Merge http://sucs.org/~rohan/git/gfs2-3.0-nmw

* http://sucs.org/~rohan/git/gfs2-3.0-nmw: (24 commits)
  GFS2: Move readahead of metadata during deallocation into its own function
  GFS2: Remove two unused variables
  GFS2: Misc fixes
  GFS2: rewrite fallocate code to write blocks directly
  GFS2: speed up delete/unlink performance for large files
  GFS2: Fix off-by-one in gfs2_blk2rgrpd
  GFS2: Clean up ->page_mkwrite
  GFS2: Correctly set goal block after allocation
  GFS2: Fix AIL flush issue during fsync
  GFS2: Use cached rgrp in gfs2_rlist_add()
  GFS2: Call do_strip() directly from recursive_scan()
  GFS2: Remove obsolete assert
  GFS2: Cache the most recently used resource group in the inode
  GFS2: Make resource groups "append only" during life of fs
  GFS2: Use rbtree for resource groups and clean up bitmap buffer ref count scheme
  GFS2: Fix lseek after SEEK_DATA, SEEK_HOLE have been added
  GFS2: Clean up gfs2_create
  GFS2: Use ->dirty_inode()
  GFS2: Fix bug trap and journaled data fsync
  GFS2: Fix inode allocation error path
  ...

fs/gfs2/acl.c

@@ -82,7 +82,7 @@ static int gfs2_set_mode(struct inode *inode, umode_t mode)
 		iattr.ia_valid = ATTR_MODE;
 		iattr.ia_mode = mode;
 
-		error = gfs2_setattr_simple(GFS2_I(inode), &iattr);
+		error = gfs2_setattr_simple(inode, &iattr);
 	}
 
 	return error;
@@ -160,6 +160,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode)
 
 int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
 {
+	struct inode *inode = &ip->i_inode;
 	struct posix_acl *acl;
 	char *data;
 	unsigned int len;
@@ -169,7 +170,7 @@ int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	if (!acl)
-		return gfs2_setattr_simple(ip, attr);
+		return gfs2_setattr_simple(inode, attr);
 
 	error = posix_acl_chmod(&acl, GFP_NOFS, attr->ia_mode);
 	if (error)

fs/gfs2/aops.c

@@ -663,7 +663,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	if (&ip->i_inode == sdp->sd_rindex)
 		rblocks += 2 * RES_STATFS;
 	if (alloc_required)
-		rblocks += gfs2_rg_blocks(al);
+		rblocks += gfs2_rg_blocks(ip);
 
 	error = gfs2_trans_begin(sdp, rblocks,
 				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
@@ -787,7 +787,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	u64 to = pos + copied;
 	void *kaddr;
 	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
-	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
 
 	BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
 	kaddr = kmap_atomic(page, KM_USER0);
@@ -804,7 +803,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	if (copied) {
 		if (inode->i_size < to)
 			i_size_write(inode, to);
-		gfs2_dinode_out(ip, di);
 		mark_inode_dirty(inode);
 	}
 
@@ -873,10 +871,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 		gfs2_page_add_databufs(ip, page, from, to);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	if (ret > 0) {
-		gfs2_dinode_out(ip, dibh->b_data);
-		mark_inode_dirty(inode);
-	}
 
 	if (inode == sdp->sd_rindex) {
 		adjust_fs_space(inode);

fs/gfs2/bmap.c

@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 
@@ -36,11 +37,6 @@ struct metapath {
 	__u16 mp_list[GFS2_MAX_META_HEIGHT];
 };
 
-typedef int (*block_call_t) (struct gfs2_inode *ip, struct buffer_head *dibh,
-			     struct buffer_head *bh, __be64 *top,
-			     __be64 *bottom, unsigned int height,
-			     void *data);
-
 struct strip_mine {
 	int sm_first;
 	unsigned int sm_height;
@@ -273,6 +269,30 @@ static inline __be64 *metapointer(unsigned int height, const struct metapath *mp
 	return ((__be64 *)(bh->b_data + head_size)) + mp->mp_list[height];
 }
 
+static void gfs2_metapath_ra(struct gfs2_glock *gl,
+			     const struct buffer_head *bh, const __be64 *pos)
+{
+	struct buffer_head *rabh;
+	const __be64 *endp = (const __be64 *)(bh->b_data + bh->b_size);
+	const __be64 *t;
+
+	for (t = pos; t < endp; t++) {
+		if (!*t)
+			continue;
+
+		rabh = gfs2_getbuf(gl, be64_to_cpu(*t), CREATE);
+		if (trylock_buffer(rabh)) {
+			if (!buffer_uptodate(rabh)) {
+				rabh->b_end_io = end_buffer_read_sync;
+				submit_bh(READA | REQ_META, rabh);
+				continue;
+			}
+			unlock_buffer(rabh);
+		}
+		brelse(rabh);
+	}
+}
+
 /**
  * lookup_metapath - Walk the metadata tree to a specific point
  * @ip: The inode
@@ -432,12 +452,14 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct super_block *sb = sdp->sd_vfs;
 	struct buffer_head *dibh = mp->mp_bh[0];
 	u64 bn, dblock = 0;
 	unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
 	unsigned dblks = 0;
 	unsigned ptrs_per_blk;
 	const unsigned end_of_metadata = height - 1;
+	int ret;
 	int eob = 0;
 	enum alloc_state state;
 	__be64 *ptr;
@@ -540,6 +562,15 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 			dblock = bn;
 			while (n-- > 0)
 				*ptr++ = cpu_to_be64(bn++);
+			if (buffer_zeronew(bh_map)) {
+				ret = sb_issue_zeroout(sb, dblock, dblks,
+						       GFP_NOFS);
+				if (ret) {
+					fs_err(sdp,
+					       "Failed to zero data buffers\n");
+					clear_buffer_zeronew(bh_map);
+				}
+			}
 			break;
 		}
 	} while ((state != ALLOC_DATA) || !dblock);
@@ -667,76 +698,6 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi
 	return ret;
 }
 
-/**
- * recursive_scan - recursively scan through the end of a file
- * @ip: the inode
- * @dibh: the dinode buffer
- * @mp: the path through the metadata to the point to start
- * @height: the height the recursion is at
- * @block: the indirect block to look at
- * @first: 1 if this is the first block
- * @bc: the call to make for each piece of metadata
- * @data: data opaque to this function to pass to @bc
- *
- * When this is first called @height and @block should be zero and
- * @first should be 1.
- *
- * Returns: errno
- */
-
-static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
-			  struct metapath *mp, unsigned int height,
-			  u64 block, int first, block_call_t bc,
-			  void *data)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct buffer_head *bh = NULL;
-	__be64 *top, *bottom;
-	u64 bn;
-	int error;
-	int mh_size = sizeof(struct gfs2_meta_header);
-
-	if (!height) {
-		error = gfs2_meta_inode_buffer(ip, &bh);
-		if (error)
-			return error;
-		dibh = bh;
-
-		top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0];
-		bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs;
-	} else {
-		error = gfs2_meta_indirect_buffer(ip, height, block, 0, &bh);
-		if (error)
-			return error;
-
-		top = (__be64 *)(bh->b_data + mh_size) +
-				  (first ? mp->mp_list[height] : 0);
-
-		bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs;
-	}
-
-	error = bc(ip, dibh, bh, top, bottom, height, data);
-	if (error)
-		goto out;
-
-	if (height < ip->i_height - 1)
-		for (; top < bottom; top++, first = 0) {
-			if (!*top)
-				continue;
-
-			bn = be64_to_cpu(*top);
-
-			error = recursive_scan(ip, dibh, mp, height + 1, bn,
-					       first, bc, data);
-			if (error)
-				break;
-		}
-
-out:
-	brelse(bh);
-	return error;
-}
-
 /**
  * do_strip - Look for a layer a particular layer of the file and strip it off
  * @ip: the inode
@@ -752,9 +713,8 @@ static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
 
 static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		    struct buffer_head *bh, __be64 *top, __be64 *bottom,
-		    unsigned int height, void *data)
+		    unsigned int height, struct strip_mine *sm)
 {
-	struct strip_mine *sm = data;
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrp_list rlist;
 	u64 bn, bstart;
@@ -783,11 +743,6 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	else if (ip->i_depth)
 		revokes = sdp->sd_inptrs;
 
-	if (ip != GFS2_I(sdp->sd_rindex))
-		error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
-	else if (!sdp->sd_rgrps)
-		error = gfs2_ri_update(ip);
-
 	if (error)
 		return error;
 
@@ -805,7 +760,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 			blen++;
 		else {
 			if (bstart)
-				gfs2_rlist_add(sdp, &rlist, bstart);
+				gfs2_rlist_add(ip, &rlist, bstart);
 
 			bstart = bn;
 			blen = 1;
@@ -813,7 +768,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	}
 
 	if (bstart)
-		gfs2_rlist_add(sdp, &rlist, bstart);
+		gfs2_rlist_add(ip, &rlist, bstart);
 	else
 		goto out; /* Nothing to do */
 
@@ -887,11 +842,81 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 out_rlist:
 	gfs2_rlist_free(&rlist);
 out:
-	if (ip != GFS2_I(sdp->sd_rindex))
-		gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
 	return error;
 }
 
+/**
+ * recursive_scan - recursively scan through the end of a file
+ * @ip: the inode
+ * @dibh: the dinode buffer
+ * @mp: the path through the metadata to the point to start
+ * @height: the height the recursion is at
+ * @block: the indirect block to look at
+ * @first: 1 if this is the first block
+ * @sm: data opaque to this function to pass to @bc
+ *
+ * When this is first called @height and @block should be zero and
+ * @first should be 1.
+ *
+ * Returns: errno
+ */
+
+static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
+			  struct metapath *mp, unsigned int height,
+			  u64 block, int first, struct strip_mine *sm)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh = NULL;
+	__be64 *top, *bottom;
+	u64 bn;
+	int error;
+	int mh_size = sizeof(struct gfs2_meta_header);
+
+	if (!height) {
+		error = gfs2_meta_inode_buffer(ip, &bh);
+		if (error)
+			return error;
+		dibh = bh;
+
+		top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0];
+		bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs;
+	} else {
+		error = gfs2_meta_indirect_buffer(ip, height, block, 0, &bh);
+		if (error)
+			return error;
+
+		top = (__be64 *)(bh->b_data + mh_size) +
+				  (first ? mp->mp_list[height] : 0);
+
+		bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs;
+	}
+
+	error = do_strip(ip, dibh, bh, top, bottom, height, sm);
+	if (error)
+		goto out;
+
+	if (height < ip->i_height - 1) {
+
+		gfs2_metapath_ra(ip->i_gl, bh, top);
+
+		for (; top < bottom; top++, first = 0) {
+			if (!*top)
+				continue;
+
+			bn = be64_to_cpu(*top);
+
+			error = recursive_scan(ip, dibh, mp, height + 1, bn,
+					       first, sm);
+			if (error)
+				break;
+		}
+	}
+out:
+	brelse(bh);
+	return error;
+}
+
+
 /**
  * gfs2_block_truncate_page - Deal with zeroing out data for truncate
  *
@@ -1031,7 +1056,7 @@ static int trunc_dealloc(struct gfs2_inode *ip, u64 size)
 		sm.sm_first = !!size;
 		sm.sm_height = height;
 
-		error = recursive_scan(ip, NULL, &mp, 0, 0, 1, do_strip, &sm);
+		error = recursive_scan(ip, NULL, &mp, 0, 0, 1, &sm);
 		if (error)
 			break;
 	}

fs/gfs2/dir.c

@@ -240,16 +240,15 @@ static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf,
 	return error;
 }
 
-static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, char *buf,
-				 u64 offset, unsigned int size)
+static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, __be64 *buf,
+				 unsigned int size)
 {
 	struct buffer_head *dibh;
 	int error;
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
 	if (!error) {
-		offset += sizeof(struct gfs2_dinode);
-		memcpy(buf, dibh->b_data + offset, size);
+		memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), size);
 		brelse(dibh);
 	}
 
@@ -261,13 +260,12 @@ static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, char *buf,
  * gfs2_dir_read_data - Read a data from a directory inode
  * @ip: The GFS2 Inode
  * @buf: The buffer to place result into
- * @offset: File offset to begin jdata_readng from
  * @size: Amount of data to transfer
  *
  * Returns: The amount of data actually copied or the error
  */
-static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
-			      unsigned int size, unsigned ra)
+static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf,
+			      unsigned int size)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	u64 lblock, dblock;
@@ -275,24 +273,14 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
 	unsigned int o;
 	int copied = 0;
 	int error = 0;
-	u64 disksize = i_size_read(&ip->i_inode);
-
-	if (offset >= disksize)
-		return 0;
-
-	if (offset + size > disksize)
-		size = disksize - offset;
-
-	if (!size)
-		return 0;
 
 	if (gfs2_is_stuffed(ip))
-		return gfs2_dir_read_stuffed(ip, buf, offset, size);
+		return gfs2_dir_read_stuffed(ip, buf, size);
 
 	if (gfs2_assert_warn(sdp, gfs2_is_jdata(ip)))
 		return -EINVAL;
 
-	lblock = offset;
+	lblock = 0;
 	o = do_div(lblock, sdp->sd_jbsize) + sizeof(struct gfs2_meta_header);
 
 	while (copied < size) {
@@ -311,8 +299,6 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
 			if (error || !dblock)
 				goto fail;
 			BUG_ON(extlen < 1);
-			if (!ra)
-				extlen = 1;
 			bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
 		} else {
 			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh);
@@ -328,7 +314,7 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
 		extlen--;
 		memcpy(buf, bh->b_data + o, amount);
 		brelse(bh);
-		buf += amount;
+		buf += (amount/sizeof(__be64));
 		copied += amount;
 		lblock++;
 		o = sizeof(struct gfs2_meta_header);
@@ -371,7 +357,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip)
 	if (hc == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	ret = gfs2_dir_read_data(ip, (char *)hc, 0, hsize, 1);
+	ret = gfs2_dir_read_data(ip, hc, hsize);
 	if (ret < 0) {
 		kfree(hc);
 		return ERR_PTR(ret);
@@ -1695,7 +1681,6 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
 	const struct qstr *name = &dentry->d_name;
 	struct gfs2_dirent *dent, *prev = NULL;
 	struct buffer_head *bh;
-	int error;
 
 	/* Returns _either_ the entry (if its first in block) or the
 	   previous entry otherwise */
@@ -1724,22 +1709,15 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
 	}
 	brelse(bh);
 
-	error = gfs2_meta_inode_buffer(dip, &bh);
-	if (error)
-		return error;
-
 	if (!dip->i_entries)
 		gfs2_consist_inode(dip);
-	gfs2_trans_add_bh(dip->i_gl, bh, 1);
 	dip->i_entries--;
 	dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
 	if (S_ISDIR(dentry->d_inode->i_mode))
 		drop_nlink(&dip->i_inode);
-	gfs2_dinode_out(dip, bh->b_data);
-	brelse(bh);
 	mark_inode_dirty(&dip->i_inode);
 
-	return error;
+	return 0;
 }
 
 /**
@@ -1829,10 +1807,6 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 	if (error)
 		goto out_put;
 
-	error = gfs2_rindex_hold(sdp, &dip->i_alloc->al_ri_gh);
-	if (error)
-		goto out_qs;
-
 	/*  Count the number of leaves  */
 	bh = leaf_bh;
 
@@ -1847,7 +1821,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 		if (blk != leaf_no)
 			brelse(bh);
 
-		gfs2_rlist_add(sdp, &rlist, blk);
+		gfs2_rlist_add(dip, &rlist, blk);
 		l_blocks++;
 	}
 
@@ -1911,8 +1885,6 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 	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);
-out_qs:
 	gfs2_quota_unhold(dip);
 out_put:
 	gfs2_alloc_put(dip);

fs/gfs2/glops.c

@@ -28,40 +28,55 @@
 #include "trans.h"
 #include "dir.h"
 
+static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
+{
+	fs_err(gl->gl_sbd, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page state 0x%lx\n",
+	       bh, (unsigned long long)bh->b_blocknr, bh->b_state,
+	       bh->b_page->mapping, bh->b_page->flags);
+	fs_err(gl->gl_sbd, "AIL glock %u:%llu mapping %p\n",
+	       gl->gl_name.ln_type, gl->gl_name.ln_number,
+	       gfs2_glock2aspace(gl));
+	gfs2_lm_withdraw(gl->gl_sbd, "AIL error\n");
+}
+
 /**
  * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
  * @gl: the glock
+ * @fsync: set when called from fsync (not all buffers will be clean)
  *
  * None of the buffers should be dirty, locked, or pinned.
  */
 
-static void __gfs2_ail_flush(struct gfs2_glock *gl)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct list_head *head = &gl->gl_ail_list;
-	struct gfs2_bufdata *bd;
+	struct gfs2_bufdata *bd, *tmp;
 	struct buffer_head *bh;
+	const unsigned long b_state = (1UL << BH_Dirty)|(1UL << BH_Pinned)|(1UL << BH_Lock);
+	sector_t blocknr;
 
+	gfs2_log_lock(sdp);
 	spin_lock(&sdp->sd_ail_lock);
-	while (!list_empty(head)) {
-		bd = list_entry(head->next, struct gfs2_bufdata,
-				bd_ail_gl_list);
+	list_for_each_entry_safe(bd, tmp, head, bd_ail_gl_list) {
 		bh = bd->bd_bh;
-		gfs2_remove_from_ail(bd);
-		bd->bd_bh = NULL;
+		if (bh->b_state & b_state) {
+			if (fsync)
+				continue;
+			gfs2_ail_error(gl, bh);
+		}
+		blocknr = bh->b_blocknr;
 		bh->b_private = NULL;
-		spin_unlock(&sdp->sd_ail_lock);
+		gfs2_remove_from_ail(bd); /* drops ref on bh */
 
-		bd->bd_blkno = bh->b_blocknr;
-		gfs2_log_lock(sdp);
-		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
-		gfs2_trans_add_revoke(sdp, bd);
-		gfs2_log_unlock(sdp);
+		bd->bd_bh = NULL;
+		bd->bd_blkno = blocknr;
 
-		spin_lock(&sdp->sd_ail_lock);
+		gfs2_trans_add_revoke(sdp, bd);
 	}
-	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	BUG_ON(!fsync && atomic_read(&gl->gl_ail_count));
 	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
 }
 
 
@@ -84,13 +99,13 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	BUG_ON(current->journal_info);
 	current->journal_info = &tr;
 
-	__gfs2_ail_flush(gl);
+	__gfs2_ail_flush(gl, 0);
 
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
 }
 
-void gfs2_ail_flush(struct gfs2_glock *gl)
+void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	unsigned int revokes = atomic_read(&gl->gl_ail_count);
@@ -102,7 +117,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl)
 	ret = gfs2_trans_begin(sdp, 0, revokes);
 	if (ret)
 		return;
-	__gfs2_ail_flush(gl);
+	__gfs2_ail_flush(gl, fsync);
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
 }
@@ -119,6 +134,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl)
 static void rgrp_go_sync(struct gfs2_glock *gl)
 {
 	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	struct gfs2_rgrpd *rgd;
 	int error;
 
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
@@ -130,6 +146,12 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
 	error = filemap_fdatawait(metamapping);
         mapping_set_error(metamapping, error);
 	gfs2_ail_empty_gl(gl);
+
+	spin_lock(&gl->gl_spin);
+	rgd = gl->gl_object;
+	if (rgd)
+		gfs2_free_clones(rgd);
+	spin_unlock(&gl->gl_spin);
 }
 
 /**
@@ -429,33 +451,6 @@ static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
 	return 0;
 }
 
-/**
- * rgrp_go_lock - operation done after an rgrp lock is locked by
- *    a first holder on this node.
- * @gl: the glock
- * @flags:
- *
- * Returns: errno
- */
-
-static int rgrp_go_lock(struct gfs2_holder *gh)
-{
-	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
-}
-
-/**
- * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
- *    a last holder on this node.
- * @gl: the glock
- * @flags:
- *
- */
-
-static void rgrp_go_unlock(struct gfs2_holder *gh)
-{
-	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
-}
-
 /**
  * trans_go_sync - promote/demote the transaction glock
  * @gl: the glock
@@ -558,8 +553,8 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_xmote_th = rgrp_go_sync,
 	.go_inval = rgrp_go_inval,
-	.go_lock = rgrp_go_lock,
-	.go_unlock = rgrp_go_unlock,
+	.go_lock = gfs2_rgrp_go_lock,
+	.go_unlock = gfs2_rgrp_go_unlock,
 	.go_dump = gfs2_rgrp_dump,
 	.go_type = LM_TYPE_RGRP,
 	.go_flags = GLOF_ASPACE,

fs/gfs2/glops.h

@@ -23,6 +23,6 @@ extern const struct gfs2_glock_operations gfs2_quota_glops;
 extern const struct gfs2_glock_operations gfs2_journal_glops;
 extern const struct gfs2_glock_operations *gfs2_glops_list[];
 
-extern void gfs2_ail_flush(struct gfs2_glock *gl);
+extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
 
 #endif /* __GLOPS_DOT_H__ */

fs/gfs2/incore.h

@@ -18,6 +18,7 @@
 #include <linux/rcupdate.h>
 #include <linux/rculist_bl.h>
 #include <linux/completion.h>
+#include <linux/rbtree.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -78,8 +79,7 @@ struct gfs2_bitmap {
 };
 
 struct gfs2_rgrpd {
-	struct list_head rd_list;	/* Link with superblock */
-	struct list_head rd_list_mru;
+	struct rb_node rd_node;		/* Link with superblock */
 	struct gfs2_glock *rd_gl;	/* Glock for this rgrp */
 	u64 rd_addr;			/* grp block disk address */
 	u64 rd_data0;			/* first data location */
@@ -91,10 +91,7 @@ struct gfs2_rgrpd {
 	u32 rd_dinodes;
 	u64 rd_igeneration;
 	struct gfs2_bitmap *rd_bits;
-	struct mutex rd_mutex;
-	struct gfs2_log_element rd_le;
 	struct gfs2_sbd *rd_sbd;
-	unsigned int rd_bh_count;
 	u32 rd_last_alloc;
 	u32 rd_flags;
 #define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
@@ -106,12 +103,15 @@ struct gfs2_rgrpd {
 enum gfs2_state_bits {
 	BH_Pinned = BH_PrivateStart,
 	BH_Escaped = BH_PrivateStart + 1,
+	BH_Zeronew = BH_PrivateStart + 2,
 };
 
 BUFFER_FNS(Pinned, pinned)
 TAS_BUFFER_FNS(Pinned, pinned)
 BUFFER_FNS(Escaped, escaped)
 TAS_BUFFER_FNS(Escaped, escaped)
+BUFFER_FNS(Zeronew, zeronew)
+TAS_BUFFER_FNS(Zeronew, zeronew)
 
 struct gfs2_bufdata {
 	struct buffer_head *bd_bh;
@@ -246,7 +246,6 @@ struct gfs2_glock {
 
 struct gfs2_alloc {
 	/* Quota stuff */
-
 	struct gfs2_quota_data *al_qd[2*MAXQUOTAS];
 	struct gfs2_holder al_qd_ghs[2*MAXQUOTAS];
 	unsigned int al_qd_num;
@@ -255,18 +254,13 @@ struct gfs2_alloc {
 	u32 al_alloced; /* Filled in by gfs2_alloc_*() */
 
 	/* Filled in by gfs2_inplace_reserve() */
-
-	unsigned int al_line;
-	char *al_file;
-	struct gfs2_holder al_ri_gh;
 	struct gfs2_holder al_rgd_gh;
-	struct gfs2_rgrpd *al_rgd;
-
 };
 
 enum {
 	GIF_INVALID		= 0,
 	GIF_QD_LOCKED		= 1,
+	GIF_ALLOC_FAILED	= 2,
 	GIF_SW_PAGED		= 3,
 };
 
@@ -282,6 +276,7 @@ struct gfs2_inode {
 	struct gfs2_holder i_iopen_gh;
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_alloc *i_alloc;
+	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
 	struct list_head i_trunc_list;
@@ -574,9 +569,7 @@ struct gfs2_sbd {
 	int sd_rindex_uptodate;
 	spinlock_t sd_rindex_spin;
 	struct mutex sd_rindex_mutex;
-	struct list_head sd_rindex_list;
-	struct list_head sd_rindex_mru_list;
-	struct gfs2_rgrpd *sd_rindex_forward;
+	struct rb_root sd_rindex_tree;
 	unsigned int sd_rgrps;
 	unsigned int sd_max_rg_data;
 

fs/gfs2/inode.c

@@ -583,7 +583,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
 			goto fail_quota_locks;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 al->al_rgd->rd_length +
+					 dip->i_rgd->rd_length +
 					 2 * RES_DINODE +
 					 RES_STATFS + RES_QUOTA, 0);
 		if (error)
@@ -613,8 +613,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
 	gfs2_trans_end(sdp);
 
 fail_ipreserv:
-	if (dip->i_alloc->al_rgd)
-		gfs2_inplace_release(dip);
+	gfs2_inplace_release(dip);
 
 fail_quota_locks:
 	gfs2_quota_unlock(dip);
@@ -661,7 +660,7 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
 
 static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 			     unsigned int mode, dev_t dev, const char *symname,
-			     unsigned int size)
+			     unsigned int size, int excl)
 {
 	const struct qstr *name = &dentry->d_name;
 	struct gfs2_holder ghs[2];
@@ -681,6 +680,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		goto fail;
 
 	error = create_ok(dip, name, mode);
+	if ((error == -EEXIST) && S_ISREG(mode) && !excl) {
+		inode = gfs2_lookupi(dir, &dentry->d_name, 0);
+		gfs2_glock_dq_uninit(ghs);
+		d_instantiate(dentry, inode);
+		return IS_ERR(inode) ? PTR_ERR(inode) : 0;
+	}
 	if (error)
 		goto fail_gunlock;
 
@@ -723,21 +728,22 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		brelse(bh);
 
 	gfs2_trans_end(sdp);
-	if (dip->i_alloc->al_rgd)
-		gfs2_inplace_release(dip);
+	gfs2_inplace_release(dip);
 	gfs2_quota_unlock(dip);
 	gfs2_alloc_put(dip);
-	gfs2_glock_dq_uninit_m(2, ghs);
 	mark_inode_dirty(inode);
+	gfs2_glock_dq_uninit_m(2, ghs);
 	d_instantiate(dentry, inode);
 	return 0;
 
 fail_gunlock2:
 	gfs2_glock_dq_uninit(ghs + 1);
-	if (inode && !IS_ERR(inode))
-		iput(inode);
 fail_gunlock:
 	gfs2_glock_dq_uninit(ghs);
+	if (inode && !IS_ERR(inode)) {
+		set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
+		iput(inode);
+	}
 fail:
 	if (bh)
 		brelse(bh);
@@ -756,24 +762,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		       int mode, struct nameidata *nd)
 {
-	struct inode *inode;
-	int ret;
-
-	for (;;) {
-		ret = gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0);
-		if (ret != -EEXIST || (nd && (nd->flags & LOOKUP_EXCL)))
-			return ret;
-
-		inode = gfs2_lookupi(dir, &dentry->d_name, 0);
-		if (inode) {
-			if (!IS_ERR(inode))
-				break;
-			return PTR_ERR(inode);
-		}
-	}
-
-	d_instantiate(dentry, inode);
-	return 0;
+	int excl = 0;
+	if (nd && (nd->flags & LOOKUP_EXCL))
+		excl = 1;
+	return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /**
@@ -900,7 +892,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 			goto out_gunlock_q;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 gfs2_rg_blocks(al) +
+					 gfs2_rg_blocks(dip) +
 					 2 * RES_DINODE + RES_STATFS +
 					 RES_QUOTA, 0);
 		if (error)
@@ -922,8 +914,9 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 	inc_nlink(&ip->i_inode);
 	ip->i_inode.i_ctime = CURRENT_TIME;
-	gfs2_dinode_out(ip, dibh->b_data);
-	mark_inode_dirty(&ip->i_inode);
+	ihold(inode);
+	d_instantiate(dentry, inode);
+	mark_inode_dirty(inode);
 
 out_brelse:
 	brelse(dibh);
@@ -945,11 +938,6 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 out_parent:
 	gfs2_holder_uninit(ghs);
 	gfs2_holder_uninit(ghs + 1);
-	if (!error) {
-		ihold(inode);
-		d_instantiate(dentry, inode);
-		mark_inode_dirty(inode);
-	}
 	return error;
 }
 
@@ -1022,8 +1010,6 @@ static int gfs2_unlink_inode(struct gfs2_inode *dip,
 		clear_nlink(inode);
 	else
 		drop_nlink(inode);
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
-	gfs2_dinode_out(ip, bh->b_data);
 	mark_inode_dirty(inode);
 	if (inode->i_nlink == 0)
 		gfs2_unlink_di(inode);
@@ -1051,13 +1037,8 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	struct buffer_head *bh;
 	struct gfs2_holder ghs[3];
 	struct gfs2_rgrpd *rgd;
-	struct gfs2_holder ri_gh;
 	int error;
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		return error;
-
 	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
 	gfs2_holder_init(ip->i_gl,  LM_ST_EXCLUSIVE, 0, ghs + 1);
 
@@ -1114,7 +1095,6 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	gfs2_glock_dq(ghs);
 out_parent:
 	gfs2_holder_uninit(ghs);
-	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
 
@@ -1137,7 +1117,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode) - 1)
 		return -ENAMETOOLONG;
 
-	return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size);
+	return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
 }
 
 /**
@@ -1151,7 +1131,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 
 static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-	return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0);
+	return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0, 0);
 }
 
 /**
@@ -1166,7 +1146,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
 		      dev_t dev)
 {
-	return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0);
+	return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0, 0);
 }
 
 /*
@@ -1232,7 +1212,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
 	struct gfs2_inode *nip = NULL;
 	struct gfs2_sbd *sdp = GFS2_SB(odir);
-	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
+	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
@@ -1246,10 +1226,6 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			return 0;
 	}
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		return error;
-
 	if (odip != ndip) {
 		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
 					   0, &r_gh);
@@ -1386,12 +1362,12 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 
 		al->al_requested = sdp->sd_max_dirres;
 
-		error = gfs2_inplace_reserve_ri(ndip);
+		error = gfs2_inplace_reserve(ndip);
 		if (error)
 			goto out_gunlock_q;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 gfs2_rg_blocks(al) +
+					 gfs2_rg_blocks(ndip) +
 					 4 * RES_DINODE + 4 * RES_LEAF +
 					 RES_STATFS + RES_QUOTA + 4, 0);
 		if (error)
@@ -1457,7 +1433,6 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	if (r_gh.gh_gl)
 		gfs2_glock_dq_uninit(&r_gh);
 out:
-	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
 
@@ -1561,21 +1536,10 @@ int gfs2_permission(struct inode *inode, int mask)
 	return error;
 }
 
-static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
 {
-	struct inode *inode = &ip->i_inode;
-	struct buffer_head *dibh;
-	int error;
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		return error;
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_dinode_out(ip, dibh->b_data);
-	brelse(dibh);
 	return 0;
 }
 
@@ -1587,19 +1551,19 @@ static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
  * Returns: errno
  */
 
-int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+int gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
 {
 	int error;
 
 	if (current->journal_info)
-		return __gfs2_setattr_simple(ip, attr);
+		return __gfs2_setattr_simple(inode, attr);
 
-	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE, 0);
+	error = gfs2_trans_begin(GFS2_SB(inode), RES_DINODE, 0);
 	if (error)
 		return error;
 
-	error = __gfs2_setattr_simple(ip, attr);
-	gfs2_trans_end(GFS2_SB(&ip->i_inode));
+	error = __gfs2_setattr_simple(inode, attr);
+	gfs2_trans_end(GFS2_SB(inode));
 	return error;
 }
 
@@ -1637,7 +1601,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 	if (error)
 		goto out_gunlock_q;
 
-	error = gfs2_setattr_simple(ip, attr);
+	error = gfs2_setattr_simple(inode, attr);
 	if (error)
 		goto out_end_trans;
 
@@ -1693,12 +1657,12 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
 		error = gfs2_acl_chmod(ip, attr);
 	else
-		error = gfs2_setattr_simple(ip, attr);
+		error = gfs2_setattr_simple(inode, attr);
 
 out:
-	gfs2_glock_dq_uninit(&i_gh);
 	if (!error)
 		mark_inode_dirty(inode);
+	gfs2_glock_dq_uninit(&i_gh);
 	return error;
 }
 

fs/gfs2/inode.h

@@ -109,7 +109,7 @@ extern int gfs2_inode_refresh(struct gfs2_inode *ip);
 extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 				  int is_root);
 extern int gfs2_permission(struct inode *inode, int mask);
-extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+extern int gfs2_setattr_simple(struct inode *inode, struct iattr *attr);
 extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
 

fs/gfs2/lops.c

@@ -60,6 +60,29 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	trace_gfs2_pin(bd, 1);
 }
 
+static bool buffer_is_rgrp(const struct gfs2_bufdata *bd)
+{
+	return bd->bd_gl->gl_name.ln_type == LM_TYPE_RGRP;
+}
+
+static void maybe_release_space(struct gfs2_bufdata *bd)
+{
+	struct gfs2_glock *gl = bd->bd_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_rgrpd *rgd = gl->gl_object;
+	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
+	struct gfs2_bitmap *bi = rgd->rd_bits + index;
+
+	if (bi->bi_clone == 0)
+		return;
+	if (sdp->sd_args.ar_discard)
+		gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi);
+	memcpy(bi->bi_clone + bi->bi_offset,
+	       bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
+	clear_bit(GBF_FULL, &bi->bi_flags);
+	rgd->rd_free_clone = rgd->rd_free;
+}
+
 /**
  * gfs2_unpin - Unpin a buffer
  * @sdp: the filesystem the buffer belongs to
@@ -81,6 +104,9 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	mark_buffer_dirty(bh);
 	clear_buffer_pinned(bh);
 
+	if (buffer_is_rgrp(bd))
+		maybe_release_space(bd);
+
 	spin_lock(&sdp->sd_ail_lock);
 	if (bd->bd_ail) {
 		list_del(&bd->bd_ail_st_list);
@@ -469,42 +495,6 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 	gfs2_revoke_clean(sdp);
 }
 
-static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
-{
-	struct gfs2_rgrpd *rgd;
-	struct gfs2_trans *tr = current->journal_info;
-
-	tr->tr_touched = 1;
-
-	rgd = container_of(le, struct gfs2_rgrpd, rd_le);
-
-	gfs2_log_lock(sdp);
-	if (!list_empty(&le->le_list)){
-		gfs2_log_unlock(sdp);
-		return;
-	}
-	gfs2_rgrp_bh_hold(rgd);
-	sdp->sd_log_num_rg++;
-	list_add(&le->le_list, &sdp->sd_log_le_rg);
-	gfs2_log_unlock(sdp);
-}
-
-static void rg_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
-{
-	struct list_head *head = &sdp->sd_log_le_rg;
-	struct gfs2_rgrpd *rgd;
-
-	while (!list_empty(head)) {
-		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_le.le_list);
-		list_del_init(&rgd->rd_le.le_list);
-		sdp->sd_log_num_rg--;
-
-		gfs2_rgrp_repolish_clones(rgd);
-		gfs2_rgrp_bh_put(rgd);
-	}
-	gfs2_assert_warn(sdp, !sdp->sd_log_num_rg);
-}
-
 /**
  * databuf_lo_add - Add a databuf to the transaction.
  *
@@ -705,8 +695,6 @@ static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 
 		brelse(bh_log);
 		brelse(bh_ip);
-		if (error)
-			break;
 
 		sdp->sd_replayed_blocks++;
 	}
@@ -771,8 +759,6 @@ const struct gfs2_log_operations gfs2_revoke_lops = {
 };
 
 const struct gfs2_log_operations gfs2_rg_lops = {
-	.lo_add = rg_lo_add,
-	.lo_after_commit = rg_lo_after_commit,
 	.lo_name = "rg",
 };
 

fs/gfs2/ops_fstype.c

@@ -77,8 +77,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	spin_lock_init(&sdp->sd_rindex_spin);
 	mutex_init(&sdp->sd_rindex_mutex);
-	INIT_LIST_HEAD(&sdp->sd_rindex_list);
-	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
+	sdp->sd_rindex_tree.rb_node = NULL;
 
 	INIT_LIST_HEAD(&sdp->sd_jindex_list);
 	spin_lock_init(&sdp->sd_jindex_spin);
@@ -652,7 +651,6 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		fs_err(sdp, "can't lookup journal index: %d\n", error);
 		return PTR_ERR(sdp->sd_jindex);
 	}
-	ip = GFS2_I(sdp->sd_jindex);
 
 	/* Load in the journal index special file */
 
@@ -764,7 +762,6 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 static int init_inodes(struct gfs2_sbd *sdp, int undo)
 {
 	int error = 0;
-	struct gfs2_inode *ip;
 	struct inode *master = sdp->sd_master_dir->d_inode;
 
 	if (undo)
@@ -789,7 +786,6 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 		fs_err(sdp, "can't get resource index inode: %d\n", error);
 		goto fail_statfs;
 	}
-	ip = GFS2_I(sdp->sd_rindex);
 	sdp->sd_rindex_uptodate = 0;
 
 	/* Read in the quota inode */

fs/gfs2/quota.c

@@ -638,15 +638,18 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	unsigned long index = loc >> PAGE_CACHE_SHIFT;
 	unsigned offset = loc & (PAGE_CACHE_SIZE - 1);
 	unsigned blocksize, iblock, pos;
-	struct buffer_head *bh, *dibh;
+	struct buffer_head *bh;
 	struct page *page;
 	void *kaddr, *ptr;
 	struct gfs2_quota q, *qp;
 	int err, nbytes;
 	u64 size;
 
-	if (gfs2_is_stuffed(ip))
-		gfs2_unstuff_dinode(ip, NULL);
+	if (gfs2_is_stuffed(ip)) {
+		err = gfs2_unstuff_dinode(ip, NULL);
+		if (err)
+			return err;
+	}
 
 	memset(&q, 0, sizeof(struct gfs2_quota));
 	err = gfs2_internal_read(ip, NULL, (char *)&q, &loc, sizeof(q));
@@ -736,22 +739,13 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 		goto get_a_page;
 	}
 
-	/* Update the disk inode timestamp and size (if extended) */
-	err = gfs2_meta_inode_buffer(ip, &dibh);
-	if (err)
-		goto out;
-
 	size = loc + sizeof(struct gfs2_quota);
 	if (size > inode->i_size)
 		i_size_write(inode, size);
 	inode->i_mtime = inode->i_atime = CURRENT_TIME;
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_dinode_out(ip, dibh->b_data);
-	brelse(dibh);
 	mark_inode_dirty(inode);
-
-out:
 	return err;
+
 unlock_out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -822,7 +816,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 		goto out_alloc;
 
 	if (nalloc)
-		blocks += gfs2_rg_blocks(al) + nalloc * ind_blocks + RES_STATFS;
+		blocks += gfs2_rg_blocks(ip) + nalloc * ind_blocks + RES_STATFS;
 
 	error = gfs2_trans_begin(sdp, blocks, 0);
 	if (error)
@@ -936,7 +930,9 @@ int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
 	unsigned int x;
 	int error = 0;
 
-	gfs2_quota_hold(ip, uid, gid);
+	error = gfs2_quota_hold(ip, uid, gid);
+	if (error)
+		return error;
 
 	if (capable(CAP_SYS_RESOURCE) ||
 	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
@@ -1607,7 +1603,7 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
 		error = gfs2_inplace_reserve(ip);
 		if (error)
 			goto out_alloc;
-		blocks += gfs2_rg_blocks(al);
+		blocks += gfs2_rg_blocks(ip);
 	}
 
 	/* Some quotas span block boundaries and can update two blocks,

fs/gfs2/rgrp.h

@@ -18,18 +18,15 @@ struct gfs2_holder;
 
 extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
 
-struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
-struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
-struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
+extern struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
+extern struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
+extern struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
 
 extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
-extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
-
-extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
-extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
-extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
-
-extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
+extern int gfs2_rindex_update(struct gfs2_sbd *sdp);
+extern void gfs2_free_clones(struct gfs2_rgrpd *rgd);
+extern int gfs2_rgrp_go_lock(struct gfs2_holder *gh);
+extern void gfs2_rgrp_go_unlock(struct gfs2_holder *gh);
 
 extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
 static inline void gfs2_alloc_put(struct gfs2_inode *ip)
@@ -39,16 +36,9 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 	ip->i_alloc = NULL;
 }
 
-extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
-				  char *file, unsigned int line);
-#define gfs2_inplace_reserve(ip) \
-	gfs2_inplace_reserve_i((ip), 1, __FILE__, __LINE__)
-#define gfs2_inplace_reserve_ri(ip) \
-	gfs2_inplace_reserve_i((ip), 0, __FILE__, __LINE__)
-
+extern int gfs2_inplace_reserve(struct gfs2_inode *ip);
 extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
-extern int gfs2_ri_update(struct gfs2_inode *ip);
 extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
 extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);
 
@@ -66,11 +56,14 @@ struct gfs2_rgrp_list {
 	struct gfs2_holder *rl_ghs;
 };
 
-extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 			   u64 block);
 extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
 extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
 extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
 extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
+extern void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+				    struct buffer_head *bh,
+				    const struct gfs2_bitmap *bi);
 
 #endif /* __RGRP_DOT_H__ */

fs/gfs2/super.c

@@ -752,51 +752,77 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
 	struct backing_dev_info *bdi = metamapping->backing_dev_info;
-	struct gfs2_holder gh;
+	int ret = 0;
+
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	if (bdi->dirty_exceeded)
+		gfs2_ail1_flush(sdp, wbc);
+	else
+		filemap_fdatawrite(metamapping);
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		ret = filemap_fdatawait(metamapping);
+	if (ret)
+		mark_inode_dirty_sync(inode);
+	return ret;
+}
+
+/**
+ * gfs2_dirty_inode - check for atime updates
+ * @inode: The inode in question
+ * @flags: The type of dirty
+ *
+ * Unfortunately it can be called under any combination of inode
+ * glock and transaction lock, so we have to check carefully.
+ *
+ * At the moment this deals only with atime - it should be possible
+ * to expand that role in future, once a review of the locking has
+ * been carried out.
+ */
+
+static void gfs2_dirty_inode(struct inode *inode, int flags)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *bh;
-	struct timespec atime;
-	struct gfs2_dinode *di;
-	int ret = -EAGAIN;
-	int unlock_required = 0;
-
-	/* Skip timestamp update, if this is from a memalloc */
-	if (current->flags & PF_MEMALLOC)
-		goto do_flush;
+	struct gfs2_holder gh;
+	int need_unlock = 0;
+	int need_endtrans = 0;
+	int ret;
+
+	if (!(flags & (I_DIRTY_DATASYNC|I_DIRTY_SYNC)))
+		return;
+
 	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
 		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-		if (ret)
-			goto do_flush;
-		unlock_required = 1;
+		if (ret) {
+			fs_err(sdp, "dirty_inode: glock %d\n", ret);
+			return;
+		}
+		need_unlock = 1;
 	}
-	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
-	if (ret)
-		goto do_unlock;
+
+	if (current->journal_info == NULL) {
+		ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+		if (ret) {
+			fs_err(sdp, "dirty_inode: gfs2_trans_begin %d\n", ret);
+			goto out;
+		}
+		need_endtrans = 1;
+	}
+
 	ret = gfs2_meta_inode_buffer(ip, &bh);
 	if (ret == 0) {
-		di = (struct gfs2_dinode *)bh->b_data;
-		atime.tv_sec = be64_to_cpu(di->di_atime);
-		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
-		if (timespec_compare(&inode->i_atime, &atime) > 0) {
-			gfs2_trans_add_bh(ip->i_gl, bh, 1);
-			gfs2_dinode_out(ip, bh->b_data);
-		}
+		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		gfs2_dinode_out(ip, bh->b_data);
 		brelse(bh);
 	}
-	gfs2_trans_end(sdp);
-do_unlock:
-	if (unlock_required)
+
+	if (need_endtrans)
+		gfs2_trans_end(sdp);
+out:
+	if (need_unlock)
 		gfs2_glock_dq_uninit(&gh);
-do_flush:
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
-	filemap_fdatawrite(metamapping);
-	if (bdi->dirty_exceeded)
-		gfs2_ail1_flush(sdp, wbc);
-	if (!ret && (wbc->sync_mode == WB_SYNC_ALL))
-		ret = filemap_fdatawait(metamapping);
-	if (ret)
-		mark_inode_dirty_sync(inode);
-	return ret;
 }
 
 /**
@@ -1011,7 +1037,6 @@ static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
 
 static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
 {
-	struct gfs2_holder ri_gh;
 	struct gfs2_rgrpd *rgd_next;
 	struct gfs2_holder *gha, *gh;
 	unsigned int slots = 64;
@@ -1024,10 +1049,6 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 	if (!gha)
 		return -ENOMEM;
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		goto out;
-
 	rgd_next = gfs2_rgrpd_get_first(sdp);
 
 	for (;;) {
@@ -1070,9 +1091,6 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 		yield();
 	}
 
-	gfs2_glock_dq_uninit(&ri_gh);
-
-out:
 	kfree(gha);
 	return error;
 }
@@ -1124,6 +1142,10 @@ static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct gfs2_statfs_change_host sc;
 	int error;
 
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		return error;
+
 	if (gfs2_tune_get(sdp, gt_statfs_slow))
 		error = gfs2_statfs_slow(sdp, &sc);
 	else
@@ -1394,21 +1416,17 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
 	if (error)
 		goto out;
 
-	error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
-	if (error)
-		goto out_qs;
-
 	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
 	if (!rgd) {
 		gfs2_consist_inode(ip);
 		error = -EIO;
-		goto out_rindex_relse;
+		goto out_qs;
 	}
 
 	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
 				   &al->al_rgd_gh);
 	if (error)
-		goto out_rindex_relse;
+		goto out_qs;
 
 	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
 				 sdp->sd_jdesc->jd_blocks);
@@ -1423,8 +1441,6 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
 
 out_rg_gunlock:
 	gfs2_glock_dq_uninit(&al->al_rgd_gh);
-out_rindex_relse:
-	gfs2_glock_dq_uninit(&al->al_ri_gh);
 out_qs:
 	gfs2_quota_unhold(ip);
 out:
@@ -1471,9 +1487,11 @@ static void gfs2_evict_inode(struct inode *inode)
 		goto out;
 	}
 
-	error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
-	if (error)
-		goto out_truncate;
+	if (!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
+		error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+		if (error)
+			goto out_truncate;
+	}
 
 	if (test_bit(GIF_INVALID, &ip->i_flags)) {
 		error = gfs2_inode_refresh(ip);
@@ -1513,6 +1531,10 @@ static void gfs2_evict_inode(struct inode *inode)
 	goto out_unlock;
 
 out_truncate:
+	gfs2_log_flush(sdp, ip->i_gl);
+	write_inode_now(inode, 1);
+	gfs2_ail_flush(ip->i_gl, 0);
+
 	/* Case 2 starts here */
 	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
 	if (error)
@@ -1552,6 +1574,7 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (ip) {
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
+		ip->i_rgd = NULL;
 	}
 	return &ip->i_inode;
 }
@@ -1572,6 +1595,7 @@ const struct super_operations gfs2_super_ops = {
 	.alloc_inode		= gfs2_alloc_inode,
 	.destroy_inode		= gfs2_destroy_inode,
 	.write_inode		= gfs2_write_inode,
+	.dirty_inode		= gfs2_dirty_inode,
 	.evict_inode		= gfs2_evict_inode,
 	.put_super		= gfs2_put_super,
 	.sync_fs		= gfs2_sync_fs,

fs/gfs2/trans.c

@@ -185,8 +185,3 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
 	gfs2_log_unlock(sdp);
 }
 
-void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd)
-{
-	lops_add(rgd->rd_sbd, &rgd->rd_le);
-}
-

fs/gfs2/trans.h

@@ -28,20 +28,20 @@ struct gfs2_glock;
 
 /* reserve either the number of blocks to be allocated plus the rg header
  * block, or all of the blocks in the rg, whichever is smaller */
-static inline unsigned int gfs2_rg_blocks(const struct gfs2_alloc *al)
+static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip)
 {
-	return (al->al_requested < al->al_rgd->rd_length)?
-	       al->al_requested + 1 : al->al_rgd->rd_length;
+	const struct gfs2_alloc *al = ip->i_alloc;
+	if (al->al_requested < ip->i_rgd->rd_length)
+		return al->al_requested + 1;
+	return ip->i_rgd->rd_length;
 }
 
-int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
-		     unsigned int revokes);
+extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+			    unsigned int revokes);
 
-void gfs2_trans_end(struct gfs2_sbd *sdp);
-
-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, unsigned int len);
-void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
+extern void gfs2_trans_end(struct gfs2_sbd *sdp);
+extern void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
+extern void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+extern void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
 
 #endif /* __TRANS_DOT_H__ */

fs/gfs2/xattr.c

@@ -332,15 +332,8 @@ static int ea_remove_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh,
 	if (error)
 		goto out_alloc;
 
-	error = gfs2_rindex_hold(GFS2_SB(&ip->i_inode), &al->al_ri_gh);
-	if (error)
-		goto out_quota;
-
 	error = ea_dealloc_unstuffed(ip, bh, ea, prev, (leave) ? &error : NULL);
 
-	gfs2_glock_dq_uninit(&al->al_ri_gh);
-
-out_quota:
 	gfs2_quota_unhold(ip);
 out_alloc:
 	gfs2_alloc_put(ip);
@@ -734,7 +727,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er,
 		goto out_gunlock_q;
 
 	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode),
-				 blks + gfs2_rg_blocks(al) +
+				 blks + gfs2_rg_blocks(ip) +
 				 RES_DINODE + RES_STATFS + RES_QUOTA, 0);
 	if (error)
 		goto out_ipres;
@@ -1296,7 +1289,8 @@ static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip,
 
 int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct inode *inode = &ip->i_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_ea_location el;
 	int error;
 
@@ -1319,7 +1313,7 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 	if (error)
 		return error;
 
-	error = gfs2_setattr_simple(ip, attr);
+	error = gfs2_setattr_simple(inode, attr);
 	gfs2_trans_end(sdp);
 	return error;
 }
@@ -1362,14 +1356,14 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip)
 			blen++;
 		else {
 			if (bstart)
-				gfs2_rlist_add(sdp, &rlist, bstart);
+				gfs2_rlist_add(ip, &rlist, bstart);
 			bstart = bn;
 			blen = 1;
 		}
 		blks++;
 	}
 	if (bstart)
-		gfs2_rlist_add(sdp, &rlist, bstart);
+		gfs2_rlist_add(ip, &rlist, bstart);
 	else
 		goto out;
 
@@ -1501,24 +1495,18 @@ int gfs2_ea_dealloc(struct gfs2_inode *ip)
 	if (error)
 		goto out_alloc;
 
-	error = gfs2_rindex_hold(GFS2_SB(&ip->i_inode), &al->al_ri_gh);
-	if (error)
-		goto out_quota;
-
 	error = ea_foreach(ip, ea_dealloc_unstuffed, NULL);
 	if (error)
-		goto out_rindex;
+		goto out_quota;
 
 	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
 		error = ea_dealloc_indirect(ip);
 		if (error)
-			goto out_rindex;
+			goto out_quota;
 	}
 
 	error = ea_dealloc_block(ip);
 
-out_rindex:
-	gfs2_glock_dq_uninit(&al->al_ri_gh);
 out_quota:
 	gfs2_quota_unhold(ip);
 out_alloc: