dm-pcache: validate seg_id fields from persistent memory

cache_pos_decode(), cache_key_decode() and the last-kset branches of
cache_replay(), the writeback worker and the GC worker take a cache
segment id from the cache device metadata and index cache->segments[]
with it without checking it against cache->n_segs. That metadata is only
CRC-protected with a fixed public seed, so whoever supplies the cache
device on a table load (CAP_SYS_ADMIN) controls the id; an out-of-range
value forms a wild pcache_cache_segment pointer that is dereferenced and
written through -- an out-of-bounds read and write driven by on-disk data.

Add cache_seg_id_valid() and reject an out-of-range id at each decode
site, failing the operation with -EIO instead of indexing past the array.
Bound the id against the initialized-segment count (cache_info.n_segs)
rather than the physical device total. A forged cache_info.n_segs below
seg_num otherwise leaves segments[cache_info.n_segs..seg_num) as zeroed
structs whose data pointer is NULL, so a forged id in that window would
still be dereferenced. A later patch guarantees cache_info.n_segs <=
seg_num, and a driver-created cache sets the two equal, so valid images
are unaffected.

Fixes: 1d57628ff9 ("dm-pcache: add persistent cache target in device-mapper")
Cc: stable@vger.kernel.org
Signed-off-by: Bryam Vargas <hexlabsecurity@proton.me>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
This commit is contained in:
Bryam Vargas 2026-07-17 06:26:54 -05:00 committed by Mikulas Patocka
parent 22eb919f1b
commit 90c990a684
5 changed files with 63 additions and 6 deletions

View File

@ -118,6 +118,9 @@ int cache_pos_decode(struct pcache_cache *cache,
if (!latest_addr)
return -EIO;
if (!cache_seg_id_valid(cache, latest.cache_seg_id))
return -EIO;
pos->cache_seg = &cache->segments[latest.cache_seg_id];
pos->seg_off = latest.seg_off;
*seq = latest.header.seq;
@ -155,6 +158,7 @@ static int cache_init(struct dm_pcache *pcache)
cache->cache_dev = &pcache->cache_dev;
cache->n_segs = cache_dev->seg_num;
atomic_set(&cache->gc_errors, 0);
atomic_set(&cache->writeback_errors, 0);
spin_lock_init(&cache->seg_map_lock);
spin_lock_init(&cache->key_head_lock);

View File

@ -180,6 +180,7 @@ struct pcache_cache {
u32 advance;
int ret;
} writeback_ctx;
atomic_t writeback_errors;
char gc_kset_onmedia_buf[PCACHE_KSET_ONMEDIA_SIZE_MAX];
struct delayed_work gc_work;
@ -420,6 +421,20 @@ static inline bool cache_seg_is_ctrl_seg(u32 cache_seg_id)
return (cache_seg_id == 0);
}
/**
* cache_seg_id_valid - Validate a cache segment id read from the cache device.
* @cache: Pointer to the pcache_cache structure.
* @cache_seg_id: Segment id decoded from on-media metadata.
*
* On-media segment ids are only protected by a CRC, which an attacker who can
* format the cache device computes over their chosen value. Reject any id that
* would index cache->segments[] out of bounds before it is dereferenced.
*/
static inline bool cache_seg_id_valid(struct pcache_cache *cache, u32 cache_seg_id)
{
return cache_seg_id < cache->cache_info.n_segs;
}
/**
* cache_key_cutfront - Cuts a specified length from the front of a cache key.
* @key: Pointer to pcache_cache_key structure.

View File

@ -74,11 +74,17 @@ static bool need_gc(struct pcache_cache *cache, struct pcache_cache_pos *dirty_t
* @cache: Pointer to the pcache_cache structure.
* @kset_onmedia: Pointer to the kset_onmedia structure for the last kset.
*/
static void last_kset_gc(struct pcache_cache *cache, struct pcache_cache_kset_onmedia *kset_onmedia)
static int last_kset_gc(struct pcache_cache *cache, struct pcache_cache_kset_onmedia *kset_onmedia)
{
struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
struct pcache_cache_segment *cur_seg, *next_seg;
if (!cache_seg_id_valid(cache, kset_onmedia->next_cache_seg_id)) {
pcache_dev_err(pcache, "invalid next_cache_seg_id %u in gc (n_segs %u)\n",
kset_onmedia->next_cache_seg_id, cache->n_segs);
return -EIO;
}
cur_seg = cache->key_tail.cache_seg;
next_seg = &cache->segments[kset_onmedia->next_cache_seg_id];
@ -94,6 +100,8 @@ static void last_kset_gc(struct pcache_cache *cache, struct pcache_cache_kset_on
spin_lock(&cache->seg_map_lock);
__clear_bit(cur_seg->cache_seg_id, cache->seg_map);
spin_unlock(&cache->seg_map_lock);
return 0;
}
void pcache_cache_gc_fn(struct work_struct *work)
@ -130,7 +138,11 @@ void pcache_cache_gc_fn(struct work_struct *work)
if (dirty_tail.cache_seg == key_tail.cache_seg)
break;
last_kset_gc(cache, kset_onmedia);
ret = last_kset_gc(cache, kset_onmedia);
if (ret) {
atomic_inc(&cache->gc_errors);
return;
}
continue;
}

View File

@ -94,6 +94,12 @@ int cache_key_decode(struct pcache_cache *cache,
key->off = key_onmedia->off;
key->len = key_onmedia->len;
if (!cache_seg_id_valid(cache, key_onmedia->cache_seg_id)) {
pcache_dev_err(pcache, "invalid cache_seg_id %u in cache key (n_segs %u)\n",
key_onmedia->cache_seg_id, cache->n_segs);
return -EIO;
}
key->cache_pos.cache_seg = &cache->segments[key_onmedia->cache_seg_id];
key->cache_pos.seg_off = key_onmedia->cache_seg_off;
@ -789,6 +795,11 @@ int cache_replay(struct pcache_cache *cache)
pcache_dev_debug(pcache, "last kset replay, next: %u\n", kset_onmedia->next_cache_seg_id);
if (!cache_seg_id_valid(cache, kset_onmedia->next_cache_seg_id)) {
ret = -EIO;
goto out;
}
next_seg = &cache->segments[kset_onmedia->next_cache_seg_id];
pos->cache_seg = next_seg;

View File

@ -196,12 +196,18 @@ static int cache_kset_insert_tree(struct pcache_cache *cache, struct pcache_cach
return ret;
}
static void last_kset_writeback(struct pcache_cache *cache,
static int last_kset_writeback(struct pcache_cache *cache,
struct pcache_cache_kset_onmedia *last_kset_onmedia)
{
struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
struct pcache_cache_segment *next_seg;
if (!cache_seg_id_valid(cache, last_kset_onmedia->next_cache_seg_id)) {
pcache_dev_err(pcache, "invalid next_cache_seg_id %u in writeback (n_segs %u)\n",
last_kset_onmedia->next_cache_seg_id, cache->n_segs);
return -EIO;
}
pcache_dev_debug(pcache, "last kset, next: %u\n", last_kset_onmedia->next_cache_seg_id);
next_seg = &cache->segments[last_kset_onmedia->next_cache_seg_id];
@ -211,6 +217,8 @@ static void last_kset_writeback(struct pcache_cache *cache,
cache->dirty_tail.seg_off = 0;
cache_encode_dirty_tail(cache);
mutex_unlock(&cache->dirty_tail_lock);
return 0;
}
void cache_writeback_fn(struct work_struct *work)
@ -229,6 +237,9 @@ void cache_writeback_fn(struct work_struct *work)
if (pcache_is_stopping(pcache))
goto unlock;
if (atomic_read(&cache->writeback_errors))
goto unlock;
kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->wb_kset_onmedia_buf;
mutex_lock(&cache->dirty_tail_lock);
@ -241,15 +252,19 @@ void cache_writeback_fn(struct work_struct *work)
}
if (kset_onmedia->flags & PCACHE_KSET_FLAGS_LAST) {
last_kset_writeback(cache, kset_onmedia);
ret = last_kset_writeback(cache, kset_onmedia);
if (ret) {
atomic_inc(&cache->writeback_errors);
goto unlock;
}
delay = 0;
goto queue_work;
}
ret = cache_kset_insert_tree(cache, kset_onmedia);
if (ret) {
delay = PCACHE_CACHE_WRITEBACK_INTERVAL;
goto queue_work;
atomic_inc(&cache->writeback_errors);
goto unlock;
}
cache_wb_tree_writeback(cache, get_kset_onmedia_size(kset_onmedia));