git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 02/22] read-cache: split index file version specific functionality

From
Thomas Gummerer <t.gummerer@gmail.com>
Date
Jul 7, 2013, 08:11 UTC
Message-ID
<1373184720-29767-3-git-send-email-t.gummerer@gmail.com>
In-Reply-To
<1373184720-29767-1-git-send-email-t.gummerer@gmail.com>

Split index file version specific functionality to their own functions, to prepare for moving the index file version specific parts to their own file. This makes it easier to add a new index file format later.

Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com>
---
 cache.h              |   5 +-
 read-cache.c         | 130 +++++++++++++++++++++++++++++++++------------------
 test-index-version.c |   2 +-
 3 files changed, 90 insertions(+), 47 deletions(-)
diff --git a/cache.h b/cache.h
index c288678..7af853b 100644
--- a/cache.h
+++ b/cache.h
@@ -100,9 +100,12 @@ unsigned long git_deflate_bound(git_zstream *, unsigned long);
  */
 
 #define CACHE_SIGNATURE 0x44495243	/* "DIRC" */
-struct cache_header {
+struct cache_version_header {
 	unsigned int hdr_signature;
 	unsigned int hdr_version;
+};
+
+struct cache_header {
 	unsigned int hdr_entries;
 };
 
diff --git a/read-cache.c b/read-cache.c
index d5201f9..93947bf 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1268,10 +1268,8 @@ struct ondisk_cache_entry_extended {
 			    ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
 			    ondisk_cache_entry_size(ce_namelen(ce)))
 
-static int verify_hdr(struct cache_header *hdr, unsigned long size)
+static int verify_hdr_version(struct cache_version_header *hdr, unsigned long size)
 {
-	git_SHA_CTX c;
-	unsigned char sha1[20];
 	int hdr_version;
 
 	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
@@ -1279,10 +1277,22 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size)
 	hdr_version = ntohl(hdr->hdr_version);
 	if (hdr_version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < hdr_version)
 		return error("bad index version %d", hdr_version);
+	return 0;
+}
+
+static int verify_hdr(void *mmap, unsigned long size)
+{
+	git_SHA_CTX c;
+	unsigned char sha1[20];
+
+	if (size < sizeof(struct cache_version_header)
+	    + sizeof(struct cache_header) + 20)
+		die("index file smaller than expected");
+
 	git_SHA1_Init(&c);
-	git_SHA1_Update(&c, hdr, size - 20);
+	git_SHA1_Update(&c, mmap, size - 20);
 	git_SHA1_Final(sha1, &c);
-	if (hashcmp(sha1, (unsigned char *)hdr + size - 20))
+	if (hashcmp(sha1, (unsigned char *)mmap + size - 20))
 		return error("bad index file sha1 signature");
 	return 0;
 }
@@ -1424,47 +1434,19 @@ static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk,
 	return ce;
 }
 
-/* remember to discard_cache() before reading a different cache! */
-int read_index_from(struct index_state *istate, const char *path)
+static int read_index_v2(struct index_state *istate, void *mmap, unsigned long mmap_size)
 {
-	int fd, i;
-	struct stat st;
+	int i;
 	unsigned long src_offset;
-	struct cache_header *hdr;
-	void *mmap;
-	size_t mmap_size;
+	struct cache_version_header *hdr;
+	struct cache_header *hdr_v2;
 	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
 
-	if (istate->initialized)
-		return istate->cache_nr;
-
-	istate->timestamp.sec = 0;
-	istate->timestamp.nsec = 0;
-	fd = open(path, O_RDONLY);
-	if (fd < 0) {
-		if (errno == ENOENT)
-			return 0;
-		die_errno("index file open failed");
-	}
-
-	if (fstat(fd, &st))
-		die_errno("cannot stat the open index");
-
-	mmap_size = xsize_t(st.st_size);
-	if (mmap_size < sizeof(struct cache_header) + 20)
-		die("index file smaller than expected");
-
-	mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
-	if (mmap == MAP_FAILED)
-		die_errno("unable to map index file");
-	close(fd);
-
 	hdr = mmap;
-	if (verify_hdr(hdr, mmap_size) < 0)
-		goto unmap;
+	hdr_v2 = (struct cache_header *)((char *)mmap + sizeof(*hdr));
 
 	istate->version = ntohl(hdr->hdr_version);
-	istate->cache_nr = ntohl(hdr->hdr_entries);
+	istate->cache_nr = ntohl(hdr_v2->hdr_entries);
 	istate->cache_alloc = alloc_nr(istate->cache_nr);
 	istate->cache = xcalloc(istate->cache_alloc, sizeof(*istate->cache));
 	istate->initialized = 1;
@@ -1474,7 +1456,7 @@ int read_index_from(struct index_state *istate, const char *path)
 	else
 		previous_name = NULL;
 
-	src_offset = sizeof(*hdr);
+	src_offset = sizeof(*hdr) + sizeof(*hdr_v2);
 	for (i = 0; i < istate->cache_nr; i++) {
 		struct ondisk_cache_entry *disk_ce;
 		struct cache_entry *ce;
@@ -1487,8 +1469,6 @@ int read_index_from(struct index_state *istate, const char *path)
 		src_offset += consumed;
 	}
 	strbuf_release(&previous_name_buf);
-	istate->timestamp.sec = st.st_mtime;
-	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 
 	while (src_offset <= mmap_size - 20 - 8) {
 		/* After an array of active_nr index entries,
@@ -1508,6 +1488,58 @@ int read_index_from(struct index_state *istate, const char *path)
 		src_offset += 8;
 		src_offset += extsize;
 	}
+	return 0;
+unmap:
+	munmap(mmap, mmap_size);
+	die("index file corrupt");
+}
+
+/* remember to discard_cache() before reading a different cache! */
+int read_index_from(struct index_state *istate, const char *path)
+{
+	int fd;
+	struct stat st;
+	struct cache_version_header *hdr;
+	void *mmap;
+	size_t mmap_size;
+
+	errno = EBUSY;
+	if (istate->initialized)
+		return istate->cache_nr;
+
+	errno = ENOENT;
+	istate->timestamp.sec = 0;
+	istate->timestamp.nsec = 0;
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		if (errno == ENOENT)
+			return 0;
+		die_errno("index file open failed");
+	}
+
+	if (fstat(fd, &st))
+		die_errno("cannot stat the open index");
+
+	errno = EINVAL;
+	mmap_size = xsize_t(st.st_size);
+	if (mmap_size < sizeof(struct cache_header) + 20)
+		die("index file smaller than expected");
+
+	mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+	close(fd);
+	if (mmap == MAP_FAILED)
+		die_errno("unable to map index file");
+
+	hdr = mmap;
+	if (verify_hdr_version(hdr, mmap_size) < 0)
+		goto unmap;
+
+	if (verify_hdr(mmap, mmap_size) < 0)
+		goto unmap;
+
+	read_index_v2(istate, mmap, mmap_size);
+	istate->timestamp.sec = st.st_mtime;
+	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 	munmap(mmap, mmap_size);
 	return istate->cache_nr;
 
@@ -1771,10 +1803,11 @@ void update_index_if_able(struct index_state *istate, struct lock_file *lockfile
 		rollback_lock_file(lockfile);
 }
 
-int write_index(struct index_state *istate, int newfd)
+static int write_index_v2(struct index_state *istate, int newfd)
 {
 	git_SHA_CTX c;
-	struct cache_header hdr;
+	struct cache_version_header hdr;
+	struct cache_header hdr_v2;
 	int i, err, removed, extended, hdr_version;
 	struct cache_entry **cache = istate->cache;
 	int entries = istate->cache_nr;
@@ -1804,11 +1837,13 @@ int write_index(struct index_state *istate, int newfd)
 
 	hdr.hdr_signature = htonl(CACHE_SIGNATURE);
 	hdr.hdr_version = htonl(hdr_version);
-	hdr.hdr_entries = htonl(entries - removed);
+	hdr_v2.hdr_entries = htonl(entries - removed);
 
 	git_SHA1_Init(&c);
 	if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0)
 		return -1;
+	if (ce_write(&c, newfd, &hdr_v2, sizeof(hdr_v2)) < 0)
+		return -1;
 
 	previous_name = (hdr_version == 4) ? &previous_name_buf : NULL;
 	for (i = 0; i < entries; i++) {
@@ -1854,6 +1889,11 @@ int write_index(struct index_state *istate, int newfd)
 	return 0;
 }
 
+int write_index(struct index_state *istate, int newfd)
+{
+	return write_index_v2(istate, newfd);
+}
+
 /*
  * Read the index file that is potentially unmerged into given
  * index_state, dropping any unmerged entries.  Returns true if
diff --git a/test-index-version.c b/test-index-version.c
index 05d4699..4c0386f 100644
--- a/test-index-version.c
+++ b/test-index-version.c
@@ -2,7 +2,7 @@
 
 int main(int argc, char **argv)
 {
-	struct cache_header hdr;
+	struct cache_version_header hdr;
 	int version;
 
 	memset(&hdr,0,sizeof(hdr));

-- 
1.8.3.453.g1dfc63d
Previous: Thomas GummererNext: Thomas Gummerer
Message 3 of 51 in “Index v5”
  1. 00/22 Index v5Thomas Gummerer, Jul 7, 2013
  2. 01/22 t2104: Don't fail for index versions other than [23]Thomas Gummerer, Jul 7, 2013
  3. 02/22 read-cache: split index file version specific functionalityThomas Gummerer, Jul 7, 2013
  4. 03/22 read-cache: move index v2 specific functions to their own fileThomas Gummerer, Jul 7, 2013
  5. 04/22 read-cache: Re-read index if index file changedThomas Gummerer, Jul 7, 2013
  6. 05/22 read-cache: add index reading apiThomas Gummerer, Jul 7, 2013
  7. Duy NguyenJul 8, 2013
  8. Thomas GummererJul 8, 2013
  9. Duy NguyenJul 8, 2013
  10. Thomas GummererJul 8, 2013
  11. Duy NguyenJul 8, 2013
  12. Thomas GummererJul 8, 2013
  13. 5/22 Add documentation for the index apiThomas Gummerer, Jul 8, 2013
  14. Duy NguyenJul 9, 2013
  15. Thomas GummererJul 9, 2013
  16. Duy NguyenJul 10, 2013
  17. Thomas GummererJul 11, 2013
  18. Duy NguyenJul 11, 2013
  19. Duy NguyenJul 11, 2013
  20. Junio C HamanoJul 8, 2013
  21. Thomas GummererJul 8, 2013
  22. Junio C HamanoJul 8, 2013
  23. Thomas GummererJul 9, 2013
  24. 06/22 make sure partially read index is not changedThomas Gummerer, Jul 7, 2013
  25. Junio C HamanoJul 8, 2013
  26. Thomas GummererJul 8, 2013
  27. 07/22 dir.c: use index apiThomas Gummerer, Jul 7, 2013
  28. 08/22 tree.c: use index apiThomas Gummerer, Jul 7, 2013
  29. 09/22 name-hash.c: use index apiThomas Gummerer, Jul 7, 2013
  30. 10/22 grep.c: Use index apiThomas Gummerer, Jul 7, 2013
  31. 11/22 ls-files.c: use the index apiThomas Gummerer, Jul 7, 2013
  32. 12/22 read-cache: make read_blob_data_from_index use index apiThomas Gummerer, Jul 7, 2013
  33. 13/22 documentation: add documentation of the index-v5 file formatThomas Gummerer, Jul 7, 2013
  34. Duy NguyenJul 11, 2013
  35. Thomas GummererJul 11, 2013
  36. Duy NguyenJul 11, 2013
  37. Thomas GummererJul 11, 2013
  38. Duy NguyenJul 11, 2013
  39. 14/22 read-cache: make in-memory format aware of stat_crcThomas Gummerer, Jul 7, 2013
  40. 15/22 read-cache: read index-v5Thomas Gummerer, Jul 7, 2013
  41. Eric SunshineJul 7, 2013
  42. Thomas GummererJul 8, 2013
  43. 16/22 read-cache: read resolve-undo dataThomas Gummerer, Jul 7, 2013
  44. 17/22 read-cache: read cache-tree in index-v5Thomas Gummerer, Jul 7, 2013
  45. Eric SunshineJul 7, 2013
  46. 18/22 read-cache: write index-v5Thomas Gummerer, Jul 7, 2013
  47. Eric SunshineJul 7, 2013
  48. 19/22 read-cache: write index-v5 cache-tree dataThomas Gummerer, Jul 7, 2013
  49. 20/22 read-cache: write resolve-undo data for index-v5Thomas Gummerer, Jul 7, 2013
  50. 21/22 update-index.c: rewrite index when index-version is givenThomas Gummerer, Jul 7, 2013
  51. 22/22 p0003-index.sh: add perf test for the index formatsThomas Gummerer, Jul 7, 2013

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.