![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/pack-check.c b/pack-check.c
index 8e123b71ed7898d2054ed9ef729c70ed40422bc3..0f8ad2c00f21d9a0a64b541ed95fff91650d7175 100644 (file)
--- a/pack-check.c
+++ b/pack-check.c
#include "cache.h"
#include "pack.h"
+#include "pack-revindex.h"
-#define BATCH (1u<<20)
+struct idx_entry
+{
+ const unsigned char *sha1;
+ off_t offset;
+};
-static int verify_packfile(struct packed_git *p)
+static int compare_entries(const void *e1, const void *e2)
{
- unsigned long index_size = p->index_size;
- void *index_base = p->index_base;
+ const struct idx_entry *entry1 = e1;
+ const struct idx_entry *entry2 = e2;
+ if (entry1->offset < entry2->offset)
+ return -1;
+ if (entry1->offset > entry2->offset)
+ return 1;
+ return 0;
+}
+
+static int verify_packfile(struct packed_git *p,
+ struct pack_window **w_curs)
+{
+ off_t index_size = p->index_size;
+ const unsigned char *index_base = p->index_data;
SHA_CTX ctx;
unsigned char sha1[20];
- struct pack_header *hdr;
- int nr_objects, err, i;
- unsigned char *packdata;
- unsigned long datasize;
-
- /* Header consistency check */
- hdr = p->pack_base;
- if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
- return error("Packfile %s signature mismatch", p->pack_name);
- if (!pack_version_ok(hdr->hdr_version))
- return error("Packfile version %d unsupported",
- ntohl(hdr->hdr_version));
- nr_objects = ntohl(hdr->hdr_entries);
- if (num_packed_objects(p) != nr_objects)
- return error("Packfile claims to have %d objects, "
- "while idx size expects %d", nr_objects,
- num_packed_objects(p));
-
- /* Check integrity of pack data with its SHA-1 checksum */
+ off_t offset = 0, pack_sig = p->pack_size - 20;
+ uint32_t nr_objects, i;
+ int err;
+ struct idx_entry *entries;
+
+ /* Note that the pack header checks are actually performed by
+ * use_pack when it first opens the pack file. If anything
+ * goes wrong during those checks then the call will die out
+ * immediately.
+ */
+
SHA1_Init(&ctx);
- packdata = p->pack_base;
- datasize = p->pack_size - 20;
- while (datasize) {
- unsigned long batch = (datasize < BATCH) ? datasize : BATCH;
- SHA1_Update(&ctx, packdata, batch);
- datasize -= batch;
- packdata += batch;
+ while (offset < pack_sig) {
+ unsigned int remaining;
+ unsigned char *in = use_pack(p, w_curs, offset, &remaining);
+ offset += remaining;
+ if (offset > pack_sig)
+ remaining -= (unsigned int)(offset - pack_sig);
+ SHA1_Update(&ctx, in, remaining);
}
SHA1_Final(sha1, &ctx);
-
- if (hashcmp(sha1, (unsigned char *)(p->pack_base) + p->pack_size - 20))
+ if (hashcmp(sha1, use_pack(p, w_curs, pack_sig, NULL)))
return error("Packfile %s SHA1 mismatch with itself",
p->pack_name);
- if (hashcmp(sha1, (unsigned char *)index_base + index_size - 40))
+ if (hashcmp(sha1, index_base + index_size - 40))
return error("Packfile %s SHA1 mismatch with idx",
p->pack_name);
+ unuse_pack(w_curs);
/* Make sure everything reachable from idx is valid. Since we
* have verified that nr_objects matches between idx and pack,
* we do not do scan-streaming check on the pack file.
*/
- for (i = err = 0; i < nr_objects; i++) {
- unsigned char sha1[20];
- void *data;
- char type[20];
- unsigned long size, offset;
-
- if (nth_packed_object_sha1(p, i, sha1))
+ nr_objects = p->num_objects;
+ entries = xmalloc(nr_objects * sizeof(*entries));
+ /* first sort entries by pack offset, since unpacking them is more efficient that way */
+ for (i = 0; i < nr_objects; i++) {
+ entries[i].sha1 = nth_packed_object_sha1(p, i);
+ if (!entries[i].sha1)
die("internal error pack-check nth-packed-object");
- offset = find_pack_entry_one(sha1, p);
- if (!offset)
+ entries[i].offset = find_pack_entry_one(entries[i].sha1, p);
+ if (!entries[i].offset)
die("internal error pack-check find-pack-entry-one");
- data = unpack_entry_gently(p, offset, type, &size);
+ }
+ qsort(entries, nr_objects, sizeof(*entries), compare_entries);
+
+ for (i = 0, err = 0; i < nr_objects; i++) {
+ void *data;
+ enum object_type type;
+ unsigned long size;
+
+ data = unpack_entry(p, entries[i].offset, &type, &size);
if (!data) {
err = error("cannot unpack %s from %s",
- sha1_to_hex(sha1), p->pack_name);
+ sha1_to_hex(entries[i].sha1), p->pack_name);
continue;
}
- if (check_sha1_signature(sha1, data, size, type)) {
+ if (check_sha1_signature(entries[i].sha1, data, size, typename(type))) {
err = error("packed %s from %s is corrupt",
- sha1_to_hex(sha1), p->pack_name);
+ sha1_to_hex(entries[i].sha1), p->pack_name);
free(data);
continue;
}
free(data);
}
+ free(entries);
return err;
}
-#define MAX_CHAIN 40
+#define MAX_CHAIN 50
static void show_pack_info(struct packed_git *p)
{
- struct pack_header *hdr;
- int nr_objects, i;
- unsigned int chain_histogram[MAX_CHAIN];
+ uint32_t nr_objects, i, chain_histogram[MAX_CHAIN+1];
- hdr = p->pack_base;
- nr_objects = ntohl(hdr->hdr_entries);
+ nr_objects = p->num_objects;
memset(chain_histogram, 0, sizeof(chain_histogram));
+ init_pack_revindex();
for (i = 0; i < nr_objects; i++) {
- unsigned char sha1[20], base_sha1[20];
- char type[20];
+ const unsigned char *sha1;
+ unsigned char base_sha1[20];
+ const char *type;
unsigned long size;
unsigned long store_size;
- unsigned long offset;
+ off_t offset;
unsigned int delta_chain_length;
- if (nth_packed_object_sha1(p, i, sha1))
+ sha1 = nth_packed_object_sha1(p, i);
+ if (!sha1)
die("internal error pack-check nth-packed-object");
offset = find_pack_entry_one(sha1, p);
if (!offset)
die("internal error pack-check find-pack-entry-one");
- packed_object_info_detail(p, offset, type, &size, &store_size,
- &delta_chain_length,
- base_sha1);
+ type = packed_object_info_detail(p, offset, &size, &store_size,
+ &delta_chain_length,
+ base_sha1);
printf("%s ", sha1_to_hex(sha1));
if (!delta_chain_length)
- printf("%-6s %lu %lu\n", type, size, offset);
+ printf("%-6s %lu %lu %"PRIuMAX"\n",
+ type, size, store_size, (uintmax_t)offset);
else {
- printf("%-6s %lu %lu %u %s\n", type, size, offset,
+ printf("%-6s %lu %lu %"PRIuMAX" %u %s\n",
+ type, size, store_size, (uintmax_t)offset,
delta_chain_length, sha1_to_hex(base_sha1));
- if (delta_chain_length < MAX_CHAIN)
+ if (delta_chain_length <= MAX_CHAIN)
chain_histogram[delta_chain_length]++;
else
chain_histogram[0]++;
}
}
- for (i = 0; i < MAX_CHAIN; i++) {
+ for (i = 0; i <= MAX_CHAIN; i++) {
if (!chain_histogram[i])
continue;
- printf("chain length %s %d: %d object%s\n",
- i ? "=" : ">=",
- i ? i : MAX_CHAIN,
- chain_histogram[i],
- 1 < chain_histogram[i] ? "s" : "");
+ printf("chain length = %d: %d object%s\n", i,
+ chain_histogram[i], chain_histogram[i] > 1 ? "s" : "");
}
+ if (chain_histogram[0])
+ printf("chain length > %d: %d object%s\n", MAX_CHAIN,
+ chain_histogram[0], chain_histogram[0] > 1 ? "s" : "");
}
int verify_pack(struct packed_git *p, int verbose)
{
- unsigned long index_size = p->index_size;
- void *index_base = p->index_base;
+ off_t index_size;
+ const unsigned char *index_base;
SHA_CTX ctx;
unsigned char sha1[20];
int ret;
+ if (open_pack_index(p))
+ return error("packfile %s index not opened", p->pack_name);
+ index_size = p->index_size;
+ index_base = p->index_data;
+
ret = 0;
/* Verify SHA1 sum of the index file */
SHA1_Init(&ctx);
- SHA1_Update(&ctx, index_base, index_size - 20);
+ SHA1_Update(&ctx, index_base, (unsigned int)(index_size - 20));
SHA1_Final(sha1, &ctx);
- if (hashcmp(sha1, (unsigned char *)index_base + index_size - 20))
+ if (hashcmp(sha1, index_base + index_size - 20))
ret = error("Packfile index for %s SHA1 mismatch",
p->pack_name);
if (!ret) {
/* Verify pack file */
- use_packed_git(p);
- ret = verify_packfile(p);
- unuse_packed_git(p);
+ struct pack_window *w_curs = NULL;
+ ret = verify_packfile(p, &w_curs);
+ unuse_pack(&w_curs);
}
if (verbose) {
if (ret)
printf("%s: bad\n", p->pack_name);
else {
- use_packed_git(p);
show_pack_info(p);
- unuse_packed_git(p);
printf("%s: ok\n", p->pack_name);
}
}