Skip to contentSkip to conversation

xfs: don't assert fail on bad inode numbers

PATCH Superseded Dave Chinner 3 participants 56 messages Sep 30, 2013 – Oct 22, 2013 1 message not in the archive

v1 of 5 Superseded Latest is v5 →

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

PATCH 1/32 xfsprogs: fix automatic dependency generation

From: Dave Chinner <[email protected]>

Adding are removing a header file does not result in dependency regeneration like it should. make clean will rebuild the dependencies, but a normal make won't. Fix it.

---
 include/buildrules | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)
include/buildrules +16 -4
index 49cb2a4..edb1beb 100644
@@ -79,18 +79,30 @@ endif # _BUILDRULES_INCLUDED_
 $(_FORCE):
 
 # dependency build is automatic, relies on gcc -MM to generate.
+#
+# This is a bit messy. It regenerates the depenencies on each build so
+# that we catch files being added and removed. There are other ways of doing
+# this (e.g. per-file dependency files) but that requires more in-depth changes
+# to the build system. Compile time is not an issue for us, so the
+# rebuild on every make invocation isn't a problem we need to care about. Just
+# do it silently so it doesn't make the build unnecessarily noisy.
+
 .PHONY : depend ltdepend install-qa
 
 MAKEDEP := $(MAKEDEPEND) $(CFLAGS)
 
-ltdepend: .ltdep
+ltdepend: rmltdep .ltdep
+
+rmltdep:
+	@rm -f .ltdep
 
 .ltdep: $(CFILES) $(HFILES)
-	@echo "    [LTDEP]"
 	$(Q)$(MAKEDEP) $(CFILES) | $(SED) -e 's,^\([^:]*\)\.o,\1.lo,' > .ltdep
 
-depend: .dep
+depend: rmdep .dep
+
+rmdep:
+	@rm -f .dep
 
 .dep: $(CFILES) $(HFILES)
-	@echo "    [DEP]"
 	$(Q)$(MAKEDEP) $(CFILES) > .dep
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 1/32
#2 lore raw

Re: [PATCH 01/32] xfsprogs: fix automatic dependency generation

Quoted 3 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Adding are removing a header file does not result in dependency

s/are/or/

Quoted 13 lines

regeneration like it should. make clean will rebuild the dependencies, but a normal make won't. Fix it.

---
 include/buildrules | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)
include/buildrules +0 -0
index 49cb2a4..edb1beb 100644

include/buildrules endif # _BUILDRULES_INCLUDED_ · line 83

Quoted 5 lines
include/buildrules +2 -0
@@ -79,18 +79,30 @@ endif # _BUILDRULES_INCLUDED_
 $(_FORCE):
 
 # dependency build is automatic, relies on gcc -MM to generate.
+#
+# This is a bit messy. It regenerates the depenencies on each build so

dependencies

I'm no make guru but seems relatively harmless. ;)

Quoted 20 lines
include/buildrules +10 -2
+# that we catch files being added and removed. There are other ways of doing
+# this (e.g. per-file dependency files) but that requires more in-depth changes
+# to the build system. Compile time is not an issue for us, so the
+# rebuild on every make invocation isn't a problem we need to care about. Just
+# do it silently so it doesn't make the build unnecessarily noisy.
+
 .PHONY : depend ltdepend install-qa
 
 MAKEDEP := $(MAKEDEPEND) $(CFLAGS)
 
-ltdepend: .ltdep
+ltdepend: rmltdep .ltdep
+
+rmltdep:
+	@rm -f .ltdep
 
 .ltdep: $(CFILES) $(HFILES)
-	@echo "    [LTDEP]"
 	$(Q)$(MAKEDEP) $(CFILES) | $(SED) -e 's,^\([^:]*\)\.o,\1.lo,' > .ltdep

include/buildrules endif # _BUILDRULES_INCLUDED_ · line 108

Quoted 10 lines
include/buildrules +4 -2
 
-depend: .dep
+depend: rmdep .dep
+
+rmdep:
+	@rm -f .dep
 
 .dep: $(CFILES) $(HFILES)
-	@echo "    [DEP]"
 	$(Q)$(MAKEDEP) $(CFILES) > .dep

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#3 lore raw

PATCH 2/32 libxfs: fix missing filetype updates to xfs_dir2.c

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

They were missed in the original patch that was committed.

---
 libxfs/xfs_dir2.c | 3 +++
 1 file changed, 3 insertions(+)
libxfs/xfs_dir2.c +3 -0
index 010c701..96a3c1d 100644
@@ -194,6 +194,7 @@ xfs_dir_createname(
 	memset(&args, 0, sizeof(xfs_da_args_t));
 	args.name = name->name;
 	args.namelen = name->len;
+	args.filetype = name->type;
 	args.hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args.inumber = inum;
 	args.dp = dp;
@@ -268,6 +269,7 @@ xfs_dir_lookup(
 	memset(&args, 0, sizeof(xfs_da_args_t));
 	args.name = name->name;
 	args.namelen = name->len;
+	args.filetype = name->type;
 	args.hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args.dp = dp;
 	args.whichfork = XFS_DATA_FORK;
@@ -323,6 +325,7 @@ xfs_dir_removename(
 	memset(&args, 0, sizeof(xfs_da_args_t));
 	args.name = name->name;
 	args.namelen = name->len;
+	args.filetype = name->type;
 	args.hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args.inumber = ino;
 	args.dp = dp;
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 2/32
#4 lore raw

Re: [PATCH 02/32] libxfs: fix missing filetype updates to xfs_dir2.c

Quoted 3 lines · Dave Chinner

From: Dave Chinner <[email protected]>

They were missed in the original patch that was committed.

I'm not sure it's required in lookup or remove, at least today nothing looks at it on those paths, does it?

Anyway, matches kernel, at worst the last 2 are harmless:

Quoted 27 lines
---
 libxfs/xfs_dir2.c | 3 +++
 1 file changed, 3 insertions(+)
libxfs/xfs_dir2.c +2 -0
index 010c701..96a3c1d 100644
@@ -194,6 +194,7 @@ xfs_dir_createname(
 	memset(&args, 0, sizeof(xfs_da_args_t));
 	args.name = name->name;
 	args.namelen = name->len;
+	args.filetype = name->type;
 	args.hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args.inumber = inum;
 	args.dp = dp;
@@ -268,6 +269,7 @@ xfs_dir_lookup(
 	memset(&args, 0, sizeof(xfs_da_args_t));
 	args.name = name->name;
 	args.namelen = name->len;
+	args.filetype = name->type;
 	args.hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args.dp = dp;
 	args.whichfork = XFS_DATA_FORK;

libxfs/xfs_dir2.c xfs_dir_removename( · line 331

Quoted 7 lines
libxfs/xfs_dir2.c +1 -0
@@ -323,6 +325,7 @@ xfs_dir_removename(
 	memset(&args, 0, sizeof(xfs_da_args_t));
 	args.name = name->name;
 	args.namelen = name->len;
+	args.filetype = name->type;
 	args.hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args.inumber = ino;
 	args.dp = dp;

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#5 lore raw

Re: [PATCH 02/32] libxfs: fix missing filetype updates to xfs_dir2.c

Quoted 7 lines · Eric Sandeen
Quoted 3 lines · Dave Chinner

From: Dave Chinner <[email protected]>

They were missed in the original patch that was committed.

I'm not sure it's required in lookup or remove, at least today nothing looks at it on those paths, does it?

Correct, but...

Quoted 1 line

Anyway, matches kernel, at worst the last 2 are harmless:

... matching the kernel code is more important at this point.

Quoted 1 line

Thanks,

Dave.

Signature · 7 lines
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#7 lore raw

PATCH 3/32 xfs: fix some minor sparse warnings

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

A couple of simple locking annotations and 0 vs NULL warnings. Nothing that changes any code behaviour, just removes build noise.

---
 libxfs/xfs_bmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
libxfs/xfs_bmap.c +1 -1
index 2d480cc..7336abf 100644
@@ -4415,7 +4415,7 @@ xfs_bmapi_write(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
-	struct xfs_bmalloca	bma = { 0 };	/* args for xfs_bmap_alloc */
+	struct xfs_bmalloca	bma = { NULL };	/* args for xfs_bmap_alloc */
 	xfs_fileoff_t		end;		/* end of mapped file region */
 	int			eof;		/* after the end of extents */
 	int			error;		/* error return */
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#8 lore raw

Re: [PATCH 03/32] xfs: fix some minor sparse warnings

Quoted 4 lines · Dave Chinner

From: Dave Chinner <[email protected]>

A couple of simple locking annotations and 0 vs NULL warnings. Nothing that changes any code behaviour, just removes build noise.

The patch is fine as it is, but it doesn't reflect the commit log.

Is part of it missing?

Quoted 11 lines
---
 libxfs/xfs_bmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
libxfs/xfs_bmap.c +0 -0
index 2d480cc..7336abf 100644

libxfs/xfs_bmap.c xfs_bmapi_write( · line 4421

Quoted 8 lines
libxfs/xfs_bmap.c +1 -1
@@ -4415,7 +4415,7 @@ xfs_bmapi_write(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
-	struct xfs_bmalloca	bma = { 0 };	/* args for xfs_bmap_alloc */
+	struct xfs_bmalloca	bma = { NULL };	/* args for xfs_bmap_alloc */
 	xfs_fileoff_t		end;		/* end of mapped file region */
 	int			eof;		/* after the end of extents */
 	int			error;		/* error return */

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#9 lore raw

Re: [PATCH 03/32] xfs: fix some minor sparse warnings

Quoted 9 lines · Eric Sandeen
Quoted 4 lines · Dave Chinner

From: Dave Chinner <[email protected]>

A couple of simple locking annotations and 0 vs NULL warnings. Nothing that changes any code behaviour, just removes build noise.

The patch is fine as it is, but it doesn't reflect the commit log.

Is part of it missing?

It's trimmed down from the kernel commit to just the bits that are in libxfs. I haven't altered it in any other way, so it's entirely possible the commit message has bits in it that the patch now doesn't.

Cheers,

Dave.

Signature · 7 lines
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#10 lore raw

PATCH 4/32 xfs: check magic numbers in dir3 leaf verifier first

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Calling xfs_dir3_leaf_hdr_from_disk() in a verifier before validating the magic numbers in the buffer results in ASSERT failures due to mismatching magic numbers when a corruption occurs. Seeing as the verifier is supposed to catch the corruption and pass it back to the caller, having the verifier assert fail on error defeats the purpose of detecting the errors in the first place.

Check the magic numbers direct from the buffer before decoding the header.

---
 libxfs/xfs_dir2_leaf.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)
libxfs/xfs_dir2_leaf.c +13 -7
index 7ec2f19..c035c4d 100644
@@ -161,6 +161,11 @@ xfs_dir3_leaf_check_int(
 	return true;
 }
 
+/*
+ * We verify the magic numbers before decoding the leaf header so that on debug
+ * kernels we don't get assertion failures in xfs_dir3_leaf_hdr_from_disk() due
+ * to incorrect magic numbers.
+ */
 static bool
 xfs_dir3_leaf_verify(
 	struct xfs_buf		*bp,
@@ -172,24 +177,25 @@ xfs_dir3_leaf_verify(
 
 	ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
 
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+		__uint16_t		magic3;
 
-		if ((magic == XFS_DIR2_LEAF1_MAGIC &&
-		     leafhdr.magic != XFS_DIR3_LEAF1_MAGIC) ||
-		    (magic == XFS_DIR2_LEAFN_MAGIC &&
-		     leafhdr.magic != XFS_DIR3_LEAFN_MAGIC))
-			return false;
+		magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC
+							 : XFS_DIR3_LEAFN_MAGIC;
 
+		if (leaf3->info.hdr.magic != cpu_to_be16(magic3))
+			return false;
 		if (!uuid_equal(&leaf3->info.uuid, &mp->m_sb.sb_uuid))
 			return false;
 		if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
 			return false;
 	} else {
-		if (leafhdr.magic != magic)
+		if (leaf->hdr.info.magic != cpu_to_be16(magic))
 			return false;
 	}
+
+	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
 	return xfs_dir3_leaf_check_int(mp, &leafhdr, leaf);
 }
 
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 4/32
#11 lore raw

Re: [PATCH 04/32] xfs: check magic numbers in dir3 leaf verifier first

Quoted 11 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Calling xfs_dir3_leaf_hdr_from_disk() in a verifier before validating the magic numbers in the buffer results in ASSERT failures due to mismatching magic numbers when a corruption occurs. Seeing as the verifier is supposed to catch the corruption and pass it back to the caller, having the verifier assert fail on error defeats the purpose of detecting the errors in the first place.

Check the magic numbers direct from the buffer before decoding the header.

Looks good; have you sent this for the kernel yet?

(I thought we wanted changes to hit kernelspace first) :)

Quoted 45 lines
---
 libxfs/xfs_dir2_leaf.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)
libxfs/xfs_dir2_leaf.c +10 -6
index 7ec2f19..c035c4d 100644
@@ -161,6 +161,11 @@ xfs_dir3_leaf_check_int(
 	return true;
 }
 
+/*
+ * We verify the magic numbers before decoding the leaf header so that on debug
+ * kernels we don't get assertion failures in xfs_dir3_leaf_hdr_from_disk() due
+ * to incorrect magic numbers.
+ */
 static bool
 xfs_dir3_leaf_verify(
 	struct xfs_buf		*bp,
@@ -172,24 +177,25 @@ xfs_dir3_leaf_verify(
 
 	ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
 
-	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
+		__uint16_t		magic3;
 
-		if ((magic == XFS_DIR2_LEAF1_MAGIC &&
-		     leafhdr.magic != XFS_DIR3_LEAF1_MAGIC) ||
-		    (magic == XFS_DIR2_LEAFN_MAGIC &&
-		     leafhdr.magic != XFS_DIR3_LEAFN_MAGIC))
-			return false;
+		magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC
+							 : XFS_DIR3_LEAFN_MAGIC;
 
+		if (leaf3->info.hdr.magic != cpu_to_be16(magic3))
+			return false;
 		if (!uuid_equal(&leaf3->info.uuid, &mp->m_sb.sb_uuid))
 			return false;
 		if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
 			return false;

libxfs/xfs_dir2_leaf.c xfs_dir3_leaf_verify( · line 201

Quoted 10 lines
libxfs/xfs_dir2_leaf.c +3 -1
 	} else {
-		if (leafhdr.magic != magic)
+		if (leaf->hdr.info.magic != cpu_to_be16(magic))
 			return false;
 	}
+
+	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
 	return xfs_dir3_leaf_check_int(mp, &leafhdr, leaf);
 }
 

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#12 lore raw

Re: [PATCH 04/32] xfs: check magic numbers in dir3 leaf verifier first

Quoted 10 lines · Eric Sandeen
Quoted 9 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Calling xfs_dir3_leaf_hdr_from_disk() in a verifier before validating the magic numbers in the buffer results in ASSERT failures due to mismatching magic numbers when a corruption occurs. Seeing as the verifier is supposed to catch the corruption and pass it back to the caller, having the verifier assert fail on error defeats the purpose of detecting the errors in the first place.

Quoted 6 lines
Quoted 2 lines

Check the magic numbers direct from the buffer before decoding the header.

Looks good; have you sent this for the kernel yet?

(I thought we wanted changes to hit kernelspace first) :)

Yes, commit 0f295a214bb7658ca37bd61a8a1f0cd4a9d86c1f.

Cheers,

Dave.

Signature · 7 lines
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#13 lore raw

Re: [PATCH 04/32] xfs: check magic numbers in dir3 leaf verifier first

Quoted 11 lines · Dave Chinner
Quoted 10 lines · Eric Sandeen
Quoted 9 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Calling xfs_dir3_leaf_hdr_from_disk() in a verifier before validating the magic numbers in the buffer results in ASSERT failures due to mismatching magic numbers when a corruption occurs. Seeing as the verifier is supposed to catch the corruption and pass it back to the caller, having the verifier assert fail on error defeats the purpose of detecting the errors in the first place.

Quoted 8 lines
Quoted 6 lines
Quoted 2 lines

Check the magic numbers direct from the buffer before decoding the header.

Looks good; have you sent this for the kernel yet?

(I thought we wanted changes to hit kernelspace first) :)

Yes, commit 0f295a214bb7658ca37bd61a8a1f0cd4a9d86c1f.

Sorry I missed that, man, I swear I looked.

-Eric

Quoted 4 lines

Cheers,

Dave.

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#14 lore raw

PATCH 5/32 xfs: ensure we copy buffer type in da btree root splits

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

When splitting the root of the da btree, we shuffled data between buffers and the structures that track them. At one point, we copy data and state from one buffer to another, including the ops associated with the buffer. When we do this, we also need to copy the buffer type associated with the buf log item so that the buffer is logged correctly. If we don't do that, log recovery won't recognise it and hence it won't recalculate the CRC on the buffer after recovery. This leads to a directory block that can't be read after recovery has run.

Found by inspection after finding the same problem with remote symlink buffers.

---
 libxfs/xfs_da_btree.c | 1 +
 1 file changed, 1 insertion(+)
libxfs/xfs_da_btree.c +1 -0
index b7b6705..f106e06 100644
@@ -612,6 +612,7 @@ xfs_da3_root_split(
 	xfs_trans_log_buf(tp, bp, 0, size - 1);
 
 	bp->b_ops = blk1->bp->b_ops;
+	xfs_trans_buf_copy_type(bp, blk1->bp);
 	blk1->bp = bp;
 	blk1->blkno = blkno;
 
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 5/32
#15 lore raw

Re: [PATCH 05/32] xfs: ensure we copy buffer type in da btree root splits

Quoted 12 lines · Dave Chinner

From: Dave Chinner <[email protected]>

When splitting the root of the da btree, we shuffled data between buffers and the structures that track them. At one point, we copy data and state from one buffer to another, including the ops associated with the buffer. When we do this, we also need to copy the buffer type associated with the buf log item so that the buffer is logged correctly. If we don't do that, log recovery won't recognise it and hence it won't recalculate the CRC on the buffer after recovery. This leads to a directory block that can't be read after recovery has run.

Quoted 2 lines

Found by inspection after finding the same problem with remote symlink buffers.

Makes sense, matches kernel commit 0a4edc8f0b54cd5f613e7fda7dc8106cb9869bc9

Quoted 11 lines
---
 libxfs/xfs_da_btree.c | 1 +
 1 file changed, 1 insertion(+)
libxfs/xfs_da_btree.c +0 -0
index b7b6705..f106e06 100644

libxfs/xfs_da_btree.c xfs_da3_root_split( · line 618

Quoted 7 lines
libxfs/xfs_da_btree.c +1 -0
@@ -612,6 +612,7 @@ xfs_da3_root_split(
 	xfs_trans_log_buf(tp, bp, 0, size - 1);
 
 	bp->b_ops = blk1->bp->b_ops;
+	xfs_trans_buf_copy_type(bp, blk1->bp);
 	blk1->bp = bp;
 	blk1->blkno = blkno;
 

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#17 lore raw

PATCH 6/32 xfs: don't assert fail on bad inode numbers

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Let the inode verifier do it's work by returning an error when we fail to find correct magic numbers in an inode buffer.

---
 libxfs/xfs_inode_buf.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)
libxfs/xfs_inode_buf.c +3 -5
index 6205318..b096f77 100644
@@ -39,9 +39,8 @@ xfs_inobp_check(
 					i * mp->m_sb.sb_inodesize);
 		if (!dip->di_next_unlinked)  {
 			xfs_alert(mp,
-	"Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
-				bp);
-			ASSERT(dip->di_next_unlinked);
+	"Detected bogus zero next_unlinked field in inode %d buffer 0x%llx.",
+				i, (long long)bp->b_bn);
 		}
 	}
 }
@@ -74,11 +73,10 @@ xfs_inode_buf_verify(
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
 					     mp, dip);
 #ifdef DEBUG
-			xfs_emerg(mp,
+			xfs_alert(mp,
 				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
 				(unsigned long long)bp->b_bn, i,
 				be16_to_cpu(dip->di_magic));
-			ASSERT(0);
 #endif
 		}
 	}
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 6/32
#18 lore raw
Quoted 4 lines · Dave Chinner

From: Dave Chinner <[email protected]>

Let the inode verifier do it's work by returning an error when we fail to find correct magic numbers in an inode buffer.

Makes sense & matches kernel 74ffa796e127906883cacedcf3871494192c9e42

Quoted 25 lines
---
 libxfs/xfs_inode_buf.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)
libxfs/xfs_inode_buf.c +2 -3
index 6205318..b096f77 100644
@@ -39,9 +39,8 @@ xfs_inobp_check(
 					i * mp->m_sb.sb_inodesize);
 		if (!dip->di_next_unlinked)  {
 			xfs_alert(mp,
-	"Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
-				bp);
-			ASSERT(dip->di_next_unlinked);
+	"Detected bogus zero next_unlinked field in inode %d buffer 0x%llx.",
+				i, (long long)bp->b_bn);
 		}
 	}
 }
@@ -74,11 +73,10 @@ xfs_inode_buf_verify(
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
 					     mp, dip);

libxfs/xfs_inode_buf.c xfs_inode_buf_verify( · line 82

Quoted 10 lines
libxfs/xfs_inode_buf.c +1 -2
 #ifdef DEBUG
-			xfs_emerg(mp,
+			xfs_alert(mp,
 				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
 				(unsigned long long)bp->b_bn, i,
 				be16_to_cpu(dip->di_magic));
-			ASSERT(0);
 #endif
 		}
 	}

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#19 lore raw

PATCH 7/32 xfs: dirent dtype presence is dependent on directory magic numbers

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

The determination of whether a directory entry contains a dtype field originally was dependent on the filesystem having CRCs enabled. This meant that the format for dtype beign enabled could be determined by checking the directory block magic number rather than doing a feature bit check. This was useful in that it meant that we didn't need to pass a struct xfs_mount around to functions that were already supplied with a directory block header.

Unfortunately, the introduction of dtype fields into the v4 structure via a feature bit meant this "use the directory block magic number" method of discriminating the dirent entry sizes is broken. Hence we need to convert the places that use magic number checks to use feature bit checks so that they work correctly and not by chance.

The current code works on v4 filesystems only because the dirent size roundup covers the extra byte needed by the dtype field in the places where this problem occurs.

---
 db/check.c                |  2 +-
 include/xfs_dir2_format.h | 51 +++++++++++++++++++----------------------------
 libxfs/xfs_dir2_block.c   |  6 +++---
 libxfs/xfs_dir2_sf.c      |  6 +++---
 repair/dir2.c             |  4 ++--
 5 files changed, 29 insertions(+), 40 deletions(-)
db/check.c +1 -1
index 2d4718d..4867698 100644
@@ -3434,7 +3434,7 @@ process_sf_dir_v2(
 		dbprintf(_("dir %lld entry . %lld\n"), id->ino, id->ino);
 	(*dot)++;
 	sfe = xfs_dir2_sf_firstentry(sf);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	for (i = sf->count - 1, i8 = 0; i >= 0; i--) {
 		if ((__psint_t)sfe + xfs_dir3_sf_entsize(mp, sf, sfe->namelen) -
 		    (__psint_t)sf > be64_to_cpu(dip->di_size)) {
include/xfs_dir2_format.h +20 -31

89 lines not on this page · raw message

libxfs/xfs_dir2_block.c +3 -3
index 3e4bc53..1d8f598 100644
@@ -1139,7 +1139,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Create entry for .
 	 */
-	dep = xfs_dir3_data_dot_entry_p(hdr);
+	dep = xfs_dir3_data_dot_entry_p(mp, hdr);
 	dep->inumber = cpu_to_be64(dp->i_ino);
 	dep->namelen = 1;
 	dep->name[0] = '.';
@@ -1153,7 +1153,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Create entry for ..
 	 */
-	dep = xfs_dir3_data_dotdot_entry_p(hdr);
+	dep = xfs_dir3_data_dotdot_entry_p(mp, hdr);
 	dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
 	dep->namelen = 2;
 	dep->name[0] = dep->name[1] = '.';
@@ -1164,7 +1164,7 @@ xfs_dir2_sf_to_block(
 	blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
 	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
 				(char *)dep - (char *)hdr));
-	offset = xfs_dir3_data_first_offset(hdr);
+	offset = xfs_dir3_data_first_offset(mp);
 	/*
 	 * Loop over existing entries, stuff them in.
 	 */
libxfs/xfs_dir2_sf.c +3 -3
index 740cab0..7580333 100644
@@ -540,7 +540,7 @@ xfs_dir2_sf_addname_hard(
 	 * to insert the new entry.
 	 * If it's going to end up at the end then oldsfep will point there.
 	 */
-	for (offset = XFS_DIR3_DATA_FIRST_OFFSET(mp),
+	for (offset = xfs_dir3_data_first_offset(mp),
 	      oldsfep = xfs_dir2_sf_firstentry(oldsfp),
 	      add_datasize = xfs_dir3_data_entsize(mp, args->namelen),
 	      eof = (char *)oldsfep == &buf[old_isize];
@@ -623,7 +623,7 @@ xfs_dir2_sf_addname_pick(
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	size = xfs_dir3_data_entsize(mp, args->namelen);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	holefit = 0;
 	/*
@@ -696,7 +696,7 @@ xfs_dir2_sf_check(
 	mp = dp->i_mount;
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	ino = xfs_dir2_sf_get_parent_ino(sfp);
 	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
 
repair/dir2.c +2 -2
index a856631..d931d1d 100644
@@ -705,7 +705,7 @@ process_sf_dir2_fixoff(
 
 	sfp = (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip);
 	sfep = xfs_dir2_sf_firstentry(sfp);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 
 	for (i = 0; i < sfp->count; i++) {
 		xfs_dir2_sf_put_offset(sfep, offset);
@@ -759,7 +759,7 @@ process_sf_dir2(
 	max_size = XFS_DFORK_DSIZE(dip, mp);
 	num_entries = sfp->count;
 	ino_dir_size = be64_to_cpu(dip->di_size);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	bad_offset = *repair = 0;
 
 	ASSERT(ino_dir_size <= max_size);
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 7/32
#20 lore raw

Re: [PATCH 07/32] xfs: dirent dtype presence is dependent on directory magic numbers

Quoted 17 lines · Dave Chinner

From: Dave Chinner <[email protected]>

The determination of whether a directory entry contains a dtype field originally was dependent on the filesystem having CRCs enabled. This meant that the format for dtype beign enabled could be determined by checking the directory block magic number rather than doing a feature bit check. This was useful in that it meant that we didn't need to pass a struct xfs_mount around to functions that were already supplied with a directory block header.

Unfortunately, the introduction of dtype fields into the v4 structure via a feature bit meant this "use the directory block magic number" method of discriminating the dirent entry sizes is broken. Hence we need to convert the places that use magic number checks to use feature bit checks so that they work correctly and not by chance.

Quoted 3 lines

The current code works on v4 filesystems only because the dirent size roundup covers the extra byte needed by the dtype field in the places where this problem occurs.

Looks right to me. Nitpicks & questions though:

FWIW, I find it confusing that we call xfs_dir3_*() functions from dir2 code or to find out whether the dir is in fact dir2 or dir3.

i.e.:

return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));

that just seems like an odd name to calculate the header size for dir2 vs. dir3 directories.

Also -

Is there any pro or con to defining the 3 offsets recursively:

static inline xfs_dir2_data_aoff_t xfs_dir3_data_dot_offset(struct xfs_mount *mp)
{
return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
}

static inline xfs_dir2_data_aoff_t xfs_dir3_data_dotdot_offset(struct xfs_mount *mp) {
return xfs_dir3_data_dot_offset(mp) +

		xfs_dir3_data_entsize(mp, 1);

}

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_first_offset(struct xfs_mount *mp)

 {
	return xfs_dir3_data_dotdot_offset(mp) +
		xfs_dir3_data_entsize(mp, 2);

}

vs directly, i.e.:

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_first_offset(struct xfs_mount *mp)

 {
	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb)) +
		xfs_dir3_data_entsize(mp, 1);	/* Dot */
		xfs_dir3_data_entsize(mp, 2);	/* Dotdot */

}

?

Looks technically correct though, so:

-Eric

Quoted 193 lines
---
 db/check.c                |  2 +-
 include/xfs_dir2_format.h | 51 +++++++++++++++++++----------------------------
 libxfs/xfs_dir2_block.c   |  6 +++---
 libxfs/xfs_dir2_sf.c      |  6 +++---
 repair/dir2.c             |  4 ++--
 5 files changed, 29 insertions(+), 40 deletions(-)
db/check.c +1 -1
index 2d4718d..4867698 100644
@@ -3434,7 +3434,7 @@ process_sf_dir_v2(
 		dbprintf(_("dir %lld entry . %lld\n"), id->ino, id->ino);
 	(*dot)++;
 	sfe = xfs_dir2_sf_firstentry(sf);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	for (i = sf->count - 1, i8 = 0; i >= 0; i--) {
 		if ((__psint_t)sfe + xfs_dir3_sf_entsize(mp, sf, sfe->namelen) -
 		    (__psint_t)sf > be64_to_cpu(dip->di_size)) {
include/xfs_dir2_format.h +20 -31
index a0961a6..9cf6738 100644
@@ -497,69 +497,58 @@ xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
 /*
  * Offsets of . and .. in data space (always block 0)
  *
- * The macros are used for shortform directories as they have no headers to read
- * the magic number out of. Shortform directories need to know the size of the
- * data block header because the sfe embeds the block offset of the entry into
- * it so that it doesn't change when format conversion occurs. Bad Things Happen
- * if we don't follow this rule.
- *
  * XXX: there is scope for significant optimisation of the logic here. Right
  * now we are checking for "dir3 format" over and over again. Ideally we should
  * only do it once for each operation.
  */
-#define	XFS_DIR3_DATA_DOT_OFFSET(mp)	\
-	xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&(mp)->m_sb))
-#define	XFS_DIR3_DATA_DOTDOT_OFFSET(mp)	\
-	(XFS_DIR3_DATA_DOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 1))
-#define	XFS_DIR3_DATA_FIRST_OFFSET(mp)		\
-	(XFS_DIR3_DATA_DOTDOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 2))
-
 static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dot_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dot_offset(struct xfs_mount *mp)
 {
-	return xfs_dir3_data_entry_offset(hdr);
+	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
 }
 
 static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dotdot_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
 {
-	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
-	return xfs_dir3_data_dot_offset(hdr) +
-		__xfs_dir3_data_entsize(dir3, 1);
+	return xfs_dir3_data_dot_offset(mp) +
+		xfs_dir3_data_entsize(mp, 1);
 }
 
 static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_first_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_first_offset(struct xfs_mount *mp)
 {
-	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
-	return xfs_dir3_data_dotdot_offset(hdr) +
-		__xfs_dir3_data_entsize(dir3, 2);
+	return xfs_dir3_data_dotdot_offset(mp) +
+		xfs_dir3_data_entsize(mp, 2);
 }
 
 /*
  * location of . and .. in data space (always block 0)
  */
 static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dot_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dot_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
 {
 	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dot_offset(hdr));
+		((char *)hdr + xfs_dir3_data_dot_offset(mp));
 }
 
 static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dotdot_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dotdot_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
 {
 	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dotdot_offset(hdr));
+		((char *)hdr + xfs_dir3_data_dotdot_offset(mp));
 }
 
 static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_first_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_first_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
 {
 	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_first_offset(hdr));
+		((char *)hdr + xfs_dir3_data_first_offset(mp));
 }
 
 /*
libxfs/xfs_dir2_block.c +3 -3
index 3e4bc53..1d8f598 100644
@@ -1139,7 +1139,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Create entry for .
 	 */
-	dep = xfs_dir3_data_dot_entry_p(hdr);
+	dep = xfs_dir3_data_dot_entry_p(mp, hdr);
 	dep->inumber = cpu_to_be64(dp->i_ino);
 	dep->namelen = 1;
 	dep->name[0] = '.';
@@ -1153,7 +1153,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Create entry for ..
 	 */
-	dep = xfs_dir3_data_dotdot_entry_p(hdr);
+	dep = xfs_dir3_data_dotdot_entry_p(mp, hdr);
 	dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
 	dep->namelen = 2;
 	dep->name[0] = dep->name[1] = '.';
@@ -1164,7 +1164,7 @@ xfs_dir2_sf_to_block(
 	blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
 	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
 				(char *)dep - (char *)hdr));
-	offset = xfs_dir3_data_first_offset(hdr);
+	offset = xfs_dir3_data_first_offset(mp);
 	/*
 	 * Loop over existing entries, stuff them in.
 	 */
libxfs/xfs_dir2_sf.c +3 -3
index 740cab0..7580333 100644
@@ -540,7 +540,7 @@ xfs_dir2_sf_addname_hard(
 	 * to insert the new entry.
 	 * If it's going to end up at the end then oldsfep will point there.
 	 */
-	for (offset = XFS_DIR3_DATA_FIRST_OFFSET(mp),
+	for (offset = xfs_dir3_data_first_offset(mp),
 	      oldsfep = xfs_dir2_sf_firstentry(oldsfp),
 	      add_datasize = xfs_dir3_data_entsize(mp, args->namelen),
 	      eof = (char *)oldsfep == &buf[old_isize];
@@ -623,7 +623,7 @@ xfs_dir2_sf_addname_pick(
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	size = xfs_dir3_data_entsize(mp, args->namelen);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	holefit = 0;
 	/*
@@ -696,7 +696,7 @@ xfs_dir2_sf_check(
 	mp = dp->i_mount;
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	ino = xfs_dir2_sf_get_parent_ino(sfp);
 	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
 
repair/dir2.c +1 -1
index a856631..d931d1d 100644
@@ -705,7 +705,7 @@ process_sf_dir2_fixoff(
 
 	sfp = (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip);
 	sfep = xfs_dir2_sf_firstentry(sfp);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 
 	for (i = 0; i < sfp->count; i++) {
 		xfs_dir2_sf_put_offset(sfep, offset);

repair/dir2.c process_sf_dir2( · line 765

Quoted 8 lines
repair/dir2.c +1 -1
@@ -759,7 +759,7 @@ process_sf_dir2(
 	max_size = XFS_DFORK_DSIZE(dip, mp);
 	num_entries = sfp->count;
 	ino_dir_size = be64_to_cpu(dip->di_size);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	bad_offset = *repair = 0;
 
 	ASSERT(ino_dir_size <= max_size);

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#21 lore raw

Re: [PATCH 07/32] xfs: dirent dtype presence is dependent on directory magic numbers

Quoted 24 lines · Eric Sandeen
Quoted 17 lines · Dave Chinner

From: Dave Chinner <[email protected]>

The determination of whether a directory entry contains a dtype field originally was dependent on the filesystem having CRCs enabled. This meant that the format for dtype beign enabled could be determined by checking the directory block magic number rather than doing a feature bit check. This was useful in that it meant that we didn't need to pass a struct xfs_mount around to functions that were already supplied with a directory block header.

Unfortunately, the introduction of dtype fields into the v4 structure via a feature bit meant this "use the directory block magic number" method of discriminating the dirent entry sizes is broken. Hence we need to convert the places that use magic number checks to use feature bit checks so that they work correctly and not by chance.

Quoted 3 lines

The current code works on v4 filesystems only because the dirent size roundup covers the extra byte needed by the dtype field in the places where this problem occurs.

Looks right to me. Nitpicks & questions though:

Quoted 7 lines

FWIW, I find it confusing that we call xfs_dir3_*() functions from dir2 code or to find out whether the dir is in fact dir2 or dir3.

i.e.:

return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));

It's the convention I've used since first introducing the CRC code. dir2 means it handles just dir2 format, dir3 means it handles either the dir2 or the CRC enabled format.

That said, this goes away in the directory ops vectorisation patch set, when dir2 means "handles dir2 format" and dir3 means "handles only dir3 format"....

Quoted 29 lines

that just seems like an odd name to calculate the header size for dir2 vs. dir3 directories.

Also -

Is there any pro or con to defining the 3 offsets recursively:

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_dot_offset(struct xfs_mount *mp)
{

include/xfs_dir2_format.h +0 -0
 	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
 }
 
 static inline xfs_dir2_data_aoff_t
 xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
 {
 	return xfs_dir3_data_dot_offset(mp) +
		xfs_dir3_data_entsize(mp, 1);

}

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_first_offset(struct xfs_mount *mp)

 {
	return xfs_dir3_data_dotdot_offset(mp) +
		xfs_dir3_data_entsize(mp, 2);

}

vs directly, i.e.:

Quoted 7 lines

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_first_offset(struct xfs_mount *mp)

 {
	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb)) +
		xfs_dir3_data_entsize(mp, 1);	/* Dot */
		xfs_dir3_data_entsize(mp, 2);	/* Dotdot */

}

None, really. This is just a mechanical change to fix the bug, not a change of logic. This is changed to the direct method in the dir ops vectorisation series....

Cheers,

Dave.

Signature · 7 lines
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#22 lore raw

Re: [PATCH 07/32] xfs: dirent dtype presence is dependent on directory magic numbers

Quoted 78 lines · Dave Chinner
Quoted 24 lines · Eric Sandeen
Quoted 17 lines · Dave Chinner

From: Dave Chinner <[email protected]>

The determination of whether a directory entry contains a dtype field originally was dependent on the filesystem having CRCs enabled. This meant that the format for dtype beign enabled could be determined by checking the directory block magic number rather than doing a feature bit check. This was useful in that it meant that we didn't need to pass a struct xfs_mount around to functions that were already supplied with a directory block header.

Unfortunately, the introduction of dtype fields into the v4 structure via a feature bit meant this "use the directory block magic number" method of discriminating the dirent entry sizes is broken. Hence we need to convert the places that use magic number checks to use feature bit checks so that they work correctly and not by chance.

Quoted 3 lines

The current code works on v4 filesystems only because the dirent size roundup covers the extra byte needed by the dtype field in the places where this problem occurs.

Looks right to me. Nitpicks & questions though:

Quoted 7 lines

FWIW, I find it confusing that we call xfs_dir3_*() functions from dir2 code or to find out whether the dir is in fact dir2 or dir3.

i.e.:

return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));

It's the convention I've used since first introducing the CRC code. dir2 means it handles just dir2 format, dir3 means it handles either the dir2 or the CRC enabled format.

That said, this goes away in the directory ops vectorisation patch set, when dir2 means "handles dir2 format" and dir3 means "handles only dir3 format"....

Quoted 29 lines

that just seems like an odd name to calculate the header size for dir2 vs. dir3 directories.

Also -

Is there any pro or con to defining the 3 offsets recursively:

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_dot_offset(struct xfs_mount *mp)
{

include/xfs_dir2_format.h +0 -0
 	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
 }
 
 static inline xfs_dir2_data_aoff_t
 xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
 {
 	return xfs_dir3_data_dot_offset(mp) +
		xfs_dir3_data_entsize(mp, 1);

}

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_first_offset(struct xfs_mount *mp)

 {
	return xfs_dir3_data_dotdot_offset(mp) +
		xfs_dir3_data_entsize(mp, 2);

}

vs directly, i.e.:

Quoted 7 lines

static inline xfs_dir2_data_aoff_t
xfs_dir3_data_first_offset(struct xfs_mount *mp)

 {
	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb)) +
		xfs_dir3_data_entsize(mp, 1);	/* Dot */
		xfs_dir3_data_entsize(mp, 2);	/* Dotdot */

}

Quoted 3 lines

None, really. This is just a mechanical change to fix the bug, not a change of logic. This is changed to the direct method in the dir ops vectorisation series....

Ok. Sorry for not keeping up.

(I knew it was mechanical, didn't mean this patch was wrong, just wondering out loud some more).

-Eric

Quoted 4 lines

Cheers,

Dave.

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#24 lore raw

PATCH 8/32 xfs: create a shared header file for format-related information

In reply to a message not in the archive

All of the buffer operations structures are needed to be exported for xfs_db, so move them all to a common location rather than spreading them all over the place. They are verifying the on-disk format, so while xfs_format.h might be a good place, it is not part of the on disk format.

Hence we need to create a new header file that we centralise these related definitions. Start by moving the bffer operations structures, and then also move all the other definitions that have crept into xfs_log_format.h and xfs_format.h as there was no other shared header file to put them in.

---
 include/Makefile           |   1 +
 include/libxfs.h           |   1 +
 include/xfs_ag.h           |   4 -
 include/xfs_alloc.h        |   3 -
 include/xfs_alloc_btree.h  |   2 -
 include/xfs_attr_leaf.h    |   2 -
 include/xfs_attr_remote.h  |   2 -
 include/xfs_bmap_btree.h   |   2 -
 include/xfs_da_btree.h     |   2 -
 include/xfs_format.h       |  10 --
 include/xfs_ialloc.h       |   2 -
 include/xfs_ialloc_btree.h |   2 -
 include/xfs_inode_buf.h    |   2 -
 include/xfs_log_format.h   | 177 --------------------------------
 include/xfs_sb.h           |   3 -
 include/xfs_shared.h       | 244 +++++++++++++++++++++++++++++++++++++++++++++
 16 files changed, 246 insertions(+), 213 deletions(-)
 create mode 100644 include/xfs_shared.h
include/Makefile +1 -0
index 628a087..fd2d61b 100644
@@ -38,6 +38,7 @@ QAHFILES = libxfs.h libxlog.h \
 	xfs_metadump.h \
 	xfs_quota_defs.h \
 	xfs_sb.h \
+	xfs_shared.h \
 	xfs_trace.h \
 	xfs_trans_resv.h \
 	xfs_trans_space.h
include/libxfs.h +1 -0
index ffd83bf..a5d6388 100644
@@ -37,6 +37,7 @@
 #include <xfs/xfs_fs.h>
 #include <xfs/xfs_arch.h>
 
+#include <xfs/xfs_shared.h>
 #include <xfs/xfs_format.h>
 #include <xfs/xfs_log_format.h>
 #include <xfs/xfs_quota_defs.h>
include/xfs_ag.h +0 -4
index 1cb740a..3fc1098 100644
@@ -128,8 +128,6 @@ typedef struct xfs_agf {
 extern int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
 
-extern const struct xfs_buf_ops xfs_agf_buf_ops;
-
 /*
  * Size of the unlinked inode hash table in the agi.
  */
@@ -191,8 +189,6 @@ typedef struct xfs_agi {
 extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 				xfs_agnumber_t agno, struct xfs_buf **bpp);
 
-extern const struct xfs_buf_ops xfs_agi_buf_ops;
-
 /*
  * The third a.g. block contains the a.g. freelist, an array
  * of block pointers to blocks owned by the allocation btree code.
include/xfs_alloc.h +0 -3
index 99d0a61..feacb06 100644
@@ -231,7 +231,4 @@ xfs_alloc_get_rec(
 	xfs_extlen_t		*len,	/* output: length of extent */
 	int			*stat);	/* output: success/failure */
 
-extern const struct xfs_buf_ops xfs_agf_buf_ops;
-extern const struct xfs_buf_ops xfs_agfl_buf_ops;
-
 #endif	/* __XFS_ALLOC_H__ */
include/xfs_alloc_btree.h +0 -2
index e3a3f74..72676c3 100644
@@ -95,6 +95,4 @@ extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *,
 		xfs_agnumber_t, xfs_btnum_t);
 extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
 
-extern const struct xfs_buf_ops xfs_allocbt_buf_ops;
-
 #endif	/* __XFS_ALLOC_BTREE_H__ */
include/xfs_attr_leaf.h +0 -2
index c102213..da34e64 100644
@@ -336,6 +336,4 @@ void	xfs_attr3_leaf_hdr_from_disk(struct xfs_attr3_icleaf_hdr *to,
 void	xfs_attr3_leaf_hdr_to_disk(struct xfs_attr_leafblock *to,
 				   struct xfs_attr3_icleaf_hdr *from);
 
-extern const struct xfs_buf_ops xfs_attr3_leaf_buf_ops;
-
 #endif	/* __XFS_ATTR_LEAF_H__ */
include/xfs_attr_remote.h +0 -2
index 92a8fd7..b3e1e1b 100644
@@ -45,8 +45,6 @@ struct xfs_attr3_rmt_hdr {
 	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
 			sizeof(struct xfs_attr3_rmt_hdr) : 0))
 
-extern const struct xfs_buf_ops xfs_attr3_rmt_buf_ops;
-
 int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
include/xfs_bmap_btree.h +0 -2
index 1b726d6..e307978 100644
@@ -239,6 +239,4 @@ extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
 
-extern const struct xfs_buf_ops xfs_bmbt_buf_ops;
-
 #endif	/* __XFS_BMAP_BTREE_H__ */
include/xfs_da_btree.h +0 -2
index b1f2679..a762cfa 100644
@@ -309,8 +309,6 @@ int	xfs_da3_node_read(struct xfs_trans *tp, struct xfs_inode *dp,
 			 xfs_dablk_t bno, xfs_daddr_t mappedbno,
 			 struct xfs_buf **bpp, int which_fork);
 
-extern const struct xfs_buf_ops xfs_da3_node_buf_ops;
-
 /*
  * Utility routines.
  */
include/xfs_format.h +0 -10
index 35c08ff..a790428 100644
@@ -156,14 +156,4 @@ struct xfs_dsymlink_hdr {
 	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
 			sizeof(struct xfs_dsymlink_hdr) : 0))
 
-int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
-int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-
-extern const struct xfs_buf_ops xfs_symlink_buf_ops;
-
 #endif /* __XFS_FORMAT_H__ */
include/xfs_ialloc.h +0 -2
index 68c0732..1557798 100644
@@ -158,6 +158,4 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
 			  xfs_agnumber_t agno, xfs_agblock_t agbno,
 			  xfs_agblock_t length, unsigned int gen);
 
-extern const struct xfs_buf_ops xfs_agi_buf_ops;
-
 #endif	/* __XFS_IALLOC_H__ */
include/xfs_ialloc_btree.h +0 -2
index 3ac36b7..cfbfe46 100644
@@ -110,6 +110,4 @@ extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
 extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
-extern const struct xfs_buf_ops xfs_inobt_buf_ops;
-
 #endif	/* __XFS_IALLOC_BTREE_H__ */
include/xfs_inode_buf.h +0 -2
index aae9fc4..e8fd3bd 100644
@@ -47,6 +47,4 @@ void		xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
 
-extern const struct xfs_buf_ops xfs_inode_buf_ops;
-
 #endif	/* __XFS_INODE_BUF_H__ */
include/xfs_log_format.h +0 -177

193 lines not on this page · raw message

include/xfs_sb.h +0 -3
index c8d8898..741b7a3 100644
@@ -695,7 +695,4 @@ extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
 extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
 extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
 
-extern const struct xfs_buf_ops xfs_sb_buf_ops;
-extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
-
 #endif	/* __XFS_SB_H__ */
include/xfs_shared.h new file +244 -0

244 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 8/32
#25 lore raw

Re: [PATCH 08/32] xfs: create a shared header file for format-related information

Quoted 6 lines · Dave Chinner

All of the buffer operations structures are needed to be exported for xfs_db, so move them all to a common location rather than spreading them all over the place. They are verifying the on-disk format, so while xfs_format.h might be a good place, it is not part of the on disk format.

Quoted 7 lines

Hence we need to create a new header file that we centralise these related definitions. Start by moving the bffer operations structures, and then also move all the other definitions that have crept into xfs_log_format.h and xfs_format.h as there was no other shared header file to put them in.

All lines present & accounted for in new file. ;)

Would be nice to fix:

"* This determine how hard the buffer cache tries to hold onto"

while you're at it, but *shrug*

Quoted 642 lines
---
 include/Makefile           |   1 +
 include/libxfs.h           |   1 +
 include/xfs_ag.h           |   4 -
 include/xfs_alloc.h        |   3 -
 include/xfs_alloc_btree.h  |   2 -
 include/xfs_attr_leaf.h    |   2 -
 include/xfs_attr_remote.h  |   2 -
 include/xfs_bmap_btree.h   |   2 -
 include/xfs_da_btree.h     |   2 -
 include/xfs_format.h       |  10 --
 include/xfs_ialloc.h       |   2 -
 include/xfs_ialloc_btree.h |   2 -
 include/xfs_inode_buf.h    |   2 -
 include/xfs_log_format.h   | 177 --------------------------------
 include/xfs_sb.h           |   3 -
 include/xfs_shared.h       | 244 +++++++++++++++++++++++++++++++++++++++++++++
 16 files changed, 246 insertions(+), 213 deletions(-)
 create mode 100644 include/xfs_shared.h
include/Makefile +1 -0
index 628a087..fd2d61b 100644
@@ -38,6 +38,7 @@ QAHFILES = libxfs.h libxlog.h \
 	xfs_metadump.h \
 	xfs_quota_defs.h \
 	xfs_sb.h \
+	xfs_shared.h \
 	xfs_trace.h \
 	xfs_trans_resv.h \
 	xfs_trans_space.h
include/libxfs.h +1 -0
index ffd83bf..a5d6388 100644
@@ -37,6 +37,7 @@
 #include <xfs/xfs_fs.h>
 #include <xfs/xfs_arch.h>
 
+#include <xfs/xfs_shared.h>
 #include <xfs/xfs_format.h>
 #include <xfs/xfs_log_format.h>
 #include <xfs/xfs_quota_defs.h>
include/xfs_ag.h +0 -4
index 1cb740a..3fc1098 100644
@@ -128,8 +128,6 @@ typedef struct xfs_agf {
 extern int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
 
-extern const struct xfs_buf_ops xfs_agf_buf_ops;
-
 /*
  * Size of the unlinked inode hash table in the agi.
  */
@@ -191,8 +189,6 @@ typedef struct xfs_agi {
 extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 				xfs_agnumber_t agno, struct xfs_buf **bpp);
 
-extern const struct xfs_buf_ops xfs_agi_buf_ops;
-
 /*
  * The third a.g. block contains the a.g. freelist, an array
  * of block pointers to blocks owned by the allocation btree code.
include/xfs_alloc.h +0 -3
index 99d0a61..feacb06 100644
@@ -231,7 +231,4 @@ xfs_alloc_get_rec(
 	xfs_extlen_t		*len,	/* output: length of extent */
 	int			*stat);	/* output: success/failure */
 
-extern const struct xfs_buf_ops xfs_agf_buf_ops;
-extern const struct xfs_buf_ops xfs_agfl_buf_ops;
-
 #endif	/* __XFS_ALLOC_H__ */
include/xfs_alloc_btree.h +0 -2
index e3a3f74..72676c3 100644
@@ -95,6 +95,4 @@ extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *,
 		xfs_agnumber_t, xfs_btnum_t);
 extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
 
-extern const struct xfs_buf_ops xfs_allocbt_buf_ops;
-
 #endif	/* __XFS_ALLOC_BTREE_H__ */
include/xfs_attr_leaf.h +0 -2
index c102213..da34e64 100644
@@ -336,6 +336,4 @@ void	xfs_attr3_leaf_hdr_from_disk(struct xfs_attr3_icleaf_hdr *to,
 void	xfs_attr3_leaf_hdr_to_disk(struct xfs_attr_leafblock *to,
 				   struct xfs_attr3_icleaf_hdr *from);
 
-extern const struct xfs_buf_ops xfs_attr3_leaf_buf_ops;
-
 #endif	/* __XFS_ATTR_LEAF_H__ */
include/xfs_attr_remote.h +0 -2
index 92a8fd7..b3e1e1b 100644
@@ -45,8 +45,6 @@ struct xfs_attr3_rmt_hdr {
 	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
 			sizeof(struct xfs_attr3_rmt_hdr) : 0))
 
-extern const struct xfs_buf_ops xfs_attr3_rmt_buf_ops;
-
 int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
include/xfs_bmap_btree.h +0 -2
index 1b726d6..e307978 100644
@@ -239,6 +239,4 @@ extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
 
-extern const struct xfs_buf_ops xfs_bmbt_buf_ops;
-
 #endif	/* __XFS_BMAP_BTREE_H__ */
include/xfs_da_btree.h +0 -2
index b1f2679..a762cfa 100644
@@ -309,8 +309,6 @@ int	xfs_da3_node_read(struct xfs_trans *tp, struct xfs_inode *dp,
 			 xfs_dablk_t bno, xfs_daddr_t mappedbno,
 			 struct xfs_buf **bpp, int which_fork);
 
-extern const struct xfs_buf_ops xfs_da3_node_buf_ops;
-
 /*
  * Utility routines.
  */
include/xfs_format.h +0 -10
index 35c08ff..a790428 100644
@@ -156,14 +156,4 @@ struct xfs_dsymlink_hdr {
 	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
 			sizeof(struct xfs_dsymlink_hdr) : 0))
 
-int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
-int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-
-extern const struct xfs_buf_ops xfs_symlink_buf_ops;
-
 #endif /* __XFS_FORMAT_H__ */
include/xfs_ialloc.h +0 -2
index 68c0732..1557798 100644
@@ -158,6 +158,4 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
 			  xfs_agnumber_t agno, xfs_agblock_t agbno,
 			  xfs_agblock_t length, unsigned int gen);
 
-extern const struct xfs_buf_ops xfs_agi_buf_ops;
-
 #endif	/* __XFS_IALLOC_H__ */
include/xfs_ialloc_btree.h +0 -2
index 3ac36b7..cfbfe46 100644
@@ -110,6 +110,4 @@ extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
 extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
-extern const struct xfs_buf_ops xfs_inobt_buf_ops;
-
 #endif	/* __XFS_IALLOC_BTREE_H__ */
include/xfs_inode_buf.h +0 -2
index aae9fc4..e8fd3bd 100644
@@ -47,6 +47,4 @@ void		xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
 
-extern const struct xfs_buf_ops xfs_inode_buf_ops;
-
 #endif	/* __XFS_INODE_BUF_H__ */
include/xfs_log_format.h +0 -177
index 31e3a06..aeaa715 100644
@@ -234,178 +234,6 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_ICREATE,	"XFS_LI_ICREATE" }
 
 /*
- * Transaction types.  Used to distinguish types of buffers.
- */
-#define XFS_TRANS_SETATTR_NOT_SIZE	1
-#define XFS_TRANS_SETATTR_SIZE		2
-#define XFS_TRANS_INACTIVE		3
-#define XFS_TRANS_CREATE		4
-#define XFS_TRANS_CREATE_TRUNC		5
-#define XFS_TRANS_TRUNCATE_FILE		6
-#define XFS_TRANS_REMOVE		7
-#define XFS_TRANS_LINK			8
-#define XFS_TRANS_RENAME		9
-#define XFS_TRANS_MKDIR			10
-#define XFS_TRANS_RMDIR			11
-#define XFS_TRANS_SYMLINK		12
-#define XFS_TRANS_SET_DMATTRS		13
-#define XFS_TRANS_GROWFS		14
-#define XFS_TRANS_STRAT_WRITE		15
-#define XFS_TRANS_DIOSTRAT		16
-/* 17 was XFS_TRANS_WRITE_SYNC */
-#define	XFS_TRANS_WRITEID		18
-#define	XFS_TRANS_ADDAFORK		19
-#define	XFS_TRANS_ATTRINVAL		20
-#define	XFS_TRANS_ATRUNCATE		21
-#define	XFS_TRANS_ATTR_SET		22
-#define	XFS_TRANS_ATTR_RM		23
-#define	XFS_TRANS_ATTR_FLAG		24
-#define	XFS_TRANS_CLEAR_AGI_BUCKET	25
-#define XFS_TRANS_QM_SBCHANGE		26
-/*
- * Dummy entries since we use the transaction type to index into the
- * trans_type[] in xlog_recover_print_trans_head()
- */
-#define XFS_TRANS_DUMMY1		27
-#define XFS_TRANS_DUMMY2		28
-#define XFS_TRANS_QM_QUOTAOFF		29
-#define XFS_TRANS_QM_DQALLOC		30
-#define XFS_TRANS_QM_SETQLIM		31
-#define XFS_TRANS_QM_DQCLUSTER		32
-#define XFS_TRANS_QM_QINOCREATE		33
-#define XFS_TRANS_QM_QUOTAOFF_END	34
-#define XFS_TRANS_SB_UNIT		35
-#define XFS_TRANS_FSYNC_TS		36
-#define	XFS_TRANS_GROWFSRT_ALLOC	37
-#define	XFS_TRANS_GROWFSRT_ZERO		38
-#define	XFS_TRANS_GROWFSRT_FREE		39
-#define	XFS_TRANS_SWAPEXT		40
-#define	XFS_TRANS_SB_COUNT		41
-#define	XFS_TRANS_CHECKPOINT		42
-#define	XFS_TRANS_ICREATE		43
-#define	XFS_TRANS_TYPE_MAX		43
-/* new transaction types need to be reflected in xfs_logprint(8) */
-
-#define XFS_TRANS_TYPES \
-	{ XFS_TRANS_SETATTR_NOT_SIZE,	"SETATTR_NOT_SIZE" }, \
-	{ XFS_TRANS_SETATTR_SIZE,	"SETATTR_SIZE" }, \
-	{ XFS_TRANS_INACTIVE,		"INACTIVE" }, \
-	{ XFS_TRANS_CREATE,		"CREATE" }, \
-	{ XFS_TRANS_CREATE_TRUNC,	"CREATE_TRUNC" }, \
-	{ XFS_TRANS_TRUNCATE_FILE,	"TRUNCATE_FILE" }, \
-	{ XFS_TRANS_REMOVE,		"REMOVE" }, \
-	{ XFS_TRANS_LINK,		"LINK" }, \
-	{ XFS_TRANS_RENAME,		"RENAME" }, \
-	{ XFS_TRANS_MKDIR,		"MKDIR" }, \
-	{ XFS_TRANS_RMDIR,		"RMDIR" }, \
-	{ XFS_TRANS_SYMLINK,		"SYMLINK" }, \
-	{ XFS_TRANS_SET_DMATTRS,	"SET_DMATTRS" }, \
-	{ XFS_TRANS_GROWFS,		"GROWFS" }, \
-	{ XFS_TRANS_STRAT_WRITE,	"STRAT_WRITE" }, \
-	{ XFS_TRANS_DIOSTRAT,		"DIOSTRAT" }, \
-	{ XFS_TRANS_WRITEID,		"WRITEID" }, \
-	{ XFS_TRANS_ADDAFORK,		"ADDAFORK" }, \
-	{ XFS_TRANS_ATTRINVAL,		"ATTRINVAL" }, \
-	{ XFS_TRANS_ATRUNCATE,		"ATRUNCATE" }, \
-	{ XFS_TRANS_ATTR_SET,		"ATTR_SET" }, \
-	{ XFS_TRANS_ATTR_RM,		"ATTR_RM" }, \
-	{ XFS_TRANS_ATTR_FLAG,		"ATTR_FLAG" }, \
-	{ XFS_TRANS_CLEAR_AGI_BUCKET,	"CLEAR_AGI_BUCKET" }, \
-	{ XFS_TRANS_QM_SBCHANGE,	"QM_SBCHANGE" }, \
-	{ XFS_TRANS_QM_QUOTAOFF,	"QM_QUOTAOFF" }, \
-	{ XFS_TRANS_QM_DQALLOC,		"QM_DQALLOC" }, \
-	{ XFS_TRANS_QM_SETQLIM,		"QM_SETQLIM" }, \
-	{ XFS_TRANS_QM_DQCLUSTER,	"QM_DQCLUSTER" }, \
-	{ XFS_TRANS_QM_QINOCREATE,	"QM_QINOCREATE" }, \
-	{ XFS_TRANS_QM_QUOTAOFF_END,	"QM_QOFF_END" }, \
-	{ XFS_TRANS_SB_UNIT,		"SB_UNIT" }, \
-	{ XFS_TRANS_FSYNC_TS,		"FSYNC_TS" }, \
-	{ XFS_TRANS_GROWFSRT_ALLOC,	"GROWFSRT_ALLOC" }, \
-	{ XFS_TRANS_GROWFSRT_ZERO,	"GROWFSRT_ZERO" }, \
-	{ XFS_TRANS_GROWFSRT_FREE,	"GROWFSRT_FREE" }, \
-	{ XFS_TRANS_SWAPEXT,		"SWAPEXT" }, \
-	{ XFS_TRANS_SB_COUNT,		"SB_COUNT" }, \
-	{ XFS_TRANS_CHECKPOINT,		"CHECKPOINT" }, \
-	{ XFS_TRANS_DUMMY1,		"DUMMY1" }, \
-	{ XFS_TRANS_DUMMY2,		"DUMMY2" }, \
-	{ XLOG_UNMOUNT_REC_TYPE,	"UNMOUNT" }
-
-/*
- * This structure is used to track log items associated with
- * a transaction.  It points to the log item and keeps some
- * flags to track the state of the log item.  It also tracks
- * the amount of space needed to log the item it describes
- * once we get to commit processing (see xfs_trans_commit()).
- */
-struct xfs_log_item_desc {
-	struct xfs_log_item	*lid_item;
-	struct list_head	lid_trans;
-	unsigned char		lid_flags;
-};
-
-#define XFS_LID_DIRTY		0x1
-
-/*
- * Values for t_flags.
- */
-#define	XFS_TRANS_DIRTY		0x01	/* something needs to be logged */
-#define	XFS_TRANS_SB_DIRTY	0x02	/* superblock is modified */
-#define	XFS_TRANS_PERM_LOG_RES	0x04	/* xact took a permanent log res */
-#define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
-#define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
-#define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
-#define XFS_TRANS_FREEZE_PROT	0x40	/* Transaction has elevated writer
-					   count in superblock */
-
-/*
- * Values for call flags parameter.
- */
-#define	XFS_TRANS_RELEASE_LOG_RES	0x4
-#define	XFS_TRANS_ABORT			0x8
-
-/*
- * Field values for xfs_trans_mod_sb.
- */
-#define	XFS_TRANS_SB_ICOUNT		0x00000001
-#define	XFS_TRANS_SB_IFREE		0x00000002
-#define	XFS_TRANS_SB_FDBLOCKS		0x00000004
-#define	XFS_TRANS_SB_RES_FDBLOCKS	0x00000008
-#define	XFS_TRANS_SB_FREXTENTS		0x00000010
-#define	XFS_TRANS_SB_RES_FREXTENTS	0x00000020
-#define	XFS_TRANS_SB_DBLOCKS		0x00000040
-#define	XFS_TRANS_SB_AGCOUNT		0x00000080
-#define	XFS_TRANS_SB_IMAXPCT		0x00000100
-#define	XFS_TRANS_SB_REXTSIZE		0x00000200
-#define	XFS_TRANS_SB_RBMBLOCKS		0x00000400
-#define	XFS_TRANS_SB_RBLOCKS		0x00000800
-#define	XFS_TRANS_SB_REXTENTS		0x00001000
-#define	XFS_TRANS_SB_REXTSLOG		0x00002000
-
-/*
- * Here we centralize the specification of XFS meta-data buffer
- * reference count values.  This determine how hard the buffer
- * cache tries to hold onto the buffer.
- */
-#define	XFS_AGF_REF		4
-#define	XFS_AGI_REF		4
-#define	XFS_AGFL_REF		3
-#define	XFS_INO_BTREE_REF	3
-#define	XFS_ALLOC_BTREE_REF	2
-#define	XFS_BMAP_BTREE_REF	2
-#define	XFS_DIR_BTREE_REF	2
-#define	XFS_INO_REF		2
-#define	XFS_ATTR_BTREE_REF	1
-#define	XFS_DQUOT_REF		1
-
-/*
- * Flags for xfs_trans_ichgtime().
- */
-#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
-#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
-#define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */
-
-
-/*
  * Inode Log Item Format definitions.
  *
  * This is the structure used to lay out an inode log item in the
@@ -793,7 +621,6 @@ typedef struct xfs_qoff_logformat {
 	char			qf_pad[12];	/* padding for future */
 } xfs_qoff_logformat_t;
 
-
 /*
  * Disk quotas status in m_qflags, and also sb_qflags. 16 bits.
  */
@@ -845,8 +672,4 @@ struct xfs_icreate_log {
 	__be32		icl_gen;	/* inode generation number to use */
 };
 
-int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
-int	xfs_log_calc_minimum_size(struct xfs_mount *);
-
-
 #endif /* __XFS_LOG_FORMAT_H__ */
include/xfs_sb.h +0 -3
index c8d8898..741b7a3 100644
@@ -695,7 +695,4 @@ extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
 extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
 extern void	xfs_sb_quota_from_disk(struct xfs_sb *sbp);
 
-extern const struct xfs_buf_ops xfs_sb_buf_ops;
-extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
-
 #endif	/* __XFS_SB_H__ */
include/xfs_shared.h new file +234 -0
new file mode 100644
index 0000000..63c94b1
@@ -0,0 +1,244 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_SHARED_H__
+#define __XFS_SHARED_H__
+
+/*
+ * Definitions shared between kernel and userspace that don't fit into any other
+ * header file that is shared with userspace.
+ */
+struct xfs_ifork;
+struct xfs_buf;
+struct xfs_buf_ops;
+struct xfs_mount;
+struct xfs_trans;
+struct xfs_inode;
+
+/*
+ * Buffer verifier operations are widely used, including userspace tools
+ */
+extern const struct xfs_buf_ops xfs_agf_buf_ops;
+extern const struct xfs_buf_ops xfs_agi_buf_ops;
+extern const struct xfs_buf_ops xfs_agf_buf_ops;
+extern const struct xfs_buf_ops xfs_agfl_buf_ops;
+extern const struct xfs_buf_ops xfs_allocbt_buf_ops;
+extern const struct xfs_buf_ops xfs_attr3_leaf_buf_ops;
+extern const struct xfs_buf_ops xfs_attr3_rmt_buf_ops;
+extern const struct xfs_buf_ops xfs_bmbt_buf_ops;
+extern const struct xfs_buf_ops xfs_da3_node_buf_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+extern const struct xfs_buf_ops xfs_agi_buf_ops;
+extern const struct xfs_buf_ops xfs_inobt_buf_ops;
+extern const struct xfs_buf_ops xfs_inode_buf_ops;
+extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_sb_buf_ops;
+extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
+extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+
+/*
+ * Transaction types.  Used to distinguish types of buffers. These never reach
+ * the log.
+ */
+#define XFS_TRANS_SETATTR_NOT_SIZE	1
+#define XFS_TRANS_SETATTR_SIZE		2
+#define XFS_TRANS_INACTIVE		3
+#define XFS_TRANS_CREATE		4
+#define XFS_TRANS_CREATE_TRUNC		5
+#define XFS_TRANS_TRUNCATE_FILE		6
+#define XFS_TRANS_REMOVE		7
+#define XFS_TRANS_LINK			8
+#define XFS_TRANS_RENAME		9
+#define XFS_TRANS_MKDIR			10
+#define XFS_TRANS_RMDIR			11
+#define XFS_TRANS_SYMLINK		12
+#define XFS_TRANS_SET_DMATTRS		13
+#define XFS_TRANS_GROWFS		14
+#define XFS_TRANS_STRAT_WRITE		15
+#define XFS_TRANS_DIOSTRAT		16
+/* 17 was XFS_TRANS_WRITE_SYNC */
+#define	XFS_TRANS_WRITEID		18
+#define	XFS_TRANS_ADDAFORK		19
+#define	XFS_TRANS_ATTRINVAL		20
+#define	XFS_TRANS_ATRUNCATE		21
+#define	XFS_TRANS_ATTR_SET		22
+#define	XFS_TRANS_ATTR_RM		23
+#define	XFS_TRANS_ATTR_FLAG		24
+#define	XFS_TRANS_CLEAR_AGI_BUCKET	25
+#define XFS_TRANS_QM_SBCHANGE		26
+/*
+ * Dummy entries since we use the transaction type to index into the
+ * trans_type[] in xlog_recover_print_trans_head()
+ */
+#define XFS_TRANS_DUMMY1		27
+#define XFS_TRANS_DUMMY2		28
+#define XFS_TRANS_QM_QUOTAOFF		29
+#define XFS_TRANS_QM_DQALLOC		30
+#define XFS_TRANS_QM_SETQLIM		31
+#define XFS_TRANS_QM_DQCLUSTER		32
+#define XFS_TRANS_QM_QINOCREATE		33
+#define XFS_TRANS_QM_QUOTAOFF_END	34
+#define XFS_TRANS_SB_UNIT		35
+#define XFS_TRANS_FSYNC_TS		36
+#define	XFS_TRANS_GROWFSRT_ALLOC	37
+#define	XFS_TRANS_GROWFSRT_ZERO		38
+#define	XFS_TRANS_GROWFSRT_FREE		39
+#define	XFS_TRANS_SWAPEXT		40
+#define	XFS_TRANS_SB_COUNT		41
+#define	XFS_TRANS_CHECKPOINT		42
+#define	XFS_TRANS_ICREATE		43
+#define	XFS_TRANS_TYPE_MAX		43
+/* new transaction types need to be reflected in xfs_logprint(8) */
+
+#define XFS_TRANS_TYPES \
+	{ XFS_TRANS_SETATTR_NOT_SIZE,	"SETATTR_NOT_SIZE" }, \
+	{ XFS_TRANS_SETATTR_SIZE,	"SETATTR_SIZE" }, \
+	{ XFS_TRANS_INACTIVE,		"INACTIVE" }, \
+	{ XFS_TRANS_CREATE,		"CREATE" }, \
+	{ XFS_TRANS_CREATE_TRUNC,	"CREATE_TRUNC" }, \
+	{ XFS_TRANS_TRUNCATE_FILE,	"TRUNCATE_FILE" }, \
+	{ XFS_TRANS_REMOVE,		"REMOVE" }, \
+	{ XFS_TRANS_LINK,		"LINK" }, \
+	{ XFS_TRANS_RENAME,		"RENAME" }, \
+	{ XFS_TRANS_MKDIR,		"MKDIR" }, \
+	{ XFS_TRANS_RMDIR,		"RMDIR" }, \
+	{ XFS_TRANS_SYMLINK,		"SYMLINK" }, \
+	{ XFS_TRANS_SET_DMATTRS,	"SET_DMATTRS" }, \
+	{ XFS_TRANS_GROWFS,		"GROWFS" }, \
+	{ XFS_TRANS_STRAT_WRITE,	"STRAT_WRITE" }, \
+	{ XFS_TRANS_DIOSTRAT,		"DIOSTRAT" }, \
+	{ XFS_TRANS_WRITEID,		"WRITEID" }, \
+	{ XFS_TRANS_ADDAFORK,		"ADDAFORK" }, \
+	{ XFS_TRANS_ATTRINVAL,		"ATTRINVAL" }, \
+	{ XFS_TRANS_ATRUNCATE,		"ATRUNCATE" }, \
+	{ XFS_TRANS_ATTR_SET,		"ATTR_SET" }, \
+	{ XFS_TRANS_ATTR_RM,		"ATTR_RM" }, \
+	{ XFS_TRANS_ATTR_FLAG,		"ATTR_FLAG" }, \
+	{ XFS_TRANS_CLEAR_AGI_BUCKET,	"CLEAR_AGI_BUCKET" }, \
+	{ XFS_TRANS_QM_SBCHANGE,	"QM_SBCHANGE" }, \
+	{ XFS_TRANS_QM_QUOTAOFF,	"QM_QUOTAOFF" }, \
+	{ XFS_TRANS_QM_DQALLOC,		"QM_DQALLOC" }, \
+	{ XFS_TRANS_QM_SETQLIM,		"QM_SETQLIM" }, \
+	{ XFS_TRANS_QM_DQCLUSTER,	"QM_DQCLUSTER" }, \
+	{ XFS_TRANS_QM_QINOCREATE,	"QM_QINOCREATE" }, \
+	{ XFS_TRANS_QM_QUOTAOFF_END,	"QM_QOFF_END" }, \
+	{ XFS_TRANS_SB_UNIT,		"SB_UNIT" }, \
+	{ XFS_TRANS_FSYNC_TS,		"FSYNC_TS" }, \
+	{ XFS_TRANS_GROWFSRT_ALLOC,	"GROWFSRT_ALLOC" }, \
+	{ XFS_TRANS_GROWFSRT_ZERO,	"GROWFSRT_ZERO" }, \
+	{ XFS_TRANS_GROWFSRT_FREE,	"GROWFSRT_FREE" }, \
+	{ XFS_TRANS_SWAPEXT,		"SWAPEXT" }, \
+	{ XFS_TRANS_SB_COUNT,		"SB_COUNT" }, \
+	{ XFS_TRANS_CHECKPOINT,		"CHECKPOINT" }, \
+	{ XFS_TRANS_DUMMY1,		"DUMMY1" }, \
+	{ XFS_TRANS_DUMMY2,		"DUMMY2" }, \
+	{ XLOG_UNMOUNT_REC_TYPE,	"UNMOUNT" }
+
+/*
+ * This structure is used to track log items associated with
+ * a transaction.  It points to the log item and keeps some
+ * flags to track the state of the log item.  It also tracks
+ * the amount of space needed to log the item it describes
+ * once we get to commit processing (see xfs_trans_commit()).
+ */
+struct xfs_log_item_desc {
+	struct xfs_log_item	*lid_item;
+	struct list_head	lid_trans;
+	unsigned char		lid_flags;
+};
+
+#define XFS_LID_DIRTY		0x1
+
+/* log size calculation functions */
+int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
+int	xfs_log_calc_minimum_size(struct xfs_mount *);
+
+
+/*
+ * Values for t_flags.
+ */
+#define	XFS_TRANS_DIRTY		0x01	/* something needs to be logged */
+#define	XFS_TRANS_SB_DIRTY	0x02	/* superblock is modified */
+#define	XFS_TRANS_PERM_LOG_RES	0x04	/* xact took a permanent log res */
+#define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
+#define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
+#define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
+#define XFS_TRANS_FREEZE_PROT	0x40	/* Transaction has elevated writer
+					   count in superblock */
+/*
+ * Values for call flags parameter.
+ */
+#define	XFS_TRANS_RELEASE_LOG_RES	0x4
+#define	XFS_TRANS_ABORT			0x8
+
+/*
+ * Field values for xfs_trans_mod_sb.
+ */
+#define	XFS_TRANS_SB_ICOUNT		0x00000001
+#define	XFS_TRANS_SB_IFREE		0x00000002
+#define	XFS_TRANS_SB_FDBLOCKS		0x00000004
+#define	XFS_TRANS_SB_RES_FDBLOCKS	0x00000008
+#define	XFS_TRANS_SB_FREXTENTS		0x00000010
+#define	XFS_TRANS_SB_RES_FREXTENTS	0x00000020
+#define	XFS_TRANS_SB_DBLOCKS		0x00000040
+#define	XFS_TRANS_SB_AGCOUNT		0x00000080
+#define	XFS_TRANS_SB_IMAXPCT		0x00000100
+#define	XFS_TRANS_SB_REXTSIZE		0x00000200
+#define	XFS_TRANS_SB_RBMBLOCKS		0x00000400
+#define	XFS_TRANS_SB_RBLOCKS		0x00000800
+#define	XFS_TRANS_SB_REXTENTS		0x00001000
+#define	XFS_TRANS_SB_REXTSLOG		0x00002000
+
+/*
+ * Here we centralize the specification of XFS meta-data buffer reference count
+ * values.  This determine how hard the buffer cache tries to hold onto the
+ * buffer.
+ */
+#define	XFS_AGF_REF		4
+#define	XFS_AGI_REF		4
+#define	XFS_AGFL_REF		3
+#define	XFS_INO_BTREE_REF	3
+#define	XFS_ALLOC_BTREE_REF	2
+#define	XFS_BMAP_BTREE_REF	2
+#define	XFS_DIR_BTREE_REF	2
+#define	XFS_INO_REF		2
+#define	XFS_ATTR_BTREE_REF	1
+#define	XFS_DQUOT_REF		1
+
+/*
+ * Flags for xfs_trans_ichgtime().
+ */
+#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
+#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
+#define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */
+
+
+/*
+ * Symlink decoding/encoding functions

include/xfs_shared.h line 244

Quoted 10 lines
include/xfs_shared.h new file +10 -0
+ */
+int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
+int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
+				 struct xfs_inode *ip, struct xfs_ifork *ifp);
+
+#endif /* __XFS_SHARED_H__ */

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#26 lore raw

Re: [PATCH 08/32] xfs: create a shared header file for format-related information

In reply to Dave Chinner

This has been committed.

Thanks
--Rich

commit dd297fd6d366f62ca2f579e510e6287699d0bd5d

Author: Dave Chinner <[email protected]>
Date:   Mon Sep 30 03:15:20 2013 +0000

xfs: create a shared header file for format-related information

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#27 lore raw

Re: [PATCH 08/32] xfs: create a shared header file for format-related information

Quoted 10 lines · Rich Johnston

This has been committed.

Thanks
--Rich

commit dd297fd6d366f62ca2f579e510e6287699d0bd5d

Author: Dave Chinner <[email protected]>
Date:   Mon Sep 30 03:15:20 2013 +0000

xfs: create a shared header file for format-related information

Rich, none of the kernel patches for this rework have been committed yet. I appreciate you catching up on outstanding patches, but lets not jump the gun completely by commit stuff to userspace that isn't yet in the kernel tree.

As it is, the last version of the kernel patch for this change was slightly modified due to review comments, which is why we should be waiting for the kernel commits to shared files before finalising and committing the userspace patches...

Cheers,

Dave.

Signature · 7 lines
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#28 lore raw

Re: [PATCH 08/32] xfs: create a shared header file for format-related information

Sorry that's why I responded to the wrong thread for patch 07/32

Quoted 17 lines · Dave Chinner
Quoted 10 lines · Rich Johnston

This has been committed.

Thanks
--Rich

commit dd297fd6d366f62ca2f579e510e6287699d0bd5d

Author: Dave Chinner <[email protected]>
Date:   Mon Sep 30 03:15:20 2013 +0000

xfs: create a shared header file for format-related information

Rich, none of the kernel patches for this rework have been committed yet. I appreciate you catching up on outstanding patches, but lets not jump the gun completely by commit stuff to userspace that isn't yet in the kernel tree.

Quoted 9 lines

As it is, the last version of the kernel patch for this change was slightly modified due to review comments, which is why we should be waiting for the kernel commits to shared files before finalising and committing the userspace patches...

Cheers,

Dave.

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#29 lore raw

Re: [PATCH 08/32] xfs: create a shared header file for format-related information

In reply to Dave Chinner
Quoted 17 lines · Dave Chinner
Quoted 10 lines · Rich Johnston

This has been committed.

Thanks
--Rich

commit dd297fd6d366f62ca2f579e510e6287699d0bd5d

Author: Dave Chinner <[email protected]>
Date:   Mon Sep 30 03:15:20 2013 +0000

xfs: create a shared header file for format-related information

Rich, none of the kernel patches for this rework have been committed yet. I appreciate you catching up on outstanding patches, but lets not jump the gun completely by commit stuff to userspace that isn't yet in the kernel tree.

Quoted 9 lines

As it is, the last version of the kernel patch for this change was slightly modified due to review comments, which is why we should be waiting for the kernel commits to shared files before finalising and committing the userspace patches...

Cheers,

Dave.

commit 77d8143bd059f6da43b46cadaa6a96c3d4573d9c

Author: Rich Johnston <[email protected]>
Date:   Tue Oct 22 13:04:53 2013 -0500

Revert "xfs: create a shared header file for format-related
information"

This reverts commit dd297fd6d366f62ca2f579e510e6287699d0bd5d.

Wait for the kernel commits to shared files before finalising and committing the userspace patches.

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#30 lore raw

PATCH 9/32 xfs: unify directory/attribute format definitions

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

The on-disk format definitions for the directory and attribute structures are spread across 3 header files right now, only one of which is dedicated to defining on-disk structures and their manipulation (xfs_dir2_format.h). Pull all the format definitions into a single header file - xfs_da_format.h - and switch all the code over to point at that.

---
 include/Makefile          |    4 +-
 include/libxfs.h          |    6 +-
 include/xfs_attr_leaf.h   |  230 --------
 include/xfs_attr_remote.h |   27 -
 include/xfs_da_btree.h    |  140 -----
 include/xfs_da_format.h   | 1362 +++++++++++++++++++++++++++++++++++++++++++++
 include/xfs_dir2_format.h |  964 --------------------------------
 7 files changed, 1368 insertions(+), 1365 deletions(-)
 create mode 100644 include/xfs_da_format.h
 delete mode 100644 include/xfs_dir2_format.h
include/Makefile +3 -1
index fd2d61b..6682b9d 100644
@@ -26,7 +26,9 @@ QAHFILES = libxfs.h libxlog.h \
 	xfs_btree_trace.h \
 	xfs_cksum.h \
 	xfs_da_btree.h \
-	xfs_dinode.h xfs_dir2.h xfs_dir2_format.h \
+	xfs_da_format.h \
+	xfs_dinode.h \
+	xfs_dir2.h \
 	xfs_format.h \
 	xfs_ialloc.h \
 	xfs_ialloc_btree.h \
include/libxfs.h +3 -3
index a5d6388..835ba37 100644
@@ -47,7 +47,6 @@
 #include <xfs/xfs_inum.h>
 #include <xfs/xfs_sb.h>
 #include <xfs/xfs_ag.h>
-#include <xfs/xfs_da_btree.h>
 #include <xfs/xfs_bmap_btree.h>
 #include <xfs/xfs_alloc_btree.h>
 #include <xfs/xfs_ialloc_btree.h>
@@ -267,9 +266,10 @@ extern void	libxfs_umount (xfs_mount_t *);
 extern void	libxfs_rtmount_destroy (xfs_mount_t *);
 
 /*
- * xfs/xfs_dir2_format.h needs struct xfs_mount to be defined
+ * xfs/xfs_da_format.h needs struct xfs_mount to be defined
  */
-#include <xfs/xfs_dir2_format.h>
+#include <xfs/xfs_da_format.h>
+#include <xfs/xfs_da_btree.h>
 #include <xfs/xfs_dir2.h>
 
 /*
include/xfs_attr_leaf.h +0 -230

242 lines not on this page · raw message

include/xfs_attr_remote.h +0 -27
index b3e1e1b..5a9acfa 100644
@@ -18,33 +18,6 @@
 #ifndef __XFS_ATTR_REMOTE_H__
 #define	__XFS_ATTR_REMOTE_H__
 
-#define XFS_ATTR3_RMT_MAGIC	0x5841524d	/* XARM */
-
-/*
- * There is one of these headers per filesystem block in a remote attribute.
- * This is done to ensure there is a 1:1 mapping between the attribute value
- * length and the number of blocks needed to store the attribute. This makes the
- * verification of a buffer a little more complex, but greatly simplifies the
- * allocation, reading and writing of these attributes as we don't have to guess
- * the number of blocks needed to store the attribute data.
- */
-struct xfs_attr3_rmt_hdr {
-	__be32	rm_magic;
-	__be32	rm_offset;
-	__be32	rm_bytes;
-	__be32	rm_crc;
-	uuid_t	rm_uuid;
-	__be64	rm_owner;
-	__be64	rm_blkno;
-	__be64	rm_lsn;
-};
-
-#define XFS_ATTR3_RMT_CRC_OFF	offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
-
-#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize)	\
-	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
-			sizeof(struct xfs_attr3_rmt_hdr) : 0))
-
 int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
include/xfs_da_btree.h +0 -140

146 lines not on this page · raw message

include/xfs_da_format.h new file +1362 -0

1,362 lines not on this page · raw message

include/xfs_dir2_format.h deleted +0 -964

964 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Reviewed-by on v1 9/32
#31 lore raw

Re: [PATCH 09/32] xfs: unify directory/attribute format definitions

Quoted 10 lines · Dave Chinner

From: Dave Chinner <[email protected]>

The on-disk format definitions for the directory and attribute structures are spread across 3 header files right now, only one of which is dedicated to defining on-disk structures and their manipulation (xfs_dir2_format.h). Pull all the format definitions into a single header file - xfs_da_format.h - and switch all the code over to point at that.

Quoted 2,818 lines
---
 include/Makefile          |    4 +-
 include/libxfs.h          |    6 +-
 include/xfs_attr_leaf.h   |  230 --------
 include/xfs_attr_remote.h |   27 -
 include/xfs_da_btree.h    |  140 -----
 include/xfs_da_format.h   | 1362 +++++++++++++++++++++++++++++++++++++++++++++
 include/xfs_dir2_format.h |  964 --------------------------------
 7 files changed, 1368 insertions(+), 1365 deletions(-)
 create mode 100644 include/xfs_da_format.h
 delete mode 100644 include/xfs_dir2_format.h
include/Makefile +3 -1
index fd2d61b..6682b9d 100644
@@ -26,7 +26,9 @@ QAHFILES = libxfs.h libxlog.h \
 	xfs_btree_trace.h \
 	xfs_cksum.h \
 	xfs_da_btree.h \
-	xfs_dinode.h xfs_dir2.h xfs_dir2_format.h \
+	xfs_da_format.h \
+	xfs_dinode.h \
+	xfs_dir2.h \
 	xfs_format.h \
 	xfs_ialloc.h \
 	xfs_ialloc_btree.h \
include/libxfs.h +3 -3
index a5d6388..835ba37 100644
@@ -47,7 +47,6 @@
 #include <xfs/xfs_inum.h>
 #include <xfs/xfs_sb.h>
 #include <xfs/xfs_ag.h>
-#include <xfs/xfs_da_btree.h>
 #include <xfs/xfs_bmap_btree.h>
 #include <xfs/xfs_alloc_btree.h>
 #include <xfs/xfs_ialloc_btree.h>
@@ -267,9 +266,10 @@ extern void	libxfs_umount (xfs_mount_t *);
 extern void	libxfs_rtmount_destroy (xfs_mount_t *);
 
 /*
- * xfs/xfs_dir2_format.h needs struct xfs_mount to be defined
+ * xfs/xfs_da_format.h needs struct xfs_mount to be defined
  */
-#include <xfs/xfs_dir2_format.h>
+#include <xfs/xfs_da_format.h>
+#include <xfs/xfs_da_btree.h>
 #include <xfs/xfs_dir2.h>
 
 /*
include/xfs_attr_leaf.h +0 -230
index da34e64..3ec5ec0 100644
@@ -19,16 +19,6 @@
 #ifndef __XFS_ATTR_LEAF_H__
 #define	__XFS_ATTR_LEAF_H__
 
-/*
- * Attribute storage layout, internal structure, access macros, etc.
- *
- * Attribute lists are structured around Btrees where all the data
- * elements are in the leaf nodes.  Attribute names are hashed into an int,
- * then that int is used as the index into the Btree.  Since the hashval
- * of an attribute name may not be unique, we may have duplicate keys.  The
- * internal links in the Btree are logical block offsets into the file.
- */
-
 struct attrlist;
 struct attrlist_cursor_kern;
 struct xfs_attr_list_context;
@@ -38,226 +28,6 @@ struct xfs_da_state_blk;
 struct xfs_inode;
 struct xfs_trans;
 
-/*========================================================================
- * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
-/*
- * This is the structure of the leaf nodes in the Btree.
- *
- * Struct leaf_entry's are packed from the top.  Name/values grow from the
- * bottom but are not packed.  The freemap contains run-length-encoded entries
- * for the free bytes after the leaf_entry's, but only the N largest such,
- * smaller runs are dropped.  When the freemap doesn't show enough space
- * for an allocation, we compact the name/value area and try again.  If we
- * still don't have enough space, then we have to split the block.  The
- * name/value structs (both local and remote versions) must be 32bit aligned.
- *
- * Since we have duplicate hash keys, for each key that matches, compare
- * the actual name string.  The root and intermediate node search always
- * takes the first-in-the-block key match found, so we should only have
- * to work "forw"ard.  If none matches, continue with the "forw"ard leaf
- * nodes until the hash key changes or the attribute name is found.
- *
- * We store the fact that an attribute is a ROOT/USER/SECURE attribute in
- * the leaf_entry.  The namespaces are independent only because we also look
- * at the namespace bit when we are looking for a matching attribute name.
- *
- * We also store an "incomplete" bit in the leaf_entry.  It shows that an
- * attribute is in the middle of being created and should not be shown to
- * the user if we crash during the time that the bit is set.  We clear the
- * bit when we have finished setting up the attribute.  We do this because
- * we cannot create some large attributes inside a single transaction, and we
- * need some indication that we weren't finished if we crash in the middle.
- */
-#define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
-
-typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
-	__be16	base;			  /* base of free region */
-	__be16	size;			  /* length of free region */
-} xfs_attr_leaf_map_t;
-
-typedef struct xfs_attr_leaf_hdr {	/* constant-structure header block */
-	xfs_da_blkinfo_t info;		/* block type, links, etc. */
-	__be16	count;			/* count of active leaf_entry's */
-	__be16	usedbytes;		/* num bytes of names/values stored */
-	__be16	firstused;		/* first used byte in name area */
-	__u8	holes;			/* != 0 if blk needs compaction */
-	__u8	pad1;
-	xfs_attr_leaf_map_t freemap[XFS_ATTR_LEAF_MAPSIZE];
-					/* N largest free regions */
-} xfs_attr_leaf_hdr_t;
-
-typedef struct xfs_attr_leaf_entry {	/* sorted on key, not name */
-	__be32	hashval;		/* hash value of name */
-	__be16	nameidx;		/* index into buffer of name/value */
-	__u8	flags;			/* LOCAL/ROOT/SECURE/INCOMPLETE flag */
-	__u8	pad2;			/* unused pad byte */
-} xfs_attr_leaf_entry_t;
-
-typedef struct xfs_attr_leaf_name_local {
-	__be16	valuelen;		/* number of bytes in value */
-	__u8	namelen;		/* length of name bytes */
-	__u8	nameval[1];		/* name/value bytes */
-} xfs_attr_leaf_name_local_t;
-
-typedef struct xfs_attr_leaf_name_remote {
-	__be32	valueblk;		/* block number of value bytes */
-	__be32	valuelen;		/* number of bytes in value */
-	__u8	namelen;		/* length of name bytes */
-	__u8	name[1];		/* name bytes */
-} xfs_attr_leaf_name_remote_t;
-
-typedef struct xfs_attr_leafblock {
-	xfs_attr_leaf_hdr_t	hdr;	/* constant-structure header block */
-	xfs_attr_leaf_entry_t	entries[1];	/* sorted on key, not name */
-	xfs_attr_leaf_name_local_t namelist;	/* grows from bottom of buf */
-	xfs_attr_leaf_name_remote_t valuelist;	/* grows from bottom of buf */
-} xfs_attr_leafblock_t;
-
-/*
- * CRC enabled leaf structures. Called "version 3" structures to match the
- * version number of the directory and dablk structures for this feature, and
- * attr2 is already taken by the variable inode attribute fork size feature.
- */
-struct xfs_attr3_leaf_hdr {
-	struct xfs_da3_blkinfo	info;
-	__be16			count;
-	__be16			usedbytes;
-	__be16			firstused;
-	__u8			holes;
-	__u8			pad1;
-	struct xfs_attr_leaf_map freemap[XFS_ATTR_LEAF_MAPSIZE];
-	__be32			pad2;		/* 64 bit alignment */
-};
-
-#define XFS_ATTR3_LEAF_CRC_OFF	(offsetof(struct xfs_attr3_leaf_hdr, info.crc))
-
-struct xfs_attr3_leafblock {
-	struct xfs_attr3_leaf_hdr	hdr;
-	struct xfs_attr_leaf_entry	entries[1];
-
-	/*
-	 * The rest of the block contains the following structures after the
-	 * leaf entries, growing from the bottom up. The variables are never
-	 * referenced, the locations accessed purely from helper functions.
-	 *
-	 * struct xfs_attr_leaf_name_local
-	 * struct xfs_attr_leaf_name_remote
-	 */
-};
-
-/*
- * incore, neutral version of the attribute leaf header
- */
-struct xfs_attr3_icleaf_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	usedbytes;
-	__uint16_t	firstused;
-	__u8		holes;
-	struct {
-		__uint16_t	base;
-		__uint16_t	size;
-	} freemap[XFS_ATTR_LEAF_MAPSIZE];
-};
-
-/*
- * Flags used in the leaf_entry[i].flags field.
- * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
- * on the system call, they are "or"ed together for various operations.
- */
-#define	XFS_ATTR_LOCAL_BIT	0	/* attr is stored locally */
-#define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */
-#define	XFS_ATTR_SECURE_BIT	2	/* limit access to secure attrs */
-#define	XFS_ATTR_INCOMPLETE_BIT	7	/* attr in middle of create/delete */
-#define XFS_ATTR_LOCAL		(1 << XFS_ATTR_LOCAL_BIT)
-#define XFS_ATTR_ROOT		(1 << XFS_ATTR_ROOT_BIT)
-#define XFS_ATTR_SECURE		(1 << XFS_ATTR_SECURE_BIT)
-#define XFS_ATTR_INCOMPLETE	(1 << XFS_ATTR_INCOMPLETE_BIT)
-
-/*
- * Conversion macros for converting namespace bits from argument flags
- * to ondisk flags.
- */
-#define XFS_ATTR_NSP_ARGS_MASK		(ATTR_ROOT | ATTR_SECURE)
-#define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
-#define XFS_ATTR_NSP_ONDISK(flags)	((flags) & XFS_ATTR_NSP_ONDISK_MASK)
-#define XFS_ATTR_NSP_ARGS(flags)	((flags) & XFS_ATTR_NSP_ARGS_MASK)
-#define XFS_ATTR_NSP_ARGS_TO_ONDISK(x)	(((x) & ATTR_ROOT ? XFS_ATTR_ROOT : 0) |\
-					 ((x) & ATTR_SECURE ? XFS_ATTR_SECURE : 0))
-#define XFS_ATTR_NSP_ONDISK_TO_ARGS(x)	(((x) & XFS_ATTR_ROOT ? ATTR_ROOT : 0) |\
-					 ((x) & XFS_ATTR_SECURE ? ATTR_SECURE : 0))
-
-/*
- * Alignment for namelist and valuelist entries (since they are mixed
- * there can be only one alignment value)
- */
-#define	XFS_ATTR_LEAF_NAME_ALIGN	((uint)sizeof(xfs_dablk_t))
-
-static inline int
-xfs_attr3_leaf_hdr_size(struct xfs_attr_leafblock *leafp)
-{
-	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
-		return sizeof(struct xfs_attr3_leaf_hdr);
-	return sizeof(struct xfs_attr_leaf_hdr);
-}
-
-static inline struct xfs_attr_leaf_entry *
-xfs_attr3_leaf_entryp(xfs_attr_leafblock_t *leafp)
-{
-	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
-		return &((struct xfs_attr3_leafblock *)leafp)->entries[0];
-	return &leafp->entries[0];
-}
-
-/*
- * Cast typed pointers for "local" and "remote" name/value structs.
- */
-static inline char *
-xfs_attr3_leaf_name(xfs_attr_leafblock_t *leafp, int idx)
-{
-	struct xfs_attr_leaf_entry *entries = xfs_attr3_leaf_entryp(leafp);
-
-	return &((char *)leafp)[be16_to_cpu(entries[idx].nameidx)];
-}
-
-static inline xfs_attr_leaf_name_remote_t *
-xfs_attr3_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx)
-{
-	return (xfs_attr_leaf_name_remote_t *)xfs_attr3_leaf_name(leafp, idx);
-}
-
-static inline xfs_attr_leaf_name_local_t *
-xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
-{
-	return (xfs_attr_leaf_name_local_t *)xfs_attr3_leaf_name(leafp, idx);
-}
-
-/*
- * Calculate total bytes used (including trailing pad for alignment) for
- * a "local" name/value structure, a "remote" name/value structure, and
- * a pointer which might be either.
- */
-static inline int xfs_attr_leaf_entsize_remote(int nlen)
-{
-	return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
-		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
-}
-
-static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
-{
-	return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
-		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
-}
-
-static inline int xfs_attr_leaf_entsize_local_max(int bsize)
-{
-	return (((bsize) >> 1) + ((bsize) >> 2));
-}
-
 /*
  * Used to keep a list of "remote value" extents when unlinking an inode.
  */
include/xfs_attr_remote.h +0 -27
index b3e1e1b..5a9acfa 100644
@@ -18,33 +18,6 @@
 #ifndef __XFS_ATTR_REMOTE_H__
 #define	__XFS_ATTR_REMOTE_H__
 
-#define XFS_ATTR3_RMT_MAGIC	0x5841524d	/* XARM */
-
-/*
- * There is one of these headers per filesystem block in a remote attribute.
- * This is done to ensure there is a 1:1 mapping between the attribute value
- * length and the number of blocks needed to store the attribute. This makes the
- * verification of a buffer a little more complex, but greatly simplifies the
- * allocation, reading and writing of these attributes as we don't have to guess
- * the number of blocks needed to store the attribute data.
- */
-struct xfs_attr3_rmt_hdr {
-	__be32	rm_magic;
-	__be32	rm_offset;
-	__be32	rm_bytes;
-	__be32	rm_crc;
-	uuid_t	rm_uuid;
-	__be64	rm_owner;
-	__be64	rm_blkno;
-	__be64	rm_lsn;
-};
-
-#define XFS_ATTR3_RMT_CRC_OFF	offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
-
-#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize)	\
-	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
-			sizeof(struct xfs_attr3_rmt_hdr) : 0))
-
 int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
include/xfs_da_btree.h +0 -140
index a762cfa..e492dca 100644
@@ -25,146 +25,6 @@ struct xfs_trans;
 struct zone;
 
 /*========================================================================
- * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
-/*
- * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
- *
- * It is used to manage a doubly linked list of all blocks at the same
- * level in the Btree, and to identify which type of block this is.
- */
-#define XFS_DA_NODE_MAGIC	0xfebe	/* magic number: non-leaf blocks */
-#define XFS_ATTR_LEAF_MAGIC	0xfbee	/* magic number: attribute leaf blks */
-#define	XFS_DIR2_LEAF1_MAGIC	0xd2f1	/* magic number: v2 dirlf single blks */
-#define	XFS_DIR2_LEAFN_MAGIC	0xd2ff	/* magic number: v2 dirlf multi blks */
-
-typedef struct xfs_da_blkinfo {
-	__be32		forw;			/* previous block in list */
-	__be32		back;			/* following block in list */
-	__be16		magic;			/* validity check on block */
-	__be16		pad;			/* unused */
-} xfs_da_blkinfo_t;
-
-/*
- * CRC enabled directory structure types
- *
- * The headers change size for the additional verification information, but
- * otherwise the tree layouts and contents are unchanged. Hence the da btree
- * code can use the struct xfs_da_blkinfo for manipulating the tree links and
- * magic numbers without modification for both v2 and v3 nodes.
- */
-#define XFS_DA3_NODE_MAGIC	0x3ebe	/* magic number: non-leaf blocks */
-#define XFS_ATTR3_LEAF_MAGIC	0x3bee	/* magic number: attribute leaf blks */
-#define	XFS_DIR3_LEAF1_MAGIC	0x3df1	/* magic number: v2 dirlf single blks */
-#define	XFS_DIR3_LEAFN_MAGIC	0x3dff	/* magic number: v2 dirlf multi blks */
-
-struct xfs_da3_blkinfo {
-	/*
-	 * the node link manipulation code relies on the fact that the first
-	 * element of this structure is the struct xfs_da_blkinfo so it can
-	 * ignore the differences in the rest of the structures.
-	 */
-	struct xfs_da_blkinfo	hdr;
-	__be32			crc;	/* CRC of block */
-	__be64			blkno;	/* first block of the buffer */
-	__be64			lsn;	/* sequence number of last write */
-	uuid_t			uuid;	/* filesystem we belong to */
-	__be64			owner;	/* inode that owns the block */
-};
-
-/*
- * This is the structure of the root and intermediate nodes in the Btree.
- * The leaf nodes are defined above.
- *
- * Entries are not packed.
- *
- * Since we have duplicate keys, use a binary search but always follow
- * all match in the block, not just the first match found.
- */
-#define	XFS_DA_NODE_MAXDEPTH	5	/* max depth of Btree */
-
-typedef struct xfs_da_node_hdr {
-	struct xfs_da_blkinfo	info;	/* block type, links, etc. */
-	__be16			__count; /* count of active entries */
-	__be16			__level; /* level above leaves (leaf == 0) */
-} xfs_da_node_hdr_t;
-
-struct xfs_da3_node_hdr {
-	struct xfs_da3_blkinfo	info;	/* block type, links, etc. */
-	__be16			__count; /* count of active entries */
-	__be16			__level; /* level above leaves (leaf == 0) */
-	__be32			__pad32;
-};
-
-#define XFS_DA3_NODE_CRC_OFF	(offsetof(struct xfs_da3_node_hdr, info.crc))
-
-typedef struct xfs_da_node_entry {
-	__be32	hashval;	/* hash value for this descendant */
-	__be32	before;		/* Btree block before this key */
-} xfs_da_node_entry_t;
-
-typedef struct xfs_da_intnode {
-	struct xfs_da_node_hdr	hdr;
-	struct xfs_da_node_entry __btree[];
-} xfs_da_intnode_t;
-
-struct xfs_da3_intnode {
-	struct xfs_da3_node_hdr	hdr;
-	struct xfs_da_node_entry __btree[];
-};
-
-/*
- * In-core version of the node header to abstract the differences in the v2 and
- * v3 disk format of the headers. Callers need to convert to/from disk format as
- * appropriate.
- */
-struct xfs_da3_icnode_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	level;
-};
-
-extern void xfs_da3_node_hdr_from_disk(struct xfs_da3_icnode_hdr *to,
-				       struct xfs_da_intnode *from);
-extern void xfs_da3_node_hdr_to_disk(struct xfs_da_intnode *to,
-				     struct xfs_da3_icnode_hdr *from);
-
-static inline int
-__xfs_da3_node_hdr_size(bool v3)
-{
-	if (v3)
-		return sizeof(struct xfs_da3_node_hdr);
-	return sizeof(struct xfs_da_node_hdr);
-}
-static inline int
-xfs_da3_node_hdr_size(struct xfs_da_intnode *dap)
-{
-	bool	v3 = dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC);
-
-	return __xfs_da3_node_hdr_size(v3);
-}
-
-static inline struct xfs_da_node_entry *
-xfs_da3_node_tree_p(struct xfs_da_intnode *dap)
-{
-	if (dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
-		struct xfs_da3_intnode *dap3 = (struct xfs_da3_intnode *)dap;
-		return dap3->__btree;
-	}
-	return dap->__btree;
-}
-
-extern void xfs_da3_intnode_from_disk(struct xfs_da3_icnode_hdr *to,
-				      struct xfs_da_intnode *from);
-extern void xfs_da3_intnode_to_disk(struct xfs_da_intnode *to,
-				    struct xfs_da3_icnode_hdr *from);
-
-#define	XFS_LBSIZE(mp)	(mp)->m_sb.sb_blocksize
-
-/*========================================================================
  * Btree searching and modification structure definitions.
  *========================================================================*/
 
include/xfs_da_format.h new file +1362 -0
new file mode 100644
index 0000000..89a1a21
@@ -0,0 +1,1362 @@
+/*
+ * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_DA_FORMAT_H__
+#define __XFS_DA_FORMAT_H__
+
+/*========================================================================
+ * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
+ *========================================================================*/
+
+/*
+ * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
+ *
+ * It is used to manage a doubly linked list of all blocks at the same
+ * level in the Btree, and to identify which type of block this is.
+ */
+#define XFS_DA_NODE_MAGIC	0xfebe	/* magic number: non-leaf blocks */
+#define XFS_ATTR_LEAF_MAGIC	0xfbee	/* magic number: attribute leaf blks */
+#define	XFS_DIR2_LEAF1_MAGIC	0xd2f1	/* magic number: v2 dirlf single blks */
+#define	XFS_DIR2_LEAFN_MAGIC	0xd2ff	/* magic number: v2 dirlf multi blks */
+
+typedef struct xfs_da_blkinfo {
+	__be32		forw;			/* previous block in list */
+	__be32		back;			/* following block in list */
+	__be16		magic;			/* validity check on block */
+	__be16		pad;			/* unused */
+} xfs_da_blkinfo_t;
+
+/*
+ * CRC enabled directory structure types
+ *
+ * The headers change size for the additional verification information, but
+ * otherwise the tree layouts and contents are unchanged. Hence the da btree
+ * code can use the struct xfs_da_blkinfo for manipulating the tree links and
+ * magic numbers without modification for both v2 and v3 nodes.
+ */
+#define XFS_DA3_NODE_MAGIC	0x3ebe	/* magic number: non-leaf blocks */
+#define XFS_ATTR3_LEAF_MAGIC	0x3bee	/* magic number: attribute leaf blks */
+#define	XFS_DIR3_LEAF1_MAGIC	0x3df1	/* magic number: v2 dirlf single blks */
+#define	XFS_DIR3_LEAFN_MAGIC	0x3dff	/* magic number: v2 dirlf multi blks */
+
+struct xfs_da3_blkinfo {
+	/*
+	 * the node link manipulation code relies on the fact that the first
+	 * element of this structure is the struct xfs_da_blkinfo so it can
+	 * ignore the differences in the rest of the structures.
+	 */
+	struct xfs_da_blkinfo	hdr;
+	__be32			crc;	/* CRC of block */
+	__be64			blkno;	/* first block of the buffer */
+	__be64			lsn;	/* sequence number of last write */
+	uuid_t			uuid;	/* filesystem we belong to */
+	__be64			owner;	/* inode that owns the block */
+};
+
+/*
+ * This is the structure of the root and intermediate nodes in the Btree.
+ * The leaf nodes are defined above.
+ *
+ * Entries are not packed.
+ *
+ * Since we have duplicate keys, use a binary search but always follow
+ * all match in the block, not just the first match found.
+ */
+#define	XFS_DA_NODE_MAXDEPTH	5	/* max depth of Btree */
+
+typedef struct xfs_da_node_hdr {
+	struct xfs_da_blkinfo	info;	/* block type, links, etc. */
+	__be16			__count; /* count of active entries */
+	__be16			__level; /* level above leaves (leaf == 0) */
+} xfs_da_node_hdr_t;
+
+struct xfs_da3_node_hdr {
+	struct xfs_da3_blkinfo	info;	/* block type, links, etc. */
+	__be16			__count; /* count of active entries */
+	__be16			__level; /* level above leaves (leaf == 0) */
+	__be32			__pad32;
+};
+
+#define XFS_DA3_NODE_CRC_OFF	(offsetof(struct xfs_da3_node_hdr, info.crc))
+
+typedef struct xfs_da_node_entry {
+	__be32	hashval;	/* hash value for this descendant */
+	__be32	before;		/* Btree block before this key */
+} xfs_da_node_entry_t;
+
+typedef struct xfs_da_intnode {
+	struct xfs_da_node_hdr	hdr;
+	struct xfs_da_node_entry __btree[];
+} xfs_da_intnode_t;
+
+struct xfs_da3_intnode {
+	struct xfs_da3_node_hdr	hdr;
+	struct xfs_da_node_entry __btree[];
+};
+
+/*
+ * In-core version of the node header to abstract the differences in the v2 and
+ * v3 disk format of the headers. Callers need to convert to/from disk format as
+ * appropriate.
+ */
+struct xfs_da3_icnode_hdr {
+	__uint32_t	forw;
+	__uint32_t	back;
+	__uint16_t	magic;
+	__uint16_t	count;
+	__uint16_t	level;
+};
+
+extern void xfs_da3_node_hdr_from_disk(struct xfs_da3_icnode_hdr *to,
+				       struct xfs_da_intnode *from);
+extern void xfs_da3_node_hdr_to_disk(struct xfs_da_intnode *to,
+				     struct xfs_da3_icnode_hdr *from);
+
+static inline int
+__xfs_da3_node_hdr_size(bool v3)
+{
+	if (v3)
+		return sizeof(struct xfs_da3_node_hdr);
+	return sizeof(struct xfs_da_node_hdr);
+}
+static inline int
+xfs_da3_node_hdr_size(struct xfs_da_intnode *dap)
+{
+	bool	v3 = dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC);
+
+	return __xfs_da3_node_hdr_size(v3);
+}
+
+static inline struct xfs_da_node_entry *
+xfs_da3_node_tree_p(struct xfs_da_intnode *dap)
+{
+	if (dap->hdr.info.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC)) {
+		struct xfs_da3_intnode *dap3 = (struct xfs_da3_intnode *)dap;
+		return dap3->__btree;
+	}
+	return dap->__btree;
+}
+
+extern void xfs_da3_intnode_from_disk(struct xfs_da3_icnode_hdr *to,
+				      struct xfs_da_intnode *from);
+extern void xfs_da3_intnode_to_disk(struct xfs_da_intnode *to,
+				    struct xfs_da3_icnode_hdr *from);
+
+#define	XFS_LBSIZE(mp)	(mp)->m_sb.sb_blocksize
+
+/*
+ * Directory version 2.
+ *
+ * There are 4 possible formats:
+ *  - shortform - embedded into the inode
+ *  - single block - data with embedded leaf at the end
+ *  - multiple data blocks, single leaf+freeindex block
+ *  - data blocks, node and leaf blocks (btree), freeindex blocks
+ *
+ * Note: many node blocks structures and constants are shared with the attr
+ * code and defined in xfs_da_btree.h.
+ */
+
+#define	XFS_DIR2_BLOCK_MAGIC	0x58443242	/* XD2B: single block dirs */
+#define	XFS_DIR2_DATA_MAGIC	0x58443244	/* XD2D: multiblock dirs */
+#define	XFS_DIR2_FREE_MAGIC	0x58443246	/* XD2F: free index blocks */
+
+/*
+ * Directory Version 3 With CRCs.
+ *
+ * The tree formats are the same as for version 2 directories.  The difference
+ * is in the block header and dirent formats. In many cases the v3 structures
+ * use v2 definitions as they are no different and this makes code sharing much
+ * easier.
+ *
+ * Also, the xfs_dir3_*() functions handle both v2 and v3 formats - if the
+ * format is v2 then they switch to the existing v2 code, or the format is v3
+ * they implement the v3 functionality. This means the existing dir2 is a mix of
+ * xfs_dir2/xfs_dir3 calls and functions. The xfs_dir3 functions are called
+ * where there is a difference in the formats, otherwise the code is unchanged.
+ *
+ * Where it is possible, the code decides what to do based on the magic numbers
+ * in the blocks rather than feature bits in the superblock. This means the code
+ * is as independent of the external XFS code as possible as doesn't require
+ * passing struct xfs_mount pointers into places where it isn't really
+ * necessary.
+ *
+ * Version 3 includes:
+ *
+ *	- a larger block header for CRC and identification purposes and so the
+ *	offsets of all the structures inside the blocks are different.
+ *
+ *	- new magic numbers to be able to detect the v2/v3 types on the fly.
+ */
+
+#define	XFS_DIR3_BLOCK_MAGIC	0x58444233	/* XDB3: single block dirs */
+#define	XFS_DIR3_DATA_MAGIC	0x58444433	/* XDD3: multiblock dirs */
+#define	XFS_DIR3_FREE_MAGIC	0x58444633	/* XDF3: free index blocks */
+
+/*
+ * Dirents in version 3 directories have a file type field. Additions to this
+ * list are an on-disk format change, requiring feature bits. Valid values
+ * are as follows:
+ */
+#define XFS_DIR3_FT_UNKNOWN		0
+#define XFS_DIR3_FT_REG_FILE		1
+#define XFS_DIR3_FT_DIR			2
+#define XFS_DIR3_FT_CHRDEV		3
+#define XFS_DIR3_FT_BLKDEV		4
+#define XFS_DIR3_FT_FIFO		5
+#define XFS_DIR3_FT_SOCK		6
+#define XFS_DIR3_FT_SYMLINK		7
+#define XFS_DIR3_FT_WHT			8
+
+#define XFS_DIR3_FT_MAX			9
+
+/*
+ * Byte offset in data block and shortform entry.
+ */
+typedef	__uint16_t	xfs_dir2_data_off_t;
+#define	NULLDATAOFF	0xffffU
+typedef uint		xfs_dir2_data_aoff_t;	/* argument form */
+
+/*
+ * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t.
+ * Only need 16 bits, this is the byte offset into the single block form.
+ */
+typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t;
+
+/*
+ * Offset in data space of a data entry.
+ */
+typedef	__uint32_t	xfs_dir2_dataptr_t;
+#define	XFS_DIR2_MAX_DATAPTR	((xfs_dir2_dataptr_t)0xffffffff)
+#define	XFS_DIR2_NULL_DATAPTR	((xfs_dir2_dataptr_t)0)
+
+/*
+ * Byte offset in a directory.
+ */
+typedef	xfs_off_t	xfs_dir2_off_t;
+
+/*
+ * Directory block number (logical dirblk in file)
+ */
+typedef	__uint32_t	xfs_dir2_db_t;
+
+/*
+ * Inode number stored as 8 8-bit values.
+ */
+typedef	struct { __uint8_t i[8]; } xfs_dir2_ino8_t;
+
+/*
+ * Inode number stored as 4 8-bit values.
+ * Works a lot of the time, when all the inode numbers in a directory
+ * fit in 32 bits.
+ */
+typedef struct { __uint8_t i[4]; } xfs_dir2_ino4_t;
+
+typedef union {
+	xfs_dir2_ino8_t	i8;
+	xfs_dir2_ino4_t	i4;
+} xfs_dir2_inou_t;
+#define	XFS_DIR2_MAX_SHORT_INUM	((xfs_ino_t)0xffffffffULL)
+
+/*
+ * Directory layout when stored internal to an inode.
+ *
+ * Small directories are packed as tightly as possible so as to fit into the
+ * literal area of the inode.  These "shortform" directories consist of a
+ * single xfs_dir2_sf_hdr header followed by zero or more xfs_dir2_sf_entry
+ * structures.  Due the different inode number storage size and the variable
+ * length name field in the xfs_dir2_sf_entry all these structure are
+ * variable length, and the accessors in this file should be used to iterate
+ * over them.
+ */
+typedef struct xfs_dir2_sf_hdr {
+	__uint8_t		count;		/* count of entries */
+	__uint8_t		i8count;	/* count of 8-byte inode #s */
+	xfs_dir2_inou_t		parent;		/* parent dir inode number */
+} __arch_pack xfs_dir2_sf_hdr_t;
+
+typedef struct xfs_dir2_sf_entry {
+	__u8			namelen;	/* actual name length */
+	xfs_dir2_sf_off_t	offset;		/* saved offset */
+	__u8			name[];		/* name, variable size */
+	/*
+	 * A single byte containing the file type field follows the inode
+	 * number for version 3 directory entries.
+	 *
+	 * A xfs_dir2_ino8_t or xfs_dir2_ino4_t follows here, at a
+	 * variable offset after the name.
+	 */
+} __arch_pack xfs_dir2_sf_entry_t;
+
+static inline int xfs_dir2_sf_hdr_size(int i8count)
+{
+	return sizeof(struct xfs_dir2_sf_hdr) -
+		(i8count == 0) *
+		(sizeof(xfs_dir2_ino8_t) - sizeof(xfs_dir2_ino4_t));
+}
+
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_sf_get_offset(xfs_dir2_sf_entry_t *sfep)
+{
+	return get_unaligned_be16(&sfep->offset.i);
+}
+
+static inline void
+xfs_dir2_sf_put_offset(xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t off)
+{
+	put_unaligned_be16(off, &sfep->offset.i);
+}
+
+static inline struct xfs_dir2_sf_entry *
+xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
+{
+	return (struct xfs_dir2_sf_entry *)
+		((char *)hdr + xfs_dir2_sf_hdr_size(hdr->i8count));
+}
+
+static inline int
+xfs_dir3_sf_entsize(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_sf_hdr	*hdr,
+	int			len)
+{
+	int count = sizeof(struct xfs_dir2_sf_entry); 	/* namelen + offset */
+
+	count += len;					/* name */
+	count += hdr->i8count ? sizeof(xfs_dir2_ino8_t) :
+				sizeof(xfs_dir2_ino4_t); /* ino # */
+	if (xfs_sb_version_hasftype(&mp->m_sb))
+		count += sizeof(__uint8_t);		/* file type */
+	return count;
+}
+
+static inline struct xfs_dir2_sf_entry *
+xfs_dir3_sf_nextentry(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return (struct xfs_dir2_sf_entry *)
+		((char *)sfep + xfs_dir3_sf_entsize(mp, hdr, sfep->namelen));
+}
+
+/*
+ * in dir3 shortform directories, the file type field is stored at a variable
+ * offset after the inode number. Because it's only a single byte, endian
+ * conversion is not necessary.
+ */
+static inline __uint8_t *
+xfs_dir3_sfe_ftypep(
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	return (__uint8_t *)&sfep->name[sfep->namelen];
+}
+
+static inline __uint8_t
+xfs_dir3_sfe_get_ftype(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep)
+{
+	__uint8_t	*ftp;
+
+	if (!xfs_sb_version_hasftype(&mp->m_sb))
+		return XFS_DIR3_FT_UNKNOWN;
+
+	ftp = xfs_dir3_sfe_ftypep(hdr, sfep);
+	if (*ftp >= XFS_DIR3_FT_MAX)
+		return XFS_DIR3_FT_UNKNOWN;
+	return *ftp;
+}
+
+static inline void
+xfs_dir3_sfe_put_ftype(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_sf_hdr	*hdr,
+	struct xfs_dir2_sf_entry *sfep,
+	__uint8_t		ftype)
+{
+	__uint8_t	*ftp;
+
+	ASSERT(ftype < XFS_DIR3_FT_MAX);
+
+	if (!xfs_sb_version_hasftype(&mp->m_sb))
+		return;
+	ftp = xfs_dir3_sfe_ftypep(hdr, sfep);
+	*ftp = ftype;
+}
+
+/*
+ * Data block structures.
+ *
+ * A pure data block looks like the following drawing on disk:
+ *
+ *    +-------------------------------------------------+
+ *    | xfs_dir2_data_hdr_t                             |
+ *    +-------------------------------------------------+
+ *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ *    | ...                                             |
+ *    +-------------------------------------------------+
+ *    | unused space                                    |
+ *    +-------------------------------------------------+
+ *
+ * As all the entries are variable size structures the accessors below should
+ * be used to iterate over them.
+ *
+ * In addition to the pure data blocks for the data and node formats,
+ * most structures are also used for the combined data/freespace "block"
+ * format below.
+ */
+
+#define	XFS_DIR2_DATA_ALIGN_LOG	3		/* i.e., 8 bytes */
+#define	XFS_DIR2_DATA_ALIGN	(1 << XFS_DIR2_DATA_ALIGN_LOG)
+#define	XFS_DIR2_DATA_FREE_TAG	0xffff
+#define	XFS_DIR2_DATA_FD_COUNT	3
+
+/*
+ * Directory address space divided into sections,
+ * spaces separated by 32GB.
+ */
+#define	XFS_DIR2_SPACE_SIZE	(1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
+#define	XFS_DIR2_DATA_SPACE	0
+#define	XFS_DIR2_DATA_OFFSET	(XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
+#define	XFS_DIR2_DATA_FIRSTDB(mp)	\
+	xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET)
+
+/*
+ * Describe a free area in the data block.
+ *
+ * The freespace will be formatted as a xfs_dir2_data_unused_t.
+ */
+typedef struct xfs_dir2_data_free {
+	__be16			offset;		/* start of freespace */
+	__be16			length;		/* length of freespace */
+} xfs_dir2_data_free_t;
+
+/*
+ * Header for the data blocks.
+ *
+ * The code knows that XFS_DIR2_DATA_FD_COUNT is 3.
+ */
+typedef struct xfs_dir2_data_hdr {
+	__be32			magic;		/* XFS_DIR2_DATA_MAGIC or */
+						/* XFS_DIR2_BLOCK_MAGIC */
+	xfs_dir2_data_free_t	bestfree[XFS_DIR2_DATA_FD_COUNT];
+} xfs_dir2_data_hdr_t;
+
+/*
+ * define a structure for all the verification fields we are adding to the
+ * directory block structures. This will be used in several structures.
+ * The magic number must be the first entry to align with all the dir2
+ * structures so we determine how to decode them just by the magic number.
+ */
+struct xfs_dir3_blk_hdr {
+	__be32			magic;	/* magic number */
+	__be32			crc;	/* CRC of block */
+	__be64			blkno;	/* first block of the buffer */
+	__be64			lsn;	/* sequence number of last write */
+	uuid_t			uuid;	/* filesystem we belong to */
+	__be64			owner;	/* inode that owns the block */
+};
+
+struct xfs_dir3_data_hdr {
+	struct xfs_dir3_blk_hdr	hdr;
+	xfs_dir2_data_free_t	best_free[XFS_DIR2_DATA_FD_COUNT];
+	__be32			pad;	/* 64 bit alignment */
+};
+
+#define XFS_DIR3_DATA_CRC_OFF  offsetof(struct xfs_dir3_data_hdr, hdr.crc)
+
+static inline struct xfs_dir2_data_free *
+xfs_dir3_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
+{
+	if (hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
+		struct xfs_dir3_data_hdr *hdr3 = (struct xfs_dir3_data_hdr *)hdr;
+		return hdr3->best_free;
+	}
+	return hdr->bestfree;
+}
+
+/*
+ * Active entry in a data block.
+ *
+ * Aligned to 8 bytes.  After the variable length name field there is a
+ * 2 byte tag field, which can be accessed using xfs_dir3_data_entry_tag_p.
+ *
+ * For dir3 structures, there is file type field between the name and the tag.
+ * This can only be manipulated by helper functions. It is packed hard against
+ * the end of the name so any padding for rounding is between the file type and
+ * the tag.
+ */
+typedef struct xfs_dir2_data_entry {
+	__be64			inumber;	/* inode number */
+	__u8			namelen;	/* name length */
+	__u8			name[];		/* name bytes, no null */
+     /* __u8			filetype; */	/* type of inode we point to */
+     /*	__be16                  tag; */		/* starting offset of us */
+} xfs_dir2_data_entry_t;
+
+/*
+ * Unused entry in a data block.
+ *
+ * Aligned to 8 bytes.  Tag appears as the last 2 bytes and must be accessed
+ * using xfs_dir2_data_unused_tag_p.
+ */
+typedef struct xfs_dir2_data_unused {
+	__be16			freetag;	/* XFS_DIR2_DATA_FREE_TAG */
+	__be16			length;		/* total free length */
+						/* variable offset */
+	__be16			tag;		/* starting offset of us */
+} xfs_dir2_data_unused_t;
+
+/*
+ * Size of a data entry.
+ */
+static inline int
+__xfs_dir3_data_entsize(
+	bool	ftype,
+	int	n)
+{
+	int	size = offsetof(struct xfs_dir2_data_entry, name[0]);
+
+	size += n;
+	size += sizeof(xfs_dir2_data_off_t);
+	if (ftype)
+		size += sizeof(__uint8_t);
+	return roundup(size, XFS_DIR2_DATA_ALIGN);
+}
+static inline int
+xfs_dir3_data_entsize(
+	struct xfs_mount	*mp,
+	int			n)
+{
+	bool ftype = xfs_sb_version_hasftype(&mp->m_sb) ? true : false;
+	return __xfs_dir3_data_entsize(ftype, n);
+}
+
+static inline __uint8_t
+xfs_dir3_dirent_get_ftype(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_entry *dep)
+{
+	if (xfs_sb_version_hasftype(&mp->m_sb)) {
+		__uint8_t	type = dep->name[dep->namelen];
+
+		ASSERT(type < XFS_DIR3_FT_MAX);
+		if (type < XFS_DIR3_FT_MAX)
+			return type;
+
+	}
+	return XFS_DIR3_FT_UNKNOWN;
+}
+
+static inline void
+xfs_dir3_dirent_put_ftype(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_entry *dep,
+	__uint8_t		type)
+{
+	ASSERT(type < XFS_DIR3_FT_MAX);
+	ASSERT(dep->namelen != 0);
+
+	if (xfs_sb_version_hasftype(&mp->m_sb))
+		dep->name[dep->namelen] = type;
+}
+
+/*
+ * Pointer to an entry's tag word.
+ */
+static inline __be16 *
+xfs_dir3_data_entry_tag_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_entry *dep)
+{
+	return (__be16 *)((char *)dep +
+		xfs_dir3_data_entsize(mp, dep->namelen) - sizeof(__be16));
+}
+
+/*
+ * Pointer to a freespace's tag word.
+ */
+static inline __be16 *
+xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
+{
+	return (__be16 *)((char *)dup +
+			be16_to_cpu(dup->length) - sizeof(__be16));
+}
+
+static inline size_t
+xfs_dir3_data_hdr_size(bool dir3)
+{
+	if (dir3)
+		return sizeof(struct xfs_dir3_data_hdr);
+	return sizeof(struct xfs_dir2_data_hdr);
+}
+
+static inline size_t
+xfs_dir3_data_entry_offset(struct xfs_dir2_data_hdr *hdr)
+{
+	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
+		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
+	return xfs_dir3_data_hdr_size(dir3);
+}
+
+static inline struct xfs_dir2_data_entry *
+xfs_dir3_data_entry_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + xfs_dir3_data_entry_offset(hdr));
+}
+
+static inline struct xfs_dir2_data_unused *
+xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_unused *)
+		((char *)hdr + xfs_dir3_data_entry_offset(hdr));
+}
+
+/*
+ * Offsets of . and .. in data space (always block 0)
+ *
+ * XXX: there is scope for significant optimisation of the logic here. Right
+ * now we are checking for "dir3 format" over and over again. Ideally we should
+ * only do it once for each operation.
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir3_data_dot_offset(struct xfs_mount *mp)
+{
+	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
+}
+
+static inline xfs_dir2_data_aoff_t
+xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
+{
+	return xfs_dir3_data_dot_offset(mp) +
+		xfs_dir3_data_entsize(mp, 1);
+}
+
+static inline xfs_dir2_data_aoff_t
+xfs_dir3_data_first_offset(struct xfs_mount *mp)
+{
+	return xfs_dir3_data_dotdot_offset(mp) +
+		xfs_dir3_data_entsize(mp, 2);
+}
+
+/*
+ * location of . and .. in data space (always block 0)
+ */
+static inline struct xfs_dir2_data_entry *
+xfs_dir3_data_dot_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + xfs_dir3_data_dot_offset(mp));
+}
+
+static inline struct xfs_dir2_data_entry *
+xfs_dir3_data_dotdot_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + xfs_dir3_data_dotdot_offset(mp));
+}
+
+static inline struct xfs_dir2_data_entry *
+xfs_dir3_data_first_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
+{
+	return (struct xfs_dir2_data_entry *)
+		((char *)hdr + xfs_dir3_data_first_offset(mp));
+}
+
+/*
+ * Leaf block structures.
+ *
+ * A pure leaf block looks like the following drawing on disk:
+ *
+ *    +---------------------------+
+ *    | xfs_dir2_leaf_hdr_t       |
+ *    +---------------------------+
+ *    | xfs_dir2_leaf_entry_t     |
+ *    | xfs_dir2_leaf_entry_t     |
+ *    | xfs_dir2_leaf_entry_t     |
+ *    | xfs_dir2_leaf_entry_t     |
+ *    | ...                       |
+ *    +---------------------------+
+ *    | xfs_dir2_data_off_t       |
+ *    | xfs_dir2_data_off_t       |
+ *    | xfs_dir2_data_off_t       |
+ *    | ...                       |
+ *    +---------------------------+
+ *    | xfs_dir2_leaf_tail_t      |
+ *    +---------------------------+
+ *
+ * The xfs_dir2_data_off_t members (bests) and tail are at the end of the block
+ * for single-leaf (magic = XFS_DIR2_LEAF1_MAGIC) blocks only, but not present
+ * for directories with separate leaf nodes and free space blocks
+ * (magic = XFS_DIR2_LEAFN_MAGIC).
+ *
+ * As all the entries are variable size structures the accessors below should
+ * be used to iterate over them.
+ */
+
+/*
+ * Offset of the leaf/node space.  First block in this space
+ * is the btree root.
+ */
+#define	XFS_DIR2_LEAF_SPACE	1
+#define	XFS_DIR2_LEAF_OFFSET	(XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE)
+#define	XFS_DIR2_LEAF_FIRSTDB(mp)	\
+	xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET)
+
+/*
+ * Leaf block header.
+ */
+typedef struct xfs_dir2_leaf_hdr {
+	xfs_da_blkinfo_t	info;		/* header for da routines */
+	__be16			count;		/* count of entries */
+	__be16			stale;		/* count of stale entries */
+} xfs_dir2_leaf_hdr_t;
+
+struct xfs_dir3_leaf_hdr {
+	struct xfs_da3_blkinfo	info;		/* header for da routines */
+	__be16			count;		/* count of entries */
+	__be16			stale;		/* count of stale entries */
+	__be32			pad;		/* 64 bit alignment */
+};
+
+struct xfs_dir3_icleaf_hdr {
+	__uint32_t		forw;
+	__uint32_t		back;
+	__uint16_t		magic;
+	__uint16_t		count;
+	__uint16_t		stale;
+};
+
+/*
+ * Leaf block entry.
+ */
+typedef struct xfs_dir2_leaf_entry {
+	__be32			hashval;	/* hash value of name */
+	__be32			address;	/* address of data entry */
+} xfs_dir2_leaf_entry_t;
+
+/*
+ * Leaf block tail.
+ */
+typedef struct xfs_dir2_leaf_tail {
+	__be32			bestcount;
+} xfs_dir2_leaf_tail_t;
+
+/*
+ * Leaf block.
+ */
+typedef struct xfs_dir2_leaf {
+	xfs_dir2_leaf_hdr_t	hdr;			/* leaf header */
+	xfs_dir2_leaf_entry_t	__ents[];		/* entries */
+} xfs_dir2_leaf_t;
+
+struct xfs_dir3_leaf {
+	struct xfs_dir3_leaf_hdr	hdr;		/* leaf header */
+	struct xfs_dir2_leaf_entry	__ents[];	/* entries */
+};
+
+#define XFS_DIR3_LEAF_CRC_OFF  offsetof(struct xfs_dir3_leaf_hdr, info.crc)
+
+extern void xfs_dir3_leaf_hdr_from_disk(struct xfs_dir3_icleaf_hdr *to,
+					struct xfs_dir2_leaf *from);
+
+static inline int
+xfs_dir3_leaf_hdr_size(struct xfs_dir2_leaf *lp)
+{
+	if (lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+	    lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC))
+		return sizeof(struct xfs_dir3_leaf_hdr);
+	return sizeof(struct xfs_dir2_leaf_hdr);
+}
+
+static inline int
+xfs_dir3_max_leaf_ents(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
+{
+	return (mp->m_dirblksize - xfs_dir3_leaf_hdr_size(lp)) /
+		(uint)sizeof(struct xfs_dir2_leaf_entry);
+}
+
+/*
+ * Get address of the bestcount field in the single-leaf block.
+ */
+static inline struct xfs_dir2_leaf_entry *
+xfs_dir3_leaf_ents_p(struct xfs_dir2_leaf *lp)
+{
+	if (lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+	    lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
+		struct xfs_dir3_leaf *lp3 = (struct xfs_dir3_leaf *)lp;
+		return lp3->__ents;
+	}
+	return lp->__ents;
+}
+
+/*
+ * Get address of the bestcount field in the single-leaf block.
+ */
+static inline struct xfs_dir2_leaf_tail *
+xfs_dir2_leaf_tail_p(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
+{
+	return (struct xfs_dir2_leaf_tail *)
+		((char *)lp + mp->m_dirblksize -
+		  sizeof(struct xfs_dir2_leaf_tail));
+}
+
+/*
+ * Get address of the bests array in the single-leaf block.
+ */
+static inline __be16 *
+xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp)
+{
+	return (__be16 *)ltp - be32_to_cpu(ltp->bestcount);
+}
+
+/*
+ * DB blocks here are logical directory block numbers, not filesystem blocks.
+ */
+
+/*
+ * Convert dataptr to byte in file space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
+{
+	return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
+}
+
+/*
+ * Convert byte in file space to dataptr.  It had better be aligned.
+ */
+static inline xfs_dir2_dataptr_t
+xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by)
+{
+	return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
+}
+
+/*
+ * Convert byte in space to (DB) block
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by)
+{
+	return (xfs_dir2_db_t)
+		(by >> (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog));
+}
+
+/*
+ * Convert dataptr to a block number
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
+{
+	return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp));
+}
+
+/*
+ * Convert byte in space to offset in a block
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by)
+{
+	return (xfs_dir2_data_aoff_t)(by &
+		((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) - 1));
+}
+
+/*
+ * Convert dataptr to a byte offset in a block
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
+{
+	return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp));
+}
+
+/*
+ * Convert block and offset to byte in space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db,
+			xfs_dir2_data_aoff_t o)
+{
+	return ((xfs_dir2_off_t)db <<
+		(mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) + o;
+}
+
+/*
+ * Convert block (DB) to block (dablk)
+ */
+static inline xfs_dablk_t
+xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return (xfs_dablk_t)(db << mp->m_sb.sb_dirblklog);
+}
+
+/*
+ * Convert byte in space to (DA) block
+ */
+static inline xfs_dablk_t
+xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by)
+{
+	return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by));
+}
+
+/*
+ * Convert block and offset to dataptr
+ */
+static inline xfs_dir2_dataptr_t
+xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db,
+			   xfs_dir2_data_aoff_t o)
+{
+	return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o));
+}
+
+/*
+ * Convert block (dablk) to block (DB)
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da)
+{
+	return (xfs_dir2_db_t)(da >> mp->m_sb.sb_dirblklog);
+}
+
+/*
+ * Convert block (dablk) to byte offset in space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
+{
+	return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0);
+}
+
+/*
+ * Free space block defintions for the node format.
+ */
+
+/*
+ * Offset of the freespace index.
+ */
+#define	XFS_DIR2_FREE_SPACE	2
+#define	XFS_DIR2_FREE_OFFSET	(XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE)
+#define	XFS_DIR2_FREE_FIRSTDB(mp)	\
+	xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET)
+
+typedef	struct xfs_dir2_free_hdr {
+	__be32			magic;		/* XFS_DIR2_FREE_MAGIC */
+	__be32			firstdb;	/* db of first entry */
+	__be32			nvalid;		/* count of valid entries */
+	__be32			nused;		/* count of used entries */
+} xfs_dir2_free_hdr_t;
+
+typedef struct xfs_dir2_free {
+	xfs_dir2_free_hdr_t	hdr;		/* block header */
+	__be16			bests[];	/* best free counts */
+						/* unused entries are -1 */
+} xfs_dir2_free_t;
+
+struct xfs_dir3_free_hdr {
+	struct xfs_dir3_blk_hdr	hdr;
+	__be32			firstdb;	/* db of first entry */
+	__be32			nvalid;		/* count of valid entries */
+	__be32			nused;		/* count of used entries */
+	__be32			pad;		/* 64 bit alignment */
+};
+
+struct xfs_dir3_free {
+	struct xfs_dir3_free_hdr hdr;
+	__be16			bests[];	/* best free counts */
+						/* unused entries are -1 */
+};
+
+#define XFS_DIR3_FREE_CRC_OFF  offsetof(struct xfs_dir3_free, hdr.hdr.crc)
+
+/*
+ * In core version of the free block header, abstracted away from on-disk format
+ * differences. Use this in the code, and convert to/from the disk version using
+ * xfs_dir3_free_hdr_from_disk/xfs_dir3_free_hdr_to_disk.
+ */
+struct xfs_dir3_icfree_hdr {
+	__uint32_t	magic;
+	__uint32_t	firstdb;
+	__uint32_t	nvalid;
+	__uint32_t	nused;
+
+};
+
+void xfs_dir3_free_hdr_from_disk(struct xfs_dir3_icfree_hdr *to,
+				 struct xfs_dir2_free *from);
+
+static inline int
+xfs_dir3_free_hdr_size(struct xfs_mount *mp)
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return sizeof(struct xfs_dir3_free_hdr);
+	return sizeof(struct xfs_dir2_free_hdr);
+}
+
+static inline int
+xfs_dir3_free_max_bests(struct xfs_mount *mp)
+{
+	return (mp->m_dirblksize - xfs_dir3_free_hdr_size(mp)) /
+		sizeof(xfs_dir2_data_off_t);
+}
+
+static inline __be16 *
+xfs_dir3_free_bests_p(struct xfs_mount *mp, struct xfs_dir2_free *free)
+{
+	return (__be16 *)((char *)free + xfs_dir3_free_hdr_size(mp));
+}
+
+/*
+ * Convert data space db to the corresponding free db.
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir3_free_max_bests(mp);
+}
+
+/*
+ * Convert data space db to the corresponding index in a free db.
+ */
+static inline int
+xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+{
+	return db % xfs_dir3_free_max_bests(mp);
+}
+
+/*
+ * Single block format.
+ *
+ * The single block format looks like the following drawing on disk:
+ *
+ *    +-------------------------------------------------+
+ *    | xfs_dir2_data_hdr_t                             |
+ *    +-------------------------------------------------+
+ *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
+ *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t :
+ *    | ...                                             |
+ *    +-------------------------------------------------+
+ *    | unused space                                    |
+ *    +-------------------------------------------------+
+ *    | ...                                             |
+ *    | xfs_dir2_leaf_entry_t                           |
+ *    | xfs_dir2_leaf_entry_t                           |
+ *    +-------------------------------------------------+
+ *    | xfs_dir2_block_tail_t                           |
+ *    +-------------------------------------------------+
+ *
+ * As all the entries are variable size structures the accessors below should
+ * be used to iterate over them.
+ */
+
+typedef struct xfs_dir2_block_tail {
+	__be32		count;			/* count of leaf entries */
+	__be32		stale;			/* count of stale lf entries */
+} xfs_dir2_block_tail_t;
+
+/*
+ * Pointer to the leaf header embedded in a data block (1-block format)
+ */
+static inline struct xfs_dir2_block_tail *
+xfs_dir2_block_tail_p(struct xfs_mount *mp, struct xfs_dir2_data_hdr *hdr)
+{
+	return ((struct xfs_dir2_block_tail *)
+		((char *)hdr + mp->m_dirblksize)) - 1;
+}
+
+/*
+ * Pointer to the leaf entries embedded in a data block (1-block format)
+ */
+static inline struct xfs_dir2_leaf_entry *
+xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
+{
+	return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count);
+}
+
+
+/*
+ * Attribute storage layout
+ *
+ * Attribute lists are structured around Btrees where all the data
+ * elements are in the leaf nodes.  Attribute names are hashed into an int,
+ * then that int is used as the index into the Btree.  Since the hashval
+ * of an attribute name may not be unique, we may have duplicate keys.  The
+ * internal links in the Btree are logical block offsets into the file.
+ *
+ *========================================================================
+ * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
+ *========================================================================
+ *
+ * Struct leaf_entry's are packed from the top.  Name/values grow from the
+ * bottom but are not packed.  The freemap contains run-length-encoded entries
+ * for the free bytes after the leaf_entry's, but only the N largest such,
+ * smaller runs are dropped.  When the freemap doesn't show enough space
+ * for an allocation, we compact the name/value area and try again.  If we
+ * still don't have enough space, then we have to split the block.  The
+ * name/value structs (both local and remote versions) must be 32bit aligned.
+ *
+ * Since we have duplicate hash keys, for each key that matches, compare
+ * the actual name string.  The root and intermediate node search always
+ * takes the first-in-the-block key match found, so we should only have
+ * to work "forw"ard.  If none matches, continue with the "forw"ard leaf
+ * nodes until the hash key changes or the attribute name is found.
+ *
+ * We store the fact that an attribute is a ROOT/USER/SECURE attribute in
+ * the leaf_entry.  The namespaces are independent only because we also look
+ * at the namespace bit when we are looking for a matching attribute name.
+ *
+ * We also store an "incomplete" bit in the leaf_entry.  It shows that an
+ * attribute is in the middle of being created and should not be shown to
+ * the user if we crash during the time that the bit is set.  We clear the
+ * bit when we have finished setting up the attribute.  We do this because
+ * we cannot create some large attributes inside a single transaction, and we
+ * need some indication that we weren't finished if we crash in the middle.
+ */
+#define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
+
+typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
+	__be16	base;			  /* base of free region */
+	__be16	size;			  /* length of free region */
+} xfs_attr_leaf_map_t;
+
+typedef struct xfs_attr_leaf_hdr {	/* constant-structure header block */
+	xfs_da_blkinfo_t info;		/* block type, links, etc. */
+	__be16	count;			/* count of active leaf_entry's */
+	__be16	usedbytes;		/* num bytes of names/values stored */
+	__be16	firstused;		/* first used byte in name area */
+	__u8	holes;			/* != 0 if blk needs compaction */
+	__u8	pad1;
+	xfs_attr_leaf_map_t freemap[XFS_ATTR_LEAF_MAPSIZE];
+					/* N largest free regions */
+} xfs_attr_leaf_hdr_t;
+
+typedef struct xfs_attr_leaf_entry {	/* sorted on key, not name */
+	__be32	hashval;		/* hash value of name */
+	__be16	nameidx;		/* index into buffer of name/value */
+	__u8	flags;			/* LOCAL/ROOT/SECURE/INCOMPLETE flag */
+	__u8	pad2;			/* unused pad byte */
+} xfs_attr_leaf_entry_t;
+
+typedef struct xfs_attr_leaf_name_local {
+	__be16	valuelen;		/* number of bytes in value */
+	__u8	namelen;		/* length of name bytes */
+	__u8	nameval[1];		/* name/value bytes */
+} xfs_attr_leaf_name_local_t;
+
+typedef struct xfs_attr_leaf_name_remote {
+	__be32	valueblk;		/* block number of value bytes */
+	__be32	valuelen;		/* number of bytes in value */
+	__u8	namelen;		/* length of name bytes */
+	__u8	name[1];		/* name bytes */
+} xfs_attr_leaf_name_remote_t;
+
+typedef struct xfs_attr_leafblock {
+	xfs_attr_leaf_hdr_t	hdr;	/* constant-structure header block */
+	xfs_attr_leaf_entry_t	entries[1];	/* sorted on key, not name */
+	xfs_attr_leaf_name_local_t namelist;	/* grows from bottom of buf */
+	xfs_attr_leaf_name_remote_t valuelist;	/* grows from bottom of buf */
+} xfs_attr_leafblock_t;
+
+/*
+ * CRC enabled leaf structures. Called "version 3" structures to match the
+ * version number of the directory and dablk structures for this feature, and
+ * attr2 is already taken by the variable inode attribute fork size feature.
+ */
+struct xfs_attr3_leaf_hdr {
+	struct xfs_da3_blkinfo	info;
+	__be16			count;
+	__be16			usedbytes;
+	__be16			firstused;
+	__u8			holes;
+	__u8			pad1;
+	struct xfs_attr_leaf_map freemap[XFS_ATTR_LEAF_MAPSIZE];
+	__be32			pad2;		/* 64 bit alignment */
+};
+
+#define XFS_ATTR3_LEAF_CRC_OFF	(offsetof(struct xfs_attr3_leaf_hdr, info.crc))
+
+struct xfs_attr3_leafblock {
+	struct xfs_attr3_leaf_hdr	hdr;
+	struct xfs_attr_leaf_entry	entries[1];
+
+	/*
+	 * The rest of the block contains the following structures after the
+	 * leaf entries, growing from the bottom up. The variables are never
+	 * referenced, the locations accessed purely from helper functions.
+	 *
+	 * struct xfs_attr_leaf_name_local
+	 * struct xfs_attr_leaf_name_remote
+	 */
+};
+
+/*
+ * incore, neutral version of the attribute leaf header
+ */
+struct xfs_attr3_icleaf_hdr {
+	__uint32_t	forw;
+	__uint32_t	back;
+	__uint16_t	magic;
+	__uint16_t	count;
+	__uint16_t	usedbytes;
+	__uint16_t	firstused;
+	__u8		holes;
+	struct {
+		__uint16_t	base;
+		__uint16_t	size;
+	} freemap[XFS_ATTR_LEAF_MAPSIZE];
+};
+
+/*
+ * Flags used in the leaf_entry[i].flags field.
+ * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
+ * on the system call, they are "or"ed together for various operations.
+ */
+#define	XFS_ATTR_LOCAL_BIT	0	/* attr is stored locally */
+#define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */
+#define	XFS_ATTR_SECURE_BIT	2	/* limit access to secure attrs */
+#define	XFS_ATTR_INCOMPLETE_BIT	7	/* attr in middle of create/delete */
+#define XFS_ATTR_LOCAL		(1 << XFS_ATTR_LOCAL_BIT)
+#define XFS_ATTR_ROOT		(1 << XFS_ATTR_ROOT_BIT)
+#define XFS_ATTR_SECURE		(1 << XFS_ATTR_SECURE_BIT)
+#define XFS_ATTR_INCOMPLETE	(1 << XFS_ATTR_INCOMPLETE_BIT)
+
+/*
+ * Conversion macros for converting namespace bits from argument flags
+ * to ondisk flags.
+ */
+#define XFS_ATTR_NSP_ARGS_MASK		(ATTR_ROOT | ATTR_SECURE)
+#define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
+#define XFS_ATTR_NSP_ONDISK(flags)	((flags) & XFS_ATTR_NSP_ONDISK_MASK)
+#define XFS_ATTR_NSP_ARGS(flags)	((flags) & XFS_ATTR_NSP_ARGS_MASK)
+#define XFS_ATTR_NSP_ARGS_TO_ONDISK(x)	(((x) & ATTR_ROOT ? XFS_ATTR_ROOT : 0) |\
+					 ((x) & ATTR_SECURE ? XFS_ATTR_SECURE : 0))
+#define XFS_ATTR_NSP_ONDISK_TO_ARGS(x)	(((x) & XFS_ATTR_ROOT ? ATTR_ROOT : 0) |\
+					 ((x) & XFS_ATTR_SECURE ? ATTR_SECURE : 0))
+
+/*
+ * Alignment for namelist and valuelist entries (since they are mixed
+ * there can be only one alignment value)
+ */
+#define	XFS_ATTR_LEAF_NAME_ALIGN	((uint)sizeof(xfs_dablk_t))
+
+static inline int
+xfs_attr3_leaf_hdr_size(struct xfs_attr_leafblock *leafp)
+{
+	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+		return sizeof(struct xfs_attr3_leaf_hdr);
+	return sizeof(struct xfs_attr_leaf_hdr);
+}
+
+static inline struct xfs_attr_leaf_entry *
+xfs_attr3_leaf_entryp(xfs_attr_leafblock_t *leafp)
+{
+	if (leafp->hdr.info.magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC))
+		return &((struct xfs_attr3_leafblock *)leafp)->entries[0];
+	return &leafp->entries[0];
+}
+
+/*
+ * Cast typed pointers for "local" and "remote" name/value structs.
+ */
+static inline char *
+xfs_attr3_leaf_name(xfs_attr_leafblock_t *leafp, int idx)
+{
+	struct xfs_attr_leaf_entry *entries = xfs_attr3_leaf_entryp(leafp);
+
+	return &((char *)leafp)[be16_to_cpu(entries[idx].nameidx)];
+}
+
+static inline xfs_attr_leaf_name_remote_t *
+xfs_attr3_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx)
+{
+	return (xfs_attr_leaf_name_remote_t *)xfs_attr3_leaf_name(leafp, idx);
+}
+
+static inline xfs_attr_leaf_name_local_t *
+xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx)
+{
+	return (xfs_attr_leaf_name_local_t *)xfs_attr3_leaf_name(leafp, idx);
+}
+
+/*
+ * Calculate total bytes used (including trailing pad for alignment) for
+ * a "local" name/value structure, a "remote" name/value structure, and
+ * a pointer which might be either.
+ */
+static inline int xfs_attr_leaf_entsize_remote(int nlen)
+{
+	return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \
+		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+}
+
+static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen)
+{
+	return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) +
+		XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1);
+}
+
+static inline int xfs_attr_leaf_entsize_local_max(int bsize)
+{
+	return (((bsize) >> 1) + ((bsize) >> 2));
+}
+
+
+
+/*
+ * Remote attribute block format definition
+ *
+ * There is one of these headers per filesystem block in a remote attribute.
+ * This is done to ensure there is a 1:1 mapping between the attribute value
+ * length and the number of blocks needed to store the attribute. This makes the
+ * verification of a buffer a little more complex, but greatly simplifies the
+ * allocation, reading and writing of these attributes as we don't have to guess
+ * the number of blocks needed to store the attribute data.
+ */
+#define XFS_ATTR3_RMT_MAGIC	0x5841524d	/* XARM */
+
+struct xfs_attr3_rmt_hdr {
+	__be32	rm_magic;
+	__be32	rm_offset;
+	__be32	rm_bytes;
+	__be32	rm_crc;
+	uuid_t	rm_uuid;
+	__be64	rm_owner;
+	__be64	rm_blkno;
+	__be64	rm_lsn;
+};
+
+#define XFS_ATTR3_RMT_CRC_OFF	offsetof(struct xfs_attr3_rmt_hdr, rm_crc)
+
+#define XFS_ATTR3_RMT_BUF_SPACE(mp, bufsize)	\
+	((bufsize) - (xfs_sb_version_hascrc(&(mp)->m_sb) ? \
+			sizeof(struct xfs_attr3_rmt_hdr) : 0))
+
+#endif /* __XFS_DA_FORMAT_H__ */
include/xfs_dir2_format.h deleted +0 -954
deleted file mode 100644
index 9cf6738..0000000
@@ -1,964 +0,0 @@
-/*
- * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
- * Copyright (c) 2013 Red Hat, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_DIR2_FORMAT_H__
-#define __XFS_DIR2_FORMAT_H__
-
-/*
- * Directory version 2.
- *
- * There are 4 possible formats:
- *  - shortform - embedded into the inode
- *  - single block - data with embedded leaf at the end
- *  - multiple data blocks, single leaf+freeindex block
- *  - data blocks, node and leaf blocks (btree), freeindex blocks
- *
- * Note: many node blocks structures and constants are shared with the attr
- * code and defined in xfs_da_btree.h.
- */
-
-#define	XFS_DIR2_BLOCK_MAGIC	0x58443242	/* XD2B: single block dirs */
-#define	XFS_DIR2_DATA_MAGIC	0x58443244	/* XD2D: multiblock dirs */
-#define	XFS_DIR2_FREE_MAGIC	0x58443246	/* XD2F: free index blocks */
-
-/*
- * Directory Version 3 With CRCs.
- *
- * The tree formats are the same as for version 2 directories.  The difference
- * is in the block header and dirent formats. In many cases the v3 structures
- * use v2 definitions as they are no different and this makes code sharing much
- * easier.
- *
- * Also, the xfs_dir3_*() functions handle both v2 and v3 formats - if the
- * format is v2 then they switch to the existing v2 code, or the format is v3
- * they implement the v3 functionality. This means the existing dir2 is a mix of
- * xfs_dir2/xfs_dir3 calls and functions. The xfs_dir3 functions are called
- * where there is a difference in the formats, otherwise the code is unchanged.
- *
- * Where it is possible, the code decides what to do based on the magic numbers
- * in the blocks rather than feature bits in the superblock. This means the code
- * is as independent of the external XFS code as possible as doesn't require
- * passing struct xfs_mount pointers into places where it isn't really
- * necessary.
- *
- * Version 3 includes:
- *
- *	- a larger block header for CRC and identification purposes and so the
- *	offsets of all the structures inside the blocks are different.
- *
- *	- new magic numbers to be able to detect the v2/v3 types on the fly.
- */
-
-#define	XFS_DIR3_BLOCK_MAGIC	0x58444233	/* XDB3: single block dirs */
-#define	XFS_DIR3_DATA_MAGIC	0x58444433	/* XDD3: multiblock dirs */
-#define	XFS_DIR3_FREE_MAGIC	0x58444633	/* XDF3: free index blocks */
-
-/*
- * Dirents in version 3 directories have a file type field. Additions to this
- * list are an on-disk format change, requiring feature bits. Valid values
- * are as follows:
- */
-#define XFS_DIR3_FT_UNKNOWN		0
-#define XFS_DIR3_FT_REG_FILE		1
-#define XFS_DIR3_FT_DIR			2
-#define XFS_DIR3_FT_CHRDEV		3
-#define XFS_DIR3_FT_BLKDEV		4
-#define XFS_DIR3_FT_FIFO		5
-#define XFS_DIR3_FT_SOCK		6
-#define XFS_DIR3_FT_SYMLINK		7
-#define XFS_DIR3_FT_WHT			8
-
-#define XFS_DIR3_FT_MAX			9
-
-/*
- * Byte offset in data block and shortform entry.
- */
-typedef	__uint16_t	xfs_dir2_data_off_t;
-#define	NULLDATAOFF	0xffffU
-typedef uint		xfs_dir2_data_aoff_t;	/* argument form */
-
-/*
- * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t.
- * Only need 16 bits, this is the byte offset into the single block form.
- */
-typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t;
-
-/*
- * Offset in data space of a data entry.
- */
-typedef	__uint32_t	xfs_dir2_dataptr_t;
-#define	XFS_DIR2_MAX_DATAPTR	((xfs_dir2_dataptr_t)0xffffffff)
-#define	XFS_DIR2_NULL_DATAPTR	((xfs_dir2_dataptr_t)0)
-
-/*
- * Byte offset in a directory.
- */
-typedef	xfs_off_t	xfs_dir2_off_t;
-
-/*
- * Directory block number (logical dirblk in file)
- */
-typedef	__uint32_t	xfs_dir2_db_t;
-
-/*
- * Inode number stored as 8 8-bit values.
- */
-typedef	struct { __uint8_t i[8]; } xfs_dir2_ino8_t;
-
-/*
- * Inode number stored as 4 8-bit values.
- * Works a lot of the time, when all the inode numbers in a directory
- * fit in 32 bits.
- */
-typedef struct { __uint8_t i[4]; } xfs_dir2_ino4_t;
-
-typedef union {
-	xfs_dir2_ino8_t	i8;
-	xfs_dir2_ino4_t	i4;
-} xfs_dir2_inou_t;
-#define	XFS_DIR2_MAX_SHORT_INUM	((xfs_ino_t)0xffffffffULL)
-
-/*
- * Directory layout when stored internal to an inode.
- *
- * Small directories are packed as tightly as possible so as to fit into the
- * literal area of the inode.  These "shortform" directories consist of a
- * single xfs_dir2_sf_hdr header followed by zero or more xfs_dir2_sf_entry
- * structures.  Due the different inode number storage size and the variable
- * length name field in the xfs_dir2_sf_entry all these structure are
- * variable length, and the accessors in this file should be used to iterate
- * over them.
- */
-typedef struct xfs_dir2_sf_hdr {
-	__uint8_t		count;		/* count of entries */
-	__uint8_t		i8count;	/* count of 8-byte inode #s */
-	xfs_dir2_inou_t		parent;		/* parent dir inode number */
-} __arch_pack xfs_dir2_sf_hdr_t;
-
-typedef struct xfs_dir2_sf_entry {
-	__u8			namelen;	/* actual name length */
-	xfs_dir2_sf_off_t	offset;		/* saved offset */
-	__u8			name[];		/* name, variable size */
-	/*
-	 * A single byte containing the file type field follows the inode
-	 * number for version 3 directory entries.
-	 *
-	 * A xfs_dir2_ino8_t or xfs_dir2_ino4_t follows here, at a
-	 * variable offset after the name.
-	 */
-} __arch_pack xfs_dir2_sf_entry_t;
-
-static inline int xfs_dir2_sf_hdr_size(int i8count)
-{
-	return sizeof(struct xfs_dir2_sf_hdr) -
-		(i8count == 0) *
-		(sizeof(xfs_dir2_ino8_t) - sizeof(xfs_dir2_ino4_t));
-}
-
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_sf_get_offset(xfs_dir2_sf_entry_t *sfep)
-{
-	return get_unaligned_be16(&sfep->offset.i);
-}
-
-static inline void
-xfs_dir2_sf_put_offset(xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t off)
-{
-	put_unaligned_be16(off, &sfep->offset.i);
-}
-
-static inline struct xfs_dir2_sf_entry *
-xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
-{
-	return (struct xfs_dir2_sf_entry *)
-		((char *)hdr + xfs_dir2_sf_hdr_size(hdr->i8count));
-}
-
-static inline int
-xfs_dir3_sf_entsize(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	int			len)
-{
-	int count = sizeof(struct xfs_dir2_sf_entry); 	/* namelen + offset */
-
-	count += len;					/* name */
-	count += hdr->i8count ? sizeof(xfs_dir2_ino8_t) :
-				sizeof(xfs_dir2_ino4_t); /* ino # */
-	if (xfs_sb_version_hasftype(&mp->m_sb))
-		count += sizeof(__uint8_t);		/* file type */
-	return count;
-}
-
-static inline struct xfs_dir2_sf_entry *
-xfs_dir3_sf_nextentry(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	return (struct xfs_dir2_sf_entry *)
-		((char *)sfep + xfs_dir3_sf_entsize(mp, hdr, sfep->namelen));
-}
-
-/*
- * in dir3 shortform directories, the file type field is stored at a variable
- * offset after the inode number. Because it's only a single byte, endian
- * conversion is not necessary.
- */
-static inline __uint8_t *
-xfs_dir3_sfe_ftypep(
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	return (__uint8_t *)&sfep->name[sfep->namelen];
-}
-
-static inline __uint8_t
-xfs_dir3_sfe_get_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep)
-{
-	__uint8_t	*ftp;
-
-	if (!xfs_sb_version_hasftype(&mp->m_sb))
-		return XFS_DIR3_FT_UNKNOWN;
-
-	ftp = xfs_dir3_sfe_ftypep(hdr, sfep);
-	if (*ftp >= XFS_DIR3_FT_MAX)
-		return XFS_DIR3_FT_UNKNOWN;
-	return *ftp;
-}
-
-static inline void
-xfs_dir3_sfe_put_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_sf_hdr	*hdr,
-	struct xfs_dir2_sf_entry *sfep,
-	__uint8_t		ftype)
-{
-	__uint8_t	*ftp;
-
-	ASSERT(ftype < XFS_DIR3_FT_MAX);
-
-	if (!xfs_sb_version_hasftype(&mp->m_sb))
-		return;
-	ftp = xfs_dir3_sfe_ftypep(hdr, sfep);
-	*ftp = ftype;
-}
-
-/*
- * Data block structures.
- *
- * A pure data block looks like the following drawing on disk:
- *
- *    +-------------------------------------------------+
- *    | xfs_dir2_data_hdr_t                             |
- *    +-------------------------------------------------+
- *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- *    | ...                                             |
- *    +-------------------------------------------------+
- *    | unused space                                    |
- *    +-------------------------------------------------+
- *
- * As all the entries are variable size structures the accessors below should
- * be used to iterate over them.
- *
- * In addition to the pure data blocks for the data and node formats,
- * most structures are also used for the combined data/freespace "block"
- * format below.
- */
-
-#define	XFS_DIR2_DATA_ALIGN_LOG	3		/* i.e., 8 bytes */
-#define	XFS_DIR2_DATA_ALIGN	(1 << XFS_DIR2_DATA_ALIGN_LOG)
-#define	XFS_DIR2_DATA_FREE_TAG	0xffff
-#define	XFS_DIR2_DATA_FD_COUNT	3
-
-/*
- * Directory address space divided into sections,
- * spaces separated by 32GB.
- */
-#define	XFS_DIR2_SPACE_SIZE	(1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
-#define	XFS_DIR2_DATA_SPACE	0
-#define	XFS_DIR2_DATA_OFFSET	(XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
-#define	XFS_DIR2_DATA_FIRSTDB(mp)	\
-	xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET)
-
-/*
- * Describe a free area in the data block.
- *
- * The freespace will be formatted as a xfs_dir2_data_unused_t.
- */
-typedef struct xfs_dir2_data_free {
-	__be16			offset;		/* start of freespace */
-	__be16			length;		/* length of freespace */
-} xfs_dir2_data_free_t;
-
-/*
- * Header for the data blocks.
- *
- * The code knows that XFS_DIR2_DATA_FD_COUNT is 3.
- */
-typedef struct xfs_dir2_data_hdr {
-	__be32			magic;		/* XFS_DIR2_DATA_MAGIC or */
-						/* XFS_DIR2_BLOCK_MAGIC */
-	xfs_dir2_data_free_t	bestfree[XFS_DIR2_DATA_FD_COUNT];
-} xfs_dir2_data_hdr_t;
-
-/*
- * define a structure for all the verification fields we are adding to the
- * directory block structures. This will be used in several structures.
- * The magic number must be the first entry to align with all the dir2
- * structures so we determine how to decode them just by the magic number.
- */
-struct xfs_dir3_blk_hdr {
-	__be32			magic;	/* magic number */
-	__be32			crc;	/* CRC of block */
-	__be64			blkno;	/* first block of the buffer */
-	__be64			lsn;	/* sequence number of last write */
-	uuid_t			uuid;	/* filesystem we belong to */
-	__be64			owner;	/* inode that owns the block */
-};
-
-struct xfs_dir3_data_hdr {
-	struct xfs_dir3_blk_hdr	hdr;
-	xfs_dir2_data_free_t	best_free[XFS_DIR2_DATA_FD_COUNT];
-	__be32			pad;	/* 64 bit alignment */
-};
-
-#define XFS_DIR3_DATA_CRC_OFF  offsetof(struct xfs_dir3_data_hdr, hdr.crc)
-
-static inline struct xfs_dir2_data_free *
-xfs_dir3_data_bestfree_p(struct xfs_dir2_data_hdr *hdr)
-{
-	if (hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
-		struct xfs_dir3_data_hdr *hdr3 = (struct xfs_dir3_data_hdr *)hdr;
-		return hdr3->best_free;
-	}
-	return hdr->bestfree;
-}
-
-/*
- * Active entry in a data block.
- *
- * Aligned to 8 bytes.  After the variable length name field there is a
- * 2 byte tag field, which can be accessed using xfs_dir3_data_entry_tag_p.
- *
- * For dir3 structures, there is file type field between the name and the tag.
- * This can only be manipulated by helper functions. It is packed hard against
- * the end of the name so any padding for rounding is between the file type and
- * the tag.
- */
-typedef struct xfs_dir2_data_entry {
-	__be64			inumber;	/* inode number */
-	__u8			namelen;	/* name length */
-	__u8			name[];		/* name bytes, no null */
-     /* __u8			filetype; */	/* type of inode we point to */
-     /*	__be16                  tag; */		/* starting offset of us */
-} xfs_dir2_data_entry_t;
-
-/*
- * Unused entry in a data block.
- *
- * Aligned to 8 bytes.  Tag appears as the last 2 bytes and must be accessed
- * using xfs_dir2_data_unused_tag_p.
- */
-typedef struct xfs_dir2_data_unused {
-	__be16			freetag;	/* XFS_DIR2_DATA_FREE_TAG */
-	__be16			length;		/* total free length */
-						/* variable offset */
-	__be16			tag;		/* starting offset of us */
-} xfs_dir2_data_unused_t;
-
-/*
- * Size of a data entry.
- */
-static inline int
-__xfs_dir3_data_entsize(
-	bool	ftype,
-	int	n)
-{
-	int	size = offsetof(struct xfs_dir2_data_entry, name[0]);
-
-	size += n;
-	size += sizeof(xfs_dir2_data_off_t);
-	if (ftype)
-		size += sizeof(__uint8_t);
-	return roundup(size, XFS_DIR2_DATA_ALIGN);
-}
-static inline int
-xfs_dir3_data_entsize(
-	struct xfs_mount	*mp,
-	int			n)
-{
-	bool ftype = xfs_sb_version_hasftype(&mp->m_sb) ? true : false;
-	return __xfs_dir3_data_entsize(ftype, n);
-}
-
-static inline __uint8_t
-xfs_dir3_dirent_get_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_entry *dep)
-{
-	if (xfs_sb_version_hasftype(&mp->m_sb)) {
-		__uint8_t	type = dep->name[dep->namelen];
-
-		ASSERT(type < XFS_DIR3_FT_MAX);
-		if (type < XFS_DIR3_FT_MAX)
-			return type;
-
-	}
-	return XFS_DIR3_FT_UNKNOWN;
-}
-
-static inline void
-xfs_dir3_dirent_put_ftype(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_entry *dep,
-	__uint8_t		type)
-{
-	ASSERT(type < XFS_DIR3_FT_MAX);
-	ASSERT(dep->namelen != 0);
-
-	if (xfs_sb_version_hasftype(&mp->m_sb))
-		dep->name[dep->namelen] = type;
-}
-
-/*
- * Pointer to an entry's tag word.
- */
-static inline __be16 *
-xfs_dir3_data_entry_tag_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_entry *dep)
-{
-	return (__be16 *)((char *)dep +
-		xfs_dir3_data_entsize(mp, dep->namelen) - sizeof(__be16));
-}
-
-/*
- * Pointer to a freespace's tag word.
- */
-static inline __be16 *
-xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
-{
-	return (__be16 *)((char *)dup +
-			be16_to_cpu(dup->length) - sizeof(__be16));
-}
-
-static inline size_t
-xfs_dir3_data_hdr_size(bool dir3)
-{
-	if (dir3)
-		return sizeof(struct xfs_dir3_data_hdr);
-	return sizeof(struct xfs_dir2_data_hdr);
-}
-
-static inline size_t
-xfs_dir3_data_entry_offset(struct xfs_dir2_data_hdr *hdr)
-{
-	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
-	return xfs_dir3_data_hdr_size(dir3);
-}
-
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_entry_p(struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_entry_offset(hdr));
-}
-
-static inline struct xfs_dir2_data_unused *
-xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_unused *)
-		((char *)hdr + xfs_dir3_data_entry_offset(hdr));
-}
-
-/*
- * Offsets of . and .. in data space (always block 0)
- *
- * XXX: there is scope for significant optimisation of the logic here. Right
- * now we are checking for "dir3 format" over and over again. Ideally we should
- * only do it once for each operation.
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dot_offset(struct xfs_mount *mp)
-{
-	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
-}
-
-static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
-{
-	return xfs_dir3_data_dot_offset(mp) +
-		xfs_dir3_data_entsize(mp, 1);
-}
-
-static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_first_offset(struct xfs_mount *mp)
-{
-	return xfs_dir3_data_dotdot_offset(mp) +
-		xfs_dir3_data_entsize(mp, 2);
-}
-
-/*
- * location of . and .. in data space (always block 0)
- */
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dot_entry_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dot_offset(mp));
-}
-
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dotdot_entry_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dotdot_offset(mp));
-}
-
-static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_first_entry_p(
-	struct xfs_mount	*mp,
-	struct xfs_dir2_data_hdr *hdr)
-{
-	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_first_offset(mp));
-}
-
-/*
- * Leaf block structures.
- *
- * A pure leaf block looks like the following drawing on disk:
- *
- *    +---------------------------+
- *    | xfs_dir2_leaf_hdr_t       |
- *    +---------------------------+
- *    | xfs_dir2_leaf_entry_t     |
- *    | xfs_dir2_leaf_entry_t     |
- *    | xfs_dir2_leaf_entry_t     |
- *    | xfs_dir2_leaf_entry_t     |
- *    | ...                       |
- *    +---------------------------+
- *    | xfs_dir2_data_off_t       |
- *    | xfs_dir2_data_off_t       |
- *    | xfs_dir2_data_off_t       |
- *    | ...                       |
- *    +---------------------------+
- *    | xfs_dir2_leaf_tail_t      |
- *    +---------------------------+
- *
- * The xfs_dir2_data_off_t members (bests) and tail are at the end of the block
- * for single-leaf (magic = XFS_DIR2_LEAF1_MAGIC) blocks only, but not present
- * for directories with separate leaf nodes and free space blocks
- * (magic = XFS_DIR2_LEAFN_MAGIC).
- *
- * As all the entries are variable size structures the accessors below should
- * be used to iterate over them.
- */
-
-/*
- * Offset of the leaf/node space.  First block in this space
- * is the btree root.
- */
-#define	XFS_DIR2_LEAF_SPACE	1
-#define	XFS_DIR2_LEAF_OFFSET	(XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE)
-#define	XFS_DIR2_LEAF_FIRSTDB(mp)	\
-	xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET)
-
-/*
- * Leaf block header.
- */
-typedef struct xfs_dir2_leaf_hdr {
-	xfs_da_blkinfo_t	info;		/* header for da routines */
-	__be16			count;		/* count of entries */
-	__be16			stale;		/* count of stale entries */
-} xfs_dir2_leaf_hdr_t;
-
-struct xfs_dir3_leaf_hdr {
-	struct xfs_da3_blkinfo	info;		/* header for da routines */
-	__be16			count;		/* count of entries */
-	__be16			stale;		/* count of stale entries */
-	__be32			pad;		/* 64 bit alignment */
-};
-
-struct xfs_dir3_icleaf_hdr {
-	__uint32_t		forw;
-	__uint32_t		back;
-	__uint16_t		magic;
-	__uint16_t		count;
-	__uint16_t		stale;
-};
-
-/*
- * Leaf block entry.
- */
-typedef struct xfs_dir2_leaf_entry {
-	__be32			hashval;	/* hash value of name */
-	__be32			address;	/* address of data entry */
-} xfs_dir2_leaf_entry_t;
-
-/*
- * Leaf block tail.
- */
-typedef struct xfs_dir2_leaf_tail {
-	__be32			bestcount;
-} xfs_dir2_leaf_tail_t;
-
-/*
- * Leaf block.
- */
-typedef struct xfs_dir2_leaf {
-	xfs_dir2_leaf_hdr_t	hdr;			/* leaf header */
-	xfs_dir2_leaf_entry_t	__ents[];		/* entries */
-} xfs_dir2_leaf_t;
-
-struct xfs_dir3_leaf {
-	struct xfs_dir3_leaf_hdr	hdr;		/* leaf header */
-	struct xfs_dir2_leaf_entry	__ents[];	/* entries */
-};
-
-#define XFS_DIR3_LEAF_CRC_OFF  offsetof(struct xfs_dir3_leaf_hdr, info.crc)
-
-extern void xfs_dir3_leaf_hdr_from_disk(struct xfs_dir3_icleaf_hdr *to,
-					struct xfs_dir2_leaf *from);
-
-static inline int
-xfs_dir3_leaf_hdr_size(struct xfs_dir2_leaf *lp)
-{
-	if (lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
-	    lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC))
-		return sizeof(struct xfs_dir3_leaf_hdr);
-	return sizeof(struct xfs_dir2_leaf_hdr);
-}
-
-static inline int
-xfs_dir3_max_leaf_ents(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
-{
-	return (mp->m_dirblksize - xfs_dir3_leaf_hdr_size(lp)) /
-		(uint)sizeof(struct xfs_dir2_leaf_entry);
-}
-
-/*
- * Get address of the bestcount field in the single-leaf block.
- */
-static inline struct xfs_dir2_leaf_entry *
-xfs_dir3_leaf_ents_p(struct xfs_dir2_leaf *lp)
-{
-	if (lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
-	    lp->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
-		struct xfs_dir3_leaf *lp3 = (struct xfs_dir3_leaf *)lp;
-		return lp3->__ents;
-	}
-	return lp->__ents;
-}
-
-/*
- * Get address of the bestcount field in the single-leaf block.
- */
-static inline struct xfs_dir2_leaf_tail *
-xfs_dir2_leaf_tail_p(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
-{
-	return (struct xfs_dir2_leaf_tail *)
-		((char *)lp + mp->m_dirblksize -
-		  sizeof(struct xfs_dir2_leaf_tail));
-}
-
-/*
- * Get address of the bests array in the single-leaf block.
- */
-static inline __be16 *
-xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp)
-{
-	return (__be16 *)ltp - be32_to_cpu(ltp->bestcount);
-}
-
-/*
- * DB blocks here are logical directory block numbers, not filesystem blocks.
- */
-
-/*
- * Convert dataptr to byte in file space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
-	return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
-}
-
-/*
- * Convert byte in file space to dataptr.  It had better be aligned.
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
-}
-
-/*
- * Convert byte in space to (DB) block
- */
-static inline xfs_dir2_db_t
-xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return (xfs_dir2_db_t)
-		(by >> (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog));
-}
-
-/*
- * Convert dataptr to a block number
- */
-static inline xfs_dir2_db_t
-xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
-	return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert byte in space to offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return (xfs_dir2_data_aoff_t)(by &
-		((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) - 1));
-}
-
-/*
- * Convert dataptr to a byte offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
-	return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert block and offset to byte in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db,
-			xfs_dir2_data_aoff_t o)
-{
-	return ((xfs_dir2_off_t)db <<
-		(mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) + o;
-}
-
-/*
- * Convert block (DB) to block (dablk)
- */
-static inline xfs_dablk_t
-xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
-	return (xfs_dablk_t)(db << mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert byte in space to (DA) block
- */
-static inline xfs_dablk_t
-xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by));
-}
-
-/*
- * Convert block and offset to dataptr
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db,
-			   xfs_dir2_data_aoff_t o)
-{
-	return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o));
-}
-
-/*
- * Convert block (dablk) to block (DB)
- */
-static inline xfs_dir2_db_t
-xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da)
-{
-	return (xfs_dir2_db_t)(da >> mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert block (dablk) to byte offset in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
-{
-	return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0);
-}
-
-/*
- * Free space block defintions for the node format.
- */
-
-/*
- * Offset of the freespace index.
- */
-#define	XFS_DIR2_FREE_SPACE	2
-#define	XFS_DIR2_FREE_OFFSET	(XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE)
-#define	XFS_DIR2_FREE_FIRSTDB(mp)	\
-	xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET)
-
-typedef	struct xfs_dir2_free_hdr {
-	__be32			magic;		/* XFS_DIR2_FREE_MAGIC */
-	__be32			firstdb;	/* db of first entry */
-	__be32			nvalid;		/* count of valid entries */
-	__be32			nused;		/* count of used entries */
-} xfs_dir2_free_hdr_t;
-
-typedef struct xfs_dir2_free {
-	xfs_dir2_free_hdr_t	hdr;		/* block header */
-	__be16			bests[];	/* best free counts */
-						/* unused entries are -1 */
-} xfs_dir2_free_t;
-
-struct xfs_dir3_free_hdr {
-	struct xfs_dir3_blk_hdr	hdr;
-	__be32			firstdb;	/* db of first entry */
-	__be32			nvalid;		/* count of valid entries */
-	__be32			nused;		/* count of used entries */
-	__be32			pad;		/* 64 bit alignment */
-};
-
-struct xfs_dir3_free {
-	struct xfs_dir3_free_hdr hdr;
-	__be16			bests[];	/* best free counts */
-						/* unused entries are -1 */
-};
-
-#define XFS_DIR3_FREE_CRC_OFF  offsetof(struct xfs_dir3_free, hdr.hdr.crc)
-
-/*
- * In core version of the free block header, abstracted away from on-disk format
- * differences. Use this in the code, and convert to/from the disk version using
- * xfs_dir3_free_hdr_from_disk/xfs_dir3_free_hdr_to_disk.
- */
-struct xfs_dir3_icfree_hdr {
-	__uint32_t	magic;
-	__uint32_t	firstdb;
-	__uint32_t	nvalid;
-	__uint32_t	nused;
-
-};
-
-void xfs_dir3_free_hdr_from_disk(struct xfs_dir3_icfree_hdr *to,
-				 struct xfs_dir2_free *from);
-
-static inline int
-xfs_dir3_free_hdr_size(struct xfs_mount *mp)
-{
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		return sizeof(struct xfs_dir3_free_hdr);
-	return sizeof(struct xfs_dir2_free_hdr);
-}
-
-static inline int
-xfs_dir3_free_max_bests(struct xfs_mount *mp)
-{
-	return (mp->m_dirblksize - xfs_dir3_free_hdr_size(mp)) /
-		sizeof(xfs_dir2_data_off_t);
-}
-
-static inline __be16 *
-xfs_dir3_free_bests_p(struct xfs_mount *mp, struct xfs_dir2_free *free)
-{
-	return (__be16 *)((char *)free + xfs_dir3_free_hdr_size(mp));
-}
-
-/*
- * Convert data space db to the corresponding free db.
- */
-static inline xfs_dir2_db_t
-xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
-	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir3_free_max_bests(mp);
-}
-
-/*
- * Convert data space db to the corresponding index in a free db.
- */
-static inline int
-xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
-	return db % xfs_dir3_free_max_bests(mp);
-}
-
-/*
- * Single block format.
- *
- * The single block format looks like the following drawing on disk:
- *
- *    +-------------------------------------------------+
- *    | xfs_dir2_data_hdr_t                             |
- *    +-------------------------------------------------+
- *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t |
- *    | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t :
- *    | ...                                             |
- *    +-------------------------------------------------+
- *    | unused space                                    |
- *    +-------------------------------------------------+
- *    | ...                                             |
- *    | xfs_dir2_leaf_entry_t                           |
- *    | xfs_dir2_leaf_entry_t                           |
- *    +-------------------------------------------------+
- *    | xfs_dir2_block_tail_t                           |
- *    +-------------------------------------------------+
- *
- * As all the entries are variable size structures the accessors below should
- * be used to iterate over them.
- */
-
-typedef struct xfs_dir2_block_tail {
-	__be32		count;			/* count of leaf entries */
-	__be32		stale;			/* count of stale lf entries */
-} xfs_dir2_block_tail_t;
-
-/*
- * Pointer to the leaf header embedded in a data block (1-block format)
- */
-static inline struct xfs_dir2_block_tail *
-xfs_dir2_block_tail_p(struct xfs_mount *mp, struct xfs_dir2_data_hdr *hdr)
-{
-	return ((struct xfs_dir2_block_tail *)
-		((char *)hdr + mp->m_dirblksize)) - 1;
-}
-

include/xfs_dir2_format.h line 964

Quoted 10 lines
include/xfs_dir2_format.h deleted +0 -10
-/*
- * Pointer to the leaf entries embedded in a data block (1-block format)
- */
-static inline struct xfs_dir2_leaf_entry *
-xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
-{
-	return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count);
-}
-
-#endif /* __XFS_DIR2_FORMAT_H__ */

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#32 lore raw

Re: [PATCH 09/32] xfs: unify directory/attribute format definitions

In reply to Dave Chinner

Sorry Dave i did not realize I needed to do a make clean first.

This has been commited.

Thanks
--Rich

commit ddd5a16201db90a255952f61c34aeaab67d0a845

Author: Dave Chinner <[email protected]>
Date:   Mon Sep 30 03:15:21 2013 +0000

xfs: unify directory/attribute format definitions

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#33 lore raw

Re: [PATCH 09/32] xfs: unify directory/attribute format definitions

Quoted 4 lines · Rich Johnston

Sorry Dave i did not realize I needed to do a make clean first.

This has been commited.

Quoted 8 lines

Thanks
--Rich

commit ddd5a16201db90a255952f61c34aeaab67d0a845

Author: Dave Chinner <[email protected]>
Date:   Mon Sep 30 03:15:21 2013 +0000

xfs: unify directory/attribute format definitions

FWIW, this is another patch that has not yet been committed to the kernel code yet.

Cheers,

Dave.

Signature · 7 lines
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#34 lore raw

PATCH 10/32 xfs: split dquot buffer operations out

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Parts of userspace want to be able to read and modify dquot buffers (e.g. xfs_db) so we need to split out the reading and writing of these buffers so it is easy to shared code with libxfs in userspace.

---
 include/libxfs.h       |   9 ++
 libxfs/Makefile        |   1 +
 libxfs/xfs_dquot_buf.c | 273 +++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 283 insertions(+)
 create mode 100644 libxfs/xfs_dquot_buf.c
include/libxfs.h +9 -0
index 835ba37..f10ab59 100644
@@ -216,6 +216,15 @@ typedef struct xfs_mount {
 	xfs_dablk_t		m_dirdatablk;	/* blockno of dir data v2 */
 	xfs_dablk_t		m_dirleafblk;	/* blockno of dir non-data v2 */
 	xfs_dablk_t		m_dirfreeblk;	/* blockno of dirfreeindex v2 */
+
+	/*
+	 * anonymous struct to allow xfs_dquot_buf.c to compile.
+	 * Pointer is always null in userspace, so code does not use it at all
+	 */
+	struct {
+		int	qi_dqperchunk;
+	}			*m_quotainfo;
+
 } xfs_mount_t;
 
 /*
libxfs/Makefile +1 -0
index f0cbae3..4522218 100644
@@ -29,6 +29,7 @@ CFILES = cache.c \
 	xfs_dir2_leaf.c \
 	xfs_dir2_node.c \
 	xfs_dir2_sf.c \
+	xfs_dquot_buf.c \
 	xfs_ialloc.c \
 	xfs_inode_buf.c \
 	xfs_inode_fork.c \
libxfs/xfs_dquot_buf.c new file +273 -0

273 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#35 lore raw

PATCH 11/32 xfs: decouple inode and bmap btree header files

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Currently the xfs_inode.h header has a dependency on the definition of the BMAP btree records as the inode fork includes an array of xfs_bmbt_rec_host_t objects in it's definition.

Move all the btree format definitions from xfs_btree.h, xfs_bmap_btree.h, xfs_alloc_btree.h and xfs_ialloc_btree.h to xfs_format.h to continue the process of centralising the on-disk format definitions. With this done, the xfs inode definitions are no longer dependent on btree header files.

The enables a massive culling of unnecessary includes, with close to 200 #include directives removed from the XFS kernel code base.

---
 include/xfs_alloc_btree.h  |  33 ------
 include/xfs_bmap_btree.h   | 103 -----------------
 include/xfs_btree.h        |  80 -------------
 include/xfs_format.h       | 281 +++++++++++++++++++++++++++++++++++++++++++++
 include/xfs_ialloc.h       |   3 +-
 include/xfs_ialloc_btree.h |  49 --------
 include/xfs_inode_fork.h   |   1 +
 7 files changed, 284 insertions(+), 266 deletions(-)
include/xfs_alloc_btree.h +0 -33
index 72676c3..45e189e 100644
@@ -27,39 +27,6 @@ struct xfs_btree_cur;
 struct xfs_mount;
 
 /*
- * There are two on-disk btrees, one sorted by blockno and one sorted
- * by blockcount and blockno.  All blocks look the same to make the code
- * simpler; if we have time later, we'll make the optimizations.
- */
-#define	XFS_ABTB_MAGIC		0x41425442	/* 'ABTB' for bno tree */
-#define	XFS_ABTB_CRC_MAGIC	0x41423342	/* 'AB3B' */
-#define	XFS_ABTC_MAGIC		0x41425443	/* 'ABTC' for cnt tree */
-#define	XFS_ABTC_CRC_MAGIC	0x41423343	/* 'AB3C' */
-
-/*
- * Data record/key structure
- */
-typedef struct xfs_alloc_rec {
-	__be32		ar_startblock;	/* starting block number */
-	__be32		ar_blockcount;	/* count of free blocks */
-} xfs_alloc_rec_t, xfs_alloc_key_t;
-
-typedef struct xfs_alloc_rec_incore {
-	xfs_agblock_t	ar_startblock;	/* starting block number */
-	xfs_extlen_t	ar_blockcount;	/* count of free blocks */
-} xfs_alloc_rec_incore_t;
-
-/* btree pointer type */
-typedef __be32 xfs_alloc_ptr_t;
-
-/*
- * Block numbers in the AG:
- * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
- */
-#define	XFS_BNO_BLOCK(mp)	((xfs_agblock_t)(XFS_AGFL_BLOCK(mp) + 1))
-#define	XFS_CNT_BLOCK(mp)	((xfs_agblock_t)(XFS_BNO_BLOCK(mp) + 1))
-
-/*
  * Btree block header size depends on a superblock flag.
  */
 #define XFS_ALLOC_BLOCK_LEN(mp) \
include/xfs_bmap_btree.h +0 -103

121 lines not on this page · raw message

include/xfs_btree.h +0 -80

86 lines not on this page · raw message

include/xfs_format.h +281 -0

285 lines not on this page · raw message

include/xfs_ialloc.h +2 -1
index 1557798..a8f76a5 100644
@@ -23,6 +23,7 @@ struct xfs_dinode;
 struct xfs_imap;
 struct xfs_mount;
 struct xfs_trans;
+struct xfs_btree_cur;
 
 /*
  * Allocation parameters for inode allocation.
@@ -42,7 +43,7 @@ struct xfs_trans;
 static inline struct xfs_dinode *
 xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
 {
-	return (xfs_dinode_t *)
+	return (struct xfs_dinode *)
 		(xfs_buf_offset(b, o << (mp)->m_sb.sb_inodelog));
 }
 
include/xfs_ialloc_btree.h +0 -49

55 lines not on this page · raw message

include/xfs_inode_fork.h +1 -0
index 28661a0..eb329a1 100644
@@ -19,6 +19,7 @@
 #define	__XFS_INODE_FORK_H__
 
 struct xfs_inode_log_item;
+struct xfs_dinode;
 
 /*
  * The following xfs_ext_irec_t struct introduces a second (top) level
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#36 lore raw

PATCH 12/32 libxfs: unify xfs_btree.c with kernel code

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

The libxfs/xfs_btree.c code does not contain a small amount of code for btree block readahead that the kernel code does. Instead, it short circuits it at a higher layer and doesn't include the lower layer functions. There is no harm in calling the lower lay functions and have them do nothing, and doing so unifies the kernel and userspace code.

---
 libxfs/xfs.h       |  8 +++++---
 libxfs/xfs_btree.c | 48 +++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 48 insertions(+), 8 deletions(-)
libxfs/xfs.h +5 -3
index 31acf1b..364fd83 100644
@@ -319,10 +319,12 @@ roundup_64(__uint64_t x, __uint32_t y)
 
 #define xfs_trans_buf_copy_type(dbp, sbp)
 
-#define xfs_buf_readahead(a,b,c,ops)		((void) 0)	/* no readahead */
+/* no readahead, need to avoid set-but-unused var warnings. */
+#define xfs_buf_readahead(a,d,c,ops)		({	\
+	xfs_daddr_t __d = d;				\
+	__d = __d; /* no set-but-unused warning */	\
+})
 #define xfs_buf_readahead_map(a,b,c,ops)	((void) 0)	/* no readahead */
-#define xfs_btree_reada_bufl(m,fsb,c,ops)	((void) 0)
-#define xfs_btree_reada_bufs(m,fsb,c,x,ops)	((void) 0)
 #define xfs_buftrace(x,y)			((void) 0)	/* debug only */
 
 #define xfs_cmn_err(tag,level,mp,fmt,args...)	cmn_err(level,fmt, ## args)
libxfs/xfs_btree.c +43 -5

84 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#37 lore raw

PATCH 13/32 libxfs: bmap btree owner swap support

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

For CRC enabled filesystems, we can't just swap inode forks from one inode to another when defragmenting a file - the blocks in the inode fork bmap btree contain pointers back to the owner inode. Hence if we are to swap the inode forks we have to atomically modify every block in the btree during the transaction.

This patch brings across the kernel code for doing the owner swap of an entire fork - something that we are likely to end up needing in xfs_repair when reparenting stray inodes to lost+found - without all the associated swap extents transaction and recovery cruft as those parts are not needed in userspace.

---
 include/xfs_bmap_btree.h |   4 ++
 include/xfs_btree.h      |  19 ++++--
 include/xfs_inode_buf.h  |  18 ++---
 include/xfs_log_format.h |   8 ++-
 libxfs/xfs_bmap_btree.c  |  44 ++++++++++++
 libxfs/xfs_btree.c       | 170 ++++++++++++++++++++++++++++++++++++++++++-----
 6 files changed, 227 insertions(+), 36 deletions(-)
include/xfs_bmap_btree.h +4 -0
index 2379d33..6e42e1e 100644
@@ -133,6 +133,10 @@ extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level);
 extern int xfs_bmdr_maxrecs(struct xfs_mount *, int blocklen, int leaf);
 extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
 
+extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
+				 int whichfork, xfs_ino_t new_owner,
+				 struct list_head *buffer_list);
+
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
 
include/xfs_btree.h +12 -7
index 227bfa5..6afe0b2 100644
@@ -41,15 +41,18 @@ extern kmem_zone_t	*xfs_btree_cur_zone;
 /*
  * For logging record fields.
  */
-#define	XFS_BB_MAGIC		0x01
-#define	XFS_BB_LEVEL		0x02
-#define	XFS_BB_NUMRECS		0x04
-#define	XFS_BB_LEFTSIB		0x08
-#define	XFS_BB_RIGHTSIB		0x10
-#define	XFS_BB_BLKNO		0x20
+#define	XFS_BB_MAGIC		(1 << 0)
+#define	XFS_BB_LEVEL		(1 << 1)
+#define	XFS_BB_NUMRECS		(1 << 2)
+#define	XFS_BB_LEFTSIB		(1 << 3)
+#define	XFS_BB_RIGHTSIB		(1 << 4)
+#define	XFS_BB_BLKNO		(1 << 5)
+#define	XFS_BB_LSN		(1 << 6)
+#define	XFS_BB_UUID		(1 << 7)
+#define	XFS_BB_OWNER		(1 << 8)
 #define	XFS_BB_NUM_BITS		5
 #define	XFS_BB_ALL_BITS		((1 << XFS_BB_NUM_BITS) - 1)
-#define	XFS_BB_NUM_BITS_CRC	8
+#define	XFS_BB_NUM_BITS_CRC	9
 #define	XFS_BB_ALL_BITS_CRC	((1 << XFS_BB_NUM_BITS_CRC) - 1)
 
 /*
@@ -381,6 +384,8 @@ int xfs_btree_new_iroot(struct xfs_btree_cur *, int *, int *);
 int xfs_btree_insert(struct xfs_btree_cur *, int *);
 int xfs_btree_delete(struct xfs_btree_cur *, int *);
 int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *);
+int xfs_btree_change_owner(struct xfs_btree_cur *cur, __uint64_t new_owner,
+			   struct list_head *buffer_list);
 
 /*
  * btree block CRC helpers
include/xfs_inode_buf.h +9 -9
index e8fd3bd..9308c47 100644
@@ -32,17 +32,17 @@ struct xfs_imap {
 	ushort		im_boffset;	/* inode offset in block in bytes */
 };
 
-int		xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
-			       struct xfs_imap *, struct xfs_dinode **,
-			       struct xfs_buf **, uint, uint);
-int		xfs_iread(struct xfs_mount *, struct xfs_trans *,
-			  struct xfs_inode *, uint);
-void		xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
-void		xfs_dinode_to_disk(struct xfs_dinode *,
-				   struct xfs_icdinode *);
+int	xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
+		       struct xfs_imap *, struct xfs_dinode **,
+		       struct xfs_buf **, uint, uint);
+int	xfs_iread(struct xfs_mount *, struct xfs_trans *,
+		  struct xfs_inode *, uint);
+void	xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
+void	xfs_dinode_to_disk(struct xfs_dinode *to, struct xfs_icdinode *from);
+void	xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from);
 
 #if defined(DEBUG)
-void		xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
+void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #else
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
include/xfs_log_format.h +6 -2
index aeaa715..f0969c7 100644
@@ -302,6 +302,8 @@ typedef struct xfs_inode_log_format_64 {
 #define	XFS_ILOG_ADATA	0x040	/* log i_af.if_data */
 #define	XFS_ILOG_AEXT	0x080	/* log i_af.if_extents */
 #define	XFS_ILOG_ABROOT	0x100	/* log i_af.i_broot */
+#define XFS_ILOG_DOWNER	0x200	/* change the data fork owner on replay */
+#define XFS_ILOG_AOWNER	0x400	/* change the attr fork owner on replay */
 
 
 /*
@@ -315,7 +317,8 @@ typedef struct xfs_inode_log_format_64 {
 #define	XFS_ILOG_NONCORE	(XFS_ILOG_DDATA | XFS_ILOG_DEXT | \
 				 XFS_ILOG_DBROOT | XFS_ILOG_DEV | \
 				 XFS_ILOG_UUID | XFS_ILOG_ADATA | \
-				 XFS_ILOG_AEXT | XFS_ILOG_ABROOT)
+				 XFS_ILOG_AEXT | XFS_ILOG_ABROOT | \
+				 XFS_ILOG_DOWNER | XFS_ILOG_AOWNER)
 
 #define	XFS_ILOG_DFORK		(XFS_ILOG_DDATA | XFS_ILOG_DEXT | \
 				 XFS_ILOG_DBROOT)
@@ -327,7 +330,8 @@ typedef struct xfs_inode_log_format_64 {
 				 XFS_ILOG_DEXT | XFS_ILOG_DBROOT | \
 				 XFS_ILOG_DEV | XFS_ILOG_UUID | \
 				 XFS_ILOG_ADATA | XFS_ILOG_AEXT | \
-				 XFS_ILOG_ABROOT | XFS_ILOG_TIMESTAMP)
+				 XFS_ILOG_ABROOT | XFS_ILOG_TIMESTAMP | \
+				 XFS_ILOG_DOWNER | XFS_ILOG_AOWNER)
 
 static inline int xfs_ilog_fbroot(int w)
 {
libxfs/xfs_bmap_btree.c +44 -0

47 lines not on this page · raw message

libxfs/xfs_btree.c +152 -18

185 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#38 lore raw

PATCH 14/32 libxfs: xfs_rtalloc.c becomes xfs_rtbitmap.c

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

To match the split-up of the kernel xfs_rtalloc.c file, convert the libxfs version of xfs_rtalloc.c to match the newly shared kernel source file with all the realtime bitmap functions in it, xfs_rtbitmap.c.

---
 libxfs/Makefile       |   2 +-
 libxfs/xfs_rtalloc.c  | 776 ----------------------------------------
 libxfs/xfs_rtbitmap.c | 951 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 952 insertions(+), 777 deletions(-)
 delete mode 100644 libxfs/xfs_rtalloc.c
 create mode 100644 libxfs/xfs_rtbitmap.c
libxfs/Makefile +1 -1
index 4522218..ae15a5d 100644
@@ -35,7 +35,7 @@ CFILES = cache.c \
 	xfs_inode_fork.c \
 	xfs_ialloc_btree.c \
 	xfs_log_rlimit.c \
-	xfs_rtalloc.c \
+	xfs_rtbitmap.c \
 	xfs_sb.c \
 	xfs_symlink_remote.c \
 	xfs_trans_resv.c
libxfs/xfs_rtalloc.c deleted +0 -776

776 lines not on this page · raw message

libxfs/xfs_rtbitmap.c new file +951 -0

951 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#39 lore raw

PATCH 15/32 libxfs: bring across inode buffer readahead verifier changes

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

These were made for log recovery readahead in the kernel, so are not directly used in userspace. Hence bringing the change across is simply to keep files in sync.

---
 libxfs/xfs_inode_buf.c | 41 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 5 deletions(-)
libxfs/xfs_inode_buf.c +36 -5
index b096f77..67d5eb4 100644
@@ -46,9 +46,22 @@ xfs_inobp_check(
 }
 #endif
 
+/*
+ * If we are doing readahead on an inode buffer, we might be in log recovery
+ * reading an inode allocation buffer that hasn't yet been replayed, and hence
+ * has not had the inode cores stamped into it. Hence for readahead, the buffer
+ * may be potentially invalid.
+ *
+ * If the readahead buffer is invalid, we don't want to mark it with an error,
+ * but we do want to clear the DONE status of the buffer so that a followup read
+ * will re-read it from disk. This will ensure that we don't get an unnecessary
+ * warnings during log recovery and we don't get unnecssary panics on debug
+ * kernels.
+ */
 static void
 xfs_inode_buf_verify(
-	struct xfs_buf	*bp)
+	struct xfs_buf	*bp,
+	bool		readahead)
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 	int		i;
@@ -69,6 +82,11 @@ xfs_inode_buf_verify(
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {
+			if (readahead) {
+				bp->b_flags &= ~XBF_DONE;
+				return;
+			}
+
 			xfs_buf_ioerror(bp, EFSCORRUPTED);
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
 					     mp, dip);
@@ -87,14 +105,21 @@ static void
 xfs_inode_buf_read_verify(
 	struct xfs_buf	*bp)
 {
-	xfs_inode_buf_verify(bp);
+	xfs_inode_buf_verify(bp, false);
+}
+
+static void
+xfs_inode_buf_readahead_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_inode_buf_verify(bp, true);
 }
 
 static void
 xfs_inode_buf_write_verify(
 	struct xfs_buf	*bp)
 {
-	xfs_inode_buf_verify(bp);
+	xfs_inode_buf_verify(bp, false);
 }
 
 const struct xfs_buf_ops xfs_inode_buf_ops = {
@@ -102,6 +127,12 @@ const struct xfs_buf_ops xfs_inode_buf_ops = {
 	.verify_write = xfs_inode_buf_write_verify,
 };
 
+const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
+	.verify_read = xfs_inode_buf_readahead_verify,
+	.verify_write = xfs_inode_buf_write_verify,
+};
+
+
 /*
  * This routine is called to map an inode to the buffer containing the on-disk
  * version of the inode.  It returns a pointer to the buffer containing the
@@ -191,7 +222,7 @@ xfs_dinode_from_disk(
 		to->di_ino = be64_to_cpu(from->di_ino);
 		to->di_lsn = be64_to_cpu(from->di_lsn);
 		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-		platform_uuid_copy(&to->di_uuid, &from->di_uuid);
+		uuid_copy(&to->di_uuid, &from->di_uuid);
 	}
 }
 
@@ -237,7 +268,7 @@ xfs_dinode_to_disk(
 		to->di_ino = cpu_to_be64(from->di_ino);
 		to->di_lsn = cpu_to_be64(from->di_lsn);
 		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-		platform_uuid_copy(&to->di_uuid, &from->di_uuid);
+		uuid_copy(&to->di_uuid, &from->di_uuid);
 		to->di_flushiter = 0;
 	} else {
 		to->di_flushiter = cpu_to_be16(from->di_flushiter);
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#40 lore raw

PATCH 16/32 libxfs: Minor cleanup and bug fix sync

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

These bring all the small single line comment, whitespace and minor code differences into sync with the kernel code. Anything left at this point is an intentional difference.

---
 include/xfs_fs.h         | 4 ++--
 include/xfs_quota_defs.h | 4 ++++
 libxfs/xfs_attr_leaf.c   | 4 +---
 libxfs/xfs_bmap.c        | 6 +++---
 libxfs/xfs_bmap_btree.c  | 2 +-
 libxfs/xfs_dir2_leaf.c   | 1 -
 libxfs/xfs_dir2_node.c   | 2 +-
 libxfs/xfs_ialloc.c      | 4 ++--
 libxfs/xfs_inode_buf.c   | 2 ++
 libxfs/xfs_inode_fork.c  | 5 +++--
 libxfs/xfs_trans_resv.c  | 2 +-
 11 files changed, 20 insertions(+), 16 deletions(-)
include/xfs_fs.h +2 -2
index 53e33c2..18272c7 100644
@@ -357,7 +357,7 @@ typedef struct xfs_error_injection {
  * Speculative preallocation trimming.
  */
 #define XFS_EOFBLOCKS_VERSION		1
-struct xfs_eofblocks {
+struct xfs_fs_eofblocks {
 	__u32		eof_version;
 	__u32		eof_flags;
 	uid_t		eof_uid;
@@ -515,7 +515,7 @@ typedef struct xfs_swapext
 /*	XFS_IOC_GETBIOSIZE ---- deprecated 47	   */
 #define XFS_IOC_GETBMAPX	_IOWR('X', 56, struct getbmap)
 #define XFS_IOC_ZERO_RANGE	_IOW ('X', 57, struct xfs_flock64)
-#define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_eofblocks)
+#define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_fs_eofblocks)
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
include/xfs_quota_defs.h +4 -0
index e6b0d6e..b3b2b10 100644
@@ -154,4 +154,8 @@ typedef __uint16_t	xfs_qwarncnt_t;
 		(XFS_QMOPT_UQUOTA | XFS_QMOPT_PQUOTA | XFS_QMOPT_GQUOTA)
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
+extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
+		       xfs_dqid_t id, uint type, uint flags, char *str);
+extern int xfs_calc_dquots_per_chunk(struct xfs_mount *mp, unsigned int nbblks);
+
 #endif	/* __XFS_QUOTA_H__ */
libxfs/xfs_attr_leaf.c +1 -3
index c09b0f3..fd52397 100644
@@ -599,7 +599,7 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args)
 	xfs_attr_sf_entry_t *sfe;
 	int i;
 
-	ASSERT(args->dp->i_d.di_aformat == XFS_IFINLINE);
+	ASSERT(args->dp->i_afp->if_flags == XFS_IFINLINE);
 	sf = (xfs_attr_shortform_t *)args->dp->i_afp->if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
@@ -909,7 +909,6 @@ out:
 	return error;
 }
 
-
 /*========================================================================
  * Routines used for growing the Btree.
  *========================================================================*/
@@ -1270,7 +1269,6 @@ xfs_attr3_leaf_compact(
 	ichdr_dst->freemap[0].size = ichdr_dst->firstused -
 						ichdr_dst->freemap[0].base;
 
-
 	/* write the header back to initialise the underlying buffer */
 	xfs_attr3_leaf_hdr_to_disk(leaf_dst, ichdr_dst);
 
libxfs/xfs_bmap.c +3 -3
index 7336abf..3e80c64 100644
@@ -510,8 +510,8 @@ xfs_bmap_trace_exlist(
 
 /*
  * Validate that the bmbt_irecs being returned from bmapi are valid
- * given the callers original parameters.  Specifically check the
- * ranges of the returned irecs to ensure that they only extent beyond
+ * given the caller's original parameters.  Specifically check the
+ * ranges of the returned irecs to ensure that they only extend beyond
  * the given parameters if the XFS_BMAPI_ENTIRE flag was set.
  */
 STATIC void
@@ -1515,7 +1515,7 @@ xfs_bmap_first_unused(
 }
 
 /*
- * Returns the file-relative block number of the last block + 1 before
+ * Returns the file-relative block number of the last block - 1 before
  * last_block (input value) in the file.
  * This is not based on i_size, it is based on the extent records.
  * Returns 0 for local files, as they do not have extent records.
libxfs/xfs_bmap_btree.c +1 -1
index 2f6b48a..6211dc2 100644
@@ -737,7 +737,7 @@ xfs_bmbt_verify(
 	 * precise.
 	 */
 	level = be16_to_cpu(block->bb_level);
-	if (level > MAX(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
+	if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
 		return false;
 	if (be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
 		return false;
libxfs/xfs_dir2_leaf.c +0 -1
index c035c4d..683536e 100644
@@ -1072,7 +1072,6 @@ xfs_dir3_leaf_compact_x1(
 	*highstalep = highstale;
 }
 
-
 /*
  * Log the bests entries indicated from a leaf1 block.
  */
libxfs/xfs_dir2_node.c +1 -1
index 6a245e5..10d1d81 100644
@@ -1796,7 +1796,7 @@ xfs_dir2_node_addname_int(
 		/*
 		 * Look at the current free entry.  Is it good enough?
 		 *
-		 * The bests initialisation should be where the buffer is read in
+		 * The bests initialisation should be where the bufer is read in
 		 * the above branch. But gcc is too stupid to realise that bests
 		 * and the freehdr are actually initialised if they are placed
 		 * there, so we have to do it here to avoid warnings. Blech.
libxfs/xfs_ialloc.c +2 -2
index 4683287..afe1a82 100644
@@ -484,7 +484,7 @@ xfs_ialloc_next_ag(
 
 /*
  * Select an allocation group to look for a free inode in, based on the parent
- * inode and then mode.  Return the allocation group buffer.
+ * inode and the mode.  Return the allocation group buffer.
  */
 STATIC xfs_agnumber_t
 xfs_ialloc_ag_select(
@@ -706,7 +706,7 @@ xfs_dialloc_ag(
 		error = xfs_inobt_get_rec(cur, &rec, &j);
 		if (error)
 			goto error0;
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+		XFS_WANT_CORRUPTED_GOTO(j == 1, error0);
 
 		if (rec.ir_freecount > 0) {
 			/*
libxfs/xfs_inode_buf.c +2 -0
index 67d5eb4..b796556 100644
@@ -101,6 +101,7 @@ xfs_inode_buf_verify(
 	xfs_inobp_check(mp, bp);
 }
 
+
 static void
 xfs_inode_buf_read_verify(
 	struct xfs_buf	*bp)
@@ -299,6 +300,7 @@ xfs_dinode_verify(
 		return false;
 	return true;
 }
+
 void
 xfs_dinode_calc_crc(
 	struct xfs_mount	*mp,
libxfs/xfs_inode_fork.c +3 -2
index 1c006f9..190690c 100644
@@ -138,7 +138,8 @@ xfs_iformat_fork(
 			}
 
 			di_size = be64_to_cpu(dip->di_size);
-			if (unlikely(di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
+			if (unlikely(di_size < 0 ||
+				     di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
 				xfs_warn(ip->i_mount,
 			"corrupt inode %Lu (bad size %Ld for local inode).",
 					(unsigned long long) ip->i_ino,
@@ -444,7 +445,7 @@ xfs_iread_extents(
  *
  * The caller must not request to add more records than would fit in
  * the on-disk inode root.  If the if_broot is currently NULL, then
- * if we adding records one will be allocated.  The caller must also
+ * if we are adding records, one will be allocated.  The caller must also
  * not request that the number of records go below zero, although
  * it can go to zero.
  *
libxfs/xfs_trans_resv.c +1 -1
index 3e14b1c..1e59fad 100644
@@ -49,7 +49,7 @@ xfs_calc_buf_res(
 
 /*
  * Logging inodes is really tricksy. They are logged in memory format,
- * which means that what we write into the log doesn't directory translate into
+ * which means that what we write into the log doesn't directly translate into
  * the amount of space they use on disk.
  *
  * Case in point - btree format forks in memory format use more space than the
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#41 lore raw

PATCH 17/32 db: separate out straight buffer IO from map based IO.

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

First step in converting to libxfs based IO.

---
 db/init.c |   7 ++--
 db/io.c   | 125 +++++++++++++++++++++++++++++++++++++++++++++++++-------------
 db/io.h   |   5 +--
 3 files changed, 104 insertions(+), 33 deletions(-)
db/init.c +3 -4
index 2932e51..0e88b56 100644
@@ -55,7 +55,7 @@ init(
 	char		**argv)
 {
 	xfs_sb_t	*sbp;
-	void		*bufp = NULL;
+	char		bufp[BBSIZE];
 	int		c;
 
 	setlocale(LC_ALL, "");
@@ -115,15 +115,14 @@ init(
 		exit(1);
 	}
 
-	if (read_bbs(XFS_SB_DADDR, 1, &bufp, NULL)) {
+	if (read_buf(XFS_SB_DADDR, 1, bufp)) {
 		fprintf(stderr, _("%s: %s is invalid (cannot read first 512 "
 			"bytes)\n"), progname, fsdevice);
 		exit(1);
 	}
 
 	/* copy SB from buffer to in-core, converting architecture as we go */
-	libxfs_sb_from_disk(&xmount.m_sb, bufp);
-	xfree(bufp);
+	libxfs_sb_from_disk(&xmount.m_sb, (struct xfs_dsb *)bufp);
 
 	sbp = &xmount.m_sb;
 	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
db/io.c +100 -25

199 lines not on this page · raw message

db/io.h +1 -4
index 549aad9..9ea6223 100644
@@ -52,10 +52,7 @@ extern void	off_cur(int off, int len);
 extern void	pop_cur(void);
 extern void	print_iocur(char *tag, iocur_t *ioc);
 extern void	push_cur(void);
-extern int	read_bbs(__int64_t daddr, int count, void **bufp,
-			 bbmap_t *bbmap);
-extern int	write_bbs(__int64_t daddr, int count, void *bufp,
-			  bbmap_t *bbmap);
+extern int	read_buf(__int64_t daddr, int count, void *bufp);
 extern void     write_cur(void);
 extern void	set_cur(const struct typ *t, __int64_t d, int c, int ring_add,
 			bbmap_t *bbmap);
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#42 lore raw

PATCH 18/32 db: rewrite bbmap to use xfs_buf_map

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Use the libxfs struct xfs_buf_map for recording the extent layout of discontiguous buffers and convert the read/write to decode them directory and use read_buf/write_buf to do the extent IO. This brings the physical xfs_db IO code to be very close to the model that libxfs uses.

---
 db/bmap.c | 15 ++++-----------
 db/io.c   | 58 ++++++++++++----------------------------------------------
 db/io.h   |  3 ++-
 3 files changed, 18 insertions(+), 58 deletions(-)
db/bmap.c +4 -11
index 0ef7a62..3951b9f 100644
@@ -293,20 +293,13 @@ make_bbmap(
 	int		nex,
 	bmap_ext_t	*bmp)
 {
-	int		d;
-	xfs_dfsbno_t	dfsbno;
 	int		i;
-	int		j;
-	int		k;
 
-	for (i = 0, d = 0; i < nex; i++) {
-		dfsbno = bmp[i].startblock;
-		for (j = 0; j < bmp[i].blockcount; j++, dfsbno++) {
-			for (k = 0; k < blkbb; k++)
-				bbmap->b[d++] =
-					XFS_FSB_TO_DADDR(mp, dfsbno) + k;
-		}
+	for (i = 0; i < nex; i++) {
+		bbmap->b[i].bm_bn = XFS_FSB_TO_DADDR(mp, bmp[i].startblock);
+		bbmap->b[i].bm_len = XFS_FSB_TO_BB(mp, bmp[i].blockcount);
 	}
+	bbmap->nmaps = nex;
 }
 
 static xfs_fsblock_t
db/io.c +12 -46

85 lines not on this page · raw message

db/io.h +2 -1
index 9ea6223..c7641d5 100644
@@ -20,7 +20,8 @@ struct typ;
 
 #define	BBMAP_SIZE		(XFS_MAX_BLOCKSIZE / BBSIZE)
 typedef struct bbmap {
-	__int64_t		b[BBMAP_SIZE];
+	int			nmaps;
+	struct xfs_buf_map	b[BBMAP_SIZE];
 } bbmap_t;
 
 typedef struct iocur {
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#43 lore raw

PATCH 19/32 db: rewrite IO engine to use libxfs

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Now that we have buffers and xfs_buf_maps, it is relatively easy to convert the IO engine to use libxfs routines. This gets rid of the most of the differences between mapped and straight buffer reads, and tracks xfs_bufs directly in the IO context that is being used.

This is not yet a perfect solution, as xfs_db does different sized IOs for the same block range which will throw warnings like:

xfs_db> inode 64
7ffff7fde740: Badness in key lookup (length) bp=(bno 0x40, len 8192 bytes) key=(bno 0x40, len 4096 bytes) xfs_db>

This is when first displaying an inode in the root inode chunk. These will need to be dealt with on a case by case basis.

---
 db/init.c        |  25 ++++++--
 db/io.c          | 176 ++++++++++++++-----------------------------------------
 db/io.h          |   4 +-
 include/libxfs.h |   3 +
 libxfs/init.c    |   5 ++
 libxfs/rdwr.c    |  61 ++++++++++++-------
 6 files changed, 116 insertions(+), 158 deletions(-)
db/init.c +21 -4
index 0e88b56..b1cddca 100644
@@ -54,8 +54,8 @@ init(
 	int		argc,
 	char		**argv)
 {
-	xfs_sb_t	*sbp;
-	char		bufp[BBSIZE];
+	struct xfs_sb	*sbp;
+	struct xfs_buf	*bp;
 	int		c;
 
 	setlocale(LC_ALL, "");
@@ -115,14 +115,25 @@ init(
 		exit(1);
 	}
 
-	if (read_buf(XFS_SB_DADDR, 1, bufp)) {
+	/*
+	 * Read the superblock, but don't validate it - we are a diagnostic
+	 * tool and so need to be able to mount busted filesystems.
+	 */
+	memset(&xmount, 0, sizeof(struct xfs_mount));
+	libxfs_buftarg_init(&xmount, x.ddev, x.logdev, x.rtdev);
+	bp = libxfs_readbuf(xmount.m_ddev_targp, XFS_SB_DADDR,
+			    1 << (XFS_MAX_SECTORSIZE_LOG - BBSHIFT), 0, NULL);
+
+	if (!bp || bp->b_error) {
 		fprintf(stderr, _("%s: %s is invalid (cannot read first 512 "
 			"bytes)\n"), progname, fsdevice);
 		exit(1);
 	}
 
 	/* copy SB from buffer to in-core, converting architecture as we go */
-	libxfs_sb_from_disk(&xmount.m_sb, (struct xfs_dsb *)bufp);
+	libxfs_sb_from_disk(&xmount.m_sb, XFS_BUF_TO_SBP(bp));
+	libxfs_putbuf(bp);
+	libxfs_purgebuf(bp);
 
 	sbp = &xmount.m_sb;
 	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
@@ -201,6 +212,12 @@ main(
 	}
 
 close_devices:
+	/*
+	 * make sure that we pop the last buffer context we held so that the
+	 * buffer is released before purge the caches during unmount.
+	 */
+	pop_cur();
+	libxfs_umount(mp);
 	if (x.ddev)
 		libxfs_device_close(x.ddev);
 	if (x.logdev && x.logdev != x.ddev)
db/io.c +45 -131

261 lines not on this page · raw message

db/io.h +2 -2
index c7641d5..2c47ccc 100644
@@ -36,8 +36,8 @@ typedef struct iocur {
 	__uint16_t		mode;	/* current inode's mode */
 	xfs_off_t		off;	/* fs offset of "data" in bytes */
 	const struct typ	*typ;	/* type of "data" */
-	int			use_bbmap; /* set if bbmap is valid */
-	bbmap_t			bbmap;	/* map daddr if fragmented */
+	bbmap_t			*bbmap;	/* map daddr if fragmented */
+	struct xfs_buf		*bp;	/* underlying buffer */
 } iocur_t;
 
 #define DB_RING_ADD 1                   /* add to ring on set_cur */
include/libxfs.h +3 -0
index f10ab59..08fd0b3 100644
@@ -447,7 +447,10 @@ extern xfs_buf_t *libxfs_getbufr(struct xfs_buftarg *, xfs_daddr_t, int);
 extern void	libxfs_putbufr(xfs_buf_t *);
 
 extern int	libxfs_writebuf_int(xfs_buf_t *, int);
+extern int	libxfs_writebufr(struct xfs_buf *);
 extern int	libxfs_readbufr(struct xfs_buftarg *, xfs_daddr_t, xfs_buf_t *, int, int);
+extern int	libxfs_readbufr_map(struct xfs_buftarg *, struct xfs_buf *,
+				    struct xfs_buf_map *, int, int);
 
 extern int libxfs_bhash_size;
 extern int libxfs_ihash_size;
libxfs/init.c +5 -0
index db7eeea..229aa50 100644
@@ -688,6 +688,9 @@ libxfs_mount(
 	libxfs_buftarg_init(mp, dev, logdev, rtdev);
 
 	mp->m_flags = (LIBXFS_MOUNT_32BITINODES|LIBXFS_MOUNT_32BITINOOPT);
+	if (flags & LIBXFS_MOUNT_ROOTINOS)
+		mp->m_flags |= LIBXFS_MOUNT_ROOTINOS;
+
 	mp->m_sb = *sb;
 	INIT_RADIX_TREE(&mp->m_perag_tree, GFP_KERNEL);
 	sbp = &(mp->m_sb);
@@ -866,6 +869,8 @@ libxfs_umount(xfs_mount_t *mp)
 	int			agno;
 
 	libxfs_rtmount_destroy(mp);
+	if ((mp->m_flags & LIBXFS_MOUNT_ROOTINOS) && mp->m_rootip)
+		libxfs_iput(mp->m_rootip, 0);
 	libxfs_icache_purge();
 	libxfs_bcache_purge();
 
libxfs/rdwr.c +40 -21

76 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#44 lore raw

PATCH 20/32 db: introduce verifier support into set_cur

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

To be able to use read and write verifiers, we need to pass the verifier to the IO routines. We do this via the set_cur() function used to trigger reading the buffer.

For most metadata types, there is only one type of verifier needed. For these, we can simply add the verifier to the type table entry for the given type and use that directly. This type entry is already carried around by the IO context, so if we ever need to get it again we have direct access to it in the context we'll be doing IO.

Only attach the verifiers to the v5 filesystem type table; there is not need for them on v4 filesystems as we don't have to verify or calculate CRCs for them.

There are some metadata types that have more than one buffer format, or aren't based in directly in buffers. For these, leave the type table verifier NULL for now - these will need to be addressed individually.

---
 db/io.c   | 13 +++++++---
 db/type.c | 88 ++++++++++++++++++++++++++++++++++-----------------------------
 db/type.h |  1 +
 3 files changed, 59 insertions(+), 43 deletions(-)
db/io.c +10 -3
index 9129963..c9452f2 100644
@@ -480,12 +480,14 @@ set_cur(
 	xfs_ino_t	dirino;
 	xfs_ino_t	ino;
 	__uint16_t	mode;
+	const struct xfs_buf_ops *ops = t ? t->bops : NULL;
 
 	if (iocur_sp < 0) {
 		dbprintf(_("set_cur no stack element to set\n"));
 		return;
 	}
 
+
 	ino = iocur_top->ino;
 	dirino = iocur_top->dirino;
 	mode = iocur_top->mode;
@@ -507,12 +509,17 @@ set_cur(
 			return;
 		memcpy(iocur_top->bbmap, bbmap, sizeof(struct bbmap));
 		bp = libxfs_readbuf_map(mp->m_ddev_targp, bbmap->b,
-					bbmap->nmaps, 0, NULL);
+					bbmap->nmaps, 0, ops);
 	} else {
-		bp = libxfs_readbuf(mp->m_ddev_targp, d, c, 0, NULL);
+		bp = libxfs_readbuf(mp->m_ddev_targp, d, c, 0, ops);
 		iocur_top->bbmap = NULL;
 	}
-	if (!bp || bp->b_error)
+
+	/*
+	 * keep the buffer even if the verifier says it is corrupted.
+	 * We're a diagnostic tool, after all.
+	 */
+	if (!bp || (bp->b_error && bp->b_error != EFSCORRUPTED))
 		return;
 	iocur_top->buf = bp->b_addr;
 	iocur_top->bp = bp;
db/type.c +48 -40

98 lines not on this page · raw message

db/type.h +1 -0
index c41aca4d..3bb26f1 100644
@@ -42,6 +42,7 @@ typedef struct typ
 	char			*name;
 	pfunc_t			pfunc;
 	const struct field	*fields;
+	const struct xfs_buf_ops *bops;
 } typ_t;
 extern const typ_t	*typtab, *cur_typ;
 
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#45 lore raw

PATCH 21/32 db: indicate if the CRC on a buffer is correct or not

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

When dumping metadata that has a CRC in it, output not only the CRC but text to tell us whether the value is correct or not. Hence we can see at a glance if there's something wrong or not.

Do this by peeking at the buffer attached to the current IO contexted. If there was a CRC error, then it will be marked with a EFSCORRUPTED error. Use this to determine what to output.

---
 db/agf.c     |  2 +-
 db/agfl.c    |  2 +-
 db/agi.c     |  2 +-
 db/btblock.c | 10 +++++-----
 db/dir2.c    |  4 ++--
 db/dquot.c   |  2 +-
 db/field.c   |  5 +++++
 db/field.h   |  4 ++++
 db/fprint.c  | 39 +++++++++++++++++++++++++++++++++++++++
 db/fprint.h  |  2 ++
 db/inode.c   |  2 +-
 db/io.h      |  6 ++++++
 db/sb.c      |  2 +-
 db/symlink.c |  2 +-
 14 files changed, 70 insertions(+), 14 deletions(-)
db/agf.c +1 -1
index 389cb43..d9a07ca 100644
@@ -71,7 +71,7 @@ const field_t	agf_flds[] = {
 	{ "btreeblks", FLDT_UINT32D, OI(OFF(btreeblks)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(uuid)), C1, 0, TYP_NONE },
 	{ "lsn", FLDT_UINT64X, OI(OFF(lsn)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(crc)), C1, 0, TYP_NONE },
 	{ NULL }
 };
 
db/agfl.c +1 -1
index e2340e6..b29538f 100644
@@ -58,7 +58,7 @@ const field_t	agfl_crc_flds[] = {
 	{ "seqno", FLDT_AGNUMBER, OI(OFF(seqno)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(uuid)), C1, 0, TYP_NONE },
 	{ "lsn", FLDT_UINT64X, OI(OFF(lsn)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(crc)), C1, 0, TYP_NONE },
 	{ "bno", FLDT_AGBLOCKNZ, OI(OFF(bno)), agfl_bno_size,
 	  FLD_ARRAY|FLD_COUNT, TYP_DATA },
 	{ NULL }
db/agi.c +1 -1
index 6b2e889..398bdbb 100644
@@ -56,7 +56,7 @@ const field_t	agi_flds[] = {
 	  CI(XFS_AGI_UNLINKED_BUCKETS), FLD_ARRAY, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(uuid)), C1, 0, TYP_NONE },
 	{ "lsn", FLDT_UINT64X, OI(OFF(lsn)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(crc)), C1, 0, TYP_NONE },
 	{ NULL }
 };
 
db/btblock.c +5 -5
index 34188db..1ea0cff 100644
@@ -295,7 +295,7 @@ const field_t	bmapbta_crc_flds[] = {
 	{ "lsn", FLDT_UINT64X, OI(OFF(u.l.bb_lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(u.l.bb_uuid)), C1, 0, TYP_NONE },
 	{ "owner", FLDT_INO, OI(OFF(u.l.bb_owner)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(u.l.bb_crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(u.l.bb_crc)), C1, 0, TYP_NONE },
 	{ "recs", FLDT_BMAPBTAREC, btblock_rec_offset, btblock_rec_count,
 	  FLD_ARRAY|FLD_ABASE1|FLD_COUNT|FLD_OFFSET, TYP_NONE },
 	{ "keys", FLDT_BMAPBTAKEY, btblock_key_offset, btblock_key_count,
@@ -314,7 +314,7 @@ const field_t	bmapbtd_crc_flds[] = {
 	{ "lsn", FLDT_UINT64X, OI(OFF(u.l.bb_lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(u.l.bb_uuid)), C1, 0, TYP_NONE },
 	{ "owner", FLDT_INO, OI(OFF(u.l.bb_owner)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(u.l.bb_crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(u.l.bb_crc)), C1, 0, TYP_NONE },
 	{ "recs", FLDT_BMAPBTDREC, btblock_rec_offset, btblock_rec_count,
 	  FLD_ARRAY|FLD_ABASE1|FLD_COUNT|FLD_OFFSET, TYP_NONE },
 	{ "keys", FLDT_BMAPBTDKEY, btblock_key_offset, btblock_key_count,
@@ -405,7 +405,7 @@ const field_t	inobt_crc_flds[] = {
 	{ "lsn", FLDT_UINT64X, OI(OFF(u.s.bb_lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(u.s.bb_uuid)), C1, 0, TYP_NONE },
 	{ "owner", FLDT_AGNUMBER, OI(OFF(u.s.bb_owner)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(u.s.bb_crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(u.s.bb_crc)), C1, 0, TYP_NONE },
 	{ "recs", FLDT_INOBTREC, btblock_rec_offset, btblock_rec_count,
 	  FLD_ARRAY|FLD_ABASE1|FLD_COUNT|FLD_OFFSET, TYP_NONE },
 	{ "keys", FLDT_INOBTKEY, btblock_key_offset, btblock_key_count,
@@ -471,7 +471,7 @@ const field_t	bnobt_crc_flds[] = {
 	{ "lsn", FLDT_UINT64X, OI(OFF(u.s.bb_lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(u.s.bb_uuid)), C1, 0, TYP_NONE },
 	{ "owner", FLDT_AGNUMBER, OI(OFF(u.s.bb_owner)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(u.s.bb_crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(u.s.bb_crc)), C1, 0, TYP_NONE },
 	{ "recs", FLDT_BNOBTREC, btblock_rec_offset, btblock_rec_count,
 	  FLD_ARRAY|FLD_ABASE1|FLD_COUNT|FLD_OFFSET, TYP_NONE },
 	{ "keys", FLDT_BNOBTKEY, btblock_key_offset, btblock_key_count,
@@ -533,7 +533,7 @@ const field_t	cntbt_crc_flds[] = {
 	{ "lsn", FLDT_UINT64X, OI(OFF(u.s.bb_lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(u.s.bb_uuid)), C1, 0, TYP_NONE },
 	{ "owner", FLDT_AGNUMBER, OI(OFF(u.s.bb_owner)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(u.s.bb_crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(u.s.bb_crc)), C1, 0, TYP_NONE },
 	{ "recs", FLDT_CNTBTREC, btblock_rec_offset, btblock_rec_count,
 	  FLD_ARRAY|FLD_ABASE1|FLD_COUNT|FLD_OFFSET, TYP_NONE },
 	{ "keys", FLDT_CNTBTKEY, btblock_key_offset, btblock_key_count,
db/dir2.c +2 -2
index 8b08d48..2ec64e0 100644
@@ -922,7 +922,7 @@ const field_t	dir3_data_union_flds[] = {
 #define	DBH3OFF(f)	bitize(offsetof(struct xfs_dir3_blk_hdr, f))
 const field_t	dir3_blkhdr_flds[] = {
 	{ "magic", FLDT_UINT32X, OI(DBH3OFF(magic)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(DBH3OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(DBH3OFF(crc)), C1, 0, TYP_NONE },
 	{ "bno", FLDT_DFSBNO, OI(DBH3OFF(blkno)), C1, 0, TYP_BMAPBTD },
 	{ "lsn", FLDT_UINT64X, OI(DBH3OFF(lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(DBH3OFF(uuid)), C1, 0, TYP_NONE },
@@ -959,7 +959,7 @@ const field_t	dir3_free_hdr_flds[] = {
 #define	DB3OFF(f)	bitize(offsetof(struct xfs_da3_blkinfo, f))
 const field_t	da3_blkinfo_flds[] = {
 	{ "hdr", FLDT_DA_BLKINFO, OI(DB3OFF(hdr)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(DB3OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(DB3OFF(crc)), C1, 0, TYP_NONE },
 	{ "bno", FLDT_DFSBNO, OI(DB3OFF(blkno)), C1, 0, TYP_BMAPBTD },
 	{ "lsn", FLDT_UINT64X, OI(DB3OFF(lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(DB3OFF(uuid)), C1, 0, TYP_NONE },
db/dquot.c +1 -1
index 6927956..2f7d463 100644
@@ -48,7 +48,7 @@ const field_t	dqblk_flds[] = {
 	{ "diskdq", FLDT_DISK_DQUOT, OI(DDOFF(diskdq)), C1, 0, TYP_NONE },
 	{ "fill", FLDT_CHARS, OI(DDOFF(fill)), CI(DDSZC(fill)), FLD_SKIPALL,
 	  TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(DDOFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(DDOFF(crc)), C1, 0, TYP_NONE },
 	{ "lsn", FLDT_UINT64X, OI(DDOFF(lsn)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(DDOFF(uuid)), C1, 0, TYP_NONE },
 	{ NULL }
db/field.c +5 -0
index c6d7404..4582097 100644
@@ -163,6 +163,11 @@ const ftattr_t	ftattrtab[] = {
 	  0, fa_agblock, NULL },
 	{ FLDT_CNTBTREC, "cntbtrec", fp_sarray, (char *)cntbt_rec_flds,
 	  SI(bitsz(xfs_alloc_rec_t)), 0, NULL, cntbt_rec_flds },
+
+/* CRC field */
+	{ FLDT_CRC, "crc", fp_crc, "%#x (%s)", SI(bitsz(__uint32_t)),
+	  0, NULL, NULL },
+
 	{ FLDT_DEV, "dev", fp_num, "%#x", SI(bitsz(xfs_dev_t)), 0, NULL, NULL },
 	{ FLDT_DFILOFFA, "dfiloffa", fp_num, "%llu", SI(bitsz(xfs_dfiloff_t)),
 	  0, fa_dfiloffa, NULL },
db/field.h +4 -0
index aecdf9f..6343c9a 100644
@@ -80,6 +80,10 @@ typedef enum fldt	{
 	FLDT_CNTBTKEY,
 	FLDT_CNTBTPTR,
 	FLDT_CNTBTREC,
+
+	/* CRC field type */
+	FLDT_CRC,
+
 	FLDT_DEV,
 	FLDT_DFILOFFA,
 	FLDT_DFILOFFD,
db/fprint.c +39 -0
index 1d2f29c..435d984 100644
@@ -30,6 +30,7 @@
 #include "output.h"
 #include "sig.h"
 #include "malloc.h"
+#include "io.h"
 
 int
 fp_charns(
@@ -184,3 +185,41 @@ fp_uuid(
 	}
 	return 1;
 }
+
+/*
+ * CRC is correct is the current buffer it is being pulled out
+ * of is not marked with a EFSCORRUPTED error.
+ */
+int
+fp_crc(
+	void	*obj,
+	int	bit,
+	int	count,
+	char	*fmtstr,
+	int	size,
+	int	arg,
+	int	base,
+	int	array)
+{
+	int		bitpos;
+	int		i;
+	__int64_t	val;
+	char		*ok;
+
+	ok = iocur_crc_valid() ? "correct" : "bad";
+
+	for (i = 0, bitpos = bit;
+	     i < count && !seenint();
+	     i++, bitpos += size) {
+		if (array)
+			dbprintf("%d:", i + base);
+		val = getbitval(obj, bitpos, size, BVUNSIGNED);
+		if (size > 32)
+			dbprintf(fmtstr, val, ok);
+		else
+			dbprintf(fmtstr, (__int32_t)val, ok);
+		if (i < count - 1)
+			dbprintf(" ");
+	}
+	return 1;
+}
db/fprint.h +2 -0
index b032dbd..6a6d77e 100644
@@ -29,3 +29,5 @@ extern int	fp_time(void *obj, int bit, int count, char *fmtstr, int size,
 			int arg, int base, int array);
 extern int	fp_uuid(void *obj, int bit, int count, char *fmtstr, int size,
 			int arg, int base, int array);
+extern int	fp_crc(void *obj, int bit, int count, char *fmtstr, int size,
+		       int arg, int base, int array);
db/inode.c +1 -1
index 634dc30..ec533ee 100644
@@ -168,7 +168,7 @@ const field_t	inode_core_flds[] = {
 };
 
 const field_t	inode_v3_flds[] = {
-	{ "crc", FLDT_UINT32X, OI(COFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(COFF(crc)), C1, 0, TYP_NONE },
 	{ "change_count", FLDT_UINT64D, OI(COFF(changecount)), C1, 0, TYP_NONE },
 	{ "lsn", FLDT_UINT64X, OI(COFF(lsn)), C1, 0, TYP_NONE },
 	{ "flags2", FLDT_UINT64X, OI(COFF(flags2)), C1, 0, TYP_NONE },
db/io.h +6 -0
index 2c47ccc..d647284 100644
@@ -58,3 +58,9 @@ extern void     write_cur(void);
 extern void	set_cur(const struct typ *t, __int64_t d, int c, int ring_add,
 			bbmap_t *bbmap);
 extern void     ring_add(void);
+
+static inline bool
+iocur_crc_valid()
+{
+	return (iocur_top->bp && iocur_top->bp->b_error != EFSCORRUPTED);
+}
db/sb.c +1 -1
index d178f58..b36abf8 100644
@@ -118,7 +118,7 @@ const field_t	sb_flds[] = {
 		C1, 0, TYP_NONE },
 	{ "features_log_incompat", FLDT_UINT32X, OI(OFF(features_log_incompat)),
 		C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(crc)), C1, 0, TYP_NONE },
 	{ "pquotino", FLDT_INO, OI(OFF(pquotino)), C1, 0, TYP_INODE },
 	{ "lsn", FLDT_UINT64X, OI(OFF(lsn)), C1, 0, TYP_NONE },
 	{ NULL }
db/symlink.c +1 -1
index 9f3d0b9..a4f420f 100644
@@ -69,7 +69,7 @@ const struct field	symlink_crc_flds[] = {
 	{ "magic", FLDT_UINT32X, OI(OFF(magic)), C1, 0, TYP_NONE },
 	{ "offset", FLDT_UINT32D, OI(OFF(offset)), C1, 0, TYP_NONE },
 	{ "bytes", FLDT_UINT32D, OI(OFF(bytes)), C1, 0, TYP_NONE },
-	{ "crc", FLDT_UINT32X, OI(OFF(crc)), C1, 0, TYP_NONE },
+	{ "crc", FLDT_CRC, OI(OFF(crc)), C1, 0, TYP_NONE },
 	{ "uuid", FLDT_UUID, OI(OFF(uuid)), C1, 0, TYP_NONE },
 	{ "owner", FLDT_INO, OI(OFF(owner)), C1, 0, TYP_NONE },
 	{ "bno", FLDT_DFSBNO, OI(OFF(blkno)), C1, 0, TYP_BMAPBTD },
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#46 lore raw

PATCH 22/32 db: verify and calculate inode CRCs

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

When we set the current Io cursor to point at an inode, verify that the inode CRC is intact. And prior to writing such an IO cursor, calculate the inode CRC.

---
 db/inode.c             | 2 ++
 db/io.c                | 4 ++++
 db/io.h                | 6 +++++-
 include/libxfs.h       | 4 ++++
 libxfs/xfs_inode_buf.c | 8 ++++----
 5 files changed, 19 insertions(+), 5 deletions(-)
db/inode.c +2 -0
index ec533ee..4090855 100644
@@ -655,6 +655,8 @@ set_cur_inode(
 		blkbb, DB_RING_IGN, NULL);
 	off_cur(offset << mp->m_sb.sb_inodelog, mp->m_sb.sb_inodesize);
 	dip = iocur_top->data;
+	iocur_top->ino_crc_ok = libxfs_dinode_verify(mp, ino, dip);
+	iocur_top->ino_buf = 1;
 	iocur_top->ino = ino;
 	iocur_top->mode = be16_to_cpu(dip->di_mode);
 	if ((iocur_top->mode & S_IFMT) == S_IFDIR)
db/io.c +4 -0
index c9452f2..8ddb5e5 100644
@@ -462,6 +462,9 @@ write_cur(void)
 		return;
 	}
 
+	if (iocur_top->ino_buf)
+		libxfs_dinode_calc_crc(mp, iocur_top->data);
+
 	if (iocur_top->bbmap)
 		write_cur_bbs();
 	else
@@ -534,6 +537,7 @@ set_cur(
 	iocur_top->ino = ino;
 	iocur_top->dirino = dirino;
 	iocur_top->mode = mode;
+	iocur_top->ino_buf = 0;
 
 	/* store location in ring */
 	if (ring_flag)
db/io.h +5 -1
index d647284..1f8270d 100644
@@ -38,6 +38,8 @@ typedef struct iocur {
 	const struct typ	*typ;	/* type of "data" */
 	bbmap_t			*bbmap;	/* map daddr if fragmented */
 	struct xfs_buf		*bp;	/* underlying buffer */
+	int			ino_crc_ok:1;
+	int			ino_buf:1;
 } iocur_t;
 
 #define DB_RING_ADD 1                   /* add to ring on set_cur */
@@ -62,5 +64,7 @@ extern void     ring_add(void);
 static inline bool
 iocur_crc_valid()
 {
-	return (iocur_top->bp && iocur_top->bp->b_error != EFSCORRUPTED);
+	return (iocur_top->bp &&
+		iocur_top->bp->b_error != EFSCORRUPTED &&
+		(!iocur_top->ino_buf || iocur_top->ino_crc_ok));
 }
include/libxfs.h +4 -0
index 08fd0b3..d28ac48 100644
@@ -755,6 +755,10 @@ void	xfs_dinode_from_disk(struct xfs_icdinode *,
 #define libxfs_idata_realloc		xfs_idata_realloc
 #define libxfs_idestroy_fork		xfs_idestroy_fork
 
+#define libxfs_dinode_verify		xfs_dinode_verify
+bool xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
+		       struct xfs_dinode *dip);
+
 /* xfs_sb.h */
 #define libxfs_mod_sb			xfs_mod_sb
 #define libxfs_sb_from_disk		xfs_sb_from_disk
libxfs/xfs_inode_buf.c +4 -4
index b796556..728ef71 100644
@@ -276,10 +276,10 @@ xfs_dinode_to_disk(
 	}
 }
 
-static bool
+bool
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
-	struct xfs_inode	*ip,
+	xfs_ino_t		ino,
 	struct xfs_dinode	*dip)
 {
 	if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
@@ -294,7 +294,7 @@ xfs_dinode_verify(
 	if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
 			      offsetof(struct xfs_dinode, di_crc)))
 		return false;
-	if (be64_to_cpu(dip->di_ino) != ip->i_ino)
+	if (be64_to_cpu(dip->di_ino) != ino)
 		return false;
 	if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_uuid))
 		return false;
@@ -346,7 +346,7 @@ xfs_iread(
 		return error;
 
 	/* even unallocated inodes are verified */
-	if (!xfs_dinode_verify(mp, ip, dip)) {
+	if (!xfs_dinode_verify(mp, ip->i_ino, dip)) {
 		xfs_alert(mp, "%s: validation failed for inode %lld failed",
 				__func__, ip->i_ino);
 
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#47 lore raw

PATCH 23/32 db: verify and calculate dquot CRCs

In reply to a message not in the archive

When we set the current Io cursor to point at a dquot block, verify that the dquot CRC is intact. And prior to writing such an IO cursor, calculate the dquot CRC.

---
 db/io.c | 5 ++++-
 db/io.h | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)
db/io.c +4 -1
index 8ddb5e5..7281148 100644
@@ -464,7 +464,9 @@ write_cur(void)
 
 	if (iocur_top->ino_buf)
 		libxfs_dinode_calc_crc(mp, iocur_top->data);
-
+	if (iocur_top->dquot_buf)
+		xfs_update_cksum(iocur_top->data, sizeof(struct xfs_dqblk),
+				 XFS_DQUOT_CRC_OFF);
 	if (iocur_top->bbmap)
 		write_cur_bbs();
 	else
@@ -538,6 +540,7 @@ set_cur(
 	iocur_top->dirino = dirino;
 	iocur_top->mode = mode;
 	iocur_top->ino_buf = 0;
+	iocur_top->dquot_buf = 0;
 
 	/* store location in ring */
 	if (ring_flag)
db/io.h +1 -0
index 1f8270d..4f24c83 100644
@@ -40,6 +40,7 @@ typedef struct iocur {
 	struct xfs_buf		*bp;	/* underlying buffer */
 	int			ino_crc_ok:1;
 	int			ino_buf:1;
+	int			dquot_buf:1;
 } iocur_t;
 
 #define DB_RING_ADD 1                   /* add to ring on set_cur */
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#48 lore raw

PATCH 24/32 db: add a special directory buffer verifier

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Because we only have a single directory type that is used for all the different buffer types, we need to provide a special verifier for the read code. That verifier needs to know all the directory types and when it find one it knows about, switch to the correct verifier and call it.

We already do this for certain readahead cases in the directory code, so there is precedence for this. If we don't find a magic number we recognise, the verifier fails...

---
 db/dir2.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 db/dir2.h |  2 ++
 db/type.c |  3 ++-
 3 files changed, 65 insertions(+), 1 deletion(-)
db/dir2.c +61 -0
index 2ec64e0..5a10955 100644
@@ -24,6 +24,7 @@
 #include "field.h"
 #include "dir2.h"
 #include "init.h"
+#include "output.h"
 
 static int	dir2_block_hdr_count(void *obj, int startoff);
 static int	dir2_block_leaf_count(void *obj, int startoff);
@@ -975,3 +976,63 @@ const field_t	da3_node_hdr_flds[] = {
 	{ "pad", FLDT_UINT32D, OI(H3OFF(__pad32)), C1, 0, TYP_NONE },
 	{ NULL }
 };
+
+/*
+ * Special read verifier for directory buffers. detect the magic number
+ * appropriately and set the correct verifier and call it.
+ */
+static void
+xfs_dir3_db_read_verify(
+	struct xfs_buf		*bp)
+{
+	__be32			magic32;
+	__be16			magic16;
+
+	magic32 = *(__be32 *)bp->b_addr;
+	magic16 = ((struct xfs_da_blkinfo *)bp->b_addr)->magic;
+
+	switch (magic32) {
+	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
+		bp->b_ops = &xfs_dir3_block_buf_ops;
+		goto verify;
+	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
+		bp->b_ops = &xfs_dir3_data_buf_ops;
+		goto verify;
+	case cpu_to_be32(XFS_DIR3_FREE_MAGIC):
+		bp->b_ops = &xfs_dir3_free_buf_ops;
+		goto verify;
+	default:
+		break;
+	}
+
+	switch (magic16) {
+	case cpu_to_be16(XFS_DIR3_LEAF1_MAGIC):
+		bp->b_ops = &xfs_dir3_leaf1_buf_ops;
+		break;
+	case cpu_to_be16(XFS_DIR3_LEAFN_MAGIC):
+		bp->b_ops = &xfs_dir3_leafn_buf_ops;
+		break;
+	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+		bp->b_ops = &xfs_da3_node_buf_ops;
+		break;
+	default:
+		dbprintf(_("Unknown directory buffer type!\n"));
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+		return;
+	}
+verify:
+	bp->b_ops->verify_read(bp);
+}
+
+static void
+xfs_dir3_db_write_verify(
+	struct xfs_buf		*bp)
+{
+	dbprintf(_("Writing unknown directory buffer type!\n"));
+	xfs_buf_ioerror(bp, EFSCORRUPTED);
+}
+
+const struct xfs_buf_ops xfs_dir3_db_buf_ops = {
+	.verify_read = xfs_dir3_db_read_verify,
+	.verify_write = xfs_dir3_db_write_verify,
+};
db/dir2.h +2 -0
index b3651d5..5054493 100644
@@ -60,3 +60,5 @@ static inline xfs_dir2_inou_t *xfs_dir2_sf_inumberp(xfs_dir2_sf_entry_t *sfep)
 
 extern int	dir2_data_union_size(void *obj, int startoff, int idx);
 extern int	dir2_size(void *obj, int startoff, int idx);
+
+extern const struct xfs_buf_ops xfs_dir3_db_buf_ops;
db/type.c +2 -1
index b3f3d87..2c3431e 100644
@@ -87,7 +87,8 @@ static const typ_t	__typtab_crc[] = {
 	{ TYP_CNTBT, "cntbt", handle_struct, cntbt_crc_hfld,
 		&xfs_allocbt_buf_ops },
 	{ TYP_DATA, "data", handle_block, NULL, NULL },
-	{ TYP_DIR2, "dir3", handle_struct, dir3_hfld, NULL },
+	{ TYP_DIR2, "dir3", handle_struct, dir3_hfld,
+		&xfs_dir3_db_buf_ops },
 	{ TYP_DQBLK, "dqblk", handle_struct, dqblk_hfld,
 		&xfs_dquot_buf_ops },
 	{ TYP_INOBT, "inobt", handle_struct, inobt_crc_hfld,
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#49 lore raw

PATCH 25/32 db: add a special attribute buffer verifier

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Because we only have a single attribute type that is used for all the attribute buffer types, we need to provide a special verifier for the read code. That verifier needs to know all the attribute types and when it find one it knows about, switch to the correct verifier and call it.

---
 db/attr.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 db/attr.h |  2 ++
 db/type.c |  3 ++-
 3 files changed, 55 insertions(+), 1 deletion(-)
db/attr.c +51 -0
index cd95a0a..359af7b 100644
@@ -25,6 +25,7 @@
 #include "attr.h"
 #include "io.h"
 #include "init.h"
+#include "output.h"
 
 static int	attr_leaf_entries_count(void *obj, int startoff);
 static int	attr_leaf_hdr_count(void *obj, int startoff);
@@ -522,3 +523,53 @@ const field_t	attr3_leaf_hdr_flds[] = {
 	{ NULL }
 };
 
+/*
+ * Special read verifier for attribute buffers. detect the magic number
+ * appropriately and set the correct verifier and call it.
+ */
+static void
+xfs_attr3_db_read_verify(
+	struct xfs_buf		*bp)
+{
+	__be32			magic32;
+	__be16			magic16;
+
+	magic32 = *(__be32 *)bp->b_addr;
+	magic16 = ((struct xfs_da_blkinfo *)bp->b_addr)->magic;
+
+	switch (magic16) {
+	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+		bp->b_ops = &xfs_attr3_leaf_buf_ops;
+		goto verify;
+	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+		bp->b_ops = &xfs_da3_node_buf_ops;
+		goto verify;
+	default:
+		break;
+	}
+
+	switch (magic32) {
+	case cpu_to_be32(XFS_ATTR3_RMT_MAGIC):
+		bp->b_ops = &xfs_attr3_rmt_buf_ops;
+		break;
+	default:
+		dbprintf(_("Unknown attribute buffer type!\n"));
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+		return;
+	}
+verify:
+	bp->b_ops->verify_read(bp);
+}
+
+static void
+xfs_attr3_db_write_verify(
+	struct xfs_buf		*bp)
+{
+	dbprintf(_("Writing unknown attribute buffer type!\n"));
+	xfs_buf_ioerror(bp, EFSCORRUPTED);
+}
+
+const struct xfs_buf_ops xfs_attr3_db_buf_ops = {
+	.verify_read = xfs_attr3_db_read_verify,
+	.verify_write = xfs_attr3_db_write_verify,
+};
db/attr.h +2 -0
index 3065372..bc3431f 100644
@@ -33,3 +33,5 @@ extern const field_t	attr3_node_hdr_flds[];
 
 extern int	attr_leaf_name_size(void *obj, int startoff, int idx);
 extern int	attr_size(void *obj, int startoff, int idx);
+
+extern const struct xfs_buf_ops xfs_attr3_db_buf_ops;
db/type.c +2 -1
index 2c3431e..04d0d56 100644
@@ -77,7 +77,8 @@ static const typ_t	__typtab_crc[] = {
 	{ TYP_AGF, "agf", handle_struct, agf_hfld, &xfs_agf_buf_ops },
 	{ TYP_AGFL, "agfl", handle_struct, agfl_crc_hfld, &xfs_agfl_buf_ops },
 	{ TYP_AGI, "agi", handle_struct, agi_hfld, &xfs_agfl_buf_ops },
-	{ TYP_ATTR, "attr3", handle_struct, attr3_hfld, NULL },
+	{ TYP_ATTR, "attr3", handle_struct, attr3_hfld,
+		&xfs_attr3_db_buf_ops },
 	{ TYP_BMAPBTA, "bmapbta", handle_struct, bmapbta_crc_hfld,
 		&xfs_bmbt_buf_ops },
 	{ TYP_BMAPBTD, "bmapbtd", handle_struct, bmapbtd_crc_hfld,
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#50 lore raw

PATCH 26/32 db: re-enable write support for v5 filesystems.

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

As we can now verify and recalculate CRCs on IO, we can modify the on-disk structures without corrupting the filesyste, This makes it safe to turn write support on for v5 filesystems for the first time.

---
 db/init.c | 15 ---------------
 1 file changed, 15 deletions(-)
db/init.c +0 -15
index b1cddca..a9b357b 100644
@@ -143,21 +143,6 @@ init(
 			exit(EXIT_FAILURE);
 	}
 
-	/*
-	 * Don't allow modifications to CRC enabled filesystems until we support
-	 * CRC recalculation in the IO path. Unless, of course, the user is in
-	 * the process of hitting us with a big hammer.
-	 */
-	if (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_5 &&
-	    !(x.isreadonly & LIBXFS_ISREADONLY)) {
-		fprintf(stderr, 
-	_("%s: modifications to %s are not supported in thi version.\n"
-	"Use \"-r\" to run %s in read-only mode on this filesystem .\n"),
-			progname, fsdevice, progname);
-		if (!force)
-			exit(EXIT_FAILURE);
-	}
-
 	mp = libxfs_mount(&xmount, sbp, x.ddev, x.logdev, x.rtdev,
 				LIBXFS_MOUNT_ROOTINOS | LIBXFS_MOUNT_DEBUGGER);
 	if (!mp) {
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#51 lore raw

PATCH 27/32 libxfs: fix root inode handling inconsistencies

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

When "mounting" a filesystem via libxfs_mount(), callers can tell libxfs to read the root and realtime inodes into cache. However, when unmounting the filesystem, libxfs_unmount() used to unconditionally free root inodes if they were present.

This leads to interesting issues like in mkfs, when it handles creation, reading and freeing of the root and rt inodes itself. It, however, passes in the flag to tell libxfs_mount() to read the root inode, and so when unmounting throws an error like:

cache_node_put: node put on refcount 0 (node=0x684610)

When a second libxfs_iput() call is made on the root inode.

Clean this up and fix up all the callers that use magic numbers rather than symbolic values to tell libxfs tomount the root inodes.

---
 copy/xfs_copy.c | 3 ++-
 mkfs/xfs_mkfs.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)
copy/xfs_copy.c +2 -1
index bb37279..b6695d7 100644
@@ -684,7 +684,8 @@ main(int argc, char **argv)
 	sb = &mbuf.m_sb;
 	libxfs_sb_from_disk(sb, XFS_BUF_TO_SBP(sbp));
 
-	mp = libxfs_mount(&mbuf, sb, xargs.ddev, xargs.logdev, xargs.rtdev, 1);
+	mp = libxfs_mount(&mbuf, sb, xargs.ddev, xargs.logdev, xargs.rtdev,
+			  LIBXFS_MOUNT_ROOTINOS);
 	if (mp == NULL) {
 		do_log(_("%s: %s filesystem failed to initialize\n"
 			"%s: Aborting.\n"), progname, source_name, progname);
mkfs/xfs_mkfs.c +2 -1
index eafbed3..60e4d88 100644
@@ -2556,6 +2556,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 	memset(XFS_BUF_PTR(buf), 0, sectorsize);
 	libxfs_sb_to_disk((void *)XFS_BUF_PTR(buf), sbp, XFS_SB_ALL_BITS);
 	libxfs_writebuf(buf, LIBXFS_EXIT_ON_FAILURE);
+	libxfs_purgebuf(buf);
 
 	/*
 	 * If the data area is a file, then grow it out to its final size
@@ -2590,7 +2591,7 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 		(xfs_extlen_t)XFS_FSB_TO_BB(mp, logblocks),
 		&sbp->sb_uuid, logversion, lsunit, XLOG_FMT);
 
-	mp = libxfs_mount(mp, sbp, xi.ddev, xi.logdev, xi.rtdev, 1);
+	mp = libxfs_mount(mp, sbp, xi.ddev, xi.logdev, xi.rtdev, 0);
 	if (mp == NULL) {
 		fprintf(stderr, _("%s: filesystem failed to initialize\n"),
 			progname);
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#52 lore raw

PATCH 28/32 xfs_db: avoid libxfs buffer lookup warnings

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

When we mount the filesystem inside xfs_db, libxfs is tasked with reading some information from disk, such as root inodes. Because libxfs does this inode reading, it uses inode cluster buffers to read the inodes. xfs_db, OTOH, just uses FSB sized buffers to read inodes, and hence xfs_db throws a warning when reading the root inode block like so:

$ sudo xfs_db -c "sb 0" -c "p rootino" -c "inode 32" /dev/vda
Version 5 superblock detected. xfsprogs has EXPERIMENTAL support enabled!
Use of these features is at your own risk!
rootino = 32
7f59f20e6740: Badness in key lookup (length)
bp=(bno 0x20, len 8192 bytes) key=(bno 0x20, len 1024 bytes)
$

There is another way this can happen, and that is dumping raw data from disk using either the "fsb NNN" or "daddr MMM" commands to dump untyped information. This is always read in sector or filesystem block units, and so will cause similar badness warnings.

xfs_db is unique in the way it can read the same blocks with different lengths, so we really need a way to avoid having duplicate buffers in the cache. To handle this in a generic way, introduce a "purge on compare failure" feature to libxfs.

What this feature does is instead of throwing a warning when a buffer miscompare occurs (e.g. due to a length mismatch), it purges the buffer that is in cache from the cache. We can do this safely in the context of xfs_db because it always writes back changes made to buffers before it releases the reference to the buffer. Hence we can purge buffers directly from the lookup code without having to worry about whether they are dirty or not.

Doing this purge on miscompare operation avoids the problem that libxfs is currently warning about, and hence if the feature flag is set then we don't need to warn about miscompares any more. Hence the whole problem goes away entirely for xfs_db, without affecting any of the other users of libxfs based IO.

---
 db/init.c           |  1 +
 db/inode.c          | 33 +++++++++++++++++++--
 db/io.c             |  4 ++-
 include/cache.h     | 22 +++++++++++++-
 include/libxfs.h    |  2 ++
 libxfs/cache.c      | 83 +++++++++++++++++++++++++++++++++++++++--------------
 libxfs/init.c       |  6 ++--
 libxfs/rdwr.c       | 30 ++++++++++---------
 repair/xfs_repair.c |  4 +--
 9 files changed, 143 insertions(+), 42 deletions(-)
db/init.c +1 -0
index a9b357b..2b643f9 100644
@@ -109,6 +109,7 @@ init(
 	else
 		x.dname = fsdevice;
 
+	x.bcache_flags = CACHE_MISCOMPARE_PURGE;
 	if (!libxfs_init(&x)) {
 		fputs(_("\nfatal error -- couldn't initialize XFS library\n"),
 			stderr);
db/inode.c +31 -2
index 4090855..24170ba 100644
@@ -623,6 +623,14 @@ inode_u_symlink_count(
 		(int)be64_to_cpu(dip->di_size) : 0;
 }
 
+/*
+ * We are now using libxfs for our IO backend, so we should always try to use
+ * inode cluster buffers rather than filesystem block sized buffers for reading
+ * inodes. This means that we always use the same buffers as libxfs operations
+ * does, and that avoids buffer cache issues caused by overlapping buffers. This
+ * can be seen clearly when trying to read the root inode. Much of this logic is
+ * similar to libxfs_imap().
+ */
 void
 set_cur_inode(
 	xfs_ino_t	ino)
@@ -632,6 +640,9 @@ set_cur_inode(
 	xfs_agnumber_t	agno;
 	xfs_dinode_t	*dip;
 	int		offset;
+	int		numblks = blkbb;
+	xfs_agblock_t	cluster_agbno;
+
 
 	agno = XFS_INO_TO_AGNO(mp, ino);
 	agino = XFS_INO_TO_AGINO(mp, ino);
@@ -644,6 +655,24 @@ set_cur_inode(
 		return;
 	}
 	cur_agno = agno;
+
+	if (mp->m_inode_cluster_size > mp->m_sb.sb_blocksize &&
+	    mp->m_inoalign_mask) {
+		xfs_agblock_t	chunk_agbno;
+		xfs_agblock_t	offset_agbno;
+		int		blks_per_cluster;
+
+		blks_per_cluster = mp->m_inode_cluster_size >>
+							mp->m_sb.sb_blocklog;
+		offset_agbno = agbno & mp->m_inoalign_mask;
+		chunk_agbno = agbno - offset_agbno;
+		cluster_agbno = chunk_agbno +
+			((offset_agbno / blks_per_cluster) * blks_per_cluster);
+		offset += ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock);
+		numblks = XFS_FSB_TO_BB(mp, blks_per_cluster);
+	} else
+		cluster_agbno = agbno;
+
 	/*
 	 * First set_cur to the block with the inode
 	 * then use off_cur to get the right part of the buffer.
@@ -651,8 +680,8 @@ set_cur_inode(
 	ASSERT(typtab[TYP_INODE].typnm == TYP_INODE);
 
 	/* ingore ring update here, do it explicitly below */
-	set_cur(&typtab[TYP_INODE], XFS_AGB_TO_DADDR(mp, agno, agbno),
-		blkbb, DB_RING_IGN, NULL);
+	set_cur(&typtab[TYP_INODE], XFS_AGB_TO_DADDR(mp, agno, cluster_agbno),
+		numblks, DB_RING_IGN, NULL);
 	off_cur(offset << mp->m_sb.sb_inodelog, mp->m_sb.sb_inodesize);
 	dip = iocur_top->data;
 	iocur_top->ino_crc_ok = libxfs_dinode_verify(mp, ino, dip);
db/io.c +3 -1
index 7281148..123214d 100644
@@ -104,8 +104,10 @@ pop_cur(void)
 		dbprintf(_("can't pop anything from I/O stack\n"));
 		return;
 	}
-	if (iocur_top->bp)
+	if (iocur_top->bp) {
 		libxfs_putbuf(iocur_top->bp);
+		iocur_top->bp = NULL;
+	}
 	if (iocur_top->bbmap) {
 		free(iocur_top->bbmap);
 		iocur_top->bbmap = NULL;
include/cache.h +21 -1
index 0c0a1c5..c5757d0 100644
@@ -18,6 +18,25 @@
 #ifndef __CACHE_H__
 #define __CACHE_H__
 
+/*
+ * initialisation flags
+ */
+/*
+ * xfs_db always writes changes immediately, and so we need to purge buffers
+ * when we get a buffer lookup mismatch due to readin the same block with a
+ * different buffer configuration.
+ */
+#define CACHE_MISCOMPARE_PURGE	(1 << 0)
+
+/*
+ * cache object campare return values
+ */
+enum {
+	CACHE_HIT,
+	CACHE_MISS,
+	CACHE_PURGE,
+};
+
 #define	HASH_CACHE_RATIO	8
 
 /*
@@ -82,6 +101,7 @@ struct cache_node {
 };
 
 struct cache {
+	int			c_flags;	/* behavioural flags */
 	unsigned int		c_maxcount;	/* max cache nodes */
 	unsigned int		c_count;	/* count of nodes */
 	pthread_mutex_t		c_mutex;	/* node count mutex */
@@ -99,7 +119,7 @@ struct cache {
 	unsigned int 		c_max;		/* max nodes ever used */
 };
 
-struct cache *cache_init(unsigned int, struct cache_operations *);
+struct cache *cache_init(int, unsigned int, struct cache_operations *);
 void cache_destroy(struct cache *);
 void cache_walk(struct cache *, cache_walk_t);
 void cache_purge(struct cache *);
include/libxfs.h +2 -0
index d28ac48..049b217 100644
@@ -110,6 +110,8 @@ typedef struct {
 	int             dfd;            /* data subvolume file descriptor */
 	int             logfd;          /* log subvolume file descriptor */
 	int             rtfd;           /* realtime subvolume file descriptor */
+	int		icache_flags;	/* cache init flags */
+	int		bcache_flags;	/* cache init flags */
 } libxfs_init_t;
 
 #define LIBXFS_EXIT_ON_FAILURE	0x0001	/* exit the program if a call fails */
libxfs/cache.c +62 -21

140 lines not on this page · raw message

libxfs/init.c +4 -2
index 229aa50..637f29e 100644
@@ -337,10 +337,12 @@ libxfs_init(libxfs_init_t *a)
 		chdir(curdir);
 	if (!libxfs_ihash_size)
 		libxfs_ihash_size = LIBXFS_IHASHSIZE(sbp);
-	libxfs_icache = cache_init(libxfs_ihash_size, &libxfs_icache_operations);
+	libxfs_icache = cache_init(a->icache_flags, libxfs_ihash_size,
+				   &libxfs_icache_operations);
 	if (!libxfs_bhash_size)
 		libxfs_bhash_size = LIBXFS_BHASHSIZE(sbp);
-	libxfs_bcache = cache_init(libxfs_bhash_size, &libxfs_bcache_operations);
+	libxfs_bcache = cache_init(a->bcache_flags, libxfs_bhash_size,
+				   &libxfs_bcache_operations);
 	use_xfs_buf_lock = a->usebuflock;
 	manage_zones(0);
 	rval = 1;
libxfs/rdwr.c +17 -13
index 8d8bcfc..6d6a915 100644
@@ -323,20 +323,24 @@ libxfs_bcompare(struct cache_node *node, cache_key_t key)
 	struct xfs_buf	*bp = (struct xfs_buf *)node;
 	struct xfs_bufkey *bkey = (struct xfs_bufkey *)key;
 
-#ifdef IO_BCOMPARE_CHECK
 	if (bp->b_target->dev == bkey->buftarg->dev &&
-	    bp->b_bn == bkey->blkno &&
-	    bp->b_bcount != BBTOB(bkey->bblen))
-		fprintf(stderr, "%lx: Badness in key lookup (length)\n"
-			"bp=(bno 0x%llx, len %u bytes) key=(bno 0x%llx, len %u bytes)\n",
-			pthread_self(),
-			(unsigned long long)bp->b_bn, (int)bp->b_bcount,
-			(unsigned long long)bkey->blkno, BBTOB(bkey->bblen));
+	    bp->b_bn == bkey->blkno) {
+		if (bp->b_bcount == BBTOB(bkey->bblen))
+			return CACHE_HIT;
+#ifdef IO_BCOMPARE_CHECK
+		if (!(libxfs_bcache->c_flags & CACHE_MISCOMPARE_PURGE)) {
+			fprintf(stderr,
+	"%lx: Badness in key lookup (length)\n"
+	"bp=(bno 0x%llx, len %u bytes) key=(bno 0x%llx, len %u bytes)\n",
+				pthread_self(),
+				(unsigned long long)bp->b_bn, (int)bp->b_bcount,
+				(unsigned long long)bkey->blkno,
+				BBTOB(bkey->bblen));
+		}
 #endif
-
-	return (bp->b_target->dev == bkey->buftarg->dev &&
-		bp->b_bn == bkey->blkno &&
-		bp->b_bcount == BBTOB(bkey->bblen));
+		return CACHE_PURGE;
+	}
+	return CACHE_MISS;
 }
 
 void
@@ -1029,7 +1033,7 @@ libxfs_icompare(struct cache_node *node, cache_key_t key)
 {
 	xfs_inode_t	*ip = (xfs_inode_t *)node;
 
-	return (ip->i_ino == *(xfs_ino_t *)key);
+	return (ip->i_ino == *(xfs_ino_t *)key) ? CACHE_HIT : CACHE_MISS;
 }
 
 int
repair/xfs_repair.c +2 -2
index 820e7a2..55a451b 100644
@@ -712,9 +712,9 @@ main(int argc, char **argv)
 		if (!ihash_option_used)
 			libxfs_ihash_size = libxfs_bhash_size;
 
-		libxfs_icache = cache_init(libxfs_ihash_size,
+		libxfs_icache = cache_init(0, libxfs_ihash_size,
 						&libxfs_icache_operations);
-		libxfs_bcache = cache_init(libxfs_bhash_size,
+		libxfs_bcache = cache_init(0, libxfs_bhash_size,
 						&libxfs_bcache_operations);
 	}
 
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#53 lore raw

PATCH 29/32 libxfs: work around do_div() not handling 32 bit numerators

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

The libxfs dquot buffer code uses do_div() with a 32 bit numerator. This gives incorrect results as do_div() passes the numerator by reference as a pointer to a 64 bit value. Hence it does the division using 32 bits of garbage gives the wrong result. The kernel code handles 32 bit numerators just fine, so this patch is a temporary workaround in the dquot buffer code until we fix do_div() to handle 32 bit numerators correctly.

---
 libxfs/xfs_dquot_buf.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
libxfs/xfs_dquot_buf.c +12 -2
index 620d9d3..ce6b09c 100644
@@ -18,18 +18,28 @@
  */
 #include "xfs.h"
 
+/*
+ * XXX: the userspace implementation of the do_div() macro does not handle 32
+ * bit numerators properly as it passes it by reference as a pointer to a 64 bit
+ * variable and dereferences it as such. Hence the result is way, way off
+ * because it uses 32 bits of garbage for the upper 32 bits of the numerator.
+ *
+ * This is being left here as a reminder that we need to fix do_div() in
+ * userspace as every time we do a libxfs kernel/userspace diff we'll see this
+ * comment.
+ */
 int
 xfs_calc_dquots_per_chunk(
 	struct xfs_mount	*mp,
 	unsigned int		nbblks)	/* basic block units */
 {
-	unsigned int	ndquots;
+	uint64_t	ndquots;
 
 	ASSERT(nbblks > 0);
 	ndquots = BBTOB(nbblks);
 	do_div(ndquots, sizeof(xfs_dqblk_t));
 
-	return ndquots;
+	return (int)ndquots;
 }
 
 /*
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#54 lore raw

PATCH 30/32 db: enable metadump on CRC filesystems

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

Now that we can calculate CRCs through xfs_db, we can add support for recalculating CRCs on obfuscated metadump images. This simply requires us to call the write verifier manually before writing the buffer to the metadump image.

We don't need to do anything special to mdrestore, as the metadata blocks it reads from the image file should already have all the correct CRCs in them. hence it can be mostly oblivious to the fact that the filesystem it is resotring contains CRCs.

While there, add IO stack unwinding to xfs_db to prevent metadump and other db programs from exiting with unreleased buffers in the IO stack and hence emitting warnings like:

cache_purge: shake on cache 0x69e4f0 left 7 nodes!?

---
 db/init.c                 |  5 ++++-
 db/metadump.c             | 24 +++++++++++++++++++-----
 mdrestore/xfs_mdrestore.c |  3 ---
 3 files changed, 23 insertions(+), 9 deletions(-)
db/init.c +4 -1
index 2b643f9..dc915fb 100644
@@ -173,9 +173,11 @@ main(
 	int	c, i, done = 0;
 	char	*input;
 	char	**v;
+	int	start_iocur_sp;
 
 	pushfile(stdin);
 	init(argc, argv);
+	start_iocur_sp = iocur_sp;
 
 	for (i = 0; !done && i < ncmdline; i++) {
 		v = breakline(cmdline[i], &c);
@@ -202,7 +204,8 @@ close_devices:
 	 * make sure that we pop the last buffer context we held so that the
 	 * buffer is released before purge the caches during unmount.
 	 */
-	pop_cur();
+	while (iocur_sp > start_iocur_sp)
+		pop_cur();
 	libxfs_umount(mp);
 	if (x.ddev)
 		libxfs_device_close(x.ddev);
db/metadump.c +19 -5
index ac6a4d6..117dc42 100644
@@ -172,6 +172,22 @@ write_buf(
 	__int64_t	off;
 	int		i;
 
+	/*
+	 * Run the write verifier to recalculate the buffer CRCs and check
+	 * we are writing something valid to disk
+	 */
+	if (buf->bp && buf->bp->b_ops) {
+		buf->bp->b_error = 0;
+		buf->bp->b_ops->verify_write(buf->bp);
+		if (buf->bp->b_error) {
+			fprintf(stderr,
+	_("%s: write verifer failed on bno 0x%llx/0x%x\n"),
+				__func__, (long long)buf->bp->b_bn,
+				buf->bp->b_bcount);
+			return buf->bp->b_error;
+		}
+	}
+
 	for (i = 0, off = buf->bb, data = buf->data;
 			i < buf->blen;
 			i++, off++, data += BBSIZE) {
@@ -1727,6 +1743,9 @@ copy_inode_chunk(
 
 		if (!process_inode(agno, agino + i, dip))
 			goto pop_out;
+
+		/* calculate the new CRC for the inode */
+		xfs_dinode_calc_crc(mp, dip);
 	}
 skip_processing:
 	if (!write_buf(iocur_top))
@@ -2053,11 +2072,6 @@ metadump_f(
 		return 0;
 	}
 
-	if (xfs_sb_version_hascrc(&mp->m_sb) && dont_obfuscate == 0) {
-		print_warning("Can't obfuscate CRC enabled filesystems yet.");
-		return 0;
-	}
-
 	metablock = (xfs_metablock_t *)calloc(BBSIZE + 1, BBSIZE);
 	if (metablock == NULL) {
 		print_warning("memory allocation failure");
mdrestore/xfs_mdrestore.c +0 -3
index fe61766..e57bdb2 100644
@@ -109,9 +109,6 @@ perform_restore(
 	if (sb.sb_magicnum != XFS_SB_MAGIC)
 		fatal("bad magic number for primary superblock\n");
 
-	if (xfs_sb_version_hascrc(&sb))
-		fatal("Can't restore CRC enabled filesystems yet.\n");
-
 	((xfs_dsb_t*)block_buffer)->sb_inprogress = 1;
 
 	if (is_target_file)  {
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#55 lore raw

PATCH 31/32 xfs: support larger inode clusters on v5 filesystems

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

To allow the kernel to use larger inode clusters than the standard 8192 bytes, we need to set the inode alignment fields appropriately so that the kernel is consistent in it's inode to buffer mappings. We set the alignment to allow a constant 32 inodes per cluster, instead of a fixed 8k cluster size.

---
 include/libxfs.h |  2 +-
 mkfs/xfs_mkfs.c  |  5 ++++-
 repair/sb.c      | 41 ++++++++++++++++++++++++++++-------------
 3 files changed, 33 insertions(+), 15 deletions(-)
include/libxfs.h +1 -1
index 049b217..9d7c579 100644
@@ -182,7 +182,7 @@ typedef struct xfs_mount {
 	__uint8_t		m_sectbb_log;	/* sectorlog - BBSHIFT */
 	__uint8_t		m_agno_log;	/* log #ag's */
 	__uint8_t		m_agino_log;	/* #bits for agino in inum */
-	__uint16_t		m_inode_cluster_size;/* min inode buf size */
+	uint			m_inode_cluster_size;/* min inode buf size */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	uint			m_blockwmask;	/* blockwsize-1 */
mkfs/xfs_mkfs.c +4 -1
index 60e4d88..feb5bd0 100644
@@ -2501,7 +2501,10 @@ _("size %s specified for log subvolume is too large, maximum is %lld blocks\n"),
 	} else
 		sbp->sb_logsunit = 0;
 	if (iaflag) {
-		sbp->sb_inoalignmt = XFS_INODE_BIG_CLUSTER_SIZE >> blocklog;
+		int	cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
+		if (crcs_enabled)
+			cluster_size *= isize / XFS_DINODE_MIN_SIZE;
+		sbp->sb_inoalignmt = cluster_size >> blocklog;
 		iaflag = sbp->sb_inoalignmt != 0;
 	} else
 		sbp->sb_inoalignmt = 0;
repair/sb.c +28 -13

64 lines not on this page · raw message

Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#56 lore raw

PATCH 32/32 xfsprogs: kill experimental warnings for v5 filesystems

In reply to a message not in the archive

From: Dave Chinner <[email protected]>

With xfsprogs now being close to feature complete on v5 filesystems, remove the experimental warnings from the superblock verifier. This means that we don't need to filter such warnings from the output in xfstests and so we can see exactly what tests are failing due to code deficiencies rather than from detecting warning noise.

---
 libxfs/xfs_sb.c | 4 ----
 1 file changed, 4 deletions(-)
libxfs/xfs_sb.c +0 -4
index 8b90b88..6febcb3 100644
@@ -180,10 +180,6 @@ xfs_mount_validate_sb(
 	 * write validation, we don't need to check feature masks.
 	 */
 	if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
-		xfs_alert(mp,
-"Version 5 superblock detected. xfsprogs has EXPERIMENTAL support enabled!\n"
-"Use of these features is at your own risk!");
-
 		if (xfs_sb_has_compat_feature(sbp,
 					XFS_SB_FEAT_COMPAT_UNKNOWN)) {
 			xfs_warn(mp,
Signature · 6 lines
1.8.3.2

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs