git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / Atom feed
From: Thomas Gummerer <t.gummerer@gmail.com>
To: git@vger.kernel.org
Cc: trast@inf.ethz.ch, mhagger@alum.mit.edu, gitster@pobox.com,
	pclouds@gmail.com, robin.rosenberg@dewire.com,
	t.gummerer@gmail.com
Subject: [PATCH 02/22] read-cache: split index file version specific functionality
Date: Sun,  7 Jul 2013 10:11:40 +0200
Message-ID: <1373184720-29767-3-git-send-email-t.gummerer@gmail.com> (raw)
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

  parent reply	other threads:[~2013-07-07  8:12 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-07  8:11 [PATCH 00/22] Index v5 Thomas Gummerer
2013-07-07  8:11 ` [PATCH 01/22] t2104: Don't fail for index versions other than [23] Thomas Gummerer
2013-07-07  8:11 ` Thomas Gummerer [this message]
2013-07-07  8:11 ` [PATCH 03/22] read-cache: move index v2 specific functions to their own file Thomas Gummerer
2013-07-07  8:11 ` [PATCH 04/22] read-cache: Re-read index if index file changed Thomas Gummerer
2013-07-07  8:11 ` [PATCH 05/22] read-cache: add index reading api Thomas Gummerer
2013-07-08  2:01   ` Duy Nguyen
2013-07-08 11:40     ` Thomas Gummerer
2013-07-08  2:19   ` Duy Nguyen
2013-07-08 11:20     ` Thomas Gummerer
2013-07-08 12:45       ` Duy Nguyen
2013-07-08 13:37         ` Thomas Gummerer
2013-07-08 20:54         ` [PATCH 5.5/22] Add documentation for the index api Thomas Gummerer
2013-07-09 15:42           ` Duy Nguyen
2013-07-09 20:10             ` Thomas Gummerer
2013-07-10  5:28               ` Duy Nguyen
2013-07-11 11:30                 ` Thomas Gummerer
2013-07-11 11:42                   ` Duy Nguyen
2013-07-11 12:27                     ` Duy Nguyen
2013-07-08 16:36   ` [PATCH 05/22] read-cache: add index reading api Junio C Hamano
2013-07-08 20:10     ` Thomas Gummerer
2013-07-08 23:09       ` Junio C Hamano
2013-07-09 20:13         ` Thomas Gummerer
2013-07-07  8:11 ` [PATCH 06/22] make sure partially read index is not changed Thomas Gummerer
2013-07-08 16:31   ` Junio C Hamano
2013-07-08 18:33     ` Thomas Gummerer
2013-07-07  8:11 ` [PATCH 07/22] dir.c: use index api Thomas Gummerer
2013-07-07  8:11 ` [PATCH 08/22] tree.c: " Thomas Gummerer
2013-07-07  8:11 ` [PATCH 09/22] name-hash.c: " Thomas Gummerer
2013-07-07  8:11 ` [PATCH 10/22] grep.c: Use " Thomas Gummerer
2013-07-07  8:11 ` [PATCH 11/22] ls-files.c: use the " Thomas Gummerer
2013-07-07  8:11 ` [PATCH 12/22] read-cache: make read_blob_data_from_index use " Thomas Gummerer
2013-07-07  8:11 ` [PATCH 13/22] documentation: add documentation of the index-v5 file format Thomas Gummerer
2013-07-11 10:39   ` Duy Nguyen
2013-07-11 11:39     ` Thomas Gummerer
2013-07-11 11:47       ` Duy Nguyen
2013-07-11 12:26         ` Thomas Gummerer
2013-07-11 12:50           ` Duy Nguyen
2013-07-07  8:11 ` [PATCH 14/22] read-cache: make in-memory format aware of stat_crc Thomas Gummerer
2013-07-07  8:11 ` [PATCH 15/22] read-cache: read index-v5 Thomas Gummerer
2013-07-07 20:18   ` Eric Sunshine
2013-07-08 11:40     ` Thomas Gummerer
2013-07-07  8:11 ` [PATCH 16/22] read-cache: read resolve-undo data Thomas Gummerer
2013-07-07  8:11 ` [PATCH 17/22] read-cache: read cache-tree in index-v5 Thomas Gummerer
2013-07-07 20:41   ` Eric Sunshine
2013-07-07  8:11 ` [PATCH 18/22] read-cache: write index-v5 Thomas Gummerer
2013-07-07 20:43   ` Eric Sunshine
2013-07-07  8:11 ` [PATCH 19/22] read-cache: write index-v5 cache-tree data Thomas Gummerer
2013-07-07  8:11 ` [PATCH 20/22] read-cache: write resolve-undo data for index-v5 Thomas Gummerer
2013-07-07  8:11 ` [PATCH 21/22] update-index.c: rewrite index when index-version is given Thomas Gummerer
2013-07-07  8:12 ` [PATCH 22/22] p0003-index.sh: add perf test for the index formats Thomas Gummerer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1373184720-29767-3-git-send-email-t.gummerer@gmail.com \
    --to=t.gummerer@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=mhagger@alum.mit.edu \
    --cc=pclouds@gmail.com \
    --cc=robin.rosenberg@dewire.com \
    --cc=trast@inf.ethz.ch \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org list mirror (unofficial, one of many)

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 git git/ https://public-inbox.org/git \
		git@vger.kernel.org
	public-inbox-index git

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.io/gmane.comp.version-control.git
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for the project(s) associated with this inbox:

	https://80x24.org/mirrors/git.git

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git