[PATCH] ext4: fix clang build regression

[PATCH] ext4: fix clang build regression

[Arnd Bergmann]

As Stefan pointed out, I misremembered what clang can do specifically,
and it turns out that the variable-length array at the end of the
structure did not work (a flexible array would have worked here
but not solved the problem):

fs/ext4/mballoc.c:2303:17: error: fields must have a constant size:
'variable length array in structure' extension will never be supported
                ext4_grpblk_t counters[blocksize_bits + 2];

This reverts part of my previous patch, using a fixed-size array
again, but keeping the check for the array overflow.

Fixes: 2df2c3402fc8 ("ext4: fix warning about stack corruption")
Reported-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 fs/ext4/mballoc.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5a1052627a81..701085620cd8 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2300,7 +2300,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 					     EXT4_MAX_BLOCK_LOG_SIZE);
 	struct sg {
 		struct ext4_group_info info;
-		ext4_grpblk_t counters[blocksize_bits + 2];
+		ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
 	} sg;
 
 	group--;
@@ -2309,6 +2309,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
 			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
+	i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
+		sizeof(struct ext4_group_info);
+
 	grinfo = ext4_get_group_info(sb, group);
 	/* Load the group info in memory only if not already loaded. */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
@@ -2320,7 +2323,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 		buddy_loaded = 1;
 	}
 
-	memcpy(&sg, ext4_get_group_info(sb, group), sizeof(sg));
+	memcpy(&sg, ext4_get_group_info(sb, group), i);
 
 	if (buddy_loaded)
 		ext4_mb_unload_buddy(&e4b);
-- 
2.9.0

Re: [PATCH] ext4: fix clang build regression

[Chandan Rajendra]

On Monday, August 7, 2017 4:26:51 PM IST Arnd Bergmann wrote:
> As Stefan pointed out, I misremembered what clang can do specifically,
> and it turns out that the variable-length array at the end of the
> structure did not work (a flexible array would have worked here
> but not solved the problem):
> 
> fs/ext4/mballoc.c:2303:17: error: fields must have a constant size:
> 'variable length array in structure' extension will never be supported
>                 ext4_grpblk_t counters[blocksize_bits + 2];
> 
> This reverts part of my previous patch, using a fixed-size array
> again, but keeping the check for the array overflow.
> 
> Fixes: 2df2c3402fc8 ("ext4: fix warning about stack corruption")
> Reported-by: Stefan Agner <stefan@agner.ch>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>

I executed xfstests on a ppc64 machine with both 4k and 64k block size 
combination.

Tested-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>

-- 
chandan

Re: [PATCH] ext4: fix clang build regression

[Theodore Ts'o]

On Sat, Aug 12, 2017 at 02:09:29PM +0530, Chandan Rajendra wrote:
> On Monday, August 7, 2017 4:26:51 PM IST Arnd Bergmann wrote:
> > As Stefan pointed out, I misremembered what clang can do specifically,
> > and it turns out that the variable-length array at the end of the
> > structure did not work (a flexible array would have worked here
> > but not solved the problem):
> > 
> > fs/ext4/mballoc.c:2303:17: error: fields must have a constant size:
> > 'variable length array in structure' extension will never be supported
> >                 ext4_grpblk_t counters[blocksize_bits + 2];
> > 
> > This reverts part of my previous patch, using a fixed-size array
> > again, but keeping the check for the array overflow.
> > 
> > Fixes: 2df2c3402fc8 ("ext4: fix warning about stack corruption")
> > Reported-by: Stefan Agner <stefan@agner.ch>
> > Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> 
> I executed xfstests on a ppc64 machine with both 4k and 64k block size 
> combination.
> 
> Tested-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>

Thanks, applied.

						- Ted