1 files changed, 265 insertions, 108 deletions

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 0d149dcc04e..2ffc67dce87 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -26,53 +26,107 @@
 #include "rgrp.h"
 #include "util.h"
 #include "trans.h"
+#include "dir.h"
+
+static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
+{
+	fs_err(gl->gl_sbd, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page state 0x%lx\n",
+	       bh, (unsigned long long)bh->b_blocknr, bh->b_state,
+	       bh->b_page->mapping, bh->b_page->flags);
+	fs_err(gl->gl_sbd, "AIL glock %u:%llu mapping %p\n",
+	       gl->gl_name.ln_type, gl->gl_name.ln_number,
+	       gfs2_glock2aspace(gl));
+	gfs2_lm_withdraw(gl->gl_sbd, "AIL error\n");
+}
 
 /**
- * ail_empty_gl - remove all buffers for a given lock from the AIL
+ * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
  * @gl: the glock
+ * @fsync: set when called from fsync (not all buffers will be clean)
  *
  * None of the buffers should be dirty, locked, or pinned.
  */
 
-static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
+			     unsigned int nr_revokes)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct list_head *head = &gl->gl_ail_list;
-	struct gfs2_bufdata *bd;
+	struct gfs2_bufdata *bd, *tmp;
 	struct buffer_head *bh;
+	const unsigned long b_state = (1UL << BH_Dirty)|(1UL << BH_Pinned)|(1UL << BH_Lock);
+
+	gfs2_log_lock(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) {
+		if (nr_revokes == 0)
+			break;
+		bh = bd->bd_bh;
+		if (bh->b_state & b_state) {
+			if (fsync)
+				continue;
+			gfs2_ail_error(gl, bh);
+		}
+		gfs2_trans_add_revoke(sdp, bd);
+		nr_revokes--;
+	}
+	GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count));
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+}
+
+
+static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct gfs2_trans tr;
 
 	memset(&tr, 0, sizeof(tr));
+	INIT_LIST_HEAD(&tr.tr_buf);
+	INIT_LIST_HEAD(&tr.tr_databuf);
 	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
 
 	if (!tr.tr_revokes)
 		return;
 
-	/* A shortened, inline version of gfs2_trans_begin() */
+	/* A shortened, inline version of gfs2_trans_begin()
+         * tr->alloced is not set since the transaction structure is
+         * on the stack */
 	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
 	tr.tr_ip = (unsigned long)__builtin_return_address(0);
-	INIT_LIST_HEAD(&tr.tr_list_buf);
-	gfs2_log_reserve(sdp, tr.tr_reserved);
-	BUG_ON(current->journal_info);
+	sb_start_intwrite(sdp->sd_vfs);
+	if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) {
+		sb_end_intwrite(sdp->sd_vfs);
+		return;
+	}
+	WARN_ON_ONCE(current->journal_info);
 	current->journal_info = &tr;
 
-	gfs2_log_lock(sdp);
-	while (!list_empty(head)) {
-		bd = list_entry(head->next, struct gfs2_bufdata,
-				bd_ail_gl_list);
-		bh = bd->bd_bh;
-		gfs2_remove_from_ail(bd);
-		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);
+	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
+
+	gfs2_trans_end(sdp);
+	gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+}
+
+void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
+{
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	unsigned int revokes = atomic_read(&gl->gl_ail_count);
+	unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
+	int ret;
+
+	if (!revokes)
+		return;
 
+	while (revokes > max_revokes)
+		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
+
+	ret = gfs2_trans_begin(sdp, 0, max_revokes);
+	if (ret)
+		return;
+	__gfs2_ail_flush(gl, fsync, max_revokes);
 	gfs2_trans_end(sdp);
-	gfs2_log_flush(sdp, NULL);
+	gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
 }
 
 /**
@@ -86,18 +140,26 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 
 static void rgrp_go_sync(struct gfs2_glock *gl)
 {
-	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct address_space *mapping = &sdp->sd_aspace;
+	struct gfs2_rgrpd *rgd;
 	int error;
 
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
 		return;
-	BUG_ON(gl->gl_state != LM_ST_EXCLUSIVE);
+	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
 
-	gfs2_log_flush(gl->gl_sbd, gl);
-	filemap_fdatawrite(metamapping);
-	error = filemap_fdatawait(metamapping);
-        mapping_set_error(metamapping, error);
+	gfs2_log_flush(sdp, gl, NORMAL_FLUSH);
+	filemap_fdatawrite_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
+	error = filemap_fdatawait_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
+	mapping_set_error(mapping, error);
 	gfs2_ail_empty_gl(gl);
+
+	spin_lock(&gl->gl_spin);
+	rgd = gl->gl_object;
+	if (rgd)
+		gfs2_free_clones(rgd);
+	spin_unlock(&gl->gl_spin);
 }
 
 /**
@@ -112,11 +174,12 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
 
 static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
 {
-	struct address_space *mapping = gfs2_glock2aspace(gl);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct address_space *mapping = &sdp->sd_aspace;
 
-	BUG_ON(!(flags & DIO_METADATA));
-	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
-	truncate_inode_pages(mapping, 0);
+	WARN_ON_ONCE(!(flags & DIO_METADATA));
+	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	truncate_inode_pages_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
 
 	if (gl->gl_object) {
 		struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object;
@@ -138,14 +201,17 @@ static void inode_go_sync(struct gfs2_glock *gl)
 
 	if (ip && !S_ISREG(ip->i_inode.i_mode))
 		ip = NULL;
-	if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
-		unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+	if (ip) {
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+		inode_dio_wait(&ip->i_inode);
+	}
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
 		return;
 
-	BUG_ON(gl->gl_state != LM_ST_EXCLUSIVE);
+	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
 
-	gfs2_log_flush(gl->gl_sbd, gl);
+	gfs2_log_flush(gl->gl_sbd, gl, NORMAL_FLUSH);
 	filemap_fdatawrite(metamapping);
 	if (ip) {
 		struct address_space *mapping = ip->i_inode.i_mapping;
@@ -160,7 +226,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
 	 * Writeback of the data mapping may cause the dirty flag to be set
 	 * so we have to clear it again here.
 	 */
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(GLF_DIRTY, &gl->gl_flags);
 }
 
@@ -168,8 +234,8 @@ static void inode_go_sync(struct gfs2_glock *gl)
  * inode_go_inval - prepare a inode glock to be released
  * @gl: the glock
  * @flags:
- * 
- * Normally we invlidate everything, but if we are moving into
+ *
+ * Normally we invalidate everything, but if we are moving into
  * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
  * can keep hold of the metadata, since it won't have changed.
  *
@@ -187,11 +253,14 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 		if (ip) {
 			set_bit(GIF_INVALID, &ip->i_flags);
 			forget_all_cached_acls(&ip->i_inode);
+			gfs2_dir_hash_inval(ip);
 		}
 	}
 
-	if (ip == GFS2_I(gl->gl_sbd->sd_rindex))
+	if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) {
+		gfs2_log_flush(gl->gl_sbd, NULL, NORMAL_FLUSH);
 		gl->gl_sbd->sd_rindex_uptodate = 0;
+	}
 	if (ip && S_ISREG(ip->i_inode.i_mode))
 		truncate_inode_pages(ip->i_inode.i_mapping, 0);
 }
@@ -206,12 +275,130 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 static int inode_go_demote_ok(const struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_holder *gh;
+
 	if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
 		return 0;
+
+	if (!list_empty(&gl->gl_holders)) {
+		gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+		if (gh->gh_list.next != &gl->gl_holders)
+			return 0;
+	}
+
 	return 1;
 }
 
 /**
+ * gfs2_set_nlink - Set the inode's link count based on on-disk info
+ * @inode: The inode in question
+ * @nlink: The link count
+ *
+ * If the link count has hit zero, it must never be raised, whatever the
+ * on-disk inode might say. When new struct inodes are created the link
+ * count is set to 1, so that we can safely use this test even when reading
+ * in on disk information for the first time.
+ */
+
+static void gfs2_set_nlink(struct inode *inode, u32 nlink)
+{
+	/*
+	 * We will need to review setting the nlink count here in the
+	 * light of the forthcoming ro bind mount work. This is a reminder
+	 * to do that.
+	 */
+	if ((inode->i_nlink != nlink) && (inode->i_nlink != 0)) {
+		if (nlink == 0)
+			clear_nlink(inode);
+		else
+			set_nlink(inode, nlink);
+	}
+}
+
+static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
+{
+	const struct gfs2_dinode *str = buf;
+	struct timespec atime;
+	u16 height, depth;
+
+	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
+		goto corrupt;
+	ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
+	ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
+	ip->i_inode.i_rdev = 0;
+	switch (ip->i_inode.i_mode & S_IFMT) {
+	case S_IFBLK:
+	case S_IFCHR:
+		ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
+					   be32_to_cpu(str->di_minor));
+		break;
+	};
+
+	i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
+	i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid));
+	gfs2_set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink));
+	i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
+	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
+	atime.tv_sec = be64_to_cpu(str->di_atime);
+	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+	if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+		ip->i_inode.i_atime = atime;
+	ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
+	ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
+	ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
+	ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
+
+	ip->i_goal = be64_to_cpu(str->di_goal_meta);
+	ip->i_generation = be64_to_cpu(str->di_generation);
+
+	ip->i_diskflags = be32_to_cpu(str->di_flags);
+	ip->i_eattr = be64_to_cpu(str->di_eattr);
+	/* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */
+	gfs2_set_inode_flags(&ip->i_inode);
+	height = be16_to_cpu(str->di_height);
+	if (unlikely(height > GFS2_MAX_META_HEIGHT))
+		goto corrupt;
+	ip->i_height = (u8)height;
+
+	depth = be16_to_cpu(str->di_depth);
+	if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
+		goto corrupt;
+	ip->i_depth = (u8)depth;
+	ip->i_entries = be32_to_cpu(str->di_entries);
+
+	if (S_ISREG(ip->i_inode.i_mode))
+		gfs2_set_aops(&ip->i_inode);
+
+	return 0;
+corrupt:
+	gfs2_consist_inode(ip);
+	return -EIO;
+}
+
+/**
+ * gfs2_inode_refresh - Refresh the incore copy of the dinode
+ * @ip: The GFS2 inode
+ *
+ * Returns: errno
+ */
+
+int gfs2_inode_refresh(struct gfs2_inode *ip)
+{
+	struct buffer_head *dibh;
+	int error;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		return error;
+
+	error = gfs2_dinode_in(ip, dibh->b_data);
+	brelse(dibh);
+	clear_bit(GIF_INVALID, &ip->i_flags);
+
+	return error;
+}
+
+/**
  * inode_go_lock - operation done after an inode lock is locked by a process
  * @gl: the glock
  * @flags:
@@ -235,6 +422,9 @@ static int inode_go_lock(struct gfs2_holder *gh)
 			return error;
 	}
 
+	if (gh->gh_state != LM_ST_DEFERRED)
+		inode_dio_wait(&ip->i_inode);
+
 	if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
 	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
 	    (gh->gh_state == LM_ST_EXCLUSIVE)) {
@@ -254,90 +444,55 @@ static int inode_go_lock(struct gfs2_holder *gh)
  * @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)
+static void 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;
+		return;
 	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\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,
 		  (unsigned int)ip->i_diskflags,
 		  (unsigned long long)i_size_read(&ip->i_inode));
-	return 0;
 }
 
 /**
- * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
- * @gl: the glock
- *
- * Returns: 1 if it's ok
- */
-
-static int rgrp_go_demote_ok(const struct gfs2_glock *gl)
-{
-	const struct address_space *mapping = (const struct address_space *)(gl + 1);
-	return !mapping->nrpages;
-}
-
-/**
- * rgrp_go_lock - operation done after an rgrp lock is locked by
- *    a first holder on this node.
- * @gl: the glock
- * @flags:
- *
- * Returns: errno
- */
-
-static int rgrp_go_lock(struct gfs2_holder *gh)
-{
-	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
-}
-
-/**
- * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
- *    a last holder on this node.
- * @gl: the glock
- * @flags:
- *
- */
-
-static void rgrp_go_unlock(struct gfs2_holder *gh)
-{
-	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
-}
-
-/**
- * trans_go_sync - promote/demote the transaction glock
+ * freeze_go_sync - promote/demote the freeze glock
  * @gl: the glock
  * @state: the requested state
  * @flags:
  *
  */
 
-static void trans_go_sync(struct gfs2_glock *gl)
+static void freeze_go_sync(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
+	DEFINE_WAIT(wait);
 
-	if (gl->gl_state != LM_ST_UNLOCKED &&
+	if (gl->gl_state == LM_ST_SHARED &&
 	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		flush_workqueue(gfs2_delete_workqueue);
-		gfs2_meta_syncfs(sdp);
-		gfs2_log_shutdown(sdp);
+		atomic_set(&sdp->sd_log_freeze, 1);
+		wake_up(&sdp->sd_logd_waitq);
+		do {
+			prepare_to_wait(&sdp->sd_log_frozen_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&sdp->sd_log_freeze))
+				io_schedule();
+		} while(atomic_read(&sdp->sd_log_freeze));
+		finish_wait(&sdp->sd_log_frozen_wait, &wait);
 	}
 }
 
 /**
- * trans_go_xmote_bh - After promoting/demoting the transaction glock
+ * freeze_go_xmote_bh - After promoting/demoting the freeze glock
  * @gl: the glock
  *
  */
 
-static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
+static int freeze_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);
@@ -370,7 +525,7 @@ static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
  * Always returns 0
  */
 
-static int trans_go_demote_ok(const struct gfs2_glock *gl)
+static int freeze_go_demote_ok(const struct gfs2_glock *gl)
 {
 	return 0;
 }
@@ -381,15 +536,19 @@ static int trans_go_demote_ok(const struct gfs2_glock *gl)
  *
  * gl_spin lock is held while calling this
  */
-static void iopen_go_callback(struct gfs2_glock *gl)
+static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 {
 	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY))
+		return;
 
 	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
 	    gl->gl_state == LM_ST_SHARED && ip) {
-		gfs2_glock_hold(gl);
+		gl->gl_lockref.count++;
 		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
-			gfs2_glock_put_nolock(gl);
+			gl->gl_lockref.count--;
 	}
 }
 
@@ -398,32 +557,29 @@ const struct gfs2_glock_operations gfs2_meta_glops = {
 };
 
 const struct gfs2_glock_operations gfs2_inode_glops = {
-	.go_xmote_th = inode_go_sync,
+	.go_sync = inode_go_sync,
 	.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 / 5,
 	.go_flags = GLOF_ASPACE,
 };
 
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
-	.go_xmote_th = rgrp_go_sync,
+	.go_sync = rgrp_go_sync,
 	.go_inval = rgrp_go_inval,
-	.go_demote_ok = rgrp_go_demote_ok,
-	.go_lock = rgrp_go_lock,
-	.go_unlock = rgrp_go_unlock,
+	.go_lock = gfs2_rgrp_go_lock,
+	.go_unlock = gfs2_rgrp_go_unlock,
 	.go_dump = gfs2_rgrp_dump,
 	.go_type = LM_TYPE_RGRP,
-	.go_min_hold_time = HZ / 5,
-	.go_flags = GLOF_ASPACE,
+	.go_flags = GLOF_LVB,
 };
 
-const struct gfs2_glock_operations gfs2_trans_glops = {
-	.go_xmote_th = trans_go_sync,
-	.go_xmote_bh = trans_go_xmote_bh,
-	.go_demote_ok = trans_go_demote_ok,
+const struct gfs2_glock_operations gfs2_freeze_glops = {
+	.go_sync = freeze_go_sync,
+	.go_xmote_bh = freeze_go_xmote_bh,
+	.go_demote_ok = freeze_go_demote_ok,
 	.go_type = LM_TYPE_NONDISK,
 };
 
@@ -442,6 +598,7 @@ const struct gfs2_glock_operations gfs2_nondisk_glops = {
 
 const struct gfs2_glock_operations gfs2_quota_glops = {
 	.go_type = LM_TYPE_QUOTA,
+	.go_flags = GLOF_LVB,
 };
 
 const struct gfs2_glock_operations gfs2_journal_glops = {