1 files changed, 244 insertions, 85 deletions

diff --git a/read-cache.c b/read-cache.c
index 27e9fc6ee8..ef355cc9a8 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -12,6 +12,8 @@
 #include "commit.h"
 #include "blob.h"
 #include "resolve-undo.h"
+#include "strbuf.h"
+#include "varint.h"
 
 static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really);
 
@@ -157,16 +159,6 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st)
 	return 0;
 }
 
-static int is_empty_blob_sha1(const unsigned char *sha1)
-{
-	static const unsigned char empty_blob_sha1[20] = {
-		0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b,
-		0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91
-	};
-
-	return !hashcmp(sha1, empty_blob_sha1);
-}
-
 static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 {
 	unsigned int changed = 0;
@@ -1120,11 +1112,16 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p
 		struct cache_entry *ce, *new;
 		int cache_errno = 0;
 		int changed = 0;
+		int filtered = 0;
 
 		ce = istate->cache[i];
 		if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
 			continue;
 
+		if (pathspec &&
+		    !match_pathspec(pathspec, ce->name, strlen(ce->name), 0, seen))
+			filtered = 1;
+
 		if (ce_stage(ce)) {
 			while ((i < istate->cache_nr) &&
 			       ! strcmp(istate->cache[i]->name, ce->name))
@@ -1132,12 +1129,14 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p
 			i--;
 			if (allow_unmerged)
 				continue;
-			show_file(unmerged_fmt, ce->name, in_porcelain, &first, header_msg);
+			if (!filtered)
+				show_file(unmerged_fmt, ce->name, in_porcelain,
+					  &first, header_msg);
 			has_errors = 1;
 			continue;
 		}
 
-		if (pathspec && !match_pathspec(pathspec, ce->name, strlen(ce->name), 0, seen))
+		if (filtered)
 			continue;
 
 		new = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
@@ -1182,15 +1181,74 @@ static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int reall
 	return refresh_cache_ent(&the_index, ce, really, NULL, NULL);
 }
 
+
+/*****************************************************************
+ * Index File I/O
+ *****************************************************************/
+
+#define INDEX_FORMAT_DEFAULT 3
+
+/*
+ * dev/ino/uid/gid/size are also just tracked to the low 32 bits
+ * Again - this is just a (very strong in practice) heuristic that
+ * the inode hasn't changed.
+ *
+ * We save the fields in big-endian order to allow using the
+ * index file over NFS transparently.
+ */
+struct ondisk_cache_entry {
+	struct cache_time ctime;
+	struct cache_time mtime;
+	unsigned int dev;
+	unsigned int ino;
+	unsigned int mode;
+	unsigned int uid;
+	unsigned int gid;
+	unsigned int size;
+	unsigned char sha1[20];
+	unsigned short flags;
+	char name[FLEX_ARRAY]; /* more */
+};
+
+/*
+ * This struct is used when CE_EXTENDED bit is 1
+ * The struct must match ondisk_cache_entry exactly from
+ * ctime till flags
+ */
+struct ondisk_cache_entry_extended {
+	struct cache_time ctime;
+	struct cache_time mtime;
+	unsigned int dev;
+	unsigned int ino;
+	unsigned int mode;
+	unsigned int uid;
+	unsigned int gid;
+	unsigned int size;
+	unsigned char sha1[20];
+	unsigned short flags;
+	unsigned short flags2;
+	char name[FLEX_ARRAY]; /* more */
+};
+
+/* These are only used for v3 or lower */
+#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7)
+#define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len)
+#define ondisk_cache_entry_extended_size(len) align_flex_name(ondisk_cache_entry_extended,len)
+#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_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)
 {
 	git_SHA_CTX c;
 	unsigned char sha1[20];
+	int hdr_version;
 
 	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
 		return error("bad signature");
-	if (hdr->hdr_version != htonl(2) && hdr->hdr_version != htonl(3))
-		return error("bad index version");
+	hdr_version = ntohl(hdr->hdr_version);
+	if (hdr_version < 2 || 4 < hdr_version)
+		return error("bad index version %d", hdr_version);
 	git_SHA1_Init(&c);
 	git_SHA1_Update(&c, hdr, size - 20);
 	git_SHA1_Final(sha1, &c);
@@ -1224,63 +1282,115 @@ int read_index(struct index_state *istate)
 	return read_index_from(istate, get_index_file());
 }
 
-static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
+#ifndef NEEDS_ALIGNED_ACCESS
+#define ntoh_s(var) ntohs(var)
+#define ntoh_l(var) ntohl(var)
+#else
+static inline uint16_t ntoh_s_force_align(void *p)
+{
+	uint16_t x;
+	memcpy(&x, p, sizeof(x));
+	return ntohs(x);
+}
+static inline uint32_t ntoh_l_force_align(void *p)
 {
+	uint32_t x;
+	memcpy(&x, p, sizeof(x));
+	return ntohl(x);
+}
+#define ntoh_s(var) ntoh_s_force_align(&(var))
+#define ntoh_l(var) ntoh_l_force_align(&(var))
+#endif
+
+static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *ondisk,
+						   unsigned int flags,
+						   const char *name,
+						   size_t len)
+{
+	struct cache_entry *ce = xmalloc(cache_entry_size(len));
+
+	ce->ce_ctime.sec = ntoh_l(ondisk->ctime.sec);
+	ce->ce_mtime.sec = ntoh_l(ondisk->mtime.sec);
+	ce->ce_ctime.nsec = ntoh_l(ondisk->ctime.nsec);
+	ce->ce_mtime.nsec = ntoh_l(ondisk->mtime.nsec);
+	ce->ce_dev   = ntoh_l(ondisk->dev);
+	ce->ce_ino   = ntoh_l(ondisk->ino);
+	ce->ce_mode  = ntoh_l(ondisk->mode);
+	ce->ce_uid   = ntoh_l(ondisk->uid);
+	ce->ce_gid   = ntoh_l(ondisk->gid);
+	ce->ce_size  = ntoh_l(ondisk->size);
+	ce->ce_flags = flags;
+	hashcpy(ce->sha1, ondisk->sha1);
+	memcpy(ce->name, name, len);
+	ce->name[len] = '\0';
+	return ce;
+}
+
+/*
+ * Adjacent cache entries tend to share the leading paths, so it makes
+ * sense to only store the differences in later entries.  In the v4
+ * on-disk format of the index, each on-disk cache entry stores the
+ * number of bytes to be stripped from the end of the previous name,
+ * and the bytes to append to the result, to come up with its name.
+ */
+static unsigned long expand_name_field(struct strbuf *name, const char *cp_)
+{
+	const unsigned char *ep, *cp = (const unsigned char *)cp_;
+	size_t len = decode_varint(&cp);
+
+	if (name->len < len)
+		die("malformed name field in the index");
+	strbuf_remove(name, name->len - len, len);
+	for (ep = cp; *ep; ep++)
+		; /* find the end */
+	strbuf_add(name, cp, ep - cp);
+	return (const char *)ep + 1 - cp_;
+}
+
+static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk,
+					    unsigned long *ent_size,
+					    struct strbuf *previous_name)
+{
+	struct cache_entry *ce;
 	size_t len;
 	const char *name;
+	unsigned int flags;
 
-	ce->ce_ctime.sec = ntohl(ondisk->ctime.sec);
-	ce->ce_mtime.sec = ntohl(ondisk->mtime.sec);
-	ce->ce_ctime.nsec = ntohl(ondisk->ctime.nsec);
-	ce->ce_mtime.nsec = ntohl(ondisk->mtime.nsec);
-	ce->ce_dev   = ntohl(ondisk->dev);
-	ce->ce_ino   = ntohl(ondisk->ino);
-	ce->ce_mode  = ntohl(ondisk->mode);
-	ce->ce_uid   = ntohl(ondisk->uid);
-	ce->ce_gid   = ntohl(ondisk->gid);
-	ce->ce_size  = ntohl(ondisk->size);
 	/* On-disk flags are just 16 bits */
-	ce->ce_flags = ntohs(ondisk->flags);
+	flags = ntoh_s(ondisk->flags);
+	len = flags & CE_NAMEMASK;
 
-	hashcpy(ce->sha1, ondisk->sha1);
-
-	len = ce->ce_flags & CE_NAMEMASK;
-
-	if (ce->ce_flags & CE_EXTENDED) {
+	if (flags & CE_EXTENDED) {
 		struct ondisk_cache_entry_extended *ondisk2;
 		int extended_flags;
 		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
-		extended_flags = ntohs(ondisk2->flags2) << 16;
+		extended_flags = ntoh_s(ondisk2->flags2) << 16;
 		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
 		if (extended_flags & ~CE_EXTENDED_FLAGS)
 			die("Unknown index entry format %08x", extended_flags);
-		ce->ce_flags |= extended_flags;
+		flags |= extended_flags;
 		name = ondisk2->name;
 	}
 	else
 		name = ondisk->name;
 
-	if (len == CE_NAMEMASK)
-		len = strlen(name);
-	/*
-	 * NEEDSWORK: If the original index is crafted, this copy could
-	 * go unchecked.
-	 */
-	memcpy(ce->name, name, len + 1);
-}
-
-static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
-{
-	size_t fix_size_mem = offsetof(struct cache_entry, name);
-	size_t fix_size_dsk = offsetof(struct ondisk_cache_entry, name);
-	long per_entry = (fix_size_mem - fix_size_dsk + 7) & ~7;
-
-	/*
-	 * Alignment can cause differences. This should be "alignof", but
-	 * since that's a gcc'ism, just use the size of a pointer.
-	 */
-	per_entry += sizeof(void *);
-	return ondisk_size + entries*per_entry;
+	if (!previous_name) {
+		/* v3 and earlier */
+		if (len == CE_NAMEMASK)
+			len = strlen(name);
+		ce = cache_entry_from_ondisk(ondisk, flags, name, len);
+
+		*ent_size = ondisk_ce_size(ce);
+	} else {
+		unsigned long consumed;
+		consumed = expand_name_field(previous_name, name);
+		ce = cache_entry_from_ondisk(ondisk, flags,
+					     previous_name->buf,
+					     previous_name->len);
+
+		*ent_size = (name - ((char *)ondisk)) + consumed;
+	}
+	return ce;
 }
 
 /* remember to discard_cache() before reading a different cache! */
@@ -1288,10 +1398,11 @@ int read_index_from(struct index_state *istate, const char *path)
 {
 	int fd, i;
 	struct stat st;
-	unsigned long src_offset, dst_offset;
+	unsigned long src_offset;
 	struct cache_header *hdr;
 	void *mmap;
 	size_t mmap_size;
+	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
 
 	errno = EBUSY;
 	if (istate->initialized)
@@ -1324,33 +1435,30 @@ int read_index_from(struct index_state *istate, const char *path)
 	if (verify_hdr(hdr, mmap_size) < 0)
 		goto unmap;
 
+	istate->version = ntohl(hdr->hdr_version);
 	istate->cache_nr = ntohl(hdr->hdr_entries);
 	istate->cache_alloc = alloc_nr(istate->cache_nr);
 	istate->cache = xcalloc(istate->cache_alloc, sizeof(struct cache_entry *));
-
-	/*
-	 * The disk format is actually larger than the in-memory format,
-	 * due to space for nsec etc, so even though the in-memory one
-	 * has room for a few  more flags, we can allocate using the same
-	 * index size
-	 */
-	istate->alloc = xmalloc(estimate_cache_size(mmap_size, istate->cache_nr));
 	istate->initialized = 1;
 
+	if (istate->version == 4)
+		previous_name = &previous_name_buf;
+	else
+		previous_name = NULL;
+
 	src_offset = sizeof(*hdr);
-	dst_offset = 0;
 	for (i = 0; i < istate->cache_nr; i++) {
 		struct ondisk_cache_entry *disk_ce;
 		struct cache_entry *ce;
+		unsigned long consumed;
 
 		disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
-		ce = (struct cache_entry *)((char *)istate->alloc + dst_offset);
-		convert_from_disk(disk_ce, ce);
+		ce = create_from_disk(disk_ce, &consumed, previous_name);
 		set_index_entry(istate, i, ce);
 
-		src_offset += ondisk_ce_size(ce);
-		dst_offset += ce_size(ce);
+		src_offset += consumed;
 	}
+	strbuf_release(&previous_name_buf);
 	istate->timestamp.sec = st.st_mtime;
 	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 
@@ -1383,11 +1491,15 @@ unmap:
 
 int is_index_unborn(struct index_state *istate)
 {
-	return (!istate->cache_nr && !istate->alloc && !istate->timestamp.sec);
+	return (!istate->cache_nr && !istate->timestamp.sec);
 }
 
 int discard_index(struct index_state *istate)
 {
+	int i;
+
+	for (i = 0; i < istate->cache_nr; i++)
+		free(istate->cache[i]);
 	resolve_undo_clear_index(istate);
 	istate->cache_nr = 0;
 	istate->cache_changed = 0;
@@ -1396,8 +1508,6 @@ int discard_index(struct index_state *istate)
 	istate->name_hash_initialized = 0;
 	free_hash(&istate->name_hash);
 	cache_tree_free(&(istate->cache_tree));
-	free(istate->alloc);
-	istate->alloc = NULL;
 	istate->initialized = 0;
 
 	/* no need to throw away allocated active_cache */
@@ -1532,13 +1642,10 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
 	}
 }
 
-static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce)
+/* Copy miscellaneous fields but not the name */
+static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
+				       struct cache_entry *ce)
 {
-	int size = ondisk_ce_size(ce);
-	struct ondisk_cache_entry *ondisk = xcalloc(1, size);
-	char *name;
-	int result;
-
 	ondisk->ctime.sec = htonl(ce->ce_ctime.sec);
 	ondisk->mtime.sec = htonl(ce->ce_mtime.sec);
 	ondisk->ctime.nsec = htonl(ce->ce_ctime.nsec);
@@ -1555,11 +1662,52 @@ static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce)
 		struct ondisk_cache_entry_extended *ondisk2;
 		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
 		ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
-		name = ondisk2->name;
+		return ondisk2->name;
+	}
+	else {
+		return ondisk->name;
+	}
+}
+
+static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce,
+			  struct strbuf *previous_name)
+{
+	int size;
+	struct ondisk_cache_entry *ondisk;
+	char *name;
+	int result;
+
+	if (!previous_name) {
+		size = ondisk_ce_size(ce);
+		ondisk = xcalloc(1, size);
+		name = copy_cache_entry_to_ondisk(ondisk, ce);
+		memcpy(name, ce->name, ce_namelen(ce));
+	} else {
+		int common, to_remove, prefix_size;
+		unsigned char to_remove_vi[16];
+		for (common = 0;
+		     (ce->name[common] &&
+		      common < previous_name->len &&
+		      ce->name[common] == previous_name->buf[common]);
+		     common++)
+			; /* still matching */
+		to_remove = previous_name->len - common;
+		prefix_size = encode_varint(to_remove, to_remove_vi);
+
+		if (ce->ce_flags & CE_EXTENDED)
+			size = offsetof(struct ondisk_cache_entry_extended, name);
+		else
+			size = offsetof(struct ondisk_cache_entry, name);
+		size += prefix_size + (ce_namelen(ce) - common + 1);
+
+		ondisk = xcalloc(1, size);
+		name = copy_cache_entry_to_ondisk(ondisk, ce);
+		memcpy(name, to_remove_vi, prefix_size);
+		memcpy(name + prefix_size, ce->name + common, ce_namelen(ce) - common);
+
+		strbuf_splice(previous_name, common, to_remove,
+			      ce->name + common, ce_namelen(ce) - common);
 	}
-	else
-		name = ondisk->name;
-	memcpy(name, ce->name, ce_namelen(ce));
 
 	result = ce_write(c, fd, ondisk, size);
 	free(ondisk);
@@ -1595,10 +1743,11 @@ int write_index(struct index_state *istate, int newfd)
 {
 	git_SHA_CTX c;
 	struct cache_header hdr;
-	int i, err, removed, extended;
+	int i, err, removed, extended, hdr_version;
 	struct cache_entry **cache = istate->cache;
 	int entries = istate->cache_nr;
 	struct stat st;
+	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
 
 	for (i = removed = extended = 0; i < entries; i++) {
 		if (cache[i]->ce_flags & CE_REMOVE)
@@ -1612,24 +1761,34 @@ int write_index(struct index_state *istate, int newfd)
 		}
 	}
 
+	if (!istate->version)
+		istate->version = INDEX_FORMAT_DEFAULT;
+
+	/* demote version 3 to version 2 when the latter suffices */
+	if (istate->version == 3 || istate->version == 2)
+		istate->version = extended ? 3 : 2;
+
+	hdr_version = istate->version;
+
 	hdr.hdr_signature = htonl(CACHE_SIGNATURE);
-	/* for extended format, increase version so older git won't try to read it */
-	hdr.hdr_version = htonl(extended ? 3 : 2);
+	hdr.hdr_version = htonl(hdr_version);
 	hdr.hdr_entries = htonl(entries - removed);
 
 	git_SHA1_Init(&c);
 	if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0)
 		return -1;
 
+	previous_name = (hdr_version == 4) ? &previous_name_buf : NULL;
 	for (i = 0; i < entries; i++) {
 		struct cache_entry *ce = cache[i];
 		if (ce->ce_flags & CE_REMOVE)
 			continue;
 		if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce))
 			ce_smudge_racily_clean_entry(ce);
-		if (ce_write_entry(&c, newfd, ce) < 0)
+		if (ce_write_entry(&c, newfd, ce, previous_name) < 0)
 			return -1;
 	}
+	strbuf_release(&previous_name_buf);
 
 	/* Write extension data here */
 	if (istate->cache_tree) {