Pre-pull patch posting

index 3f0974e..6a3eeba 100644
@@ -545,12 +545,14 @@ static int rq_demote(struct gfs2_glock *gl)
 		return 0;
 	}
 	set_bit(GLF_LOCK, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
 	if (gl->gl_demote_state == LM_ST_UNLOCKED ||
-	    gl->gl_state != LM_ST_EXCLUSIVE)
+	    gl->gl_state != LM_ST_EXCLUSIVE) {
+		spin_unlock(&gl->gl_spin);
 		gfs2_glock_drop_th(gl);
-	else
+	} else {
+		spin_unlock(&gl->gl_spin);
 		gfs2_glock_xmote_th(gl, NULL);
+	}
 	spin_lock(&gl->gl_spin);
 
 	return 0;

@@ -760,10 +762,20 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret)
 
 	if (!gh) {
 		gl->gl_stamp = jiffies;
-		if (ret & LM_OUT_CANCELED)
+		if (ret & LM_OUT_CANCELED) {
 			op_done = 0;
-		else
+		} else {
+			spin_lock(&gl->gl_spin);
+			if (gl->gl_state != gl->gl_demote_state) {
+				gl->gl_req_bh = NULL;
+				spin_unlock(&gl->gl_spin);
+				gfs2_glock_drop_th(gl);
+				gfs2_glock_put(gl);
+				return;
+			}
 			gfs2_demote_wake(gl);
+			spin_unlock(&gl->gl_spin);
+		}
 	} else {
 		spin_lock(&gl->gl_spin);
 		list_del_init(&gh->gh_list);

@@ -817,7 +829,7 @@ out:
  *
  */
 
-void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
+static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	int flags = gh ? gh->gh_flags : 0;

index 6a3eeba..6b6ae45 100644
@@ -697,8 +697,9 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state, int remot
 			}
 			return;
 		}
-	} else if (gl->gl_demote_state != LM_ST_UNLOCKED) {
-		gl->gl_demote_state = state;
+	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&
+			gl->gl_demote_state != state) {
+		gl->gl_demote_state = LM_ST_UNLOCKED;
 	}
 	spin_unlock(&gl->gl_spin);
 }

index 6b6ae45..d403fd7 100644
@@ -25,8 +25,6 @@
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
-#include <linux/module.h>
-#include <linux/kallsyms.h>
 
 #include "gfs2.h"
 #include "incore.h"

index 24d70f7..9e8265d 100644
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/list.h>

index 0d149c8..d3b8ce6 100644
@@ -9,7 +9,6 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/fs.h>

index 911c115..5b8b994 100644
@@ -69,7 +69,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
 			mark_inode_dirty(inode);
 			break;
 		} else if (PTR_ERR(inode) != -EEXIST ||
-			   (nd->intent.open.flags & O_EXCL)) {
+			   (nd && (nd->intent.open.flags & O_EXCL))) {
 			gfs2_holder_uninit(ghs);
 			return PTR_ERR(inode);
 		}

index d403fd7..e4bc8ae 100644
@@ -46,7 +46,6 @@ struct glock_iter {
 	int hash;                     /* hash bucket index         */
 	struct gfs2_sbd *sdp;         /* incore superblock         */
 	struct gfs2_glock *gl;        /* current glock struct      */
-	struct hlist_head *hb_list;   /* current hash bucket ptr   */
 	struct seq_file *seq;         /* sequence file for debugfs */
 	char string[512];             /* scratch space             */
 };

@@ -1990,47 +1989,38 @@ int __init gfs2_glock_init(void)
 
 static int gfs2_glock_iter_next(struct glock_iter *gi)
 {
+	struct gfs2_glock *gl;
+
 	read_lock(gl_lock_addr(gi->hash));
-	while (1) {
-		if (!gi->hb_list) {  /* If we don't have a hash bucket yet */
-			gi->hb_list = &gl_hash_table[gi->hash].hb_list;
-			if (hlist_empty(gi->hb_list)) {
-				read_unlock(gl_lock_addr(gi->hash));
-				gi->hash++;
-				read_lock(gl_lock_addr(gi->hash));
-				gi->hb_list = NULL;
-				if (gi->hash >= GFS2_GL_HASH_SIZE) {
-					read_unlock(gl_lock_addr(gi->hash));
-					return 1;
-				}
-				else
-					continue;
-			}
-			if (!hlist_empty(gi->hb_list)) {
-				gi->gl = list_entry(gi->hb_list->first,
-						    struct gfs2_glock,
-						    gl_list);
-			}
-		} else {
-			if (gi->gl->gl_list.next == NULL) {
-				read_unlock(gl_lock_addr(gi->hash));
-				gi->hash++;
-				read_lock(gl_lock_addr(gi->hash));
-				gi->hb_list = NULL;
-				continue;
-			}
-			gi->gl = list_entry(gi->gl->gl_list.next,
-					    struct gfs2_glock, gl_list);
-		}
+	gl = gi->gl;
+	if (gl) {
+		gi->gl = hlist_entry(gl->gl_list.next, struct gfs2_glock,
+				     gl_list);
 		if (gi->gl)
-			break;
+			gfs2_glock_hold(gi->gl);
 	}
 	read_unlock(gl_lock_addr(gi->hash));
+	if (gl)
+		gfs2_glock_put(gl);
+
+	while(gi->gl == NULL) {
+		gi->hash++;
+		if (gi->hash >= GFS2_GL_HASH_SIZE)
+			return 1;
+		read_lock(gl_lock_addr(gi->hash));
+		gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+				     struct gfs2_glock, gl_list);
+		if (gi->gl)
+			gfs2_glock_hold(gi->gl);
+		read_unlock(gl_lock_addr(gi->hash));
+	}
 	return 0;
 }
 
 static void gfs2_glock_iter_free(struct glock_iter *gi)
 {
+	if (gi->gl)
+		gfs2_glock_put(gi->gl);
 	kfree(gi);
 }
 

@@ -2044,12 +2034,17 @@ static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
 
 	gi->sdp = sdp;
 	gi->hash = 0;
-	gi->gl = NULL;
-	gi->hb_list = NULL;
 	gi->seq = NULL;
 	memset(gi->string, 0, sizeof(gi->string));
 
-	if (gfs2_glock_iter_next(gi)) {
+	read_lock(gl_lock_addr(gi->hash));
+	gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+			     struct gfs2_glock, gl_list);
+	if (gi->gl)
+		gfs2_glock_hold(gi->gl);
+	read_unlock(gl_lock_addr(gi->hash));
+
+	if (!gi->gl && gfs2_glock_iter_next(gi)) {
 		gfs2_glock_iter_free(gi);
 		return NULL;
 	}

@@ -2066,7 +2061,7 @@ static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
 	if (!gi)
 		return NULL;
 
-	while (n--) {
+	while(n--) {
 		if (gfs2_glock_iter_next(gi)) {
 			gfs2_glock_iter_free(gi);
 			return NULL;

@@ -2093,7 +2088,9 @@ static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
 
 static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
 {
-	/* nothing for now */
+	struct glock_iter *gi = iter_ptr;
+	if (gi)
+		gfs2_glock_iter_free(gi);
 }
 
 static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)

index 3b395c4..a0371f8 100644
@@ -117,7 +117,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 	struct buffer_head *bh;
 	struct gfs2_log_descriptor *ld;
 	struct gfs2_bufdata *bd1 = NULL, *bd2;
-	unsigned int total = sdp->sd_log_num_buf;
+	unsigned int total;
 	unsigned int offset = BUF_OFFSET;
 	unsigned int limit;
 	unsigned int num;

@@ -127,12 +127,16 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 	limit = buf_limit(sdp);
 	/* for 4k blocks, limit = 503 */
 
+	gfs2_log_lock(sdp);
+	total = sdp->sd_log_num_buf;
 	bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list);
 	while(total) {
 		num = total;
 		if (total > limit)
 			num = limit;
+		gfs2_log_unlock(sdp);
 		bh = gfs2_log_get_buf(sdp);
+		gfs2_log_lock(sdp);
 		ld = (struct gfs2_log_descriptor *)bh->b_data;
 		ptr = (__be64 *)(bh->b_data + offset);
 		ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);

@@ -152,21 +156,27 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 				break;
 		}
 
+		gfs2_log_unlock(sdp);
 		set_buffer_dirty(bh);
 		ll_rw_block(WRITE, 1, &bh);
+		gfs2_log_lock(sdp);
 
 		n = 0;
 		list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
 					     bd_le.le_list) {
+			gfs2_log_unlock(sdp);
 			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
 			set_buffer_dirty(bh);
 			ll_rw_block(WRITE, 1, &bh);
+			gfs2_log_lock(sdp);
 			if (++n >= num)
 				break;
 		}
 
+		BUG_ON(total < num);
 		total -= num;
 	}
+	gfs2_log_unlock(sdp);
 }
 
 static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)

@@ -524,7 +534,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 	struct gfs2_log_descriptor *ld;
 	unsigned int limit;
 	unsigned int total_dbuf;
-	unsigned int total_jdata = sdp->sd_log_num_jdata;
+	unsigned int total_jdata;
 	unsigned int num, n;
 	__be64 *ptr = NULL;
 

@@ -536,6 +546,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 	 */
 	gfs2_log_lock(sdp);
 	total_dbuf = sdp->sd_log_num_databuf;
+	total_jdata = sdp->sd_log_num_jdata;
 	bd2 = bd1 = list_prepare_entry(bd1, &sdp->sd_log_le_databuf,
 				       bd_le.le_list);
 	while(total_dbuf) {

@@ -621,10 +632,10 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 		}
 		gfs2_log_unlock(sdp);
 		if (bh) {
-			set_buffer_mapped(bh);
 			set_buffer_dirty(bh);
 			ll_rw_block(WRITE, 1, &bh);
 			bh = NULL;
+			ptr = NULL;
 		}
 		n = 0;
 		gfs2_log_lock(sdp);

index f49a12e..f7c0608 100644
@@ -83,11 +83,6 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 
 			gfs2_assert(sdp, bd->bd_ail == ai);
 
-			if (!bh){
-				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
-                                continue;
-                        }
-
 			if (!buffer_busy(bh)) {
 				if (!buffer_uptodate(bh)) {
 					gfs2_log_unlock(sdp);

@@ -130,11 +125,6 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl
 					 bd_ail_st_list) {
 		bh = bd->bd_bh;
 
-		if (!bh){
-			list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
-			continue;
-		}
-
 		gfs2_assert(sdp, bd->bd_ail == ai);
 
 		if (buffer_busy(bh)) {

@@ -155,13 +145,14 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl
 
 static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
 {
-	struct list_head *head = &sdp->sd_ail1_list;
+	struct list_head *head;
 	u64 sync_gen;
 	struct list_head *first;
 	struct gfs2_ail *first_ai, *ai, *tmp;
 	int done = 0;
 
 	gfs2_log_lock(sdp);
+	head = &sdp->sd_ail1_list;
 	if (list_empty(head)) {
 		gfs2_log_unlock(sdp);
 		return;

index ce48c45..b93ac45 100644
@@ -31,6 +31,7 @@
 #include "inode.h"
 
 #define BFITNOENT ((u32)~0)
+#define NO_BLOCK ((u64)~0)
 
 /*
  * These routines are used by the resource group routines (rgrp.c)

@@ -116,8 +117,7 @@ static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
  * @buffer: the buffer that holds the bitmaps
  * @buflen: the length (in bytes) of the buffer
  * @goal: start search at this block's bit-pair (within @buffer)
- * @old_state: GFS2_BLKST_XXX the state of the block we're looking for;
- *       bit 0 = alloc(1)/free(0), bit 1 = meta(1)/data(0)
+ * @old_state: GFS2_BLKST_XXX the state of the block we're looking for.
  *
  * Scope of @goal and returned block number is only within this bitmap buffer,
  * not entire rgrp or filesystem.  @buffer will be offset from the actual

@@ -137,9 +137,13 @@ static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer,
 	byte = buffer + (goal / GFS2_NBBY);
 	bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE;
 	end = buffer + buflen;
-	alloc = (old_state & 1) ? 0 : 0x55;
+	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;
 

@@ -859,19 +863,21 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
 static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 {
 	struct inode *inode;
-	u32 goal = 0;
+	u32 goal = 0, block;
 	u64 no_addr;
 
 	for(;;) {
 		if (goal >= rgd->rd_data)
 			break;
-		goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
-				    GFS2_BLKST_UNLINKED);
-		if (goal == BFITNOENT)
+		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
+				     GFS2_BLKST_UNLINKED);
+		if (block == BFITNOENT)
 			break;
-		no_addr = goal + rgd->rd_data0;
+		/* rgblk_search can return a block < goal, so we need to
+		   keep it marching forward. */
+		no_addr = block + rgd->rd_data0;
 		goal++;
-		if (no_addr < *last_unlinked)
+		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
 			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,

@@ -1152,7 +1158,7 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
 	struct gfs2_alloc *al = &ip->i_alloc;
 	struct inode *inode;
 	int error = 0;
-	u64 last_unlinked = 0;
+	u64 last_unlinked = NO_BLOCK;
 
 	if (gfs2_assert_warn(sdp, al->al_requested))
 		return -EINVAL;

@@ -1305,9 +1311,7 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 		goal = 0;
 	}
 
-	if (old_state != new_state) {
-		gfs2_assert_withdraw(rgd->rd_sbd, blk != BFITNOENT);
-
+	if (blk != BFITNOENT && old_state != new_state) {
 		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
 		gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset,
 			    bi->bi_len, blk, new_state);

index fba1f1d..1f7b038 100644
@@ -346,15 +346,16 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 
 static unsigned int dev_poll(struct file *file, poll_table *wait)
 {
+	unsigned int mask = 0;
+
 	poll_wait(file, &send_wq, wait);
 
 	spin_lock(&ops_lock);
-	if (!list_empty(&send_list)) {
-		spin_unlock(&ops_lock);
-		return POLLIN | POLLRDNORM;
-	}
+	if (!list_empty(&send_list))
+		mask = POLLIN | POLLRDNORM;
 	spin_unlock(&ops_lock);
-	return 0;
+
+	return mask;
 }
 
 static const struct file_operations dev_fops = {

index f7c0608..00ab6c0 100644
@@ -219,6 +219,7 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 {
 	struct list_head *head = &ai->ai_ail2_list;
 	struct gfs2_bufdata *bd;
+	struct gfs2_inode *bh_ip;
 
 	while (!list_empty(head)) {
 		bd = list_entry(head->prev, struct gfs2_bufdata,

@@ -228,6 +229,8 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 		list_del(&bd->bd_ail_st_list);
 		list_del(&bd->bd_ail_gl_list);
 		atomic_dec(&bd->bd_gl->gl_ail_count);
+		bh_ip = GFS2_I(bd->bd_bh->b_page->mapping->host);
+		gfs2_meta_cache_flush(bh_ip);
 		brelse(bd->bd_bh);
 	}
 }

index 1ab3e9d..aa8dbf3 100644
@@ -200,28 +200,28 @@ static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er)
 	return gfs2_ea_remove_i(ip, er);
 }
 
-static struct gfs2_eattr_operations gfs2_user_eaops = {
+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_name = "user",
 };
 
-struct gfs2_eattr_operations gfs2_system_eaops = {
+const struct gfs2_eattr_operations gfs2_system_eaops = {
 	.eo_get = system_eo_get,
 	.eo_set = system_eo_set,
 	.eo_remove = system_eo_remove,
 	.eo_name = "system",
 };
 
-static struct gfs2_eattr_operations gfs2_security_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_name = "security",
 };
 
-struct gfs2_eattr_operations *gfs2_ea_ops[] = {
+const struct gfs2_eattr_operations *gfs2_ea_ops[] = {
 	NULL,
 	&gfs2_user_eaops,
 	&gfs2_system_eaops,

index 508b4f7..da2f7fb 100644
@@ -22,9 +22,9 @@ struct gfs2_eattr_operations {
 
 unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name);
 
-extern struct gfs2_eattr_operations gfs2_system_eaops;
+extern const struct gfs2_eattr_operations gfs2_system_eaops;
 
-extern struct gfs2_eattr_operations *gfs2_ea_ops[];
+extern const struct gfs2_eattr_operations *gfs2_ea_ops[];
 
 #endif /* __EAOPS_DOT_H__ */
 

index e4bc8ae..0054b7d 100644
@@ -2103,7 +2103,7 @@ static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
 	return 0;
 }
 
-static struct seq_operations gfs2_glock_seq_ops = {
+static const struct seq_operations gfs2_glock_seq_ops = {
 	.start = gfs2_glock_seq_start,
 	.next  = gfs2_glock_seq_next,
 	.stop  = gfs2_glock_seq_stop,

index cf5aa50..9a5e840 100644
@@ -28,6 +28,7 @@
 #include "lm.h"
 #include "mount.h"
 #include "ops_fstype.h"
+#include "ops_dentry.h"
 #include "ops_super.h"
 #include "recovery.h"
 #include "rgrp.h"

@@ -38,8 +39,6 @@
 #define DO 0
 #define UNDO 1
 
-extern struct dentry_operations gfs2_dops;
-
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp;

index 3548d9f..3731ab0 100644
@@ -35,30 +35,6 @@
    The kthread functions used to start these daemons block and flush signals. */
 
 /**
- * gfs2_scand - Look for cached glocks and inodes to toss from memory
- * @sdp: Pointer to GFS2 superblock
- *
- * One of these daemons runs, finding candidates to add to sd_reclaim_list.
- * See gfs2_glockd()
- */
-
-int gfs2_scand(void *data)
-{
-	struct gfs2_sbd *sdp = data;
-	unsigned long t;
-
-	while (!kthread_should_stop()) {
-		gfs2_scand_internal(sdp);
-		t = gfs2_tune_get(sdp, gt_scand_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
-		schedule_timeout_interruptible(t);
-	}
-
-	return 0;
-}
-
-/**
  * gfs2_glockd - Reclaim unused glock structures
  * @sdp: Pointer to GFS2 superblock
  *

index 8010071..0de9b35 100644
@@ -10,7 +10,6 @@
 #ifndef __DAEMON_DOT_H__
 #define __DAEMON_DOT_H__
 
-int gfs2_scand(void *data);
 int gfs2_glockd(void *data);
 int gfs2_recoverd(void *data);
 int gfs2_logd(void *data);

108 lines not on this page · raw message

index 7721ca3..f7a8e62 100644
@@ -132,11 +132,11 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data);
 
 void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl);
 void gfs2_reclaim_glock(struct gfs2_sbd *sdp);
-
-void gfs2_scand_internal(struct gfs2_sbd *sdp);
 void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
 
 int __init gfs2_glock_init(void);
+void gfs2_glock_exit(void);
+
 int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
 void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
 int gfs2_register_debugfs(void);

index 170ba93..1390b30 100644
@@ -429,7 +429,6 @@ struct gfs2_tune {
 	unsigned int gt_log_flush_secs;
 	unsigned int gt_jindex_refresh_secs; /* Check for new journal index */
 
-	unsigned int gt_scand_secs;
 	unsigned int gt_recoverd_secs;
 	unsigned int gt_logd_secs;
 	unsigned int gt_quotad_secs;

@@ -574,7 +573,6 @@ struct gfs2_sbd {
 
 	/* Daemon stuff */
 
-	struct task_struct *sd_scand_process;
 	struct task_struct *sd_recoverd_process;
 	struct task_struct *sd_logd_process;
 	struct task_struct *sd_quotad_process;

index d5d4e68..79c91fd 100644
@@ -107,6 +107,8 @@ static int __init init_gfs2_fs(void)
 fail_unregister:
 	unregister_filesystem(&gfs2_fs_type);
 fail:
+	gfs2_glock_exit();
+
 	if (gfs2_bufdata_cachep)
 		kmem_cache_destroy(gfs2_bufdata_cachep);
 

@@ -127,6 +129,7 @@ fail:
 
 static void __exit exit_gfs2_fs(void)
 {
+	gfs2_glock_exit();
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);

index 9a5e840..58c730b 100644
@@ -160,14 +160,6 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
 	if (undo)
 		goto fail_trans;
 
-	p = kthread_run(gfs2_scand, sdp, "gfs2_scand");
-	error = IS_ERR(p);
-	if (error) {
-		fs_err(sdp, "can't start scand thread: %d\n", error);
-		return error;
-	}
-	sdp->sd_scand_process = p;
-
 	for (sdp->sd_glockd_num = 0;
 	     sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd;
 	     sdp->sd_glockd_num++) {

@@ -228,7 +220,6 @@ fail:
 	while (sdp->sd_glockd_num--)
 		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
 
-	kthread_stop(sdp->sd_scand_process);
 	return error;
 }
 

index 603d940..4316690 100644
@@ -92,7 +92,6 @@ static void gfs2_put_super(struct super_block *sb)
 	kthread_stop(sdp->sd_recoverd_process);
 	while (sdp->sd_glockd_num--)
 		kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
-	kthread_stop(sdp->sd_scand_process);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		error = gfs2_make_fs_ro(sdp);

index f916b97..5589802 100644
@@ -58,7 +58,6 @@ void gfs2_tune_init(struct gfs2_tune *gt)
 	gt->gt_incore_log_blocks = 1024;
 	gt->gt_log_flush_secs = 60;
 	gt->gt_jindex_refresh_secs = 60;
-	gt->gt_scand_secs = 15;
 	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quotad_secs = 5;

index c26c21b..ba3a172 100644
@@ -442,7 +442,6 @@ TUNE_ATTR(quota_simul_sync, 1);
 TUNE_ATTR(quota_cache_secs, 1);
 TUNE_ATTR(stall_secs, 1);
 TUNE_ATTR(statfs_quantum, 1);
-TUNE_ATTR_DAEMON(scand_secs, scand_process);
 TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process);
 TUNE_ATTR_DAEMON(logd_secs, logd_process);
 TUNE_ATTR_DAEMON(quotad_secs, quotad_process);

@@ -464,7 +463,6 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_quota_cache_secs.attr,
 	&tune_attr_stall_secs.attr,
 	&tune_attr_statfs_quantum.attr,
-	&tune_attr_scand_secs.attr,
 	&tune_attr_recoverd_secs.attr,
 	&tune_attr_logd_secs.attr,
 	&tune_attr_quotad_secs.attr,

index b93ac45..2d7f7ea 100644
@@ -865,12 +865,15 @@ static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 	struct inode *inode;
 	u32 goal = 0, block;
 	u64 no_addr;
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
 
 	for(;;) {
 		if (goal >= rgd->rd_data)
 			break;
+		down_write(&sdp->sd_log_flush_lock);
 		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
 				     GFS2_BLKST_UNLINKED);
+		up_write(&sdp->sd_log_flush_lock);
 		if (block == BFITNOENT)
 			break;
 		/* rgblk_search can return a block < goal, so we need to

@@ -1295,7 +1298,9 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 	   allocatable block anywhere else, we want to be able wrap around and
 	   search in the first part of our first-searched bit block.  */
 	for (x = 0; x <= length; x++) {
-		if (bi->bi_clone)
+		/* 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,
 					  bi->bi_len, goal, old_state);
 		else

index 58c730b..f0bcaa2 100644
@@ -358,7 +358,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 
 		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | GL_EXACT,
+					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
 					   &sdp->sd_jinode_gh);
 		if (error) {
 			fs_err(sdp, "can't acquire journal inode glock: %d\n",

index 5ada38c..beb6c7a 100644
@@ -469,7 +469,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
 		};
 
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP, &ji_gh);
+					   LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
 		if (error)
 			goto fail_gunlock_j;
 	} else {

index f0bcaa2..32b2859 100644
@@ -808,7 +808,6 @@ static struct super_block* get_gfs2_sb(const char *dev_name)
 	struct nameidata nd;
 	struct file_system_type *fstype;
 	struct super_block *sb = NULL, *s;
-	struct list_head *l;
 	int error;
 
 	error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);

@@ -820,8 +819,7 @@ static struct super_block* get_gfs2_sb(const char *dev_name)
 	error = vfs_getattr(nd.mnt, nd.dentry, &stat);
 
 	fstype = get_fs_type("gfs2");
-	list_for_each(l, &fstype->fs_supers) {
-		s = list_entry(l, struct super_block, s_instances);
+	list_for_each_entry(s, &fstype->fs_supers, s_instances) {
 		if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
 		    (S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
 			sb = s;

index 32b2859..25cfab9 100644
@@ -849,7 +849,7 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
 		error = -ENOENT;
 		goto error;
 	}
-	sdp = (struct gfs2_sbd*) sb->s_fs_info;
+	sdp = sb->s_fs_info;
 	if (sdp->sd_vfs_meta) {
 		printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
 		error = -EBUSY;

index 25cfab9..6c820cb 100644
@@ -144,7 +144,8 @@ static int init_names(struct gfs2_sbd *sdp, int silent)
 	snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
 	snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
 
-	while ((table = strchr(sdp->sd_table_name, '/')))
+	table = sdp->sd_table_name;
+	while ((table = strchr(table, '/')))
 		*table = '_';
 
 out:

index 6e546ee..5dfa465 100644
@@ -614,6 +614,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	s64 value;
 	int err = -EIO;
 
+	if (gfs2_is_stuffed(ip)) {
+		struct gfs2_alloc *al = NULL;
+		al = gfs2_alloc_get(ip);
+		/* just request 1 blk */
+		al->al_requested = 1;
+		gfs2_inplace_reserve(ip);
+		gfs2_unstuff_dinode(ip, NULL);
+		gfs2_inplace_release(ip);
+		gfs2_alloc_put(ip);
+	}
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return -ENOMEM;

index 6c820cb..c1c6672 100644
@@ -292,8 +292,9 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
 		fs_err(sdp, "can't get root dentry\n");
 		error = -ENOMEM;
 		iput(inode);
-	}
-	sb->s_root->d_op = &gfs2_dops;
+	} else
+		sb->s_root->d_op = &gfs2_dops;
+	
 out:
 	gfs2_glock_dq_uninit(&sb_gh);
 	return error;

index 5dfa465..addb51e 100644
@@ -70,6 +70,7 @@ struct gfs2_quota_host {
 	u64 qu_limit;
 	u64 qu_warn;
 	s64 qu_value;
+	u32 qu_ll_next;
 };
 
 struct gfs2_quota_change_host {

@@ -580,6 +581,7 @@ static void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf)
 	qu->qu_limit = be64_to_cpu(str->qu_limit);
 	qu->qu_warn = be64_to_cpu(str->qu_warn);
 	qu->qu_value = be64_to_cpu(str->qu_value);
+	qu->qu_ll_next = be32_to_cpu(str->qu_ll_next);
 }
 
 static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf)

@@ -589,6 +591,7 @@ static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf)
 	str->qu_limit = cpu_to_be64(qu->qu_limit);
 	str->qu_warn = cpu_to_be64(qu->qu_warn);
 	str->qu_value = cpu_to_be64(qu->qu_value);
+	str->qu_ll_next = cpu_to_be32(qu->qu_ll_next);
 	memset(&str->qu_reserved, 0, sizeof(str->qu_reserved));
 }
 

index a44a6a0..c3c19f9 100644
@@ -170,6 +170,33 @@ struct gfs2_rgrp {
 };
 
 /*
+ * quota linked list: user quotas and group quotas form two separate 
+ * singly linked lists. ll_next stores uids or gids of next quotas in the 
+ * linked list.
+
+Given the uid/gid, how to calculate the quota file offsets for the corresponding
+gfs2_quota structures on disk:
+
+for user quotas, given uid,
+offset = uid * sizeof(struct gfs2_quota);
+
+for group quotas, given gid,
+offset = (gid * sizeof(struct gfs2_quota)) + sizeof(struct gfs2_quota);
+
+
+  uid:0   gid:0       uid:12   gid:12      uid:17   gid:17     uid:5142 gid:5142
++-------+-------+    +-------+-------+    +-------+- - - -+    +- - - -+-------+
+| valid | valid | :: | valid | valid | :: | valid | inval | :: | inval | valid |
++-------+-------+    +-------+-------+    +-------+- - - -+    +- - - -+-------+
+next:12   next:12    next:17 next:5142    next:NULL                    next:NULL
+    |       |            |       |            |<-- user quota list         |
+     \______|___________/ \______|___________/         group quota list -->|
+            |                    |                                         |
+             \__________________/ \_______________________________________/
+
+*/
+
+/*
  * quota structure
  */
 

@@ -177,7 +204,8 @@ struct gfs2_quota {
 	__be64 qu_limit;
 	__be64 qu_warn;
 	__be64 qu_value;
-	__u8 qu_reserved[64];
+	__be32 qu_ll_next; /* location of next quota in list */
+	__u8 qu_reserved[60];
 };
 
 /*

index 777ca46..88342e0 100644
@@ -156,9 +156,11 @@ static void inode_go_sync(struct gfs2_glock *gl)
 		ip = NULL;
 
 	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
-		if (ip)
+		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);
 		if (ip) {
 			struct address_space *mapping = ip->i_inode.i_mapping;

index 00ab6c0..d0e6b42 100644
@@ -229,8 +229,10 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 		list_del(&bd->bd_ail_st_list);
 		list_del(&bd->bd_ail_gl_list);
 		atomic_dec(&bd->bd_gl->gl_ail_count);
-		bh_ip = GFS2_I(bd->bd_bh->b_page->mapping->host);
-		gfs2_meta_cache_flush(bh_ip);
+		if (bd->bd_bh->b_page->mapping) {
+			bh_ip = GFS2_I(bd->bd_bh->b_page->mapping->host);
+			gfs2_meta_cache_flush(bh_ip);
+		}
 		brelse(bd->bd_bh);
 	}
 }

176 lines not on this page · raw message

index c1c6672..9e0e9be 100644
@@ -35,6 +35,7 @@
 #include "super.h"
 #include "sys.h"
 #include "util.h"
+#include "log.h"
 
 #define DO 0
 #define UNDO 1

@@ -887,6 +888,7 @@ error:
 static void gfs2_kill_sb(struct super_block *sb)
 {
 	gfs2_delete_debugfs_file(sb->s_fs_info);
+	gfs2_meta_syncfs(sb->s_fs_info);
 	kill_block_super(sb);
 }
 

index 2beb2f4..08c6dd0 100644
@@ -1043,6 +1043,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	error = gfs2_meta_inode_buffer(dip, &dibh);
 	if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) {
+		gfs2_trans_add_bh(dip->i_gl, dibh, 1);
 		dip->i_di.di_blocks++;
 		gfs2_set_inode_blocks(&dip->i_inode);
 		gfs2_dinode_out(dip, dibh->b_data);

index 4864659..b941f9f 100644
@@ -42,6 +42,7 @@ enum {
 	Opt_nosuiddir,
 	Opt_data_writeback,
 	Opt_data_ordered,
+	Opt_err,
 };
 
 static match_table_t tokens = {

@@ -64,7 +65,8 @@ static match_table_t tokens = {
 	{Opt_suiddir, "suiddir"},
 	{Opt_nosuiddir, "nosuiddir"},
 	{Opt_data_writeback, "data=writeback"},
-	{Opt_data_ordered, "data=ordered"}
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_err, NULL}
 };
 
 /**

@@ -237,6 +239,7 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
 		case Opt_data_ordered:
 			args->ar_data = GFS2_DATA_ORDERED;
 			break;
+		case Opt_err:
 		default:
 			fs_info(sdp, "unknown option: %s\n", o);
 			error = -EINVAL;

index cd805a6..9b89904 100644
@@ -1085,6 +1085,33 @@ static int do_shrink(struct gfs2_inode *ip, u64 size)
 	return error;
 }
 
+static int do_touch(struct gfs2_inode *ip, u64 size)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (error)
+		return error;
+
+	down_write(&ip->i_rw_mutex);
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto do_touch_out;
+
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_dinode_out(ip, dibh->b_data);
+	brelse(dibh);
+
+do_touch_out:
+	up_write(&ip->i_rw_mutex);
+	gfs2_trans_end(sdp);
+	return error;
+}
+
 /**
  * gfs2_truncatei - make a file a given size
  * @ip: the inode

@@ -1105,8 +1132,11 @@ int gfs2_truncatei(struct gfs2_inode *ip, u64 size)
 
 	if (size > ip->i_di.di_size)
 		error = do_grow(ip, size);
-	else
+	else if (size < ip->i_di.di_size)
 		error = do_shrink(ip, size);
+	else
+		/* update time stamps */
+		error = do_touch(ip, size);
 
 	return error;
 }

index 9e9d2e8..62a8a6c 100644
@@ -334,18 +334,8 @@ static void close_connection(struct connection *con, bool and_other)
 		con->rx_page = NULL;
 	}
 
-	/* If we are an 'othercon' then NULL the pointer to us
-	   from the parent and tidy ourself up */
-	if (test_bit(CF_IS_OTHERCON, &con->flags)) {
-		struct connection *parent = __nodeid2con(con->nodeid, 0);
-		parent->othercon = NULL;
-		kmem_cache_free(con_cache, con);
-	}
-	else {
-		/* Parent connections get reused */
-		con->retries = 0;
-		mutex_unlock(&con->sock_mutex);
-	}
+	con->retries = 0;
+	mutex_unlock(&con->sock_mutex);
 }
 
 /* We only send shutdown messages to nodes that are not part of the cluster */

@@ -731,6 +721,8 @@ static int tcp_accept_from_sock(struct connection *con)
 			INIT_WORK(&othercon->swork, process_send_sockets);
 			INIT_WORK(&othercon->rwork, process_recv_sockets);
 			set_bit(CF_IS_OTHERCON, &othercon->flags);
+		}
+		if (!othercon->sock) {
 			newcon->othercon = othercon;
 			othercon->sock = newsock;
 			newsock->sk->sk_user_data = othercon;

index 559937c..3d94918 100644
@@ -1844,7 +1844,7 @@ static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
 
 	spin_lock(&gl->gl_spin);
 
-	print_dbg(gi, "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
+	print_dbg(gi, "Glock 0x%p (%u, 0x%llx)\n", gl, gl->gl_name.ln_type,
 		   (unsigned long long)gl->gl_name.ln_number);
 	print_dbg(gi, "  gl_flags =");
 	for (x = 0; x < 32; x++) {

@@ -2024,20 +2024,21 @@ static int gfs2_glock_iter_next(struct glock_iter *gi)
 {
 	struct gfs2_glock *gl;
 
+restart:
 	read_lock(gl_lock_addr(gi->hash));
 	gl = gi->gl;
 	if (gl) {
-		gi->gl = hlist_entry(gl->gl_list.next, struct gfs2_glock,
-				     gl_list);
+		gi->gl = hlist_entry(gl->gl_list.next,
+				     struct gfs2_glock, gl_list);
 		if (gi->gl)
 			gfs2_glock_hold(gi->gl);
 	}
 	read_unlock(gl_lock_addr(gi->hash));
 	if (gl)
 		gfs2_glock_put(gl);
-
-	while(gi->gl == NULL) {
+	if (gl && gi->gl == NULL)
 		gi->hash++;
+	while(gi->gl == NULL) {
 		if (gi->hash >= GFS2_GL_HASH_SIZE)
 			return 1;
 		read_lock(gl_lock_addr(gi->hash));

@@ -2046,7 +2047,12 @@ static int gfs2_glock_iter_next(struct glock_iter *gi)
 		if (gi->gl)
 			gfs2_glock_hold(gi->gl);
 		read_unlock(gl_lock_addr(gi->hash));
+		gi->hash++;
 	}
+
+	if (gi->sdp != gi->gl->gl_sbd)
+		goto restart;
+
 	return 0;
 }
 

@@ -2068,16 +2074,10 @@ static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
 	gi->sdp = sdp;
 	gi->hash = 0;
 	gi->seq = NULL;
+	gi->gl = NULL;
 	memset(gi->string, 0, sizeof(gi->string));
 
-	read_lock(gl_lock_addr(gi->hash));
-	gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
-			     struct gfs2_glock, gl_list);
-	if (gi->gl)
-		gfs2_glock_hold(gi->gl);
-	read_unlock(gl_lock_addr(gi->hash));
-
-	if (!gi->gl && gfs2_glock_iter_next(gi)) {
+	if (gfs2_glock_iter_next(gi)) {
 		gfs2_glock_iter_free(gi);
 		return NULL;
 	}

index a0371f8..7ef3356 100644
@@ -492,11 +492,12 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 
 	gfs2_trans_add_gl(bd->bd_gl);
 	if (gfs2_is_jdata(ip)) {
-		sdp->sd_log_num_jdata++;
 		gfs2_pin(sdp, bd->bd_bh);
 		tr->tr_num_databuf_new++;
 	}
 	gfs2_log_lock(sdp);
+	if (gfs2_is_jdata(ip))
+		sdp->sd_log_num_jdata++;
 	sdp->sd_log_num_databuf++;
 	list_add(&le->le_list, &sdp->sd_log_le_databuf);
 	gfs2_log_unlock(sdp);

index 9e0e9be..314c113 100644
@@ -887,8 +887,10 @@ error:
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-	gfs2_delete_debugfs_file(sb->s_fs_info);
-	gfs2_meta_syncfs(sb->s_fs_info);
+	if (sb->s_fs_info) {
+		gfs2_delete_debugfs_file(sb->s_fs_info);
+		gfs2_meta_syncfs(sb->s_fs_info);
+	}
 	kill_block_super(sb);
 }
 

index 3d94918..931368a 100644
@@ -27,6 +27,8 @@
 #include <linux/debugfs.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
 
 #include "gfs2.h"
 #include "incore.h"

@@ -58,10 +60,13 @@ static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
 static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
 static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
 static void gfs2_glock_drop_th(struct gfs2_glock *gl);
+static void run_queue(struct gfs2_glock *gl);
+
 static DECLARE_RWSEM(gfs2_umount_flush_sem);
 static struct dentry *gfs2_root;
 static struct task_struct *scand_process;
 static unsigned int scand_secs = 5;
+static struct workqueue_struct *glock_workqueue;
 
 #define GFS2_GL_HASH_SHIFT      15
 #define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)

@@ -277,6 +282,18 @@ static struct gfs2_glock *gfs2_glock_find(const struct gfs2_sbd *sdp,
 	return gl;
 }
 
+static void glock_work_func(struct work_struct *work)
+{
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+
+	spin_lock(&gl->gl_spin);
+	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags))
+		set_bit(GLF_DEMOTE, &gl->gl_flags);
+	run_queue(gl);
+	spin_unlock(&gl->gl_spin);
+	gfs2_glock_put(gl);
+}
+
 /**
  * gfs2_glock_get() - Get a glock, or create one if one doesn't exist
  * @sdp: The GFS2 superblock

@@ -316,6 +333,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_name = name;
 	atomic_set(&gl->gl_ref, 1);
 	gl->gl_state = LM_ST_UNLOCKED;
+	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_hash = hash;
 	gl->gl_owner_pid = 0;
 	gl->gl_ip = 0;

@@ -324,10 +342,12 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_req_bh = NULL;
 	gl->gl_vn = 0;
 	gl->gl_stamp = jiffies;
+	gl->gl_tchange = jiffies;
 	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,
 	   create a VFS inode to manage the pages/buffers holding them. */

@@ -441,6 +461,8 @@ 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();
         wake_up_bit(&gl->gl_flags, GLF_DEMOTE);

@@ -682,10 +704,14 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl)
  * practise: LM_ST_SHARED and LM_ST_UNLOCKED
  */
 
-static void handle_callback(struct gfs2_glock *gl, unsigned int state, int remote)
+static void handle_callback(struct gfs2_glock *gl, unsigned int state,
+			    int remote, unsigned long delay)
 {
+	int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
+
 	spin_lock(&gl->gl_spin);
-	if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) {
+	set_bit(bit, &gl->gl_flags);
+	if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
 		gl->gl_demote_state = state;
 		gl->gl_demote_time = jiffies;
 		if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&

@@ -727,6 +753,7 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
 	}
 
 	gl->gl_state = new_state;
+	gl->gl_tchange = jiffies;
 }
 
 /**

@@ -813,7 +840,6 @@ out:
 		gl->gl_req_gh = NULL;
 		gl->gl_req_bh = NULL;
 		clear_bit(GLF_LOCK, &gl->gl_flags);
-		run_queue(gl);
 		spin_unlock(&gl->gl_spin);
 	}
 

@@ -885,7 +911,6 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
 	gfs2_assert_warn(sdp, !ret);
 
 	state_change(gl, LM_ST_UNLOCKED);
-	gfs2_demote_wake(gl);
 
 	if (glops->go_inval)
 		glops->go_inval(gl, DIO_METADATA);

@@ -898,10 +923,10 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret)
 	}
 
 	spin_lock(&gl->gl_spin);
+	gfs2_demote_wake(gl);
 	gl->gl_req_gh = NULL;
 	gl->gl_req_bh = NULL;
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
 
 	gfs2_glock_put(gl);

@@ -1209,9 +1234,10 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
+	unsigned delay = 0;
 
 	if (gh->gh_flags & GL_NOCACHE)
-		handle_callback(gl, LM_ST_UNLOCKED, 0);
+		handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 
 	gfs2_glmutex_lock(gl);
 

@@ -1229,8 +1255,14 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 	}
 
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	run_queue(gl);
 	spin_unlock(&gl->gl_spin);
+
+	gfs2_glock_hold(gl);
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
+		delay = gl->gl_ops->go_min_hold_time;
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 void gfs2_glock_dq_wait(struct gfs2_holder *gh)

@@ -1457,18 +1489,21 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
 			unsigned int state)
 {
 	struct gfs2_glock *gl;
+	unsigned long delay = 0;
+	unsigned long holdtime;
+	unsigned long now = jiffies;
 
 	gl = gfs2_glock_find(sdp, name);
 	if (!gl)
 		return;
 
-	handle_callback(gl, state, 1);
-
-	spin_lock(&gl->gl_spin);
-	run_queue(gl);
-	spin_unlock(&gl->gl_spin);
+	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
+	if (time_before(now, holdtime))
+		delay = holdtime - now;
 
-	gfs2_glock_put(gl);
+	handle_callback(gl, state, 1, delay);
+	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
+		gfs2_glock_put(gl);
 }
 
 /**

@@ -1509,7 +1544,8 @@ void gfs2_glock_cb(void *cb_data, unsigned int type, void *data)
 			return;
 		if (!gfs2_assert_warn(sdp, gl->gl_req_bh))
 			gl->gl_req_bh(gl, async->lc_ret);
-		gfs2_glock_put(gl);
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gfs2_glock_put(gl);
 		up_read(&gfs2_umount_flush_sem);
 		return;
 	}

@@ -1602,7 +1638,7 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp)
 	if (gfs2_glmutex_trylock(gl)) {
 		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl))
-			handle_callback(gl, LM_ST_UNLOCKED, 0);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 

@@ -1702,7 +1738,7 @@ static void clear_glock(struct gfs2_glock *gl)
 	if (gfs2_glmutex_trylock(gl)) {
 		if (list_empty(&gl->gl_holders) &&
 		    gl->gl_state != LM_ST_UNLOCKED)
-			handle_callback(gl, LM_ST_UNLOCKED, 0);
+			handle_callback(gl, LM_ST_UNLOCKED, 0, 0);
 		gfs2_glmutex_unlock(gl);
 	}
 }

@@ -2009,11 +2045,18 @@ int __init gfs2_glock_init(void)
 	if (IS_ERR(scand_process))
 		return PTR_ERR(scand_process);
 
+	glock_workqueue = create_workqueue("glock_workqueue");
+	if (IS_ERR(glock_workqueue)) {
+		kthread_stop(scand_process);
+		return PTR_ERR(glock_workqueue);
+	}
+
 	return 0;
 }
 
 void gfs2_glock_exit(void)
 {
+	destroy_workqueue(glock_workqueue);
 	kthread_stop(scand_process);
 }
 

index 88342e0..7ef6b23 100644
@@ -454,6 +454,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
 	.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 = {

@@ -464,6 +465,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_lock = rgrp_go_lock,
 	.go_unlock = rgrp_go_unlock,
 	.go_type = LM_TYPE_RGRP,
+	.go_min_hold_time = HZ / 10,
 };
 
 const struct gfs2_glock_operations gfs2_trans_glops = {

index 1390b30..23b611a 100644
@@ -11,6 +11,7 @@
 #define __INCORE_DOT_H__
 
 #include <linux/fs.h>
+#include <linux/workqueue.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020

@@ -130,6 +131,7 @@ struct gfs2_glock_operations {
 	int (*go_lock) (struct gfs2_holder *gh);
 	void (*go_unlock) (struct gfs2_holder *gh);
 	const int go_type;
+	const unsigned long go_min_hold_time;
 };
 
 enum {

@@ -161,6 +163,7 @@ enum {
 	GLF_LOCK		= 1,
 	GLF_STICKY		= 2,
 	GLF_DEMOTE		= 3,
+	GLF_PENDING_DEMOTE	= 4,
 	GLF_DIRTY		= 5,
 };
 

@@ -193,6 +196,7 @@ struct gfs2_glock {
 
 	u64 gl_vn;
 	unsigned long gl_stamp;
+	unsigned long gl_tchange;
 	void *gl_object;
 
 	struct list_head gl_reclaim;

@@ -203,6 +207,7 @@ struct gfs2_glock {
 	struct gfs2_log_element gl_le;
 	struct list_head gl_ail_list;
 	atomic_t gl_ail_count;
+	struct delayed_work gl_work;
 };
 
 struct gfs2_alloc {

index 34f7bcd..013f00b 100644
@@ -244,6 +244,11 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	return 0;
 }
 
+static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh)
+{
+	ip->i_cache[0] = bh;
+}
+
 /**
  * gfs2_inode_refresh - Refresh the incore copy of the dinode
  * @ip: The GFS2 inode

@@ -688,7 +693,7 @@ out:
 static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 			const struct gfs2_inum_host *inum, unsigned int mode,
 			unsigned int uid, unsigned int gid,
-			const u64 *generation, dev_t dev)
+			const u64 *generation, dev_t dev, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_dinode *di;

@@ -743,13 +748,15 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 	di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
 	di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
 	memset(&di->di_reserved, 0, sizeof(di->di_reserved));
+	
+	set_buffer_uptodate(dibh);
 
-	brelse(dibh);
+	*bhp = dibh;
 }
 
 static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 		       unsigned int mode, const struct gfs2_inum_host *inum,
-		       const u64 *generation, dev_t dev)
+		       const u64 *generation, dev_t dev, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	unsigned int uid, gid;

@@ -770,7 +777,7 @@ static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
 	if (error)
 		goto out_quota;
 
-	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev);
+	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, bhp);
 	gfs2_quota_change(dip, +1, uid, gid);
 	gfs2_trans_end(sdp);
 

@@ -909,6 +916,7 @@ 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;
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return ERR_PTR(-ENAMETOOLONG);

@@ -935,7 +943,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	if (error)
 		goto fail_gunlock;
 
-	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev);
+	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, &bh);
 	if (error)
 		goto fail_gunlock2;
 

@@ -945,6 +953,8 @@ 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;

index 5b8b994..2cbe5a3 100644
@@ -278,17 +278,25 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
 
 
-	error = gfs2_glock_nq_m(3, ghs);
+	error = gfs2_glock_nq(ghs); /* parent */
 	if (error)
-		goto out;
+		goto out_parent;
+
+	error = gfs2_glock_nq(ghs + 1); /* child */
+	if (error)
+		goto out_child;
+
+	error = gfs2_glock_nq(ghs + 2); /* rgrp */
+	if (error)
+		goto out_rgrp;
 
 	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
 	if (error)
-		goto out_gunlock;
+		goto out_rgrp;
 
 	error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
 	if (error)
-		goto out_gunlock;
+		goto out_rgrp;
 
 	error = gfs2_dir_del(dip, &dentry->d_name);
         if (error)

@@ -298,12 +306,15 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 out_end_trans:
 	gfs2_trans_end(sdp);
-out_gunlock:
-	gfs2_glock_dq_m(3, ghs);
-out:
-	gfs2_holder_uninit(ghs);
-	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs + 2);
+out_rgrp:
 	gfs2_holder_uninit(ghs + 2);
+	gfs2_glock_dq(ghs + 1);
+out_child:
+	gfs2_holder_uninit(ghs + 1);
+	gfs2_glock_dq(ghs);
+out_parent:
+	gfs2_holder_uninit(ghs);
 	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }

index 7ef6b23..b17346a 100644
@@ -60,11 +60,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 		blkno = bh->b_blocknr;
 		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
 
-		bd->bd_ail = NULL;
-		list_del(&bd->bd_ail_st_list);
-		list_del(&bd->bd_ail_gl_list);
-		atomic_dec(&gl->gl_ail_count);
-		brelse(bh);
+		gfs2_remove_from_ail(NULL, bd);
 		gfs2_log_unlock(sdp);
 
 		gfs2_trans_add_revoke(sdp, blkno);

index d0e6b42..d8232ec 100644
@@ -60,6 +60,26 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 }
 
 /**
+ * gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
+ * @mapping: The associated mapping (maybe NULL)
+ * @bd: The gfs2_bufdata to remove
+ *
+ * The log lock _must_ be held when calling this function
+ *
+ */
+
+void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd)
+{
+	bd->bd_ail = NULL;
+	list_del(&bd->bd_ail_st_list);
+	list_del(&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);
+}
+
+/**
  * gfs2_ail1_start_one - Start I/O on a part of the AIL
  * @sdp: the filesystem
  * @tr: the part of the AIL

@@ -219,21 +239,12 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 {
 	struct list_head *head = &ai->ai_ail2_list;
 	struct gfs2_bufdata *bd;
-	struct gfs2_inode *bh_ip;
 
 	while (!list_empty(head)) {
 		bd = list_entry(head->prev, struct gfs2_bufdata,
 				bd_ail_st_list);
 		gfs2_assert(sdp, bd->bd_ail == ai);
-		bd->bd_ail = NULL;
-		list_del(&bd->bd_ail_st_list);
-		list_del(&bd->bd_ail_gl_list);
-		atomic_dec(&bd->bd_gl->gl_ail_count);
-		if (bd->bd_bh->b_page->mapping) {
-			bh_ip = GFS2_I(bd->bd_bh->b_page->mapping->host);
-			gfs2_meta_cache_flush(bh_ip);
-		}
-		brelse(bd->bd_bh);
+		gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd);
 	}
 }
 

index 8e7aa0f..6394235 100644
@@ -58,6 +58,7 @@ 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_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd);
 
 void gfs2_log_shutdown(struct gfs2_sbd *sdp);
 void gfs2_meta_syncfs(struct gfs2_sbd *sdp);

index 9b89904..1e56f4d 100644
@@ -95,7 +95,8 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 	set_buffer_uptodate(bh);
 	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
-	mark_buffer_dirty(bh);
+	if (!gfs2_is_jdata(ip))
+		mark_buffer_dirty(bh);
 
 	if (release) {
 		unlock_page(page);

index 7ef3356..3ec5871 100644
@@ -27,7 +27,71 @@
 #include "trans.h"
 #include "util.h"
 
-static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
+/**
+ * gfs2_pin - Pin a buffer in memory
+ * @sdp: The superblock
+ * @bh: The buffer to be pinned
+ *
+ * The log lock must be held when calling this function
+ */
+static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+{
+	struct gfs2_bufdata *bd;
+
+	gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
+
+	clear_buffer_dirty(bh);
+	if (test_set_buffer_pinned(bh))
+		gfs2_assert_withdraw(sdp, 0);
+	if (!buffer_uptodate(bh))
+		gfs2_io_error_bh(sdp, bh);
+	bd = bh->b_private;
+	/* If this buffer is in the AIL and it has already been written
+	 * to in-place disk block, remove it from the AIL.
+	 */
+	if (bd->bd_ail)
+		list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
+	get_bh(bh);
+}
+
+/**
+ * gfs2_unpin - Unpin a buffer
+ * @sdp: the filesystem the buffer belongs to
+ * @bh: The buffer to unpin
+ * @ai:
+ *
+ */
+
+static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
+		       struct gfs2_ail *ai)
+{
+	struct gfs2_bufdata *bd = bh->b_private;
+
+	gfs2_assert_withdraw(sdp, buffer_uptodate(bh));
+
+	if (!buffer_pinned(bh))
+		gfs2_assert_withdraw(sdp, 0);
+
+	lock_buffer(bh);
+	mark_buffer_dirty(bh);
+	clear_buffer_pinned(bh);
+
+	gfs2_log_lock(sdp);
+	if (bd->bd_ail) {
+		list_del(&bd->bd_ail_st_list);
+		brelse(bh);
+	} else {
+		struct gfs2_glock *gl = bd->bd_gl;
+		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
+		atomic_inc(&gl->gl_ail_count);
+	}
+	bd->bd_ail = ai;
+	list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+	gfs2_log_unlock(sdp);
+	unlock_buffer(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;

@@ -38,15 +102,19 @@ static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
 		return;
 
-	gfs2_log_lock(sdp);
-	if (!list_empty(&le->le_list)){
-		gfs2_log_unlock(sdp);
+	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);
 }
 

@@ -71,30 +139,25 @@ 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);
 	struct gfs2_trans *tr;
 
+	lock_buffer(bd->bd_bh);
 	gfs2_log_lock(sdp);
-	if (!list_empty(&bd->bd_list_tr)) {
-		gfs2_log_unlock(sdp);
-		return;
-	}
+	if (!list_empty(&bd->bd_list_tr))
+		goto out;
 	tr = current->journal_info;
 	tr->tr_touched = 1;
 	tr->tr_num_buf++;
 	list_add(&bd->bd_list_tr, &tr->tr_list_buf);
-	gfs2_log_unlock(sdp);
-
 	if (!list_empty(&le->le_list))
-		return;
-
-	gfs2_trans_add_gl(bd->bd_gl);
-
+		goto out;
+	__glock_lo_add(sdp, &bd->bd_gl->gl_le);
 	gfs2_meta_check(sdp, bd->bd_bh);
 	gfs2_pin(sdp, bd->bd_bh);
-	gfs2_log_lock(sdp);
 	sdp->sd_log_num_buf++;
 	list_add(&le->le_list, &sdp->sd_log_le_buf);
-	gfs2_log_unlock(sdp);
-
 	tr->tr_num_buf_new++;
+out:
+	gfs2_log_unlock(sdp);
+	unlock_buffer(bd->bd_bh);
 }
 
 static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)

@@ -476,31 +539,29 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	struct address_space *mapping = bd->bd_bh->b_page->mapping;
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 
+	lock_buffer(bd->bd_bh);
 	gfs2_log_lock(sdp);
-	if (!list_empty(&bd->bd_list_tr)) {
-		gfs2_log_unlock(sdp);
-		return;
-	}
+	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);
 	}
-	gfs2_log_unlock(sdp);
 	if (!list_empty(&le->le_list))
-		return;
+		goto out;
 
-	gfs2_trans_add_gl(bd->bd_gl);
+	__glock_lo_add(sdp, &bd->bd_gl->gl_le);
 	if (gfs2_is_jdata(ip)) {
 		gfs2_pin(sdp, bd->bd_bh);
 		tr->tr_num_databuf_new++;
-	}
-	gfs2_log_lock(sdp);
-	if (gfs2_is_jdata(ip))
 		sdp->sd_log_num_jdata++;
+	}
 	sdp->sd_log_num_databuf++;
 	list_add(&le->le_list, &sdp->sd_log_le_databuf);
+out:
 	gfs2_log_unlock(sdp);
+	unlock_buffer(bd->bd_bh);
 }
 
 static int gfs2_check_magic(struct buffer_head *bh)

76 lines not on this page · raw message

index 527bf19..fd67f07 100644
@@ -50,9 +50,6 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
 
 void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
 			 int meta);
-void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
-void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
-		struct gfs2_ail *ai);
 
 void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
 

index 23b611a..388dc1b 100644
@@ -612,13 +612,13 @@ struct gfs2_sbd {
 	unsigned int sd_log_num_revoke;
 	unsigned int sd_log_num_rg;
 	unsigned int sd_log_num_databuf;
-	unsigned int sd_log_num_jdata;
 
 	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;
 	struct mutex sd_log_reserve_mutex;

82 lines not on this page · raw message

209 lines not on this page · raw message

68 lines not on this page · raw message

index 314c113..35f3dfa 100644
@@ -82,6 +82,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
 	INIT_LIST_HEAD(&sdp->sd_log_le_rg);
 	INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+	INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
 
 	mutex_init(&sdp->sd_log_reserve_mutex);
 	INIT_LIST_HEAD(&sdp->sd_ail1_list);

index 1e56f4d..93fa427 100644
@@ -93,10 +93,10 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 		map_bh(bh, inode->i_sb, block);
 
 	set_buffer_uptodate(bh);
-	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
-		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 	if (!gfs2_is_jdata(ip))
 		mark_buffer_dirty(bh);
+	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
+		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 
 	if (release) {
 		unlock_page(page);

index 388dc1b..8aa5780 100644
@@ -114,7 +114,13 @@ struct gfs2_bufdata {
 	struct buffer_head *bd_bh;
 	struct gfs2_glock *bd_gl;
 
-	struct list_head bd_list_tr;
+	union {
+		struct list_head list_tr;
+		u64 blkno;
+	} u;
+#define bd_list_tr u.list_tr
+#define bd_blkno u.blkno
+
 	struct gfs2_log_element bd_le;
 
 	struct gfs2_ail *bd_ail;

@@ -298,11 +304,6 @@ struct gfs2_file {
 	struct gfs2_holder f_fl_gh;
 };
 
-struct gfs2_revoke {
-	struct gfs2_log_element rv_le;
-	u64 rv_blkno;
-};
-
 struct gfs2_revoke_replay {
 	struct list_head rr_list;
 	u64 rr_blkno;

index 7e2d4e6..cf6fe36 100644
@@ -357,7 +357,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 	struct buffer_head *bh;
 	unsigned int offset;
 	struct list_head *head = &sdp->sd_log_le_revoke;
-	struct gfs2_revoke *rv;
+	struct gfs2_bufdata *bd;
 
 	if (!sdp->sd_log_num_revoke)
 		return;

@@ -376,8 +376,8 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 	offset = sizeof(struct gfs2_log_descriptor);
 
 	while (!list_empty(head)) {
-		rv = list_entry(head->next, struct gfs2_revoke, rv_le.le_list);
-		list_del_init(&rv->rv_le.le_list);
+		bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+		list_del_init(&bd->bd_le.le_list);
 		sdp->sd_log_num_revoke--;
 
 		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {

@@ -392,8 +392,8 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 			offset = sizeof(struct gfs2_meta_header);
 		}
 
-		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(rv->rv_blkno);
-		kfree(rv);
+		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno);
+		kfree(bd);
 
 		offset += sizeof(u64);
 	}

index f8dabf8..eadf96e 100644
@@ -144,23 +144,23 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
 
 void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno)
 {
-	struct gfs2_revoke *rv = kmalloc(sizeof(struct gfs2_revoke),
-					 GFP_NOFS | __GFP_NOFAIL);
-	lops_init_le(&rv->rv_le, &gfs2_revoke_lops);
-	rv->rv_blkno = blkno;
-	lops_add(sdp, &rv->rv_le);
+	struct gfs2_bufdata *bd = kmalloc(sizeof(struct gfs2_bufdata),
+					  GFP_NOFS | __GFP_NOFAIL);
+	lops_init_le(&bd->bd_le, &gfs2_revoke_lops);
+	bd->bd_blkno = blkno;
+	lops_add(sdp, &bd->bd_le);
 }
 
 void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
 {
-	struct gfs2_revoke *rv;
+	struct gfs2_bufdata *bd;
 	int found = 0;
 
 	gfs2_log_lock(sdp);
 
-	list_for_each_entry(rv, &sdp->sd_log_le_revoke, rv_le.le_list) {
-		if (rv->rv_blkno == blkno) {
-			list_del(&rv->rv_le.le_list);
+	list_for_each_entry(bd, &sdp->sd_log_le_revoke, bd_le.le_list) {
+		if (bd->bd_blkno == blkno) {
+			list_del(&bd->bd_le.le_list);
 			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
 			sdp->sd_log_num_revoke--;
 			found = 1;

@@ -172,7 +172,7 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
 
 	if (found) {
 		struct gfs2_trans *tr = current->journal_info;
-		kfree(rv);
+		kfree(bd);
 		tr->tr_num_revoke_rm++;
 	}
 }

index cf6fe36..4cbef4c 100644
@@ -393,7 +393,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 		}
 
 		*(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno);
-		kfree(bd);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
 
 		offset += sizeof(u64);
 	}

index eadf96e..01cc27f 100644
@@ -144,7 +144,7 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
 
 void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno)
 {
-	struct gfs2_bufdata *bd = kmalloc(sizeof(struct gfs2_bufdata),
+	struct gfs2_bufdata *bd = kmem_cache_alloc(gfs2_bufdata_cachep,
 					  GFP_NOFS | __GFP_NOFAIL);
 	lops_init_le(&bd->bd_le, &gfs2_revoke_lops);
 	bd->bd_blkno = blkno;

@@ -172,7 +172,7 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
 
 	if (found) {
 		struct gfs2_trans *tr = current->journal_info;
-		kfree(bd);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
 		tr->tr_num_revoke_rm++;
 	}
 }

index b17346a..4670dcb 100644
@@ -41,7 +41,6 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	struct list_head *head = &gl->gl_ail_list;
 	struct gfs2_bufdata *bd;
 	struct buffer_head *bh;
-	u64 blkno;
 	int error;
 
 	blocks = atomic_read(&gl->gl_ail_count);

@@ -57,15 +56,12 @@ 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;
-		blkno = bh->b_blocknr;
-		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
-
 		gfs2_remove_from_ail(NULL, bd);
-		gfs2_log_unlock(sdp);
-
-		gfs2_trans_add_revoke(sdp, blkno);
-
-		gfs2_log_lock(sdp);
+		bd->bd_bh = NULL;
+		bh->b_private = NULL;
+		bd->bd_blkno = bh->b_blocknr;
+		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
+		gfs2_trans_add_revoke(sdp, bd);
 	}
 	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
 	gfs2_log_unlock(sdp);

index 20fa528..4d04e6f 100644
@@ -71,8 +71,8 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd)
 {
 	bd->bd_ail = NULL;
-	list_del(&bd->bd_ail_st_list);
-	list_del(&bd->bd_ail_gl_list);
+	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));

index 4cbef4c..342c10e 100644
@@ -343,11 +343,8 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	tr = current->journal_info;
 	tr->tr_touched = 1;
 	tr->tr_num_revoke++;
-
-	gfs2_log_lock(sdp);
 	sdp->sd_log_num_revoke++;
 	list_add(&le->le_list, &sdp->sd_log_le_revoke);
-	gfs2_log_unlock(sdp);
 }
 
 static void revoke_lo_before_commit(struct gfs2_sbd *sdp)

index d762e4f..19097bc 100644
@@ -313,42 +313,31 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
 	while (blen) {
 		bh = getbuf(ip->i_gl, bstart, NO_CREATE);
 		if (bh) {
-			struct gfs2_bufdata *bd = bh->b_private;
+			struct gfs2_bufdata *bd;
 
+			lock_buffer(bh);
+			gfs2_log_lock(sdp);
+			bd = bh->b_private;
 			if (test_clear_buffer_pinned(bh)) {
 				struct gfs2_trans *tr = current->journal_info;
-				struct gfs2_inode *bh_ip =
-					GFS2_I(bh->b_page->mapping->host);
-
-				gfs2_log_lock(sdp);
 				list_del_init(&bd->bd_le.le_list);
 				gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
 				sdp->sd_log_num_buf--;
-				gfs2_log_unlock(sdp);
-				if (bh_ip->i_inode.i_private != NULL)
-					tr->tr_num_databuf_rm++;
-				else
-					tr->tr_num_buf_rm++;
+				tr->tr_num_buf_rm++;
 				brelse(bh);
 			}
 			if (bd) {
-				gfs2_log_lock(sdp);
 				if (bd->bd_ail) {
-					u64 blkno = bh->b_blocknr;
-					bd->bd_ail = NULL;
-					list_del(&bd->bd_ail_st_list);
-					list_del(&bd->bd_ail_gl_list);
-					atomic_dec(&bd->bd_gl->gl_ail_count);
-					brelse(bh);
-					gfs2_log_unlock(sdp);
-					gfs2_trans_add_revoke(sdp, blkno);
-				} else
-					gfs2_log_unlock(sdp);
+					gfs2_remove_from_ail(NULL, bd);
+					bh->b_private = NULL;
+					bd->bd_bh = NULL;
+					bd->bd_blkno = bh->b_blocknr;
+					gfs2_trans_add_revoke(sdp, bd);
+				}
 			}
-
-			lock_buffer(bh);
 			clear_buffer_dirty(bh);
 			clear_buffer_uptodate(bh);
+			gfs2_log_unlock(sdp);
 			unlock_buffer(bh);
 
 			brelse(bh);

index 01cc27f..717983e 100644
@@ -142,12 +142,12 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
 	lops_add(sdp, &bd->bd_le);
 }
 
-void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, u64 blkno)
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 {
-	struct gfs2_bufdata *bd = kmem_cache_alloc(gfs2_bufdata_cachep,
-					  GFP_NOFS | __GFP_NOFAIL);
+	BUG_ON(!list_empty(&bd->bd_le.le_list));
+	BUG_ON(!list_empty(&bd->bd_ail_st_list));
+	BUG_ON(!list_empty(&bd->bd_ail_gl_list));
 	lops_init_le(&bd->bd_le, &gfs2_revoke_lops);
-	bd->bd_blkno = blkno;
 	lops_add(sdp, &bd->bd_le);
 }
 

@@ -160,7 +160,7 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno)
 
 	list_for_each_entry(bd, &sdp->sd_log_le_revoke, bd_le.le_list) {
 		if (bd->bd_blkno == blkno) {
-			list_del(&bd->bd_le.le_list);
+			list_del_init(&bd->bd_le.le_list);
 			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
 			sdp->sd_log_num_revoke--;
 			found = 1;

index 23d4cbe..043d5f4 100644
@@ -32,7 +32,7 @@ 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, u64 blkno);
+void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno);
 void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
 

index 931368a..d631cad 100644
@@ -1106,24 +1106,31 @@ static void add_to_queue(struct gfs2_holder *gh)
 	if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
 		BUG();
 
-	existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner_pid);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n",
-				existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
-		printk(KERN_INFO "lock type : %d lock state : %d\n",
-				gl->gl_name.ln_type, gl->gl_state);
-		BUG();
-	}
-
-	existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner_pid);
-	if (existing) {
-		print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
-		print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
-		BUG();
+	if (!(gh->gh_flags & GL_FLOCK)) {
+		existing = find_holder_by_owner(&gl->gl_holders, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       existing->gh_gl->gl_name.ln_type, 
+			       existing->gh_gl->gl_state);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
+			printk(KERN_INFO "lock type : %d lock state : %d\n",
+			       gl->gl_name.ln_type, gl->gl_state);
+			BUG();
+		}
+		
+		existing = find_holder_by_owner(&gl->gl_waiters3, 
+						gh->gh_owner_pid);
+		if (existing) {
+			print_symbol(KERN_WARNING "original: %s\n", 
+				     existing->gh_ip);
+			print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
+			BUG();
+		}
 	}
 
 	if (gh->gh_flags & LM_FLAG_PRIORITY)

index f7a8e62..b16f604 100644
@@ -26,6 +26,7 @@
 #define GL_SKIP			0x00000100
 #define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
+#define GL_FLOCK		0x00000800
 #define GL_NOCANCEL		0x00001000
 
 #define GLR_TRYFAILED		13

index 94d76ac..46a9e10 100644
@@ -571,7 +571,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	int error = 0;
 
 	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE 
+		| GL_FLOCK;
 
 	mutex_lock(&fp->f_fl_mutex);
 

@@ -579,21 +580,19 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (gl) {
 		if (fl_gh->gh_state == state)
 			goto out;
-		gfs2_glock_hold(gl);
 		flock_lock_file_wait(file,
 				     &(struct file_lock){.fl_type = F_UNLCK});
-		gfs2_glock_dq_uninit(fl_gh);
+		gfs2_glock_dq_wait(fl_gh);
+		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
 		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
 				      ip->i_no_addr, &gfs2_flock_glops,
 				      CREATE, &gl);
 		if (error)
 			goto out;
+		gfs2_holder_init(gl, state, flags, fl_gh);
+		gfs2_glock_put(gl);
 	}
-
-	gfs2_holder_init(gl, state, flags, fl_gh);
-	gfs2_glock_put(gl);
-
 	error = gfs2_glock_nq(fl_gh);
 	if (error) {
 		gfs2_holder_uninit(fl_gh);

index d631cad..a37efe4 100644
@@ -716,12 +716,8 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
 		gl->gl_demote_time = jiffies;
 		if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN &&
 		    gl->gl_object) {
-			struct inode *inode = igrab(gl->gl_object);
+			gfs2_glock_schedule_for_reclaim(gl);
 			spin_unlock(&gl->gl_spin);
-			if (inode) {
-				d_prune_aliases(inode);
-				iput(inode);
-			}
 			return;
 		}
 	} else if (gl->gl_demote_state != LM_ST_UNLOCKED &&

index 62a8a6c..58bf3f5 100644
@@ -1264,14 +1264,15 @@ static void send_to_sock(struct connection *con)
 		if (len) {
 			ret = sendpage(con->sock, e->page, offset, len,
 				       msg_flags);
-			if (ret == -EAGAIN || ret == 0)
+			if (ret == -EAGAIN || ret == 0) {
+				cond_resched();
 				goto out;
+			}
 			if (ret <= 0)
 				goto send_error;
-		} else {
+		}
 			/* Don't starve people filling buffers */
 			cond_resched();
-		}
 
 		spin_lock(&con->writequeue_lock);
 		e->offset += ret;

index 1aca51e..bd938f0 100644
@@ -268,20 +268,16 @@ static inline int check_drop(struct gdlm_ls *ls)
 	return 0;
 }
 
-static int gdlm_thread(void *data)
+static int gdlm_thread(void *data, int blist)
 {
 	struct gdlm_ls *ls = (struct gdlm_ls *) data;
 	struct gdlm_lock *lp = NULL;
-	int blist = 0;
 	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. */
 
-	if (current == ls->thread1)
-		blist = 1;
-
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		add_wait_queue(&ls->thread_wait, &wait);

@@ -333,12 +329,22 @@ static int gdlm_thread(void *data)
 	return 0;
 }
 
+static int gdlm_thread1(void *data)
+{
+	return gdlm_thread(data, 1);
+}
+
+static int gdlm_thread2(void *data)
+{
+	return gdlm_thread(data, 0);
+}
+
 int gdlm_init_threads(struct gdlm_ls *ls)
 {
 	struct task_struct *p;
 	int error;
 
-	p = kthread_run(gdlm_thread, ls, "lock_dlm1");
+	p = kthread_run(gdlm_thread1, ls, "lock_dlm1");
 	error = IS_ERR(p);
 	if (error) {
 		log_error("can't start lock_dlm1 thread %d", error);

@@ -346,7 +352,7 @@ int gdlm_init_threads(struct gdlm_ls *ls)
 	}
 	ls->thread1 = p;
 
-	p = kthread_run(gdlm_thread, ls, "lock_dlm2");
+	p = kthread_run(gdlm_thread2, ls, "lock_dlm2");
 	error = IS_ERR(p);
 	if (error) {
 		log_error("can't start lock_dlm2 thread %d", error);

index 8aa5780..eaddfb5 100644
@@ -341,12 +341,6 @@ struct gfs2_quota_data {
 	unsigned long qd_last_touched;
 };
 
-struct gfs2_log_buf {
-	struct list_head lb_list;
-	struct buffer_head *lb_bh;
-	struct buffer_head *lb_real;
-};
-
 struct gfs2_trans {
 	unsigned long tr_ip;
 

@@ -631,7 +625,8 @@ struct gfs2_sbd {
 
 	unsigned long sd_log_flush_time;
 	struct rw_semaphore sd_log_flush_lock;
-	struct list_head sd_log_flush_list;
+	atomic_t sd_log_in_flight;
+	wait_queue_head_t sd_log_flush_wait;
 
 	unsigned int sd_log_flush_head;
 	u64 sd_log_flush_wrapped;

228 lines not on this page · raw message

index 6394235..dae2824 100644
@@ -52,6 +52,7 @@ 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);
 
 struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
 struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,

335 lines not on this page · raw message

71 lines not on this page · raw message

index fd67f07..b704822 100644
@@ -51,6 +51,9 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
 void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
 			 int meta);
 
+void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr,
+			      int meta);
+
 void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen);
 
 void gfs2_meta_cache_flush(struct gfs2_inode *ip);

index dd1ea49..b7baf18 100644
@@ -414,7 +414,8 @@ static int gfs2_prepare_write(struct file *file, struct page *page,
 	if (ind_blocks || data_blocks)
 		rblocks += RES_STATFS + RES_QUOTA;
 
-	error = gfs2_trans_begin(sdp, rblocks, 0);
+	error = gfs2_trans_begin(sdp, rblocks,
+				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
 	if (error)
 		goto out_trans_fail;
 

@@ -625,10 +626,10 @@ static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	clear_buffer_dirty(bh);
 	bd = bh->b_private;
 	if (bd) {
-		if (!list_empty(&bd->bd_le.le_list)) {
-			if (!buffer_pinned(bh))
-				list_del_init(&bd->bd_le.le_list);
-		}
+		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
+			list_del_init(&bd->bd_le.le_list);
+		else
+			gfs2_remove_from_journal(bh, current->journal_info, 0);
 	}
 	bh->b_bdev = NULL;
 	clear_buffer_mapped(bh);

index 35f3dfa..1ac9afa 100644
@@ -89,7 +89,8 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	INIT_LIST_HEAD(&sdp->sd_ail2_list);
 
 	init_rwsem(&sdp->sd_log_flush_lock);
-	INIT_LIST_HEAD(&sdp->sd_log_flush_list);
+	atomic_set(&sdp->sd_log_in_flight, 0);
+	init_waitqueue_head(&sdp->sd_log_flush_wait);
 
 	INIT_LIST_HEAD(&sdp->sd_revoke_list);
 

index 2cbe5a3..291f0c7 100644
@@ -905,12 +905,17 @@ static int gfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
 static int setattr_size(struct inode *inode, struct iattr *attr)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	int error;
 
 	if (attr->ia_size != ip->i_di.di_size) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
 		if (error)
 			return error;
+		error = vmtruncate(inode, attr->ia_size);
+		gfs2_trans_end(sdp);
+		if (error) 
+			return error;
 	}
 
 	error = gfs2_truncatei(ip, attr->ia_size);

index 4316690..950f314 100644
@@ -455,12 +455,15 @@ static void gfs2_delete_inode(struct inode *inode)
 	}
 
 	error = gfs2_dinode_dealloc(ip);
-	/*
-	 * Must do this before unlock to avoid trying to write back
-	 * potentially dirty data now that inode no longer exists
-	 * on disk.
-	 */
+	if (error)
+		goto out_unlock;
+
+	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_unlock;
+	/* Needs to be done before glock release & also in a transaction */
 	truncate_inode_pages(&inode->i_data, 0);
+	gfs2_trans_end(sdp);
 
 out_unlock:
 	gfs2_glock_dq(&ip->i_iopen_gh);

index 1d80f2d..4da4239 100644
@@ -374,10 +374,10 @@ void gfs2_meta_cache_flush(struct gfs2_inode *ip)
 
 	for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) {
 		bh_slot = &ip->i_cache[x];
-		if (!*bh_slot)
-			break;
-		brelse(*bh_slot);
-		*bh_slot = NULL;
+		if (*bh_slot) {
+			brelse(*bh_slot);
+			*bh_slot = NULL;
+		}
 	}
 
 	spin_unlock(&ip->i_spin);

index b7baf18..4002f41 100644
@@ -90,7 +90,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 	error = gfs2_block_map(inode, lblock, 0, bh_result);
 	if (error)
 		return error;
-	if (bh_result->b_blocknr == 0)
+	if (!buffer_mapped(bh_result))
 		return -EIO;
 	return 0;
 }

index 08c6dd0..9949bb7 100644
@@ -1502,7 +1502,7 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name)
 		inode = gfs2_inode_lookup(dir->i_sb, 
 				be16_to_cpu(dent->de_type),
 				be64_to_cpu(dent->de_inum.no_addr),
-				be64_to_cpu(dent->de_inum.no_formal_ino));
+				be64_to_cpu(dent->de_inum.no_formal_ino), 0);
 		brelse(bh);
 		return inode;
 	}

86 lines not on this page · raw message

index 4517ac8..351ac87 100644
@@ -49,7 +49,8 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip,
 void gfs2_inode_attr_in(struct gfs2_inode *ip);
 void gfs2_set_iop(struct inode *inode);
 struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				u64 no_addr, u64 no_formal_ino);
+				u64 no_addr, u64 no_formal_ino,
+				int skip_freeing);
 struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
 
 int gfs2_inode_refresh(struct gfs2_inode *ip);

index b8312ed..e2d1347 100644
@@ -237,7 +237,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj)
 
 	inode = gfs2_inode_lookup(sb, DT_UNKNOWN,
 					inum->no_addr,
-					0);
+					0, 0);
 	if (!inode)
 		goto fail;
 	if (IS_ERR(inode)) {

index 1ac9afa..17de58e 100644
@@ -230,7 +230,7 @@ fail:
 static inline struct inode *gfs2_lookup_root(struct super_block *sb,
 					     u64 no_addr)
 {
-	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
+	return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
 }
 
 static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)

index 2d7f7ea..708c287 100644
@@ -884,7 +884,7 @@ static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
-					  no_addr, -1);
+					  no_addr, -1, 1);
 		if (!IS_ERR(inode))
 			return inode;
 	}

index 4002f41..873a511 100644
@@ -747,7 +747,7 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
 	struct gfs2_bufdata *bd;
 
 	if (!page_has_buffers(page))
-		goto out;
+		return 0;
 
 	gfs2_log_lock(sdp);
 	head = bh = page_buffers(page);

@@ -787,7 +787,6 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
 		bh = bh->b_this_page;
 	} while (bh != head);
 
-out:
 	return try_to_free_buffers(page);
 cannot_release:
 	gfs2_log_unlock(sdp);

index ee70467..7df7024 100644
@@ -513,7 +513,8 @@ struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
 static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
 {
 	struct buffer_head *real_bh = bh->b_private;
-	struct gfs2_sbd *sdp = GFS2_SB(real_bh->b_page->mapping->host);
+	struct gfs2_bufdata *bd = real_bh->b_private;
+	struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
 
 	end_buffer_write_sync(bh, uptodate);
 	free_buffer_head(bh);