Yifan reported a "segmentation fault (core dumped)" error days ago
with a large dataset (enwik9 x 5). Let's fix it.
Reported-by: Yifan Zhao <zhaoyi...@sjtu.edu.cn>
Fixes: 861037f4fc15 ("erofs-utils: add a built-in DEFLATE compressor")
Signed-off-by: Gao Xiang <hsiang...@linux.alibaba.com>
---
include/erofs/defs.h | 3 +++
lib/kite_deflate.c | 12 ++++++++++++
2 files changed, 15 insertions(+)
diff --git a/include/erofs/defs.h b/include/erofs/defs.h
index e7384a1..4ea9a55 100644
--- a/include/erofs/defs.h
+++ b/include/erofs/defs.h
@@ -343,6 +343,9 @@ unsigned long __roundup_pow_of_two(unsigned long n)
#define ST_MTIM_NSEC(stbuf) 0
#endif
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+
#ifdef __cplusplus
}
#endif
diff --git a/lib/kite_deflate.c b/lib/kite_deflate.c
index 8667954..cb81626 100644
--- a/lib/kite_deflate.c
+++ b/lib/kite_deflate.c
@@ -859,6 +859,18 @@ static void kite_mf_reset(struct kite_matchfinder *mf,
*/
mf->base += mf->offset + kHistorySize32 + 1;
+ /*
+ * Unlike other LZ encoders like liblzma [1], we simply reset the hash
+ * chain instead of normalization. This avoids extra complexity, as we
+ * don't consider extreme large input buffers in one go.
+ *
+ * [1]
https://github.com/tukaani-project/xz/blob/v5.4.0/src/liblzma/lz/lz_encoder_mf.c#L94
+ */
+ if (unlikely(mf->base > ((typeof(mf->base))-1) >> 1)) {
+ mf->base = kHistorySize32 + 1;
+ memset(mf->hash, 0, 0x10000 * sizeof(mf->hash[0]));
+ memset(mf->chain, 0, sizeof(mf->chain[0]) * mf->wsiz);
+ }
mf->offset = 0;
mf->cyclic_pos = 0;
--
2.39.3
