From: Steven Whitehouse <swhiteho@redhat.com>
Subject: [RHEL5.1] [GFS2] Fix bz 224480, gfs2_delete_inode: 13
Date: Fri, 20 Apr 2007 11:13:39 +0100
Bugzilla: 224480
Message-Id: <1177064019.1636.384.camel@quoit.chygwyn.com>
Changelog: [GFS2] gfs2_delete_inode: 13


Hi,

This patch fixes bz 224480 and it taken from the upstream kernel. Its
had a fair amount of testing upstream. It must be applied _after_ Bob's
recent patch for bz #228540.

Steve.


diff -Nru linux-rhel-base/fs/gfs2/glock.c linux-2.6.18.noarch/fs/gfs2/glock.c
--- linux-rhel-base/fs/gfs2/glock.c	2007-04-20 09:35:33.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/glock.c	2007-04-20 10:58:40.000000000 +0100
@@ -57,7 +57,7 @@
 
 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_holder *gh);
+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 DECLARE_RWSEM(gfs2_umount_flush_sem);
 
@@ -215,7 +215,6 @@
 		gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
 		gfs2_assert(sdp, list_empty(&gl->gl_holders));
 		gfs2_assert(sdp, list_empty(&gl->gl_waiters1));
-		gfs2_assert(sdp, list_empty(&gl->gl_waiters2));
 		gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
 		glock_free(gl);
 		rv = 1;
@@ -402,7 +401,7 @@
 {
 	gh->gh_state = state;
 	gh->gh_flags = flags;
-	gh->gh_iflags &= 1 << HIF_ALLOCED;
+	gh->gh_iflags = 0;
 	gh->gh_ip = (unsigned long)__builtin_return_address(0);
 }
 
@@ -419,54 +418,8 @@
 	gh->gh_ip = 0;
 }
 
-/**
- * gfs2_holder_get - get a struct gfs2_holder structure
- * @gl: the glock
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gfp_flags:
- *
- * Figure out how big an impact this function has.  Either:
- * 1) Replace it with a cache of structures hanging off the struct gfs2_sbd
- * 2) Leave it like it is
- *
- * Returns: the holder structure, NULL on ENOMEM
- */
-
-static struct gfs2_holder *gfs2_holder_get(struct gfs2_glock *gl,
-					   unsigned int state,
-					   int flags, gfp_t gfp_flags)
-{
-	struct gfs2_holder *gh;
-
-	gh = kmalloc(sizeof(struct gfs2_holder), gfp_flags);
-	if (!gh)
-		return NULL;
-
-	gfs2_holder_init(gl, state, flags, gh);
-	set_bit(HIF_ALLOCED, &gh->gh_iflags);
-	gh->gh_ip = (unsigned long)__builtin_return_address(0);
-	return gh;
-}
-
-/**
- * gfs2_holder_put - get rid of a struct gfs2_holder structure
- * @gh: the holder structure
- *
- */
-
-static void gfs2_holder_put(struct gfs2_holder *gh)
-{
-	gfs2_holder_uninit(gh);
-	kfree(gh);
-}
-
-static void gfs2_holder_dispose_or_wake(struct gfs2_holder *gh)
+static void gfs2_holder_wake(struct gfs2_holder *gh)
 {
-	if (test_bit(HIF_DEALLOC, &gh->gh_iflags)) {
-		gfs2_holder_put(gh);
-		return;
-	}
 	clear_bit(HIF_WAIT, &gh->gh_iflags);
 	smp_mb();
 	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
@@ -532,7 +485,7 @@
 				gfs2_reclaim_glock(sdp);
 			}
 
-			gfs2_glock_xmote_th(gh);
+			gfs2_glock_xmote_th(gh->gh_gl, gh);
 			spin_lock(&gl->gl_spin);
 		}
 		return 1;
@@ -555,7 +508,7 @@
 	gh->gh_error = 0;
 	set_bit(HIF_HOLDER, &gh->gh_iflags);
 
-	gfs2_holder_dispose_or_wake(gh);
+	gfs2_holder_wake(gh);
 
 	return 0;
 }
@@ -567,32 +520,24 @@
  * Returns: 1 if the queue is blocked
  */
 
-static int rq_demote(struct gfs2_holder *gh)
+static int rq_demote(struct gfs2_glock *gl)
 {
-	struct gfs2_glock *gl = gh->gh_gl;
-
 	if (!list_empty(&gl->gl_holders))
 		return 1;
 
-	if (gl->gl_state == gh->gh_state || gl->gl_state == LM_ST_UNLOCKED) {
-		list_del_init(&gh->gh_list);
-		gh->gh_error = 0;
-		spin_unlock(&gl->gl_spin);
-		gfs2_holder_dispose_or_wake(gh);
-		spin_lock(&gl->gl_spin);
-	} else {
-		gl->gl_req_gh = gh;
-		set_bit(GLF_LOCK, &gl->gl_flags);
-		spin_unlock(&gl->gl_spin);
-
-		if (gh->gh_state == LM_ST_UNLOCKED ||
-		    gl->gl_state != LM_ST_EXCLUSIVE)
-			gfs2_glock_drop_th(gl);
-		else
-			gfs2_glock_xmote_th(gh);
-
-		spin_lock(&gl->gl_spin);
+	if (gl->gl_state == gl->gl_demote_state ||
+	    gl->gl_state == LM_ST_UNLOCKED) {
+		clear_bit(GLF_DEMOTE, &gl->gl_flags);
+		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)
+		gfs2_glock_drop_th(gl);
+	else
+		gfs2_glock_xmote_th(gl, NULL);
+	spin_lock(&gl->gl_spin);
 
 	return 0;
 }
@@ -620,16 +565,8 @@
 			else
 				gfs2_assert_warn(gl->gl_sbd, 0);
 
-		} else if (!list_empty(&gl->gl_waiters2) &&
-			   !test_bit(GLF_SKIP_WAITERS2, &gl->gl_flags)) {
-			gh = list_entry(gl->gl_waiters2.next,
-					struct gfs2_holder, gh_list);
-
-			if (test_bit(HIF_DEMOTE, &gh->gh_iflags))
-				blocked = rq_demote(gh);
-			else
-				gfs2_assert_warn(gl->gl_sbd, 0);
-
+		} else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+			blocked = rq_demote(gl);
 		} else if (!list_empty(&gl->gl_waiters3)) {
 			gh = list_entry(gl->gl_waiters3.next,
 					struct gfs2_holder, gh_list);
@@ -720,50 +657,24 @@
 }
 
 /**
- * handle_callback - add a demote request to a lock's queue
+ * handle_callback - process a demote request
  * @gl: the glock
  * @state: the state the caller wants us to change to
  *
- * Note: This may fail sliently if we are out of memory.
+ * There are only two requests that we are going to see in actual
+ * practise: LM_ST_SHARED and LM_ST_UNLOCKED
  */
 
 static void handle_callback(struct gfs2_glock *gl, unsigned int state)
 {
-	struct gfs2_holder *gh, *new_gh = NULL;
-
-restart:
 	spin_lock(&gl->gl_spin);
-
-	list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
-		if (test_bit(HIF_DEMOTE, &gh->gh_iflags) &&
-		    gl->gl_req_gh != gh) {
-			if (gh->gh_state != state)
-				gh->gh_state = LM_ST_UNLOCKED;
-			goto out;
-		}
-	}
-
-	if (new_gh) {
-		list_add_tail(&new_gh->gh_list, &gl->gl_waiters2);
-		new_gh = NULL;
-	} else {
-		spin_unlock(&gl->gl_spin);
-
-		new_gh = gfs2_holder_get(gl, state, LM_FLAG_TRY, GFP_NOFS);
-		if (!new_gh)
-			return;
-		set_bit(HIF_DEMOTE, &new_gh->gh_iflags);
-		set_bit(HIF_DEALLOC, &new_gh->gh_iflags);
-		set_bit(HIF_WAIT, &new_gh->gh_iflags);
-
-		goto restart;
+	if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) {
+		gl->gl_demote_state = state;
+		gl->gl_demote_time = jiffies;
+	} else if (gl->gl_demote_state != LM_ST_UNLOCKED) {
+		gl->gl_demote_state = state;
 	}
-
-out:
 	spin_unlock(&gl->gl_spin);
-
-	if (new_gh)
-		gfs2_holder_put(new_gh);
 }
 
 /**
@@ -823,56 +734,37 @@
 
 	/*  Deal with each possible exit condition  */
 
-	if (!gh)
+	if (!gh) {
 		gl->gl_stamp = jiffies;
-	else if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+		if (ret & LM_OUT_CANCELED)
+			op_done = 0;
+		else
+			clear_bit(GLF_DEMOTE, &gl->gl_flags);
+	} else {
 		spin_lock(&gl->gl_spin);
 		list_del_init(&gh->gh_list);
 		gh->gh_error = -EIO;
-		spin_unlock(&gl->gl_spin);
-	} else if (test_bit(HIF_DEMOTE, &gh->gh_iflags)) {
-		spin_lock(&gl->gl_spin);
-		list_del_init(&gh->gh_list);
-		if (gl->gl_state == gh->gh_state ||
-		    gl->gl_state == LM_ST_UNLOCKED) {
+		if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) 
+			goto out;
+		gh->gh_error = GLR_CANCELED;
+		if (ret & LM_OUT_CANCELED) 
+			goto out;
+		if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
+			list_add_tail(&gh->gh_list, &gl->gl_holders);
 			gh->gh_error = 0;
-		} else {
-			if (gfs2_assert_warn(sdp, gh->gh_flags &
-					(LM_FLAG_TRY | LM_FLAG_TRY_1CB)) == -1)
-				fs_warn(sdp, "ret = 0x%.8X\n", ret);
-			gh->gh_error = GLR_TRYFAILED;
+			set_bit(HIF_HOLDER, &gh->gh_iflags);
+			set_bit(HIF_FIRST, &gh->gh_iflags);
+			op_done = 0;
+			goto out;
 		}
-		spin_unlock(&gl->gl_spin);
-
-		if (ret & LM_OUT_CANCELED)
-			handle_callback(gl, LM_ST_UNLOCKED);
-
-	} else if (ret & LM_OUT_CANCELED) {
-		spin_lock(&gl->gl_spin);
-		list_del_init(&gh->gh_list);
-		gh->gh_error = GLR_CANCELED;
-		spin_unlock(&gl->gl_spin);
-
-	} else if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
-		spin_lock(&gl->gl_spin);
-		list_move_tail(&gh->gh_list, &gl->gl_holders);
-		gh->gh_error = 0;
-		set_bit(HIF_HOLDER, &gh->gh_iflags);
-		spin_unlock(&gl->gl_spin);
-
-		set_bit(HIF_FIRST, &gh->gh_iflags);
-
-		op_done = 0;
-
-	} else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
-		spin_lock(&gl->gl_spin);
-		list_del_init(&gh->gh_list);
 		gh->gh_error = GLR_TRYFAILED;
-		spin_unlock(&gl->gl_spin);
-
-	} else {
+		if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+			goto out;
+		gh->gh_error = -EINVAL;
 		if (gfs2_assert_withdraw(sdp, 0) == -1)
 			fs_err(sdp, "ret = 0x%.8X\n", ret);
+out:
+		spin_unlock(&gl->gl_spin);
 	}
 
 	if (glops->go_xmote_bh)
@@ -890,7 +782,7 @@
 	gfs2_glock_put(gl);
 
 	if (gh)
-		gfs2_holder_dispose_or_wake(gh);
+		gfs2_holder_wake(gh);
 }
 
 /**
@@ -901,12 +793,11 @@
  *
  */
 
-void gfs2_glock_xmote_th(struct gfs2_holder *gh)
+void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
-	struct gfs2_glock *gl = gh->gh_gl;
 	struct gfs2_sbd *sdp = gl->gl_sbd;
-	int flags = gh->gh_flags;
-	unsigned state = gh->gh_state;
+	int flags = gh ? gh->gh_flags : 0;
+	unsigned state = gh ? gh->gh_state : gl->gl_demote_state;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	int lck_flags = flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB |
 				 LM_FLAG_NOEXP | LM_FLAG_ANY |
@@ -956,6 +847,7 @@
 	gfs2_assert_warn(sdp, !ret);
 
 	state_change(gl, LM_ST_UNLOCKED);
+	clear_bit(GLF_DEMOTE, &gl->gl_flags);
 
 	if (glops->go_inval)
 		glops->go_inval(gl, DIO_METADATA);
@@ -977,7 +869,7 @@
 	gfs2_glock_put(gl);
 
 	if (gh)
-		gfs2_holder_dispose_or_wake(gh);
+		gfs2_holder_wake(gh);
 }
 
 /**
@@ -1294,9 +1186,8 @@
 		if (glops->go_unlock)
 			glops->go_unlock(gh);
 
-		gl->gl_stamp = jiffies;
-
 		spin_lock(&gl->gl_spin);
+		gl->gl_stamp = jiffies;
 	}
 
 	clear_bit(GLF_LOCK, &gl->gl_flags);
@@ -2015,6 +1906,11 @@
 		if (error)
 			goto out;
 	}
+	if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+		print_dbg(gi, "  Demotion req to state %u (%llu uS ago)\n",
+			  gl->gl_demote_state,
+			  (u64)(jiffies - gl->gl_demote_time)*(1000000/HZ));
+	}
 	if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) {
 		if (!test_bit(GLF_LOCK, &gl->gl_flags) &&
 			list_empty(&gl->gl_holders)) {
diff -Nru linux-rhel-base/fs/gfs2/glock.h linux-2.6.18.noarch/fs/gfs2/glock.h
--- linux-rhel-base/fs/gfs2/glock.h	2007-04-20 09:35:33.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/glock.h	2007-04-20 10:53:50.000000000 +0100
@@ -67,7 +67,7 @@
 {
 	int ret;
 	spin_lock(&gl->gl_spin);
-	ret = !list_empty(&gl->gl_waiters2) || !list_empty(&gl->gl_waiters3);
+	ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
 	spin_unlock(&gl->gl_spin);
 	return ret;
 }
diff -Nru linux-rhel-base/fs/gfs2/incore.h linux-2.6.18.noarch/fs/gfs2/incore.h
--- linux-rhel-base/fs/gfs2/incore.h	2007-04-20 09:35:33.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/incore.h	2007-04-20 10:56:58.000000000 +0100
@@ -115,11 +115,8 @@
 	/* Actions */
 	HIF_MUTEX		= 0,
 	HIF_PROMOTE		= 1,
-	HIF_DEMOTE		= 2,
 
 	/* States */
-	HIF_ALLOCED		= 4,
-	HIF_DEALLOC		= 5,
 	HIF_HOLDER		= 6,
 	HIF_FIRST		= 7,
 	HIF_ABORTED		= 9,
@@ -142,8 +139,8 @@
 enum {
 	GLF_LOCK		= 1,
 	GLF_STICKY		= 2,
+	GLF_DEMOTE		= 3,
 	GLF_DIRTY		= 5,
-	GLF_SKIP_WAITERS2	= 6,
 };
 
 struct gfs2_glock {
@@ -156,11 +153,12 @@
 
 	unsigned int gl_state;
 	unsigned int gl_hash;
+	unsigned int gl_demote_state; /* state requested by remote node */
+	unsigned long gl_demote_time; /* time of first demote request */
 	pid_t gl_owner_pid;
 	unsigned long gl_ip;
 	struct list_head gl_holders;
 	struct list_head gl_waiters1;	/* HIF_MUTEX */
-	struct list_head gl_waiters2;	/* HIF_DEMOTE */
 	struct list_head gl_waiters3;	/* HIF_PROMOTE */
 
 	const struct gfs2_glock_operations *gl_ops;
diff -Nru linux-rhel-base/fs/gfs2/main.c linux-2.6.18.noarch/fs/gfs2/main.c
--- linux-rhel-base/fs/gfs2/main.c	2007-04-20 09:35:33.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/main.c	2007-04-20 10:53:50.000000000 +0100
@@ -46,7 +46,6 @@
 		spin_lock_init(&gl->gl_spin);
 		INIT_LIST_HEAD(&gl->gl_holders);
 		INIT_LIST_HEAD(&gl->gl_waiters1);
-		INIT_LIST_HEAD(&gl->gl_waiters2);
 		INIT_LIST_HEAD(&gl->gl_waiters3);
 		gl->gl_lvb = NULL;
 		atomic_set(&gl->gl_lvb_count, 0);
diff -Nru linux-rhel-base/fs/gfs2/ops_super.c linux-2.6.18.noarch/fs/gfs2/ops_super.c
--- linux-rhel-base/fs/gfs2/ops_super.c	2007-04-20 09:35:33.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/ops_super.c	2007-04-20 11:01:21.000000000 +0100
@@ -284,6 +284,31 @@
 }
 
 /**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+static void gfs2_drop_inode(struct inode *inode)
+{
+	if (inode->i_private && inode->i_nlink) {
+		struct gfs2_inode *ip = GFS2_I(inode);
+		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+			inode->i_nlink = 0;
+	}
+	generic_drop_inode(inode);
+}
+
+/**
  * gfs2_clear_inode - Deallocate an inode when VFS is done with it
  * @inode: The VFS inode
  *
@@ -441,7 +466,7 @@
 out_uninit:
 	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
-	if (error)
+	if (error && error != GLR_TRYFAILED)
 		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
 out:
 	truncate_inode_pages(&inode->i_data, 0);
@@ -481,6 +506,7 @@
 	.statfs			= gfs2_statfs,
 	.remount_fs		= gfs2_remount_fs,
 	.clear_inode		= gfs2_clear_inode,
+	.drop_inode		= gfs2_drop_inode,
 	.show_options		= gfs2_show_options,
 };