Merge tag 'gfs2-4.19.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull gfs2 updates from Andreas Gruenbacher:

 - iomap support for buffered writes and for direct I/O

 - two patches that reduce the size of struct gfs2_inode

 - lots of fixes and cleanups

* tag 'gfs2-4.19.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2: (25 commits)
  gfs2: eliminate update_rgrp_lvb_unlinked
  gfs2: Fix gfs2_testbit to use clone bitmaps
  gfs2: Get rid of gfs2_ea_strlen
  gfs2: cleanup: call gfs2_rgrp_ondisk2lvb from gfs2_rgrp_out
  gfs2: Special-case rindex for gfs2_grow
  GFS2: rgrp free blocks used incorrectly
  gfs2: remove redundant variable 'moved'
  gfs2: use iomap_readpage for blocksize == PAGE_SIZE
  gfs2: Use iomap for stuffed direct I/O reads
  gfs2: fallocate_chunk: Always initialize struct iomap
  GFS2: Fix recovery issues for spectators
  fs: gfs2: Adding new return type vm_fault_t
  gfs2: using posix_acl_xattr_size instead of posix_acl_to_xattr
  gfs2: Don't reject a supposedly full bitmap if we have blocks reserved
  gfs2: Eliminate redundant ip->i_rgd
  gfs2: Stop messing with ip->i_rgd in the rlist code
  gfs2: Remove gfs2_write_{begin,end}
  gfs2: iomap direct I/O support
  gfs2: gfs2_extent_length cleanup
  gfs2: iomap buffered write support
  ...

fs/gfs2/acl.c

@@ -82,14 +82,12 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
 int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	int error;
-	int len;
+	size_t len;
 	char *data;
 	const char *name = gfs2_acl_name(type);
 
 	if (acl) {
-		len = posix_acl_to_xattr(&init_user_ns, acl, NULL, 0);
-		if (len == 0)
-			return 0;
+		len = posix_acl_xattr_size(acl->a_count);
 		data = kmalloc(len, GFP_NOFS);
 		if (data == NULL)
 			return -ENOMEM;

fs/gfs2/aops.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Red Hat, Inc.  All rights reserved.
+ */
+
+#ifndef __AOPS_DOT_H__
+#define __AOPS_DOT_H__
+
+#include "incore.h"
+
+extern int stuffed_readpage(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+				  loff_t pos, unsigned copied,
+				  struct page *page);
+extern void adjust_fs_space(struct inode *inode);
+extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int len);
+
+#endif /* __AOPS_DOT_H__ */

fs/gfs2/dir.c

@@ -1011,7 +1011,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 	u64 bn, leaf_no;
 	__be64 *lp;
 	u32 index;
-	int x, moved = 0;
+	int x;
 	int error;
 
 	index = name->hash >> (32 - dip->i_depth);
@@ -1113,8 +1113,6 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 			if (!prev)
 				prev = dent;
-
-			moved = 1;
 		} else {
 			prev = dent;
 		}

fs/gfs2/file.c

@@ -26,10 +26,12 @@
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
 #include <linux/delay.h>
+#include <linux/backing-dev.h>
 
 #include "gfs2.h"
 #include "incore.h"
 #include "bmap.h"
+#include "aops.h"
 #include "dir.h"
 #include "glock.h"
 #include "glops.h"
@@ -387,7 +389,7 @@ static int gfs2_allocate_page_backing(struct page *page)
  * blocks allocated on disk to back that page.
  */
 
-static int gfs2_page_mkwrite(struct vm_fault *vmf)
+static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -688,12 +690,83 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 	return ret ? ret : ret1;
 }
 
+static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	size_t count = iov_iter_count(to);
+	struct gfs2_holder gh;
+	ssize_t ret;
+
+	if (!count)
+		return 0; /* skip atime */
+
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out_uninit;
+
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL);
+
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	size_t len = iov_iter_count(from);
+	loff_t offset = iocb->ki_pos;
+	struct gfs2_holder gh;
+	ssize_t ret;
+
+	/*
+	 * Deferred lock, even if its a write, since we do no allocation on
+	 * this path. All we need to change is the atime, and this lock mode
+	 * ensures that other nodes have flushed their buffered read caches
+	 * (i.e. their page cache entries for this inode). We do not,
+	 * unfortunately, have the option of only flushing a range like the
+	 * VFS does.
+	 */
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out_uninit;
+
+	/* Silently fall back to buffered I/O when writing beyond EOF */
+	if (offset + len > i_size_read(&ip->i_inode))
+		goto out;
+
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL);
+
+out:
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ret = gfs2_file_direct_read(iocb, to);
+		if (likely(ret != -ENOTBLK))
+			return ret;
+		iocb->ki_flags &= ~IOCB_DIRECT;
+	}
+	return generic_file_read_iter(iocb, to);
+}
+
 /**
  * gfs2_file_write_iter - Perform a write to a file
  * @iocb: The io context
- * @iov: The data to write
- * @nr_segs: Number of @iov segments
- * @pos: The file position
+ * @from: The data to write
  *
  * We have to do a lock/unlock here to refresh the inode size for
  * O_APPEND writes, otherwise we can land up writing at the wrong
@@ -705,8 +778,9 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct gfs2_inode *ip = GFS2_I(file_inode(file));
-	int ret;
+	struct inode *inode = file_inode(file);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	ssize_t written = 0, ret;
 
 	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
@@ -723,7 +797,71 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		gfs2_glock_dq_uninit(&gh);
 	}
 
-	return generic_file_write_iter(iocb, from);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = inode_to_bdi(inode);
+
+	ret = file_remove_privs(file);
+	if (ret)
+		goto out2;
+
+	ret = file_update_time(file);
+	if (ret)
+		goto out2;
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		struct address_space *mapping = file->f_mapping;
+		loff_t pos, endbyte;
+		ssize_t buffered;
+
+		written = gfs2_file_direct_write(iocb, from);
+		if (written < 0 || !iov_iter_count(from))
+			goto out2;
+
+		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+		if (unlikely(ret < 0))
+			goto out2;
+		buffered = ret;
+
+		/*
+		 * We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		pos = iocb->ki_pos;
+		endbyte = pos + buffered - 1;
+		ret = filemap_write_and_wait_range(mapping, pos, endbyte);
+		if (!ret) {
+			iocb->ki_pos += buffered;
+			written += buffered;
+			invalidate_mapping_pages(mapping,
+						 pos >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
+	} else {
+		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+		if (likely(ret > 0))
+			iocb->ki_pos += ret;
+	}
+
+out2:
+	current->backing_dev_info = NULL;
+out:
+	inode_unlock(inode);
+	if (likely(ret > 0)) {
+		/* Handle various SYNC-type writes */
+		ret = generic_write_sync(iocb, ret);
+	}
+	return written ? written : ret;
 }
 
 static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
@@ -733,7 +871,6 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	loff_t end = offset + len;
 	struct buffer_head *dibh;
-	struct iomap iomap = { };
 	int error;
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
@@ -749,12 +886,14 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	}
 
 	while (offset < end) {
+		struct iomap iomap = { };
+
 		error = gfs2_iomap_get_alloc(inode, offset, end - offset,
 					     &iomap);
 		if (error)
 			goto out;
 		offset = iomap.offset + iomap.length;
-		if (iomap.type != IOMAP_HOLE)
+		if (!(iomap.flags & IOMAP_F_NEW))
 			continue;
 		error = sb_issue_zeroout(sb, iomap.addr >> inode->i_blkbits,
 					 iomap.length >> inode->i_blkbits,
@@ -1125,7 +1264,7 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 
 const struct file_operations gfs2_file_fops = {
 	.llseek		= gfs2_llseek,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= gfs2_file_read_iter,
 	.write_iter	= gfs2_file_write_iter,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
@@ -1155,7 +1294,7 @@ const struct file_operations gfs2_dir_fops = {
 
 const struct file_operations gfs2_file_fops_nolock = {
 	.llseek		= gfs2_llseek,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= gfs2_file_read_iter,
 	.write_iter	= gfs2_file_write_iter,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,

fs/gfs2/incore.h

@@ -65,6 +65,27 @@ struct gfs2_log_operations {
 
 #define GBF_FULL 1
 
+/**
+ * Clone bitmaps (bi_clone):
+ *
+ * - When a block is freed, we remember the previous state of the block in the
+ *   clone bitmap, and only mark the block as free in the real bitmap.
+ *
+ * - When looking for a block to allocate, we check for a free block in the
+ *   clone bitmap, and if no clone bitmap exists, in the real bitmap.
+ *
+ * - For allocating a block, we mark it as allocated in the real bitmap, and if
+ *   a clone bitmap exists, also in the clone bitmap.
+ *
+ * - At the end of a log_flush, we copy the real bitmap into the clone bitmap
+ *   to make the clone bitmap reflect the current allocation state.
+ *   (Alternatively, we could remove the clone bitmap.)
+ *
+ * The clone bitmaps are in-core only, and is never written to disk.
+ *
+ * These steps ensure that blocks which have been freed in a transaction cannot
+ * be reallocated in that same transaction.
+ */
 struct gfs2_bitmap {
 	struct buffer_head *bi_bh;
 	char *bi_clone;
@@ -295,7 +316,6 @@ struct gfs2_blkreserv {
 	struct rb_node rs_node;       /* link to other block reservations */
 	struct gfs2_rbm rs_rbm;       /* Start of reservation */
 	u32 rs_free;                  /* how many blocks are still free */
-	u64 rs_inum;                  /* Inode number for reservation */
 };
 
 /*
@@ -398,7 +418,6 @@ struct gfs2_inode {
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_qadata *i_qadata; /* quota allocation data */
 	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */
-	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
 	struct list_head i_ordered;

fs/gfs2/lock_dlm.c

@@ -821,6 +821,13 @@ static int control_mount(struct gfs2_sbd *sdp)
 		goto fail;
 	}
 
+	/**
+	 * If we're a spectator, we don't want to take the lock in EX because
+	 * we cannot do the first-mount responsibility it implies: recovery.
+	 */
+	if (sdp->sd_args.ar_spectator)
+		goto locks_done;
+
 	error = mounted_lock(sdp, DLM_LOCK_EX, DLM_LKF_CONVERT|DLM_LKF_NOQUEUE);
 	if (!error) {
 		mounted_mode = DLM_LOCK_EX;
@@ -896,9 +903,16 @@ static int control_mount(struct gfs2_sbd *sdp)
 	if (lvb_gen < mount_gen) {
 		/* wait for mounted nodes to update control_lock lvb to our
 		   generation, which might include new recovery bits set */
-		fs_info(sdp, "control_mount wait1 block %u start %u mount %u "
-			"lvb %u flags %lx\n", block_gen, start_gen, mount_gen,
-			lvb_gen, ls->ls_recover_flags);
+		if (sdp->sd_args.ar_spectator) {
+			fs_info(sdp, "Recovery is required. Waiting for a "
+				"non-spectator to mount.\n");
+			msleep_interruptible(1000);
+		} else {
+			fs_info(sdp, "control_mount wait1 block %u start %u "
+				"mount %u lvb %u flags %lx\n", block_gen,
+				start_gen, mount_gen, lvb_gen,
+				ls->ls_recover_flags);
+		}
 		spin_unlock(&ls->ls_recover_spin);
 		goto restart;
 	}

fs/gfs2/log.c

@@ -92,7 +92,8 @@ static void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
 
 static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
 			       struct writeback_control *wbc,
-			       struct gfs2_trans *tr)
+			       struct gfs2_trans *tr,
+			       bool *withdraw)
 __releases(&sdp->sd_ail_lock)
 __acquires(&sdp->sd_ail_lock)
 {
@@ -107,8 +108,10 @@ __acquires(&sdp->sd_ail_lock)
 		gfs2_assert(sdp, bd->bd_tr == tr);
 
 		if (!buffer_busy(bh)) {
-			if (!buffer_uptodate(bh))
+			if (!buffer_uptodate(bh)) {
 				gfs2_io_error_bh(sdp, bh);
+				*withdraw = true;
+			}
 			list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 			continue;
 		}
@@ -148,6 +151,7 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 	struct list_head *head = &sdp->sd_ail1_list;
 	struct gfs2_trans *tr;
 	struct blk_plug plug;
+	bool withdraw = false;
 
 	trace_gfs2_ail_flush(sdp, wbc, 1);
 	blk_start_plug(&plug);
@@ -156,11 +160,13 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 	list_for_each_entry_reverse(tr, head, tr_list) {
 		if (wbc->nr_to_write <= 0)
 			break;
-		if (gfs2_ail1_start_one(sdp, wbc, tr))
+		if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw))
 			goto restart;
 	}
 	spin_unlock(&sdp->sd_ail_lock);
 	blk_finish_plug(&plug);
+	if (withdraw)
+		gfs2_lm_withdraw(sdp, NULL);
 	trace_gfs2_ail_flush(sdp, wbc, 0);
 }
 
@@ -188,7 +194,8 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
  *
  */
 
-static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+				bool *withdraw)
 {
 	struct gfs2_bufdata *bd, *s;
 	struct buffer_head *bh;
@@ -199,11 +206,12 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 		gfs2_assert(sdp, bd->bd_tr == tr);
 		if (buffer_busy(bh))
 			continue;
-		if (!buffer_uptodate(bh))
+		if (!buffer_uptodate(bh)) {
 			gfs2_io_error_bh(sdp, bh);
+			*withdraw = true;
+		}
 		list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 	}
-
 }
 
 /**
@@ -218,10 +226,11 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 	struct gfs2_trans *tr, *s;
 	int oldest_tr = 1;
 	int ret;
+	bool withdraw = false;
 
 	spin_lock(&sdp->sd_ail_lock);
 	list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
-		gfs2_ail1_empty_one(sdp, tr);
+		gfs2_ail1_empty_one(sdp, tr, &withdraw);
 		if (list_empty(&tr->tr_ail1_list) && oldest_tr)
 			list_move(&tr->tr_list, &sdp->sd_ail2_list);
 		else
@@ -230,6 +239,9 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 	ret = list_empty(&sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
 
+	if (withdraw)
+		gfs2_lm_withdraw(sdp, "fatal: I/O error(s)\n");
+
 	return ret;
 }
 
@@ -689,7 +701,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 	hash = ~crc32(~0, lh, LH_V1_SIZE);
 	lh->lh_hash = cpu_to_be32(hash);
 
-	tv = current_kernel_time64();
+	ktime_get_coarse_real_ts64(&tv);
 	lh->lh_nsec = cpu_to_be32(tv.tv_nsec);
 	lh->lh_sec = cpu_to_be64(tv.tv_sec);
 	addr = gfs2_log_bmap(sdp);

fs/gfs2/lops.c

@@ -49,7 +49,7 @@ void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	if (test_set_buffer_pinned(bh))
 		gfs2_assert_withdraw(sdp, 0);
 	if (!buffer_uptodate(bh))
-		gfs2_io_error_bh(sdp, bh);
+		gfs2_io_error_bh_wd(sdp, bh);
 	bd = bh->b_private;
 	/* If this buffer is in the AIL and it has already been written
 	 * to in-place disk block, remove it from the AIL.

fs/gfs2/meta_io.c

@@ -293,7 +293,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
 		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
-			gfs2_io_error_bh(sdp, bh);
+			gfs2_io_error_bh_wd(sdp, bh);
 		brelse(bh);
 		*bhp = NULL;
 		return -EIO;
@@ -320,7 +320,7 @@ 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 && test_bit(TR_TOUCHED, &tr->tr_flags))
-			gfs2_io_error_bh(sdp, bh);
+			gfs2_io_error_bh_wd(sdp, bh);
 		return -EIO;
 	}
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))

fs/gfs2/recovery.c

@@ -413,12 +413,13 @@ void gfs2_recover_func(struct work_struct *work)
 	ktime_t t_start, t_jlck, t_jhd, t_tlck, t_rep;
 	int ro = 0;
 	unsigned int pass;
-	int error;
+	int error = 0;
 	int jlocked = 0;
 
 	t_start = ktime_get();
-	if (sdp->sd_args.ar_spectator ||
-	    (jd->jd_jid != sdp->sd_lockstruct.ls_jid)) {
+	if (sdp->sd_args.ar_spectator)
+		goto fail;
+	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
 		fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
 			jd->jd_jid);
 		jlocked = 1;

fs/gfs2/super.c

@@ -1729,7 +1729,6 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (ip) {
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
-		ip->i_rgd = NULL;
 		memset(&ip->i_res, 0, sizeof(ip->i_res));
 		RB_CLEAR_NODE(&ip->i_res.rs_node);
 		ip->i_rahead = 0;

fs/gfs2/sys.c

@@ -429,11 +429,18 @@ int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid)
 
 	spin_lock(&sdp->sd_jindex_spin);
 	rv = -EBUSY;
-	if (sdp->sd_jdesc->jd_jid == jid)
+	/**
+	 * If we're a spectator, we use journal0, but it's not really ours.
+	 * So we need to wait for its recovery too. If we skip it we'd never
+	 * queue work to the recovery workqueue, and so its completion would
+	 * never clear the DFL_BLOCK_LOCKS flag, so all our locks would
+	 * permanently stop working.
+	 */
+	if (sdp->sd_jdesc->jd_jid == jid && !sdp->sd_args.ar_spectator)
 		goto out;
 	rv = -ENOENT;
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
-		if (jd->jd_jid != jid)
+		if (jd->jd_jid != jid && !sdp->sd_args.ar_spectator)
 			continue;
 		rv = gfs2_recover_journal(jd, false);
 		break;

fs/gfs2/trace_gfs2.h

@@ -606,7 +606,8 @@ TRACE_EVENT(gfs2_rs,
 		__entry->rd_addr	= rs->rs_rbm.rgd->rd_addr;
 		__entry->rd_free_clone	= rs->rs_rbm.rgd->rd_free_clone;
 		__entry->rd_reserved	= rs->rs_rbm.rgd->rd_reserved;
-		__entry->inum		= rs->rs_inum;
+		__entry->inum		= container_of(rs, struct gfs2_inode,
+						       i_res)->i_no_addr;
 		__entry->start		= gfs2_rbm_to_block(&rs->rs_rbm);
 		__entry->free		= rs->rs_free;
 		__entry->func		= func;

fs/gfs2/trans.h

@@ -30,9 +30,11 @@ struct gfs2_glock;
  * block, or all of the blocks in the rg, whichever is smaller */
 static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip, unsigned requested)
 {
-	if (requested < ip->i_rgd->rd_length)
+	struct gfs2_rgrpd *rgd = ip->i_res.rs_rbm.rgd;
+
+	if (requested < rgd->rd_length)
 		return requested + 1;
-	return ip->i_rgd->rd_length;
+	return rgd->rd_length;
 }
 
 extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,

fs/gfs2/util.c

@@ -46,6 +46,7 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 	    test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
 		return 0;
 
+	if (fmt) {
 		va_start(args, fmt);
 
 		vaf.fmt = fmt;
@@ -54,6 +55,7 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 		fs_err(sdp, "%pV", &vaf);
 
 		va_end(args);
+	}
 
 	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
 		fs_err(sdp, "about to withdraw this file system\n");
@@ -246,21 +248,21 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
 }
 
 /**
- * gfs2_io_error_bh_i - Flag a buffer I/O error and withdraw
- * Returns: -1 if this call withdrew the machine,
- *          0 if it was already withdrawn
+ * gfs2_io_error_bh_i - Flag a buffer I/O error
+ * @withdraw: withdraw the filesystem
  */
 
-int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
-		       const char *function, char *file, unsigned int line)
+void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			const char *function, char *file, unsigned int line,
+			bool withdraw)
 {
-	int rv;
-	rv = gfs2_lm_withdraw(sdp,
+	fs_err(sdp,
 	       "fatal: I/O error\n"
 	       "  block = %llu\n"
 	       "  function = %s, file = %s, line = %u\n",
 	       (unsigned long long)bh->b_blocknr,
 	       function, file, line);
-	return rv;
+	if (withdraw)
+		gfs2_lm_withdraw(sdp, NULL);
 }
 

fs/gfs2/util.h

@@ -136,11 +136,15 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
 gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__);
 
 
-int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
-		       const char *function, char *file, unsigned int line);
+void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			const char *function, char *file, unsigned int line,
+			bool withdraw);
+
+#define gfs2_io_error_bh_wd(sdp, bh) \
+gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, true);
 
 #define gfs2_io_error_bh(sdp, bh) \
-gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__);
+gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, false);
 
 
 extern struct kmem_cache *gfs2_glock_cachep;

fs/gfs2/xattr.c

@@ -343,39 +343,19 @@ struct ea_list {
 	unsigned int ei_size;
 };
 
-static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
-{
-	switch (ea->ea_type) {
-	case GFS2_EATYPE_USR:
-		return 5 + ea->ea_name_len + 1;
-	case GFS2_EATYPE_SYS:
-		return 7 + ea->ea_name_len + 1;
-	case GFS2_EATYPE_SECURITY:
-		return 9 + ea->ea_name_len + 1;
-	default:
-		return 0;
-	}
-}
-
 static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh,
 		     struct gfs2_ea_header *ea, struct gfs2_ea_header *prev,
 		     void *private)
 {
 	struct ea_list *ei = private;
 	struct gfs2_ea_request *er = ei->ei_er;
-	unsigned int ea_size = gfs2_ea_strlen(ea);
+	unsigned int ea_size;
+	char *prefix;
+	unsigned int l;
 
 	if (ea->ea_type == GFS2_EATYPE_UNUSED)
 		return 0;
 
-	if (er->er_data_len) {
-		char *prefix = NULL;
-		unsigned int l = 0;
-		char c = 0;
-
-		if (ei->ei_size + ea_size > er->er_data_len)
-			return -ERANGE;
-
 	switch (ea->ea_type) {
 	case GFS2_EATYPE_USR:
 		prefix = "user.";
@@ -389,14 +369,19 @@ static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh,
 		prefix = "security.";
 		l = 9;
 		break;
+	default:
+		BUG();
 	}
 
-		BUG_ON(l == 0);
+	ea_size = l + ea->ea_name_len + 1;
+	if (er->er_data_len) {
+		if (ei->ei_size + ea_size > er->er_data_len)
+			return -ERANGE;
 
 		memcpy(er->er_data + ei->ei_size, prefix, l);
 		memcpy(er->er_data + ei->ei_size + l, GFS2_EA2NAME(ea),
 		       ea->ea_name_len);
-		memcpy(er->er_data + ei->ei_size + ea_size - 1, &c, 1);
+		er->er_data[ei->ei_size + ea_size - 1] = 0;
 	}
 
 	ei->ei_size += ea_size;