Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw: (56 commits)
  [GFS2] Allow journal recovery on read-only mount
  [GFS2] Lockup on error
  [GFS2] Fix page_mkwrite truncation race path
  [GFS2] Fix typo
  [GFS2] Fix write alloc required shortcut calculation
  [GFS2] gfs2_alloc_required performance
  [GFS2] Remove unneeded i_spin
  [GFS2] Reduce inode size by moving i_alloc out of line
  [GFS2] Fix assert in log code
  [GFS2] Fix problems relating to execution of files on GFS2
  [GFS2] Initialize extent_list earlier
  [GFS2] Allow page migration for writeback and ordered pages
  [GFS2] Remove unused variable
  [GFS2] Fix log block mapper
  [GFS2] Minor correction
  [GFS2] Eliminate the no longer needed sd_statfs_mutex
  [GFS2] Incremental patch to fix compiler warning
  [GFS2] Function meta_read optimization
  [GFS2] Only fetch the dinode once in block_map
  [GFS2] Reorganize function gfs2_glmutex_lock
  ...

fs/gfs2/Makefile

@@ -2,7 +2,7 @@ obj-$(CONFIG_GFS2_FS) += gfs2.o
 gfs2-y := acl.o bmap.o daemon.o dir.o eaops.o eattr.o glock.o \
 	glops.o inode.o lm.o log.o lops.o locking.o main.o meta_io.o \
 	mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \
-	ops_fstype.o ops_inode.o ops_super.o ops_vm.o quota.o \
+	ops_fstype.o ops_inode.o ops_super.o quota.o \
 	recovery.o rgrp.o super.o sys.o trans.o util.o
 
 obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += locking/nolock/

fs/gfs2/bmap.c

@@ -59,7 +59,6 @@ struct strip_mine {
 static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 			       u64 block, struct page *page)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct inode *inode = &ip->i_inode;
 	struct buffer_head *bh;
 	int release = 0;
@@ -95,7 +94,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 	set_buffer_uptodate(bh);
 	if (!gfs2_is_jdata(ip))
 		mark_buffer_dirty(bh);
-	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
+	if (!gfs2_is_writeback(ip))
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 
 	if (release) {
@@ -453,8 +452,8 @@ static inline void bmap_unlock(struct inode *inode, int create)
  * Returns: errno
  */
 
-int gfs2_block_map(struct inode *inode, u64 lblock, int create,
-		   struct buffer_head *bh_map)
+int gfs2_block_map(struct inode *inode, sector_t lblock,
+		   struct buffer_head *bh_map, int create)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -470,6 +469,7 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create,
 	unsigned int maxlen = bh_map->b_size >> inode->i_blkbits;
 	struct metapath mp;
 	u64 size;
+	struct buffer_head *dibh = NULL;
 
 	BUG_ON(maxlen == 0);
 
@@ -500,6 +500,8 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create,
 	error = gfs2_meta_inode_buffer(ip, &bh);
 	if (error)
 		goto out_fail;
+	dibh = bh;
+	get_bh(dibh);
 
 	for (x = 0; x < end_of_metadata; x++) {
 		lookup_block(ip, bh, x, &mp, create, &new, &dblock);
@@ -518,13 +520,8 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create,
 		if (boundary)
 			set_buffer_boundary(bh_map);
 		if (new) {
-			struct buffer_head *dibh;
-			error = gfs2_meta_inode_buffer(ip, &dibh);
-			if (!error) {
-				gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-				gfs2_dinode_out(ip, dibh->b_data);
-				brelse(dibh);
-			}
+			gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+			gfs2_dinode_out(ip, dibh->b_data);
 			set_buffer_new(bh_map);
 			goto out_brelse;
 		}
@@ -545,6 +542,8 @@ out_brelse:
 out_ok:
 	error = 0;
 out_fail:
+	if (dibh)
+		brelse(dibh);
 	bmap_unlock(inode, create);
 	return error;
 }
@@ -560,7 +559,7 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi
 	BUG_ON(!new);
 
 	bh.b_size = 1 << (inode->i_blkbits + 5);
-	ret = gfs2_block_map(inode, lblock, create, &bh);
+	ret = gfs2_block_map(inode, lblock, &bh, create);
 	*extlen = bh.b_size >> inode->i_blkbits;
 	*dblock = bh.b_blocknr;
 	if (buffer_new(&bh))
@@ -684,7 +683,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (metadata)
 		revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs;
 
-	error = gfs2_rindex_hold(sdp, &ip->i_alloc.al_ri_gh);
+	error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
 	if (error)
 		return error;
 
@@ -786,7 +785,7 @@ out_rg_gunlock:
 out_rlist:
 	gfs2_rlist_free(&rlist);
 out:
-	gfs2_glock_dq_uninit(&ip->i_alloc.al_ri_gh);
+	gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
 	return error;
 }
 
@@ -879,7 +878,6 @@ static int gfs2_block_truncate_page(struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	loff_t from = inode->i_size;
 	unsigned long index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
@@ -911,7 +909,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping)
 	err = 0;
 
 	if (!buffer_mapped(bh)) {
-		gfs2_get_block(inode, iblock, bh, 0);
+		gfs2_block_map(inode, iblock, bh, 0);
 		/* unmapped? It's a hole - nothing to do */
 		if (!buffer_mapped(bh))
 			goto unlock;
@@ -931,7 +929,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping)
 		err = 0;
 	}
 
-	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
+	if (!gfs2_is_writeback(ip))
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 
 	zero_user_page(page, offset, length, KM_USER0);
@@ -1224,8 +1222,13 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
 		do_div(lblock_stop, bsize);
 	} else {
 		unsigned int shift = sdp->sd_sb.sb_bsize_shift;
+		u64 end_of_file = (ip->i_di.di_size + sdp->sd_sb.sb_bsize - 1) >> shift;
 		lblock = offset >> shift;
 		lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
+		if (lblock_stop > end_of_file) {
+			*alloc_required = 1;
+			return 0;
+		}
 	}
 
 	for (; lblock < lblock_stop; lblock += extlen) {

fs/gfs2/bmap.h

@@ -15,7 +15,7 @@ struct gfs2_inode;
 struct page;
 
 int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
-int gfs2_block_map(struct inode *inode, u64 lblock, int create, struct buffer_head *bh);
+int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh, int create);
 int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen);
 
 int gfs2_truncatei(struct gfs2_inode *ip, u64 size);

fs/gfs2/daemon.c

@@ -82,56 +82,6 @@ int gfs2_recoverd(void *data)
 	return 0;
 }
 
-/**
- * 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;
-	struct gfs2_holder ji_gh;
-	unsigned long t;
-	int need_flush;
-
-	while (!kthread_should_stop()) {
-		/* Advance the log tail */
-
-		t = sdp->sd_log_flush_time +
-		    gfs2_tune_get(sdp, gt_log_flush_secs) * HZ;
-
-		gfs2_ail1_empty(sdp, DIO_ALL);
-		gfs2_log_lock(sdp);
-		need_flush = sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks);
-		gfs2_log_unlock(sdp);
-		if (need_flush || time_after_eq(jiffies, t)) {
-			gfs2_log_flush(sdp, NULL);
-			sdp->sd_log_flush_time = jiffies;
-		}
-
-		/* Check for latest journal index */
-
-		t = sdp->sd_jindex_refresh_time +
-		    gfs2_tune_get(sdp, gt_jindex_refresh_secs) * HZ;
-
-		if (time_after_eq(jiffies, t)) {
-			if (!gfs2_jindex_hold(sdp, &ji_gh))
-				gfs2_glock_dq_uninit(&ji_gh);
-			sdp->sd_jindex_refresh_time = jiffies;
-		}
-
-		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
-		schedule_timeout_interruptible(t);
-	}
-
-	return 0;
-}
-
 /**
  * gfs2_quotad - Write cached quota changes into the quota file
  * @sdp: Pointer to GFS2 superblock

fs/gfs2/daemon.h

@@ -12,7 +12,6 @@
 
 int gfs2_glockd(void *data);
 int gfs2_recoverd(void *data);
-int gfs2_logd(void *data);
 int gfs2_quotad(void *data);
 
 #endif /* __DAEMON_DOT_H__ */

fs/gfs2/dir.c

@@ -1876,7 +1876,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 	if (error)
 		goto out;
 
-	error = gfs2_rindex_hold(sdp, &dip->i_alloc.al_ri_gh);
+	error = gfs2_rindex_hold(sdp, &dip->i_alloc->al_ri_gh);
 	if (error)
 		goto out_qs;
 
@@ -1949,7 +1949,7 @@ out_rg_gunlock:
 	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
 out_rlist:
 	gfs2_rlist_free(&rlist);
-	gfs2_glock_dq_uninit(&dip->i_alloc.al_ri_gh);
+	gfs2_glock_dq_uninit(&dip->i_alloc->al_ri_gh);
 out_qs:
 	gfs2_quota_unhold(dip);
 out:

fs/gfs2/eaops.c

@@ -56,46 +56,6 @@ unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name)
 	return type;
 }
 
-static int user_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
-	struct inode *inode = &ip->i_inode;
-	int error = permission(inode, MAY_READ, NULL);
-	if (error)
-		return error;
-
-	return gfs2_ea_get_i(ip, er);
-}
-
-static int user_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
-	struct inode *inode = &ip->i_inode;
-
-	if (S_ISREG(inode->i_mode) ||
-	    (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) {
-		int error = permission(inode, MAY_WRITE, NULL);
-		if (error)
-			return error;
-	} else
-		return -EPERM;
-
-	return gfs2_ea_set_i(ip, er);
-}
-
-static int user_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
-	struct inode *inode = &ip->i_inode;
-
-	if (S_ISREG(inode->i_mode) ||
-	    (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) {
-		int error = permission(inode, MAY_WRITE, NULL);
-		if (error)
-			return error;
-	} else
-		return -EPERM;
-
-	return gfs2_ea_remove_i(ip, er);
-}
-
 static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
 {
 	if (!GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) &&
@@ -108,8 +68,6 @@ static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
 	     GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len)))
 		return -EOPNOTSUPP;
 
-
-
 	return gfs2_ea_get_i(ip, er);
 }
 
@@ -170,40 +128,10 @@ static int system_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
 	return gfs2_ea_remove_i(ip, er);
 }
 
-static int security_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
-	struct inode *inode = &ip->i_inode;
-	int error = permission(inode, MAY_READ, NULL);
-	if (error)
-		return error;
-
-	return gfs2_ea_get_i(ip, er);
-}
-
-static int security_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
-	struct inode *inode = &ip->i_inode;
-	int error = permission(inode, MAY_WRITE, NULL);
-	if (error)
-		return error;
-
-	return gfs2_ea_set_i(ip, er);
-}
-
-static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
-{
-	struct inode *inode = &ip->i_inode;
-	int error = permission(inode, MAY_WRITE, NULL);
-	if (error)
-		return error;
-
-	return gfs2_ea_remove_i(ip, er);
-}
-
 static const struct gfs2_eattr_operations gfs2_user_eaops = {
-	.eo_get = user_eo_get,
-	.eo_set = user_eo_set,
-	.eo_remove = user_eo_remove,
+	.eo_get = gfs2_ea_get_i,
+	.eo_set = gfs2_ea_set_i,
+	.eo_remove = gfs2_ea_remove_i,
 	.eo_name = "user",
 };
 
@@ -215,9 +143,9 @@ const struct gfs2_eattr_operations gfs2_system_eaops = {
 };
 
 static const struct gfs2_eattr_operations gfs2_security_eaops = {
-	.eo_get = security_eo_get,
-	.eo_set = security_eo_set,
-	.eo_remove = security_eo_remove,
+	.eo_get = gfs2_ea_get_i,
+	.eo_set = gfs2_ea_set_i,
+	.eo_remove = gfs2_ea_remove_i,
 	.eo_name = "security",
 };
 

fs/gfs2/eattr.c

@@ -1418,7 +1418,7 @@ out:
 static int ea_dealloc_block(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_rgrpd *rgd;
 	struct buffer_head *dibh;
 	int error;

fs/gfs2/glock.c

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -217,7 +217,6 @@ int gfs2_glock_put(struct gfs2_glock *gl)
 	if (atomic_dec_and_test(&gl->gl_ref)) {
 		hlist_del(&gl->gl_list);
 		write_unlock(gl_lock_addr(gl->gl_hash));
-		BUG_ON(spin_is_locked(&gl->gl_spin));
 		gfs2_assert(sdp, gl->gl_state == LM_ST_UNLOCKED);
 		gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
 		gfs2_assert(sdp, list_empty(&gl->gl_holders));
@@ -346,7 +345,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_object = NULL;
 	gl->gl_sbd = sdp;
 	gl->gl_aspace = NULL;
-	lops_init_le(&gl->gl_le, &gfs2_glock_lops);
 	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
 
 	/* If this glock protects actual on-disk data or metadata blocks,
@@ -461,7 +459,6 @@ static void wait_on_holder(struct gfs2_holder *gh)
 
 static void gfs2_demote_wake(struct gfs2_glock *gl)
 {
-	BUG_ON(!spin_is_locked(&gl->gl_spin));
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
         clear_bit(GLF_DEMOTE, &gl->gl_flags);
         smp_mb__after_clear_bit();
@@ -507,21 +504,12 @@ static int rq_mutex(struct gfs2_holder *gh)
 static int rq_promote(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
 
 	if (!relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
 		if (list_empty(&gl->gl_holders)) {
 			gl->gl_req_gh = gh;
 			set_bit(GLF_LOCK, &gl->gl_flags);
 			spin_unlock(&gl->gl_spin);
-
-			if (atomic_read(&sdp->sd_reclaim_count) >
-			    gfs2_tune_get(sdp, gt_reclaim_limit) &&
-			    !(gh->gh_flags & LM_FLAG_PRIORITY)) {
-				gfs2_reclaim_glock(sdp);
-				gfs2_reclaim_glock(sdp);
-			}
-
 			gfs2_glock_xmote_th(gh->gh_gl, gh);
 			spin_lock(&gl->gl_spin);
 		}
@@ -567,7 +555,10 @@ static int rq_demote(struct gfs2_glock *gl)
 		gfs2_demote_wake(gl);
 		return 0;
 	}
+
 	set_bit(GLF_LOCK, &gl->gl_flags);
+	set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
+
 	if (gl->gl_demote_state == LM_ST_UNLOCKED ||
 	    gl->gl_state != LM_ST_EXCLUSIVE) {
 		spin_unlock(&gl->gl_spin);
@@ -576,7 +567,9 @@ static int rq_demote(struct gfs2_glock *gl)
 		spin_unlock(&gl->gl_spin);
 		gfs2_glock_xmote_th(gl, NULL);
 	}
+
 	spin_lock(&gl->gl_spin);
+	clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
 
 	return 0;
 }
@@ -598,23 +591,18 @@ static void run_queue(struct gfs2_glock *gl)
 		if (!list_empty(&gl->gl_waiters1)) {
 			gh = list_entry(gl->gl_waiters1.next,
 					struct gfs2_holder, gh_list);
-
-			if (test_bit(HIF_MUTEX, &gh->gh_iflags))
-				blocked = rq_mutex(gh);
-			else
-				gfs2_assert_warn(gl->gl_sbd, 0);
-
+			blocked = rq_mutex(gh);
 		} else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
 			blocked = rq_demote(gl);
+			if (gl->gl_waiters2 && !blocked) {
+				set_bit(GLF_DEMOTE, &gl->gl_flags);
+				gl->gl_demote_state = LM_ST_UNLOCKED;
+			}
+			gl->gl_waiters2 = 0;
 		} else if (!list_empty(&gl->gl_waiters3)) {
 			gh = list_entry(gl->gl_waiters3.next,
 					struct gfs2_holder, gh_list);
-
-			if (test_bit(HIF_PROMOTE, &gh->gh_iflags))
-				blocked = rq_promote(gh);
-			else
-				gfs2_assert_warn(gl->gl_sbd, 0);
-
+			blocked = rq_promote(gh);
 		} else
 			break;
 
@@ -632,27 +620,21 @@ static void run_queue(struct gfs2_glock *gl)
 
 static void gfs2_glmutex_lock(struct gfs2_glock *gl)
 {
-	struct gfs2_holder gh;
-
-	gfs2_holder_init(gl, 0, 0, &gh);
-	set_bit(HIF_MUTEX, &gh.gh_iflags);
-	if (test_and_set_bit(HIF_WAIT, &gh.gh_iflags))
-		BUG();
-
 	spin_lock(&gl->gl_spin);
 	if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+		struct gfs2_holder gh;
+
+		gfs2_holder_init(gl, 0, 0, &gh);
+		set_bit(HIF_WAIT, &gh.gh_iflags);
 		list_add_tail(&gh.gh_list, &gl->gl_waiters1);
+		spin_unlock(&gl->gl_spin);
+		wait_on_holder(&gh);
+		gfs2_holder_uninit(&gh);
 	} else {
 		gl->gl_owner_pid = current->pid;
 		gl->gl_ip = (unsigned long)__builtin_return_address(0);
-		clear_bit(HIF_WAIT, &gh.gh_iflags);
-		smp_mb();
-		wake_up_bit(&gh.gh_iflags, HIF_WAIT);
+		spin_unlock(&gl->gl_spin);
 	}
-	spin_unlock(&gl->gl_spin);
-
-	wait_on_holder(&gh);
-	gfs2_holder_uninit(&gh);
 }
 
 /**
@@ -691,7 +673,6 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
 	gl->gl_owner_pid = 0;
 	gl->gl_ip = 0;
 	run_queue(gl);
-	BUG_ON(!spin_is_locked(&gl->gl_spin));
 	spin_unlock(&gl->gl_spin);
 }
 
@@ -722,7 +703,10 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
 		}
 	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
 			gl->gl_demote_state != state) {
-		gl->gl_demote_state = LM_ST_UNLOCKED;
+		if (test_bit(GLF_DEMOTE_IN_PROGRESS,  &gl->gl_flags)) 
+			gl->gl_waiters2 = 1;
+		else 
+			gl->gl_demote_state = LM_ST_UNLOCKED;
 	}
 	spin_unlock(&gl->gl_spin);
 }
@@ -943,8 +927,8 @@ static void gfs2_glock_drop_th(struct gfs2_glock *gl)
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	unsigned int ret;
 
-	if (glops->go_drop_th)
-		glops->go_drop_th(gl);
+	if (glops->go_xmote_th)
+		glops->go_xmote_th(gl);
 
 	gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags));
 	gfs2_assert_warn(sdp, list_empty(&gl->gl_holders));
@@ -1156,8 +1140,6 @@ restart:
 		return -EIO;
 	}
 
-	set_bit(HIF_PROMOTE, &gh->gh_iflags);
-
 	spin_lock(&gl->gl_spin);
 	add_to_queue(gh);
 	run_queue(gl);
@@ -1248,12 +1230,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 	list_del_init(&gh->gh_list);
 
 	if (list_empty(&gl->gl_holders)) {
-		spin_unlock(&gl->gl_spin);
-
-		if (glops->go_unlock)
+		if (glops->go_unlock) {
+			spin_unlock(&gl->gl_spin);
 			glops->go_unlock(gh);
-
-		spin_lock(&gl->gl_spin);
+			spin_lock(&gl->gl_spin);
+		}
 		gl->gl_stamp = jiffies;
 	}
 
@@ -1910,8 +1891,6 @@ static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
 	print_dbg(gi, "  req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
 	print_dbg(gi, "  lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
 	print_dbg(gi, "  object = %s\n", (gl->gl_object) ? "yes" : "no");
-	print_dbg(gi, "  le = %s\n",
-		   (list_empty(&gl->gl_le.le_list)) ? "no" : "yes");
 	print_dbg(gi, "  reclaim = %s\n",
 		   (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
 	if (gl->gl_aspace)

fs/gfs2/glops.c

@@ -56,7 +56,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 		bd = list_entry(head->next, struct gfs2_bufdata,
 				bd_ail_gl_list);
 		bh = bd->bd_bh;
-		gfs2_remove_from_ail(NULL, bd);
+		gfs2_remove_from_ail(bd);
 		bd->bd_bh = NULL;
 		bh->b_private = NULL;
 		bd->bd_blkno = bh->b_blocknr;
@@ -86,15 +86,10 @@ static void gfs2_pte_inval(struct gfs2_glock *gl)
 	if (!ip || !S_ISREG(inode->i_mode))
 		return;
 
-	if (!test_bit(GIF_PAGED, &ip->i_flags))
-		return;
-
 	unmap_shared_mapping_range(inode->i_mapping, 0, 0);
-
 	if (test_bit(GIF_SW_PAGED, &ip->i_flags))
 		set_bit(GLF_DIRTY, &gl->gl_flags);
 
-	clear_bit(GIF_SW_PAGED, &ip->i_flags);
 }
 
 /**
@@ -143,43 +138,33 @@ static void meta_go_inval(struct gfs2_glock *gl, int flags)
 static void inode_go_sync(struct gfs2_glock *gl)
 {
 	struct gfs2_inode *ip = gl->gl_object;
+	struct address_space *metamapping = gl->gl_aspace->i_mapping;
+	int error;
+
+	if (gl->gl_state != LM_ST_UNLOCKED)
+		gfs2_pte_inval(gl);
+	if (gl->gl_state != LM_ST_EXCLUSIVE)
+		return;
 
 	if (ip && !S_ISREG(ip->i_inode.i_mode))
 		ip = NULL;
 
 	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
-		if (ip && !gfs2_is_jdata(ip))
-			filemap_fdatawrite(ip->i_inode.i_mapping);
 		gfs2_log_flush(gl->gl_sbd, gl);
-		if (ip && gfs2_is_jdata(ip))
-			filemap_fdatawrite(ip->i_inode.i_mapping);
-		gfs2_meta_sync(gl);
+		filemap_fdatawrite(metamapping);
 		if (ip) {
 			struct address_space *mapping = ip->i_inode.i_mapping;
-			int error = filemap_fdatawait(mapping);
+			filemap_fdatawrite(mapping);
+			error = filemap_fdatawait(mapping);
 			mapping_set_error(mapping, error);
 		}
+		error = filemap_fdatawait(metamapping);
+		mapping_set_error(metamapping, error);
 		clear_bit(GLF_DIRTY, &gl->gl_flags);
 		gfs2_ail_empty_gl(gl);
 	}
 }
 
-/**
- * inode_go_xmote_th - promote/demote a glock
- * @gl: the glock
- * @state: the requested state
- * @flags:
- *
- */
-
-static void inode_go_xmote_th(struct gfs2_glock *gl)
-{
-	if (gl->gl_state != LM_ST_UNLOCKED)
-		gfs2_pte_inval(gl);
-	if (gl->gl_state == LM_ST_EXCLUSIVE)
-		inode_go_sync(gl);
-}
-
 /**
  * inode_go_xmote_bh - After promoting/demoting a glock
  * @gl: the glock
@@ -200,22 +185,6 @@ static void inode_go_xmote_bh(struct gfs2_glock *gl)
 	}
 }
 
-/**
- * inode_go_drop_th - unlock a glock
- * @gl: the glock
- *
- * Invoked from rq_demote().
- * Another node needs the lock in EXCLUSIVE mode, or lock (unused for too long)
- * is being purged from our node's glock cache; we're dropping lock.
- */
-
-static void inode_go_drop_th(struct gfs2_glock *gl)
-{
-	gfs2_pte_inval(gl);
-	if (gl->gl_state == LM_ST_EXCLUSIVE)
-		inode_go_sync(gl);
-}
-
 /**
  * inode_go_inval - prepare a inode glock to be released
  * @gl: the glock
@@ -234,10 +203,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 			set_bit(GIF_INVALID, &ip->i_flags);
 	}
 
-	if (ip && S_ISREG(ip->i_inode.i_mode)) {
+	if (ip && S_ISREG(ip->i_inode.i_mode))
 		truncate_inode_pages(ip->i_inode.i_mapping, 0);
-		clear_bit(GIF_PAGED, &ip->i_flags);
-	}
 }
 
 /**
@@ -293,23 +260,6 @@ static int inode_go_lock(struct gfs2_holder *gh)
 	return error;
 }
 
-/**
- * inode_go_unlock - operation done before an inode lock is unlocked by a
- *		     process
- * @gl: the glock
- * @flags:
- *
- */
-
-static void inode_go_unlock(struct gfs2_holder *gh)
-{
-	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_inode *ip = gl->gl_object;
-
-	if (ip)
-		gfs2_meta_cache_flush(ip);
-}
-
 /**
  * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
  * @gl: the glock
@@ -350,14 +300,14 @@ static void rgrp_go_unlock(struct gfs2_holder *gh)
 }
 
 /**
- * trans_go_xmote_th - promote/demote the transaction glock
+ * trans_go_sync - promote/demote the transaction glock
  * @gl: the glock
  * @state: the requested state
  * @flags:
  *
  */
 
-static void trans_go_xmote_th(struct gfs2_glock *gl)
+static void trans_go_sync(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 
@@ -384,7 +334,6 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl)
 
 	if (gl->gl_state != LM_ST_UNLOCKED &&
 	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		gfs2_meta_cache_flush(GFS2_I(sdp->sd_jdesc->jd_inode));
 		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 
 		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
@@ -401,24 +350,6 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl)
 	}
 }
 
-/**
- * trans_go_drop_th - unlock the transaction glock
- * @gl: the glock
- *
- * We want to sync the device even with localcaching.  Remember
- * that localcaching journal replay only marks buffers dirty.
- */
-
-static void trans_go_drop_th(struct gfs2_glock *gl)
-{
-	struct gfs2_sbd *sdp = gl->gl_sbd;
-
-	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		gfs2_meta_syncfs(sdp);
-		gfs2_log_shutdown(sdp);
-	}
-}
-
 /**
  * quota_go_demote_ok - Check to see if it's ok to unlock a quota glock
  * @gl: the glock
@@ -433,25 +364,21 @@ static int quota_go_demote_ok(struct gfs2_glock *gl)
 
 const struct gfs2_glock_operations gfs2_meta_glops = {
 	.go_xmote_th = meta_go_sync,
-	.go_drop_th = meta_go_sync,
 	.go_type = LM_TYPE_META,
 };
 
 const struct gfs2_glock_operations gfs2_inode_glops = {
-	.go_xmote_th = inode_go_xmote_th,
+	.go_xmote_th = inode_go_sync,
 	.go_xmote_bh = inode_go_xmote_bh,
-	.go_drop_th = inode_go_drop_th,
 	.go_inval = inode_go_inval,
 	.go_demote_ok = inode_go_demote_ok,
 	.go_lock = inode_go_lock,
-	.go_unlock = inode_go_unlock,
 	.go_type = LM_TYPE_INODE,
 	.go_min_hold_time = HZ / 10,
 };
 
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_xmote_th = meta_go_sync,
-	.go_drop_th = meta_go_sync,
 	.go_inval = meta_go_inval,
 	.go_demote_ok = rgrp_go_demote_ok,
 	.go_lock = rgrp_go_lock,
@@ -461,9 +388,8 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 };
 
 const struct gfs2_glock_operations gfs2_trans_glops = {
-	.go_xmote_th = trans_go_xmote_th,
+	.go_xmote_th = trans_go_sync,
 	.go_xmote_bh = trans_go_xmote_bh,
-	.go_drop_th = trans_go_drop_th,
 	.go_type = LM_TYPE_NONDISK,
 };
 

fs/gfs2/incore.h

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -131,7 +131,6 @@ struct gfs2_bufdata {
 struct gfs2_glock_operations {
 	void (*go_xmote_th) (struct gfs2_glock *gl);
 	void (*go_xmote_bh) (struct gfs2_glock *gl);
-	void (*go_drop_th) (struct gfs2_glock *gl);
 	void (*go_inval) (struct gfs2_glock *gl, int flags);
 	int (*go_demote_ok) (struct gfs2_glock *gl);
 	int (*go_lock) (struct gfs2_holder *gh);
@@ -141,10 +140,6 @@ struct gfs2_glock_operations {
 };
 
 enum {
-	/* Actions */
-	HIF_MUTEX		= 0,
-	HIF_PROMOTE		= 1,
-
 	/* States */
 	HIF_HOLDER		= 6,
 	HIF_FIRST		= 7,
@@ -171,6 +166,8 @@ enum {
 	GLF_DEMOTE		= 3,
 	GLF_PENDING_DEMOTE	= 4,
 	GLF_DIRTY		= 5,
+	GLF_DEMOTE_IN_PROGRESS	= 6,
+	GLF_LFLUSH		= 7,
 };
 
 struct gfs2_glock {
@@ -190,6 +187,7 @@ struct gfs2_glock {
 	struct list_head gl_holders;
 	struct list_head gl_waiters1;	/* HIF_MUTEX */
 	struct list_head gl_waiters3;	/* HIF_PROMOTE */
+	int gl_waiters2;		/* GIF_DEMOTE */
 
 	const struct gfs2_glock_operations *gl_ops;
 
@@ -210,7 +208,6 @@ struct gfs2_glock {
 	struct gfs2_sbd *gl_sbd;
 
 	struct inode *gl_aspace;
-	struct gfs2_log_element gl_le;
 	struct list_head gl_ail_list;
 	atomic_t gl_ail_count;
 	struct delayed_work gl_work;
@@ -239,7 +236,6 @@ struct gfs2_alloc {
 enum {
 	GIF_INVALID		= 0,
 	GIF_QD_LOCKED		= 1,
-	GIF_PAGED		= 2,
 	GIF_SW_PAGED		= 3,
 };
 
@@ -268,14 +264,10 @@ struct gfs2_inode {
 	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_alloc i_alloc;
+	struct gfs2_alloc *i_alloc;
 	u64 i_last_rg_alloc;
 
-	spinlock_t i_spin;
 	struct rw_semaphore i_rw_mutex;
-	unsigned long i_last_pfault;
-
-	struct buffer_head *i_cache[GFS2_MAX_META_HEIGHT];
 };
 
 /*
@@ -287,19 +279,12 @@ static inline struct gfs2_inode *GFS2_I(struct inode *inode)
 	return container_of(inode, struct gfs2_inode, i_inode);
 }
 
-/* To be removed? */
-static inline struct gfs2_sbd *GFS2_SB(struct inode *inode)
+static inline struct gfs2_sbd *GFS2_SB(const struct inode *inode)
 {
 	return inode->i_sb->s_fs_info;
 }
 
-enum {
-	GFF_DID_DIRECT_ALLOC	= 0,
-	GFF_EXLOCK = 1,
-};
-
 struct gfs2_file {
-	unsigned long f_flags;		/* GFF_... */
 	struct mutex f_fl_mutex;
 	struct gfs2_holder f_fl_gh;
 };
@@ -373,8 +358,17 @@ struct gfs2_ail {
 	u64 ai_sync_gen;
 };
 
+struct gfs2_journal_extent {
+	struct list_head extent_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;
 
 	struct inode *jd_inode;
 	unsigned int jd_jid;
@@ -421,13 +415,9 @@ struct gfs2_args {
 struct gfs2_tune {
 	spinlock_t gt_spin;
 
-	unsigned int gt_ilimit;
-	unsigned int gt_ilimit_tries;
-	unsigned int gt_ilimit_min;
 	unsigned int gt_demote_secs; /* Cache retention for unheld glock */
 	unsigned int gt_incore_log_blocks;
 	unsigned int gt_log_flush_secs;
-	unsigned int gt_jindex_refresh_secs; /* Check for new journal index */
 
 	unsigned int gt_recoverd_secs;
 	unsigned int gt_logd_secs;
@@ -443,10 +433,8 @@ struct gfs2_tune {
 	unsigned int gt_new_files_jdata;
 	unsigned int gt_new_files_directio;
 	unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
-	unsigned int gt_lockdump_size;
 	unsigned int gt_stall_secs; /* Detects trouble! */
 	unsigned int gt_complain_secs;
-	unsigned int gt_reclaim_limit; /* Max num of glocks in reclaim list */
 	unsigned int gt_statfs_quantum;
 	unsigned int gt_statfs_slow;
 };
@@ -539,7 +527,6 @@ struct gfs2_sbd {
 	/* StatFS stuff */
 
 	spinlock_t sd_statfs_spin;
-	struct mutex sd_statfs_mutex;
 	struct gfs2_statfs_change_host sd_statfs_master;
 	struct gfs2_statfs_change_host sd_statfs_local;
 	unsigned long sd_statfs_sync_time;
@@ -602,20 +589,18 @@ struct gfs2_sbd {
 	unsigned int sd_log_commited_databuf;
 	unsigned int sd_log_commited_revoke;
 
-	unsigned int sd_log_num_gl;
 	unsigned int sd_log_num_buf;
 	unsigned int sd_log_num_revoke;
 	unsigned int sd_log_num_rg;
 	unsigned int sd_log_num_databuf;
 
-	struct list_head sd_log_le_gl;
 	struct list_head sd_log_le_buf;
 	struct list_head sd_log_le_revoke;
 	struct list_head sd_log_le_rg;
 	struct list_head sd_log_le_databuf;
 	struct list_head sd_log_le_ordered;
 
-	unsigned int sd_log_blks_free;
+	atomic_t sd_log_blks_free;
 	struct mutex sd_log_reserve_mutex;
 
 	u64 sd_log_sequence;

fs/gfs2/inode.c

@@ -31,7 +31,6 @@
 #include "log.h"
 #include "meta_io.h"
 #include "ops_address.h"
-#include "ops_file.h"
 #include "ops_inode.h"
 #include "quota.h"
 #include "rgrp.h"
@@ -132,15 +131,21 @@ static struct inode *gfs2_iget_skip(struct super_block *sb,
 
 void gfs2_set_iop(struct inode *inode)
 {
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	umode_t mode = inode->i_mode;
 
 	if (S_ISREG(mode)) {
 		inode->i_op = &gfs2_file_iops;
-		inode->i_fop = &gfs2_file_fops;
-		inode->i_mapping->a_ops = &gfs2_file_aops;
+		if (sdp->sd_args.ar_localflocks)
+			inode->i_fop = &gfs2_file_fops_nolock;
+		else
+			inode->i_fop = &gfs2_file_fops;
 	} else if (S_ISDIR(mode)) {
 		inode->i_op = &gfs2_dir_iops;
-		inode->i_fop = &gfs2_dir_fops;
+		if (sdp->sd_args.ar_localflocks)
+			inode->i_fop = &gfs2_dir_fops_nolock;
+		else
+			inode->i_fop = &gfs2_dir_fops;
 	} else if (S_ISLNK(mode)) {
 		inode->i_op = &gfs2_symlink_iops;
 	} else {
@@ -291,12 +296,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	di->di_entries = be32_to_cpu(str->di_entries);
 
 	di->di_eattr = be64_to_cpu(str->di_eattr);
-	return 0;
-}
+	if (S_ISREG(ip->i_inode.i_mode))
+		gfs2_set_aops(&ip->i_inode);
 
-static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh)
-{
-	ip->i_cache[0] = bh;
+	return 0;
 }
 
 /**
@@ -366,7 +369,8 @@ int gfs2_dinode_dealloc(struct gfs2_inode *ip)
 	if (error)
 		goto out_rg_gunlock;
 
-	gfs2_trans_add_gl(ip->i_gl);
+	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
+	set_bit(GLF_LFLUSH, &ip->i_gl->gl_flags);
 
 	gfs2_free_di(rgd, ip);
 
@@ -707,9 +711,10 @@ static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	int error;
 
-	gfs2_alloc_get(dip);
+	if (gfs2_alloc_get(dip) == NULL)
+		return -ENOMEM;
 
-	dip->i_alloc.al_requested = RES_DINODE;
+	dip->i_alloc->al_requested = RES_DINODE;
 	error = gfs2_inplace_reserve(dip);
 	if (error)
 		goto out;
@@ -855,7 +860,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
 
 	error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name);
 	if (alloc_required < 0)
-		goto fail;
+		goto fail_quota_locks;
 	if (alloc_required) {
 		error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid);
 		if (error)
@@ -896,7 +901,7 @@ fail_end_trans:
 	gfs2_trans_end(sdp);
 
 fail_ipreserv:
-	if (dip->i_alloc.al_rgd)
+	if (dip->i_alloc->al_rgd)
 		gfs2_inplace_release(dip);
 
 fail_quota_locks:
@@ -966,7 +971,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
 	int error;
 	u64 generation;
-	struct buffer_head *bh=NULL;
+	struct buffer_head *bh = NULL;
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -1003,8 +1008,6 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	if (IS_ERR(inode))
 		goto fail_gunlock2;
 
-	gfs2_inode_bh(GFS2_I(inode), bh);
-
 	error = gfs2_inode_refresh(GFS2_I(inode));
 	if (error)
 		goto fail_gunlock2;
@@ -1021,6 +1024,8 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	if (error)
 		goto fail_gunlock2;
 
+	if (bh)
+		brelse(bh);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	return inode;
@@ -1032,6 +1037,8 @@ fail_gunlock2:
 fail_gunlock:
 	gfs2_glock_dq(ghs);
 fail:
+	if (bh)
+		brelse(bh);
 	return ERR_PTR(error);
 }
 

fs/gfs2/inode.h

@@ -20,6 +20,18 @@ static inline int gfs2_is_jdata(const struct gfs2_inode *ip)
 	return ip->i_di.di_flags & 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);

fs/gfs2/locking/dlm/mount.c

@@ -67,6 +67,11 @@ static int make_args(struct gdlm_ls *ls, char *data_arg, int *nodir)
 	memset(data, 0, 256);
 	strncpy(data, data_arg, 255);
 
+	if (!strlen(data)) {
+		log_error("no mount options, (u)mount helpers not installed");
+		return -EINVAL;
+	}
+
 	for (options = data; (x = strsep(&options, ":")); ) {
 		if (!*x)
 			continue;

fs/gfs2/locking/dlm/plock.c

@@ -89,15 +89,19 @@ int gdlm_plock(void *lockspace, struct lm_lockname *name,
 	op->info.number		= name->ln_number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner		= (__u64)(long) fl->fl_owner;
 	if (fl->fl_lmops && fl->fl_lmops->fl_grant) {
+		/* fl_owner is lockd which doesn't distinguish
+		   processes on the nfs client */
+		op->info.owner	= (__u64) fl->fl_pid;
 		xop->callback	= fl->fl_lmops->fl_grant;
 		locks_init_lock(&xop->flc);
 		locks_copy_lock(&xop->flc, fl);
 		xop->fl		= fl;
 		xop->file	= file;
-	} else
+	} else {
+		op->info.owner	= (__u64)(long) fl->fl_owner;
 		xop->callback	= NULL;
+	}
 
 	send_op(op);
 
@@ -203,7 +207,10 @@ int gdlm_punlock(void *lockspace, struct lm_lockname *name,
 	op->info.number		= name->ln_number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner		= (__u64)(long) fl->fl_owner;
+	if (fl->fl_lmops && fl->fl_lmops->fl_grant)
+		op->info.owner	= (__u64) fl->fl_pid;
+	else
+		op->info.owner	= (__u64)(long) fl->fl_owner;
 
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
@@ -242,7 +249,10 @@ int gdlm_plock_get(void *lockspace, struct lm_lockname *name,
 	op->info.number		= name->ln_number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner		= (__u64)(long) fl->fl_owner;
+	if (fl->fl_lmops && fl->fl_lmops->fl_grant)
+		op->info.owner	= (__u64) fl->fl_pid;
+	else
+		op->info.owner	= (__u64)(long) fl->fl_owner;
 
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));

fs/gfs2/locking/dlm/thread.c

@@ -273,18 +273,13 @@ static int gdlm_thread(void *data, int blist)
 	struct gdlm_ls *ls = (struct gdlm_ls *) data;
 	struct gdlm_lock *lp = NULL;
 	uint8_t complete, blocking, submit, drop;
-	DECLARE_WAITQUEUE(wait, current);
 
 	/* Only thread1 is allowed to do blocking callbacks since gfs
 	   may wait for a completion callback within a blocking cb. */
 
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		add_wait_queue(&ls->thread_wait, &wait);
-		if (no_work(ls, blist))
-			schedule();
-		remove_wait_queue(&ls->thread_wait, &wait);
-		set_current_state(TASK_RUNNING);
+		wait_event_interruptible(ls->thread_wait,
+				!no_work(ls, blist) || kthread_should_stop());
 
 		complete = blocking = submit = drop = 0;
 

fs/gfs2/log.c

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -16,6 +16,8 @@
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
 #include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -68,14 +70,12 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
  *
  */
 
-void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd)
+void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
 {
 	bd->bd_ail = 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);
-	if (mapping)
-		gfs2_meta_cache_flush(GFS2_I(mapping->host));
 	brelse(bd->bd_bh);
 }
 
@@ -92,8 +92,6 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 	struct buffer_head *bh;
 	int retry;
 
-	BUG_ON(!spin_is_locked(&sdp->sd_log_lock));
-
 	do {
 		retry = 0;
 
@@ -210,7 +208,7 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
 	gfs2_log_unlock(sdp);
 }
 
-int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags)
+static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags)
 {
 	struct gfs2_ail *ai, *s;
 	int ret;
@@ -248,7 +246,7 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 		bd = list_entry(head->prev, struct gfs2_bufdata,
 				bd_ail_st_list);
 		gfs2_assert(sdp, bd->bd_ail == ai);
-		gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd);
+		gfs2_remove_from_ail(bd);
 	}
 }
 
@@ -303,7 +301,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
 
 	mutex_lock(&sdp->sd_log_reserve_mutex);
 	gfs2_log_lock(sdp);
-	while(sdp->sd_log_blks_free <= (blks + reserved_blks)) {
+	while(atomic_read(&sdp->sd_log_blks_free) <= (blks + reserved_blks)) {
 		gfs2_log_unlock(sdp);
 		gfs2_ail1_empty(sdp, 0);
 		gfs2_log_flush(sdp, NULL);
@@ -312,7 +310,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
 			gfs2_ail1_start(sdp, 0);
 		gfs2_log_lock(sdp);
 	}
-	sdp->sd_log_blks_free -= blks;
+	atomic_sub(blks, &sdp->sd_log_blks_free);
 	gfs2_log_unlock(sdp);
 	mutex_unlock(&sdp->sd_log_reserve_mutex);
 
@@ -332,27 +330,23 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
 {
 
 	gfs2_log_lock(sdp);
-	sdp->sd_log_blks_free += blks;
+	atomic_add(blks, &sdp->sd_log_blks_free);
 	gfs2_assert_withdraw(sdp,
-			     sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+			     atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
 	gfs2_log_unlock(sdp);
 	up_read(&sdp->sd_log_flush_lock);
 }
 
 static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
 {
-	struct inode *inode = sdp->sd_jdesc->jd_inode;
-	int error;
-	struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
-
-	bh_map.b_size = 1 << inode->i_blkbits;
-	error = gfs2_block_map(inode, lbn, 0, &bh_map);
-	if (error || !bh_map.b_blocknr)
-		printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error,
-		       (unsigned long long)bh_map.b_blocknr, lbn);
-	gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr);
-
-	return bh_map.b_blocknr;
+	struct gfs2_journal_extent *je;
+
+	list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) {
+		if (lbn >= je->lblock && lbn < je->lblock + je->blocks)
+			return je->dblock + lbn - je->lblock;
+	}
+
+	return -1;
 }
 
 /**
@@ -561,8 +555,8 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 	ail2_empty(sdp, new_tail);
 
 	gfs2_log_lock(sdp);
-	sdp->sd_log_blks_free += dist;
-	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks);
+	atomic_add(dist, &sdp->sd_log_blks_free);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
 	gfs2_log_unlock(sdp);
 
 	sdp->sd_log_tail = new_tail;
@@ -652,7 +646,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 		get_bh(bh);
 		gfs2_log_unlock(sdp);
 		lock_buffer(bh);
-		if (test_clear_buffer_dirty(bh)) {
+		if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
 			bh->b_end_io = end_buffer_write_sync;
 			submit_bh(WRITE, bh);
 		} else {
@@ -694,20 +688,16 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
  *
  */
 
-void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 {
 	struct gfs2_ail *ai;
 
 	down_write(&sdp->sd_log_flush_lock);
 
-	if (gl) {
-		gfs2_log_lock(sdp);
-		if (list_empty(&gl->gl_le.le_list)) {
-			gfs2_log_unlock(sdp);
-			up_write(&sdp->sd_log_flush_lock);
-			return;
-		}
-		gfs2_log_unlock(sdp);
+	/* 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;
 	}
 
 	ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
@@ -739,7 +729,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 		log_flush_commit(sdp);
 	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
 		gfs2_log_lock(sdp);
-		sdp->sd_log_blks_free--; /* Adjust for unreserved buffer */
+		atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
 		gfs2_log_unlock(sdp);
 		log_write_header(sdp, 0, PULL);
 	}
@@ -767,7 +757,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
 	unsigned int reserved;
-	unsigned int old;
+	unsigned int unused;
 
 	gfs2_log_lock(sdp);
 
@@ -779,14 +769,11 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
 	gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0);
 	reserved = calc_reserved(sdp);
-	old = sdp->sd_log_blks_free;
-	sdp->sd_log_blks_free += tr->tr_reserved -
-				 (reserved - sdp->sd_log_blks_reserved);
-
-	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old);
-	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <=
+	unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
+	gfs2_assert_withdraw(sdp, unused >= 0);
+	atomic_add(unused, &sdp->sd_log_blks_free);
+	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);
@@ -825,7 +812,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	down_write(&sdp->sd_log_flush_lock);
 
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
-	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_gl);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
@@ -838,7 +824,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT,
 			 (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL);
 
-	gfs2_assert_warn(sdp, sdp->sd_log_blks_free == sdp->sd_jdesc->jd_blocks);
+	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
 	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
 	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
 
@@ -866,3 +852,42 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
 	}
 }
 
+
+/**
+ * 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;
+	int need_flush;
+
+	while (!kthread_should_stop()) {
+		/* Advance the log tail */
+
+		t = sdp->sd_log_flush_time +
+		    gfs2_tune_get(sdp, gt_log_flush_secs) * HZ;
+
+		gfs2_ail1_empty(sdp, DIO_ALL);
+		gfs2_log_lock(sdp);
+		need_flush = sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks);
+		gfs2_log_unlock(sdp);
+		if (need_flush || time_after_eq(jiffies, t)) {
+			gfs2_log_flush(sdp, NULL);
+			sdp->sd_log_flush_time = jiffies;
+		}
+
+		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
+		if (freezing(current))
+			refrigerator();
+		schedule_timeout_interruptible(t);
+	}
+
+	return 0;
+}
+

fs/gfs2/log.h

@@ -48,8 +48,6 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
 unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 			    unsigned int ssize);
 
-int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags);
-
 int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
 void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
 void gfs2_log_incr_head(struct gfs2_sbd *sdp);
@@ -57,11 +55,19 @@ void gfs2_log_incr_head(struct gfs2_sbd *sdp);
 struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
 struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
 				      struct buffer_head *real);
-void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
+void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
+
+static inline void gfs2_log_flush(struct gfs2_sbd *sbd, struct gfs2_glock *gl)
+{
+	if (!gl || test_bit(GLF_LFLUSH, &gl->gl_flags))
+		__gfs2_log_flush(sbd, gl);
+}
+
 void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
-void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd);
+void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
 
 void gfs2_log_shutdown(struct gfs2_sbd *sdp);
 void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
+int gfs2_logd(void *data);
 
 #endif /* __LOG_DOT_H__ */

fs/gfs2/lops.c

@@ -87,6 +87,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	}
 	bd->bd_ail = ai;
 	list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+	clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
 	gfs2_log_unlock(sdp);
 	unlock_buffer(bh);
 }
@@ -124,49 +125,6 @@ static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type)
 	return bh;
 }
 
-static void __glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
-{
-	struct gfs2_glock *gl;
-	struct gfs2_trans *tr = current->journal_info;
-
-	tr->tr_touched = 1;
-
-	gl = container_of(le, struct gfs2_glock, gl_le);
-	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
-		return;
-
-	if (!list_empty(&le->le_list))
-		return;
-
-	gfs2_glock_hold(gl);
-	set_bit(GLF_DIRTY, &gl->gl_flags);
-	sdp->sd_log_num_gl++;
-	list_add(&le->le_list, &sdp->sd_log_le_gl);
-}
-
-static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
-{
-	gfs2_log_lock(sdp);
-	__glock_lo_add(sdp, le);
-	gfs2_log_unlock(sdp);
-}
-
-static void glock_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
-{
-	struct list_head *head = &sdp->sd_log_le_gl;
-	struct gfs2_glock *gl;
-
-	while (!list_empty(head)) {
-		gl = list_entry(head->next, struct gfs2_glock, gl_le.le_list);
-		list_del_init(&gl->gl_le.le_list);
-		sdp->sd_log_num_gl--;
-
-		gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl));
-		gfs2_glock_put(gl);
-	}
-	gfs2_assert_warn(sdp, !sdp->sd_log_num_gl);
-}
-
 static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 {
 	struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
@@ -182,7 +140,8 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	list_add(&bd->bd_list_tr, &tr->tr_list_buf);
 	if (!list_empty(&le->le_list))
 		goto out;
-	__glock_lo_add(sdp, &bd->bd_gl->gl_le);
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
 	gfs2_meta_check(sdp, bd->bd_bh);
 	gfs2_pin(sdp, bd->bd_bh);
 	sdp->sd_log_num_buf++;
@@ -556,17 +515,20 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 
 	lock_buffer(bd->bd_bh);
 	gfs2_log_lock(sdp);
-	if (!list_empty(&bd->bd_list_tr))
-		goto out;
-	tr->tr_touched = 1;
-	if (gfs2_is_jdata(ip)) {
-		tr->tr_num_buf++;
-		list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+	if (tr) {
+		if (!list_empty(&bd->bd_list_tr))
+			goto out;
+		tr->tr_touched = 1;
+		if (gfs2_is_jdata(ip)) {
+			tr->tr_num_buf++;
+			list_add(&bd->bd_list_tr, &tr->tr_list_buf);
+		}
 	}
 	if (!list_empty(&le->le_list))
 		goto out;
 
-	__glock_lo_add(sdp, &bd->bd_gl->gl_le);
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
 	if (gfs2_is_jdata(ip)) {
 		gfs2_pin(sdp, bd->bd_bh);
 		tr->tr_num_databuf_new++;
@@ -773,12 +735,6 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 }
 
 
-const struct gfs2_log_operations gfs2_glock_lops = {
-	.lo_add = glock_lo_add,
-	.lo_after_commit = glock_lo_after_commit,
-	.lo_name = "glock",
-};
-
 const struct gfs2_log_operations gfs2_buf_lops = {
 	.lo_add = buf_lo_add,
 	.lo_incore_commit = buf_lo_incore_commit,
@@ -816,7 +772,6 @@ const struct gfs2_log_operations gfs2_databuf_lops = {
 };
 
 const struct gfs2_log_operations *gfs2_log_ops[] = {
-	&gfs2_glock_lops,
 	&gfs2_databuf_lops,
 	&gfs2_buf_lops,
 	&gfs2_rg_lops,

fs/gfs2/main.c

@@ -29,9 +29,8 @@ static void gfs2_init_inode_once(struct kmem_cache *cachep, void *foo)
 	struct gfs2_inode *ip = foo;
 
 	inode_init_once(&ip->i_inode);
-	spin_lock_init(&ip->i_spin);
 	init_rwsem(&ip->i_rw_mutex);
-	memset(ip->i_cache, 0, sizeof(ip->i_cache));
+	ip->i_alloc = NULL;
 }
 
 static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo)

fs/gfs2/meta_io.c

@@ -50,6 +50,7 @@ static int gfs2_aspace_writepage(struct page *page,
 static const struct address_space_operations aspace_aops = {
 	.writepage = gfs2_aspace_writepage,
 	.releasepage = gfs2_releasepage,
+	.sync_page = block_sync_page,
 };
 
 /**
@@ -221,13 +222,14 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 		   struct buffer_head **bhp)
 {
 	*bhp = getbuf(gl, blkno, CREATE);
-	if (!buffer_uptodate(*bhp))
+	if (!buffer_uptodate(*bhp)) {
 		ll_rw_block(READ_META, 1, bhp);
-	if (flags & DIO_WAIT) {
-		int error = gfs2_meta_wait(gl->gl_sbd, *bhp);
-		if (error) {
-			brelse(*bhp);
-			return error;
+		if (flags & DIO_WAIT) {
+			int error = gfs2_meta_wait(gl->gl_sbd, *bhp);
+			if (error) {
+				brelse(*bhp);
+				return error;
+			}
 		}
 	}
 
@@ -282,7 +284,7 @@ void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
 		return;
 	}
 
-	bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL),
+	bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
 	bd->bd_bh = bh;
 	bd->bd_gl = gl;
 
@@ -317,7 +319,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
 	}
 	if (bd) {
 		if (bd->bd_ail) {
-			gfs2_remove_from_ail(NULL, bd);
+			gfs2_remove_from_ail(bd);
 			bh->b_private = NULL;
 			bd->bd_bh = NULL;
 			bd->bd_blkno = bh->b_blocknr;
@@ -357,32 +359,6 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
 	}
 }
 
-/**
- * gfs2_meta_cache_flush - get rid of any references on buffers for this inode
- * @ip: The GFS2 inode
- *
- * This releases buffers that are in the most-recently-used array of
- * blocks used for indirect block addressing for this inode.
- */
-
-void gfs2_meta_cache_flush(struct gfs2_inode *ip)
-{
-	struct buffer_head **bh_slot;
-	unsigned int x;
-
-	spin_lock(&ip->i_spin);
-
-	for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) {
-		bh_slot = &ip->i_cache[x];
-		if (*bh_slot) {
-			brelse(*bh_slot);
-			*bh_slot = NULL;
-		}
-	}
-
-	spin_unlock(&ip->i_spin);
-}
-
 /**
  * gfs2_meta_indirect_buffer - Get a metadata buffer
  * @ip: The GFS2 inode
@@ -391,8 +367,6 @@ void gfs2_meta_cache_flush(struct gfs2_inode *ip)
  * @new: Non-zero if we may create a new buffer
  * @bhp: the buffer is returned here
  *
- * Try to use the gfs2_inode's MRU metadata tree cache.
- *
  * Returns: errno
  */
 
@@ -401,58 +375,25 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_glock *gl = ip->i_gl;
-	struct buffer_head *bh = NULL, **bh_slot = ip->i_cache + height;
-	int in_cache = 0;
-
-	BUG_ON(!gl);
-	BUG_ON(!sdp);
-
-	spin_lock(&ip->i_spin);
-	if (*bh_slot && (*bh_slot)->b_blocknr == num) {
-		bh = *bh_slot;
-		get_bh(bh);
-		in_cache = 1;
-	}
-	spin_unlock(&ip->i_spin);
-
-	if (!bh)
-		bh = getbuf(gl, num, CREATE);
-
-	if (!bh)
-		return -ENOBUFS;
+	struct buffer_head *bh;
+	int ret = 0;
 
 	if (new) {
-		if (gfs2_assert_warn(sdp, height))
-			goto err;
-		meta_prep_new(bh);
+		BUG_ON(height == 0);
+		bh = gfs2_meta_new(gl, num);
 		gfs2_trans_add_bh(ip->i_gl, bh, 1);
 		gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
 		gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
 	} else {
 		u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
-		if (!buffer_uptodate(bh)) {
-			ll_rw_block(READ_META, 1, &bh);
-			if (gfs2_meta_wait(sdp, bh))
-				goto err;
+		ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh);
+		if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
+			brelse(bh);
+			ret = -EIO;
 		}
-		if (gfs2_metatype_check(sdp, bh, mtype))
-			goto err;
-	}
-
-	if (!in_cache) {
-		spin_lock(&ip->i_spin);
-		if (*bh_slot)
-			brelse(*bh_slot);
-		*bh_slot = bh;
-		get_bh(bh);
-		spin_unlock(&ip->i_spin);
 	}
-
 	*bhp = bh;
-	return 0;
-err:
-	brelse(bh);
-	return -EIO;
+	return ret;
 }
 
 /**

fs/gfs2/meta_io.h

@@ -56,7 +56,6 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr,
 
 void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
 
-void gfs2_meta_cache_flush(struct gfs2_inode *ip);
 int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
 			      int new, struct buffer_head **bhp);
 

fs/gfs2/ops_address.c

@@ -20,6 +20,8 @@
 #include <linux/swap.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/lm_interface.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -32,7 +34,6 @@
 #include "quota.h"
 #include "trans.h"
 #include "rgrp.h"
-#include "ops_file.h"
 #include "super.h"
 #include "util.h"
 #include "glops.h"
@@ -57,22 +58,6 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
 	}
 }
 
-/**
- * gfs2_get_block - Fills in a buffer head with details about a block
- * @inode: The inode
- * @lblock: The block number to look up
- * @bh_result: The buffer head to return the result in
- * @create: Non-zero if we may add block to the file
- *
- * Returns: errno
- */
-
-int gfs2_get_block(struct inode *inode, sector_t lblock,
-	           struct buffer_head *bh_result, int create)
-{
-	return gfs2_block_map(inode, lblock, create, bh_result);
-}
-
 /**
  * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
  * @inode: The inode
@@ -88,7 +73,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 {
 	int error;
 
-	error = gfs2_block_map(inode, lblock, 0, bh_result);
+	error = gfs2_block_map(inode, lblock, bh_result, 0);
 	if (error)
 		return error;
 	if (!buffer_mapped(bh_result))
@@ -99,20 +84,19 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
 				 struct buffer_head *bh_result, int create)
 {
-	return gfs2_block_map(inode, lblock, 0, bh_result);
+	return gfs2_block_map(inode, lblock, bh_result, 0);
 }
 
 /**
- * gfs2_writepage - Write complete page
- * @page: Page to write
+ * gfs2_writepage_common - Common bits of writepage
+ * @page: The page to be written
+ * @wbc: The writeback control
  *
- * Returns: errno
- *
- * Some of this is copied from block_write_full_page() although we still
- * call it to do most of the work.
+ * Returns: 1 if writepage is ok, otherwise an error code or zero if no error.
  */
 
-static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
+static int gfs2_writepage_common(struct page *page,
+				 struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
@@ -120,41 +104,133 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
 	loff_t i_size = i_size_read(inode);
 	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
 	unsigned offset;
-	int error;
-	int done_trans = 0;
+	int ret = -EIO;
 
-	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) {
-		unlock_page(page);
-		return -EIO;
-	}
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
+		goto out;
+	ret = 0;
 	if (current->journal_info)
-		goto out_ignore;
-
+		goto redirty;
 	/* Is the page fully outside i_size? (truncate in progress) */
-        offset = i_size & (PAGE_CACHE_SIZE-1);
+	offset = i_size & (PAGE_CACHE_SIZE-1);
 	if (page->index > end_index || (page->index == end_index && !offset)) {
 		page->mapping->a_ops->invalidatepage(page, 0);
-		unlock_page(page);
-		return 0; /* don't care */
+		goto out;
+	}
+	return 1;
+redirty:
+	redirty_page_for_writepage(wbc, page);
+out:
+	unlock_page(page);
+	return 0;
+}
+
+/**
+ * gfs2_writeback_writepage - Write page for writeback mappings
+ * @page: The page
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_writeback_writepage(struct page *page,
+				    struct writeback_control *wbc)
+{
+	int ret;
+
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret <= 0)
+		return ret;
+
+	ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc);
+	if (ret == -EAGAIN)
+		ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+	return ret;
+}
+
+/**
+ * gfs2_ordered_writepage - Write page for ordered data files
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ */
+
+static int gfs2_ordered_writepage(struct page *page,
+				  struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	int ret;
+
+	ret = gfs2_writepage_common(page, wbc);
+	if (ret <= 0)
+		return ret;
+
+	if (!page_has_buffers(page)) {
+		create_empty_buffers(page, inode->i_sb->s_blocksize,
+				     (1 << BH_Dirty)|(1 << BH_Uptodate));
 	}
+	gfs2_page_add_databufs(ip, page, 0, inode->i_sb->s_blocksize-1);
+	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
 
-	if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) &&
-	    PageChecked(page)) {
+/**
+ * __gfs2_jdata_writepage - The core of jdata writepage
+ * @page: The page to write
+ * @wbc: The writeback control
+ *
+ * This is shared between writepage and writepages and implements the
+ * core of the writepage operation. If a transaction is required then
+ * PageChecked will have been set and the transaction will have
+ * already been started before this is called.
+ */
+
+static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	if (PageChecked(page)) {
 		ClearPageChecked(page);
-		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
-		if (error)
-			goto out_ignore;
 		if (!page_has_buffers(page)) {
 			create_empty_buffers(page, inode->i_sb->s_blocksize,
 					     (1 << BH_Dirty)|(1 << BH_Uptodate));
 		}
 		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
+	}
+	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+}
+
+/**
+ * gfs2_jdata_writepage - Write complete page
+ * @page: Page to write
+ *
+ * Returns: errno
+ *
+ */
+
+static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	int error;
+	int done_trans = 0;
+
+	error = gfs2_writepage_common(page, wbc);
+	if (error <= 0)
+		return error;
+
+	if (PageChecked(page)) {
+		if (wbc->sync_mode != WB_SYNC_ALL)
+			goto out_ignore;
+		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
+		if (error)
+			goto out_ignore;
 		done_trans = 1;
 	}
-	error = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+	error = __gfs2_jdata_writepage(page, wbc);
 	if (done_trans)
 		gfs2_trans_end(sdp);
-	gfs2_meta_cache_flush(ip);
 	return error;
 
 out_ignore:
@@ -164,29 +240,190 @@ out_ignore:
 }
 
 /**
- * gfs2_writepages - Write a bunch of dirty pages back to disk
+ * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk
  * @mapping: The mapping to write
  * @wbc: Write-back control
  *
- * For journaled files and/or ordered writes this just falls back to the
- * kernel's default writepages path for now. We will probably want to change
- * that eventually (i.e. when we look at allocate on flush).
- *
- * For the data=writeback case though we can already ignore buffer heads
+ * For the data=writeback case we can already ignore buffer heads
  * and write whole extents at once. This is a big reduction in the
  * number of I/O requests we send and the bmap calls we make in this case.
  */
-static int gfs2_writepages(struct address_space *mapping,
-			   struct writeback_control *wbc)
+static int gfs2_writeback_writepages(struct address_space *mapping,
+				     struct writeback_control *wbc)
+{
+	return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+}
+
+/**
+ * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages
+ * @mapping: The mapping
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call for each page
+ * @pvec: The vector of pages
+ * @nr_pages: The number of pages to write
+ *
+ * Returns: non-zero if loop should terminate, zero otherwise
+ */
+
+static int gfs2_write_jdata_pagevec(struct address_space *mapping,
+				    struct writeback_control *wbc,
+				    struct pagevec *pvec,
+				    int nr_pages, pgoff_t end)
 {
 	struct inode *inode = mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
+	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	int i;
+	int ret;
+
+	ret = gfs2_trans_begin(sdp, nrblocks, 0);
+	if (ret < 0)
+		return ret;
+
+	for(i = 0; i < nr_pages; i++) {
+		struct page *page = pvec->pages[i];
+
+		lock_page(page);
+
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			continue;
+		}
+
+		if (!wbc->range_cyclic && page->index > end) {
+			ret = 1;
+			unlock_page(page);
+			continue;
+		}
+
+		if (wbc->sync_mode != WB_SYNC_NONE)
+			wait_on_page_writeback(page);
+
+		if (PageWriteback(page) ||
+		    !clear_page_dirty_for_io(page)) {
+			unlock_page(page);
+			continue;
+		}
+
+		/* Is the page fully outside i_size? (truncate in progress) */
+		if (page->index > end_index || (page->index == end_index && !offset)) {
+			page->mapping->a_ops->invalidatepage(page, 0);
+			unlock_page(page);
+			continue;
+		}
+
+		ret = __gfs2_jdata_writepage(page, wbc);
+
+		if (ret || (--(wbc->nr_to_write) <= 0))
+			ret = 1;
+		if (wbc->nonblocking && bdi_write_congested(bdi)) {
+			wbc->encountered_congestion = 1;
+			ret = 1;
+		}
+
+	}
+	gfs2_trans_end(sdp);
+	return ret;
+}
+
+/**
+ * gfs2_write_cache_jdata - Like write_cache_pages but different
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * @writepage: The writepage function to call
+ * @data: The data to pass to writepage
+ *
+ * The reason that we use our own function here is that we need to
+ * start transactions before we grab page locks. This allows us
+ * to get the ordering right.
+ */
+
+static int gfs2_write_cache_jdata(struct address_space *mapping,
+				  struct writeback_control *wbc)
+{
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	int ret = 0;
+	int done = 0;
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;
+	int scanned = 0;
+	int range_whole = 0;
+
+	if (wbc->nonblocking && bdi_write_congested(bdi)) {
+		wbc->encountered_congestion = 1;
+		return 0;
+	}
+
+	pagevec_init(&pvec, 0);
+	if (wbc->range_cyclic) {
+		index = mapping->writeback_index; /* Start from prev offset */
+		end = -1;
+	} else {
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
+		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
+		scanned = 1;
+	}
 
-	if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip))
-		return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
+retry:
+	 while (!done && (index <= end) &&
+		(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+					       PAGECACHE_TAG_DIRTY,
+					       min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+		scanned = 1;
+		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
+		if (ret)
+			done = 1;
+		if (ret > 0)
+			ret = 0;
+
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+
+	if (!scanned && !done) {
+		/*
+		 * We hit the last page and there is more work to be done: wrap
+		 * back to the start of the file
+		 */
+		scanned = 1;
+		index = 0;
+		goto retry;
+	}
+
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		mapping->writeback_index = index;
+	return ret;
+}
+
+
+/**
+ * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ * 
+ */
 
-	return generic_writepages(mapping, wbc);
+static int gfs2_jdata_writepages(struct address_space *mapping,
+				 struct writeback_control *wbc)
+{
+	struct gfs2_inode *ip = GFS2_I(mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	int ret;
+
+	ret = gfs2_write_cache_jdata(mapping, wbc);
+	if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) {
+		gfs2_log_flush(sdp, ip->i_gl);
+		ret = gfs2_write_cache_jdata(mapping, wbc);
+	}
+	return ret;
 }
 
 /**
@@ -231,62 +468,107 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 
 
 /**
- * gfs2_readpage - readpage with locking
- * @file: The file to read a page for. N.B. This may be NULL if we are
- * reading an internal file.
+ * __gfs2_readpage - readpage
+ * @file: The file to read a page for
  * @page: The page to read
  *
- * Returns: errno
+ * This is the core of gfs2's readpage. Its used by the internal file
+ * reading code as in that case we already hold the glock. Also its
+ * called by gfs2_readpage() once the required lock has been granted.
+ *
  */
 
-static int gfs2_readpage(struct file *file, struct page *page)
+static int __gfs2_readpage(void *file, struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
 	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-	struct gfs2_file *gf = NULL;
-	struct gfs2_holder gh;
 	int error;
-	int do_unlock = 0;
-
-	if (likely(file != &gfs2_internal_file_sentinel)) {
-		if (file) {
-			gf = file->private_data;
-			if (test_bit(GFF_EXLOCK, &gf->f_flags))
-				/* gfs2_sharewrite_fault has grabbed the ip->i_gl already */
-				goto skip_lock;
-		}
-		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
-		do_unlock = 1;
-		error = gfs2_glock_nq_atime(&gh);
-		if (unlikely(error))
-			goto out_unlock;
-	}
 
-skip_lock:
 	if (gfs2_is_stuffed(ip)) {
 		error = stuffed_readpage(ip, page);
 		unlock_page(page);
-	} else
-		error = mpage_readpage(page, gfs2_get_block);
+	} else {
+		error = mpage_readpage(page, gfs2_block_map);
+	}
 
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
-		error = -EIO;
+		return -EIO;
+
+	return error;
+}
+
+/**
+ * gfs2_readpage - read a page of a file
+ * @file: The file to read
+ * @page: The page of the file
+ *
+ * This deals with the locking required. We use a trylock in order to
+ * avoid the page lock / glock ordering problems returning AOP_TRUNCATED_PAGE
+ * in the event that we are unable to get the lock.
+ */
+
+static int gfs2_readpage(struct file *file, struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_holder gh;
+	int error;
 
-	if (do_unlock) {
-		gfs2_glock_dq_m(1, &gh);
-		gfs2_holder_uninit(&gh);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
+	error = gfs2_glock_nq_atime(&gh);
+	if (unlikely(error)) {
+		unlock_page(page);
+		goto out;
 	}
+	error = __gfs2_readpage(file, page);
+	gfs2_glock_dq(&gh);
 out:
-	return error;
-out_unlock:
-	unlock_page(page);
+	gfs2_holder_uninit(&gh);
 	if (error == GLR_TRYFAILED) {
-		error = AOP_TRUNCATED_PAGE;
 		yield();
+		return AOP_TRUNCATED_PAGE;
 	}
-	if (do_unlock)
-		gfs2_holder_uninit(&gh);
-	goto out;
+	return error;
+}
+
+/**
+ * gfs2_internal_read - read an internal file
+ * @ip: The gfs2 inode
+ * @ra_state: The readahead state (or NULL for no readahead)
+ * @buf: The buffer to fill
+ * @pos: The file position
+ * @size: The amount to read
+ *
+ */
+
+int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
+                       char *buf, loff_t *pos, unsigned size)
+{
+	struct address_space *mapping = ip->i_inode.i_mapping;
+	unsigned long index = *pos / PAGE_CACHE_SIZE;
+	unsigned offset = *pos & (PAGE_CACHE_SIZE - 1);
+	unsigned copied = 0;
+	unsigned amt;
+	struct page *page;
+	void *p;
+
+	do {
+		amt = size - copied;
+		if (offset + size > PAGE_CACHE_SIZE)
+			amt = PAGE_CACHE_SIZE - offset;
+		page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+		p = kmap_atomic(page, KM_USER0);
+		memcpy(buf + copied, p + offset, amt);
+		kunmap_atomic(p, KM_USER0);
+		mark_page_accessed(page);
+		page_cache_release(page);
+		copied += amt;
+		index++;
+		offset = 0;
+	} while(copied < size);
+	(*pos) += size;
+	return size;
 }
 
 /**
@@ -300,10 +582,9 @@ out_unlock:
  *    Any I/O we ignore at this time will be done via readpage later.
  * 2. We don't handle stuffed files here we let readpage do the honours.
  * 3. mpage_readpages() does most of the heavy lifting in the common case.
- * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places.
- * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as
- *    well as read-ahead.
+ * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
  */
+
 static int gfs2_readpages(struct file *file, struct address_space *mapping,
 			  struct list_head *pages, unsigned nr_pages)
 {
@@ -311,42 +592,20 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_holder gh;
-	int ret = 0;
-	int do_unlock = 0;
+	int ret;
 
-	if (likely(file != &gfs2_internal_file_sentinel)) {
-		if (file) {
-			struct gfs2_file *gf = file->private_data;
-			if (test_bit(GFF_EXLOCK, &gf->f_flags))
-				goto skip_lock;
-		}
-		gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
-				 LM_FLAG_TRY_1CB|GL_ATIME, &gh);
-		do_unlock = 1;
-		ret = gfs2_glock_nq_atime(&gh);
-		if (ret == GLR_TRYFAILED)
-			goto out_noerror;
-		if (unlikely(ret))
-			goto out_unlock;
-	}
-skip_lock:
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
+	ret = gfs2_glock_nq_atime(&gh);
+	if (unlikely(ret))
+		goto out_uninit;
 	if (!gfs2_is_stuffed(ip))
-		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);
-
-	if (do_unlock) {
-		gfs2_glock_dq_m(1, &gh);
-		gfs2_holder_uninit(&gh);
-	}
-out:
+		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
 		ret = -EIO;
 	return ret;
-out_noerror:
-	ret = 0;
-out_unlock:
-	if (do_unlock)
-		gfs2_holder_uninit(&gh);
-	goto out;
 }
 
 /**
@@ -382,20 +641,11 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	if (unlikely(error))
 		goto out_uninit;
 
-	error = -ENOMEM;
-	page = __grab_cache_page(mapping, index);
-	*pagep = page;
-	if (!page)
-		goto out_unlock;
-
 	gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
-
 	error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
 	if (error)
-		goto out_putpage;
-
+		goto out_unlock;
 
-	ip->i_alloc.al_requested = 0;
 	if (alloc_required) {
 		al = gfs2_alloc_get(ip);
 
@@ -424,40 +674,47 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	if (error)
 		goto out_trans_fail;
 
+	error = -ENOMEM;
+	page = __grab_cache_page(mapping, index);
+	*pagep = page;
+	if (unlikely(!page))
+		goto out_endtrans;
+
 	if (gfs2_is_stuffed(ip)) {
+		error = 0;
 		if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
 			error = gfs2_unstuff_dinode(ip, page);
 			if (error == 0)
 				goto prepare_write;
-		} else if (!PageUptodate(page))
+		} else if (!PageUptodate(page)) {
 			error = stuffed_readpage(ip, page);
+		}
 		goto out;
 	}
 
 prepare_write:
-	error = block_prepare_write(page, from, to, gfs2_get_block);
-
+	error = block_prepare_write(page, from, to, gfs2_block_map);
 out:
-	if (error) {
-		gfs2_trans_end(sdp);
+	if (error == 0)
+		return 0;
+
+	page_cache_release(page);
+	if (pos + len > ip->i_inode.i_size)
+		vmtruncate(&ip->i_inode, ip->i_inode.i_size);
+out_endtrans:
+	gfs2_trans_end(sdp);
 out_trans_fail:
-		if (alloc_required) {
-			gfs2_inplace_release(ip);
+	if (alloc_required) {
+		gfs2_inplace_release(ip);
 out_qunlock:
-			gfs2_quota_unlock(ip);
+		gfs2_quota_unlock(ip);
 out_alloc_put:
-			gfs2_alloc_put(ip);
-		}
-out_putpage:
-		page_cache_release(page);
-		if (pos + len > ip->i_inode.i_size)
-			vmtruncate(&ip->i_inode, ip->i_inode.i_size);
+		gfs2_alloc_put(ip);
+	}
 out_unlock:
-		gfs2_glock_dq_m(1, &ip->i_gh);
+	gfs2_glock_dq(&ip->i_gh);
 out_uninit:
-		gfs2_holder_uninit(&ip->i_gh);
-	}
-
+	gfs2_holder_uninit(&ip->i_gh);
 	return error;
 }
 
@@ -565,7 +822,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *dibh;
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_dinode *di;
 	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
 	unsigned int to = from + len;
@@ -585,19 +842,16 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	if (gfs2_is_stuffed(ip))
 		return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
 
-	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
+	if (!gfs2_is_writeback(ip))
 		gfs2_page_add_databufs(ip, page, from, to);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
 
-	if (likely(ret >= 0)) {
-		copied = ret;
-		if  ((pos + copied) > inode->i_size) {
-			di = (struct gfs2_dinode *)dibh->b_data;
-			ip->i_di.di_size = inode->i_size;
-			di->di_size = cpu_to_be64(inode->i_size);
-			mark_inode_dirty(inode);
-		}
+	if (likely(ret >= 0) && (inode->i_size > ip->i_di.di_size)) {
+		di = (struct gfs2_dinode *)dibh->b_data;
+		ip->i_di.di_size = inode->i_size;
+		di->di_size = cpu_to_be64(inode->i_size);
+		mark_inode_dirty(inode);
 	}
 
 	if (inode == sdp->sd_rindex)
@@ -606,7 +860,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	brelse(dibh);
 	gfs2_trans_end(sdp);
 failed:
-	if (al->al_requested) {
+	if (al) {
 		gfs2_inplace_release(ip);
 		gfs2_quota_unlock(ip);
 		gfs2_alloc_put(ip);
@@ -625,11 +879,7 @@ failed:
  
 static int gfs2_set_page_dirty(struct page *page)
 {
-	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
-
-	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
-		SetPageChecked(page);
+	SetPageChecked(page);
 	return __set_page_dirty_buffers(page);
 }
 
@@ -653,7 +903,7 @@ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
 		return 0;
 
 	if (!gfs2_is_stuffed(ip))
-		dblock = generic_block_bmap(mapping, lblock, gfs2_get_block);
+		dblock = generic_block_bmap(mapping, lblock, gfs2_block_map);
 
 	gfs2_glock_dq_uninit(&i_gh);
 
@@ -719,13 +969,9 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
 {
 	/*
 	 * Should we return an error here? I can't see that O_DIRECT for
-	 * a journaled file makes any sense. For now we'll silently fall
-	 * back to buffered I/O, likewise we do the same for stuffed
-	 * files since they are (a) small and (b) unaligned.
+	 * a stuffed file makes any sense. For now we'll silently fall
+	 * back to buffered I/O
 	 */
-	if (gfs2_is_jdata(ip))
-		return 0;
-
 	if (gfs2_is_stuffed(ip))
 		return 0;
 
@@ -836,9 +1082,23 @@ cannot_release:
 	return 0;
 }
 
-const struct address_space_operations gfs2_file_aops = {
-	.writepage = gfs2_writepage,
-	.writepages = gfs2_writepages,
+static const struct address_space_operations gfs2_writeback_aops = {
+	.writepage = gfs2_writeback_writepage,
+	.writepages = gfs2_writeback_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+	.direct_IO = gfs2_direct_IO,
+	.migratepage = buffer_migrate_page,
+};
+
+static const struct address_space_operations gfs2_ordered_aops = {
+	.writepage = gfs2_ordered_writepage,
 	.readpage = gfs2_readpage,
 	.readpages = gfs2_readpages,
 	.sync_page = block_sync_page,
@@ -849,5 +1109,34 @@ const struct address_space_operations gfs2_file_aops = {
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
 	.direct_IO = gfs2_direct_IO,
+	.migratepage = buffer_migrate_page,
 };
 
+static const struct address_space_operations gfs2_jdata_aops = {
+	.writepage = gfs2_jdata_writepage,
+	.writepages = gfs2_jdata_writepages,
+	.readpage = gfs2_readpage,
+	.readpages = gfs2_readpages,
+	.sync_page = block_sync_page,
+	.write_begin = gfs2_write_begin,
+	.write_end = gfs2_write_end,
+	.set_page_dirty = gfs2_set_page_dirty,
+	.bmap = gfs2_bmap,
+	.invalidatepage = gfs2_invalidatepage,
+	.releasepage = gfs2_releasepage,
+};
+
+void gfs2_set_aops(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (gfs2_is_writeback(ip))
+		inode->i_mapping->a_ops = &gfs2_writeback_aops;
+	else if (gfs2_is_ordered(ip))
+		inode->i_mapping->a_ops = &gfs2_ordered_aops;
+	else if (gfs2_is_jdata(ip))
+		inode->i_mapping->a_ops = &gfs2_jdata_aops;
+	else
+		BUG();
+}
+

fs/gfs2/ops_address.h

@@ -14,9 +14,10 @@
 #include <linux/buffer_head.h>
 #include <linux/mm.h>
 
-extern const struct address_space_operations gfs2_file_aops;
-extern int gfs2_get_block(struct inode *inode, sector_t lblock,
-			  struct buffer_head *bh_result, int create);
 extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      struct file_ra_state *ra_state,
+			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_set_aops(struct inode *inode);
 
 #endif /* __OPS_ADDRESS_DOT_H__ */

fs/gfs2/ops_file.c

@@ -33,57 +33,12 @@
 #include "lm.h"
 #include "log.h"
 #include "meta_io.h"
-#include "ops_file.h"
-#include "ops_vm.h"
 #include "quota.h"
 #include "rgrp.h"
 #include "trans.h"
 #include "util.h"
 #include "eaops.h"
-
-/*
- * Most fields left uninitialised to catch anybody who tries to
- * use them. f_flags set to prevent file_accessed() from touching
- * any other part of this. Its use is purely as a flag so that we
- * know (in readpage()) whether or not do to locking.
- */
-struct file gfs2_internal_file_sentinel = {
-	.f_flags = O_NOATIME|O_RDONLY,
-};
-
-static int gfs2_read_actor(read_descriptor_t *desc, struct page *page,
-			   unsigned long offset, unsigned long size)
-{
-	char *kaddr;
-	unsigned long count = desc->count;
-
-	if (size > count)
-		size = count;
-
-	kaddr = kmap(page);
-	memcpy(desc->arg.data, kaddr + offset, size);
-	kunmap(page);
-
-	desc->count = count - size;
-	desc->written += size;
-	desc->arg.buf += size;
-	return size;
-}
-
-int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
-		       char *buf, loff_t *pos, unsigned size)
-{
-	struct inode *inode = &ip->i_inode;
-	read_descriptor_t desc;
-	desc.written = 0;
-	desc.arg.data = buf;
-	desc.count = size;
-	desc.error = 0;
-	do_generic_mapping_read(inode->i_mapping, ra_state,
-				&gfs2_internal_file_sentinel, pos, &desc,
-				gfs2_read_actor);
-	return desc.written ? desc.written : desc.error;
-}
+#include "ops_address.h"
 
 /**
  * gfs2_llseek - seek to a location in a file
@@ -214,7 +169,7 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
 	if (put_user(fsflags, ptr))
 		error = -EFAULT;
 
-	gfs2_glock_dq_m(1, &gh);
+	gfs2_glock_dq(&gh);
 	gfs2_holder_uninit(&gh);
 	return error;
 }
@@ -291,7 +246,16 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
 		if (error)
 			goto out;
 	}
-
+	if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
+		if (flags & GFS2_DIF_JDATA)
+			gfs2_log_flush(sdp, ip->i_gl);
+		error = filemap_fdatawrite(inode->i_mapping);
+		if (error)
+			goto out;
+		error = filemap_fdatawait(inode->i_mapping);
+		if (error)
+			goto out;
+	}
 	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
 	if (error)
 		goto out;
@@ -303,6 +267,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
 	gfs2_dinode_out(ip, bh->b_data);
 	brelse(bh);
 	gfs2_set_inode_flags(inode);
+	gfs2_set_aops(inode);
 out_trans_end:
 	gfs2_trans_end(sdp);
 out:
@@ -338,6 +303,128 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	return -ENOTTY;
 }
 
+/**
+ * gfs2_allocate_page_backing - Use bmap to allocate blocks
+ * @page: The (locked) page to allocate backing for
+ *
+ * We try to allocate all the blocks required for the page in
+ * one go. This might fail for various reasons, so we keep
+ * trying until all the blocks to back this page are allocated.
+ * If some of the blocks are already allocated, thats ok too.
+ */
+
+static int gfs2_allocate_page_backing(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct buffer_head bh;
+	unsigned long size = PAGE_CACHE_SIZE;
+	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+	do {
+		bh.b_state = 0;
+		bh.b_size = size;
+		gfs2_block_map(inode, lblock, &bh, 1);
+		if (!buffer_mapped(&bh))
+			return -EIO;
+		size -= bh.b_size;
+		lblock += (bh.b_size >> inode->i_blkbits);
+	} while(size > 0);
+	return 0;
+}
+
+/**
+ * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
+ * @vma: The virtual memory area
+ * @page: The page which is about to become writable
+ *
+ * When the page becomes writable, we need to ensure that we have
+ * blocks allocated on disk to back that page.
+ */
+
+static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+{
+	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	unsigned long last_index;
+	u64 pos = page->index << (PAGE_CACHE_SIZE - inode->i_blkbits);
+	unsigned int data_blocks, ind_blocks, rblocks;
+	int alloc_required = 0;
+	struct gfs2_holder gh;
+	struct gfs2_alloc *al;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &gh);
+	ret = gfs2_glock_nq_atime(&gh);
+	if (ret)
+		goto out;
+
+	set_bit(GIF_SW_PAGED, &ip->i_flags);
+	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
+	ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
+	if (ret || !alloc_required)
+		goto out_unlock;
+	ret = -ENOMEM;
+	al = gfs2_alloc_get(ip);
+	if (al == NULL)
+		goto out_unlock;
+
+	ret = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (ret)
+		goto out_alloc_put;
+	ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
+	if (ret)
+		goto out_quota_unlock;
+	al->al_requested = data_blocks + ind_blocks;
+	ret = gfs2_inplace_reserve(ip);
+	if (ret)
+		goto out_quota_unlock;
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+	ret = gfs2_trans_begin(sdp, rblocks, 0);
+	if (ret)
+		goto out_trans_fail;
+
+	lock_page(page);
+	ret = -EINVAL;
+	last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
+	if (page->index > last_index)
+		goto out_unlock_page;
+	ret = 0;
+	if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
+		goto out_unlock_page;
+	if (gfs2_is_stuffed(ip)) {
+		ret = gfs2_unstuff_dinode(ip, page);
+		if (ret)
+			goto out_unlock_page;
+	}
+	ret = gfs2_allocate_page_backing(page);
+
+out_unlock_page:
+	unlock_page(page);
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_quota_unlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&gh);
+out:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static struct vm_operations_struct gfs2_vm_ops = {
+	.fault = filemap_fault,
+	.page_mkwrite = gfs2_page_mkwrite,
+};
+
 
 /**
  * gfs2_mmap -
@@ -360,14 +447,7 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 		return error;
 	}
 
-	/* This is VM_MAYWRITE instead of VM_WRITE because a call
-	   to mprotect() can turn on VM_WRITE later. */
-
-	if ((vma->vm_flags & (VM_MAYSHARE | VM_MAYWRITE)) ==
-	    (VM_MAYSHARE | VM_MAYWRITE))
-		vma->vm_ops = &gfs2_vm_ops_sharewrite;
-	else
-		vma->vm_ops = &gfs2_vm_ops_private;
+	vma->vm_ops = &gfs2_vm_ops;
 
 	gfs2_glock_dq_uninit(&i_gh);
 
@@ -538,15 +618,6 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 	if (__mandatory_lock(&ip->i_inode))
 		return -ENOLCK;
 
-	if (sdp->sd_args.ar_localflocks) {
-		if (IS_GETLK(cmd)) {
-			posix_test_lock(file, fl);
-			return 0;
-		} else {
-			return posix_lock_file_wait(file, fl);
-		}
-	}
-
 	if (cmd == F_CANCELLK) {
 		/* Hack: */
 		cmd = F_SETLK;
@@ -632,16 +703,12 @@ static void do_unflock(struct file *file, struct file_lock *fl)
 static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 {
 	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
 
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 	if (__mandatory_lock(&ip->i_inode))
 		return -ENOLCK;
 
-	if (sdp->sd_args.ar_localflocks)
-		return flock_lock_file_wait(file, fl);
-
 	if (fl->fl_type == F_UNLCK) {
 		do_unflock(file, fl);
 		return 0;
@@ -678,3 +745,27 @@ const struct file_operations gfs2_dir_fops = {
 	.flock		= gfs2_flock,
 };
 
+const struct file_operations gfs2_file_fops_nolock = {
+	.llseek		= gfs2_llseek,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.mmap		= gfs2_mmap,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+	.setlease	= gfs2_setlease,
+};
+
+const struct file_operations gfs2_dir_fops_nolock = {
+	.readdir	= gfs2_readdir,
+	.unlocked_ioctl	= gfs2_ioctl,
+	.open		= gfs2_open,
+	.release	= gfs2_close,
+	.fsync		= gfs2_fsync,
+};
+

fs/gfs2/ops_file.h

@@ -1,24 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#ifndef __OPS_FILE_DOT_H__
-#define __OPS_FILE_DOT_H__
-
-#include <linux/fs.h>
-struct gfs2_inode;
-
-extern struct file gfs2_internal_file_sentinel;
-extern int gfs2_internal_read(struct gfs2_inode *ip,
-			      struct file_ra_state *ra_state,
-			      char *buf, loff_t *pos, unsigned size);
-extern void gfs2_set_inode_flags(struct inode *inode);
-extern const struct file_operations gfs2_file_fops;
-extern const struct file_operations gfs2_dir_fops;
-
-#endif /* __OPS_FILE_DOT_H__ */

fs/gfs2/ops_fstype.c

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -21,6 +21,7 @@
 
 #include "gfs2.h"
 #include "incore.h"
+#include "bmap.h"
 #include "daemon.h"
 #include "glock.h"
 #include "glops.h"
@@ -59,7 +60,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	mutex_init(&sdp->sd_inum_mutex);
 	spin_lock_init(&sdp->sd_statfs_spin);
-	mutex_init(&sdp->sd_statfs_mutex);
 
 	spin_lock_init(&sdp->sd_rindex_spin);
 	mutex_init(&sdp->sd_rindex_mutex);
@@ -77,7 +77,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	spin_lock_init(&sdp->sd_log_lock);
 
-	INIT_LIST_HEAD(&sdp->sd_log_le_gl);
 	INIT_LIST_HEAD(&sdp->sd_log_le_buf);
 	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
 	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
@@ -303,6 +302,67 @@ out:
 	return error;
 }
 
+/**
+ * map_journal_extents - create a reusable "extent" mapping from all logical
+ * blocks to all physical blocks for the given journal.  This will save
+ * us time when writing journal blocks.  Most journals will have only one
+ * extent that maps all their logical blocks.  That's because gfs2.mkfs
+ * arranges the journal blocks sequentially to maximize performance.
+ * So the extent would map the first block for the entire file length.
+ * However, gfs2_jadd can happen while file activity is happening, so
+ * those journals may not be sequential.  Less likely is the case where
+ * the users created their own journals by mounting the metafs and
+ * laying it out.  But it's still possible.  These journals might have
+ * several extents.
+ *
+ * TODO: This should be done in bigger chunks rather than one block at a time,
+ *       but since it's only done at mount time, I'm not worried about the
+ *       time it takes.
+ */
+static int map_journal_extents(struct gfs2_sbd *sdp)
+{
+	struct gfs2_jdesc *jd = sdp->sd_jdesc;
+	unsigned int lb;
+	u64 db, prev_db; /* logical block, disk block, prev disk block */
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct gfs2_journal_extent *jext = NULL;
+	struct buffer_head bh;
+	int rc = 0;
+
+	prev_db = 0;
+
+	for (lb = 0; lb < ip->i_di.di_size >> sdp->sd_sb.sb_bsize_shift; lb++) {
+		bh.b_state = 0;
+		bh.b_blocknr = 0;
+		bh.b_size = 1 << ip->i_inode.i_blkbits;
+		rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
+		db = bh.b_blocknr;
+		if (rc || !db) {
+			printk(KERN_INFO "GFS2 journal mapping error %d: lb="
+			       "%u db=%llu\n", rc, lb, (unsigned long long)db);
+			break;
+		}
+		if (!prev_db || db != prev_db + 1) {
+			jext = kzalloc(sizeof(struct gfs2_journal_extent),
+				       GFP_KERNEL);
+			if (!jext) {
+				printk(KERN_INFO "GFS2 error: out of memory "
+				       "mapping journal extents.\n");
+				rc = -ENOMEM;
+				break;
+			}
+			jext->dblock = db;
+			jext->lblock = lb;
+			jext->blocks = 1;
+			list_add_tail(&jext->extent_list, &jd->extent_list);
+		} else {
+			jext->blocks++;
+		}
+		prev_db = db;
+	}
+	return rc;
+}
+
 static int init_journal(struct gfs2_sbd *sdp, int undo)
 {
 	struct gfs2_holder ji_gh;
@@ -340,7 +400,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 
 	if (sdp->sd_args.ar_spectator) {
 		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
-		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
 	} else {
 		if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
 			fs_err(sdp, "can't mount journal #%u\n",
@@ -377,7 +437,10 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 			       sdp->sd_jdesc->jd_jid, error);
 			goto fail_jinode_gh;
 		}
-		sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+
+		/* Map the extents for this journal's blocks */
+		map_journal_extents(sdp);
 	}
 
 	if (sdp->sd_lockstruct.ls_first) {

fs/gfs2/ops_inode.c

@@ -61,7 +61,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		inode = gfs2_createi(ghs, &dentry->d_name, S_IFREG | mode, 0);
 		if (!IS_ERR(inode)) {
 			gfs2_trans_end(sdp);
-			if (dip->i_alloc.al_rgd)
+			if (dip->i_alloc->al_rgd)
 				gfs2_inplace_release(dip);
 			gfs2_quota_unlock(dip);
 			gfs2_alloc_put(dip);
@@ -113,8 +113,18 @@ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 	if (inode && IS_ERR(inode))
 		return ERR_PTR(PTR_ERR(inode));
 
-	if (inode)
+	if (inode) {
+		struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
+		struct gfs2_holder gh;
+		int error;
+		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+		if (error) {
+			iput(inode);
+			return ERR_PTR(error);
+		}
+		gfs2_glock_dq_uninit(&gh);
 		return d_splice_alias(inode, dentry);
+	}
 	d_add(dentry, inode);
 
 	return NULL;
@@ -366,7 +376,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	}
 
 	gfs2_trans_end(sdp);
-	if (dip->i_alloc.al_rgd)
+	if (dip->i_alloc->al_rgd)
 		gfs2_inplace_release(dip);
 	gfs2_quota_unlock(dip);
 	gfs2_alloc_put(dip);
@@ -442,7 +452,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	gfs2_assert_withdraw(sdp, !error); /* dip already pinned */
 
 	gfs2_trans_end(sdp);
-	if (dip->i_alloc.al_rgd)
+	if (dip->i_alloc->al_rgd)
 		gfs2_inplace_release(dip);
 	gfs2_quota_unlock(dip);
 	gfs2_alloc_put(dip);
@@ -548,7 +558,7 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
 	}
 
 	gfs2_trans_end(sdp);
-	if (dip->i_alloc.al_rgd)
+	if (dip->i_alloc->al_rgd)
 		gfs2_inplace_release(dip);
 	gfs2_quota_unlock(dip);
 	gfs2_alloc_put(dip);

fs/gfs2/ops_inode.h

@@ -16,5 +16,11 @@ 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 inode_operations gfs2_dev_iops;
+extern const struct file_operations gfs2_file_fops;
+extern const struct file_operations gfs2_dir_fops;
+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);
 
 #endif /* __OPS_INODE_DOT_H__ */

fs/gfs2/ops_super.c

@@ -487,7 +487,6 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (ip) {
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
-		ip->i_last_pfault = jiffies;
 	}
 	return &ip->i_inode;
 }

fs/gfs2/ops_vm.c

@@ -1,169 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/lm_interface.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "bmap.h"
-#include "glock.h"
-#include "inode.h"
-#include "ops_vm.h"
-#include "quota.h"
-#include "rgrp.h"
-#include "trans.h"
-#include "util.h"
-
-static int gfs2_private_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct gfs2_inode *ip = GFS2_I(vma->vm_file->f_mapping->host);
-
-	set_bit(GIF_PAGED, &ip->i_flags);
-	return filemap_fault(vma, vmf);
-}
-
-static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned long index = page->index;
-	u64 lblock = index << (PAGE_CACHE_SHIFT -
-				    sdp->sd_sb.sb_bsize_shift);
-	unsigned int blocks = PAGE_CACHE_SIZE >> sdp->sd_sb.sb_bsize_shift;
-	struct gfs2_alloc *al;
-	unsigned int data_blocks, ind_blocks;
-	unsigned int x;
-	int error;
-
-	al = gfs2_alloc_get(ip);
-
-	error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
-	if (error)
-		goto out;
-
-	error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
-	if (error)
-		goto out_gunlock_q;
-
-	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
-
-	al->al_requested = data_blocks + ind_blocks;
-
-	error = gfs2_inplace_reserve(ip);
-	if (error)
-		goto out_gunlock_q;
-
-	error = gfs2_trans_begin(sdp, al->al_rgd->rd_length +
-				 ind_blocks + RES_DINODE +
-				 RES_STATFS + RES_QUOTA, 0);
-	if (error)
-		goto out_ipres;
-
-	if (gfs2_is_stuffed(ip)) {
-		error = gfs2_unstuff_dinode(ip, NULL);
-		if (error)
-			goto out_trans;
-	}
-
-	for (x = 0; x < blocks; ) {
-		u64 dblock;
-		unsigned int extlen;
-		int new = 1;
-
-		error = gfs2_extent_map(&ip->i_inode, lblock, &new, &dblock, &extlen);
-		if (error)
-			goto out_trans;
-
-		lblock += extlen;
-		x += extlen;
-	}
-
-	gfs2_assert_warn(sdp, al->al_alloced);
-
-out_trans:
-	gfs2_trans_end(sdp);
-out_ipres:
-	gfs2_inplace_release(ip);
-out_gunlock_q:
-	gfs2_quota_unlock(ip);
-out:
-	gfs2_alloc_put(ip);
-	return error;
-}
-
-static int gfs2_sharewrite_fault(struct vm_area_struct *vma,
-						struct vm_fault *vmf)
-{
-	struct file *file = vma->vm_file;
-	struct gfs2_file *gf = file->private_data;
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_holder i_gh;
-	int alloc_required;
-	int error;
-	int ret = 0;
-
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
-	if (error)
-		goto out;
-
-	set_bit(GIF_PAGED, &ip->i_flags);
-	set_bit(GIF_SW_PAGED, &ip->i_flags);
-
-	error = gfs2_write_alloc_required(ip,
-					(u64)vmf->pgoff << PAGE_CACHE_SHIFT,
-					PAGE_CACHE_SIZE, &alloc_required);
-	if (error) {
-		ret = VM_FAULT_OOM; /* XXX: are these right? */
-		goto out_unlock;
-	}
-
-	set_bit(GFF_EXLOCK, &gf->f_flags);
-	ret = filemap_fault(vma, vmf);
-	clear_bit(GFF_EXLOCK, &gf->f_flags);
-	if (ret & VM_FAULT_ERROR)
-		goto out_unlock;
-
-	if (alloc_required) {
-		/* XXX: do we need to drop page lock around alloc_page_backing?*/
-		error = alloc_page_backing(ip, vmf->page);
-		if (error) {
-			/*
-			 * VM_FAULT_LOCKED should always be the case for
-			 * filemap_fault, but it may not be in a future
-			 * implementation.
-			 */
-			if (ret & VM_FAULT_LOCKED)
-				unlock_page(vmf->page);
-			page_cache_release(vmf->page);
-			ret = VM_FAULT_OOM;
-			goto out_unlock;
-		}
-		set_page_dirty(vmf->page);
-	}
-
-out_unlock:
-	gfs2_glock_dq_uninit(&i_gh);
-out:
-	return ret;
-}
-
-struct vm_operations_struct gfs2_vm_ops_private = {
-	.fault = gfs2_private_fault,
-};
-
-struct vm_operations_struct gfs2_vm_ops_sharewrite = {
-	.fault = gfs2_sharewrite_fault,
-};
-

fs/gfs2/ops_vm.h

@@ -1,18 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#ifndef __OPS_VM_DOT_H__
-#define __OPS_VM_DOT_H__
-
-#include <linux/mm.h>
-
-extern struct vm_operations_struct gfs2_vm_ops_private;
-extern struct vm_operations_struct gfs2_vm_ops_sharewrite;
-
-#endif /* __OPS_VM_DOT_H__ */

fs/gfs2/quota.c

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -59,7 +59,6 @@
 #include "super.h"
 #include "trans.h"
 #include "inode.h"
-#include "ops_file.h"
 #include "ops_address.h"
 #include "util.h"
 
@@ -274,10 +273,10 @@ static int bh_get(struct gfs2_quota_data *qd)
 	}
 
 	block = qd->qd_slot / sdp->sd_qc_per_block;
-	offset = qd->qd_slot % sdp->sd_qc_per_block;;
+	offset = qd->qd_slot % sdp->sd_qc_per_block;
 
 	bh_map.b_size = 1 << ip->i_inode.i_blkbits;
-	error = gfs2_block_map(&ip->i_inode, block, 0, &bh_map);
+	error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
 	if (error)
 		goto fail;
 	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh);
@@ -454,7 +453,7 @@ static void qdsb_put(struct gfs2_quota_data *qd)
 int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_quota_data **qd = al->al_qd;
 	int error;
 
@@ -502,7 +501,7 @@ out:
 void gfs2_quota_unhold(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	unsigned int x;
 
 	gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
@@ -646,7 +645,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	}
 
 	if (!buffer_mapped(bh)) {
-		gfs2_get_block(inode, iblock, bh, 1);
+		gfs2_block_map(inode, iblock, bh, 1);
 		if (!buffer_mapped(bh))
 			goto unlock;
 	}
@@ -793,11 +792,9 @@ static int do_glock(struct gfs2_quota_data *qd, int force_refresh,
 	struct gfs2_holder i_gh;
 	struct gfs2_quota_host q;
 	char buf[sizeof(struct gfs2_quota)];
-	struct file_ra_state ra_state;
 	int error;
 	struct gfs2_quota_lvb *qlvb;
 
-	file_ra_state_init(&ra_state, sdp->sd_quota_inode->i_mapping);
 restart:
 	error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh);
 	if (error)
@@ -820,8 +817,8 @@ restart:
 
 		memset(buf, 0, sizeof(struct gfs2_quota));
 		pos = qd2offset(qd);
-		error = gfs2_internal_read(ip, &ra_state, buf,
-					   &pos, sizeof(struct gfs2_quota));
+		error = gfs2_internal_read(ip, NULL, buf, &pos,
+					   sizeof(struct gfs2_quota));
 		if (error < 0)
 			goto fail_gunlock;
 
@@ -856,7 +853,7 @@ fail:
 int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	unsigned int x;
 	int error = 0;
 
@@ -924,7 +921,7 @@ static int need_sync(struct gfs2_quota_data *qd)
 
 void gfs2_quota_unlock(struct gfs2_inode *ip)
 {
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_quota_data *qda[4];
 	unsigned int count = 0;
 	unsigned int x;
@@ -972,7 +969,7 @@ static int print_message(struct gfs2_quota_data *qd, char *type)
 int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_quota_data *qd;
 	s64 value;
 	unsigned int x;
@@ -1016,10 +1013,9 @@ int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid)
 void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 		       u32 uid, u32 gid)
 {
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_quota_data *qd;
 	unsigned int x;
-	unsigned int found = 0;
 
 	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
 		return;
@@ -1032,7 +1028,6 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 		if ((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
 		    (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))) {
 			do_qc(qd, change);
-			found++;
 		}
 	}
 }

fs/gfs2/recovery.c

@@ -391,7 +391,7 @@ static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *hea
 	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, 0, &bh_map);
+	error = gfs2_block_map(&ip->i_inode, lblock, &bh_map, 0);
 	if (error)
 		return error;
 	if (!bh_map.b_blocknr) {
@@ -504,13 +504,21 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
 			if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
 				ro = 1;
 		} else {
-			if (sdp->sd_vfs->s_flags & MS_RDONLY)
-				ro = 1;
+			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 FS\n",
-				jd->jd_jid);
+			fs_warn(sdp, "jid=%u: Can't replay: read-only block "
+				"device\n", jd->jd_jid);
 			error = -EROFS;
 			goto fail_gunlock_tr;
 		}

fs/gfs2/rgrp.c

@@ -25,10 +25,10 @@
 #include "rgrp.h"
 #include "super.h"
 #include "trans.h"
-#include "ops_file.h"
 #include "util.h"
 #include "log.h"
 #include "inode.h"
+#include "ops_address.h"
 
 #define BFITNOENT ((u32)~0)
 #define NO_BLOCK ((u64)~0)
@@ -126,41 +126,43 @@ static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
  * Return: the block number (bitmap buffer scope) that was found
  */
 
-static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
-			    unsigned int buflen, u32 goal,
-			    unsigned char old_state)
+static u32 gfs2_bitfit(unsigned char *buffer, unsigned int buflen, u32 goal,
+		       unsigned char old_state)
 {
-	unsigned char *byte, *end, alloc;
+	unsigned char *byte;
 	u32 blk = goal;
-	unsigned int bit;
+	unsigned int bit, bitlong;
+	unsigned long *plong, plong55;
 
 	byte = buffer + (goal / GFS2_NBBY);
+	plong = (unsigned long *)(buffer + (goal / GFS2_NBBY));
 	bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE;
-	end = buffer + buflen;
-	alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0;
-
-	while (byte < end) {
-		/* If we're looking for a free block we can eliminate all
-		   bitmap settings with 0x55, which represents four data
-		   blocks in a row.  If we're looking for a data block, we can
-		   eliminate 0x00 which corresponds to four free blocks. */
-		if ((*byte & 0x55) == alloc) {
-			blk += (8 - bit) >> 1;
-
-			bit = 0;
-			byte++;
-
+	bitlong = bit;
+#if BITS_PER_LONG == 32
+	plong55 = 0x55555555;
+#else
+	plong55 = 0x5555555555555555;
+#endif
+	while (byte < buffer + buflen) {
+
+		if (bitlong == 0 && old_state == 0 && *plong == plong55) {
+			plong++;
+			byte += sizeof(unsigned long);
+			blk += sizeof(unsigned long) * GFS2_NBBY;
 			continue;
 		}
-
 		if (((*byte >> bit) & GFS2_BIT_MASK) == old_state)
 			return blk;
-
 		bit += GFS2_BIT_SIZE;
 		if (bit >= 8) {
 			bit = 0;
 			byte++;
 		}
+		bitlong += GFS2_BIT_SIZE;
+		if (bitlong >= sizeof(unsigned long) * 8) {
+			bitlong = 0;
+			plong++;
+		}
 
 		blk++;
 	}
@@ -817,11 +819,9 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
 
 struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
 {
-	struct gfs2_alloc *al = &ip->i_alloc;
-
-	/* FIXME: Should assert that the correct locks are held here... */
-	memset(al, 0, sizeof(*al));
-	return al;
+	BUG_ON(ip->i_alloc != NULL);
+	ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_KERNEL);
+	return ip->i_alloc;
 }
 
 /**
@@ -1059,26 +1059,34 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 	struct inode *inode = NULL;
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *rgd, *begin = NULL;
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	int flags = LM_FLAG_TRY;
 	int skipped = 0;
 	int loops = 0;
-	int error;
+	int error, rg_locked;
 
 	/* Try recently successful rgrps */
 
 	rgd = recent_rgrp_first(sdp, ip->i_last_rg_alloc);
 
 	while (rgd) {
-		error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
-					   LM_FLAG_TRY, &al->al_rgd_gh);
+		rg_locked = 0;
+
+		if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) {
+			rg_locked = 1;
+			error = 0;
+		} else {
+			error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+						   LM_FLAG_TRY, &al->al_rgd_gh);
+		}
 		switch (error) {
 		case 0:
 			if (try_rgrp_fit(rgd, al))
 				goto out;
 			if (rgd->rd_flags & GFS2_RDF_CHECK)
 				inode = try_rgrp_unlink(rgd, last_unlinked);
-			gfs2_glock_dq_uninit(&al->al_rgd_gh);
+			if (!rg_locked)
+				gfs2_glock_dq_uninit(&al->al_rgd_gh);
 			if (inode)
 				return inode;
 			rgd = recent_rgrp_next(rgd, 1);
@@ -1098,15 +1106,23 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 	begin = rgd = forward_rgrp_get(sdp);
 
 	for (;;) {
-		error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags,
-					  &al->al_rgd_gh);
+		rg_locked = 0;
+
+		if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) {
+			rg_locked = 1;
+			error = 0;
+		} else {
+			error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags,
+						   &al->al_rgd_gh);
+		}
 		switch (error) {
 		case 0:
 			if (try_rgrp_fit(rgd, al))
 				goto out;
 			if (rgd->rd_flags & GFS2_RDF_CHECK)
 				inode = try_rgrp_unlink(rgd, last_unlinked);
-			gfs2_glock_dq_uninit(&al->al_rgd_gh);
+			if (!rg_locked)
+				gfs2_glock_dq_uninit(&al->al_rgd_gh);
 			if (inode)
 				return inode;
 			break;
@@ -1158,7 +1174,7 @@ out:
 int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct inode *inode;
 	int error = 0;
 	u64 last_unlinked = NO_BLOCK;
@@ -1204,7 +1220,7 @@ try_again:
 void gfs2_inplace_release(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 
 	if (gfs2_assert_warn(sdp, al->al_alloced <= al->al_requested) == -1)
 		fs_warn(sdp, "al_alloced = %u, al_requested = %u "
@@ -1213,7 +1229,8 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
 			     al->al_line);
 
 	al->al_rgd = NULL;
-	gfs2_glock_dq_uninit(&al->al_rgd_gh);
+	if (al->al_rgd_gh.gh_gl)
+		gfs2_glock_dq_uninit(&al->al_rgd_gh);
 	if (ip != GFS2_I(sdp->sd_rindex))
 		gfs2_glock_dq_uninit(&al->al_ri_gh);
 }
@@ -1301,11 +1318,10 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
 		   bitmaps, so we must search the originals for that. */
 		if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone)
-			blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset,
+			blk = gfs2_bitfit(bi->bi_clone + bi->bi_offset,
 					  bi->bi_len, goal, old_state);
 		else
-			blk = gfs2_bitfit(rgd,
-					  bi->bi_bh->b_data + bi->bi_offset,
+			blk = gfs2_bitfit(bi->bi_bh->b_data + bi->bi_offset,
 					  bi->bi_len, goal, old_state);
 		if (blk != BFITNOENT)
 			break;
@@ -1394,7 +1410,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
 u64 gfs2_alloc_data(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_rgrpd *rgd = al->al_rgd;
 	u32 goal, blk;
 	u64 block;
@@ -1439,7 +1455,7 @@ u64 gfs2_alloc_data(struct gfs2_inode *ip)
 u64 gfs2_alloc_meta(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al = &ip->i_alloc;
+	struct gfs2_alloc *al = ip->i_alloc;
 	struct gfs2_rgrpd *rgd = al->al_rgd;
 	u32 goal, blk;
 	u64 block;
@@ -1485,7 +1501,7 @@ u64 gfs2_alloc_meta(struct gfs2_inode *ip)
 u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
-	struct gfs2_alloc *al = &dip->i_alloc;
+	struct gfs2_alloc *al = dip->i_alloc;
 	struct gfs2_rgrpd *rgd = al->al_rgd;
 	u32 blk;
 	u64 block;

fs/gfs2/rgrp.h

@@ -32,7 +32,9 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
 struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
 static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 {
-	return; /* So we can see where ip->i_alloc is used */
+	BUG_ON(ip->i_alloc == NULL);
+	kfree(ip->i_alloc);
+	ip->i_alloc = NULL;
 }
 
 int gfs2_inplace_reserve_i(struct gfs2_inode *ip,

fs/gfs2/super.c

@@ -1,6 +1,6 @@
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  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
@@ -51,13 +51,9 @@ void gfs2_tune_init(struct gfs2_tune *gt)
 {
 	spin_lock_init(&gt->gt_spin);
 
-	gt->gt_ilimit = 100;
-	gt->gt_ilimit_tries = 3;
-	gt->gt_ilimit_min = 1;
 	gt->gt_demote_secs = 300;
 	gt->gt_incore_log_blocks = 1024;
 	gt->gt_log_flush_secs = 60;
-	gt->gt_jindex_refresh_secs = 60;
 	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quotad_secs = 5;
@@ -71,10 +67,8 @@ void gfs2_tune_init(struct gfs2_tune *gt)
 	gt->gt_new_files_jdata = 0;
 	gt->gt_new_files_directio = 0;
 	gt->gt_max_readahead = 1 << 18;
-	gt->gt_lockdump_size = 131072;
 	gt->gt_stall_secs = 600;
 	gt->gt_complain_secs = 10;
-	gt->gt_reclaim_limit = 5000;
 	gt->gt_statfs_quantum = 30;
 	gt->gt_statfs_slow = 0;
 }
@@ -393,6 +387,7 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 		if (!jd)
 			break;
 
+		INIT_LIST_HEAD(&jd->extent_list);
 		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1, NULL);
 		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
 			if (!jd->jd_inode)
@@ -422,8 +417,9 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 
 void gfs2_jindex_free(struct gfs2_sbd *sdp)
 {
-	struct list_head list;
+	struct list_head list, *head;
 	struct gfs2_jdesc *jd;
+	struct gfs2_journal_extent *jext;
 
 	spin_lock(&sdp->sd_jindex_spin);
 	list_add(&list, &sdp->sd_jindex_list);
@@ -433,6 +429,14 @@ void gfs2_jindex_free(struct gfs2_sbd *sdp)
 
 	while (!list_empty(&list)) {
 		jd = list_entry(list.next, struct gfs2_jdesc, jd_list);
+		head = &jd->extent_list;
+		while (!list_empty(head)) {
+			jext = list_entry(head->next,
+					  struct gfs2_journal_extent,
+					  extent_list);
+			list_del(&jext->extent_list);
+			kfree(jext);
+		}
 		list_del(&jd->jd_list);
 		iput(jd->jd_inode);
 		kfree(jd);
@@ -543,7 +547,6 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	if (error)
 		return error;
 
-	gfs2_meta_cache_flush(ip);
 	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 
 	error = gfs2_find_jhead(sdp->sd_jdesc, &head);
@@ -686,9 +689,7 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
 	if (error)
 		return;
 
-	mutex_lock(&sdp->sd_statfs_mutex);
 	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
-	mutex_unlock(&sdp->sd_statfs_mutex);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	l_sc->sc_total += total;
@@ -736,9 +737,7 @@ int gfs2_statfs_sync(struct gfs2_sbd *sdp)
 	if (error)
 		goto out_bh2;
 
-	mutex_lock(&sdp->sd_statfs_mutex);
 	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
-	mutex_unlock(&sdp->sd_statfs_mutex);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	m_sc->sc_total += l_sc->sc_total;

fs/gfs2/sys.c

@@ -32,7 +32,8 @@ spinlock_t gfs2_sys_margs_lock;
 
 static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_vfs->s_id);
+	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)
@@ -425,13 +426,11 @@ TUNE_ATTR_2(name, name##_store)
 TUNE_ATTR(demote_secs, 0);
 TUNE_ATTR(incore_log_blocks, 0);
 TUNE_ATTR(log_flush_secs, 0);
-TUNE_ATTR(jindex_refresh_secs, 0);
 TUNE_ATTR(quota_warn_period, 0);
 TUNE_ATTR(quota_quantum, 0);
 TUNE_ATTR(atime_quantum, 0);
 TUNE_ATTR(max_readahead, 0);
 TUNE_ATTR(complain_secs, 0);
-TUNE_ATTR(reclaim_limit, 0);
 TUNE_ATTR(statfs_slow, 0);
 TUNE_ATTR(new_files_jdata, 0);
 TUNE_ATTR(new_files_directio, 0);
@@ -448,13 +447,11 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_demote_secs.attr,
 	&tune_attr_incore_log_blocks.attr,
 	&tune_attr_log_flush_secs.attr,
-	&tune_attr_jindex_refresh_secs.attr,
 	&tune_attr_quota_warn_period.attr,
 	&tune_attr_quota_quantum.attr,
 	&tune_attr_atime_quantum.attr,
 	&tune_attr_max_readahead.attr,
 	&tune_attr_complain_secs.attr,
-	&tune_attr_reclaim_limit.attr,
 	&tune_attr_statfs_slow.attr,
 	&tune_attr_quota_simul_sync.attr,
 	&tune_attr_quota_cache_secs.attr,

fs/gfs2/trans.c

@@ -114,11 +114,6 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 		gfs2_log_flush(sdp, NULL);
 }
 
-void gfs2_trans_add_gl(struct gfs2_glock *gl)
-{
-	lops_add(gl->gl_sbd, &gl->gl_le);
-}
-
 /**
  * gfs2_trans_add_bh - Add a to-be-modified buffer to the current transaction
  * @gl: the glock the buffer belongs to

fs/gfs2/trans.h

@@ -30,7 +30,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 
 void gfs2_trans_end(struct gfs2_sbd *sdp);
 
-void gfs2_trans_add_gl(struct gfs2_glock *gl);
 void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
 void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno);