Merge tag 'gfs2-4.11.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull GFS2 updates from Robert Peterson:
 "We've got eight GFS2 patches for this merge window:

   - Andy Price submitted a patch to make gfs2_write_full_page a static
     function.

   - Dan Carpenter submitted a patch to fix a ERR_PTR thinko.

  Three patches fix bugs related to deleting very large files, which
  cause GFS2 to run out of journal space:

   - The first one prevents GFS2 delete operation from requesting too
     much journal space.

   - The second one fixes a problem whereby GFS2 can hang because it
     wasn't taking journal space demand into its calculations.

   - The third one wakes up IO waiters when a flush is done to restart
     processes stuck waiting for journal space to become available.

  The final three patches are a performance improvement related to
  spin_lock contention between multiple writers:

   - The "tr_touched" variable was switched to a flag to be more atomic
     and eliminate the possibility of some races.

   - Function meta_lo_add was moved inline with its only caller to make
     the code more readable and efficient.

   - Contention on the gfs2_log_lock spinlock was greatly reduced by
     avoiding the lock altogether in cases where we don't really need
     it: buffers that already appear in the appropriate metadata list
     for the journal. Many thanks to Steve Whitehouse for the ideas and
     principles behind these patches"

* tag 'gfs2-4.11.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
  gfs2: Make gfs2_write_full_page static
  GFS2: Reduce contention on gfs2_log_lock
  GFS2: Inline function meta_lo_add
  GFS2: Switch tr_touched to flag in transaction
  GFS2: Wake up io waiters whenever a flush is done
  GFS2: Made logd daemon take into account log demand
  GFS2: Limit number of transaction blocks requested for truncates
  GFS2: Fix reference to ERR_PTR in gfs2_glock_iter_next

8 files changed, 105 insertions, 60 deletions

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 6b039d7ce160..ed7a2e252ad8 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -143,8 +143,8 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
 /* This is the same as calling block_write_full_page, but it also
  * writes pages outside of i_size
  */
-int gfs2_write_full_page(struct page *page, get_block_t *get_block,
-			 struct writeback_control *wbc)
+static int gfs2_write_full_page(struct page *page, get_block_t *get_block,
+				struct writeback_control *wbc)
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index fc5da4cbe88c..01b97c012c6e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -720,6 +720,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrp_list rlist;
+	struct gfs2_trans *tr;
 	u64 bn, bstart;
 	u32 blen, btotal;
 	__be64 *p;
@@ -728,6 +729,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	unsigned int revokes = 0;
 	int x;
 	int error;
+	int jblocks_rqsted;
 
 	error = gfs2_rindex_update(sdp);
 	if (error)
@@ -791,12 +793,17 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
 		gfs2_rs_deltree(&ip->i_res);
 
-	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
-				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
-				 revokes);
+restart:
+	jblocks_rqsted = rg_blocks + RES_DINODE +
+		RES_INDIRECT + RES_STATFS + RES_QUOTA +
+		gfs2_struct2blk(sdp, revokes, sizeof(u64));
+	if (jblocks_rqsted > atomic_read(&sdp->sd_log_thresh2))
+		jblocks_rqsted = atomic_read(&sdp->sd_log_thresh2);
+	error = gfs2_trans_begin(sdp, jblocks_rqsted, revokes);
 	if (error)
 		goto out_rg_gunlock;
 
+	tr = current->journal_info;
 	down_write(&ip->i_rw_mutex);
 
 	gfs2_trans_add_meta(ip->i_gl, dibh);
@@ -810,6 +817,16 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		if (!*p)
 			continue;
 
+		/* check for max reasonable journal transaction blocks */
+		if (tr->tr_num_buf_new + RES_STATFS +
+		    RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) {
+			if (rg_blocks >= tr->tr_num_buf_new)
+				rg_blocks -= tr->tr_num_buf_new;
+			else
+				rg_blocks = 0;
+			break;
+		}
+
 		bn = be64_to_cpu(*p);
 
 		if (bstart + blen == bn)
@@ -827,6 +844,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		*p = 0;
 		gfs2_add_inode_blocks(&ip->i_inode, -1);
 	}
+	if (p == bottom)
+		rg_blocks = 0;
+
 	if (bstart) {
 		__gfs2_free_blocks(ip, bstart, blen, metadata);
 		btotal += blen;
@@ -844,6 +864,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 
 	gfs2_trans_end(sdp);
 
+	if (rg_blocks)
+		goto restart;
+
 out_rg_gunlock:
 	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
 out_rlist:
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 94f50cac91c6..a2d45db32cd5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1802,16 +1802,18 @@ void gfs2_glock_exit(void)
 
 static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 {
-	do {
-		gi->gl = rhashtable_walk_next(&gi->hti);
+	while ((gi->gl = rhashtable_walk_next(&gi->hti))) {
 		if (IS_ERR(gi->gl)) {
 			if (PTR_ERR(gi->gl) == -EAGAIN)
 				continue;
 			gi->gl = NULL;
+			return;
 		}
-	/* Skip entries for other sb and dead entries */
-	} while ((gi->gl) && ((gi->sdp != gi->gl->gl_name.ln_sbd) ||
-			      __lockref_is_dead(&gi->gl->gl_lockref)));
+		/* Skip entries for other sb and dead entries */
+		if (gi->sdp == gi->gl->gl_name.ln_sbd &&
+		    !__lockref_is_dead(&gi->gl->gl_lockref))
+			return;
+	}
 }
 
 static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a6a3389a07fc..c45084ac642d 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -470,15 +470,19 @@ struct gfs2_quota_data {
 	struct rcu_head qd_rcu;
 };
 
+enum {
+	TR_TOUCHED = 1,
+	TR_ATTACHED = 2,
+	TR_ALLOCED = 3,
+};
+
 struct gfs2_trans {
 	unsigned long tr_ip;
 
 	unsigned int tr_blocks;
 	unsigned int tr_revokes;
 	unsigned int tr_reserved;
-	unsigned int tr_touched:1;
-	unsigned int tr_attached:1;
-	unsigned int tr_alloced:1;
+	unsigned long tr_flags;
 
 	unsigned int tr_num_buf_new;
 	unsigned int tr_num_databuf_new;
@@ -794,6 +798,7 @@ struct gfs2_sbd {
 	atomic_t sd_log_thresh1;
 	atomic_t sd_log_thresh2;
 	atomic_t sd_log_blks_free;
+	atomic_t sd_log_blks_needed;
 	wait_queue_head_t sd_log_waitq;
 	wait_queue_head_t sd_logd_waitq;
 
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 27c00a16def0..f865b96374df 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -349,6 +349,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
 	if (gfs2_assert_warn(sdp, blks) ||
 	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
 		return -EINVAL;
+	atomic_add(blks, &sdp->sd_log_blks_needed);
 retry:
 	free_blocks = atomic_read(&sdp->sd_log_blks_free);
 	if (unlikely(free_blocks <= wanted)) {
@@ -370,6 +371,7 @@ retry:
 			wake_up(&sdp->sd_reserving_log_wait);
 		goto retry;
 	}
+	atomic_sub(blks, &sdp->sd_log_blks_needed);
 	trace_gfs2_log_blocks(sdp, -blks);
 
 	/*
@@ -797,7 +799,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 
 static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 {
-	WARN_ON_ONCE(old->tr_attached != 1);
+	WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags));
 
 	old->tr_num_buf_new	+= new->tr_num_buf_new;
 	old->tr_num_databuf_new	+= new->tr_num_databuf_new;
@@ -821,9 +823,9 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	if (sdp->sd_log_tr) {
 		gfs2_merge_trans(sdp->sd_log_tr, tr);
 	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
-		gfs2_assert_withdraw(sdp, tr->tr_alloced);
+		gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags));
 		sdp->sd_log_tr = tr;
-		tr->tr_attached = 1;
+		set_bit(TR_ATTACHED, &tr->tr_flags);
 	}
 
 	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
@@ -891,13 +893,16 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 
 static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
 {
-	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+	return (atomic_read(&sdp->sd_log_pinned) +
+		atomic_read(&sdp->sd_log_blks_needed) >=
+		atomic_read(&sdp->sd_log_thresh1));
 }
 
 static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
 {
 	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
-	return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
+	return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >=
+		atomic_read(&sdp->sd_log_thresh2);
 }
 
 /**
@@ -913,12 +918,15 @@ int gfs2_logd(void *data)
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
 	DEFINE_WAIT(wait);
+	bool did_flush;
 
 	while (!kthread_should_stop()) {
 
+		did_flush = false;
 		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+			did_flush = true;
 		}
 
 		if (gfs2_ail_flush_reqd(sdp)) {
@@ -926,9 +934,10 @@ int gfs2_logd(void *data)
 			gfs2_ail1_wait(sdp);
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+			did_flush = true;
 		}
 
-		if (!gfs2_ail_flush_reqd(sdp))
+		if (!gfs2_ail_flush_reqd(sdp) || did_flush)
 			wake_up(&sdp->sd_log_waitq);
 
 		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 49db8ef13fdf..663ffc135ef3 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -292,7 +292,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	wait_on_buffer(bh);
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
-		if (tr && tr->tr_touched)
+		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
 			gfs2_io_error_bh(sdp, bh);
 		brelse(bh);
 		*bhp = NULL;
@@ -319,7 +319,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 
 	if (!buffer_uptodate(bh)) {
 		struct gfs2_trans *tr = current->journal_info;
-		if (tr && tr->tr_touched)
+		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
 			gfs2_io_error_bh(sdp, bh);
 		return -EIO;
 	}
@@ -345,7 +345,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, int meta)
 			tr->tr_num_buf_rm++;
 		else
 			tr->tr_num_databuf_rm++;
-		tr->tr_touched = 1;
+		set_bit(TR_TOUCHED, &tr->tr_flags);
 		was_pinned = 1;
 		brelse(bh);
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index a34308df927f..58704799f0b9 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -683,6 +683,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		goto fail_jindex;
 	}
 
+	atomic_set(&sdp->sd_log_blks_needed, 0);
 	if (sdp->sd_args.ar_spectator) {
 		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
 		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 0c1bde395062..affef3c066e0 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -48,7 +48,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	tr->tr_blocks = blocks;
 	tr->tr_revokes = revokes;
 	tr->tr_reserved = 1;
-	tr->tr_alloced = 1;
+	set_bit(TR_ALLOCED, &tr->tr_flags);
 	if (blocks)
 		tr->tr_reserved += 6 + blocks;
 	if (revokes)
@@ -78,7 +78,8 @@ static void gfs2_print_trans(const struct gfs2_trans *tr)
 {
 	pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
 	pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n",
-		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
+		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
+		test_bit(TR_TOUCHED, &tr->tr_flags));
 	pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
 		tr->tr_num_buf_new, tr->tr_num_buf_rm,
 		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
@@ -89,12 +90,12 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 {
 	struct gfs2_trans *tr = current->journal_info;
 	s64 nbuf;
-	int alloced = tr->tr_alloced;
+	int alloced = test_bit(TR_ALLOCED, &tr->tr_flags);
 
 	BUG_ON(!tr);
 	current->journal_info = NULL;
 
-	if (!tr->tr_touched) {
+	if (!test_bit(TR_TOUCHED, &tr->tr_flags)) {
 		gfs2_log_release(sdp, tr->tr_reserved);
 		if (alloced) {
 			kfree(tr);
@@ -112,8 +113,8 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 		gfs2_print_trans(tr);
 
 	gfs2_log_commit(sdp, tr);
-	if (alloced && !tr->tr_attached)
-			kfree(tr);
+	if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags))
+		kfree(tr);
 	up_read(&sdp->sd_log_flush_lock);
 
 	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
@@ -169,6 +170,10 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 	}
 
 	lock_buffer(bh);
+	if (buffer_pinned(bh)) {
+		set_bit(TR_TOUCHED, &tr->tr_flags);
+		goto out;
+	}
 	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd == NULL) {
@@ -182,7 +187,7 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		gfs2_log_lock(sdp);
 	}
 	gfs2_assert(sdp, bd->bd_gl == gl);
-	tr->tr_touched = 1;
+	set_bit(TR_TOUCHED, &tr->tr_flags);
 	if (list_empty(&bd->bd_list)) {
 		set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
 		set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
@@ -191,45 +196,24 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		list_add_tail(&bd->bd_list, &tr->tr_databuf);
 	}
 	gfs2_log_unlock(sdp);
+out:
 	unlock_buffer(bh);
 }
 
-static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
-	struct gfs2_meta_header *mh;
-	struct gfs2_trans *tr;
-	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
-
-	tr = current->journal_info;
-	tr->tr_touched = 1;
-	if (!list_empty(&bd->bd_list))
-		return;
-	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
-	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
-	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
-	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
-		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
-		       (unsigned long long)bd->bd_bh->b_blocknr);
-		BUG();
-	}
-	if (unlikely(state == SFS_FROZEN)) {
-		printk(KERN_INFO "GFS2:adding buf while frozen\n");
-		gfs2_assert_withdraw(sdp, 0);
-	}
-	gfs2_pin(sdp, bd->bd_bh);
-	mh->__pad0 = cpu_to_be64(0);
-	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
-	list_add(&bd->bd_list, &tr->tr_buf);
-	tr->tr_num_buf_new++;
-}
-
 void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_bufdata *bd;
+	struct gfs2_meta_header *mh;
+	struct gfs2_trans *tr = current->journal_info;
+	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 
 	lock_buffer(bh);
+	if (buffer_pinned(bh)) {
+		set_bit(TR_TOUCHED, &tr->tr_flags);
+		goto out;
+	}
 	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd == NULL) {
@@ -245,8 +229,29 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 		gfs2_log_lock(sdp);
 	}
 	gfs2_assert(sdp, bd->bd_gl == gl);
-	meta_lo_add(sdp, bd);
+	set_bit(TR_TOUCHED, &tr->tr_flags);
+	if (!list_empty(&bd->bd_list))
+		goto out_unlock;
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
+	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
+		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
+		       (unsigned long long)bd->bd_bh->b_blocknr);
+		BUG();
+	}
+	if (unlikely(state == SFS_FROZEN)) {
+		printk(KERN_INFO "GFS2:adding buf while frozen\n");
+		gfs2_assert_withdraw(sdp, 0);
+	}
+	gfs2_pin(sdp, bd->bd_bh);
+	mh->__pad0 = cpu_to_be64(0);
+	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	list_add(&bd->bd_list, &tr->tr_buf);
+	tr->tr_num_buf_new++;
+out_unlock:
 	gfs2_log_unlock(sdp);
+out:
 	unlock_buffer(bh);
 }
 
@@ -256,7 +261,7 @@ void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 
 	BUG_ON(!list_empty(&bd->bd_list));
 	gfs2_add_revoke(sdp, bd);
-	tr->tr_touched = 1;
+	set_bit(TR_TOUCHED, &tr->tr_flags);
 	tr->tr_num_revoke++;
 }