_disk_hash(name->name, name->len);
+}
+
+/* N.B. This probably ought to take inum & type as args as well */
+static inline void gfs2_qstr2dirent(const struct qstr *name, u16 reclen, struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_addr = cpu_to_be64(0);
+	dent->de_inum.no_formal_ino = cpu_to_be64(0);
+	dent->de_hash = cpu_to_be32(name->hash);
+	dent->de_rec_len = cpu_to_be16(reclen);
+	dent->de_name_len = cpu_to_be16(name->len);
+	dent->de_type = cpu_to_be16(0);
+	memset(dent->__pad, 0, sizeof(dent->__pad));
+	memcpy(dent + 1, name->name, name->len);
+}
+
+extern struct qstr gfs2_qdot;
+extern struct qstr gfs2_qdotdot;
+
+#endif /* __DIR_DOT_H__ */

fs/gfs2/export.c

@@ -0,0 +1,206 @@
+/*
+ * 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/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/exportfs.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "dir.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "super.h"
+#include "rgrp.h"
+#include "util.h"
+
+#define GFS2_SMALL_FH_SIZE 4
+#define GFS2_LARGE_FH_SIZE 8
+#define GFS2_OLD_FH_SIZE 10
+
+static int gfs2_encode_fh(struct inode *inode, __u32 *p, int *len,
+			  struct inode *parent)
+{
+	__be32 *fh = (__force __be32 *)p;
+	struct super_block *sb = inode->i_sb;
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (parent && (*len < GFS2_LARGE_FH_SIZE)) {
+		*len = GFS2_LARGE_FH_SIZE;
+		return FILEID_INVALID;
+	} else if (*len < GFS2_SMALL_FH_SIZE) {
+		*len = GFS2_SMALL_FH_SIZE;
+		return FILEID_INVALID;
+	}
+
+	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
+	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
+	fh[2] = cpu_to_be32(ip->i_no_addr >> 32);
+	fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
+	*len = GFS2_SMALL_FH_SIZE;
+
+	if (!parent || inode == sb->s_root->d_inode)
+		return *len;
+
+	ip = GFS2_I(parent);
+
+	fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32);
+	fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
+	fh[6] = cpu_to_be32(ip->i_no_addr >> 32);
+	fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF);
+	*len = GFS2_LARGE_FH_SIZE;
+
+	return *len;
+}
+
+struct get_name_filldir {
+	struct dir_context ctx;
+	struct gfs2_inum_host inum;
+	char *name;
+};
+
+static int get_name_filldir(void *opaque, const char *name, int length,
+			    loff_t offset, u64 inum, unsigned int type)
+{
+	struct get_name_filldir *gnfd = opaque;
+
+	if (inum != gnfd->inum.no_addr)
+		return 0;
+
+	memcpy(gnfd->name, name, length);
+	gnfd->name[length] = 0;
+
+	return 1;
+}
+
+static int gfs2_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct inode *dir = parent->d_inode;
+	struct inode *inode = child->d_inode;
+	struct gfs2_inode *dip, *ip;
+	struct get_name_filldir gnfd = {
+		.ctx.actor = get_name_filldir,
+		.name = name
+	};
+	struct gfs2_holder gh;
+	int error;
+	struct file_ra_state f_ra = { .start = 0 };
+
+	if (!dir)
+		return -EINVAL;
+
+	if (!S_ISDIR(dir->i_mode) || !inode)
+		return -EINVAL;
+
+	dip = GFS2_I(dir);
+	ip = GFS2_I(inode);
+
+	*name = 0;
+	gnfd.inum.no_addr = ip->i_no_addr;
+	gnfd.inum.no_formal_ino = ip->i_no_formal_ino;
+
+	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (error)
+		return error;
+
+	error = gfs2_dir_read(dir, &gnfd.ctx, &f_ra);
+
+	gfs2_glock_dq_uninit(&gh);
+
+	if (!error && !*name)
+		error = -ENOENT;
+
+	return error;
+}
+
+static struct dentry *gfs2_get_parent(struct dentry *child)
+{
+	return d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
+}
+
+static struct dentry *gfs2_get_dentry(struct super_block *sb,
+				      struct gfs2_inum_host *inum)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct inode *inode;
+
+	inode = gfs2_ilookup(sb, inum->no_addr, 0);
+	if (inode) {
+		if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
+		goto out_inode;
+	}
+
+	inode = gfs2_lookup_by_inum(sdp, inum->no_addr, &inum->no_formal_ino,
+				    GFS2_BLKST_DINODE);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+out_inode:
+	return d_obtain_alias(inode);
+}
+
+static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	struct gfs2_inum_host this;
+	__be32 *fh = (__force __be32 *)fid->raw;
+
+	switch (fh_type) {
+	case GFS2_SMALL_FH_SIZE:
+	case GFS2_LARGE_FH_SIZE:
+	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_SMALL_FH_SIZE)
+			return NULL;
+		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
+		this.no_formal_ino |= be32_to_cpu(fh[1]);
+		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
+		this.no_addr |= be32_to_cpu(fh[3]);
+		return gfs2_get_dentry(sb, &this);
+	default:
+		return NULL;
+	}
+}
+
+static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	struct gfs2_inum_host parent;
+	__be32 *fh = (__force __be32 *)fid->raw;
+
+	switch (fh_type) {
+	case GFS2_LARGE_FH_SIZE:
+	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_LARGE_FH_SIZE)
+			return NULL;
+		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
+		parent.no_formal_ino |= be32_to_cpu(fh[5]);
+		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
+		parent.no_addr |= be32_to_cpu(fh[7]);
+		return gfs2_get_dentry(sb, &parent);
+	default:
+		return NULL;
+	}
+}
+
+const struct export_operations gfs2_export_ops = {
+	.encode_fh = gfs2_encode_fh,
+	.fh_to_dentry = gfs2_fh_to_dentry,
+	.fh_to_parent = gfs2_fh_to_parent,
+	.get_name = gfs2_get_name,
+	.get_parent = gfs2_get_parent,
+};
+

fs/gfs2/gfs2.h

@@ -0,0 +1,26 @@
+/*
+ * 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 __GFS2_DOT_H__
+#define __GFS2_DOT_H__
+
+enum {
+	NO_CREATE = 0,
+	CREATE = 1,
+};
+
+enum {
+	NO_FORCE = 0,
+	FORCE = 1,
+};
+
+#define GFS2_FAST_NAME_SIZE 8
+
+#endif /* __GFS2_DOT_H__ */
+

fs/gfs2/glock.h

@@ -0,0 +1,250 @@
+/*
+ * 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 __GLOCK_DOT_H__
+#define __GLOCK_DOT_H__
+
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include "incore.h"
+
+/* Options for hostdata parser */
+
+enum {
+	Opt_jid,
+	Opt_id,
+	Opt_first,
+	Opt_nodir,
+	Opt_err,
+};
+
+/*
+ * lm_lockname types
+ */
+
+#define LM_TYPE_RESERVED	0x00
+#define LM_TYPE_NONDISK		0x01
+#define LM_TYPE_INODE		0x02
+#define LM_TYPE_RGRP		0x03
+#define LM_TYPE_META		0x04
+#define LM_TYPE_IOPEN		0x05
+#define LM_TYPE_FLOCK		0x06
+#define LM_TYPE_PLOCK		0x07
+#define LM_TYPE_QUOTA		0x08
+#define LM_TYPE_JOURNAL		0x09
+
+/*
+ * lm_lock() states
+ *
+ * SHARED is compatible with SHARED, not with DEFERRED or EX.
+ * DEFERRED is compatible with DEFERRED, not with SHARED or EX.
+ */
+
+#define LM_ST_UNLOCKED		0
+#define LM_ST_EXCLUSIVE		1
+#define LM_ST_DEFERRED		2
+#define LM_ST_SHARED		3
+
+/*
+ * lm_lock() flags
+ *
+ * LM_FLAG_TRY
+ * Don't wait to acquire the lock if it can't be granted immediately.
+ *
+ * LM_FLAG_TRY_1CB
+ * Send one blocking callback if TRY is set and the lock is not granted.
+ *
+ * LM_FLAG_NOEXP
+ * GFS sets this flag on lock requests it makes while doing journal recovery.
+ * These special requests should not be blocked due to the recovery like
+ * ordinary locks would be.
+ *
+ * LM_FLAG_ANY
+ * A SHARED request may also be granted in DEFERRED, or a DEFERRED request may
+ * also be granted in SHARED.  The preferred state is whichever is compatible
+ * with other granted locks, or the specified state if no other locks exist.
+ *
+ * LM_FLAG_PRIORITY
+ * Override fairness considerations.  Suppose a lock is held in a shared state
+ * and there is a pending request for the deferred state.  A shared lock
+ * request with the priority flag would be allowed to bypass the deferred
+ * request and directly join the other shared lock.  A shared lock request
+ * without the priority flag might be forced to wait until the deferred
+ * requested had acquired and released the lock.
+ */
+
+#define LM_FLAG_TRY		0x00000001
+#define LM_FLAG_TRY_1CB		0x00000002
+#define LM_FLAG_NOEXP		0x00000004
+#define LM_FLAG_ANY		0x00000008
+#define LM_FLAG_PRIORITY	0x00000010
+#define GL_ASYNC		0x00000040
+#define GL_EXACT		0x00000080
+#define GL_SKIP			0x00000100
+#define GL_NOCACHE		0x00000400
+  
+/*
+ * lm_async_cb return flags
+ *
+ * LM_OUT_ST_MASK
+ * Masks the lower two bits of lock state in the returned value.
+ *
+ * LM_OUT_CANCELED
+ * The lock request was canceled.
+ *
+ */
+
+#define LM_OUT_ST_MASK		0x00000003
+#define LM_OUT_CANCELED		0x00000008
+#define LM_OUT_ERROR		0x00000004
+
+/*
+ * lm_recovery_done() messages
+ */
+
+#define LM_RD_GAVEUP		308
+#define LM_RD_SUCCESS		309
+
+#define GLR_TRYFAILED		13
+
+#define GL_GLOCK_MAX_HOLD        (long)(HZ / 5)
+#define GL_GLOCK_DFT_HOLD        (long)(HZ / 5)
+#define GL_GLOCK_MIN_HOLD        (long)(10)
+#define GL_GLOCK_HOLD_INCR       (long)(HZ / 20)
+#define GL_GLOCK_HOLD_DECR       (long)(HZ / 40)
+
+struct lm_lockops {
+	const char *lm_proto_name;
+	int (*lm_mount) (struct gfs2_sbd *sdp, const char *table);
+	void (*lm_first_done) (struct gfs2_sbd *sdp);
+	void (*lm_recovery_result) (struct gfs2_sbd *sdp, unsigned int jid,
+				    unsigned int result);
+	void (*lm_unmount) (struct gfs2_sbd *sdp);
+	void (*lm_withdraw) (struct gfs2_sbd *sdp);
+	void (*lm_put_lock) (struct gfs2_glock *gl);
+	int (*lm_lock) (struct gfs2_glock *gl, unsigned int req_state,
+			unsigned int flags);
+	void (*lm_cancel) (struct gfs2_glock *gl);
+	const match_table_t *lm_tokens;
+};
+
+extern struct workqueue_struct *gfs2_delete_workqueue;
+static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+	struct pid *pid;
+
+	/* Look in glock's list of holders for one with current task as owner */
+	spin_lock(&gl->gl_spin);
+	pid = task_pid(current);
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			break;
+		if (gh->gh_owner_pid == pid)
+			goto out;
+	}
+	gh = NULL;
+out:
+	spin_unlock(&gl->gl_spin);
+
+	return gh;
+}
+
+static inline int gfs2_glock_is_held_excl(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_EXCLUSIVE;
+}
+
+static inline int gfs2_glock_is_held_dfrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_DEFERRED;
+}
+
+static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl)
+{
+	return gl->gl_state == LM_ST_SHARED;
+}
+
+static inline struct address_space *gfs2_glock2aspace(struct gfs2_glock *gl)
+{
+	if (gl->gl_ops->go_flags & GLOF_ASPACE)
+		return (struct address_space *)(gl + 1);
+	return NULL;
+}
+
+extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
+			  const struct gfs2_glock_operations *glops,
+			  int create, struct gfs2_glock **glp);
+extern void gfs2_glock_put(struct gfs2_glock *gl);
+extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
+			     unsigned flags, struct gfs2_holder *gh);
+extern void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			       struct gfs2_holder *gh);
+extern void gfs2_holder_uninit(struct gfs2_holder *gh);
+extern int gfs2_glock_nq(struct gfs2_holder *gh);
+extern int gfs2_glock_poll(struct gfs2_holder *gh);
+extern int gfs2_glock_wait(struct gfs2_holder *gh);
+extern void gfs2_glock_dq(struct gfs2_holder *gh);
+extern void gfs2_glock_dq_wait(struct gfs2_holder *gh);
+extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
+extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
+			     const struct gfs2_glock_operations *glops,
+			     unsigned int state, int flags,
+			     struct gfs2_holder *gh);
+extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+extern void gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl);
+#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0)
+extern __printf(2, 3)
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
+
+/**
+ * gfs2_glock_nq_init - initialize a holder and enqueue it on a glock
+ * @gl: the glock
+ * @state: the state we're requesting
+ * @flags: the modifier flags
+ * @gh: the holder structure
+ *
+ * Returns: 0, GLR_*, or errno
+ */
+
+static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
+				     unsigned int state, int flags,
+				     struct gfs2_holder *gh)
+{
+	int error;
+
+	gfs2_holder_init(gl, state, flags, gh);
+
+	error = gfs2_glock_nq(gh);
+	if (error)
+		gfs2_holder_uninit(gh);
+
+	return error;
+}
+
+extern void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state);
+extern void gfs2_glock_complete(struct gfs2_glock *gl, int ret);
+extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
+extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip);
+extern void gfs2_glock_thaw(struct gfs2_sbd *sdp);
+extern void gfs2_glock_add_to_lru(struct gfs2_glock *gl);
+extern void gfs2_glock_free(struct gfs2_glock *gl);
+
+extern int __init gfs2_glock_init(void);
+extern void gfs2_glock_exit(void);
+
+extern int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
+extern void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
+extern int gfs2_register_debugfs(void);
+extern void gfs2_unregister_debugfs(void);
+
+extern const struct lm_lockops gfs2_dlm_ops;
+
+#endif /* __GLOCK_DOT_H__ */

fs/gfs2/glops.c

@@ -0,0 +1,618 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 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/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/posix_acl.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "util.h"
+#include "trans.h"
+#include "dir.h"
+
+static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
+{
+	fs_err(gl->gl_sbd, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page state 0x%lx\n",
+	       bh, (unsigned long long)bh->b_blocknr, bh->b_state,
+	       bh->b_page->mapping, bh->b_page->flags);
+	fs_err(gl->gl_sbd, "AIL glock %u:%llu mapping %p\n",
+	       gl->gl_name.ln_type, gl->gl_name.ln_number,
+	       gfs2_glock2aspace(gl));
+	gfs2_lm_withdraw(gl->gl_sbd, "AIL error\n");
+}
+
+/**
+ * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
+ * @gl: the glock
+ * @fsync: set when called from fsync (not all buffers will be clean)
+ *
+ * None of the buffers should be dirty, locked, or pinned.
+ */
+
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
+			     unsigned int nr_revokes)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct list_head *head = &gl->gl_ail_list;
+	struct gfs2_bufdata *bd, *tmp;
+	struct buffer_head *bh;
+	const unsigned long b_state = (1UL << BH_Dirty)|(1UL << BH_Pinned)|(1UL << BH_Lock);
+
+	gfs2_log_lock(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) {
+		if (nr_revokes == 0)
+			break;
+		bh = bd->bd_bh;
+		if (bh->b_state & b_state) {
+			if (fsync)
+				continue;
+			gfs2_ail_error(gl, bh);
+		}
+		gfs2_trans_add_revoke(sdp, bd);
+		nr_revokes--;
+	}
+	GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count));
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+}
+
+
+static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_trans tr;
+
+	memset(&tr, 0, sizeof(tr));
+	INIT_LIST_HEAD(&tr.tr_buf);
+	INIT_LIST_HEAD(&tr.tr_databuf);
+	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
+
+	if (!tr.tr_revokes)
+		return;
+
+	/* A shortened, inline version of gfs2_trans_begin()
+         * tr->alloced is not set since the transaction structure is
+         * on the stack */
+	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
+	tr.tr_ip = _RET_IP_;
+	sb_start_intwrite(sdp->sd_vfs);
+	if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) {
+		sb_end_intwrite(sdp->sd_vfs);
+		return;
+	}
+	WARN_ON_ONCE(current->journal_info);
+	current->journal_info = &tr;
+
+	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
+
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+}
+
+void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	unsigned int revokes = atomic_read(&gl->gl_ail_count);
+	unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
+	int ret;
+
+	if (!revokes)
+		return;
+
+	while (revokes > max_revokes)
+		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
+
+	ret = gfs2_trans_begin(sdp, 0, max_revokes);
+	if (ret)
+		return;
+	__gfs2_ail_flush(gl, fsync, max_revokes);
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+}
+
+/**
+ * rgrp_go_sync - sync out the metadata for this glock
+ * @gl: the glock
+ *
+ * Called when demoting or unlocking an EX glock.  We must flush
+ * to disk all dirty buffers/pages relating to this glock, and must not
+ * not return to caller to demote/unlock the glock until I/O is complete.
+ */
+
+static void rgrp_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct address_space *mapping = &sdp->sd_aspace;
+	struct gfs2_rgrpd *rgd;
+	int error;
+
+	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
+		return;
+	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
+
+	gfs2_log_flush(sdp, gl, NORMAL_FLUSH);
+	filemap_fdatawrite_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
+	error = filemap_fdatawait_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
+	mapping_set_error(mapping, error);
+	gfs2_ail_empty_gl(gl);
+
+	spin_lock(&gl->gl_spin);
+	rgd = gl->gl_object;
+	if (rgd)
+		gfs2_free_clones(rgd);
+	spin_unlock(&gl->gl_spin);
+}
+
+/**
+ * rgrp_go_inval - invalidate the metadata for this glock
+ * @gl: the glock
+ * @flags:
+ *
+ * We never used LM_ST_DEFERRED with resource groups, so that we
+ * should always see the metadata flag set here.
+ *
+ */
+
+static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct address_space *mapping = &sdp->sd_aspace;
+
+	WARN_ON_ONCE(!(flags & DIO_METADATA));
+	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	truncate_inode_pages_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
+
+	if (gl->gl_object) {
+		struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object;
+		rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+	}
+}
+
+/**
+ * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * @gl: the glock protecting the inode
+ *
+ */
+
+static void inode_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	int error;
+
+	if (ip && !S_ISREG(ip->i_inode.i_mode))
+		ip = NULL;
+	if (ip) {
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+		inode_dio_wait(&ip->i_inode);
+	}
+	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
+		return;
+
+	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
+
+	gfs2_log_flush(gl->gl_sbd, gl, NORMAL_FLUSH);
+	filemap_fdatawrite(metamapping);
+	if (ip) {
+		struct address_space *mapping = ip->i_inode.i_mapping;
+		filemap_fdatawrite(mapping);
+		error = filemap_fdatawait(mapping);
+		mapping_set_error(mapping, error);
+	}
+	error = filemap_fdatawait(metamapping);
+	mapping_set_error(metamapping, error);
+	gfs2_ail_empty_gl(gl);
+	/*
+	 * Writeback of the data mapping may cause the dirty flag to be set
+	 * so we have to clear it again here.
+	 */
+	smp_mb__before_atomic();
+	clear_bit(GLF_DIRTY, &gl->gl_flags);
+}
+
+/**
+ * inode_go_inval - prepare a inode glock to be released
+ * @gl: the glock
+ * @flags:
+ *
+ * Normally we invalidate everything, but if we are moving into
+ * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
+ * can keep hold of the metadata, since it won't have changed.
+ *
+ */
+
+static void inode_go_inval(struct gfs2_glock *gl, int flags)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+
+	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
+
+	if (flags & DIO_METADATA) {
+		struct address_space *mapping = gfs2_glock2aspace(gl);
+		truncate_inode_pages(mapping, 0);
+		if (ip) {
+			set_bit(GIF_INVALID, &ip->i_flags);
+			forget_all_cached_acls(&ip->i_inode);
+			gfs2_dir_hash_inval(ip);
+		}
+	}
+
+	if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) {
+		gfs2_log_flush(gl->gl_sbd, NULL, NORMAL_FLUSH);
+		gl->gl_sbd->sd_rindex_uptodate = 0;
+	}
+	if (ip && S_ISREG(ip->i_inode.i_mode))
+		truncate_inode_pages(ip->i_inode.i_mapping, 0);
+}
+
+/**
+ * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int inode_go_demote_ok(const struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_holder *gh;
+
+	if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
+		return 0;
+
+	if (!list_empty(&gl->gl_holders)) {
+		gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+		if (gh->gh_list.next != &gl->gl_holders)
+			return 0;
+	}
+
+	return 1;
+}
+
+/**
+ * gfs2_set_nlink - Set the inode's link count based on on-disk info
+ * @inode: The inode in question
+ * @nlink: The link count
+ *
+ * If the link count has hit zero, it must never be raised, whatever the
+ * on-disk inode might say. When new struct inodes are created the link
+ * count is set to 1, so that we can safely use this test even when reading
+ * in on disk information for the first time.
+ */
+
+static void gfs2_set_nlink(struct inode *inode, u32 nlink)
+{
+	/*
+	 * We will need to review setting the nlink count here in the
+	 * light of the forthcoming ro bind mount work. This is a reminder
+	 * to do that.
+	 */
+	if ((inode->i_nlink != nlink) && (inode->i_nlink != 0)) {
+		if (nlink == 0)
+			clear_nlink(inode);
+		else
+			set_nlink(inode, nlink);
+	}
+}
+
+static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
+{
+	const struct gfs2_dinode *str = buf;
+	struct timespec atime;
+	u16 height, depth;
+
+	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
+		goto corrupt;
+	ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
+	ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
+	ip->i_inode.i_rdev = 0;
+	switch (ip->i_inode.i_mode & S_IFMT) {
+	case S_IFBLK:
+	case S_IFCHR:
+		ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
+					   be32_to_cpu(str->di_minor));
+		break;
+	};
+
+	i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
+	i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid));
+	gfs2_set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink));
+	i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
+	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
+	atime.tv_sec = be64_to_cpu(str->di_atime);
+	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+		ip->i_inode.i_atime = atime;
+	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
+	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
+	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
+	ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
+
+	ip->i_goal = be64_to_cpu(str->di_goal_meta);
+	ip->i_generation = be64_to_cpu(str->di_generation);
+
+	ip->i_diskflags = be32_to_cpu(str->di_flags);
+	ip->i_eattr = be64_to_cpu(str->di_eattr);
+	/* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */
+	gfs2_set_inode_flags(&ip->i_inode);
+	height = be16_to_cpu(str->di_height);
+	if (unlikely(height > GFS2_MAX_META_HEIGHT))
+		goto corrupt;
+	ip->i_height = (u8)height;
+
+	depth = be16_to_cpu(str->di_depth);
+	if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
+		goto corrupt;
+	ip->i_depth = (u8)depth;
+	ip->i_entries = be32_to_cpu(str->di_entries);
+
+	if (S_ISREG(ip->i_inode.i_mode))
+		gfs2_set_aops(&ip->i_inode);
+
+	return 0;
+corrupt:
+	gfs2_consist_inode(ip);
+	return -EIO;
+}
+
+/**
+ * gfs2_inode_refresh - Refresh the incore copy of the dinode
+ * @ip: The GFS2 inode
+ *
+ * Returns: errno
+ */
+
+int gfs2_inode_refresh(struct gfs2_inode *ip)
+{
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	error = gfs2_dinode_in(ip, dibh->b_data);
+	brelse(dibh);
+	clear_bit(GIF_INVALID, &ip->i_flags);
+
+	return error;
+}
+
+/**
+ * inode_go_lock - operation done after an inode lock is locked by a process
+ * @gl: the glock
+ * @flags:
+ *
+ * Returns: errno
+ */
+
+static int inode_go_lock(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = gl->gl_object;
+	int error = 0;
+
+	if (!ip || (gh->gh_flags & GL_SKIP))
+		return 0;
+
+	if (test_bit(GIF_INVALID, &ip->i_flags)) {
+		error = gfs2_inode_refresh(ip);
+		if (error)
+			return error;
+	}
+
+	if (gh->gh_state != LM_ST_DEFERRED)
+		inode_dio_wait(&ip->i_inode);
+
+	if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
+	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
+	    (gh->gh_state == LM_ST_EXCLUSIVE)) {
+		spin_lock(&sdp->sd_trunc_lock);
+		if (list_empty(&ip->i_trunc_list))
+			list_add(&sdp->sd_trunc_list, &ip->i_trunc_list);
+		spin_unlock(&sdp->sd_trunc_lock);
+		wake_up(&sdp->sd_quota_wait);
+		return 1;
+	}
+
+	return error;
+}
+
+/**
+ * inode_go_dump - print information about an inode
+ * @seq: The iterator
+ * @ip: the inode
+ *
+ */
+
+static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_inode *ip = gl->gl_object;
+	if (ip == NULL)
+		return;
+	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n",
+		  (unsigned long long)ip->i_no_formal_ino,
+		  (unsigned long long)ip->i_no_addr,
+		  IF2DT(ip->i_inode.i_mode), ip->i_flags,
+		  (unsigned int)ip->i_diskflags,
+		  (unsigned long long)i_size_read(&ip->i_inode));
+}
+
+/**
+ * freeze_go_sync - promote/demote the freeze glock
+ * @gl: the glock
+ * @state: the requested state
+ * @flags:
+ *
+ */
+
+static void freeze_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	DEFINE_WAIT(wait);
+
+	if (gl->gl_state == LM_ST_SHARED &&
+	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		atomic_set(&sdp->sd_log_freeze, 1);
+		wake_up(&sdp->sd_logd_waitq);
+		do {
+			prepare_to_wait(&sdp->sd_log_frozen_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&sdp->sd_log_freeze))
+				io_schedule();
+		} while(atomic_read(&sdp->sd_log_freeze));
+		finish_wait(&sdp->sd_log_frozen_wait, &wait);
+	}
+}
+
+/**
+ * freeze_go_xmote_bh - After promoting/demoting the freeze glock
+ * @gl: the glock
+ *
+ */
+
+static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+	struct gfs2_glock *j_gl = ip->i_gl;
+	struct gfs2_log_header_host head;
+	int error;
+
+	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
+
+		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+		if (error)
+			gfs2_consist(sdp);
+		if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
+			gfs2_consist(sdp);
+
+		/*  Initialize some head of the log stuff  */
+		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+			sdp->sd_log_sequence = head.lh_sequence + 1;
+			gfs2_log_pointers_init(sdp, head.lh_blkno);
+		}
+	}
+	return 0;
+}
+
+/**
+ * trans_go_demote_ok
+ * @gl: the glock
+ *
+ * Always returns 0
+ */
+
+static int freeze_go_demote_ok(const struct gfs2_glock *gl)
+{
+	return 0;
+}
+
+/**
+ * iopen_go_callback - schedule the dcache entry for the inode to be deleted
+ * @gl: the glock
+ *
+ * gl_spin lock is held while calling this
+ */
+static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
+{
+	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY))
+		return;
+
+	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
+	    gl->gl_state == LM_ST_SHARED && ip) {
+		gl->gl_lockref.count++;
+		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
+			gl->gl_lockref.count--;
+	}
+}
+
+const struct gfs2_glock_operations gfs2_meta_glops = {
+	.go_type = LM_TYPE_META,
+};
+
+const struct gfs2_glock_operations gfs2_inode_glops = {
+	.go_sync = inode_go_sync,
+	.go_inval = inode_go_inval,
+	.go_demote_ok = inode_go_demote_ok,
+	.go_lock = inode_go_lock,
+	.go_dump = inode_go_dump,
+	.go_type = LM_TYPE_INODE,
+	.go_flags = GLOF_ASPACE,
+};
+
+const struct gfs2_glock_operations gfs2_rgrp_glops = {
+	.go_sync = rgrp_go_sync,
+	.go_inval = rgrp_go_inval,
+	.go_lock = gfs2_rgrp_go_lock,
+	.go_unlock = gfs2_rgrp_go_unlock,
+	.go_dump = gfs2_rgrp_dump,
+	.go_type = LM_TYPE_RGRP,
+	.go_flags = GLOF_LVB,
+};
+
+const struct gfs2_glock_operations gfs2_freeze_glops = {
+	.go_sync = freeze_go_sync,
+	.go_xmote_bh = freeze_go_xmote_bh,
+	.go_demote_ok = freeze_go_demote_ok,
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_iopen_glops = {
+	.go_type = LM_TYPE_IOPEN,
+	.go_callback = iopen_go_callback,
+};
+
+const struct gfs2_glock_operations gfs2_flock_glops = {
+	.go_type = LM_TYPE_FLOCK,
+};
+
+const struct gfs2_glock_operations gfs2_nondisk_glops = {
+	.go_type = LM_TYPE_NONDISK,
+};
+
+const struct gfs2_glock_operations gfs2_quota_glops = {
+	.go_type = LM_TYPE_QUOTA,
+	.go_flags = GLOF_LVB,
+};
+
+const struct gfs2_glock_operations gfs2_journal_glops = {
+	.go_type = LM_TYPE_JOURNAL,
+};
+
+const struct gfs2_glock_operations *gfs2_glops_list[] = {
+	[LM_TYPE_META] = &gfs2_meta_glops,
+	[LM_TYPE_INODE] = &gfs2_inode_glops,
+	[LM_TYPE_RGRP] = &gfs2_rgrp_glops,
+	[LM_TYPE_IOPEN] = &gfs2_iopen_glops,
+	[LM_TYPE_FLOCK] = &gfs2_flock_glops,
+	[LM_TYPE_NONDISK] = &gfs2_nondisk_glops,
+	[LM_TYPE_QUOTA] = &gfs2_quota_glops,
+	[LM_TYPE_JOURNAL] = &gfs2_journal_glops,
+};
+

fs/gfs2/glops.h

@@ -0,0 +1,28 @@
+/*
+ * 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 __GLOPS_DOT_H__
+#define __GLOPS_DOT_H__
+
+#include "incore.h"
+
+extern const struct gfs2_glock_operations gfs2_meta_glops;
+extern const struct gfs2_glock_operations gfs2_inode_glops;
+extern const struct gfs2_glock_operations gfs2_rgrp_glops;
+extern const struct gfs2_glock_operations gfs2_freeze_glops;
+extern const struct gfs2_glock_operations gfs2_iopen_glops;
+extern const struct gfs2_glock_operations gfs2_flock_glops;
+extern const struct gfs2_glock_operations gfs2_nondisk_glops;
+extern const struct gfs2_glock_operations gfs2_quota_glops;
+extern const struct gfs2_glock_operations gfs2_journal_glops;
+extern const struct gfs2_glock_operations *gfs2_glops_list[];
+
+extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
+
+#endif /* __GLOPS_DOT_H__ */

fs/gfs2/incore.h

@@ -0,0 +1,834 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 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 __INCORE_DOT_H__
+#define __INCORE_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/workqueue.h>
+#include <linux/dlm.h>
+#include <linux/buffer_head.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <linux/completion.h>
+#include <linux/rbtree.h>
+#include <linux/ktime.h>
+#include <linux/percpu.h>
+#include <linux/lockref.h>
+
+#define DIO_WAIT	0x00000010
+#define DIO_METADATA	0x00000020
+
+struct gfs2_log_operations;
+struct gfs2_bufdata;
+struct gfs2_holder;
+struct gfs2_glock;
+struct gfs2_quota_data;
+struct gfs2_trans;
+struct gfs2_jdesc;
+struct gfs2_sbd;
+struct lm_lockops;
+
+typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret);
+
+struct gfs2_log_header_host {
+	u64 lh_sequence;	/* Sequence number of this transaction */
+	u32 lh_flags;		/* GFS2_LOG_HEAD_... */
+	u32 lh_tail;		/* Block number of log tail */
+	u32 lh_blkno;
+	u32 lh_hash;
+};
+
+/*
+ * Structure of operations that are associated with each
+ * type of element in the log.
+ */
+
+struct gfs2_log_operations {
+	void (*lo_before_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
+	void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
+	void (*lo_before_scan) (struct gfs2_jdesc *jd,
+				struct gfs2_log_header_host *head, int pass);
+	int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start,
+				 struct gfs2_log_descriptor *ld, __be64 *ptr,
+				 int pass);
+	void (*lo_after_scan) (struct gfs2_jdesc *jd, int error, int pass);
+	const char *lo_name;
+};
+
+#define GBF_FULL 1
+
+struct gfs2_bitmap {
+	struct buffer_head *bi_bh;
+	char *bi_clone;
+	unsigned long bi_flags;
+	u32 bi_offset;
+	u32 bi_start;
+	u32 bi_len;
+	u32 bi_blocks;
+};
+
+struct gfs2_rgrpd {
+	struct rb_node rd_node;		/* Link with superblock */
+	struct gfs2_glock *rd_gl;	/* Glock for this rgrp */
+	u64 rd_addr;			/* grp block disk address */
+	u64 rd_data0;			/* first data location */
+	u32 rd_length;			/* length of rgrp header in fs blocks */
+	u32 rd_data;			/* num of data blocks in rgrp */
+	u32 rd_bitbytes;		/* number of bytes in data bitmaps */
+	u32 rd_free;
+	u32 rd_reserved;                /* number of blocks reserved */
+	u32 rd_free_clone;
+	u32 rd_dinodes;
+	u64 rd_igeneration;
+	struct gfs2_bitmap *rd_bits;
+	struct gfs2_sbd *rd_sbd;
+	struct gfs2_rgrp_lvb *rd_rgl;
+	u32 rd_last_alloc;
+	u32 rd_flags;
+	u32 rd_extfail_pt;		/* extent failure point */
+#define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
+#define GFS2_RDF_UPTODATE	0x20000000 /* rg is up to date */
+#define GFS2_RDF_ERROR		0x40000000 /* error in rg */
+#define GFS2_RDF_MASK		0xf0000000 /* mask for internal flags */
+	spinlock_t rd_rsspin;           /* protects reservation related vars */
+	struct rb_root rd_rstree;       /* multi-block reservation tree */
+};
+
+struct gfs2_rbm {
+	struct gfs2_rgrpd *rgd;
+	u32 offset;		/* The offset is bitmap relative */
+	int bii;		/* Bitmap index */
+};
+
+static inline struct gfs2_bitmap *rbm_bi(const struct gfs2_rbm *rbm)
+{
+	return rbm->rgd->rd_bits + rbm->bii;
+}
+
+static inline u64 gfs2_rbm_to_block(const struct gfs2_rbm *rbm)
+{
+	return rbm->rgd->rd_data0 + (rbm_bi(rbm)->bi_start * GFS2_NBBY) +
+		rbm->offset;
+}
+
+static inline bool gfs2_rbm_eq(const struct gfs2_rbm *rbm1,
+			       const struct gfs2_rbm *rbm2)
+{
+	return (rbm1->rgd == rbm2->rgd) && (rbm1->bii == rbm2->bii) &&
+	       (rbm1->offset == rbm2->offset);
+}
+
+enum gfs2_state_bits {
+	BH_Pinned = BH_PrivateStart,
+	BH_Escaped = BH_PrivateStart + 1,
+	BH_Zeronew = BH_PrivateStart + 2,
+};
+
+BUFFER_FNS(Pinned, pinned)
+TAS_BUFFER_FNS(Pinned, pinned)
+BUFFER_FNS(Escaped, escaped)
+TAS_BUFFER_FNS(Escaped, escaped)
+BUFFER_FNS(Zeronew, zeronew)
+TAS_BUFFER_FNS(Zeronew, zeronew)
+
+struct gfs2_bufdata {
+	struct buffer_head *bd_bh;
+	struct gfs2_glock *bd_gl;
+	u64 bd_blkno;
+
+	struct list_head bd_list;
+	const struct gfs2_log_operations *bd_ops;
+
+	struct gfs2_trans *bd_tr;
+	struct list_head bd_ail_st_list;
+	struct list_head bd_ail_gl_list;
+};
+
+/*
+ * Internally, we prefix things with gdlm_ and GDLM_ (for gfs-dlm) since a
+ * prefix of lock_dlm_ gets awkward.
+ */
+
+#define GDLM_STRNAME_BYTES	25
+#define GDLM_LVB_SIZE		32
+
+/*
+ * ls_recover_flags:
+ *
+ * DFL_BLOCK_LOCKS: dlm is in recovery and will grant locks that had been
+ * held by failed nodes whose journals need recovery.  Those locks should
+ * only be used for journal recovery until the journal recovery is done.
+ * This is set by the dlm recover_prep callback and cleared by the
+ * gfs2_control thread when journal recovery is complete.  To avoid
+ * races between recover_prep setting and gfs2_control clearing, recover_spin
+ * is held while changing this bit and reading/writing recover_block
+ * and recover_start.
+ *
+ * DFL_NO_DLM_OPS: dlm lockspace ops/callbacks are not being used.
+ *
+ * DFL_FIRST_MOUNT: this node is the first to mount this fs and is doing
+ * recovery of all journals before allowing other nodes to mount the fs.
+ * This is cleared when FIRST_MOUNT_DONE is set.
+ *
+ * DFL_FIRST_MOUNT_DONE: this node was the first mounter, and has finished
+ * recovery of all journals, and now allows other nodes to mount the fs.
+ *
+ * DFL_MOUNT_DONE: gdlm_mount has completed successfully and cleared
+ * BLOCK_LOCKS for the first time.  The gfs2_control thread should now
+ * control clearing BLOCK_LOCKS for further recoveries.
+ *
+ * DFL_UNMOUNT: gdlm_unmount sets to keep sdp off gfs2_control_wq.
+ *
+ * DFL_DLM_RECOVERY: set while dlm is in recovery, between recover_prep()
+ * and recover_done(), i.e. set while recover_block == recover_start.
+ */
+
+enum {
+	DFL_BLOCK_LOCKS		= 0,
+	DFL_NO_DLM_OPS		= 1,
+	DFL_FIRST_MOUNT		= 2,
+	DFL_FIRST_MOUNT_DONE	= 3,
+	DFL_MOUNT_DONE		= 4,
+	DFL_UNMOUNT		= 5,
+	DFL_DLM_RECOVERY	= 6,
+};
+
+struct lm_lockname {
+	u64 ln_number;
+	unsigned int ln_type;
+};
+
+#define lm_name_equal(name1, name2) \
+        (((name1)->ln_number == (name2)->ln_number) && \
+         ((name1)->ln_type == (name2)->ln_type))
+
+
+struct gfs2_glock_operations {
+	void (*go_sync) (struct gfs2_glock *gl);
+	int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
+	void (*go_inval) (struct gfs2_glock *gl, int flags);
+	int (*go_demote_ok) (const struct gfs2_glock *gl);
+	int (*go_lock) (struct gfs2_holder *gh);
+	void (*go_unlock) (struct gfs2_holder *gh);
+	void (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
+	void (*go_callback)(struct gfs2_glock *gl, bool remote);
+	const int go_type;
+	const unsigned long go_flags;
+#define GLOF_ASPACE 1
+#define GLOF_LVB    2
+};
+
+enum {
+	GFS2_LKS_SRTT = 0,	/* Non blocking smoothed round trip time */
+	GFS2_LKS_SRTTVAR = 1,	/* Non blocking smoothed variance */
+	GFS2_LKS_SRTTB = 2,	/* Blocking smoothed round trip time */
+	GFS2_LKS_SRTTVARB = 3,	/* Blocking smoothed variance */
+	GFS2_LKS_SIRT = 4,	/* Smoothed Inter-request time */
+	GFS2_LKS_SIRTVAR = 5,	/* Smoothed Inter-request variance */
+	GFS2_LKS_DCOUNT = 6,	/* Count of dlm requests */
+	GFS2_LKS_QCOUNT = 7,	/* Count of gfs2_holder queues */
+	GFS2_NR_LKSTATS
+};
+
+struct gfs2_lkstats {
+	s64 stats[GFS2_NR_LKSTATS];
+};
+
+enum {
+	/* States */
+	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
+	HIF_FIRST		= 7,
+	HIF_WAIT		= 10,
+};
+
+struct gfs2_holder {
+	struct list_head gh_list;
+
+	struct gfs2_glock *gh_gl;
+	struct pid *gh_owner_pid;
+	unsigned int gh_state;
+	unsigned gh_flags;
+
+	int gh_error;
+	unsigned long gh_iflags; /* HIF_... */
+	unsigned long gh_ip;
+};
+
+/* Number of quota types we support */
+#define GFS2_MAXQUOTAS 2
+
+/* Resource group multi-block reservation, in order of appearance:
+
+   Step 1. Function prepares to write, allocates a mb, sets the size hint.
+   Step 2. User calls inplace_reserve to target an rgrp, sets the rgrp info
+   Step 3. Function get_local_rgrp locks the rgrp, determines which bits to use
+   Step 4. Bits are assigned from the rgrp based on either the reservation
+           or wherever it can.
+*/
+
+struct gfs2_blkreserv {
+	/* components used during write (step 1): */
+	atomic_t rs_sizehint;         /* hint of the write size */
+
+	struct gfs2_holder rs_rgd_gh; /* Filled in by get_local_rgrp */
+	struct rb_node rs_node;       /* link to other block reservations */
+	struct gfs2_rbm rs_rbm;       /* Start of reservation */
+	u32 rs_free;                  /* how many blocks are still free */
+	u64 rs_inum;                  /* Inode number for reservation */
+
+	/* ancillary quota stuff */
+	struct gfs2_quota_data *rs_qa_qd[2 * GFS2_MAXQUOTAS];
+	struct gfs2_holder rs_qa_qd_ghs[2 * GFS2_MAXQUOTAS];
+	unsigned int rs_qa_qd_num;
+};
+
+/*
+ * Allocation parameters
+ * @target: The number of blocks we'd ideally like to allocate
+ * @aflags: The flags (e.g. Orlov flag)
+ *
+ * The intent is to gradually expand this structure over time in
+ * order to give more information, e.g. alignment, min extent size
+ * to the allocation code.
+ */
+struct gfs2_alloc_parms {
+	u32 target;
+	u32 aflags;
+};
+
+enum {
+	GLF_LOCK			= 1,
+	GLF_DEMOTE			= 3,
+	GLF_PENDING_DEMOTE		= 4,
+	GLF_DEMOTE_IN_PROGRESS		= 5,
+	GLF_DIRTY			= 6,
+	GLF_LFLUSH			= 7,
+	GLF_INVALIDATE_IN_PROGRESS	= 8,
+	GLF_REPLY_PENDING		= 9,
+	GLF_INITIAL			= 10,
+	GLF_FROZEN			= 11,
+	GLF_QUEUED			= 12,
+	GLF_LRU				= 13,
+	GLF_OBJECT			= 14, /* Used only for tracing */
+	GLF_BLOCKING			= 15,
+};
+
+struct gfs2_glock {
+	struct hlist_bl_node gl_list;
+	struct gfs2_sbd *gl_sbd;
+	unsigned long gl_flags;		/* GLF_... */
+	struct lm_lockname gl_name;
+
+	struct lockref gl_lockref;
+#define gl_spin gl_lockref.lock
+
+	/* State fields protected by gl_spin */
+	unsigned int gl_state:2,	/* Current state */
+		     gl_target:2,	/* Target state */
+		     gl_demote_state:2,	/* State requested by remote node */
+		     gl_req:2,		/* State in last dlm request */
+		     gl_reply:8;	/* Last reply from the dlm */
+
+	unsigned int gl_hash;
+	unsigned long gl_demote_time; /* time of first demote request */
+	long gl_hold_time;
+	struct list_head gl_holders;
+
+	const struct gfs2_glock_operations *gl_ops;
+	ktime_t gl_dstamp;
+	struct gfs2_lkstats gl_stats;
+	struct dlm_lksb gl_lksb;
+	unsigned long gl_tchange;
+	void *gl_object;
+
+	struct list_head gl_lru;
+	struct list_head gl_ail_list;
+	atomic_t gl_ail_count;
+	atomic_t gl_revokes;
+	struct delayed_work gl_work;
+	union {
+		/* For inode and iopen glocks only */
+		struct work_struct gl_delete;
+		/* For rgrp glocks only */
+		struct {
+			loff_t start;
+			loff_t end;
+		} gl_vm;
+	};
+	struct rcu_head gl_rcu;
+};
+
+#define GFS2_MIN_LVB_SIZE 32	/* Min size of LVB that gfs2 supports */
+
+enum {
+	GIF_INVALID		= 0,
+	GIF_QD_LOCKED		= 1,
+	GIF_ALLOC_FAILED	= 2,
+	GIF_SW_PAGED		= 3,
+	GIF_ORDERED		= 4,
+	GIF_FREE_VFS_INODE      = 5,
+};
+
+struct gfs2_inode {
+	struct inode i_inode;
+	u64 i_no_addr;
+	u64 i_no_formal_ino;
+	u64 i_generation;
+	u64 i_eattr;
+	unsigned long i_flags;		/* GIF_... */
+	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_holder i_iopen_gh;
+	struct gfs2_holder i_gh; /* for prepare/commit_write only */
+	struct gfs2_blkreserv *i_res; /* rgrp multi-block reservation */
+	struct gfs2_rgrpd *i_rgd;
+	u64 i_goal;	/* goal block for allocations */
+	struct rw_semaphore i_rw_mutex;
+	struct list_head i_ordered;
+	struct list_head i_trunc_list;
+	__be64 *i_hash_cache;
+	u32 i_entries;
+	u32 i_diskflags;
+	u8 i_height;
+	u8 i_depth;
+};
+
+/*
+ * Since i_inode is the first element of struct gfs2_inode,
+ * this is effectively a cast.
+ */
+static inline struct gfs2_inode *GFS2_I(struct inode *inode)
+{
+	return container_of(inode, struct gfs2_inode, i_inode);
+}
+
+static inline struct gfs2_sbd *GFS2_SB(const struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
+struct gfs2_file {
+	struct mutex f_fl_mutex;
+	struct gfs2_holder f_fl_gh;
+};
+
+struct gfs2_revoke_replay {
+	struct list_head rr_list;
+	u64 rr_blkno;
+	unsigned int rr_where;
+};
+
+enum {
+	QDF_CHANGE		= 1,
+	QDF_LOCKED		= 2,
+	QDF_REFRESH		= 3,
+};
+
+struct gfs2_quota_data {
+	struct hlist_bl_node qd_hlist;
+	struct list_head qd_list;
+	struct kqid qd_id;
+	struct gfs2_sbd *qd_sbd;
+	struct lockref qd_lockref;
+	struct list_head qd_lru;
+	unsigned qd_hash;
+
+	unsigned long qd_flags;		/* QDF_... */
+
+	s64 qd_change;
+	s64 qd_change_sync;
+
+	unsigned int qd_slot;
+	unsigned int qd_slot_count;
+
+	struct buffer_head *qd_bh;
+	struct gfs2_quota_change *qd_bh_qc;
+	unsigned int qd_bh_count;
+
+	struct gfs2_glock *qd_gl;
+	struct gfs2_quota_lvb qd_qb;
+
+	u64 qd_sync_gen;
+	unsigned long qd_last_warn;
+	struct rcu_head qd_rcu;
+};
+
+struct gfs2_trans {
+	unsigned long tr_ip;
+
+	unsigned int tr_blocks;
+	unsigned int tr_revokes;
+	unsigned int tr_reserved;
+	unsigned int tr_touched:1;
+	unsigned int tr_attached:1;
+	unsigned int tr_alloced:1;
+
+	unsigned int tr_num_buf_new;
+	unsigned int tr_num_databuf_new;
+	unsigned int tr_num_buf_rm;
+	unsigned int tr_num_databuf_rm;
+	unsigned int tr_num_revoke;
+	unsigned int tr_num_revoke_rm;
+
+	struct list_head tr_list;
+	struct list_head tr_databuf;
+	struct list_head tr_buf;
+
+	unsigned int tr_first;
+	struct list_head tr_ail1_list;
+	struct list_head tr_ail2_list;
+};
+
+struct gfs2_journal_extent {
+	struct list_head list;
+
+	unsigned int lblock; /* First logical block */
+	u64 dblock; /* First disk block */
+	u64 blocks;
+};
+
+struct gfs2_jdesc {
+	struct list_head jd_list;
+	struct list_head extent_list;
+	unsigned int nr_extents;
+	struct work_struct jd_work;
+	struct inode *jd_inode;
+	unsigned long jd_flags;
+#define JDF_RECOVERY 1
+	unsigned int jd_jid;
+	unsigned int jd_blocks;
+	int jd_recover_error;
+	/* Replay stuff */
+
+	unsigned int jd_found_blocks;
+	unsigned int jd_found_revokes;
+	unsigned int jd_replayed_blocks;
+
+	struct list_head jd_revoke_list;
+	unsigned int jd_replay_tail;
+
+};
+
+struct gfs2_statfs_change_host {
+	s64 sc_total;
+	s64 sc_free;
+	s64 sc_dinodes;
+};
+
+#define GFS2_QUOTA_DEFAULT	GFS2_QUOTA_OFF
+#define GFS2_QUOTA_OFF		0
+#define GFS2_QUOTA_ACCOUNT	1
+#define GFS2_QUOTA_ON		2
+
+#define GFS2_DATA_DEFAULT	GFS2_DATA_ORDERED
+#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 */
+	char ar_hostdata[GFS2_LOCKNAME_LEN];	/* Host specific data */
+	unsigned int ar_spectator:1;		/* Don't get a journal */
+	unsigned int ar_localflocks:1;		/* Let the VFS do flock|fcntl */
+	unsigned int ar_debug:1;		/* Oops on errors */
+	unsigned int ar_posix_acl:1;		/* Enable posix acls */
+	unsigned int ar_quota:2;		/* off/account/on */
+	unsigned int ar_suiddir:1;		/* suiddir support */
+	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 */
+	unsigned int ar_nobarrier:1;            /* do not send barriers */
+	unsigned int ar_rgrplvb:1;		/* use lvbs for rgrp info */
+	int ar_commit;				/* Commit interval */
+	int ar_statfs_quantum;			/* The fast statfs interval */
+	int ar_quota_quantum;			/* The quota interval */
+	int ar_statfs_percent;			/* The % change to force sync */
+};
+
+struct gfs2_tune {
+	spinlock_t gt_spin;
+
+	unsigned int gt_logd_secs;
+
+	unsigned int gt_quota_warn_period; /* Secs between quota warn msgs */
+	unsigned int gt_quota_scale_num; /* Numerator */
+	unsigned int gt_quota_scale_den; /* Denominator */
+	unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
+	unsigned int gt_new_files_jdata;
+	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
+	unsigned int gt_complain_secs;
+	unsigned int gt_statfs_quantum;
+	unsigned int gt_statfs_slow;
+};
+
+enum {
+	SDF_JOURNAL_CHECKED	= 0,
+	SDF_JOURNAL_LIVE	= 1,
+	SDF_SHUTDOWN		= 2,
+	SDF_NOBARRIERS		= 3,
+	SDF_NORECOVERY		= 4,
+	SDF_DEMOTE		= 5,
+	SDF_NOJOURNALID		= 6,
+	SDF_RORECOVERY		= 7, /* read only recovery */
+	SDF_SKIP_DLM_UNLOCK	= 8,
+};
+
+#define GFS2_FSNAME_LEN		256
+
+struct gfs2_inum_host {
+	u64 no_formal_ino;
+	u64 no_addr;
+};
+
+struct gfs2_sb_host {
+	u32 sb_magic;
+	u32 sb_type;
+	u32 sb_format;
+
+	u32 sb_fs_format;
+	u32 sb_multihost_format;
+	u32 sb_bsize;
+	u32 sb_bsize_shift;
+
+	struct gfs2_inum_host sb_master_dir;
+	struct gfs2_inum_host sb_root_dir;
+
+	char sb_lockproto[GFS2_LOCKNAME_LEN];
+	char sb_locktable[GFS2_LOCKNAME_LEN];
+};
+
+/*
+ * lm_mount() return values
+ *
+ * ls_jid - the journal ID this node should use
+ * ls_first - this node is the first to mount the file system
+ * ls_lockspace - lock module's context for this file system
+ * ls_ops - lock module's functions
+ */
+
+struct lm_lockstruct {
+	int ls_jid;
+	unsigned int ls_first;
+	const struct lm_lockops *ls_ops;
+	dlm_lockspace_t *ls_dlm;
+
+	int ls_recover_jid_done;   /* These two are deprecated, */
+	int ls_recover_jid_status; /* used previously by gfs_controld */
+
+	struct dlm_lksb ls_mounted_lksb; /* mounted_lock */
+	struct dlm_lksb ls_control_lksb; /* control_lock */
+	char ls_control_lvb[GDLM_LVB_SIZE]; /* control_lock lvb */
+	struct completion ls_sync_wait; /* {control,mounted}_{lock,unlock} */
+	char *ls_lvb_bits;
+
+	spinlock_t ls_recover_spin; /* protects following fields */
+	unsigned long ls_recover_flags; /* DFL_ */
+	uint32_t ls_recover_mount; /* gen in first recover_done cb */
+	uint32_t ls_recover_start; /* gen in last recover_done cb */
+	uint32_t ls_recover_block; /* copy recover_start in last recover_prep */
+	uint32_t ls_recover_size; /* size of recover_submit, recover_result */
+	uint32_t *ls_recover_submit; /* gen in last recover_slot cb per jid */
+	uint32_t *ls_recover_result; /* result of last jid recovery */
+};
+
+struct gfs2_pcpu_lkstats {
+	/* One struct for each glock type */
+	struct gfs2_lkstats lkstats[10];
+};
+
+struct gfs2_sbd {
+	struct super_block *sd_vfs;
+	struct gfs2_pcpu_lkstats __percpu *sd_lkstats;
+	struct kobject sd_kobj;
+	unsigned long sd_flags;	/* SDF_... */
+	struct gfs2_sb_host sd_sb;
+
+	/* Constants computed on mount */
+
+	u32 sd_fsb2bb;
+	u32 sd_fsb2bb_shift;
+	u32 sd_diptrs;	/* Number of pointers in a dinode */
+	u32 sd_inptrs;	/* Number of pointers in a indirect block */
+	u32 sd_jbsize;	/* Size of a journaled data block */
+	u32 sd_hash_bsize;	/* sizeof(exhash block) */
+	u32 sd_hash_bsize_shift;
+	u32 sd_hash_ptrs;	/* Number of pointers in a hash block */
+	u32 sd_qc_per_block;
+	u32 sd_blocks_per_bitmap;
+	u32 sd_max_dirres;	/* Max blocks needed to add a directory entry */
+	u32 sd_max_height;	/* Max height of a file's metadata tree */
+	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
+	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
+	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
+
+	struct gfs2_args sd_args;	/* Mount arguments */
+	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */
+
+	/* Lock Stuff */
+
+	struct lm_lockstruct sd_lockstruct;
+	struct gfs2_holder sd_live_gh;
+	struct gfs2_glock *sd_rename_gl;
+	struct gfs2_glock *sd_freeze_gl;
+	wait_queue_head_t sd_glock_wait;
+	atomic_t sd_glock_disposal;
+	struct completion sd_locking_init;
+	struct completion sd_wdack;
+	struct delayed_work sd_control_work;
+
+	/* Inode Stuff */
+
+	struct dentry *sd_master_dir;
+	struct dentry *sd_root_dir;
+
+	struct inode *sd_jindex;
+	struct inode *sd_statfs_inode;
+	struct inode *sd_sc_inode;
+	struct inode *sd_qc_inode;
+	struct inode *sd_rindex;
+	struct inode *sd_quota_inode;
+
+	/* StatFS stuff */
+
+	spinlock_t sd_statfs_spin;
+	struct gfs2_statfs_change_host sd_statfs_master;
+	struct gfs2_statfs_change_host sd_statfs_local;
+	int sd_statfs_force_sync;
+
+	/* Resource group stuff */
+
+	int sd_rindex_uptodate;
+	spinlock_t sd_rindex_spin;
+	struct rb_root sd_rindex_tree;
+	unsigned int sd_rgrps;
+	unsigned int sd_max_rg_data;
+
+	/* Journal index stuff */
+
+	struct list_head sd_jindex_list;
+	spinlock_t sd_jindex_spin;
+	struct mutex sd_jindex_mutex;
+	unsigned int sd_journals;
+
+	struct gfs2_jdesc *sd_jdesc;
+	struct gfs2_holder sd_journal_gh;
+	struct gfs2_holder sd_jinode_gh;
+
+	struct gfs2_holder sd_sc_gh;
+	struct gfs2_holder sd_qc_gh;
+
+	struct completion sd_journal_ready;
+
+	/* Daemon stuff */
+
+	struct task_struct *sd_logd_process;
+	struct task_struct *sd_quotad_process;
+
+	/* Quota stuff */
+
+	struct list_head sd_quota_list;
+	atomic_t sd_quota_count;
+	struct mutex sd_quota_mutex;
+	struct mutex sd_quota_sync_mutex;
+	wait_queue_head_t sd_quota_wait;
+	struct list_head sd_trunc_list;
+	spinlock_t sd_trunc_lock;
+
+	unsigned int sd_quota_slots;
+	unsigned long *sd_quota_bitmap;
+	spinlock_t sd_bitmap_lock;
+
+	u64 sd_quota_sync_gen;
+
+	/* Log stuff */
+
+	struct address_space sd_aspace;
+
+	spinlock_t sd_log_lock;
+
+	struct gfs2_trans *sd_log_tr;
+	unsigned int sd_log_blks_reserved;
+	int sd_log_commited_revoke;
+
+	atomic_t sd_log_pinned;
+	unsigned int sd_log_num_revoke;
+
+	struct list_head sd_log_le_revoke;
+	struct list_head sd_log_le_ordered;
+	spinlock_t sd_ordered_lock;
+
+	atomic_t sd_log_thresh1;
+	atomic_t sd_log_thresh2;
+	atomic_t sd_log_blks_free;
+	wait_queue_head_t sd_log_waitq;
+	wait_queue_head_t sd_logd_waitq;
+
+	u64 sd_log_sequence;
+	unsigned int sd_log_head;
+	unsigned int sd_log_tail;
+	int sd_log_idle;
+
+	struct rw_semaphore sd_log_flush_lock;
+	atomic_t sd_log_in_flight;
+	struct bio *sd_log_bio;
+	wait_queue_head_t sd_log_flush_wait;
+	int sd_log_error;
+
+	unsigned int sd_log_flush_head;
+	u64 sd_log_flush_wrapped;
+
+	spinlock_t sd_ail_lock;
+	struct list_head sd_ail1_list;
+	struct list_head sd_ail2_list;
+
+	/* For quiescing the filesystem */
+	struct gfs2_holder sd_freeze_gh;
+	struct gfs2_holder sd_freeze_root_gh;
+	struct gfs2_holder sd_thaw_gh;
+	atomic_t sd_log_freeze;
+	atomic_t sd_frozen_root;
+	wait_queue_head_t sd_frozen_root_wait;
+	wait_queue_head_t sd_log_frozen_wait;
+
+	char sd_fsname[GFS2_FSNAME_LEN];
+	char sd_table_name[GFS2_FSNAME_LEN];
+	char sd_proto_name[GFS2_FSNAME_LEN];
+
+	/* Debugging crud */
+
+	unsigned long sd_last_warning;
+	struct dentry *debugfs_dir;    /* debugfs directory */
+	struct dentry *debugfs_dentry_glocks;
+	struct dentry *debugfs_dentry_glstats;
+	struct dentry *debugfs_dentry_sbstats;
+};
+
+static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which)
+{
+	gl->gl_stats.stats[which]++;
+}
+
+static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which)
+{
+	const struct gfs2_sbd *sdp = gl->gl_sbd;
+	preempt_disable();
+	this_cpu_ptr(sdp->sd_lkstats)->lkstats[gl->gl_name.ln_type].stats[which]++;
+	preempt_enable();
+}
+
+#endif /* __INCORE_DOT_H__ */
+

fs/gfs2/inode.h

@@ -0,0 +1,141 @@
+/*
+ * 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 __INODE_DOT_H__
+#define __INODE_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include "util.h"
+
+extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_set_aops(struct inode *inode);
+
+static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
+{
+	return !ip->i_height;
+}
+
+static inline int gfs2_is_jdata(const struct gfs2_inode *ip)
+{
+	return ip->i_diskflags & GFS2_DIF_JDATA;
+}
+
+static inline int gfs2_is_writeback(const struct gfs2_inode *ip)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	return (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK) && !gfs2_is_jdata(ip);
+}
+
+static inline int gfs2_is_ordered(const struct gfs2_inode *ip)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	return (sdp->sd_args.ar_data == GFS2_DATA_ORDERED) && !gfs2_is_jdata(ip);
+}
+
+static inline int gfs2_is_dir(const struct gfs2_inode *ip)
+{
+	return S_ISDIR(ip->i_inode.i_mode);
+}
+
+static inline void gfs2_set_inode_blocks(struct inode *inode, u64 blocks)
+{
+	inode->i_blocks = blocks <<
+		(GFS2_SB(inode)->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT);
+}
+
+static inline u64 gfs2_get_inode_blocks(const struct inode *inode)
+{
+	return inode->i_blocks >>
+		(GFS2_SB(inode)->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT);
+}
+
+static inline void gfs2_add_inode_blocks(struct inode *inode, s64 change)
+{
+	gfs2_assert(GFS2_SB(inode), (change >= 0 || inode->i_blocks > -change));
+	change *= (GFS2_SB(inode)->sd_sb.sb_bsize/GFS2_BASIC_BLOCK);
+	inode->i_blocks += change;
+}
+
+static inline int gfs2_check_inum(const struct gfs2_inode *ip, u64 no_addr,
+				  u64 no_formal_ino)
+{
+	return ip->i_no_addr == no_addr && ip->i_no_formal_ino == no_formal_ino;
+}
+
+static inline void gfs2_inum_out(const struct gfs2_inode *ip,
+				 struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
+	dent->de_inum.no_addr = cpu_to_be64(ip->i_no_addr);
+}
+
+static inline int gfs2_check_internal_file_size(struct inode *inode,
+						u64 minsize, u64 maxsize)
+{
+	u64 size = i_size_read(inode);
+	if (size < minsize || size > maxsize)
+		goto err;
+	if (size & ((1 << inode->i_blkbits) - 1))
+		goto err;
+	return 0;
+err:
+	gfs2_consist_inode(GFS2_I(inode));
+	return -EIO;
+}
+
+extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
+				       u64 no_addr, u64 no_formal_ino,
+				       int non_block);
+extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
+					 u64 *no_formal_ino,
+					 unsigned int blktype);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int nonblock);
+
+extern int gfs2_inode_refresh(struct gfs2_inode *ip);
+
+extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+				  int is_root);
+extern int gfs2_permission(struct inode *inode, int mask);
+extern int gfs2_setattr_simple(struct inode *inode, struct iattr *attr);
+extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
+extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
+extern int gfs2_open_common(struct inode *inode, struct file *file);
+
+extern const struct inode_operations gfs2_file_iops;
+extern const struct inode_operations gfs2_dir_iops;
+extern const struct inode_operations gfs2_symlink_iops;
+extern const struct file_operations gfs2_file_fops_nolock;
+extern const struct file_operations gfs2_dir_fops_nolock;
+
+extern void gfs2_set_inode_flags(struct inode *inode);
+ 
+#ifdef CONFIG_GFS2_FS_LOCKING_DLM
+extern const struct file_operations gfs2_file_fops;
+extern const struct file_operations gfs2_dir_fops;
+
+static inline int gfs2_localflocks(const struct gfs2_sbd *sdp)
+{
+	return sdp->sd_args.ar_localflocks;
+}
+#else /* Single node only */
+#define gfs2_file_fops gfs2_file_fops_nolock
+#define gfs2_dir_fops gfs2_dir_fops_nolock
+
+static inline int gfs2_localflocks(const struct gfs2_sbd *sdp)
+{
+	return 1;
+}
+#endif /* CONFIG_GFS2_FS_LOCKING_DLM */
+
+#endif /* __INODE_DOT_H__ */
+

fs/gfs2/log.c

@@ -0,0 +1,950 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/writeback.h>
+#include <linux/list_sort.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "util.h"
+#include "dir.h"
+#include "trace_gfs2.h"
+
+/**
+ * gfs2_struct2blk - compute stuff
+ * @sdp: the filesystem
+ * @nstruct: the number of structures
+ * @ssize: the size of the structures
+ *
+ * Compute the number of log descriptor blocks needed to hold a certain number
+ * of structures of a certain size.
+ *
+ * Returns: the number of blocks needed (minimum is always 1)
+ */
+
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			     unsigned int ssize)
+{
+	unsigned int blks;
+	unsigned int first, second;
+
+	blks = 1;
+	first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+
+	if (nstruct > first) {
+		second = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_meta_header)) / ssize;
+		blks += DIV_ROUND_UP(nstruct - first, second);
+	}
+
+	return blks;
+}
+
+/**
+ * gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
+ * @mapping: The associated mapping (maybe NULL)
+ * @bd: The gfs2_bufdata to remove
+ *
+ * The ail lock _must_ be held when calling this function
+ *
+ */
+
+void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
+{
+	bd->bd_tr = NULL;
+	list_del_init(&bd->bd_ail_st_list);
+	list_del_init(&bd->bd_ail_gl_list);
+	atomic_dec(&bd->bd_gl->gl_ail_count);
+	brelse(bd->bd_bh);
+}
+
+/**
+ * gfs2_ail1_start_one - Start I/O on a part of the AIL
+ * @sdp: the filesystem
+ * @wbc: The writeback control structure
+ * @ai: The ail structure
+ *
+ */
+
+static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
+			       struct writeback_control *wbc,
+			       struct gfs2_trans *tr)
+__releases(&sdp->sd_ail_lock)
+__acquires(&sdp->sd_ail_lock)
+{
+	struct gfs2_glock *gl = NULL;
+	struct address_space *mapping;
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+
+	list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) {
+		bh = bd->bd_bh;
+
+		gfs2_assert(sdp, bd->bd_tr == tr);
+
+		if (!buffer_busy(bh)) {
+			if (!buffer_uptodate(bh))
+				gfs2_io_error_bh(sdp, bh);
+			list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
+			continue;
+		}
+
+		if (!buffer_dirty(bh))
+			continue;
+		if (gl == bd->bd_gl)
+			continue;
+		gl = bd->bd_gl;
+		list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list);
+		mapping = bh->b_page->mapping;
+		if (!mapping)
+			continue;
+		spin_unlock(&sdp->sd_ail_lock);
+		generic_writepages(mapping, wbc);
+		spin_lock(&sdp->sd_ail_lock);
+		if (wbc->nr_to_write <= 0)
+			break;
+		return 1;
+	}
+
+	return 0;
+}
+
+
+/**
+ * gfs2_ail1_flush - start writeback of some ail1 entries 
+ * @sdp: The super block
+ * @wbc: The writeback control structure
+ *
+ * Writes back some ail1 entries, according to the limits in the
+ * writeback control structure
+ */
+
+void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
+{
+	struct list_head *head = &sdp->sd_ail1_list;
+	struct gfs2_trans *tr;
+	struct blk_plug plug;
+
+	trace_gfs2_ail_flush(sdp, wbc, 1);
+	blk_start_plug(&plug);
+	spin_lock(&sdp->sd_ail_lock);
+restart:
+	list_for_each_entry_reverse(tr, head, tr_list) {
+		if (wbc->nr_to_write <= 0)
+			break;
+		if (gfs2_ail1_start_one(sdp, wbc, tr))
+			goto restart;
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+	blk_finish_plug(&plug);
+	trace_gfs2_ail_flush(sdp, wbc, 0);
+}
+
+/**
+ * gfs2_ail1_start - start writeback of all ail1 entries
+ * @sdp: The superblock
+ */
+
+static void gfs2_ail1_start(struct gfs2_sbd *sdp)
+{
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_NONE,
+		.nr_to_write = LONG_MAX,
+		.range_start = 0,
+		.range_end = LLONG_MAX,
+	};
+
+	return gfs2_ail1_flush(sdp, &wbc);
+}
+
+/**
+ * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct gfs2_bufdata *bd, *s;
+	struct buffer_head *bh;
+
+	list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list,
+					 bd_ail_st_list) {
+		bh = bd->bd_bh;
+		gfs2_assert(sdp, bd->bd_tr == tr);
+		if (buffer_busy(bh))
+			continue;
+		if (!buffer_uptodate(bh))
+			gfs2_io_error_bh(sdp, bh);
+		list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
+	}
+
+}
+
+/**
+ * gfs2_ail1_empty - Try to empty the ail1 lists
+ * @sdp: The superblock
+ *
+ * Tries to empty the ail1 lists, starting with the oldest first
+ */
+
+static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr, *s;
+	int oldest_tr = 1;
+	int ret;
+
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
+		gfs2_ail1_empty_one(sdp, tr);
+		if (list_empty(&tr->tr_ail1_list) && oldest_tr)
+			list_move(&tr->tr_list, &sdp->sd_ail2_list);
+		else
+			oldest_tr = 0;
+	}
+	ret = list_empty(&sdp->sd_ail1_list);
+	spin_unlock(&sdp->sd_ail_lock);
+
+	return ret;
+}
+
+static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr;
+	struct gfs2_bufdata *bd;
+	struct buffer_head *bh;
+
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) {
+		list_for_each_entry(bd, &tr->tr_ail1_list, bd_ail_st_list) {
+			bh = bd->bd_bh;
+			if (!buffer_locked(bh))
+				continue;
+			get_bh(bh);
+			spin_unlock(&sdp->sd_ail_lock);
+			wait_on_buffer(bh);
+			brelse(bh);
+			return;
+		}
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+}
+
+/**
+ * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
+ * @sdp: the filesystem
+ * @ai: the AIL entry
+ *
+ */
+
+static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head = &tr->tr_ail2_list;
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->prev, struct gfs2_bufdata,
+				bd_ail_st_list);
+		gfs2_assert(sdp, bd->bd_tr == tr);
+		gfs2_remove_from_ail(bd);
+	}
+}
+
+static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
+{
+	struct gfs2_trans *tr, *safe;
+	unsigned int old_tail = sdp->sd_log_tail;
+	int wrap = (new_tail < old_tail);
+	int a, b, rm;
+
+	spin_lock(&sdp->sd_ail_lock);
+
+	list_for_each_entry_safe(tr, safe, &sdp->sd_ail2_list, tr_list) {
+		a = (old_tail <= tr->tr_first);
+		b = (tr->tr_first < new_tail);
+		rm = (wrap) ? (a || b) : (a && b);
+		if (!rm)
+			continue;
+
+		gfs2_ail2_empty_one(sdp, tr);
+		list_del(&tr->tr_list);
+		gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
+		gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
+		kfree(tr);
+	}
+
+	spin_unlock(&sdp->sd_ail_lock);
+}
+
+/**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+	atomic_add(blks, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, blks);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+				  sdp->sd_jdesc->jd_blocks);
+	up_read(&sdp->sd_log_flush_lock);
+}
+
+/**
+ * gfs2_log_reserve - Make a log reservation
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks to reserve
+ *
+ * Note that we never give out the last few blocks of the journal. Thats
+ * due to the fact that there is a small number of header blocks
+ * associated with each log flush. The exact number can't be known until
+ * flush time, so we ensure that we have just enough free blocks at all
+ * times to avoid running out during a log flush.
+ *
+ * We no longer flush the log here, instead we wake up logd to do that
+ * for us. To avoid the thundering herd and to ensure that we deal fairly
+ * with queued waiters, we use an exclusive wait. This means that when we
+ * get woken with enough journal space to get our reservation, we need to
+ * wake the next waiter on the list.
+ *
+ * Returns: errno
+ */
+
+int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
+{
+	unsigned reserved_blks = 7 * (4096 / sdp->sd_vfs->s_blocksize);
+	unsigned wanted = blks + reserved_blks;
+	DEFINE_WAIT(wait);
+	int did_wait = 0;
+	unsigned int free_blocks;
+
+	if (gfs2_assert_warn(sdp, blks) ||
+	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
+		return -EINVAL;
+retry:
+	free_blocks = atomic_read(&sdp->sd_log_blks_free);
+	if (unlikely(free_blocks <= wanted)) {
+		do {
+			prepare_to_wait_exclusive(&sdp->sd_log_waitq, &wait,
+					TASK_UNINTERRUPTIBLE);
+			wake_up(&sdp->sd_logd_waitq);
+			did_wait = 1;
+			if (atomic_read(&sdp->sd_log_blks_free) <= wanted)
+				io_schedule();
+			free_blocks = atomic_read(&sdp->sd_log_blks_free);
+		} while(free_blocks <= wanted);
+		finish_wait(&sdp->sd_log_waitq, &wait);
+	}
+	if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks,
+				free_blocks - blks) != free_blocks)
+		goto retry;
+	trace_gfs2_log_blocks(sdp, -blks);
+
+	/*
+	 * If we waited, then so might others, wake them up _after_ we get
+	 * our share of the log.
+	 */
+	if (unlikely(did_wait))
+		wake_up(&sdp->sd_log_waitq);
+
+	down_read(&sdp->sd_log_flush_lock);
+	if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
+		gfs2_log_release(sdp, blks);
+		return -EROFS;
+	}
+	return 0;
+}
+
+/**
+ * log_distance - Compute distance between two journal blocks
+ * @sdp: The GFS2 superblock
+ * @newer: The most recent journal block of the pair
+ * @older: The older journal block of the pair
+ *
+ *   Compute the distance (in the journal direction) between two
+ *   blocks in the journal
+ *
+ * Returns: the distance in blocks
+ */
+
+static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
+					unsigned int older)
+{
+	int dist;
+
+	dist = newer - older;
+	if (dist < 0)
+		dist += sdp->sd_jdesc->jd_blocks;
+
+	return dist;
+}
+
+/**
+ * calc_reserved - Calculate the number of blocks to reserve when
+ *                 refunding a transaction's unused buffers.
+ * @sdp: The GFS2 superblock
+ *
+ * This is complex.  We need to reserve room for all our currently used
+ * metadata buffers (e.g. normal file I/O rewriting file time stamps) and 
+ * all our journaled data buffers for journaled files (e.g. files in the 
+ * meta_fs like rindex, or files for which chattr +j was done.)
+ * If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush
+ * will count it as free space (sd_log_blks_free) and corruption will follow.
+ *
+ * We can have metadata bufs and jdata bufs in the same journal.  So each
+ * type gets its own log header, for which we need to reserve a block.
+ * In fact, each type has the potential for needing more than one header 
+ * in cases where we have more buffers than will fit on a journal page.
+ * Metadata journal entries take up half the space of journaled buffer entries.
+ * Thus, metadata entries have buf_limit (502) and journaled buffers have
+ * databuf_limit (251) before they cause a wrap around.
+ *
+ * Also, we need to reserve blocks for revoke journal entries and one for an
+ * overall header for the lot.
+ *
+ * Returns: the number of blocks reserved
+ */
+static unsigned int calc_reserved(struct gfs2_sbd *sdp)
+{
+	unsigned int reserved = 0;
+	unsigned int mbuf;
+	unsigned int dbuf;
+	struct gfs2_trans *tr = sdp->sd_log_tr;
+
+	if (tr) {
+		mbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
+		dbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
+		reserved = mbuf + dbuf;
+		/* Account for header blocks */
+		reserved += DIV_ROUND_UP(mbuf, buf_limit(sdp));
+		reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
+	}
+
+	if (sdp->sd_log_commited_revoke > 0)
+		reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
+					  sizeof(u64));
+	/* One for the overall header */
+	if (reserved)
+		reserved++;
+	return reserved;
+}
+
+static unsigned int current_tail(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr;
+	unsigned int tail;
+
+	spin_lock(&sdp->sd_ail_lock);
+
+	if (list_empty(&sdp->sd_ail1_list)) {
+		tail = sdp->sd_log_head;
+	} else {
+		tr = list_entry(sdp->sd_ail1_list.prev, struct gfs2_trans,
+				tr_list);
+		tail = tr->tr_first;
+	}
+
+	spin_unlock(&sdp->sd_ail_lock);
+
+	return tail;
+}
+
+static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
+{
+	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
+
+	ail2_empty(sdp, new_tail);
+
+	atomic_add(dist, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, dist);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+			     sdp->sd_jdesc->jd_blocks);
+
+	sdp->sd_log_tail = new_tail;
+}
+
+
+static void log_flush_wait(struct gfs2_sbd *sdp)
+{
+	DEFINE_WAIT(wait);
+
+	if (atomic_read(&sdp->sd_log_in_flight)) {
+		do {
+			prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&sdp->sd_log_in_flight))
+				io_schedule();
+		} while(atomic_read(&sdp->sd_log_in_flight));
+		finish_wait(&sdp->sd_log_flush_wait, &wait);
+	}
+}
+
+static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct gfs2_inode *ipa, *ipb;
+
+	ipa = list_entry(a, struct gfs2_inode, i_ordered);
+	ipb = list_entry(b, struct gfs2_inode, i_ordered);
+
+	if (ipa->i_no_addr < ipb->i_no_addr)
+		return -1;
+	if (ipa->i_no_addr > ipb->i_no_addr)
+		return 1;
+	return 0;
+}
+
+static void gfs2_ordered_write(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *ip;
+	LIST_HEAD(written);
+
+	spin_lock(&sdp->sd_ordered_lock);
+	list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+		list_move(&ip->i_ordered, &written);
+		if (ip->i_inode.i_mapping->nrpages == 0)
+			continue;
+		spin_unlock(&sdp->sd_ordered_lock);
+		filemap_fdatawrite(ip->i_inode.i_mapping);
+		spin_lock(&sdp->sd_ordered_lock);
+	}
+	list_splice(&written, &sdp->sd_log_le_ordered);
+	spin_unlock(&sdp->sd_ordered_lock);
+}
+
+static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
+{
+	struct gfs2_inode *ip;
+
+	spin_lock(&sdp->sd_ordered_lock);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+		list_del(&ip->i_ordered);
+		WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
+		if (ip->i_inode.i_mapping->nrpages == 0)
+			continue;
+		spin_unlock(&sdp->sd_ordered_lock);
+		filemap_fdatawait(ip->i_inode.i_mapping);
+		spin_lock(&sdp->sd_ordered_lock);
+	}
+	spin_unlock(&sdp->sd_ordered_lock);
+}
+
+void gfs2_ordered_del_inode(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	spin_lock(&sdp->sd_ordered_lock);
+	if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
+		list_del(&ip->i_ordered);
+	spin_unlock(&sdp->sd_ordered_lock);
+}
+
+void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
+{
+	struct buffer_head *bh = bd->bd_bh;
+	struct gfs2_glock *gl = bd->bd_gl;
+
+	bh->b_private = NULL;
+	bd->bd_blkno = bh->b_blocknr;
+	gfs2_remove_from_ail(bd); /* drops ref on bh */
+	bd->bd_bh = NULL;
+	bd->bd_ops = &gfs2_revoke_lops;
+	sdp->sd_log_num_revoke++;
+	atomic_inc(&gl->gl_revokes);
+	set_bit(GLF_LFLUSH, &gl->gl_flags);
+	list_add(&bd->bd_list, &sdp->sd_log_le_revoke);
+}
+
+void gfs2_write_revokes(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr;
+	struct gfs2_bufdata *bd, *tmp;
+	int have_revokes = 0;
+	int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
+
+	gfs2_ail1_empty(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
+		list_for_each_entry(bd, &tr->tr_ail2_list, bd_ail_st_list) {
+			if (list_empty(&bd->bd_list)) {
+				have_revokes = 1;
+				goto done;
+			}
+		}
+	}
+done:
+	spin_unlock(&sdp->sd_ail_lock);
+	if (have_revokes == 0)
+		return;
+	while (sdp->sd_log_num_revoke > max_revokes)
+		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	max_revokes -= sdp->sd_log_num_revoke;
+	if (!sdp->sd_log_num_revoke) {
+		atomic_dec(&sdp->sd_log_blks_free);
+		/* If no blocks have been reserved, we need to also
+		 * reserve a block for the header */
+		if (!sdp->sd_log_blks_reserved)
+			atomic_dec(&sdp->sd_log_blks_free);
+	}
+	gfs2_log_lock(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
+		list_for_each_entry_safe(bd, tmp, &tr->tr_ail2_list, bd_ail_st_list) {
+			if (max_revokes == 0)
+				goto out_of_blocks;
+			if (!list_empty(&bd->bd_list))
+				continue;
+			gfs2_add_revoke(sdp, bd);
+			max_revokes--;
+		}
+	}
+out_of_blocks:
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+
+	if (!sdp->sd_log_num_revoke) {
+		atomic_inc(&sdp->sd_log_blks_free);
+		if (!sdp->sd_log_blks_reserved)
+			atomic_inc(&sdp->sd_log_blks_free);
+	}
+}
+
+/**
+ * log_write_header - Get and initialize a journal header buffer
+ * @sdp: The GFS2 superblock
+ *
+ * Returns: the initialized log buffer descriptor
+ */
+
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
+{
+	struct gfs2_log_header *lh;
+	unsigned int tail;
+	u32 hash;
+	int rw = WRITE_FLUSH_FUA | REQ_META;
+	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+	lh = page_address(page);
+	clear_page(lh);
+
+	tail = current_tail(sdp);
+
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.__pad0 = cpu_to_be64(0);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
+	lh->lh_flags = cpu_to_be32(flags);
+	lh->lh_tail = cpu_to_be32(tail);
+	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+	hash = gfs2_disk_hash(page_address(page), sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
+		gfs2_ordered_wait(sdp);
+		log_flush_wait(sdp);
+		rw = WRITE_SYNC | REQ_META | REQ_PRIO;
+	}
+
+	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
+	gfs2_log_write_page(sdp, page);
+	gfs2_log_flush_bio(sdp, rw);
+	log_flush_wait(sdp);
+
+	if (sdp->sd_log_tail != tail)
+		log_pull_tail(sdp, tail);
+}
+
+/**
+ * gfs2_log_flush - flush incore transaction(s)
+ * @sdp: the filesystem
+ * @gl: The glock structure to flush.  If NULL, flush the whole incore log
+ *
+ */
+
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+		    enum gfs2_flush_type type)
+{
+	struct gfs2_trans *tr;
+
+	down_write(&sdp->sd_log_flush_lock);
+
+	/* Log might have been flushed while we waited for the flush lock */
+	if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags)) {
+		up_write(&sdp->sd_log_flush_lock);
+		return;
+	}
+	trace_gfs2_log_flush(sdp, 1);
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+	tr = sdp->sd_log_tr;
+	if (tr) {
+		sdp->sd_log_tr = NULL;
+		INIT_LIST_HEAD(&tr->tr_ail1_list);
+		INIT_LIST_HEAD(&tr->tr_ail2_list);
+		tr->tr_first = sdp->sd_log_flush_head;
+	}
+
+	gfs2_assert_withdraw(sdp,
+			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+
+	gfs2_ordered_write(sdp);
+	lops_before_commit(sdp, tr);
+	gfs2_log_flush_bio(sdp, WRITE);
+
+	if (sdp->sd_log_head != sdp->sd_log_flush_head) {
+		log_flush_wait(sdp);
+		log_write_header(sdp, 0);
+	} else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
+		atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+		trace_gfs2_log_blocks(sdp, -1);
+		log_write_header(sdp, 0);
+	}
+	lops_after_commit(sdp, tr);
+
+	gfs2_log_lock(sdp);
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_blks_reserved = 0;
+	sdp->sd_log_commited_revoke = 0;
+
+	spin_lock(&sdp->sd_ail_lock);
+	if (tr && !list_empty(&tr->tr_ail1_list)) {
+		list_add(&tr->tr_list, &sdp->sd_ail1_list);
+		tr = NULL;
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+
+	if (atomic_read(&sdp->sd_log_freeze))
+		type = FREEZE_FLUSH;
+	if (type != NORMAL_FLUSH) {
+		if (!sdp->sd_log_idle) {
+			for (;;) {
+				gfs2_ail1_start(sdp);
+				gfs2_ail1_wait(sdp);
+				if (gfs2_ail1_empty(sdp))
+					break;
+			}
+			atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+			trace_gfs2_log_blocks(sdp, -1);
+			sdp->sd_log_flush_wrapped = 0;
+			log_write_header(sdp, 0);
+			sdp->sd_log_head = sdp->sd_log_flush_head;
+		}
+		if (type == SHUTDOWN_FLUSH || type == FREEZE_FLUSH)
+			gfs2_log_shutdown(sdp);
+		if (type == FREEZE_FLUSH) {
+			int error;
+
+			atomic_set(&sdp->sd_log_freeze, 0);
+			wake_up(&sdp->sd_log_frozen_wait);
+			error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
+						   LM_ST_SHARED, 0,
+						   &sdp->sd_thaw_gh);
+			if (error) {
+				printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error);
+				gfs2_assert_withdraw(sdp, 0);
+			}
+			else
+				gfs2_glock_dq_uninit(&sdp->sd_thaw_gh);
+		}
+	}
+
+	trace_gfs2_log_flush(sdp, 0);
+	up_write(&sdp->sd_log_flush_lock);
+
+	kfree(tr);
+}
+
+/**
+ * gfs2_merge_trans - Merge a new transaction into a cached transaction
+ * @old: Original transaction to be expanded
+ * @new: New transaction to be merged
+ */
+
+static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
+{
+	WARN_ON_ONCE(old->tr_attached != 1);
+
+	old->tr_num_buf_new	+= new->tr_num_buf_new;
+	old->tr_num_databuf_new	+= new->tr_num_databuf_new;
+	old->tr_num_buf_rm	+= new->tr_num_buf_rm;
+	old->tr_num_databuf_rm	+= new->tr_num_databuf_rm;
+	old->tr_num_revoke	+= new->tr_num_revoke;
+	old->tr_num_revoke_rm	+= new->tr_num_revoke_rm;
+
+	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
+	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
+}
+
+static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	unsigned int reserved;
+	unsigned int unused;
+	unsigned int maxres;
+
+	gfs2_log_lock(sdp);
+
+	if (sdp->sd_log_tr) {
+		gfs2_merge_trans(sdp->sd_log_tr, tr);
+	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
+		gfs2_assert_withdraw(sdp, tr->tr_alloced);
+		sdp->sd_log_tr = tr;
+		tr->tr_attached = 1;
+	}
+
+	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
+	reserved = calc_reserved(sdp);
+	maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
+	gfs2_assert_withdraw(sdp, maxres >= reserved);
+	unused = maxres - reserved;
+	atomic_add(unused, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, unused);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+			     sdp->sd_jdesc->jd_blocks);
+	sdp->sd_log_blks_reserved = reserved;
+
+	gfs2_log_unlock(sdp);
+}
+
+/**
+ * gfs2_log_commit - Commit a transaction to the log
+ * @sdp: the filesystem
+ * @tr: the transaction
+ *
+ * We wake up gfs2_logd if the number of pinned blocks exceed thresh1
+ * or the total number of used blocks (pinned blocks plus AIL blocks)
+ * is greater than thresh2.
+ *
+ * At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of
+ * journal size.
+ *
+ * Returns: errno
+ */
+
+void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	log_refund(sdp, tr);
+
+	if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
+	    ((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
+	    atomic_read(&sdp->sd_log_thresh2)))
+		wake_up(&sdp->sd_logd_waitq);
+}
+
+/**
+ * gfs2_log_shutdown - write a shutdown header into a journal
+ * @sdp: the filesystem
+ *
+ */
+
+void gfs2_log_shutdown(struct gfs2_sbd *sdp)
+{
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
+	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
+
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+
+	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT);
+
+	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
+	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
+
+	sdp->sd_log_head = sdp->sd_log_flush_head;
+	sdp->sd_log_tail = sdp->sd_log_head;
+}
+
+static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
+{
+	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1) || atomic_read(&sdp->sd_log_freeze));
+}
+
+static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
+{
+	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
+	return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
+}
+
+/**
+ * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
+ * @sdp: Pointer to GFS2 superblock
+ *
+ * Also, periodically check to make sure that we're using the most recent
+ * journal index.
+ */
+
+int gfs2_logd(void *data)
+{
+	struct gfs2_sbd *sdp = data;
+	unsigned long t = 1;
+	DEFINE_WAIT(wait);
+
+	while (!kthread_should_stop()) {
+
+		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
+			gfs2_ail1_empty(sdp);
+			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+		}
+
+		if (gfs2_ail_flush_reqd(sdp)) {
+			gfs2_ail1_start(sdp);
+			gfs2_ail1_wait(sdp);
+			gfs2_ail1_empty(sdp);
+			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+		}
+
+		if (!gfs2_ail_flush_reqd(sdp))
+			wake_up(&sdp->sd_log_waitq);
+
+		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
+
+		try_to_freeze();
+
+		do {
+			prepare_to_wait(&sdp->sd_logd_waitq, &wait,
+					TASK_INTERRUPTIBLE);
+			if (!gfs2_ail_flush_reqd(sdp) &&
+			    !gfs2_jrnl_flush_reqd(sdp) &&
+			    !kthread_should_stop())
+				t = schedule_timeout(t);
+		} while(t && !gfs2_ail_flush_reqd(sdp) &&
+			!gfs2_jrnl_flush_reqd(sdp) &&
+			!kthread_should_stop());
+		finish_wait(&sdp->sd_logd_waitq, &wait);
+	}
+
+	return 0;
+}
+

fs/gfs2/log.h

@@ -0,0 +1,85 @@
+/*
+ * 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 __LOG_DOT_H__
+#define __LOG_DOT_H__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/writeback.h>
+#include "incore.h"
+
+/**
+ * gfs2_log_lock - acquire the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_lock(struct gfs2_sbd *sdp)
+__acquires(&sdp->sd_log_lock)
+{
+	spin_lock(&sdp->sd_log_lock);
+}
+
+/**
+ * gfs2_log_unlock - release the right to mess with the log manager
+ * @sdp: the filesystem
+ *
+ */
+
+static inline void gfs2_log_unlock(struct gfs2_sbd *sdp)
+__releases(&sdp->sd_log_lock)
+{
+	spin_unlock(&sdp->sd_log_lock);
+}
+
+static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
+					  unsigned int value)
+{
+	if (++value == sdp->sd_jdesc->jd_blocks) {
+		value = 0;
+	}
+	sdp->sd_log_head = sdp->sd_log_tail = value;
+}
+
+static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
+		spin_lock(&sdp->sd_ordered_lock);
+		if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
+			list_add(&ip->i_ordered, &sdp->sd_log_le_ordered);
+		spin_unlock(&sdp->sd_ordered_lock);
+	}
+}
+extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
+extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+			    unsigned int ssize);
+
+extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
+extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
+enum gfs2_flush_type {
+	NORMAL_FLUSH = 0,
+	SYNC_FLUSH,
+	SHUTDOWN_FLUSH,
+	FREEZE_FLUSH
+};
+extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+			   enum gfs2_flush_type type);
+extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
+extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
+
+extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
+extern int gfs2_logd(void *data);
+extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+extern void gfs2_write_revokes(struct gfs2_sbd *sdp);
+
+#endif /* __LOG_DOT_H__ */

fs/gfs2/lops.c

@@ -0,0 +1,886 @@
+/*
+ * 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/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/mempool.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
+#include <linux/list_sort.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "inode.h"
+#include "glock.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+/**
+ * gfs2_pin - Pin a buffer in memory
+ * @sdp: The superblock
+ * @bh: The buffer to be pinned
+ *
+ * The log lock must be held when calling this function
+ */
+void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	BUG_ON(!current->journal_info);
+
+	clear_buffer_dirty(bh);
+	if (test_set_buffer_pinned(bh))
+		gfs2_assert_withdraw(sdp, 0);
+	if (!buffer_uptodate(bh))
+		gfs2_io_error_bh(sdp, bh);
+	bd = bh->b_private;
+	/* If this buffer is in the AIL and it has already been written
+	 * to in-place disk block, remove it from the AIL.
+	 */
+	spin_lock(&sdp->sd_ail_lock);
+	if (bd->bd_tr)
+		list_move(&bd->bd_ail_st_list, &bd->bd_tr->tr_ail2_list);
+	spin_unlock(&sdp->sd_ail_lock);
+	get_bh(bh);
+	atomic_inc(&sdp->sd_log_pinned);
+	trace_gfs2_pin(bd, 1);
+}
+
+static bool buffer_is_rgrp(const struct gfs2_bufdata *bd)
+{
+	return bd->bd_gl->gl_name.ln_type == LM_TYPE_RGRP;
+}
+
+static void maybe_release_space(struct gfs2_bufdata *bd)
+{
+	struct gfs2_glock *gl = bd->bd_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_rgrpd *rgd = gl->gl_object;
+	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
+	struct gfs2_bitmap *bi = rgd->rd_bits + index;
+
+	if (bi->bi_clone == NULL)
+		return;
+	if (sdp->sd_args.ar_discard)
+		gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL);
+	memcpy(bi->bi_clone + bi->bi_offset,
+	       bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
+	clear_bit(GBF_FULL, &bi->bi_flags);
+	rgd->rd_free_clone = rgd->rd_free;
+	rgd->rd_extfail_pt = rgd->rd_free;
+}
+
+/**
+ * gfs2_unpin - Unpin a buffer
+ * @sdp: the filesystem the buffer belongs to
+ * @bh: The buffer to unpin
+ * @ai:
+ * @flags: The inode dirty flags
+ *
+ */
+
+static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       struct gfs2_trans *tr)
+{
+	struct gfs2_bufdata *bd = bh->b_private;
+
+	BUG_ON(!buffer_uptodate(bh));
+	BUG_ON(!buffer_pinned(bh));
+
+	lock_buffer(bh);
+	mark_buffer_dirty(bh);
+	clear_buffer_pinned(bh);
+
+	if (buffer_is_rgrp(bd))
+		maybe_release_space(bd);
+
+	spin_lock(&sdp->sd_ail_lock);
+	if (bd->bd_tr) {
+		list_del(&bd->bd_ail_st_list);
+		brelse(bh);
+	} else {
+		struct gfs2_glock *gl = bd->bd_gl;
+		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
+		atomic_inc(&gl->gl_ail_count);
+	}
+	bd->bd_tr = tr;
+	list_add(&bd->bd_ail_st_list, &tr->tr_ail1_list);
+	spin_unlock(&sdp->sd_ail_lock);
+
+	clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	trace_gfs2_pin(bd, 0);
+	unlock_buffer(bh);
+	atomic_dec(&sdp->sd_log_pinned);
+}
+
+static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
+{
+	BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
+	       (sdp->sd_log_flush_head != sdp->sd_log_head));
+
+	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
+		sdp->sd_log_flush_head = 0;
+		sdp->sd_log_flush_wrapped = 1;
+	}
+}
+
+static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
+{
+	unsigned int lbn = sdp->sd_log_flush_head;
+	struct gfs2_journal_extent *je;
+	u64 block;
+
+	list_for_each_entry(je, &sdp->sd_jdesc->extent_list, list) {
+		if ((lbn >= je->lblock) && (lbn < (je->lblock + je->blocks))) {
+			block = je->dblock + lbn - je->lblock;
+			gfs2_log_incr_head(sdp);
+			return block;
+		}
+	}
+
+	return -1;
+}
+
+/**
+ * gfs2_end_log_write_bh - end log write of pagecache data with buffers
+ * @sdp: The superblock
+ * @bvec: The bio_vec
+ * @error: The i/o status
+ *
+ * This finds the relavent buffers and unlocks then and sets the
+ * error flag according to the status of the i/o request. This is
+ * used when the log is writing data which has an in-place version
+ * that is pinned in the pagecache.
+ */
+
+static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
+				  int error)
+{
+	struct buffer_head *bh, *next;
+	struct page *page = bvec->bv_page;
+	unsigned size;
+
+	bh = page_buffers(page);
+	size = bvec->bv_len;
+	while (bh_offset(bh) < bvec->bv_offset)
+		bh = bh->b_this_page;
+	do {
+		if (error)
+			set_buffer_write_io_error(bh);
+		unlock_buffer(bh);
+		next = bh->b_this_page;
+		size -= bh->b_size;
+		brelse(bh);
+		bh = next;
+	} while(bh && size);
+}
+
+/**
+ * gfs2_end_log_write - end of i/o to the log
+ * @bio: The bio
+ * @error: Status of i/o request
+ *
+ * Each bio_vec contains either data from the pagecache or data
+ * relating to the log itself. Here we iterate over the bio_vec
+ * array, processing both kinds of data.
+ *
+ */
+
+static void gfs2_end_log_write(struct bio *bio, int error)
+{
+	struct gfs2_sbd *sdp = bio->bi_private;
+	struct bio_vec *bvec;
+	struct page *page;
+	int i;
+
+	if (error) {
+		sdp->sd_log_error = error;
+		fs_err(sdp, "Error %d writing to log\n", error);
+	}
+
+	bio_for_each_segment_all(bvec, bio, i) {
+		page = bvec->bv_page;
+		if (page_has_buffers(page))
+			gfs2_end_log_write_bh(sdp, bvec, error);
+		else
+			mempool_free(page, gfs2_page_pool);
+	}
+
+	bio_put(bio);
+	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
+		wake_up(&sdp->sd_log_flush_wait);
+}
+
+/**
+ * gfs2_log_flush_bio - Submit any pending log bio
+ * @sdp: The superblock
+ * @rw: The rw flags
+ *
+ * Submit any pending part-built or full bio to the block device. If
+ * there is no pending bio, then this is a no-op.
+ */
+
+void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw)
+{
+	if (sdp->sd_log_bio) {
+		atomic_inc(&sdp->sd_log_in_flight);
+		submit_bio(rw, sdp->sd_log_bio);
+		sdp->sd_log_bio = NULL;
+	}
+}
+
+/**
+ * gfs2_log_alloc_bio - Allocate a new bio for log writing
+ * @sdp: The superblock
+ * @blkno: The next device block number we want to write to
+ *
+ * This should never be called when there is a cached bio in the
+ * super block. When it returns, there will be a cached bio in the
+ * super block which will have as many bio_vecs as the device is
+ * happy to handle.
+ *
+ * Returns: Newly allocated bio
+ */
+
+static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev);
+	struct bio *bio;
+
+	BUG_ON(sdp->sd_log_bio);
+
+	while (1) {
+		bio = bio_alloc(GFP_NOIO, nrvecs);
+		if (likely(bio))
+			break;
+		nrvecs = max(nrvecs/2, 1U);
+	}
+
+	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
+	bio->bi_bdev = sb->s_bdev;
+	bio->bi_end_io = gfs2_end_log_write;
+	bio->bi_private = sdp;
+
+	sdp->sd_log_bio = bio;
+
+	return bio;
+}
+
+/**
+ * gfs2_log_get_bio - Get cached log bio, or allocate a new one
+ * @sdp: The superblock
+ * @blkno: The device block number we want to write to
+ *
+ * If there is a cached bio, then if the next block number is sequential
+ * with the previous one, return it, otherwise flush the bio to the
+ * device. If there is not a cached bio, or we just flushed it, then
+ * allocate a new one.
+ *
+ * Returns: The bio to use for log writes
+ */
+
+static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno)
+{
+	struct bio *bio = sdp->sd_log_bio;
+	u64 nblk;
+
+	if (bio) {
+		nblk = bio_end_sector(bio);
+		nblk >>= sdp->sd_fsb2bb_shift;
+		if (blkno == nblk)
+			return bio;
+		gfs2_log_flush_bio(sdp, WRITE);
+	}
+
+	return gfs2_log_alloc_bio(sdp, blkno);
+}
+
+
+/**
+ * gfs2_log_write - write to log
+ * @sdp: the filesystem
+ * @page: the page to write
+ * @size: the size of the data to write
+ * @offset: the offset within the page 
+ *
+ * Try and add the page segment to the current bio. If that fails,
+ * submit the current bio to the device and create a new one, and
+ * then add the page segment to that.
+ */
+
+static void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
+			   unsigned size, unsigned offset)
+{
+	u64 blkno = gfs2_log_bmap(sdp);
+	struct bio *bio;
+	int ret;
+
+	bio = gfs2_log_get_bio(sdp, blkno);
+	ret = bio_add_page(bio, page, size, offset);
+	if (ret == 0) {
+		gfs2_log_flush_bio(sdp, WRITE);
+		bio = gfs2_log_alloc_bio(sdp, blkno);
+		ret = bio_add_page(bio, page, size, offset);
+		WARN_ON(ret == 0);
+	}
+}
+
+/**
+ * gfs2_log_write_bh - write a buffer's content to the log
+ * @sdp: The super block
+ * @bh: The buffer pointing to the in-place location
+ * 
+ * This writes the content of the buffer to the next available location
+ * in the log. The buffer will be unlocked once the i/o to the log has
+ * completed.
+ */
+
+static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh));
+}
+
+/**
+ * gfs2_log_write_page - write one block stored in a page, into the log
+ * @sdp: The superblock
+ * @page: The struct page
+ *
+ * This writes the first block-sized part of the page into the log. Note
+ * that the page must have been allocated from the gfs2_page_pool mempool
+ * and that after this has been called, ownership has been transferred and
+ * the page may be freed at any time.
+ */
+
+void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	gfs2_log_write(sdp, page, sb->s_blocksize, 0);
+}
+
+static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type,
+				      u32 ld_length, u32 ld_data1)
+{
+	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+	struct gfs2_log_descriptor *ld = page_address(page);
+	clear_page(ld);
+	ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD);
+	ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD);
+	ld->ld_type = cpu_to_be32(ld_type);
+	ld->ld_length = cpu_to_be32(ld_length);
+	ld->ld_data1 = cpu_to_be32(ld_data1);
+	ld->ld_data2 = 0;
+	return page;
+}
+
+static void gfs2_check_magic(struct buffer_head *bh)
+{
+	void *kaddr;
+	__be32 *ptr;
+
+	clear_buffer_escaped(bh);
+	kaddr = kmap_atomic(bh->b_page);
+	ptr = kaddr + bh_offset(bh);
+	if (*ptr == cpu_to_be32(GFS2_MAGIC))
+		set_buffer_escaped(bh);
+	kunmap_atomic(kaddr);
+}
+
+static int blocknr_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct gfs2_bufdata *bda, *bdb;
+
+	bda = list_entry(a, struct gfs2_bufdata, bd_list);
+	bdb = list_entry(b, struct gfs2_bufdata, bd_list);
+
+	if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
+		return -1;
+	if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
+		return 1;
+	return 0;
+}
+
+static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit,
+				unsigned int total, struct list_head *blist,
+				bool is_databuf)
+{
+	struct gfs2_log_descriptor *ld;
+	struct gfs2_bufdata *bd1 = NULL, *bd2;
+	struct page *page;
+	unsigned int num;
+	unsigned n;
+	__be64 *ptr;
+
+	gfs2_log_lock(sdp);
+	list_sort(NULL, blist, blocknr_cmp);
+	bd1 = bd2 = list_prepare_entry(bd1, blist, bd_list);
+	while(total) {
+		num = total;
+		if (total > limit)
+			num = limit;
+		gfs2_log_unlock(sdp);
+		page = gfs2_get_log_desc(sdp,
+					 is_databuf ? GFS2_LOG_DESC_JDATA :
+					 GFS2_LOG_DESC_METADATA, num + 1, num);
+		ld = page_address(page);
+		gfs2_log_lock(sdp);
+		ptr = (__be64 *)(ld + 1);
+
+		n = 0;
+		list_for_each_entry_continue(bd1, blist, bd_list) {
+			*ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr);
+			if (is_databuf) {
+				gfs2_check_magic(bd1->bd_bh);
+				*ptr++ = cpu_to_be64(buffer_escaped(bd1->bd_bh) ? 1 : 0);
+			}
+			if (++n >= num)
+				break;
+		}
+
+		gfs2_log_unlock(sdp);
+		gfs2_log_write_page(sdp, page);
+		gfs2_log_lock(sdp);
+
+		n = 0;
+		list_for_each_entry_continue(bd2, blist, bd_list) {
+			get_bh(bd2->bd_bh);
+			gfs2_log_unlock(sdp);
+			lock_buffer(bd2->bd_bh);
+
+			if (buffer_escaped(bd2->bd_bh)) {
+				void *kaddr;
+				page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+				ptr = page_address(page);
+				kaddr = kmap_atomic(bd2->bd_bh->b_page);
+				memcpy(ptr, kaddr + bh_offset(bd2->bd_bh),
+				       bd2->bd_bh->b_size);
+				kunmap_atomic(kaddr);
+				*(__be32 *)ptr = 0;
+				clear_buffer_escaped(bd2->bd_bh);
+				unlock_buffer(bd2->bd_bh);
+				brelse(bd2->bd_bh);
+				gfs2_log_write_page(sdp, page);
+			} else {
+				gfs2_log_write_bh(sdp, bd2->bd_bh);
+			}
+			gfs2_log_lock(sdp);
+			if (++n >= num)
+				break;
+		}
+
+		BUG_ON(total < num);
+		total -= num;
+	}
+	gfs2_log_unlock(sdp);
+}
+
+static void buf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	unsigned int limit = buf_limit(sdp); /* 503 for 4k blocks */
+	unsigned int nbuf;
+	if (tr == NULL)
+		return;
+	nbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
+	gfs2_before_commit(sdp, limit, nbuf, &tr->tr_buf, 0);
+}
+
+static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head;
+	struct gfs2_bufdata *bd;
+
+	if (tr == NULL)
+		return;
+
+	head = &tr->tr_buf;
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		gfs2_unpin(sdp, bd->bd_bh, tr);
+	}
+}
+
+static void buf_lo_before_scan(struct gfs2_jdesc *jd,
+			       struct gfs2_log_header_host *head, int pass)
+{
+	if (pass != 0)
+		return;
+
+	jd->jd_found_blocks = 0;
+	jd->jd_replayed_blocks = 0;
+}
+
+static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				struct gfs2_log_descriptor *ld, __be64 *ptr,
+				int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_METADATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+
+		jd->jd_found_blocks++;
+
+		if (gfs2_revoke_check(jd, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		if (gfs2_meta_check(sdp, bh_ip))
+			error = -EIO;
+		else
+			mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+
+		if (error)
+			break;
+
+		jd->jd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+/**
+ * gfs2_meta_sync - Sync all buffers associated with a glock
+ * @gl: The glock
+ *
+ */
+
+static void gfs2_meta_sync(struct gfs2_glock *gl)
+{
+	struct address_space *mapping = gfs2_glock2aspace(gl);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	int error;
+
+	if (mapping == NULL)
+		mapping = &sdp->sd_aspace;
+
+	filemap_fdatawrite(mapping);
+	error = filemap_fdatawait(mapping);
+
+	if (error)
+		gfs2_io_error(gl->gl_sbd);
+}
+
+static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
+	        jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
+}
+
+static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct gfs2_meta_header *mh;
+	unsigned int offset;
+	struct list_head *head = &sdp->sd_log_le_revoke;
+	struct gfs2_bufdata *bd;
+	struct page *page;
+	unsigned int length;
+
+	gfs2_write_revokes(sdp);
+	if (!sdp->sd_log_num_revoke)
+		return;
+
+	length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64));
+	page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke);
+	offset = sizeof(struct gfs2_log_descriptor);
+
+	list_for_each_entry(bd, head, bd_list) {
+		sdp->sd_log_num_revoke--;
+
+		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
+
+			gfs2_log_write_page(sdp, page);
+			page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+			mh = page_address(page);
+			clear_page(mh);
+			mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+			mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB);
+			mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB);
+			offset = sizeof(struct gfs2_meta_header);
+		}
+
+		*(__be64 *)(page_address(page) + offset) = cpu_to_be64(bd->bd_blkno);
+		offset += sizeof(u64);
+	}
+	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
+
+	gfs2_log_write_page(sdp, page);
+}
+
+static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head = &sdp->sd_log_le_revoke;
+	struct gfs2_bufdata *bd;
+	struct gfs2_glock *gl;
+
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		gl = bd->bd_gl;
+		atomic_dec(&gl->gl_revokes);
+		clear_bit(GLF_LFLUSH, &gl->gl_flags);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+}
+
+static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
+				  struct gfs2_log_header_host *head, int pass)
+{
+	if (pass != 0)
+		return;
+
+	jd->jd_found_revokes = 0;
+	jd->jd_replay_tail = head->lh_tail;
+}
+
+static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				   struct gfs2_log_descriptor *ld, __be64 *ptr,
+				   int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int blks = be32_to_cpu(ld->ld_length);
+	unsigned int revokes = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh;
+	unsigned int offset;
+	u64 blkno;
+	int first = 1;
+	int error;
+
+	if (pass != 0 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_REVOKE)
+		return 0;
+
+	offset = sizeof(struct gfs2_log_descriptor);
+
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+
+		if (!first)
+			gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LB);
+
+		while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
+			blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
+
+			error = gfs2_revoke_add(jd, blkno, start);
+			if (error < 0) {
+				brelse(bh);
+				return error;
+			}
+			else if (error)
+				jd->jd_found_revokes++;
+
+			if (!--revokes)
+				break;
+			offset += sizeof(u64);
+		}
+
+		brelse(bh);
+		offset = sizeof(struct gfs2_meta_header);
+		first = 0;
+	}
+
+	return 0;
+}
+
+static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_revoke_clean(jd);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	fs_info(sdp, "jid=%u: Found %u revoke tags\n",
+	        jd->jd_jid, jd->jd_found_revokes);
+
+	gfs2_revoke_clean(jd);
+}
+
+/**
+ * databuf_lo_before_commit - Scan the data buffers, writing as we go
+ *
+ */
+
+static void databuf_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	unsigned int limit = databuf_limit(sdp);
+	unsigned int nbuf;
+	if (tr == NULL)
+		return;
+	nbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
+	gfs2_before_commit(sdp, limit, nbuf, &tr->tr_databuf, 1);
+}
+
+static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				    struct gfs2_log_descriptor *ld,
+				    __be64 *ptr, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	unsigned int blks = be32_to_cpu(ld->ld_data1);
+	struct buffer_head *bh_log, *bh_ip;
+	u64 blkno;
+	u64 esc;
+	int error = 0;
+
+	if (pass != 1 || be32_to_cpu(ld->ld_type) != GFS2_LOG_DESC_JDATA)
+		return 0;
+
+	gfs2_replay_incr_blk(sdp, &start);
+	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
+		blkno = be64_to_cpu(*ptr++);
+		esc = be64_to_cpu(*ptr++);
+
+		jd->jd_found_blocks++;
+
+		if (gfs2_revoke_check(jd, blkno, start))
+			continue;
+
+		error = gfs2_replay_read_block(jd, start, &bh_log);
+		if (error)
+			return error;
+
+		bh_ip = gfs2_meta_new(gl, blkno);
+		memcpy(bh_ip->b_data, bh_log->b_data, bh_log->b_size);
+
+		/* Unescape */
+		if (esc) {
+			__be32 *eptr = (__be32 *)bh_ip->b_data;
+			*eptr = cpu_to_be32(GFS2_MAGIC);
+		}
+		mark_buffer_dirty(bh_ip);
+
+		brelse(bh_log);
+		brelse(bh_ip);
+
+		jd->jd_replayed_blocks++;
+	}
+
+	return error;
+}
+
+/* FIXME: sort out accounting for log blocks etc. */
+
+static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+
+	if (error) {
+		gfs2_meta_sync(ip->i_gl);
+		return;
+	}
+	if (pass != 1)
+		return;
+
+	/* data sync? */
+	gfs2_meta_sync(ip->i_gl);
+
+	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
+		jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
+}
+
+static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+	struct list_head *head;
+	struct gfs2_bufdata *bd;
+
+	if (tr == NULL)
+		return;
+
+	head = &tr->tr_databuf;
+	while (!list_empty(head)) {
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		gfs2_unpin(sdp, bd->bd_bh, tr);
+	}
+}
+
+
+const struct gfs2_log_operations gfs2_buf_lops = {
+	.lo_before_commit = buf_lo_before_commit,
+	.lo_after_commit = buf_lo_after_commit,
+	.lo_before_scan = buf_lo_before_scan,
+	.lo_scan_elements = buf_lo_scan_elements,
+	.lo_after_scan = buf_lo_after_scan,
+	.lo_name = "buf",
+};
+
+const struct gfs2_log_operations gfs2_revoke_lops = {
+	.lo_before_commit = revoke_lo_before_commit,
+	.lo_after_commit = revoke_lo_after_commit,
+	.lo_before_scan = revoke_lo_before_scan,
+	.lo_scan_elements = revoke_lo_scan_elements,
+	.lo_after_scan = revoke_lo_after_scan,
+	.lo_name = "revoke",
+};
+
+const struct gfs2_log_operations gfs2_databuf_lops = {
+	.lo_before_commit = databuf_lo_before_commit,
+	.lo_after_commit = databuf_lo_after_commit,
+	.lo_scan_elements = databuf_lo_scan_elements,
+	.lo_after_scan = databuf_lo_after_scan,
+	.lo_name = "databuf",
+};
+
+const struct gfs2_log_operations *gfs2_log_ops[] = {
+	&gfs2_databuf_lops,
+	&gfs2_buf_lops,
+	&gfs2_revoke_lops,
+	NULL,
+};
+

fs/gfs2/lops.h

@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 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 __LOPS_DOT_H__
+#define __LOPS_DOT_H__
+
+#include <linux/list.h>
+#include "incore.h"
+
+#define BUF_OFFSET \
+	((sizeof(struct gfs2_log_descriptor) + sizeof(__be64) - 1) & \
+	 ~(sizeof(__be64) - 1))
+#define DATABUF_OFFSET \
+	((sizeof(struct gfs2_log_descriptor) + (2 * sizeof(__be64) - 1)) & \
+	 ~(2 * sizeof(__be64) - 1))
+
+extern const struct gfs2_log_operations gfs2_glock_lops;
+extern const struct gfs2_log_operations gfs2_buf_lops;
+extern const struct gfs2_log_operations gfs2_revoke_lops;
+extern const struct gfs2_log_operations gfs2_databuf_lops;
+
+extern const struct gfs2_log_operations *gfs2_log_ops[];
+extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page);
+extern void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw);
+extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
+
+static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
+{
+	unsigned int limit;
+
+	limit = (sdp->sd_sb.sb_bsize - BUF_OFFSET) / sizeof(__be64);
+	return limit;
+}
+
+static inline unsigned int databuf_limit(struct gfs2_sbd *sdp)
+{
+	unsigned int limit;
+
+	limit = (sdp->sd_sb.sb_bsize - DATABUF_OFFSET) / (2 * sizeof(__be64));
+	return limit;
+}
+
+static inline void lops_before_commit(struct gfs2_sbd *sdp,
+				      struct gfs2_trans *tr)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_commit)
+			gfs2_log_ops[x]->lo_before_commit(sdp, tr);
+}
+
+static inline void lops_after_commit(struct gfs2_sbd *sdp,
+				     struct gfs2_trans *tr)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_after_commit)
+			gfs2_log_ops[x]->lo_after_commit(sdp, tr);
+}
+
+static inline void lops_before_scan(struct gfs2_jdesc *jd,
+				    struct gfs2_log_header_host *head,
+				    unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_before_scan(jd, head, pass);
+}
+
+static inline int lops_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+				     struct gfs2_log_descriptor *ld,
+				     __be64 *ptr,
+				     unsigned int pass)
+{
+	int x, error;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_scan_elements) {
+			error = gfs2_log_ops[x]->lo_scan_elements(jd, start,
+								  ld, ptr, pass);
+			if (error)
+				return error;
+		}
+
+	return 0;
+}
+
+static inline void lops_after_scan(struct gfs2_jdesc *jd, int error,
+				   unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_after_scan(jd, error, pass);
+}
+
+#endif /* __LOPS_DOT_H__ */
+

fs/gfs2/main.c

@@ -0,0 +1,249 @@
+/*
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <linux/atomic.h>
+#include <linux/mempool.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+#include "glock.h"
+#include "quota.h"
+#include "recovery.h"
+#include "dir.h"
+
+struct workqueue_struct *gfs2_control_wq;
+
+static void gfs2_init_inode_once(void *foo)
+{
+	struct gfs2_inode *ip = foo;
+
+	inode_init_once(&ip->i_inode);
+	init_rwsem(&ip->i_rw_mutex);
+	INIT_LIST_HEAD(&ip->i_trunc_list);
+	ip->i_res = NULL;
+	ip->i_hash_cache = NULL;
+}
+
+static void gfs2_init_glock_once(void *foo)
+{
+	struct gfs2_glock *gl = foo;
+
+	INIT_HLIST_BL_NODE(&gl->gl_list);
+	spin_lock_init(&gl->gl_spin);
+	INIT_LIST_HEAD(&gl->gl_holders);
+	INIT_LIST_HEAD(&gl->gl_lru);
+	INIT_LIST_HEAD(&gl->gl_ail_list);
+	atomic_set(&gl->gl_ail_count, 0);
+	atomic_set(&gl->gl_revokes, 0);
+}
+
+static void gfs2_init_gl_aspace_once(void *foo)
+{
+	struct gfs2_glock *gl = foo;
+	struct address_space *mapping = (struct address_space *)(gl + 1);
+
+	gfs2_init_glock_once(gl);
+	address_space_init_once(mapping);
+}
+
+/**
+ * init_gfs2_fs - Register GFS2 as a filesystem
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int __init init_gfs2_fs(void)
+{
+	int error;
+
+	gfs2_str2qstr(&gfs2_qdot, ".");
+	gfs2_str2qstr(&gfs2_qdotdot, "..");
+	gfs2_quota_hash_init();
+
+	error = gfs2_sys_init();
+	if (error)
+		return error;
+
+	error = list_lru_init(&gfs2_qd_lru);
+	if (error)
+		goto fail_lru;
+
+	error = gfs2_glock_init();
+	if (error)
+		goto fail;
+
+	error = -ENOMEM;
+	gfs2_glock_cachep = kmem_cache_create("gfs2_glock",
+					      sizeof(struct gfs2_glock),
+					      0, 0,
+					      gfs2_init_glock_once);
+	if (!gfs2_glock_cachep)
+		goto fail;
+
+	gfs2_glock_aspace_cachep = kmem_cache_create("gfs2_glock(aspace)",
+					sizeof(struct gfs2_glock) +
+					sizeof(struct address_space),
+					0, 0, gfs2_init_gl_aspace_once);
+
+	if (!gfs2_glock_aspace_cachep)
+		goto fail;
+
+	gfs2_inode_cachep = kmem_cache_create("gfs2_inode",
+					      sizeof(struct gfs2_inode),
+					      0,  SLAB_RECLAIM_ACCOUNT|
+					          SLAB_MEM_SPREAD,
+					      gfs2_init_inode_once);
+	if (!gfs2_inode_cachep)
+		goto fail;
+
+	gfs2_bufdata_cachep = kmem_cache_create("gfs2_bufdata",
+						sizeof(struct gfs2_bufdata),
+					        0, 0, NULL);
+	if (!gfs2_bufdata_cachep)
+		goto fail;
+
+	gfs2_rgrpd_cachep = kmem_cache_create("gfs2_rgrpd",
+					      sizeof(struct gfs2_rgrpd),
+					      0, 0, NULL);
+	if (!gfs2_rgrpd_cachep)
+		goto fail;
+
+	gfs2_quotad_cachep = kmem_cache_create("gfs2_quotad",
+					       sizeof(struct gfs2_quota_data),
+					       0, 0, NULL);
+	if (!gfs2_quotad_cachep)
+		goto fail;
+
+	gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk",
+					     sizeof(struct gfs2_blkreserv),
+					       0, 0, NULL);
+	if (!gfs2_rsrv_cachep)
+		goto fail;
+
+	register_shrinker(&gfs2_qd_shrinker);
+
+	error = register_filesystem(&gfs2_fs_type);
+	if (error)
+		goto fail;
+
+	error = register_filesystem(&gfs2meta_fs_type);
+	if (error)
+		goto fail_unregister;
+
+	error = -ENOMEM;
+	gfs_recovery_wq = alloc_workqueue("gfs_recovery",
+					  WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
+	if (!gfs_recovery_wq)
+		goto fail_wq;
+
+	gfs2_control_wq = alloc_workqueue("gfs2_control",
+					  WQ_UNBOUND | WQ_FREEZABLE, 0);
+	if (!gfs2_control_wq)
+		goto fail_recovery;
+
+	gfs2_page_pool = mempool_create_page_pool(64, 0);
+	if (!gfs2_page_pool)
+		goto fail_control;
+
+	gfs2_register_debugfs();
+
+	pr_info("GFS2 installed\n");
+
+	return 0;
+
+fail_control:
+	destroy_workqueue(gfs2_control_wq);
+fail_recovery:
+	destroy_workqueue(gfs_recovery_wq);
+fail_wq:
+	unregister_filesystem(&gfs2meta_fs_type);
+fail_unregister:
+	unregister_filesystem(&gfs2_fs_type);
+fail:
+	list_lru_destroy(&gfs2_qd_lru);
+fail_lru:
+	unregister_shrinker(&gfs2_qd_shrinker);
+	gfs2_glock_exit();
+
+	if (gfs2_rsrv_cachep)
+		kmem_cache_destroy(gfs2_rsrv_cachep);
+
+	if (gfs2_quotad_cachep)
+		kmem_cache_destroy(gfs2_quotad_cachep);
+
+	if (gfs2_rgrpd_cachep)
+		kmem_cache_destroy(gfs2_rgrpd_cachep);
+
+	if (gfs2_bufdata_cachep)
+		kmem_cache_destroy(gfs2_bufdata_cachep);
+
+	if (gfs2_inode_cachep)
+		kmem_cache_destroy(gfs2_inode_cachep);
+
+	if (gfs2_glock_aspace_cachep)
+		kmem_cache_destroy(gfs2_glock_aspace_cachep);
+
+	if (gfs2_glock_cachep)
+		kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+	return error;
+}
+
+/**
+ * exit_gfs2_fs - Unregister the file system
+ *
+ */
+
+static void __exit exit_gfs2_fs(void)
+{
+	unregister_shrinker(&gfs2_qd_shrinker);
+	gfs2_glock_exit();
+	gfs2_unregister_debugfs();
+	unregister_filesystem(&gfs2_fs_type);
+	unregister_filesystem(&gfs2meta_fs_type);
+	destroy_workqueue(gfs_recovery_wq);
+	destroy_workqueue(gfs2_control_wq);
+	list_lru_destroy(&gfs2_qd_lru);
+
+	rcu_barrier();
+
+	mempool_destroy(gfs2_page_pool);
+	kmem_cache_destroy(gfs2_rsrv_cachep);
+	kmem_cache_destroy(gfs2_quotad_cachep);
+	kmem_cache_destroy(gfs2_rgrpd_cachep);
+	kmem_cache_destroy(gfs2_bufdata_cachep);
+	kmem_cache_destroy(gfs2_inode_cachep);
+	kmem_cache_destroy(gfs2_glock_aspace_cachep);
+	kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+}
+
+MODULE_DESCRIPTION("Global File System");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+module_init(init_gfs2_fs);
+module_exit(exit_gfs2_fs);
+

fs/gfs2/meta_io.c

@@ -0,0 +1,403 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 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/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>
+#include <linux/swap.h>
+#include <linux/delay.h>
+#include <linux/bio.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "glops.h"
+#include "inode.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct buffer_head *bh, *head;
+	int nr_underway = 0;
+	int write_op = REQ_META | REQ_PRIO |
+		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(!page_has_buffers(page));
+
+	head = page_buffers(page);
+	bh = head;
+
+	do {
+		if (!buffer_mapped(bh))
+			continue;
+		/*
+		 * If it's a fully non-blocking write attempt and we cannot
+		 * lock the buffer then redirty the page.  Note that this can
+		 * potentially cause a busy-wait loop from flusher thread and kswapd
+		 * activity, but those code paths have their own higher-level
+		 * throttling.
+		 */
+		if (wbc->sync_mode != WB_SYNC_NONE) {
+			lock_buffer(bh);
+		} else if (!trylock_buffer(bh)) {
+			redirty_page_for_writepage(wbc, page);
+			continue;
+		}
+		if (test_clear_buffer_dirty(bh)) {
+			mark_buffer_async_write(bh);
+		} else {
+			unlock_buffer(bh);
+		}
+	} while ((bh = bh->b_this_page) != head);
+
+	/*
+	 * The page and its buffers are protected by PageWriteback(), so we can
+	 * drop the bh refcounts early.
+	 */
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+
+	do {
+		struct buffer_head *next = bh->b_this_page;
+		if (buffer_async_write(bh)) {
+			submit_bh(write_op, bh);
+			nr_underway++;
+		}
+		bh = next;
+	} while (bh != head);
+	unlock_page(page);
+
+	if (nr_underway == 0)
+		end_page_writeback(page);
+
+	return 0;
+}
+
+const struct address_space_operations gfs2_meta_aops = {
+	.writepage = gfs2_aspace_writepage,
+	.releasepage = gfs2_releasepage,
+};
+
+const struct address_space_operations gfs2_rgrp_aops = {
+	.writepage = gfs2_aspace_writepage,
+	.releasepage = gfs2_releasepage,
+};
+
+/**
+ * gfs2_getbuf - Get a buffer with a given address space
+ * @gl: the glock
+ * @blkno: the block number (filesystem scope)
+ * @create: 1 if the buffer should be created
+ *
+ * Returns: the buffer
+ */
+
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
+{
+	struct address_space *mapping = gfs2_glock2aspace(gl);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct page *page;
+	struct buffer_head *bh;
+	unsigned int shift;
+	unsigned long index;
+	unsigned int bufnum;
+
+	if (mapping == NULL)
+		mapping = &sdp->sd_aspace;
+
+	shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
+	index = blkno >> shift;             /* convert block to page */
+	bufnum = blkno - (index << shift);  /* block buf index within page */
+
+	if (create) {
+		for (;;) {
+			page = grab_cache_page(mapping, index);
+			if (page)
+				break;
+			yield();
+		}
+	} else {
+		page = find_get_page_flags(mapping, index,
+						FGP_LOCK|FGP_ACCESSED);
+		if (!page)
+			return NULL;
+	}
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
+
+	/* Locate header for our buffer within our page */
+	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
+		/* Do nothing */;
+	get_bh(bh);
+
+	if (!buffer_mapped(bh))
+		map_bh(bh, sdp->sd_vfs, blkno);
+
+	unlock_page(page);
+	page_cache_release(page);
+
+	return bh;
+}
+
+static void meta_prep_new(struct buffer_head *bh)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+
+	lock_buffer(bh);
+	clear_buffer_dirty(bh);
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+
+	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
+}
+
+/**
+ * gfs2_meta_new - Get a block
+ * @gl: The glock associated with this block
+ * @blkno: The block number
+ *
+ * Returns: The buffer
+ */
+
+struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
+{
+	struct buffer_head *bh;
+	bh = gfs2_getbuf(gl, blkno, CREATE);
+	meta_prep_new(bh);
+	return bh;
+}
+
+/**
+ * gfs2_meta_read - Read a block from disk
+ * @gl: The glock covering the block
+ * @blkno: The block number
+ * @flags: flags
+ * @bhp: the place where the buffer is returned (NULL on failure)
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
+		   struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *bh;
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+		*bhp = NULL;
+		return -EIO;
+	}
+
+	*bhp = bh = gfs2_getbuf(gl, blkno, CREATE);
+
+	lock_buffer(bh);
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+	bh->b_end_io = end_buffer_read_sync;
+	get_bh(bh);
+	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh);
+	if (!(flags & DIO_WAIT))
+		return 0;
+
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh))) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		brelse(bh);
+		*bhp = NULL;
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_meta_wait - Reread a block from disk
+ * @sdp: the filesystem
+ * @bh: The block to wait for
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	wait_on_buffer(bh);
+
+	if (!buffer_uptodate(bh)) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		return -EIO;
+	}
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	return 0;
+}
+
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
+{
+	struct address_space *mapping = bh->b_page->mapping;
+	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
+	struct gfs2_bufdata *bd = bh->b_private;
+	int was_pinned = 0;
+
+	if (test_clear_buffer_pinned(bh)) {
+		trace_gfs2_pin(bd, 0);
+		atomic_dec(&sdp->sd_log_pinned);
+		list_del_init(&bd->bd_list);
+		if (meta)
+			tr->tr_num_buf_rm++;
+		else
+			tr->tr_num_databuf_rm++;
+		tr->tr_touched = 1;
+		was_pinned = 1;
+		brelse(bh);
+	}
+	if (bd) {
+		spin_lock(&sdp->sd_ail_lock);
+		if (bd->bd_tr) {
+			gfs2_trans_add_revoke(sdp, bd);
+		} else if (was_pinned) {
+			bh->b_private = NULL;
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+		}
+		spin_unlock(&sdp->sd_ail_lock);
+	}
+	clear_buffer_dirty(bh);
+	clear_buffer_uptodate(bh);
+}
+
+/**
+ * gfs2_meta_wipe - make inode's buffers so they aren't dirty/pinned anymore
+ * @ip: the inode who owns the buffers
+ * @bstart: the first buffer in the run
+ * @blen: the number of buffers in the run
+ *
+ */
+
+void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh;
+
+	while (blen) {
+		bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
+		if (bh) {
+			lock_buffer(bh);
+			gfs2_log_lock(sdp);
+			gfs2_remove_from_journal(bh, current->journal_info, 1);
+			gfs2_log_unlock(sdp);
+			unlock_buffer(bh);
+			brelse(bh);
+		}
+
+		bstart++;
+		blen--;
+	}
+}
+
+/**
+ * gfs2_meta_indirect_buffer - Get a metadata buffer
+ * @ip: The GFS2 inode
+ * @height: The level of this buf in the metadata (indir addr) tree (if any)
+ * @num: The block number (device relative) of the buffer
+ * @bhp: the buffer is returned here
+ *
+ * Returns: errno
+ */
+
+int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+			      struct buffer_head **bhp)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	struct buffer_head *bh;
+	int ret = 0;
+	u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+
+	ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh);
+	if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
+		brelse(bh);
+		ret = -EIO;
+	}
+	*bhp = bh;
+	return ret;
+}
+
+/**
+ * gfs2_meta_ra - start readahead on an extent of a file
+ * @gl: the glock the blocks belong to
+ * @dblock: the starting disk block
+ * @extlen: the number of blocks in the extent
+ *
+ * returns: the first buffer in the extent
+ */
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *first_bh, *bh;
+	u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
+			  sdp->sd_sb.sb_bsize_shift;
+
+	BUG_ON(!extlen);
+
+	if (max_ra < 1)
+		max_ra = 1;
+	if (extlen > max_ra)
+		extlen = max_ra;
+
+	first_bh = gfs2_getbuf(gl, dblock, CREATE);
+
+	if (buffer_uptodate(first_bh))
+		goto out;
+	if (!buffer_locked(first_bh))
+		ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh);
+
+	dblock++;
+	extlen--;
+
+	while (extlen) {
+		bh = gfs2_getbuf(gl, dblock, CREATE);
+
+		if (!buffer_uptodate(bh) && !buffer_locked(bh))
+			ll_rw_block(READA | REQ_META, 1, &bh);
+		brelse(bh);
+		dblock++;
+		extlen--;
+		if (!buffer_locked(first_bh) && buffer_uptodate(first_bh))
+			goto out;
+	}
+
+	wait_on_buffer(first_bh);
+out:
+	return first_bh;
+}
+

fs/gfs2/meta_io.h

@@ -0,0 +1,78 @@
+/*
+ * 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 __DIO_DOT_H__
+#define __DIO_DOT_H__
+
+#include <linux/buffer_head.h>
+#include <linux/string.h>
+#include "incore.h"
+
+static inline void gfs2_buffer_clear(struct buffer_head *bh)
+{
+	memset(bh->b_data, 0, bh->b_size);
+}
+
+static inline void gfs2_buffer_clear_tail(struct buffer_head *bh, int head)
+{
+	BUG_ON(head > bh->b_size);
+	memset(bh->b_data + head, 0, bh->b_size - head);
+}
+
+static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh,
+					 int to_head,
+					 struct buffer_head *from_bh,
+					 int from_head)
+{
+	BUG_ON(from_head < to_head);
+	memcpy(to_bh->b_data + to_head, from_bh->b_data + from_head,
+	       from_bh->b_size - from_head);
+	memset(to_bh->b_data + to_bh->b_size + to_head - from_head,
+	       0, from_head - to_head);
+}
+
+extern const struct address_space_operations gfs2_meta_aops;
+extern const struct address_space_operations gfs2_rgrp_aops;
+
+static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
+{
+	struct inode *inode = mapping->host;
+	if (mapping->a_ops == &gfs2_meta_aops)
+		return (((struct gfs2_glock *)mapping) - 1)->gl_sbd;
+	else if (mapping->a_ops == &gfs2_rgrp_aops)
+		return container_of(mapping, struct gfs2_sbd, sd_aspace);
+	else
+		return inode->i_sb->s_fs_info;
+}
+
+extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
+extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
+			  struct buffer_head **bhp);
+extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
+extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno,
+				       int create);
+extern void gfs2_remove_from_journal(struct buffer_head *bh,
+				     struct gfs2_trans *tr, int meta);
+extern void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
+				     struct buffer_head **bhp);
+
+static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip,
+					 struct buffer_head **bhp)
+{
+	return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, bhp);
+}
+
+struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen);
+
+#define buffer_busy(bh) \
+((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock) | (1ul << BH_Pinned)))
+
+#endif /* __DIO_DOT_H__ */
+

fs/gfs2/quota.h

@@ -0,0 +1,62 @@
+/*
+ * 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 __QUOTA_DOT_H__
+#define __QUOTA_DOT_H__
+
+#include <linux/list_lru.h>
+
+struct gfs2_inode;
+struct gfs2_sbd;
+
+#define NO_UID_QUOTA_CHANGE INVALID_UID
+#define NO_GID_QUOTA_CHANGE INVALID_GID
+
+extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
+extern void gfs2_quota_unhold(struct gfs2_inode *ip);
+
+extern int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
+extern void gfs2_quota_unlock(struct gfs2_inode *ip);
+
+extern int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
+extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
+			      kuid_t uid, kgid_t gid);
+
+extern int gfs2_quota_sync(struct super_block *sb, int type);
+extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid);
+
+extern int gfs2_quota_init(struct gfs2_sbd *sdp);
+extern void gfs2_quota_cleanup(struct gfs2_sbd *sdp);
+extern int gfs2_quotad(void *data);
+
+extern void gfs2_wake_up_statfs(struct gfs2_sbd *sdp);
+
+static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int ret;
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+	ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
+	if (ret)
+		return ret;
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+		return 0;
+	ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
+	if (ret)
+		gfs2_quota_unlock(ip);
+	return ret;
+}
+
+extern const struct quotactl_ops gfs2_quotactl_ops;
+extern struct shrinker gfs2_qd_shrinker;
+extern struct list_lru gfs2_qd_lru;
+extern void __init gfs2_quota_hash_init(void);
+
+#endif /* __QUOTA_DOT_H__ */

fs/gfs2/recovery.c

@@ -0,0 +1,611 @@
+/*
+ * 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/module.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/crc32.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "bmap.h"
+#include "glock.h"
+#include "glops.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "recovery.h"
+#include "super.h"
+#include "util.h"
+#include "dir.h"
+
+struct workqueue_struct *gfs_recovery_wq;
+
+int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
+			   struct buffer_head **bh)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	int new = 0;
+	u64 dblock;
+	u32 extlen;
+	int error;
+
+	error = gfs2_extent_map(&ip->i_inode, blk, &new, &dblock, &extlen);
+	if (error)
+		return error;
+	if (!dblock) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	*bh = gfs2_meta_ra(gl, dblock, extlen);
+
+	return error;
+}
+
+int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where)
+{
+	struct list_head *head = &jd->jd_revoke_list;
+	struct gfs2_revoke_replay *rr;
+	int found = 0;
+
+	list_for_each_entry(rr, head, rr_list) {
+		if (rr->rr_blkno == blkno) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (found) {
+		rr->rr_where = where;
+		return 0;
+	}
+
+	rr = kmalloc(sizeof(struct gfs2_revoke_replay), GFP_NOFS);
+	if (!rr)
+		return -ENOMEM;
+
+	rr->rr_blkno = blkno;
+	rr->rr_where = where;
+	list_add(&rr->rr_list, head);
+
+	return 1;
+}
+
+int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where)
+{
+	struct gfs2_revoke_replay *rr;
+	int wrap, a, b, revoke;
+	int found = 0;
+
+	list_for_each_entry(rr, &jd->jd_revoke_list, rr_list) {
+		if (rr->rr_blkno == blkno) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found)
+		return 0;
+
+	wrap = (rr->rr_where < jd->jd_replay_tail);
+	a = (jd->jd_replay_tail < where);
+	b = (where < rr->rr_where);
+	revoke = (wrap) ? (a || b) : (a && b);
+
+	return revoke;
+}
+
+void gfs2_revoke_clean(struct gfs2_jdesc *jd)
+{
+	struct list_head *head = &jd->jd_revoke_list;
+	struct gfs2_revoke_replay *rr;
+
+	while (!list_empty(head)) {
+		rr = list_entry(head->next, struct gfs2_revoke_replay, rr_list);
+		list_del(&rr->rr_list);
+		kfree(rr);
+	}
+}
+
+static int gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf)
+{
+	const struct gfs2_log_header *str = buf;
+
+	if (str->lh_header.mh_magic != cpu_to_be32(GFS2_MAGIC) ||
+	    str->lh_header.mh_type != cpu_to_be32(GFS2_METATYPE_LH))
+		return 1;
+
+	lh->lh_sequence = be64_to_cpu(str->lh_sequence);
+	lh->lh_flags = be32_to_cpu(str->lh_flags);
+	lh->lh_tail = be32_to_cpu(str->lh_tail);
+	lh->lh_blkno = be32_to_cpu(str->lh_blkno);
+	lh->lh_hash = be32_to_cpu(str->lh_hash);
+	return 0;
+}
+
+/**
+ * get_log_header - read the log header for a given segment
+ * @jd: the journal
+ * @blk: the block to look at
+ * @lh: the log header to return
+ *
+ * Read the log header for a given segement in a given journal.  Do a few
+ * sanity checks on it.
+ *
+ * Returns: 0 on success,
+ *          1 if the header was invalid or incomplete,
+ *          errno on error
+ */
+
+static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk,
+			  struct gfs2_log_header_host *head)
+{
+	struct buffer_head *bh;
+	struct gfs2_log_header_host uninitialized_var(lh);
+	const u32 nothing = 0;
+	u32 hash;
+	int error;
+
+	error = gfs2_replay_read_block(jd, blk, &bh);
+	if (error)
+		return error;
+
+	hash = crc32_le((u32)~0, bh->b_data, sizeof(struct gfs2_log_header) -
+					     sizeof(u32));
+	hash = crc32_le(hash, (unsigned char const *)&nothing, sizeof(nothing));
+	hash ^= (u32)~0;
+	error = gfs2_log_header_in(&lh, bh->b_data);
+	brelse(bh);
+
+	if (error || lh.lh_blkno != blk || lh.lh_hash != hash)
+		return 1;
+
+	*head = lh;
+
+	return 0;
+}
+
+/**
+ * find_good_lh - find a good log header
+ * @jd: the journal
+ * @blk: the segment to start searching from
+ * @lh: the log header to fill in
+ * @forward: if true search forward in the log, else search backward
+ *
+ * Call get_log_header() to get a log header for a segment, but if the
+ * segment is bad, either scan forward or backward until we find a good one.
+ *
+ * Returns: errno
+ */
+
+static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk,
+			struct gfs2_log_header_host *head)
+{
+	unsigned int orig_blk = *blk;
+	int error;
+
+	for (;;) {
+		error = get_log_header(jd, *blk, head);
+		if (error <= 0)
+			return error;
+
+		if (++*blk == jd->jd_blocks)
+			*blk = 0;
+
+		if (*blk == orig_blk) {
+			gfs2_consist_inode(GFS2_I(jd->jd_inode));
+			return -EIO;
+		}
+	}
+}
+
+/**
+ * jhead_scan - make sure we've found the head of the log
+ * @jd: the journal
+ * @head: this is filled in with the log descriptor of the head
+ *
+ * At this point, seg and lh should be either the head of the log or just
+ * before.  Scan forward until we find the head.
+ *
+ * Returns: errno
+ */
+
+static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	unsigned int blk = head->lh_blkno;
+	struct gfs2_log_header_host lh;
+	int error;
+
+	for (;;) {
+		if (++blk == jd->jd_blocks)
+			blk = 0;
+
+		error = get_log_header(jd, blk, &lh);
+		if (error < 0)
+			return error;
+		if (error == 1)
+			continue;
+
+		if (lh.lh_sequence == head->lh_sequence) {
+			gfs2_consist_inode(GFS2_I(jd->jd_inode));
+			return -EIO;
+		}
+		if (lh.lh_sequence < head->lh_sequence)
+			break;
+
+		*head = lh;
+	}
+
+	return 0;
+}
+
+/**
+ * gfs2_find_jhead - find the head of a log
+ * @jd: the journal
+ * @head: the log descriptor for the head of the log is returned here
+ *
+ * Do a binary search of a journal and find the valid log entry with the
+ * highest sequence number.  (i.e. the log head)
+ *
+ * Returns: errno
+ */
+
+int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	struct gfs2_log_header_host lh_1, lh_m;
+	u32 blk_1, blk_2, blk_m;
+	int error;
+
+	blk_1 = 0;
+	blk_2 = jd->jd_blocks - 1;
+
+	for (;;) {
+		blk_m = (blk_1 + blk_2) / 2;
+
+		error = find_good_lh(jd, &blk_1, &lh_1);
+		if (error)
+			return error;
+
+		error = find_good_lh(jd, &blk_m, &lh_m);
+		if (error)
+			return error;
+
+		if (blk_1 == blk_m || blk_m == blk_2)
+			break;
+
+		if (lh_1.lh_sequence <= lh_m.lh_sequence)
+			blk_1 = blk_m;
+		else
+			blk_2 = blk_m;
+	}
+
+	error = jhead_scan(jd, &lh_1);
+	if (error)
+		return error;
+
+	*head = lh_1;
+
+	return error;
+}
+
+/**
+ * foreach_descriptor - go through the active part of the log
+ * @jd: the journal
+ * @start: the first log header in the active region
+ * @end: the last log header (don't process the contents of this entry))
+ *
+ * Call a given function once for every log descriptor in the active
+ * portion of the log.
+ *
+ * Returns: errno
+ */
+
+static int foreach_descriptor(struct gfs2_jdesc *jd, unsigned int start,
+			      unsigned int end, int pass)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct buffer_head *bh;
+	struct gfs2_log_descriptor *ld;
+	int error = 0;
+	u32 length;
+	__be64 *ptr;
+	unsigned int offset = sizeof(struct gfs2_log_descriptor);
+	offset += sizeof(__be64) - 1;
+	offset &= ~(sizeof(__be64) - 1);
+
+	while (start != end) {
+		error = gfs2_replay_read_block(jd, start, &bh);
+		if (error)
+			return error;
+		if (gfs2_meta_check(sdp, bh)) {
+			brelse(bh);
+			return -EIO;
+		}
+		ld = (struct gfs2_log_descriptor *)bh->b_data;
+		length = be32_to_cpu(ld->ld_length);
+
+		if (be32_to_cpu(ld->ld_header.mh_type) == GFS2_METATYPE_LH) {
+			struct gfs2_log_header_host lh;
+			error = get_log_header(jd, start, &lh);
+			if (!error) {
+				gfs2_replay_incr_blk(sdp, &start);
+				brelse(bh);
+				continue;
+			}
+			if (error == 1) {
+				gfs2_consist_inode(GFS2_I(jd->jd_inode));
+				error = -EIO;
+			}
+			brelse(bh);
+			return error;
+		} else if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_LD)) {
+			brelse(bh);
+			return -EIO;
+		}
+		ptr = (__be64 *)(bh->b_data + offset);
+		error = lops_scan_elements(jd, start, ld, ptr, pass);
+		if (error) {
+			brelse(bh);
+			return error;
+		}
+
+		while (length--)
+			gfs2_replay_incr_blk(sdp, &start);
+
+		brelse(bh);
+	}
+
+	return 0;
+}
+
+/**
+ * clean_journal - mark a dirty journal as being clean
+ * @sdp: the filesystem
+ * @jd: the journal
+ * @gl: the journal's glock
+ * @head: the head journal to start from
+ *
+ * Returns: errno
+ */
+
+static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	unsigned int lblock;
+	struct gfs2_log_header *lh;
+	u32 hash;
+	struct buffer_head *bh;
+	int error;
+	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
+
+	lblock = head->lh_blkno;
+	gfs2_replay_incr_blk(sdp, &lblock);
+	bh_map.b_size = 1 << ip->i_inode.i_blkbits;
+	error = gfs2_block_map(&ip->i_inode, lblock, &bh_map, 0);
+	if (error)
+		return error;
+	if (!bh_map.b_blocknr) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	bh = sb_getblk(sdp->sd_vfs, bh_map.b_blocknr);
+	lock_buffer(bh);
+	memset(bh->b_data, 0, bh->b_size);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
+	unlock_buffer(bh);
+
+	lh = (struct gfs2_log_header *)bh->b_data;
+	memset(lh, 0, sizeof(struct gfs2_log_header));
+	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
+	lh->lh_header.__pad0 = cpu_to_be64(0);
+	lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
+	lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	lh->lh_sequence = cpu_to_be64(head->lh_sequence + 1);
+	lh->lh_flags = cpu_to_be32(GFS2_LOG_HEAD_UNMOUNT);
+	lh->lh_blkno = cpu_to_be32(lblock);
+	hash = gfs2_disk_hash((const char *)lh, sizeof(struct gfs2_log_header));
+	lh->lh_hash = cpu_to_be32(hash);
+
+	set_buffer_dirty(bh);
+	if (sync_dirty_buffer(bh))
+		gfs2_io_error_bh(sdp, bh);
+	brelse(bh);
+
+	return error;
+}
+
+
+static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
+                               unsigned int message)
+{
+	char env_jid[20];
+	char env_status[20];
+	char *envp[] = { env_jid, env_status, NULL };
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+
+        ls->ls_recover_jid_done = jid;
+        ls->ls_recover_jid_status = message;
+	sprintf(env_jid, "JID=%d", jid);
+	sprintf(env_status, "RECOVERY=%s",
+		message == LM_RD_SUCCESS ? "Done" : "Failed");
+        kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
+
+	if (sdp->sd_lockstruct.ls_ops->lm_recovery_result)
+		sdp->sd_lockstruct.ls_ops->lm_recovery_result(sdp, jid, message);
+}
+
+void gfs2_recover_func(struct work_struct *work)
+{
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	struct gfs2_log_header_host head;
+	struct gfs2_holder j_gh, ji_gh, thaw_gh;
+	unsigned long t;
+	int ro = 0;
+	unsigned int pass;
+	int error;
+	int jlocked = 0;
+
+	if (sdp->sd_args.ar_spectator ||
+	    (jd->jd_jid != sdp->sd_lockstruct.ls_jid)) {
+		fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
+			jd->jd_jid);
+		jlocked = 1;
+		/* Acquire the journal lock so we can do recovery */
+
+		error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops,
+					  LM_ST_EXCLUSIVE,
+					  LM_FLAG_NOEXP | LM_FLAG_TRY | GL_NOCACHE,
+					  &j_gh);
+		switch (error) {
+		case 0:
+			break;
+
+		case GLR_TRYFAILED:
+			fs_info(sdp, "jid=%u: Busy\n", jd->jd_jid);
+			error = 0;
+
+		default:
+			goto fail;
+		};
+
+		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
+		if (error)
+			goto fail_gunlock_j;
+	} else {
+		fs_info(sdp, "jid=%u, already locked for use\n", jd->jd_jid);
+	}
+
+	fs_info(sdp, "jid=%u: Looking at journal...\n", jd->jd_jid);
+
+	error = gfs2_jdesc_check(jd);
+	if (error)
+		goto fail_gunlock_ji;
+
+	error = gfs2_find_jhead(jd, &head);
+	if (error)
+		goto fail_gunlock_ji;
+
+	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+		fs_info(sdp, "jid=%u: Acquiring the transaction lock...\n",
+			jd->jd_jid);
+
+		t = jiffies;
+
+		/* Acquire a shared hold on the freeze lock */
+
+		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY,
+					   &thaw_gh);
+		if (error)
+			goto fail_gunlock_ji;
+
+		if (test_bit(SDF_RORECOVERY, &sdp->sd_flags)) {
+			ro = 1;
+		} else if (test_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags)) {
+			if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+				ro = 1;
+		} else {
+			if (sdp->sd_vfs->s_flags & MS_RDONLY) {
+				/* check if device itself is read-only */
+				ro = bdev_read_only(sdp->sd_vfs->s_bdev);
+				if (!ro) {
+					fs_info(sdp, "recovery required on "
+						"read-only filesystem.\n");
+					fs_info(sdp, "write access will be "
+						"enabled during recovery.\n");
+				}
+			}
+		}
+
+		if (ro) {
+			fs_warn(sdp, "jid=%u: Can't replay: read-only block "
+				"device\n", jd->jd_jid);
+			error = -EROFS;
+			goto fail_gunlock_thaw;
+		}
+
+		fs_info(sdp, "jid=%u: Replaying journal...\n", jd->jd_jid);
+
+		for (pass = 0; pass < 2; pass++) {
+			lops_before_scan(jd, &head, pass);
+			error = foreach_descriptor(jd, head.lh_tail,
+						   head.lh_blkno, pass);
+			lops_after_scan(jd, error, pass);
+			if (error)
+				goto fail_gunlock_thaw;
+		}
+
+		error = clean_journal(jd, &head);
+		if (error)
+			goto fail_gunlock_thaw;
+
+		gfs2_glock_dq_uninit(&thaw_gh);
+		t = DIV_ROUND_UP(jiffies - t, HZ);
+		fs_info(sdp, "jid=%u: Journal replayed in %lus\n",
+			jd->jd_jid, t);
+	}
+
+	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS);
+
+	if (jlocked) {
+		gfs2_glock_dq_uninit(&ji_gh);
+		gfs2_glock_dq_uninit(&j_gh);
+	}
+
+	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
+	goto done;
+
+fail_gunlock_thaw:
+	gfs2_glock_dq_uninit(&thaw_gh);
+fail_gunlock_ji:
+	if (jlocked) {
+		gfs2_glock_dq_uninit(&ji_gh);
+fail_gunlock_j:
+		gfs2_glock_dq_uninit(&j_gh);
+	}
+
+	fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done");
+fail:
+	jd->jd_recover_error = error;
+	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
+done:
+	clear_bit(JDF_RECOVERY, &jd->jd_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
+}
+
+int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
+{
+	int rv;
+
+	if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
+		return -EBUSY;
+
+	/* we have JDF_RECOVERY, queue should always succeed */
+	rv = queue_work(gfs_recovery_wq, &jd->jd_work);
+	BUG_ON(!rv);
+
+	if (wait)
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
+			    TASK_UNINTERRUPTIBLE);
+
+	return wait ? jd->jd_recover_error : 0;
+}
+

fs/gfs2/recovery.h

@@ -0,0 +1,36 @@
+/*
+ * 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 __RECOVERY_DOT_H__
+#define __RECOVERY_DOT_H__
+
+#include "incore.h"
+
+extern struct workqueue_struct *gfs_recovery_wq;
+
+static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk)
+{
+	if (++*blk == sdp->sd_jdesc->jd_blocks)
+	        *blk = 0;
+}
+
+extern int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
+			   struct buffer_head **bh);
+
+extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where);
+extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where);
+extern void gfs2_revoke_clean(struct gfs2_jdesc *jd);
+
+extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
+		    struct gfs2_log_header_host *head);
+extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait);
+extern void gfs2_recover_func(struct work_struct *work);
+
+#endif /* __RECOVERY_DOT_H__ */
+

fs/gfs2/rgrp.h

@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 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 __RGRP_DOT_H__
+#define __RGRP_DOT_H__
+
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+/* Since each block in the file system is represented by two bits in the
+ * bitmap, one 64-bit word in the bitmap will represent 32 blocks.
+ * By reserving 32 blocks at a time, we can optimize / shortcut how we search
+ * through the bitmaps by looking a word at a time.
+ */
+#define RGRP_RSRV_MINBYTES 8
+#define RGRP_RSRV_MINBLKS ((u32)(RGRP_RSRV_MINBYTES * GFS2_NBBY))
+
+struct gfs2_rgrpd;
+struct gfs2_sbd;
+struct gfs2_holder;
+
+extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
+
+extern struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk, bool exact);
+extern struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
+extern struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
+
+extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
+extern int gfs2_rindex_update(struct gfs2_sbd *sdp);
+extern void gfs2_free_clones(struct gfs2_rgrpd *rgd);
+extern int gfs2_rgrp_go_lock(struct gfs2_holder *gh);
+extern void gfs2_rgrp_go_unlock(struct gfs2_holder *gh);
+
+extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
+
+#define GFS2_AF_ORLOV 1
+extern int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *ap);
+extern void gfs2_inplace_release(struct gfs2_inode *ip);
+
+extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n,
+			     bool dinode, u64 *generation);
+
+extern int gfs2_rs_alloc(struct gfs2_inode *ip);
+extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs);
+extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount);
+extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta);
+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;
+	unsigned int rl_space;
+	struct gfs2_rgrpd **rl_rgd;
+	struct gfs2_holder *rl_ghs;
+};
+
+extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
+			   u64 block);
+extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
+extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
+extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
+extern void gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
+extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+				   struct buffer_head *bh,
+				   const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed);
+extern int gfs2_fitrim(struct file *filp, void __user *argp);
+
+/* This is how to tell if a reservation is in the rgrp tree: */
+static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs)
+{
+	return rs && !RB_EMPTY_NODE(&rs->rs_node);
+}
+
+extern void check_and_update_goal(struct gfs2_inode *ip);
+#endif /* __RGRP_DOT_H__ */

fs/gfs2/super.h

@@ -0,0 +1,57 @@
+/*
+ * 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 __SUPER_DOT_H__
+#define __SUPER_DOT_H__
+
+#include <linux/fs.h>
+#include <linux/dcache.h>
+#include "incore.h"
+
+extern void gfs2_lm_unmount(struct gfs2_sbd *sdp);
+
+static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
+{
+	unsigned int x;
+	spin_lock(&sdp->sd_jindex_spin);
+	x = sdp->sd_journals;
+	spin_unlock(&sdp->sd_jindex_spin);
+	return x;
+}
+
+extern void gfs2_jindex_free(struct gfs2_sbd *sdp);
+
+extern int gfs2_mount_args(struct gfs2_args *args, char *data);
+
+extern struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid);
+extern int gfs2_jdesc_check(struct gfs2_jdesc *jd);
+
+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);
+extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc,
+				  const void *buf);
+extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
+			  struct buffer_head *l_bh);
+extern int gfs2_statfs_sync(struct super_block *sb, int type);
+
+extern struct file_system_type gfs2_fs_type;
+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 const struct xattr_handler *gfs2_xattr_handlers[];
+
+#endif /* __SUPER_DOT_H__ */
+

fs/gfs2/sys.c

@@ -0,0 +1,711 @@
+/*
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <asm/uaccess.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/genhd.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "sys.h"
+#include "super.h"
+#include "glock.h"
+#include "quota.h"
+#include "util.h"
+#include "glops.h"
+#include "recovery.h"
+
+struct gfs2_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
+};
+
+static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->show ? a->show(sdp, buf) : 0;
+}
+
+static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->store ? a->store(sdp, buf, len) : len;
+}
+
+static const struct sysfs_ops gfs2_attr_ops = {
+	.show  = gfs2_attr_show,
+	.store = gfs2_attr_store,
+};
+
+
+static struct kset *gfs2_kset;
+
+static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u:%u\n",
+			MAJOR(sdp->sd_vfs->s_dev), MINOR(sdp->sd_vfs->s_dev));
+}
+
+static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname);
+}
+
+static int gfs2_uuid_valid(const u8 *uuid)
+{
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		if (uuid[i])
+			return 1;
+	}
+	return 0;
+}
+
+static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct super_block *s = sdp->sd_vfs;
+	const u8 *uuid = s->s_uuid;
+	buf[0] = '\0';
+	if (!gfs2_uuid_valid(uuid))
+		return 0;
+	return snprintf(buf, PAGE_SIZE, "%pUB\n", uuid);
+}
+
+static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct super_block *sb = sdp->sd_vfs;
+	int frozen = (sb->s_writers.frozen == SB_UNFROZEN) ? 0 : 1;
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", frozen);
+}
+
+static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	int error;
+	int n = simple_strtol(buf, NULL, 0);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (n) {
+	case 0:
+		error = thaw_super(sdp->sd_vfs);
+		break;
+	case 1:
+		error = freeze_super(sdp->sd_vfs);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (error) {
+		fs_warn(sdp, "freeze %d error %d", n, error);
+		return error;
+	}
+
+	return len;
+}
+
+static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
+{
+	unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags);
+	return snprintf(buf, PAGE_SIZE, "%u\n", b);
+}
+
+static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_lm_withdraw(sdp, "withdrawing from cluster at user's request\n");
+
+	return len;
+}
+
+static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf,
+				 size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_statfs_sync(sdp->sd_vfs, 0);
+	return len;
+}
+
+static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf,
+				size_t len)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (simple_strtol(buf, NULL, 0) != 1)
+		return -EINVAL;
+
+	gfs2_quota_sync(sdp->sd_vfs, 0);
+	return len;
+}
+
+static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf,
+					size_t len)
+{
+	struct kqid qid;
+	int error;
+	u32 id;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	id = simple_strtoul(buf, NULL, 0);
+
+	qid = make_kqid(current_user_ns(), USRQUOTA, id);
+	if (!qid_valid(qid))
+		return -EINVAL;
+
+	error = gfs2_quota_refresh(sdp, qid);
+	return error ? error : len;
+}
+
+static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf,
+					 size_t len)
+{
+	struct kqid qid;
+	int error;
+	u32 id;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	id = simple_strtoul(buf, NULL, 0);
+
+	qid = make_kqid(current_user_ns(), GRPQUOTA, id);
+	if (!qid_valid(qid))
+		return -EINVAL;
+
+	error = gfs2_quota_refresh(sdp, qid);
+	return error ? error : len;
+}
+
+static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	struct gfs2_glock *gl;
+	const struct gfs2_glock_operations *glops;
+	unsigned int glmode;
+	unsigned int gltype;
+	unsigned long long glnum;
+	char mode[16];
+	int rv;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum,
+		    mode);
+	if (rv != 3)
+		return -EINVAL;
+
+	if (strcmp(mode, "EX") == 0)
+		glmode = LM_ST_UNLOCKED;
+	else if ((strcmp(mode, "CW") == 0) || (strcmp(mode, "DF") == 0))
+		glmode = LM_ST_DEFERRED;
+	else if ((strcmp(mode, "PR") == 0) || (strcmp(mode, "SH") == 0))
+		glmode = LM_ST_SHARED;
+	else
+		return -EINVAL;
+
+	if (gltype > LM_TYPE_JOURNAL)
+		return -EINVAL;
+	if (gltype == LM_TYPE_NONDISK && glnum == GFS2_FREEZE_LOCK)
+		glops = &gfs2_freeze_glops;
+	else
+		glops = gfs2_glops_list[gltype];
+	if (glops == NULL)
+		return -EINVAL;
+	if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
+		fs_info(sdp, "demote interface used\n");
+	rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl);
+	if (rv)
+		return rv;
+	gfs2_glock_cb(gl, glmode);
+	gfs2_glock_put(gl);
+	return len;
+}
+
+
+#define GFS2_ATTR(name, mode, show, store) \
+static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store)
+
+GFS2_ATTR(id,                  0444, id_show,       NULL);
+GFS2_ATTR(fsname,              0444, fsname_show,   NULL);
+GFS2_ATTR(uuid,                0444, uuid_show,     NULL);
+GFS2_ATTR(freeze,              0644, freeze_show,   freeze_store);
+GFS2_ATTR(withdraw,            0644, withdraw_show, withdraw_store);
+GFS2_ATTR(statfs_sync,         0200, NULL,          statfs_sync_store);
+GFS2_ATTR(quota_sync,          0200, NULL,          quota_sync_store);
+GFS2_ATTR(quota_refresh_user,  0200, NULL,          quota_refresh_user_store);
+GFS2_ATTR(quota_refresh_group, 0200, NULL,          quota_refresh_group_store);
+GFS2_ATTR(demote_rq,           0200, NULL,	    demote_rq_store);
+
+static struct attribute *gfs2_attrs[] = {
+	&gfs2_attr_id.attr,
+	&gfs2_attr_fsname.attr,
+	&gfs2_attr_uuid.attr,
+	&gfs2_attr_freeze.attr,
+	&gfs2_attr_withdraw.attr,
+	&gfs2_attr_statfs_sync.attr,
+	&gfs2_attr_quota_sync.attr,
+	&gfs2_attr_quota_refresh_user.attr,
+	&gfs2_attr_quota_refresh_group.attr,
+	&gfs2_attr_demote_rq.attr,
+	NULL,
+};
+
+static void gfs2_sbd_release(struct kobject *kobj)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+
+	kfree(sdp);
+}
+
+static struct kobj_type gfs2_ktype = {
+	.release = gfs2_sbd_release,
+	.default_attrs = gfs2_attrs,
+	.sysfs_ops     = &gfs2_attr_ops,
+};
+
+
+/*
+ * lock_module. Originally from lock_dlm
+ */
+
+static ssize_t proto_name_show(struct gfs2_sbd *sdp, char *buf)
+{
+	const struct lm_lockops *ops = sdp->sd_lockstruct.ls_ops;
+	return sprintf(buf, "%s\n", ops->lm_proto_name);
+}
+
+static ssize_t block_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	ssize_t ret;
+	int val = 0;
+
+	if (test_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags))
+		val = 1;
+	ret = sprintf(buf, "%d\n", val);
+	return ret;
+}
+
+static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if (val == 1)
+		set_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
+	else if (val == 0) {
+		clear_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
+		smp_mb__after_atomic();
+		gfs2_glock_thaw(sdp);
+	} else {
+		ret = -EINVAL;
+	}
+	return ret;
+}
+
+static ssize_t wdack_show(struct gfs2_sbd *sdp, char *buf)
+{
+	int val = completion_done(&sdp->sd_wdack) ? 1 : 0;
+
+	return sprintf(buf, "%d\n", val);
+}
+
+static ssize_t wdack_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	ssize_t ret = len;
+	int val;
+
+	val = simple_strtol(buf, NULL, 0);
+
+	if ((val == 1) &&
+	    !strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
+		complete(&sdp->sd_wdack);
+	else
+		ret = -EINVAL;
+	return ret;
+}
+
+static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_first);
+}
+
+static ssize_t lkfirst_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	unsigned first;
+	int rv;
+
+	rv = sscanf(buf, "%u", &first);
+	if (rv != 1 || first > 1)
+		return -EINVAL;
+	rv = wait_for_completion_killable(&sdp->sd_locking_init);
+	if (rv)
+		return rv;
+	spin_lock(&sdp->sd_jindex_spin);
+	rv = -EBUSY;
+	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+		goto out;
+	rv = -EINVAL;
+	if (sdp->sd_args.ar_spectator)
+		goto out;
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		goto out;
+	sdp->sd_lockstruct.ls_first = first;
+	rv = 0;
+out:
+        spin_unlock(&sdp->sd_jindex_spin);
+        return rv ? rv : len;
+}
+
+static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", !!test_bit(DFL_FIRST_MOUNT_DONE, &ls->ls_recover_flags));
+}
+
+int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid)
+{
+	struct gfs2_jdesc *jd;
+	int rv;
+
+	/* Wait for our primary journal to be initialized */
+	wait_for_completion(&sdp->sd_journal_ready);
+
+	spin_lock(&sdp->sd_jindex_spin);
+	rv = -EBUSY;
+	if (sdp->sd_jdesc->jd_jid == jid)
+		goto out;
+	rv = -ENOENT;
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (jd->jd_jid != jid)
+			continue;
+		rv = gfs2_recover_journal(jd, false);
+		break;
+	}
+out:
+	spin_unlock(&sdp->sd_jindex_spin);
+	return rv;
+}
+
+static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+	unsigned jid;
+	int rv;
+
+	rv = sscanf(buf, "%u", &jid);
+	if (rv != 1)
+		return -EINVAL;
+
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags)) {
+		rv = -ESHUTDOWN;
+		goto out;
+	}
+
+	rv = gfs2_recover_set(sdp, jid);
+out:
+	return rv ? rv : len;
+}
+
+static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_recover_jid_done);
+}
+
+static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	return sprintf(buf, "%d\n", ls->ls_recover_jid_status);
+}
+
+static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return sprintf(buf, "%d\n", sdp->sd_lockstruct.ls_jid);
+}
+
+static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+        int jid;
+	int rv;
+
+	rv = sscanf(buf, "%d", &jid);
+	if (rv != 1)
+		return -EINVAL;
+	rv = wait_for_completion_killable(&sdp->sd_locking_init);
+	if (rv)
+		return rv;
+	spin_lock(&sdp->sd_jindex_spin);
+	rv = -EINVAL;
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		goto out;
+	rv = -EBUSY;
+	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+		goto out;
+	rv = 0;
+	if (sdp->sd_args.ar_spectator && jid > 0)
+		rv = jid = -EINVAL;
+	sdp->sd_lockstruct.ls_jid = jid;
+	clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
+out:
+	spin_unlock(&sdp->sd_jindex_spin);
+	return rv ? rv : len;
+}
+
+#define GDLM_ATTR(_name,_mode,_show,_store) \
+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, wdack_show,		wdack_store);
+GDLM_ATTR(jid,			0644, jid_show,			jid_store);
+GDLM_ATTR(first,		0644, lkfirst_show,		lkfirst_store);
+GDLM_ATTR(first_done,		0444, first_done_show,		NULL);
+GDLM_ATTR(recover,		0600, NULL,			recover_store);
+GDLM_ATTR(recover_done,		0444, recover_done_show,	NULL);
+GDLM_ATTR(recover_status,	0444, recover_status_show,	NULL);
+
+static struct attribute *lock_module_attrs[] = {
+	&gdlm_attr_proto_name.attr,
+	&gdlm_attr_block.attr,
+	&gdlm_attr_withdraw.attr,
+	&gdlm_attr_jid.attr,
+	&gdlm_attr_first.attr,
+	&gdlm_attr_first_done.attr,
+	&gdlm_attr_recover.attr,
+	&gdlm_attr_recover_done.attr,
+	&gdlm_attr_recover_status.attr,
+	NULL,
+};
+
+/*
+ * get and set struct gfs2_tune fields
+ */
+
+static ssize_t quota_scale_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%u %u\n",
+			sdp->sd_tune.gt_quota_scale_num,
+			sdp->sd_tune.gt_quota_scale_den);
+}
+
+static ssize_t quota_scale_store(struct gfs2_sbd *sdp, const char *buf,
+				 size_t len)
+{
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	unsigned int x, y;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (sscanf(buf, "%u %u", &x, &y) != 2 || !y)
+		return -EINVAL;
+
+	spin_lock(&gt->gt_spin);
+	gt->gt_quota_scale_num = x;
+	gt->gt_quota_scale_den = y;
+	spin_unlock(&gt->gt_spin);
+	return len;
+}
+
+static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field,
+			int check_zero, const char *buf, size_t len)
+{
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	unsigned int x;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	x = simple_strtoul(buf, NULL, 0);
+
+	if (check_zero && !x)
+		return -EINVAL;
+
+	spin_lock(&gt->gt_spin);
+	*field = x;
+	spin_unlock(&gt->gt_spin);
+	return len;
+}
+
+#define TUNE_ATTR_3(name, show, store)                                        \
+static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store)
+
+#define TUNE_ATTR_2(name, store)                                              \
+static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                   \
+{                                                                             \
+	return snprintf(buf, PAGE_SIZE, "%u\n", sdp->sd_tune.gt_##name);      \
+}                                                                             \
+TUNE_ATTR_3(name, name##_show, store)
+
+#define TUNE_ATTR(name, check_zero)                                           \
+static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
+{                                                                             \
+	return tune_set(sdp, &sdp->sd_tune.gt_##name, check_zero, buf, len);  \
+}                                                                             \
+TUNE_ATTR_2(name, name##_store)
+
+TUNE_ATTR(quota_warn_period, 0);
+TUNE_ATTR(quota_quantum, 0);
+TUNE_ATTR(max_readahead, 0);
+TUNE_ATTR(complain_secs, 0);
+TUNE_ATTR(statfs_slow, 0);
+TUNE_ATTR(new_files_jdata, 0);
+TUNE_ATTR(statfs_quantum, 1);
+TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);
+
+static struct attribute *tune_attrs[] = {
+	&tune_attr_quota_warn_period.attr,
+	&tune_attr_quota_quantum.attr,
+	&tune_attr_max_readahead.attr,
+	&tune_attr_complain_secs.attr,
+	&tune_attr_statfs_slow.attr,
+	&tune_attr_statfs_quantum.attr,
+	&tune_attr_quota_scale.attr,
+	&tune_attr_new_files_jdata.attr,
+	NULL,
+};
+
+static struct attribute_group tune_group = {
+	.name = "tune",
+	.attrs = tune_attrs,
+};
+
+static struct attribute_group lock_module_group = {
+	.name = "lock_module",
+	.attrs = lock_module_attrs,
+};
+
+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 };
+	int sysfs_frees_sdp = 0;
+
+	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,
+				     "%s", sdp->sd_table_name);
+	if (error)
+		goto fail_reg;
+
+	sysfs_frees_sdp = 1; /* Freeing sdp is now done by sysfs calling
+				function gfs2_sbd_release. */
+	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
+	if (error)
+		goto fail_reg;
+
+	error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group);
+	if (error)
+		goto fail_tune;
+
+	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:
+	free_percpu(sdp->sd_lkstats);
+	fs_err(sdp, "error %d adding sysfs files", error);
+	if (sysfs_frees_sdp)
+		kobject_put(&sdp->sd_kobj);
+	else
+		kfree(sdp);
+	sb->s_fs_info = NULL;
+	return error;
+}
+
+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)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct super_block *s = sdp->sd_vfs;
+	const u8 *uuid = s->s_uuid;
+
+	add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
+	add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
+	if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
+		add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid);
+	if (gfs2_uuid_valid(uuid))
+		add_uevent_var(env, "UUID=%pUB", uuid);
+	return 0;
+}
+
+static const 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);
+	if (!gfs2_kset)
+		return -ENOMEM;
+	return 0;
+}
+
+void gfs2_sys_uninit(void)
+{
+	kset_unregister(gfs2_kset);
+}
+

fs/gfs2/sys.h

@@ -0,0 +1,25 @@
+/*
+ * 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 __SYS_DOT_H__
+#define __SYS_DOT_H__
+
+#include <linux/spinlock.h>
+struct gfs2_sbd;
+
+int gfs2_sys_fs_add(struct gfs2_sbd *sdp);
+void gfs2_sys_fs_del(struct gfs2_sbd *sdp);
+
+int gfs2_sys_init(void);
+void gfs2_sys_uninit(void);
+
+int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid);
+
+#endif /* __SYS_DOT_H__ */
+

fs/gfs2/trace_gfs2.h

@@ -0,0 +1,558 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM gfs2
+
+#if !defined(_TRACE_GFS2_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_GFS2_H
+
+#include <linux/tracepoint.h>
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/dlmconstants.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/writeback.h>
+#include <linux/ktime.h>
+#include "incore.h"
+#include "glock.h"
+#include "rgrp.h"
+
+#define dlm_state_name(nn) { DLM_LOCK_##nn, #nn }
+#define glock_trace_name(x) __print_symbolic(x,		\
+			    dlm_state_name(IV),		\
+			    dlm_state_name(NL),		\
+			    dlm_state_name(CR),		\
+			    dlm_state_name(CW),		\
+			    dlm_state_name(PR),		\
+			    dlm_state_name(PW),		\
+			    dlm_state_name(EX))
+
+#define block_state_name(x) __print_symbolic(x,			\
+			    { GFS2_BLKST_FREE, "free" },	\
+			    { GFS2_BLKST_USED, "used" },	\
+			    { GFS2_BLKST_DINODE, "dinode" },	\
+			    { GFS2_BLKST_UNLINKED, "unlinked" })
+
+#define TRACE_RS_DELETE  0
+#define TRACE_RS_TREEDEL 1
+#define TRACE_RS_INSERT  2
+#define TRACE_RS_CLAIM   3
+
+#define rs_func_name(x) __print_symbolic(x,	\
+					 { 0, "del " },	\
+					 { 1, "tdel" },	\
+					 { 2, "ins " },	\
+					 { 3, "clm " })
+
+#define show_glock_flags(flags) __print_flags(flags, "",	\
+	{(1UL << GLF_LOCK),			"l" },		\
+	{(1UL << GLF_DEMOTE),			"D" },		\
+	{(1UL << GLF_PENDING_DEMOTE),		"d" },		\
+	{(1UL << GLF_DEMOTE_IN_PROGRESS),	"p" },		\
+	{(1UL << GLF_DIRTY),			"y" },		\
+	{(1UL << GLF_LFLUSH),			"f" },		\
+	{(1UL << GLF_INVALIDATE_IN_PROGRESS),	"i" },		\
+	{(1UL << GLF_REPLY_PENDING),		"r" },		\
+	{(1UL << GLF_INITIAL),			"I" },		\
+	{(1UL << GLF_FROZEN),			"F" },		\
+	{(1UL << GLF_QUEUED),			"q" },		\
+	{(1UL << GLF_LRU),			"L" },		\
+	{(1UL << GLF_OBJECT),			"o" },		\
+	{(1UL << GLF_BLOCKING),			"b" })
+
+#ifndef NUMPTY
+#define NUMPTY
+static inline u8 glock_trace_state(unsigned int state)
+{
+	switch(state) {
+	case LM_ST_SHARED:
+		return DLM_LOCK_PR;
+	case LM_ST_DEFERRED:
+		return DLM_LOCK_CW;
+	case LM_ST_EXCLUSIVE:
+		return DLM_LOCK_EX;
+	}
+	return DLM_LOCK_NL;
+}
+#endif
+
+/* Section 1 - Locking
+ *
+ * Objectives:
+ * Latency: Remote demote request to state change
+ * Latency: Local lock request to state change
+ * Latency: State change to lock grant
+ * Correctness: Ordering of local lock state vs. I/O requests
+ * Correctness: Responses to remote demote requests
+ */
+
+/* General glock state change (DLM lock request completes) */
+TRACE_EVENT(gfs2_glock_state_change,
+
+	TP_PROTO(const struct gfs2_glock *gl, unsigned int new_state),
+
+	TP_ARGS(gl, new_state),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	u8,	cur_state		)
+		__field(	u8,	new_state		)
+		__field(	u8,	dmt_state		)
+		__field(	u8,	tgt_state		)
+		__field(	unsigned long,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum		= gl->gl_name.ln_number;
+		__entry->gltype		= gl->gl_name.ln_type;
+		__entry->cur_state	= glock_trace_state(gl->gl_state);
+		__entry->new_state	= glock_trace_state(new_state);
+		__entry->tgt_state	= glock_trace_state(gl->gl_target);
+		__entry->dmt_state	= glock_trace_state(gl->gl_demote_state);
+		__entry->flags		= gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+	),
+
+	TP_printk("%u,%u glock %d:%lld state %s to %s tgt:%s dmt:%s flags:%s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		 (unsigned long long)__entry->glnum,
+		  glock_trace_name(__entry->cur_state),
+		  glock_trace_name(__entry->new_state),
+		  glock_trace_name(__entry->tgt_state),
+		  glock_trace_name(__entry->dmt_state),
+		  show_glock_flags(__entry->flags))
+);
+
+/* State change -> unlocked, glock is being deallocated */
+TRACE_EVENT(gfs2_glock_put,
+
+	TP_PROTO(const struct gfs2_glock *gl),
+
+	TP_ARGS(gl),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	u8,	cur_state		)
+		__field(	unsigned long,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->gltype		= gl->gl_name.ln_type;
+		__entry->glnum		= gl->gl_name.ln_number;
+		__entry->cur_state	= glock_trace_state(gl->gl_state);
+		__entry->flags		= gl->gl_flags  | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+	),
+
+	TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->gltype, (unsigned long long)__entry->glnum,
+                  glock_trace_name(__entry->cur_state),
+		  glock_trace_name(DLM_LOCK_IV),
+		  show_glock_flags(__entry->flags))
+
+);
+
+/* Callback (local or remote) requesting lock demotion */
+TRACE_EVENT(gfs2_demote_rq,
+
+	TP_PROTO(const struct gfs2_glock *gl, bool remote),
+
+	TP_ARGS(gl, remote),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	u8,	cur_state		)
+		__field(	u8,	dmt_state		)
+		__field(	unsigned long,	flags		)
+		__field(	bool,	remote			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->gltype		= gl->gl_name.ln_type;
+		__entry->glnum		= gl->gl_name.ln_number;
+		__entry->cur_state	= glock_trace_state(gl->gl_state);
+		__entry->dmt_state	= glock_trace_state(gl->gl_demote_state);
+		__entry->flags		= gl->gl_flags  | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+		__entry->remote		= remote;
+	),
+
+	TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+                  glock_trace_name(__entry->cur_state),
+                  glock_trace_name(__entry->dmt_state),
+		  show_glock_flags(__entry->flags),
+		  __entry->remote ? "remote" : "local")
+
+);
+
+/* Promotion/grant of a glock */
+TRACE_EVENT(gfs2_promote,
+
+	TP_PROTO(const struct gfs2_holder *gh, int first),
+
+	TP_ARGS(gh, first),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	int,	first			)
+		__field(	u8,	state			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum	= gh->gh_gl->gl_name.ln_number;
+		__entry->gltype	= gh->gh_gl->gl_name.ln_type;
+		__entry->first	= first;
+		__entry->state	= glock_trace_state(gh->gh_state);
+	),
+
+	TP_printk("%u,%u glock %u:%llu promote %s %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+		  __entry->first ? "first": "other",
+		  glock_trace_name(__entry->state))
+);
+
+/* Queue/dequeue a lock request */
+TRACE_EVENT(gfs2_glock_queue,
+
+	TP_PROTO(const struct gfs2_holder *gh, int queue),
+
+	TP_ARGS(gh, queue),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	glnum			)
+		__field(	u32,	gltype			)
+		__field(	int,	queue			)
+		__field(	u8,	state			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum	= gh->gh_gl->gl_name.ln_number;
+		__entry->gltype	= gh->gh_gl->gl_name.ln_type;
+		__entry->queue	= queue;
+		__entry->state	= glock_trace_state(gh->gh_state);
+	),
+
+	TP_printk("%u,%u glock %u:%llu %squeue %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+		  __entry->queue ? "" : "de",
+		  glock_trace_name(__entry->state))
+);
+
+/* DLM sends a reply to GFS2 */
+TRACE_EVENT(gfs2_glock_lock_time,
+
+	TP_PROTO(const struct gfs2_glock *gl, s64 tdiff),
+
+	TP_ARGS(gl, tdiff),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev		)
+		__field(	u64,	glnum		)
+		__field(	u32,	gltype		)
+		__field(	int,	status		)
+		__field(	char,	flags		)
+		__field(	s64,	tdiff		)
+		__field(	s64,	srtt		)
+		__field(	s64,	srttvar		)
+		__field(	s64,	srttb		)
+		__field(	s64,	srttvarb	)
+		__field(	s64,	sirt		)
+		__field(	s64,	sirtvar		)
+		__field(	s64,	dcount		)
+		__field(	s64,	qcount		)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = gl->gl_sbd->sd_vfs->s_dev;
+		__entry->glnum          = gl->gl_name.ln_number;
+		__entry->gltype         = gl->gl_name.ln_type;
+		__entry->status		= gl->gl_lksb.sb_status;
+		__entry->flags		= gl->gl_lksb.sb_flags;
+		__entry->tdiff		= tdiff;
+		__entry->srtt		= gl->gl_stats.stats[GFS2_LKS_SRTT];
+		__entry->srttvar	= gl->gl_stats.stats[GFS2_LKS_SRTTVAR];
+		__entry->srttb		= gl->gl_stats.stats[GFS2_LKS_SRTTB];
+		__entry->srttvarb	= gl->gl_stats.stats[GFS2_LKS_SRTTVARB];
+		__entry->sirt		= gl->gl_stats.stats[GFS2_LKS_SIRT];
+		__entry->sirtvar	= gl->gl_stats.stats[GFS2_LKS_SIRTVAR];
+		__entry->dcount		= gl->gl_stats.stats[GFS2_LKS_DCOUNT];
+		__entry->qcount		= gl->gl_stats.stats[GFS2_LKS_QCOUNT];
+	),
+
+	TP_printk("%u,%u glock %d:%lld status:%d flags:%02x tdiff:%lld srtt:%lld/%lld srttb:%lld/%lld sirt:%lld/%lld dcnt:%lld qcnt:%lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
+		  (unsigned long long)__entry->glnum,
+		  __entry->status, __entry->flags,
+		  (long long)__entry->tdiff,
+		  (long long)__entry->srtt,
+		  (long long)__entry->srttvar,
+		  (long long)__entry->srttb,
+		  (long long)__entry->srttvarb,
+		  (long long)__entry->sirt,
+		  (long long)__entry->sirtvar,
+		  (long long)__entry->dcount,
+		  (long long)__entry->qcount)
+);
+
+/* Section 2 - Log/journal
+ *
+ * Objectives:
+ * Latency: Log flush time
+ * Correctness: pin/unpin vs. disk I/O ordering
+ * Performance: Log usage stats
+ */
+
+/* Pin/unpin a block in the log */
+TRACE_EVENT(gfs2_pin,
+
+	TP_PROTO(const struct gfs2_bufdata *bd, int pin),
+
+	TP_ARGS(bd, pin),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	int,	pin			)
+		__field(	u32,	len			)
+		__field(	sector_t,	block		)
+		__field(	u64,	ino			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bd->bd_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->pin		= pin;
+		__entry->len		= bd->bd_bh->b_size;
+		__entry->block		= bd->bd_bh->b_blocknr;
+		__entry->ino		= bd->bd_gl->gl_name.ln_number;
+	),
+
+	TP_printk("%u,%u log %s %llu/%lu inode %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->pin ? "pin" : "unpin",
+		  (unsigned long long)__entry->block,
+		  (unsigned long)__entry->len,
+		  (unsigned long long)__entry->ino)
+);
+
+/* Flushing the log */
+TRACE_EVENT(gfs2_log_flush,
+
+	TP_PROTO(const struct gfs2_sbd *sdp, int start),
+
+	TP_ARGS(sdp, start),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	int,	start			)
+		__field(	u64,	log_seq			)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = sdp->sd_vfs->s_dev;
+		__entry->start		= start;
+		__entry->log_seq	= sdp->sd_log_sequence;
+	),
+
+	TP_printk("%u,%u log flush %s %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->start ? "start" : "end",
+		  (unsigned long long)__entry->log_seq)
+);
+
+/* Reserving/releasing blocks in the log */
+TRACE_EVENT(gfs2_log_blocks,
+
+	TP_PROTO(const struct gfs2_sbd *sdp, int blocks),
+
+	TP_ARGS(sdp, blocks),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	int,	blocks			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sdp->sd_vfs->s_dev;
+		__entry->blocks		= blocks;
+	),
+
+	TP_printk("%u,%u log reserve %d", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), __entry->blocks)
+);
+
+/* Writing back the AIL */
+TRACE_EVENT(gfs2_ail_flush,
+
+	TP_PROTO(const struct gfs2_sbd *sdp, const struct writeback_control *wbc, int start),
+
+	TP_ARGS(sdp, wbc, start),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	int, start			)
+		__field(	int, sync_mode			)
+		__field(	long, nr_to_write		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sdp->sd_vfs->s_dev;
+		__entry->start		= start;
+		__entry->sync_mode	= wbc->sync_mode;
+		__entry->nr_to_write	= wbc->nr_to_write;
+	),
+
+	TP_printk("%u,%u ail flush %s %s %ld", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), __entry->start ? "start" : "end",
+		  __entry->sync_mode == WB_SYNC_ALL ? "all" : "none",
+		  __entry->nr_to_write)
+);
+
+/* Section 3 - bmap
+ *
+ * Objectives:
+ * Latency: Bmap request time
+ * Performance: Block allocator tracing
+ * Correctness: Test of disard generation vs. blocks allocated
+ */
+
+/* Map an extent of blocks, possibly a new allocation */
+TRACE_EVENT(gfs2_bmap,
+
+	TP_PROTO(const struct gfs2_inode *ip, const struct buffer_head *bh,
+		sector_t lblock, int create, int errno),
+
+	TP_ARGS(ip, bh, lblock, create, errno),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	sector_t, lblock		)
+		__field(	sector_t, pblock		)
+		__field(	u64,	inum			)
+		__field(	unsigned long, state		)
+		__field(	u32,	len			)
+		__field(	int,	create			)
+		__field(	int,	errno			)
+	),
+
+	TP_fast_assign(
+		__entry->dev            = ip->i_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->lblock		= lblock;
+		__entry->pblock		= buffer_mapped(bh) ?  bh->b_blocknr : 0;
+		__entry->inum		= ip->i_no_addr;
+		__entry->state		= bh->b_state;
+		__entry->len		= bh->b_size;
+		__entry->create		= create;
+		__entry->errno		= errno;
+	),
+
+	TP_printk("%u,%u bmap %llu map %llu/%lu to %llu flags:%08lx %s %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->lblock,
+		  (unsigned long)__entry->len,
+		  (unsigned long long)__entry->pblock,
+		  __entry->state, __entry->create ? "create " : "nocreate",
+		  __entry->errno)
+);
+
+/* Keep track of blocks as they are allocated/freed */
+TRACE_EVENT(gfs2_block_alloc,
+
+	TP_PROTO(const struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
+		 u64 block, unsigned len, u8 block_state),
+
+	TP_ARGS(ip, rgd, block, len, block_state),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	start			)
+		__field(	u64,	inum			)
+		__field(	u32,	len			)
+		__field(	u8,	block_state		)
+		__field(        u64,	rd_addr			)
+		__field(        u32,	rd_free_clone		)
+		__field(	u32,	rd_reserved		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= rgd->rd_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->start		= block;
+		__entry->inum		= ip->i_no_addr;
+		__entry->len		= len;
+		__entry->block_state	= block_state;
+		__entry->rd_addr	= rgd->rd_addr;
+		__entry->rd_free_clone	= rgd->rd_free_clone;
+		__entry->rd_reserved	= rgd->rd_reserved;
+	),
+
+	TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u rr:%lu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->start,
+		  (unsigned long)__entry->len,
+		  block_state_name(__entry->block_state),
+		  (unsigned long long)__entry->rd_addr,
+		  __entry->rd_free_clone, (unsigned long)__entry->rd_reserved)
+);
+
+/* Keep track of multi-block reservations as they are allocated/freed */
+TRACE_EVENT(gfs2_rs,
+
+	TP_PROTO(const struct gfs2_blkreserv *rs, u8 func),
+
+	TP_ARGS(rs, func),
+
+	TP_STRUCT__entry(
+		__field(        dev_t,  dev                     )
+		__field(	u64,	rd_addr			)
+		__field(	u32,	rd_free_clone		)
+		__field(	u32,	rd_reserved		)
+		__field(	u64,	inum			)
+		__field(	u64,	start			)
+		__field(	u32,	free			)
+		__field(	u8,	func			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= rs->rs_rbm.rgd->rd_sbd->sd_vfs->s_dev;
+		__entry->rd_addr	= rs->rs_rbm.rgd->rd_addr;
+		__entry->rd_free_clone	= rs->rs_rbm.rgd->rd_free_clone;
+		__entry->rd_reserved	= rs->rs_rbm.rgd->rd_reserved;
+		__entry->inum		= rs->rs_inum;
+		__entry->start		= gfs2_rbm_to_block(&rs->rs_rbm);
+		__entry->free		= rs->rs_free;
+		__entry->func		= func;
+	),
+
+	TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s f:%lu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long long)__entry->inum,
+		  (unsigned long long)__entry->start,
+		  (unsigned long long)__entry->rd_addr,
+		  (unsigned long)__entry->rd_free_clone,
+		  (unsigned long)__entry->rd_reserved,
+		  rs_func_name(__entry->func), (unsigned long)__entry->free)
+);
+
+#endif /* _TRACE_GFS2_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_gfs2
+#include <trace/define_trace.h>
+

fs/gfs2/trans.c

@@ -0,0 +1,270 @@
+/*
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/kallsyms.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "inode.h"
+#include "log.h"
+#include "lops.h"
+#include "meta_io.h"
+#include "trans.h"
+#include "util.h"
+#include "trace_gfs2.h"
+
+int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+		     unsigned int revokes)
+{
+	struct gfs2_trans *tr;
+	int error;
+
+	BUG_ON(current->journal_info);
+	BUG_ON(blocks == 0 && revokes == 0);
+
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+		return -EROFS;
+
+	tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
+	if (!tr)
+		return -ENOMEM;
+
+	tr->tr_ip = _RET_IP_;
+	tr->tr_blocks = blocks;
+	tr->tr_revokes = revokes;
+	tr->tr_reserved = 1;
+	tr->tr_alloced = 1;
+	if (blocks)
+		tr->tr_reserved += 6 + blocks;
+	if (revokes)
+		tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
+						   sizeof(u64));
+	INIT_LIST_HEAD(&tr->tr_databuf);
+	INIT_LIST_HEAD(&tr->tr_buf);
+
+	sb_start_intwrite(sdp->sd_vfs);
+
+	error = gfs2_log_reserve(sdp, tr->tr_reserved);
+	if (error)
+		goto fail;
+
+	current->journal_info = tr;
+
+	return 0;
+
+fail:
+	sb_end_intwrite(sdp->sd_vfs);
+	kfree(tr);
+
+	return error;
+}
+
+static void gfs2_print_trans(const struct gfs2_trans *tr)
+{
+	pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
+	pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n",
+		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
+	pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
+		tr->tr_num_buf_new, tr->tr_num_buf_rm,
+		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
+		tr->tr_num_revoke, tr->tr_num_revoke_rm);
+}
+
+void gfs2_trans_end(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr = current->journal_info;
+	s64 nbuf;
+	BUG_ON(!tr);
+	current->journal_info = NULL;
+
+	if (!tr->tr_touched) {
+		gfs2_log_release(sdp, tr->tr_reserved);
+		if (tr->tr_alloced)
+			kfree(tr);
+		sb_end_intwrite(sdp->sd_vfs);
+		return;
+	}
+
+	nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new;
+	nbuf -= tr->tr_num_buf_rm;
+	nbuf -= tr->tr_num_databuf_rm;
+
+	if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) &&
+				       (tr->tr_num_revoke <= tr->tr_revokes)))
+		gfs2_print_trans(tr);
+
+	gfs2_log_commit(sdp, tr);
+	if (tr->tr_alloced && !tr->tr_attached)
+			kfree(tr);
+	up_read(&sdp->sd_log_flush_lock);
+
+	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
+		gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+	sb_end_intwrite(sdp->sd_vfs);
+}
+
+static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
+					       struct buffer_head *bh,
+					       const struct gfs2_log_operations *lops)
+{
+	struct gfs2_bufdata *bd;
+
+	bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
+	bd->bd_bh = bh;
+	bd->bd_gl = gl;
+	bd->bd_ops = lops;
+	INIT_LIST_HEAD(&bd->bd_list);
+	bh->b_private = bd;
+	return bd;
+}
+
+/**
+ * gfs2_trans_add_data - Add a databuf to the transaction.
+ * @gl: The inode glock associated with the buffer
+ * @bh: The buffer to add
+ *
+ * This is used in two distinct cases:
+ * i) In ordered write mode
+ *    We put the data buffer on a list so that we can ensure that its
+ *    synced to disk at the right time
+ * ii) In journaled data mode
+ *    We need to journal the data block in the same way as metadata in
+ *    the functions above. The difference is that here we have a tag
+ *    which is two __be64's being the block number (as per meta data)
+ *    and a flag which says whether the data block needs escaping or
+ *    not. This means we need a new log entry for each 251 or so data
+ *    blocks, which isn't an enormous overhead but twice as much as
+ *    for normal metadata blocks.
+ */
+void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
+{
+	struct gfs2_trans *tr = current->journal_info;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct address_space *mapping = bh->b_page->mapping;
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_bufdata *bd;
+
+	if (!gfs2_is_jdata(ip)) {
+		gfs2_ordered_add_inode(ip);
+		return;
+	}
+
+	lock_buffer(bh);
+	gfs2_log_lock(sdp);
+	bd = bh->b_private;
+	if (bd == NULL) {
+		gfs2_log_unlock(sdp);
+		unlock_buffer(bh);
+		if (bh->b_private == NULL)
+			bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops);
+		lock_buffer(bh);
+		gfs2_log_lock(sdp);
+	}
+	gfs2_assert(sdp, bd->bd_gl == gl);
+	tr->tr_touched = 1;
+	if (list_empty(&bd->bd_list)) {
+		set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+		set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+		gfs2_pin(sdp, bd->bd_bh);
+		tr->tr_num_databuf_new++;
+		list_add_tail(&bd->bd_list, &tr->tr_databuf);
+	}
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bh);
+}
+
+static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
+{
+	struct gfs2_meta_header *mh;
+	struct gfs2_trans *tr;
+
+	tr = current->journal_info;
+	tr->tr_touched = 1;
+	if (!list_empty(&bd->bd_list))
+		return;
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
+	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
+		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
+		       (unsigned long long)bd->bd_bh->b_blocknr);
+		BUG();
+	}
+	gfs2_pin(sdp, bd->bd_bh);
+	mh->__pad0 = cpu_to_be64(0);
+	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	list_add(&bd->bd_list, &tr->tr_buf);
+	tr->tr_num_buf_new++;
+}
+
+void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
+{
+
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_bufdata *bd;
+
+	lock_buffer(bh);
+	gfs2_log_lock(sdp);
+	bd = bh->b_private;
+	if (bd == NULL) {
+		gfs2_log_unlock(sdp);
+		unlock_buffer(bh);
+		lock_page(bh->b_page);
+		if (bh->b_private == NULL)
+			bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops);
+		unlock_page(bh->b_page);
+		lock_buffer(bh);
+		gfs2_log_lock(sdp);
+	}
+	gfs2_assert(sdp, bd->bd_gl == gl);
+	meta_lo_add(sdp, bd);
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bh);
+}
+
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
+{
+	struct gfs2_trans *tr = current->journal_info;
+
+	BUG_ON(!list_empty(&bd->bd_list));
+	gfs2_add_revoke(sdp, bd);
+	tr->tr_touched = 1;
+	tr->tr_num_revoke++;
+}
+
+void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
+{
+	struct gfs2_bufdata *bd, *tmp;
+	struct gfs2_trans *tr = current->journal_info;
+	unsigned int n = len;
+
+	gfs2_log_lock(sdp);
+	list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_list) {
+		if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) {
+			list_del_init(&bd->bd_list);
+			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
+			sdp->sd_log_num_revoke--;
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
+			tr->tr_num_revoke_rm++;
+			if (--n == 0)
+				break;
+		}
+	}
+	gfs2_log_unlock(sdp);
+}
+

fs/gfs2/trans.h

@@ -0,0 +1,47 @@
+/*
+ * 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 __TRANS_DOT_H__
+#define __TRANS_DOT_H__
+
+#include <linux/buffer_head.h>
+struct gfs2_sbd;
+struct gfs2_rgrpd;
+struct gfs2_glock;
+
+#define RES_DINODE	1
+#define RES_INDIRECT	1
+#define RES_JDATA	1
+#define RES_DATA	1
+#define RES_LEAF	1
+#define RES_RG_HDR	1
+#define RES_RG_BIT	2
+#define RES_EATTR	1
+#define RES_STATFS	1
+#define RES_QUOTA	2
+
+/* reserve either the number of blocks to be allocated plus the rg header
+ * block, or all of the blocks in the rg, whichever is smaller */
+static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip, unsigned requested)
+{
+	if (requested < ip->i_rgd->rd_length)
+		return requested + 1;
+	return ip->i_rgd->rd_length;
+}
+
+extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+			    unsigned int revokes);
+
+extern void gfs2_trans_end(struct gfs2_sbd *sdp);
+extern void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh);
+extern void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh);
+extern void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+extern void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
+
+#endif /* __TRANS_DOT_H__ */

fs/gfs2/util.c

@@ -0,0 +1,265 @@
+/*
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/crc32.h>
+#include <linux/gfs2_ondisk.h>
+#include <asm/uaccess.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "glock.h"
+#include "util.h"
+
+struct kmem_cache *gfs2_glock_cachep __read_mostly;
+struct kmem_cache *gfs2_glock_aspace_cachep __read_mostly;
+struct kmem_cache *gfs2_inode_cachep __read_mostly;
+struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
+struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
+struct kmem_cache *gfs2_quotad_cachep __read_mostly;
+struct kmem_cache *gfs2_rsrv_cachep __read_mostly;
+mempool_t *gfs2_page_pool __read_mostly;
+
+void gfs2_assert_i(struct gfs2_sbd *sdp)
+{
+	fs_emerg(sdp, "fatal assertion failed\n");
+}
+
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
+{
+	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	const struct lm_lockops *lm = ls->ls_ops;
+	va_list args;
+	struct va_format vaf;
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
+	    test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return 0;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	fs_err(sdp, "%pV", &vaf);
+
+	va_end(args);
+
+	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);
+
+		if (!strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
+			wait_for_completion(&sdp->sd_wdack);
+
+		if (lm->lm_unmount) {
+			fs_err(sdp, "telling LM to unmount\n");
+			lm->lm_unmount(sdp);
+		}
+		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;
+}
+
+/**
+ * gfs2_assert_withdraw_i - Cause the machine to withdraw if @assertion is false
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
+			   const char *function, char *file, unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+			      "fatal: assertion \"%s\" failed\n"
+			      "   function = %s, file = %s, line = %u\n",
+			      assertion, function, file, line);
+	dump_stack();
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_assert_warn_i - Print a message to the console if @assertion is false
+ * Returns: -1 if we printed something
+ *          -2 if we didn't
+ */
+
+int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
+		       const char *function, char *file, unsigned int line)
+{
+	if (time_before(jiffies,
+			sdp->sd_last_warning +
+			gfs2_tune_get(sdp, gt_complain_secs) * HZ))
+		return -2;
+
+	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW)
+		fs_warn(sdp, "warning: assertion \"%s\" failed at function = %s, file = %s, line = %u\n",
+			assertion, 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;
+}
+
+/**
+ * gfs2_consist_i - Flag a filesystem consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide, const char *function,
+		   char *file, unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+			      "fatal: filesystem consistency error - function = %s, file = %s, line = %u\n",
+			      function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_consist_inode_i - Flag an inode consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
+			 const char *function, char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+			      "fatal: filesystem consistency error\n"
+			      "  inode = %llu %llu\n"
+			      "  function = %s, file = %s, line = %u\n",
+			      (unsigned long long)ip->i_no_formal_ino,
+			      (unsigned long long)ip->i_no_addr,
+			      function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_consist_rgrpd_i - Flag a RG consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
+			 const char *function, char *file, unsigned int line)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+			      "fatal: filesystem consistency error\n"
+			      "  RG = %llu\n"
+			      "  function = %s, file = %s, line = %u\n",
+			      (unsigned long long)rgd->rd_addr,
+			      function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_meta_check_ii - Flag a magic number consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *type, const char *function, char *file,
+		       unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+			      "fatal: invalid metadata block\n"
+			      "  bh = %llu (%s)\n"
+			      "  function = %s, file = %s, line = %u\n",
+			      (unsigned long long)bh->b_blocknr, type,
+			      function, file, line);
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_metatype_check_ii - Flag a metadata type consistency error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          -2 if it was already withdrawn
+ */
+
+int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			   u16 type, u16 t, const char *function,
+			   char *file, unsigned int line)
+{
+	int me;
+	me = gfs2_lm_withdraw(sdp,
+			      "fatal: invalid metadata block\n"
+			      "  bh = %llu (type: exp=%u, found=%u)\n"
+			      "  function = %s, file = %s, line = %u\n",
+			      (unsigned long long)bh->b_blocknr, type, t,
+			      function, file, line);
+	return (me) ? -1 : -2;
+}
+
+/**
+ * gfs2_io_error_i - Flag an I/O error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
+		    unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+			      "fatal: I/O error\n"
+			      "  function = %s, file = %s, line = %u\n",
+			      function, file, line);
+	return rv;
+}
+
+/**
+ * gfs2_io_error_bh_i - Flag a buffer I/O error and withdraw
+ * Returns: -1 if this call withdrew the machine,
+ *          0 if it was already withdrawn
+ */
+
+int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *function, char *file, unsigned int line)
+{
+	int rv;
+	rv = gfs2_lm_withdraw(sdp,
+			      "fatal: I/O error\n"
+			      "  block = %llu\n"
+			      "  function = %s, file = %s, line = %u\n",
+			      (unsigned long long)bh->b_blocknr,
+			      function, file, line);
+	return rv;
+}
+

fs/gfs2/util.h

@@ -0,0 +1,171 @@
+/*
+ * 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 __UTIL_DOT_H__
+#define __UTIL_DOT_H__
+
+#ifdef pr_fmt
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#endif
+
+#include <linux/mempool.h>
+
+#include "incore.h"
+
+#define fs_emerg(fs, fmt, ...)						\
+	pr_emerg("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+#define fs_warn(fs, fmt, ...)						\
+	pr_warn("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+#define fs_err(fs, fmt, ...)						\
+	pr_err("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+#define fs_info(fs, fmt, ...)						\
+	pr_info("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__)
+
+void gfs2_assert_i(struct gfs2_sbd *sdp);
+
+#define gfs2_assert(sdp, assertion) \
+do { \
+	if (unlikely(!(assertion))) { \
+		gfs2_assert_i(sdp); \
+		BUG(); \
+        } \
+} while (0)
+
+
+int gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion,
+			   const char *function, char *file, unsigned int line);
+
+#define gfs2_assert_withdraw(sdp, assertion) \
+((likely(assertion)) ? 0 : gfs2_assert_withdraw_i((sdp), #assertion, \
+					__func__, __FILE__, __LINE__))
+
+
+int gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion,
+		       const char *function, char *file, unsigned int line);
+
+#define gfs2_assert_warn(sdp, assertion) \
+((likely(assertion)) ? 0 : gfs2_assert_warn_i((sdp), #assertion, \
+					__func__, __FILE__, __LINE__))
+
+
+int gfs2_consist_i(struct gfs2_sbd *sdp, int cluster_wide,
+		   const char *function, char *file, unsigned int line);
+
+#define gfs2_consist(sdp) \
+gfs2_consist_i((sdp), 0, __func__, __FILE__, __LINE__)
+
+
+int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide,
+			 const char *function, char *file, unsigned int line);
+
+#define gfs2_consist_inode(ip) \
+gfs2_consist_inode_i((ip), 0, __func__, __FILE__, __LINE__)
+
+
+int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide,
+			 const char *function, char *file, unsigned int line);
+
+#define gfs2_consist_rgrpd(rgd) \
+gfs2_consist_rgrpd_i((rgd), 0, __func__, __FILE__, __LINE__)
+
+
+int gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *type, const char *function,
+		       char *file, unsigned int line);
+
+static inline int gfs2_meta_check(struct gfs2_sbd *sdp,
+				    struct buffer_head *bh)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+	u32 magic = be32_to_cpu(mh->mh_magic);
+	if (unlikely(magic != GFS2_MAGIC)) {
+		pr_err("Magic number missing at %llu\n",
+		       (unsigned long long)bh->b_blocknr);
+		return -EIO;
+	}
+	return 0;
+}
+
+int gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			   u16 type, u16 t,
+			   const char *function,
+			   char *file, unsigned int line);
+
+static inline int gfs2_metatype_check_i(struct gfs2_sbd *sdp,
+					struct buffer_head *bh,
+					u16 type,
+					const char *function,
+					char *file, unsigned int line)
+{
+	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
+	u32 magic = be32_to_cpu(mh->mh_magic);
+	u16 t = be32_to_cpu(mh->mh_type);
+	if (unlikely(magic != GFS2_MAGIC))
+		return gfs2_meta_check_ii(sdp, bh, "magic number", function,
+					  file, line);
+        if (unlikely(t != type))
+		return gfs2_metatype_check_ii(sdp, bh, type, t, function,
+					      file, line);
+	return 0;
+}
+
+#define gfs2_metatype_check(sdp, bh, type) \
+gfs2_metatype_check_i((sdp), (bh), (type), __func__, __FILE__, __LINE__)
+
+static inline void gfs2_metatype_set(struct buffer_head *bh, u16 type,
+				     u16 format)
+{
+	struct gfs2_meta_header *mh;
+	mh = (struct gfs2_meta_header *)bh->b_data;
+	mh->mh_type = cpu_to_be32(type);
+	mh->mh_format = cpu_to_be32(format);
+}
+
+
+int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
+		    char *file, unsigned int line);
+
+#define gfs2_io_error(sdp) \
+gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__);
+
+
+int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       const char *function, char *file, unsigned int line);
+
+#define gfs2_io_error_bh(sdp, bh) \
+gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__);
+
+
+extern struct kmem_cache *gfs2_glock_cachep;
+extern struct kmem_cache *gfs2_glock_aspace_cachep;
+extern struct kmem_cache *gfs2_inode_cachep;
+extern struct kmem_cache *gfs2_bufdata_cachep;
+extern struct kmem_cache *gfs2_rgrpd_cachep;
+extern struct kmem_cache *gfs2_quotad_cachep;
+extern struct kmem_cache *gfs2_rsrv_cachep;
+extern mempool_t *gfs2_page_pool;
+
+static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
+					   unsigned int *p)
+{
+	unsigned int x;
+	spin_lock(&gt->gt_spin);
+	x = *p;
+	spin_unlock(&gt->gt_spin);
+	return x;
+}
+
+#define gfs2_tune_get(sdp, field) \
+gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
+
+__printf(2, 3)
+int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...);
+
+#endif /* __UTIL_DOT_H__ */

fs/gfs2/xattr.h

@@ -0,0 +1,67 @@
+/*
+ * 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 __EATTR_DOT_H__
+#define __EATTR_DOT_H__
+
+struct gfs2_inode;
+struct iattr;
+
+#define GFS2_EA_REC_LEN(ea) be32_to_cpu((ea)->ea_rec_len)
+#define GFS2_EA_DATA_LEN(ea) be32_to_cpu((ea)->ea_data_len)
+
+#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)
+
+#define GFS2_EA_IS_STUFFED(ea) (!(ea)->ea_num_ptrs)
+#define GFS2_EA_IS_LAST(ea) ((ea)->ea_flags & GFS2_EAFLAG_LAST)
+
+#define GFS2_EAREQ_SIZE_STUFFED(er) \
+ALIGN(sizeof(struct gfs2_ea_header) + (er)->er_name_len + (er)->er_data_len, 8)
+
+#define GFS2_EA2NAME(ea) ((char *)((struct gfs2_ea_header *)(ea) + 1))
+#define GFS2_EA2DATA(ea) (GFS2_EA2NAME(ea) + (ea)->ea_name_len)
+
+#define GFS2_EA2DATAPTRS(ea) \
+((__be64 *)(GFS2_EA2NAME(ea) + ALIGN((ea)->ea_name_len, 8)))
+
+#define GFS2_EA2NEXT(ea) \
+((struct gfs2_ea_header *)((char *)(ea) + GFS2_EA_REC_LEN(ea)))
+
+#define GFS2_EA_BH2FIRST(bh) \
+((struct gfs2_ea_header *)((bh)->b_data + sizeof(struct gfs2_meta_header)))
+
+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_... */
+};
+
+struct gfs2_ea_location {
+	struct buffer_head *el_bh;
+	struct gfs2_ea_header *el_ea;
+	struct gfs2_ea_header *el_prev;
+};
+
+extern int __gfs2_xattr_set(struct inode *inode, const char *name,
+			    const void *value, size_t size,
+			    int flags, int type);
+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 */
+
+extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data);
+extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data);
+
+#endif /* __EATTR_DOT_H__ */