[GFS2] Clean up the glock core

This patch implements a number of cleanups to the core of the
GFS2 glock code. As a result a lot of code is removed. It looks
like a really big change, but actually a large part of this patch
is either removing or moving existing code.

There are some new bits too though, such as the new run_queue()
function which is considerably streamlined. Highlights of this
patch include:

 o Fixes a cluster coherency bug during SH -> EX lock conversions
 o Removes the "glmutex" code in favour of a single bit lock
 o Removes the ->go_xmote_bh() for inodes since it was duplicating
   ->go_lock()
 o We now only use the ->lm_lock() function for both locks and
   unlocks (i.e. unlock is a lock with target mode LM_ST_UNLOCKED)
 o The fast path is considerably shortly, giving performance gains
   especially with lock_nolock
 o The glock_workqueue is now used for all the callbacks from the DLM
   which allows us to simplify the lock_dlm module (see following patch)
 o The way is now open to make further changes such as eliminating the two
   threads (gfs2_glockd and gfs2_scand) in favour of a more efficient
   scheme.

This patch has undergone extensive testing with various test suites
so it should be pretty stable by now.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Bob Peterson <rpeterso@redhat.com>

fs/gfs2/glock.h

@@ -26,11 +26,8 @@
 #define GL_SKIP			0x00000100
 #define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
-#define GL_FLOCK		0x00000800
-#define GL_NOCANCEL		0x00001000
 
 #define GLR_TRYFAILED		13
-#define GLR_CANCELED		14
 
 static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
 {
@@ -41,6 +38,8 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
 	spin_lock(&gl->gl_spin);
 	pid = task_pid(current);
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			break;
 		if (gh->gh_owner_pid == pid)
 			goto out;
 	}
@@ -70,7 +69,7 @@ static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
 {
 	int ret;
 	spin_lock(&gl->gl_spin);
-	ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
+	ret = test_bit(GLF_DEMOTE, &gl->gl_flags);
 	spin_unlock(&gl->gl_spin);
 	return ret;
 }
@@ -98,6 +97,7 @@ int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
 int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
 
 /**
  * gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
@@ -130,7 +130,6 @@ int gfs2_lvb_hold(struct gfs2_glock *gl);
 void gfs2_lvb_unhold(struct gfs2_glock *gl);
 
 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_gl_hash_clear(struct gfs2_sbd *sdp, int wait);

fs/gfs2/glops.c

@@ -13,6 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/lm_interface.h>
+#include <linux/bio.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -171,26 +172,6 @@ static void inode_go_sync(struct gfs2_glock *gl)
 	}
 }
 
-/**
- * inode_go_xmote_bh - After promoting/demoting a glock
- * @gl: the glock
- *
- */
-
-static void inode_go_xmote_bh(struct gfs2_glock *gl)
-{
-	struct gfs2_holder *gh = gl->gl_req_gh;
-	struct buffer_head *bh;
-	int error;
-
-	if (gl->gl_state != LM_ST_UNLOCKED &&
-	    (!gh || !(gh->gh_flags & GL_SKIP))) {
-		error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
-		if (!error)
-			brelse(bh);
-	}
-}
-
 /**
  * inode_go_inval - prepare a inode glock to be released
  * @gl: the glock
@@ -266,6 +247,26 @@ static int inode_go_lock(struct gfs2_holder *gh)
 	return error;
 }
 
+/**
+ * inode_go_dump - print information about an inode
+ * @seq: The iterator
+ * @ip: the inode
+ *
+ * Returns: 0 on success, -ENOBUFS when we run out of space
+ */
+
+static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_inode *ip = gl->gl_object;
+	if (ip == NULL)
+		return 0;
+	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%08lx\n",
+		  (unsigned long long)ip->i_no_formal_ino,
+		  (unsigned long long)ip->i_no_addr,
+		  IF2DT(ip->i_inode.i_mode), ip->i_flags);
+	return 0;
+}
+
 /**
  * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
  * @gl: the glock
@@ -305,6 +306,22 @@ static void rgrp_go_unlock(struct gfs2_holder *gh)
 	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
 }
 
+/**
+ * rgrp_go_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
+ *
+ */
+
+static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_rgrpd *rgd = gl->gl_object;
+	if (rgd == NULL)
+		return 0;
+	gfs2_print_dbg(seq, " R: n:%llu\n", (unsigned long long)rgd->rd_addr);
+	return 0;
+}
+
 /**
  * trans_go_sync - promote/demote the transaction glock
  * @gl: the glock
@@ -330,7 +347,7 @@ static void trans_go_sync(struct gfs2_glock *gl)
  *
  */
 
-static void trans_go_xmote_bh(struct gfs2_glock *gl)
+static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
@@ -338,8 +355,7 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl)
 	struct gfs2_log_header_host head;
 	int error;
 
-	if (gl->gl_state != LM_ST_UNLOCKED &&
+	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
 		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 
 		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
@@ -354,6 +370,7 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl)
 			gfs2_log_pointers_init(sdp, head.lh_blkno);
 		}
 	}
+	return 0;
 }
 
 /**
@@ -375,12 +392,12 @@ const struct gfs2_glock_operations gfs2_meta_glops = {
 
 const struct gfs2_glock_operations gfs2_inode_glops = {
 	.go_xmote_th = inode_go_sync,
-	.go_xmote_bh = inode_go_xmote_bh,
 	.go_inval = inode_go_inval,
 	.go_demote_ok = inode_go_demote_ok,
 	.go_lock = inode_go_lock,
+	.go_dump = inode_go_dump,
 	.go_type = LM_TYPE_INODE,
-	.go_min_hold_time = HZ / 10,
+	.go_min_hold_time = HZ / 5,
 };
 
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
@@ -389,8 +406,9 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_demote_ok = rgrp_go_demote_ok,
 	.go_lock = rgrp_go_lock,
 	.go_unlock = rgrp_go_unlock,
+	.go_dump = rgrp_go_dump,
 	.go_type = LM_TYPE_RGRP,
-	.go_min_hold_time = HZ / 10,
+	.go_min_hold_time = HZ / 5,
 };
 
 const struct gfs2_glock_operations gfs2_trans_glops = {

fs/gfs2/incore.h

@@ -128,20 +128,20 @@ struct gfs2_bufdata {
 
 struct gfs2_glock_operations {
 	void (*go_xmote_th) (struct gfs2_glock *gl);
-	void (*go_xmote_bh) (struct gfs2_glock *gl);
+	int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
 	void (*go_inval) (struct gfs2_glock *gl, int flags);
 	int (*go_demote_ok) (struct gfs2_glock *gl);
 	int (*go_lock) (struct gfs2_holder *gh);
 	void (*go_unlock) (struct gfs2_holder *gh);
+	int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
 	const int go_type;
 	const unsigned long go_min_hold_time;
 };
 
 enum {
 	/* States */
-	HIF_HOLDER		= 6,
+	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
 	HIF_FIRST		= 7,
-	HIF_ABORTED		= 9,
 	HIF_WAIT		= 10,
 };
 
@@ -154,20 +154,20 @@ struct gfs2_holder {
 	unsigned gh_flags;
 
 	int gh_error;
-	unsigned long gh_iflags;
+	unsigned long gh_iflags; /* HIF_... */
 	unsigned long gh_ip;
 };
 
 enum {
-	GLF_LOCK		= 1,
+	GLF_LOCK			= 1,
-	GLF_STICKY		= 2,
+	GLF_STICKY			= 2,
-	GLF_DEMOTE		= 3,
+	GLF_DEMOTE			= 3,
-	GLF_PENDING_DEMOTE	= 4,
+	GLF_PENDING_DEMOTE		= 4,
-	GLF_DIRTY		= 5,
+	GLF_DEMOTE_IN_PROGRESS		= 5,
-	GLF_DEMOTE_IN_PROGRESS	= 6,
+	GLF_DIRTY			= 6,
-	GLF_LFLUSH		= 7,
+	GLF_LFLUSH			= 7,
-	GLF_WAITERS2		= 8,
+	GLF_INVALIDATE_IN_PROGRESS	= 8,
-	GLF_CONV_DEADLK		= 9,
+	GLF_REPLY_PENDING		= 9,
 };
 
 struct gfs2_glock {
@@ -179,19 +179,14 @@ struct gfs2_glock {
 	spinlock_t gl_spin;
 
 	unsigned int gl_state;
+	unsigned int gl_target;
+	unsigned int gl_reply;
 	unsigned int gl_hash;
 	unsigned int gl_demote_state; /* state requested by remote node */
 	unsigned long gl_demote_time; /* time of first demote request */
-	struct pid *gl_owner_pid;
-	unsigned long gl_ip;
 	struct list_head gl_holders;
-	struct list_head gl_waiters1;	/* HIF_MUTEX */
-	struct list_head gl_waiters3;	/* HIF_PROMOTE */
 
 	const struct gfs2_glock_operations *gl_ops;
-
-	struct gfs2_holder *gl_req_gh;
-
 	void *gl_lock;
 	char *gl_lvb;
 	atomic_t gl_lvb_count;

fs/gfs2/locking/dlm/lock.c

@@ -308,6 +308,9 @@ unsigned int gdlm_lock(void *lock, unsigned int cur_state,
 {
 	struct gdlm_lock *lp = lock;
 
+	if (req_state == LM_ST_UNLOCKED)
+		return gdlm_unlock(lock, cur_state);
+
 	clear_bit(LFL_DLM_CANCEL, &lp->flags);
 	if (flags & LM_FLAG_NOEXP)
 		set_bit(LFL_NOBLOCK, &lp->flags);

fs/gfs2/locking/nolock/main.c

@@ -107,6 +107,8 @@ static void nolock_put_lock(void *lock)
 static unsigned int nolock_lock(void *lock, unsigned int cur_state,
 				unsigned int req_state, unsigned int flags)
 {
+	if (req_state == LM_ST_UNLOCKED)
+		return 0;
 	return req_state | LM_OUT_CACHEABLE;
 }
 

fs/gfs2/main.c

@@ -40,8 +40,6 @@ static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo)
 	INIT_HLIST_NODE(&gl->gl_list);
 	spin_lock_init(&gl->gl_spin);
 	INIT_LIST_HEAD(&gl->gl_holders);
-	INIT_LIST_HEAD(&gl->gl_waiters1);
-	INIT_LIST_HEAD(&gl->gl_waiters3);
 	gl->gl_lvb = NULL;
 	atomic_set(&gl->gl_lvb_count, 0);
 	INIT_LIST_HEAD(&gl->gl_reclaim);

fs/gfs2/meta_io.c

@@ -129,7 +129,7 @@ void gfs2_meta_sync(struct gfs2_glock *gl)
 }
 
 /**
- * getbuf - Get a buffer with a given address space
+ * gfs2_getbuf - Get a buffer with a given address space
  * @gl: the glock
  * @blkno: the block number (filesystem scope)
  * @create: 1 if the buffer should be created
@@ -137,7 +137,7 @@ void gfs2_meta_sync(struct gfs2_glock *gl)
  * Returns: the buffer
  */
 
-static struct buffer_head *getbuf(struct gfs2_glock *gl, u64 blkno, int create)
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 {
 	struct address_space *mapping = gl->gl_aspace->i_mapping;
 	struct gfs2_sbd *sdp = gl->gl_sbd;
@@ -205,7 +205,7 @@ static void meta_prep_new(struct buffer_head *bh)
 struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 {
 	struct buffer_head *bh;
-	bh = getbuf(gl, blkno, CREATE);
+	bh = gfs2_getbuf(gl, blkno, CREATE);
 	meta_prep_new(bh);
 	return bh;
 }
@@ -223,7 +223,7 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 		   struct buffer_head **bhp)
 {
-	*bhp = getbuf(gl, blkno, CREATE);
+	*bhp = gfs2_getbuf(gl, blkno, CREATE);
 	if (!buffer_uptodate(*bhp)) {
 		ll_rw_block(READ_META, 1, bhp);
 		if (flags & DIO_WAIT) {
@@ -346,7 +346,7 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
 	struct buffer_head *bh;
 
 	while (blen) {
-		bh = getbuf(ip->i_gl, bstart, NO_CREATE);
+		bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
 		if (bh) {
 			lock_buffer(bh);
 			gfs2_log_lock(sdp);
@@ -421,7 +421,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 	if (extlen > max_ra)
 		extlen = max_ra;
 
-	first_bh = getbuf(gl, dblock, CREATE);
+	first_bh = gfs2_getbuf(gl, dblock, CREATE);
 
 	if (buffer_uptodate(first_bh))
 		goto out;
@@ -432,7 +432,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 	extlen--;
 
 	while (extlen) {
-		bh = getbuf(gl, dblock, CREATE);
+		bh = gfs2_getbuf(gl, dblock, CREATE);
 
 		if (!buffer_uptodate(bh) && !buffer_locked(bh))
 			ll_rw_block(READA, 1, &bh);

fs/gfs2/meta_io.h

@@ -47,6 +47,7 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno,
 		   int flags, struct buffer_head **bhp);
 int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
+struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create);
 
 void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
 			 int meta);

fs/gfs2/ops_address.c

@@ -507,26 +507,23 @@ static int __gfs2_readpage(void *file, struct page *page)
 static int gfs2_readpage(struct file *file, struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
-	struct gfs2_holder *gh;
+	struct gfs2_holder gh;
 	int error;
 
-	gh = gfs2_glock_is_locked_by_me(ip->i_gl);
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
-	if (!gh) {
+	error = gfs2_glock_nq_atime(&gh);
-		gh = kmalloc(sizeof(struct gfs2_holder), GFP_NOFS);
+	if (unlikely(error)) {
-		if (!gh)
-			return -ENOBUFS;
-		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, gh);
 		unlock_page(page);
-		error = gfs2_glock_nq_atime(gh);
+		goto out;
-		if (likely(error != 0))
-			goto out;
-		return AOP_TRUNCATED_PAGE;
 	}
 	error = __gfs2_readpage(file, page);
-	gfs2_glock_dq(gh);
+	gfs2_glock_dq(&gh);
 out:
-	gfs2_holder_uninit(gh);
+	gfs2_holder_uninit(&gh);
-	kfree(gh);
+	if (error == GLR_TRYFAILED) {
+		yield();
+		return AOP_TRUNCATED_PAGE;
+	}
 	return error;
 }
 

fs/gfs2/ops_file.c

@@ -669,8 +669,7 @@ 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);
 
@@ -683,9 +682,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 		gfs2_glock_dq_wait(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
-		error = gfs2_glock_get(GFS2_SB(&ip->i_inode),
+		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
-				      ip->i_no_addr, &gfs2_flock_glops,
+				       &gfs2_flock_glops, CREATE, &gl);
-				      CREATE, &gl);
 		if (error)
 			goto out;
 		gfs2_holder_init(gl, state, flags, fl_gh);

fs/gfs2/recovery.c

@@ -505,7 +505,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
 
 		error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED,
 					   LM_FLAG_NOEXP | LM_FLAG_PRIORITY |
-					   GL_NOCANCEL | GL_NOCACHE, &t_gh);
+					   GL_NOCACHE, &t_gh);
 		if (error)
 			goto fail_gunlock_ji;
 

fs/gfs2/super.c

@@ -941,8 +941,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp,
 	}
 
 	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_DEFERRED,
-			       LM_FLAG_PRIORITY | GL_NOCACHE,
+				   GL_NOCACHE, t_gh);
-			       t_gh);
 
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		error = gfs2_jdesc_check(jd);