[GFS2] Make journaled data files identical to normal files on disk

This is a very large patch, with a few still to be resolved issues
so you might want to check out the previous head of the tree since
this is known to be unstable. Fixes for the various bugs will be
forthcoming shortly.

This patch removes the special data format which has been used
up till now for journaled data files. Directories still retain the
old format so that they will remain on disk compatible with earlier
releases. As a result you can now do the following with journaled
data files:

 1) mmap them
 2) export them over NFS
 3) convert to/from normal files whenever you want to (the zero length
    restriction is gone)

In addition the level at which GFS' locking is done has changed for all
files (since they all now use the page cache) such that the locking is
done at the page cache level rather than the level of the fs operations.
This should mean that things like loopback mounts and other things which
touch the page cache directly should now work.

Current known issues:

 1. There is a lock mode inversion problem related to the resource
    group hold function which needs to be resolved.
 2. Any significant amount of I/O causes an oops with an offset of hex 320
    (NULL pointer dereference) which appears to be related to a journaled data
    buffer appearing on a list where it shouldn't be.
 3. Direct I/O writes are disabled for the time being (will reappear later)
 4. There is probably a deadlock between the page lock and GFS' locks under
    certain combinations of mmap and fs operation I/O.
 5. Issue relating to ref counting on internally used inodes causes a hang
    on umount (discovered before this patch, and not fixed by it)
 6. One part of the directory metadata is different from GFS1 and will need
    to be resolved before next release.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

1 files changed, 81 insertions, 33 deletions

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 69e8f4e92e5..138fdf559a9 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -43,20 +43,22 @@
 #include <linux/buffer_head.h>
 #include <linux/tty.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 #include <asm/semaphore.h>
 
 #include "gfs2.h"
 #include "bmap.h"
 #include "glock.h"
 #include "glops.h"
-#include "jdata.h"
 #include "log.h"
 #include "meta_io.h"
 #include "quota.h"
 #include "rgrp.h"
 #include "super.h"
 #include "trans.h"
+#include "inode.h"
 #include "ops_file.h"
+#include "ops_address.h"
 
 #define QUOTA_USER 1
 #define QUOTA_GROUP 0
@@ -561,6 +563,81 @@ static void do_qc(struct gfs2_quota_data *qd, int64_t change)
 	up(&sdp->sd_quota_mutex);
 }
 
+/**
+ * gfs2_adjust_quota
+ *
+ * This function was mostly borrowed from gfs2_block_truncate_page which was
+ * in turn mostly borrowed from ext3
+ */
+static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
+			     int64_t change, struct gfs2_quota_data *qd)
+{
+	struct inode *inode = gfs2_ip2v(ip);
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long index = loc >> PAGE_CACHE_SHIFT;
+	unsigned offset = loc & (PAGE_CACHE_SHIFT - 1);
+	unsigned blocksize, iblock, pos;
+	struct buffer_head *bh;
+	struct page *page;
+	void *kaddr;
+	__be64 *ptr;
+	u64 value;
+	int err = -EIO;
+
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return -ENOMEM;
+
+	blocksize = inode->i_sb->s_blocksize;
+	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
+
+	bh = page_buffers(page);
+	pos = blocksize;
+	while (offset >= pos) {
+		bh = bh->b_this_page;
+		iblock++;
+		pos += blocksize;
+	}
+
+	if (!buffer_mapped(bh)) {
+		gfs2_get_block(inode, iblock, bh, 1);
+		if (!buffer_mapped(bh))
+			goto unlock;
+	}
+
+	if (PageUptodate(page))
+		set_buffer_uptodate(bh);
+
+	if (!buffer_uptodate(bh)) {
+		ll_rw_block(READ, 1, &bh);
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh))
+			goto unlock;
+	}
+
+	gfs2_trans_add_bh(ip->i_gl, bh, 0);
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	ptr = (__be64 *)(kaddr + offset);
+	value = *ptr = cpu_to_be64(be64_to_cpu(*ptr) + change);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr, KM_USER0);
+	err = 0;
+	qd->qd_qb.qb_magic = cpu_to_be32(GFS2_MAGIC);
+#if 0
+	qd->qd_qb.qb_limit = cpu_to_be64(q.qu_limit);
+	qd->qd_qb.qb_warn = cpu_to_be64(q.qu_warn);
+#endif
+	qd->qd_qb.qb_value = cpu_to_be64(value);
+unlock:
+	unlock_page(page);
+	page_cache_release(page);
+	return err;
+}
+
 static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 {
 	struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_sbd;
@@ -635,43 +712,14 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 
 	file_ra_state_init(&ra_state, ip->i_vnode->i_mapping);
 	for (x = 0; x < num_qd; x++) {
-		char buf[sizeof(struct gfs2_quota)];
-		struct gfs2_quota q;
-
 		qd = qda[x];
 		offset = qd2offset(qd);
-
-		/* The quota file may not be a multiple of
-		   sizeof(struct gfs2_quota) bytes. */
-		memset(buf, 0, sizeof(struct gfs2_quota));
-
-		error = gfs2_internal_read(ip, &ra_state, buf, &offset,
-					    sizeof(struct gfs2_quota));
-		if (error < 0)
+		error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync,
+					  (struct gfs2_quota_data *)qd->qd_gl->gl_lvb);
+		if (error)
 			goto out_end_trans;
 
-		gfs2_quota_in(&q, buf);
-		q.qu_value += qda[x]->qd_change_sync;
-		gfs2_quota_out(&q, buf);
-
-		error = gfs2_jdata_write_mem(ip, buf, offset,
-					     sizeof(struct gfs2_quota));
-		if (error < 0)
-			goto out_end_trans;
-		else if (error != sizeof(struct gfs2_quota)) {
-			error = -EIO;
-			goto out_end_trans;
-		}
-
 		do_qc(qd, -qd->qd_change_sync);
-
-		memset(&qd->qd_qb, 0, sizeof(struct gfs2_quota_lvb));
-		qd->qd_qb.qb_magic = GFS2_MAGIC;
-		qd->qd_qb.qb_limit = q.qu_limit;
-		qd->qd_qb.qb_warn = q.qu_warn;
-		qd->qd_qb.qb_value = q.qu_value;
-
-		gfs2_quota_lvb_out(&qd->qd_qb, qd->qd_gl->gl_lvb);
 	}
 
 	error = 0;