summaryrefslogtreecommitdiff
path: root/fs/ext2
diff options
context:
space:
mode:
authorArnd Bergmann <arnd@arndb.de>2017-03-23 16:06:13 +0100
committerJan Kara <jack@suse.cz>2017-03-23 19:22:15 +0100
commitab4949640d6674b617b314ad3c2c00353304bab9 (patch)
treeef43d1918e6244b6cb0737f3e44a15384dc37d52 /fs/ext2
parent093b995e3b55a0ae0670226ddfcb05bfbf0099ae (diff)
reiserfs: avoid a -Wmaybe-uninitialized warning
The latest gcc-7.0.1 snapshot warns about an unintialized variable use: In file included from fs/reiserfs/lbalance.c:8:0: fs/reiserfs/lbalance.c: In function 'leaf_item_bottle.isra.3': fs/reiserfs/reiserfs.h:1279:13: error: '*((void *)&n_ih+8).v' may be used uninitialized in this function [-Werror=maybe-uninitialized] v2->v = (v2->v & cpu_to_le64(15ULL << 60)) | cpu_to_le64(offset); ~~^~~ fs/reiserfs/reiserfs.h:1279:13: error: '*((void *)&n_ih+8).v' may be used uninitialized in this function [-Werror=maybe-uninitialized] v2->v = (v2->v & cpu_to_le64(15ULL << 60)) | cpu_to_le64(offset); This happens because the offset/type pair that is stored in ih.key.u.k_offset_v2 is actually uninitialized when we call set_le_ih_k_offset() and set_le_ih_k_type(). After we have called both, all data is correct, but the first of the two reads uninitialized data for the type field and writes it back before it gets overwritten. This works around the warning by initializing the k_offset_v2 through the slightly larger memcpy(). [JK: Remove now unused define and make it obvious we initialize the key] Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'fs/ext2')
0 files changed, 0 insertions, 0 deletions