summaryrefslogtreecommitdiff
path: root/lib/xz/xz_dec_lzma2.c
diff options
context:
space:
mode:
Diffstat (limited to 'lib/xz/xz_dec_lzma2.c')
-rw-r--r--lib/xz/xz_dec_lzma2.c156
1 files changed, 154 insertions, 2 deletions
diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c
index 22b789645ce5..46b186d7eb45 100644
--- a/lib/xz/xz_dec_lzma2.c
+++ b/lib/xz/xz_dec_lzma2.c
@@ -248,6 +248,10 @@ struct lzma2_dec {
* before the first LZMA chunk.
*/
bool need_props;
+
+#ifdef XZ_DEC_MICROLZMA
+ bool pedantic_microlzma;
+#endif
};
struct xz_dec_lzma2 {
@@ -419,6 +423,12 @@ static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
}
}
+#ifdef XZ_DEC_MICROLZMA
+# define DICT_FLUSH_SUPPORTS_SKIPPING true
+#else
+# define DICT_FLUSH_SUPPORTS_SKIPPING false
+#endif
+
/*
* Flush pending data from dictionary to b->out. It is assumed that there is
* enough space in b->out. This is guaranteed because caller uses dict_limit()
@@ -437,9 +447,14 @@ static uint32_t dict_flush(struct dictionary *dict, struct xz_buf *b)
* decompression because in multi-call mode dict->buf
* has been allocated by us in this file; it's not
* provided by the caller like in single-call mode.
+ *
+ * With MicroLZMA, b->out can be NULL to skip bytes that
+ * the caller doesn't need. This cannot be done with XZ
+ * because it would break BCJ filters.
*/
- memcpy(b->out + b->out_pos, dict->buf + dict->start,
- copy_size);
+ if (!DICT_FLUSH_SUPPORTS_SKIPPING || b->out != NULL)
+ memcpy(b->out + b->out_pos, dict->buf + dict->start,
+ copy_size);
}
dict->start = dict->pos;
@@ -1190,3 +1205,140 @@ XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s)
kfree(s);
}
+
+#ifdef XZ_DEC_MICROLZMA
+/* This is a wrapper struct to have a nice struct name in the public API. */
+struct xz_dec_microlzma {
+ struct xz_dec_lzma2 s;
+};
+
+enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s_ptr,
+ struct xz_buf *b)
+{
+ struct xz_dec_lzma2 *s = &s_ptr->s;
+
+ /*
+ * sequence is SEQ_PROPERTIES before the first input byte,
+ * SEQ_LZMA_PREPARE until a total of five bytes have been read,
+ * and SEQ_LZMA_RUN for the rest of the input stream.
+ */
+ if (s->lzma2.sequence != SEQ_LZMA_RUN) {
+ if (s->lzma2.sequence == SEQ_PROPERTIES) {
+ /* One byte is needed for the props. */
+ if (b->in_pos >= b->in_size)
+ return XZ_OK;
+
+ /*
+ * Don't increment b->in_pos here. The same byte is
+ * also passed to rc_read_init() which will ignore it.
+ */
+ if (!lzma_props(s, ~b->in[b->in_pos]))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.sequence = SEQ_LZMA_PREPARE;
+ }
+
+ /*
+ * xz_dec_microlzma_reset() doesn't validate the compressed
+ * size so we do it here. We have to limit the maximum size
+ * to avoid integer overflows in lzma2_lzma(). 3 GiB is a nice
+ * round number and much more than users of this code should
+ * ever need.
+ */
+ if (s->lzma2.compressed < RC_INIT_BYTES
+ || s->lzma2.compressed > (3U << 30))
+ return XZ_DATA_ERROR;
+
+ if (!rc_read_init(&s->rc, b))
+ return XZ_OK;
+
+ s->lzma2.compressed -= RC_INIT_BYTES;
+ s->lzma2.sequence = SEQ_LZMA_RUN;
+
+ dict_reset(&s->dict, b);
+ }
+
+ /* This is to allow increasing b->out_size between calls. */
+ if (DEC_IS_SINGLE(s->dict.mode))
+ s->dict.end = b->out_size - b->out_pos;
+
+ while (true) {
+ dict_limit(&s->dict, min_t(size_t, b->out_size - b->out_pos,
+ s->lzma2.uncompressed));
+
+ if (!lzma2_lzma(s, b))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.uncompressed -= dict_flush(&s->dict, b);
+
+ if (s->lzma2.uncompressed == 0) {
+ if (s->lzma2.pedantic_microlzma) {
+ if (s->lzma2.compressed > 0 || s->lzma.len > 0
+ || !rc_is_finished(&s->rc))
+ return XZ_DATA_ERROR;
+ }
+
+ return XZ_STREAM_END;
+ }
+
+ if (b->out_pos == b->out_size)
+ return XZ_OK;
+
+ if (b->in_pos == b->in_size
+ && s->temp.size < s->lzma2.compressed)
+ return XZ_OK;
+ }
+}
+
+struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode,
+ uint32_t dict_size)
+{
+ struct xz_dec_microlzma *s;
+
+ /* Restrict dict_size to the same range as in the LZMA2 code. */
+ if (dict_size < 4096 || dict_size > (3U << 30))
+ return NULL;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s == NULL)
+ return NULL;
+
+ s->s.dict.mode = mode;
+ s->s.dict.size = dict_size;
+
+ if (DEC_IS_MULTI(mode)) {
+ s->s.dict.end = dict_size;
+
+ s->s.dict.buf = vmalloc(dict_size);
+ if (s->s.dict.buf == NULL) {
+ kfree(s);
+ return NULL;
+ }
+ }
+
+ return s;
+}
+
+void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, uint32_t comp_size,
+ uint32_t uncomp_size, int uncomp_size_is_exact)
+{
+ /*
+ * comp_size is validated in xz_dec_microlzma_run().
+ * uncomp_size can safely be anything.
+ */
+ s->s.lzma2.compressed = comp_size;
+ s->s.lzma2.uncompressed = uncomp_size;
+ s->s.lzma2.pedantic_microlzma = uncomp_size_is_exact;
+
+ s->s.lzma2.sequence = SEQ_PROPERTIES;
+ s->s.temp.size = 0;
+}
+
+void xz_dec_microlzma_end(struct xz_dec_microlzma *s)
+{
+ if (DEC_IS_MULTI(s->s.dict.mode))
+ vfree(s->s.dict.buf);
+
+ kfree(s);
+}
+#endif