undef/git-commit-vandalism
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

read-cache: avoid misaligned reads in index v4

Browse Source 
The process for reading the index into memory from disk is to first read its
contents into a single memory-mapped file buffer (type 'char *'), then
sequentially convert each on-disk index entry into a corresponding incore
'cache_entry'. To access the contents of the on-disk entry for processing, a
moving pointer within the memory-mapped file is cast to type 'struct
ondisk_cache_entry *'.

In index v4, the entries in the on-disk index file are written *without*
aligning their first byte to a 4-byte boundary; entries are a variable
length (depending on the entry name and whether or not extended flags are
used). As a result, casting the 'char *' buffer pointer to 'struct
ondisk_cache_entry *' then accessing its contents in a 'SANITIZE=undefined'
build can trigger the following error:

  read-cache.c:1886:46: runtime error: member access within misaligned
  address <address> for type 'struct ondisk_cache_entry', which requires 4
  byte alignment

Avoid this error by reading fields directly from the 'char *' buffer, using
the 'offsetof' individual fields in 'struct ondisk_cache_entry'.
Additionally, add documentation describing why the new approach avoids the
misaligned address error, as well as advice on how to improve the
implementation in the future.

Reported-by: Jeff King <peff@peff.net>
Signed-off-by: Victoria Dye <vdye@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Victoria Dye 2022-09-28 17:19:00 +00:00 committed by Junio C Hamano
parent a0feb8611d
commit 4a6ed30f96
1 changed files with 42 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
read-cache.c
View File

@ -1873,9 +1873,20 @@ static int read_index_extension(struct index_state *istate,
return 0; return 0;
} }
/*
* Parses the contents of the cache entry contained within the 'ondisk' buffer
* into a new incore 'cache_entry'.
*
* Note that 'char *ondisk' may not be aligned to a 4-byte address interval in
* index v4, so we cannot cast it to 'struct ondisk_cache_entry *' and access
* its members. Instead, we use the byte offsets of members within the struct to
* identify where 'get_be16()', 'get_be32()', and 'oidread()' (which can all
* read from an unaligned memory buffer) should read from the 'ondisk' buffer
* into the corresponding incore 'cache_entry' members.
*/
static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool, static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
unsigned int version, unsigned int version,
struct ondisk_cache_entry *ondisk, const char *ondisk,
unsigned long *ent_size, unsigned long *ent_size,
const struct cache_entry *previous_ce) const struct cache_entry *previous_ce)
{ {
@ -1883,7 +1894,7 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
size_t len; size_t len;
const char *name; const char *name;
const unsigned hashsz = the_hash_algo->rawsz; const unsigned hashsz = the_hash_algo->rawsz;
const uint16_t *flagsp = (const uint16_t *)(ondisk->data + hashsz); const char *flagsp = ondisk + offsetof(struct ondisk_cache_entry, data) + hashsz;
unsigned int flags; unsigned int flags;
size_t copy_len = 0; size_t copy_len = 0;
/* /*
@ -1901,15 +1912,15 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
if (flags & CE_EXTENDED) { if (flags & CE_EXTENDED) {
int extended_flags; int extended_flags;
extended_flags = get_be16(flagsp + 1) << 16; extended_flags = get_be16(flagsp + sizeof(uint16_t)) << 16;
/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */ /* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
if (extended_flags & ~CE_EXTENDED_FLAGS) if (extended_flags & ~CE_EXTENDED_FLAGS)
die(_("unknown index entry format 0x%08x"), extended_flags); die(_("unknown index entry format 0x%08x"), extended_flags);
flags |= extended_flags; flags |= extended_flags;
name = (const char *)(flagsp + 2); name = (const char *)(flagsp + 2 * sizeof(uint16_t));
} }
else else
name = (const char *)(flagsp + 1); name = (const char *)(flagsp + sizeof(uint16_t));
if (expand_name_field) { if (expand_name_field) {
const unsigned char *cp = (const unsigned char *)name; const unsigned char *cp = (const unsigned char *)name;
@ -1935,20 +1946,32 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
ce = mem_pool__ce_alloc(ce_mem_pool, len); ce = mem_pool__ce_alloc(ce_mem_pool, len);
ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec); /*
ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec); * NEEDSWORK: using 'offsetof()' is cumbersome and should be replaced
ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec); * with something more akin to 'load_bitmap_entries_v1()'s use of
ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec); * 'read_be16'/'read_be32'. For consistency with the corresponding
ce->ce_stat_data.sd_dev = get_be32(&ondisk->dev); * ondisk entry write function ('copy_cache_entry_to_ondisk()'), this
ce->ce_stat_data.sd_ino = get_be32(&ondisk->ino); * should be done at the same time as removing references to
ce->ce_mode = get_be32(&ondisk->mode); * 'ondisk_cache_entry' there.
ce->ce_stat_data.sd_uid = get_be32(&ondisk->uid); */
ce->ce_stat_data.sd_gid = get_be32(&ondisk->gid); ce->ce_stat_data.sd_ctime.sec = get_be32(ondisk + offsetof(struct ondisk_cache_entry, ctime)
ce->ce_stat_data.sd_size = get_be32(&ondisk->size); + offsetof(struct cache_time, sec));
ce->ce_stat_data.sd_mtime.sec = get_be32(ondisk + offsetof(struct ondisk_cache_entry, mtime)
+ offsetof(struct cache_time, sec));
ce->ce_stat_data.sd_ctime.nsec = get_be32(ondisk + offsetof(struct ondisk_cache_entry, ctime)
+ offsetof(struct cache_time, nsec));
ce->ce_stat_data.sd_mtime.nsec = get_be32(ondisk + offsetof(struct ondisk_cache_entry, mtime)
+ offsetof(struct cache_time, nsec));
ce->ce_stat_data.sd_dev = get_be32(ondisk + offsetof(struct ondisk_cache_entry, dev));
ce->ce_stat_data.sd_ino = get_be32(ondisk + offsetof(struct ondisk_cache_entry, ino));
ce->ce_mode = get_be32(ondisk + offsetof(struct ondisk_cache_entry, mode));
ce->ce_stat_data.sd_uid = get_be32(ondisk + offsetof(struct ondisk_cache_entry, uid));
ce->ce_stat_data.sd_gid = get_be32(ondisk + offsetof(struct ondisk_cache_entry, gid));
ce->ce_stat_data.sd_size = get_be32(ondisk + offsetof(struct ondisk_cache_entry, size));
ce->ce_flags = flags & ~CE_NAMEMASK; ce->ce_flags = flags & ~CE_NAMEMASK;
ce->ce_namelen = len; ce->ce_namelen = len;
ce->index = 0; ce->index = 0;
oidread(&ce->oid, ondisk->data); oidread(&ce->oid, (const unsigned char *)ondisk + offsetof(struct ondisk_cache_entry, data));
if (expand_name_field) { if (expand_name_field) {
if (copy_len) if (copy_len)
@ -2117,12 +2140,12 @@ static unsigned long load_cache_entry_block(struct index_state *istate,
unsigned long src_offset = start_offset; unsigned long src_offset = start_offset;
for (i = offset; i < offset + nr; i++) { for (i = offset; i < offset + nr; i++) {
struct ondisk_cache_entry *disk_ce;
struct cache_entry *ce; struct cache_entry *ce;
unsigned long consumed; unsigned long consumed;
disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset); ce = create_from_disk(ce_mem_pool, istate->version,
ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce); mmap + src_offset,
&consumed, previous_ce);
set_index_entry(istate, i, ce); set_index_entry(istate, i, ce);
src_offset += consumed; src_offset += consumed;