1 files changed, 364 insertions, 248 deletions

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 5f2e5224c51c..2173ccf5034b 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
  * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
  */
 
 #include <linux/spinlock.h>
@@ -13,6 +10,8 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/bio.h>
 #include <linux/posix_acl.h>
+#include <linux/security.h>
+#include <linux/log2.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -27,29 +26,39 @@
 #include "util.h"
 #include "trans.h"
 #include "dir.h"
+#include "lops.h"
+
+struct workqueue_struct *gfs2_freeze_wq;
 
 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",
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+	fs_err(sdp,
+	       "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",
+	       bh->b_folio->mapping, bh->b_folio->flags.f);
+	fs_err(sdp, "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");
+	gfs2_lm(sdp, "AIL error\n");
+	gfs2_withdraw(sdp);
 }
 
 /**
  * __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)
+ * @nr_revokes: Number of buffers to revoke
  *
  * None of the buffers should be dirty, locked, or pinned.
  */
 
-static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
+			     unsigned int nr_revokes)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct list_head *head = &gl->gl_ail_list;
 	struct gfs2_bufdata *bd, *tmp;
 	struct buffer_head *bh;
@@ -57,7 +66,9 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 
 	gfs2_log_lock(sdp);
 	spin_lock(&sdp->sd_ail_lock);
-	list_for_each_entry_safe(bd, tmp, head, bd_ail_gl_list) {
+	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)
@@ -65,6 +76,7 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 			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);
@@ -72,34 +84,62 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 }
 
 
-static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_trans tr;
+	unsigned int revokes;
+	int ret = 0;
+
+	revokes = atomic_read(&gl->gl_ail_count);
+
+	if (!revokes) {
+		bool have_revokes;
+		bool log_in_flight;
+
+		/*
+		 * We have nothing on the ail, but there could be revokes on
+		 * the sdp revoke queue, in which case, we still want to flush
+		 * the log and wait for it to finish.
+		 *
+		 * If the sdp revoke list is empty too, we might still have an
+		 * io outstanding for writing revokes, so we should wait for
+		 * it before returning.
+		 *
+		 * If none of these conditions are true, our revokes are all
+		 * flushed and we can return.
+		 */
+		gfs2_log_lock(sdp);
+		have_revokes = !list_empty(&sdp->sd_log_revokes);
+		log_in_flight = atomic_read(&sdp->sd_log_in_flight);
+		gfs2_log_unlock(sdp);
+		if (have_revokes)
+			goto flush;
+		if (log_in_flight)
+			log_flush_wait(sdp);
+		return 0;
+	}
 
 	memset(&tr, 0, sizeof(tr));
-	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
-
-	if (!tr.tr_revokes)
-		return;
-
-	/* A shortened, inline version of gfs2_trans_begin() */
-	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
-	tr.tr_ip = (unsigned long)__builtin_return_address(0);
-	sb_start_intwrite(sdp->sd_vfs);
-	gfs2_log_reserve(sdp, tr.tr_reserved);
-	WARN_ON_ONCE(current->journal_info);
-	current->journal_info = &tr;
-
-	__gfs2_ail_flush(gl, 0);
-
+	set_bit(TR_ONSTACK, &tr.tr_flags);
+	ret = __gfs2_trans_begin(&tr, sdp, 0, revokes, _RET_IP_);
+	if (ret) {
+		fs_err(sdp, "Transaction error %d: Unable to write revokes.", ret);
+		goto flush;
+	}
+	__gfs2_ail_flush(gl, 0, revokes);
 	gfs2_trans_end(sdp);
-	gfs2_log_flush(sdp, NULL);
+
+flush:
+	if (!ret)
+		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
+				GFS2_LFC_AIL_EMPTY_GL);
+	return ret;
 }
 
 void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned int revokes = atomic_read(&gl->gl_ail_count);
 	int ret;
 
@@ -109,9 +149,35 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 	ret = gfs2_trans_begin(sdp, 0, revokes);
 	if (ret)
 		return;
-	__gfs2_ail_flush(gl, fsync);
+	__gfs2_ail_flush(gl, fsync, revokes);
 	gfs2_trans_end(sdp);
-	gfs2_log_flush(sdp, NULL);
+	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
+		       GFS2_LFC_AIL_FLUSH);
+}
+
+/**
+ * gfs2_rgrp_metasync - sync out the metadata of a resource group
+ * @gl: the glock protecting the resource group
+ *
+ */
+
+static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct address_space *metamapping = gfs2_aspace(sdp);
+	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+	const unsigned bsize = sdp->sd_sb.sb_bsize;
+	loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+	loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+	int error;
+
+	filemap_fdatawrite_range(metamapping, start, end);
+	error = filemap_fdatawait_range(metamapping, start, end);
+	WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+	mapping_set_error(metamapping, error);
+	if (error)
+		gfs2_io_error(sdp);
+	return error;
 }
 
 /**
@@ -120,30 +186,26 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
  *
  * Called when demoting or unlocking an EX glock.  We must flush
  * to disk all dirty buffers/pages relating to this glock, and must not
- * not return to caller to demote/unlock the glock until I/O is complete.
+ * return to caller to demote/unlock the glock until I/O is complete.
  */
 
-static void rgrp_go_sync(struct gfs2_glock *gl)
+static int rgrp_go_sync(struct gfs2_glock *gl)
 {
-	struct address_space *metamapping = gfs2_glock2aspace(gl);
-	struct gfs2_rgrpd *rgd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
 	int error;
 
-	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
-		return;
+	if (!rgd || !test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
+		return 0;
 	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_ail_empty_gl(gl);
-
-	spin_lock(&gl->gl_spin);
-	rgd = gl->gl_object;
-	if (rgd)
-		gfs2_free_clones(rgd);
-	spin_unlock(&gl->gl_spin);
+	gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
+		       GFS2_LFC_RGRP_GO_SYNC);
+	error = gfs2_rgrp_metasync(gl);
+	if (!error)
+		error = gfs2_ail_empty_gl(gl);
+	gfs2_free_clones(rgd);
+	return error;
 }
 
 /**
@@ -158,64 +220,136 @@ 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_name.ln_sbd;
+	struct address_space *mapping = gfs2_aspace(sdp);
+	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+	const unsigned bsize = sdp->sd_sb.sb_bsize;
+	loff_t start, end;
 
+	if (!rgd)
+		return;
+	start = (rgd->rd_addr * bsize) & PAGE_MASK;
+	end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+	gfs2_rgrp_brelse(rgd);
 	WARN_ON_ONCE(!(flags & DIO_METADATA));
-	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
-	truncate_inode_pages(mapping, 0);
+	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	truncate_inode_pages_range(mapping, start, end);
+}
 
-	if (gl->gl_object) {
-		struct gfs2_rgrpd *rgd = (struct gfs2_rgrpd *)gl->gl_object;
-		rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
-	}
+static void gfs2_rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl,
+			      const char *fs_id_buf)
+{
+	struct gfs2_rgrpd *rgd = gl->gl_object;
+
+	if (rgd)
+		gfs2_rgrp_dump(seq, rgd, fs_id_buf);
+}
+
+static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip;
+
+	spin_lock(&gl->gl_lockref.lock);
+	ip = gl->gl_object;
+	if (ip)
+		set_bit(GIF_GLOP_PENDING, &ip->i_flags);
+	spin_unlock(&gl->gl_lockref.lock);
+	return ip;
+}
+
+struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl)
+{
+	struct gfs2_rgrpd *rgd;
+
+	spin_lock(&gl->gl_lockref.lock);
+	rgd = gl->gl_object;
+	spin_unlock(&gl->gl_lockref.lock);
+
+	return rgd;
+}
+
+static void gfs2_clear_glop_pending(struct gfs2_inode *ip)
+{
+	if (!ip)
+		return;
+
+	clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags);
+	wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING);
 }
 
 /**
- * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * gfs2_inode_metasync - sync out the metadata of an inode
  * @gl: the glock protecting the inode
  *
  */
-
-static void inode_go_sync(struct gfs2_glock *gl)
+int gfs2_inode_metasync(struct gfs2_glock *gl)
 {
-	struct gfs2_inode *ip = gl->gl_object;
 	struct address_space *metamapping = gfs2_glock2aspace(gl);
 	int error;
 
-	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);
+	filemap_fdatawrite(metamapping);
+	error = filemap_fdatawait(metamapping);
+	if (error)
+		gfs2_io_error(gl->gl_name.ln_sbd);
+	return error;
+}
+
+/**
+ * inode_go_sync - Sync the dirty metadata of an inode
+ * @gl: the glock protecting the inode
+ *
+ */
+
+static int inode_go_sync(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gfs2_glock2inode(gl);
+	int isreg = ip && S_ISREG(ip->i_inode.i_mode);
+	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	int error = 0, ret;
+
+	if (isreg) {
+		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;
+		goto out;
 
 	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
 
-	gfs2_log_flush(gl->gl_sbd, gl);
+	gfs2_log_flush(gl->gl_name.ln_sbd, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
+		       GFS2_LFC_INODE_GO_SYNC);
 	filemap_fdatawrite(metamapping);
-	if (ip) {
+	if (isreg) {
 		struct address_space *mapping = ip->i_inode.i_mapping;
 		filemap_fdatawrite(mapping);
 		error = filemap_fdatawait(mapping);
 		mapping_set_error(mapping, error);
 	}
-	error = filemap_fdatawait(metamapping);
-	mapping_set_error(metamapping, error);
-	gfs2_ail_empty_gl(gl);
+	ret = gfs2_inode_metasync(gl);
+	if (!error)
+		error = ret;
+	ret = gfs2_ail_empty_gl(gl);
+	if (!error)
+		error = ret;
 	/*
 	 * 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);
+
+out:
+	gfs2_clear_glop_pending(ip);
+	return error;
 }
 
 /**
  * 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.
  *
@@ -223,110 +357,78 @@ static void inode_go_sync(struct gfs2_glock *gl)
 
 static void inode_go_inval(struct gfs2_glock *gl, int flags)
 {
-	struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_inode *ip = gfs2_glock2inode(gl);
 
-	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
+	gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count));
 
 	if (flags & DIO_METADATA) {
 		struct address_space *mapping = gfs2_glock2aspace(gl);
 		truncate_inode_pages(mapping, 0);
 		if (ip) {
-			set_bit(GIF_INVALID, &ip->i_flags);
+			set_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags);
 			forget_all_cached_acls(&ip->i_inode);
+			security_inode_invalidate_secctx(&ip->i_inode);
 			gfs2_dir_hash_inval(ip);
 		}
 	}
 
-	if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) {
-		gfs2_log_flush(gl->gl_sbd, NULL);
-		gl->gl_sbd->sd_rindex_uptodate = 0;
+	if (ip == GFS2_I(gl->gl_name.ln_sbd->sd_rindex)) {
+		gfs2_log_flush(gl->gl_name.ln_sbd, NULL,
+			       GFS2_LOG_HEAD_FLUSH_NORMAL |
+			       GFS2_LFC_INODE_GO_INVAL);
+		gl->gl_name.ln_sbd->sd_rindex_uptodate = 0;
 	}
 	if (ip && S_ISREG(ip->i_inode.i_mode))
 		truncate_inode_pages(ip->i_inode.i_mapping, 0);
-}
-
-/**
- * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
- * @gl: the glock
- *
- * Returns: 1 if it's ok
- */
-
-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);
-	}
+	gfs2_clear_glop_pending(ip);
 }
 
 static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 {
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	const struct gfs2_dinode *str = buf;
-	struct timespec atime;
+	struct timespec64 atime, iatime;
 	u16 height, depth;
+	umode_t mode = be32_to_cpu(str->di_mode);
+	struct inode *inode = &ip->i_inode;
+	bool is_new = inode_state_read_once(inode) & I_NEW;
 
-	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
-		goto corrupt;
+	if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+	if (unlikely(!is_new && inode_wrong_type(inode, mode))) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
 	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));
+	inode->i_mode = mode;
+	if (is_new) {
+		inode->i_rdev = 0;
+		switch (mode & S_IFMT) {
+		case S_IFBLK:
+		case S_IFCHR:
+			inode->i_rdev = MKDEV(be32_to_cpu(str->di_major),
+					      be32_to_cpu(str->di_minor));
+			break;
+		}
+	}
+
+	i_uid_write(inode, be32_to_cpu(str->di_uid));
+	i_gid_write(inode, be32_to_cpu(str->di_gid));
+	set_nlink(inode, be32_to_cpu(str->di_nlink));
+	i_size_write(inode, be64_to_cpu(str->di_size));
+	gfs2_set_inode_blocks(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);
+	iatime = inode_get_atime(inode);
+	if (timespec64_compare(&iatime, &atime) < 0)
+		inode_set_atime_to_ts(inode, atime);
+	inode_set_mtime(inode, be64_to_cpu(str->di_mtime),
+			be32_to_cpu(str->di_mtime_nsec));
+	inode_set_ctime(inode, be64_to_cpu(str->di_ctime),
+			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);
@@ -334,25 +436,35 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 	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);
+	gfs2_set_inode_flags(inode);
 	height = be16_to_cpu(str->di_height);
-	if (unlikely(height > GFS2_MAX_META_HEIGHT))
-		goto corrupt;
+	if (unlikely(height > sdp->sd_max_height)) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
 	ip->i_height = (u8)height;
 
 	depth = be16_to_cpu(str->di_depth);
-	if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
-		goto corrupt;
+	if (unlikely(depth > GFS2_DIR_MAX_DEPTH)) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+	if ((ip->i_diskflags & GFS2_DIF_EXHASH) &&
+	    depth < ilog2(sdp->sd_hash_ptrs)) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
 	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);
+	if (gfs2_is_stuffed(ip) && inode->i_size > gfs2_max_stuffed_size(ip)) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+	if (S_ISREG(inode->i_mode))
+		gfs2_set_aops(inode);
 
 	return 0;
-corrupt:
-	gfs2_consist_inode(ip);
-	return -EIO;
 }
 
 /**
@@ -362,7 +474,7 @@ corrupt:
  * Returns: errno
  */
 
-int gfs2_inode_refresh(struct gfs2_inode *ip)
+static int gfs2_inode_refresh(struct gfs2_inode *ip)
 {
 	struct buffer_head *dibh;
 	int error;
@@ -373,45 +485,49 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
 
 	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:
+ * inode_go_instantiate - read in an inode if necessary
+ * @gl: The glock
  *
  * Returns: errno
  */
 
-static int inode_go_lock(struct gfs2_holder *gh)
+static int inode_go_instantiate(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_glock *io_gl;
+	int error;
+
+	if (!ip) /* no inode to populate - read it in later */
+		return 0;
+
+	error = gfs2_inode_refresh(ip);
+	if (error)
+		return error;
+	io_gl = ip->i_iopen_gh.gh_gl;
+	io_gl->gl_no_formal_ino = ip->i_no_formal_ino;
+	return 0;
+}
+
+static int inode_go_held(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct gfs2_inode *ip = gl->gl_object;
 	int error = 0;
 
-	if (!ip || (gh->gh_flags & GL_SKIP))
+	if (!ip) /* no inode to populate - read it in later */
 		return 0;
 
-	if (test_bit(GIF_INVALID, &ip->i_flags)) {
-		error = gfs2_inode_refresh(ip);
-		if (error)
-			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)) {
-		spin_lock(&sdp->sd_trunc_lock);
-		if (list_empty(&ip->i_trunc_list))
-			list_add(&sdp->sd_trunc_list, &ip->i_trunc_list);
-		spin_unlock(&sdp->sd_trunc_lock);
-		wake_up(&sdp->sd_quota_wait);
-		return 1;
-	}
+	    (gh->gh_state == LM_ST_EXCLUSIVE))
+		error = gfs2_truncatei_resume(ip);
 
 	return error;
 }
@@ -419,53 +535,68 @@ static int inode_go_lock(struct gfs2_holder *gh)
 /**
  * inode_go_dump - print information about an inode
  * @seq: The iterator
- * @ip: the inode
+ * @gl: The glock
+ * @fs_id_buf: file system id (may be empty)
  *
- * 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 char *fs_id_buf)
 {
-	const struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_inode *ip = gl->gl_object;
+	const struct inode *inode = &ip->i_inode;
+
 	if (ip == NULL)
-		return 0;
-	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n",
+		return;
+
+	gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu "
+		       "p:%lu\n", fs_id_buf,
 		  (unsigned long long)ip->i_no_formal_ino,
 		  (unsigned long long)ip->i_no_addr,
-		  IF2DT(ip->i_inode.i_mode), ip->i_flags,
+		  IF2DT(inode->i_mode), ip->i_flags,
 		  (unsigned int)ip->i_diskflags,
-		  (unsigned long long)i_size_read(&ip->i_inode));
-	return 0;
+		  (unsigned long long)i_size_read(inode),
+		  inode->i_data.nrpages);
 }
 
 /**
- * trans_go_sync - promote/demote the transaction glock
+ * freeze_go_callback - A cluster node is requesting a freeze
  * @gl: the glock
- * @state: the requested state
- * @flags:
- *
+ * @remote: true if this came from a different cluster node
  */
 
-static void trans_go_sync(struct gfs2_glock *gl)
+static void freeze_go_callback(struct gfs2_glock *gl, bool remote)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct super_block *sb = sdp->sd_vfs;
 
-	if (gl->gl_state != LM_ST_UNLOCKED &&
-	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		gfs2_meta_syncfs(sdp);
-		gfs2_log_shutdown(sdp);
+	if (!remote ||
+	    (gl->gl_state != LM_ST_SHARED &&
+	     gl->gl_state != LM_ST_UNLOCKED) ||
+	    gl->gl_demote_state != LM_ST_UNLOCKED)
+		return;
+
+	/*
+	 * Try to get an active super block reference to prevent racing with
+	 * unmount (see super_trylock_shared()).  But note that unmount isn't
+	 * the only place where a write lock on s_umount is taken, and we can
+	 * fail here because of things like remount as well.
+	 */
+	if (down_read_trylock(&sb->s_umount)) {
+		atomic_inc(&sb->s_active);
+		up_read(&sb->s_umount);
+		if (!queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work))
+			deactivate_super(sb);
 	}
 }
 
 /**
- * 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_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 	struct gfs2_glock *j_gl = ip->i_gl;
 	struct gfs2_log_header_host head;
@@ -475,51 +606,36 @@ static int trans_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
 		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 
 		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
-		if (error)
-			gfs2_consist(sdp);
-		if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
-			gfs2_consist(sdp);
-
-		/*  Initialize some head of the log stuff  */
-		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
-			sdp->sd_log_sequence = head.lh_sequence + 1;
-			gfs2_log_pointers_init(sdp, head.lh_blkno);
-		}
+		if (gfs2_assert_withdraw(sdp, !error))
+			return error;
+		if (gfs2_assert_withdraw(sdp, head.lh_flags &
+					 GFS2_LOG_HEAD_UNMOUNT))
+			return -EIO;
+		gfs2_log_pointers_init(sdp, &head);
 	}
 	return 0;
 }
 
 /**
- * trans_go_demote_ok
- * @gl: the glock
- *
- * Always returns 0
- */
-
-static int trans_go_demote_ok(const struct gfs2_glock *gl)
-{
-	return 0;
-}
-
-/**
  * iopen_go_callback - schedule the dcache entry for the inode to be deleted
  * @gl: the glock
+ * @remote: true if this came from a different cluster node
  *
- * gl_spin lock is held while calling this
+ * gl_lockref.lock lock is held while calling this
  */
 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;
+	struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY))
+	if (!remote || test_bit(SDF_KILL, &sdp->sd_flags))
 		return;
 
 	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
 	    gl->gl_state == LM_ST_SHARED && ip) {
-		gfs2_glock_hold(gl);
-		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
-			gfs2_glock_put_nolock(gl);
+		gl->gl_lockref.count++;
+		if (!gfs2_queue_try_to_evict(gl))
+			gl->gl_lockref.count--;
 	}
 }
 
@@ -530,33 +646,33 @@ const struct gfs2_glock_operations gfs2_meta_glops = {
 const struct gfs2_glock_operations gfs2_inode_glops = {
 	.go_sync = inode_go_sync,
 	.go_inval = inode_go_inval,
-	.go_demote_ok = inode_go_demote_ok,
-	.go_lock = inode_go_lock,
+	.go_instantiate = inode_go_instantiate,
+	.go_held = inode_go_held,
 	.go_dump = inode_go_dump,
 	.go_type = LM_TYPE_INODE,
-	.go_flags = GLOF_ASPACE,
+	.go_flags = GLOF_ASPACE | GLOF_LVB,
 };
 
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_sync = rgrp_go_sync,
 	.go_inval = rgrp_go_inval,
-	.go_lock = gfs2_rgrp_go_lock,
-	.go_unlock = gfs2_rgrp_go_unlock,
-	.go_dump = gfs2_rgrp_dump,
+	.go_instantiate = gfs2_rgrp_go_instantiate,
+	.go_dump = gfs2_rgrp_go_dump,
 	.go_type = LM_TYPE_RGRP,
-	.go_flags = GLOF_ASPACE | GLOF_LVB,
+	.go_flags = GLOF_LVB,
 };
 
-const struct gfs2_glock_operations gfs2_trans_glops = {
-	.go_sync = 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_xmote_bh = freeze_go_xmote_bh,
+	.go_callback = freeze_go_callback,
 	.go_type = LM_TYPE_NONDISK,
 };
 
 const struct gfs2_glock_operations gfs2_iopen_glops = {
 	.go_type = LM_TYPE_IOPEN,
 	.go_callback = iopen_go_callback,
+	.go_dump = inode_go_dump,
+	.go_subclass = 1,
 };
 
 const struct gfs2_glock_operations gfs2_flock_glops = {