block/dmg: support bzip2 block entry types

This patch adds support for bzip2-compressed block entries as introduced
with OS X 10.4 (source: https://en.wikipedia.org/wiki/Apple_Disk_Image).

It was tested against a 5.2G "OS X Yosemite" installation image which
stores the BLXX block in the XML property list (instead of resource
forks) and has over 5k chunks.

New configure entries are added (--enable-bzip2 / --disable-bzip2) to
control inclusion of bzip2 functionality (which requires linking against
libbz2). The help message suggests that this option is needed for DMG
files, but the tests are generic enough that other parts of QEMU can use
bzip2 if needed.

The identifiers are based on http://newosxbook.com/DMG.html.

The decompression routines are based on the zlib case, but as there is
no way to reset the decompression state (unlike zlib), memory is
allocated and deallocated for every decompression. This should not be
problematic as the decompression takes most of the time and as blocks
are typically about/over 1 MiB in size, only one allocation is done
every 2000 sectors.

Signed-off-by: Peter Wu <peter@lekensteyn.nl>
Reviewed-by: John Snow <jsnow@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1420566495-13284-12-git-send-email-peter@lekensteyn.nl
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

2 files changed, 43 insertions, 1 deletions

diff --git a/block/Makefile.objs b/block/Makefile.objs
index 010afad71a..db2933e469 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -37,5 +37,6 @@ gluster.o-libs     := $(GLUSTERFS_LIBS)
 ssh.o-cflags       := $(LIBSSH2_CFLAGS)
 ssh.o-libs         := $(LIBSSH2_LIBS)
 archipelago.o-libs := $(ARCHIPELAGO_LIBS)
+dmg.o-libs         := $(BZIP2_LIBS)
 qcow.o-libs        := -lz
 linux-aio.o-libs   := -laio
diff --git a/block/dmg.c b/block/dmg.c
index cc584b55aa..797fda3ec8 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -26,6 +26,9 @@
 #include "qemu/bswap.h"
 #include "qemu/module.h"
 #include <zlib.h>
+#ifdef CONFIG_BZIP2
+#include <bzlib.h>
+#endif
 #include <glib.h>
 
 enum {
@@ -56,6 +59,9 @@ typedef struct BDRVDMGState {
     uint8_t *compressed_chunk;
     uint8_t *uncompressed_chunk;
     z_stream zstream;
+#ifdef CONFIG_BZIP2
+    bz_stream bzstream;
+#endif
 } BDRVDMGState;
 
 static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -123,6 +129,7 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
 
     switch (s->types[chunk]) {
     case 0x80000005: /* zlib compressed */
+    case 0x80000006: /* bzip2 compressed */
         compressed_size = s->lengths[chunk];
         uncompressed_sectors = s->sectorcounts[chunk];
         break;
@@ -198,6 +205,9 @@ static bool dmg_is_known_block_type(uint32_t entry_type)
     case 0x00000001:    /* uncompressed */
     case 0x00000002:    /* zeroes */
     case 0x80000005:    /* zlib */
+#ifdef CONFIG_BZIP2
+    case 0x80000006:    /* bzip2 */
+#endif
         return true;
     default:
         return false;
@@ -564,13 +574,16 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
     if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
         int ret;
         uint32_t chunk = search_chunk(s, sector_num);
+#ifdef CONFIG_BZIP2
+        uint64_t total_out;
+#endif
 
         if (chunk >= s->n_chunks) {
             return -1;
         }
 
         s->current_chunk = s->n_chunks;
-        switch (s->types[chunk]) {
+        switch (s->types[chunk]) { /* block entry type */
         case 0x80000005: { /* zlib compressed */
             /* we need to buffer, because only the chunk as whole can be
              * inflated. */
@@ -594,6 +607,34 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
                 return -1;
             }
             break; }
+#ifdef CONFIG_BZIP2
+        case 0x80000006: /* bzip2 compressed */
+            /* we need to buffer, because only the chunk as whole can be
+             * inflated. */
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
+                             s->compressed_chunk, s->lengths[chunk]);
+            if (ret != s->lengths[chunk]) {
+                return -1;
+            }
+
+            ret = BZ2_bzDecompressInit(&s->bzstream, 0, 0);
+            if (ret != BZ_OK) {
+                return -1;
+            }
+            s->bzstream.next_in = (char *)s->compressed_chunk;
+            s->bzstream.avail_in = (unsigned int) s->lengths[chunk];
+            s->bzstream.next_out = (char *)s->uncompressed_chunk;
+            s->bzstream.avail_out = (unsigned int) 512 * s->sectorcounts[chunk];
+            ret = BZ2_bzDecompress(&s->bzstream);
+            total_out = ((uint64_t)s->bzstream.total_out_hi32 << 32) +
+                        s->bzstream.total_out_lo32;
+            BZ2_bzDecompressEnd(&s->bzstream);
+            if (ret != BZ_STREAM_END ||
+                total_out != 512 * s->sectorcounts[chunk]) {
+                return -1;
+            }
+            break;
+#endif /* CONFIG_BZIP2 */
         case 1: /* copy */
             ret = bdrv_pread(bs->file, s->offsets[chunk],
                              s->uncompressed_chunk, s->lengths[chunk]);