diff options
Diffstat (limited to 'builtin/index-pack.c')
| -rw-r--r-- | builtin/index-pack.c | 1250 | 
1 files changed, 921 insertions, 329 deletions
| diff --git a/builtin/index-pack.c b/builtin/index-pack.c index af7dc37a44..3431de2362 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -9,6 +9,8 @@  #include "progress.h"  #include "fsck.h"  #include "exec_cmd.h" +#include "streaming.h" +#include "thread-utils.h"  static const char index_pack_usage[] =  "git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])"; @@ -16,16 +18,14 @@ static const char index_pack_usage[] =  struct object_entry {  	struct pack_idx_entry idx;  	unsigned long size; -	unsigned int hdr_size; -	enum object_type type; -	enum object_type real_type; -	unsigned delta_depth; -	int base_object_no; +	unsigned char hdr_size; +	signed char type; +	signed char real_type;  }; -union delta_base { -	unsigned char sha1[20]; -	off_t offset; +struct object_stat { +	unsigned delta_depth; +	int base_object_no;  };  struct base_data { @@ -34,33 +34,51 @@ struct base_data {  	struct object_entry *obj;  	void *data;  	unsigned long size; +	int ref_first, ref_last; +	int ofs_first, ofs_last;  }; -/* - * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want - * to memcmp() only the first 20 bytes. - */ -#define UNION_BASE_SZ	20 +struct thread_local { +#ifndef NO_PTHREADS +	pthread_t thread; +#endif +	struct base_data *base_cache; +	size_t base_cache_used; +	int pack_fd; +};  #define FLAG_LINK (1u<<20)  #define FLAG_CHECKED (1u<<21) -struct delta_entry { -	union delta_base base; +struct ofs_delta_entry { +	off_t offset; +	int obj_no; +}; + +struct ref_delta_entry { +	unsigned char sha1[20];  	int obj_no;  };  static struct object_entry *objects; -static struct delta_entry *deltas; -static struct base_data *base_cache; -static size_t base_cache_used; +static struct object_stat *obj_stat; +static struct ofs_delta_entry *ofs_deltas; +static struct ref_delta_entry *ref_deltas; +static struct thread_local nothread_data;  static int nr_objects; -static int nr_deltas; +static int nr_ofs_deltas; +static int nr_ref_deltas; +static int ref_deltas_alloc;  static int nr_resolved_deltas; +static int nr_threads;  static int from_stdin;  static int strict; +static int do_fsck_object; +static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;  static int verbose; +static int show_stat; +static int check_self_contained_and_connected;  static struct progress *progress; @@ -71,15 +89,117 @@ static off_t consumed_bytes;  static unsigned deepest_delta;  static git_SHA_CTX input_ctx;  static uint32_t input_crc32; -static int input_fd, output_fd, pack_fd; +static int input_fd, output_fd; +static const char *curr_pack; + +#ifndef NO_PTHREADS -static int mark_link(struct object *obj, int type, void *data) +static struct thread_local *thread_data; +static int nr_dispatched; +static int threads_active; + +static pthread_mutex_t read_mutex; +#define read_lock()		lock_mutex(&read_mutex) +#define read_unlock()		unlock_mutex(&read_mutex) + +static pthread_mutex_t counter_mutex; +#define counter_lock()		lock_mutex(&counter_mutex) +#define counter_unlock()	unlock_mutex(&counter_mutex) + +static pthread_mutex_t work_mutex; +#define work_lock()		lock_mutex(&work_mutex) +#define work_unlock()		unlock_mutex(&work_mutex) + +static pthread_mutex_t deepest_delta_mutex; +#define deepest_delta_lock()	lock_mutex(&deepest_delta_mutex) +#define deepest_delta_unlock()	unlock_mutex(&deepest_delta_mutex) + +static pthread_mutex_t type_cas_mutex; +#define type_cas_lock()		lock_mutex(&type_cas_mutex) +#define type_cas_unlock()	unlock_mutex(&type_cas_mutex) + +static pthread_key_t key; + +static inline void lock_mutex(pthread_mutex_t *mutex) +{ +	if (threads_active) +		pthread_mutex_lock(mutex); +} + +static inline void unlock_mutex(pthread_mutex_t *mutex) +{ +	if (threads_active) +		pthread_mutex_unlock(mutex); +} + +/* + * Mutex and conditional variable can't be statically-initialized on Windows. + */ +static void init_thread(void) +{ +	int i; +	init_recursive_mutex(&read_mutex); +	pthread_mutex_init(&counter_mutex, NULL); +	pthread_mutex_init(&work_mutex, NULL); +	pthread_mutex_init(&type_cas_mutex, NULL); +	if (show_stat) +		pthread_mutex_init(&deepest_delta_mutex, NULL); +	pthread_key_create(&key, NULL); +	thread_data = xcalloc(nr_threads, sizeof(*thread_data)); +	for (i = 0; i < nr_threads; i++) { +		thread_data[i].pack_fd = open(curr_pack, O_RDONLY); +		if (thread_data[i].pack_fd == -1) +			die_errno(_("unable to open %s"), curr_pack); +	} + +	threads_active = 1; +} + +static void cleanup_thread(void) +{ +	int i; +	if (!threads_active) +		return; +	threads_active = 0; +	pthread_mutex_destroy(&read_mutex); +	pthread_mutex_destroy(&counter_mutex); +	pthread_mutex_destroy(&work_mutex); +	pthread_mutex_destroy(&type_cas_mutex); +	if (show_stat) +		pthread_mutex_destroy(&deepest_delta_mutex); +	for (i = 0; i < nr_threads; i++) +		close(thread_data[i].pack_fd); +	pthread_key_delete(key); +	free(thread_data); +} + +#else + +#define read_lock() +#define read_unlock() + +#define counter_lock() +#define counter_unlock() + +#define work_lock() +#define work_unlock() + +#define deepest_delta_lock() +#define deepest_delta_unlock() + +#define type_cas_lock() +#define type_cas_unlock() + +#endif + + +static int mark_link(struct object *obj, int type, void *data, struct fsck_options *options)  {  	if (!obj)  		return -1;  	if (type != OBJ_ANY && obj->type != type) -		die("object type mismatch at %s", sha1_to_hex(obj->sha1)); +		die(_("object type mismatch at %s"), sha1_to_hex(obj->sha1));  	obj->flags |= FLAG_LINK;  	return 0; @@ -87,31 +207,39 @@ static int mark_link(struct object *obj, int type, void *data)  /* The content of each linked object must have been checked     or it must be already present in the object database */ -static void check_object(struct object *obj) +static unsigned check_object(struct object *obj)  {  	if (!obj) -		return; +		return 0;  	if (!(obj->flags & FLAG_LINK)) -		return; +		return 0;  	if (!(obj->flags & FLAG_CHECKED)) {  		unsigned long size;  		int type = sha1_object_info(obj->sha1, &size); -		if (type != obj->type || type <= 0) -			die("object of unexpected type"); +		if (type <= 0) +			die(_("did not receive expected object %s"), +			      sha1_to_hex(obj->sha1)); +		if (type != obj->type) +			die(_("object %s: expected type %s, found %s"), +			    sha1_to_hex(obj->sha1), +			    typename(obj->type), typename(type));  		obj->flags |= FLAG_CHECKED; -		return; +		return 1;  	} + +	return 0;  } -static void check_objects(void) +static unsigned check_objects(void)  { -	unsigned i, max; +	unsigned i, max, foreign_nr = 0;  	max = get_max_object_index();  	for (i = 0; i < max; i++) -		check_object(get_indexed_object(i)); +		foreign_nr += check_object(get_indexed_object(i)); +	return foreign_nr;  } @@ -136,15 +264,18 @@ static void *fill(int min)  	if (min <= input_len)  		return input_buffer + input_offset;  	if (min > sizeof(input_buffer)) -		die("cannot fill %d bytes", min); +		die(Q_("cannot fill %d byte", +		       "cannot fill %d bytes", +		       min), +		    min);  	flush();  	do {  		ssize_t ret = xread(input_fd, input_buffer + input_len,  				sizeof(input_buffer) - input_len);  		if (ret <= 0) {  			if (!ret) -				die("early EOF"); -			die_errno("read error on input"); +				die(_("early EOF")); +			die_errno(_("read error on input"));  		}  		input_len += ret;  		if (from_stdin) @@ -156,14 +287,14 @@ static void *fill(int min)  static void use(int bytes)  {  	if (bytes > input_len) -		die("used more bytes than were available"); +		die(_("used more bytes than were available"));  	input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);  	input_len -= bytes;  	input_offset += bytes;  	/* make sure off_t is sufficiently large not to wrap */  	if (signed_add_overflows(consumed_bytes, bytes)) -		die("pack too large for current definition of off_t"); +		die(_("pack too large for current definition of off_t"));  	consumed_bytes += bytes;  } @@ -179,14 +310,14 @@ static const char *open_pack_file(const char *pack_name)  		} else  			output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);  		if (output_fd < 0) -			die_errno("unable to create '%s'", pack_name); -		pack_fd = output_fd; +			die_errno(_("unable to create '%s'"), pack_name); +		nothread_data.pack_fd = output_fd;  	} else {  		input_fd = open(pack_name, O_RDONLY);  		if (input_fd < 0) -			die_errno("cannot open packfile '%s'", pack_name); +			die_errno(_("cannot open packfile '%s'"), pack_name);  		output_fd = -1; -		pack_fd = input_fd; +		nothread_data.pack_fd = input_fd;  	}  	git_SHA1_Init(&input_ctx);  	return pack_name; @@ -198,9 +329,9 @@ static void parse_pack_header(void)  	/* Header consistency check */  	if (hdr->hdr_signature != htonl(PACK_SIGNATURE)) -		die("pack signature mismatch"); +		die(_("pack signature mismatch"));  	if (!pack_version_ok(hdr->hdr_version)) -		die("pack version %"PRIu32" unsupported", +		die(_("pack version %"PRIu32" unsupported"),  			ntohl(hdr->hdr_version));  	nr_objects = ntohl(hdr->hdr_entries); @@ -218,7 +349,34 @@ static NORETURN void bad_object(unsigned long offset, const char *format, ...)  	va_start(params, format);  	vsnprintf(buf, sizeof(buf), format, params);  	va_end(params); -	die("pack has bad object at offset %lu: %s", offset, buf); +	die(_("pack has bad object at offset %lu: %s"), offset, buf); +} + +static inline struct thread_local *get_thread_data(void) +{ +#ifndef NO_PTHREADS +	if (threads_active) +		return pthread_getspecific(key); +	assert(!threads_active && +	       "This should only be reached when all threads are gone"); +#endif +	return ¬hread_data; +} + +#ifndef NO_PTHREADS +static void set_thread_data(struct thread_local *data) +{ +	if (threads_active) +		pthread_setspecific(key, data); +} +#endif + +static struct base_data *alloc_base_data(void) +{ +	struct base_data *base = xcalloc(1, sizeof(struct base_data)); +	base->ref_last = -1; +	base->ofs_last = -1; +	return base;  }  static void free_base_data(struct base_data *c) @@ -226,15 +384,16 @@ static void free_base_data(struct base_data *c)  	if (c->data) {  		free(c->data);  		c->data = NULL; -		base_cache_used -= c->size; +		get_thread_data()->base_cache_used -= c->size;  	}  }  static void prune_base_data(struct base_data *retain)  {  	struct base_data *b; -	for (b = base_cache; -	     base_cache_used > delta_base_cache_limit && b; +	struct thread_local *data = get_thread_data(); +	for (b = data->base_cache; +	     data->base_cache_used > delta_base_cache_limit && b;  	     b = b->child) {  		if (b->data && b != retain)  			free_base_data(b); @@ -246,12 +405,12 @@ static void link_base_data(struct base_data *base, struct base_data *c)  	if (base)  		base->child = c;  	else -		base_cache = c; +		get_thread_data()->base_cache = c;  	c->base = base;  	c->child = NULL;  	if (c->data) -		base_cache_used += c->size; +		get_thread_data()->base_cache_used += c->size;  	prune_base_data(c);  } @@ -261,34 +420,67 @@ static void unlink_base_data(struct base_data *c)  	if (base)  		base->child = NULL;  	else -		base_cache = NULL; +		get_thread_data()->base_cache = NULL;  	free_base_data(c);  } -static void *unpack_entry_data(unsigned long offset, unsigned long size) +static int is_delta_type(enum object_type type)  { +	return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA); +} + +static void *unpack_entry_data(unsigned long offset, unsigned long size, +			       enum object_type type, unsigned char *sha1) +{ +	static char fixed_buf[8192];  	int status;  	git_zstream stream; -	void *buf = xmalloc(size); +	void *buf; +	git_SHA_CTX c; +	char hdr[32]; +	int hdrlen; + +	if (!is_delta_type(type)) { +		hdrlen = sprintf(hdr, "%s %lu", typename(type), size) + 1; +		git_SHA1_Init(&c); +		git_SHA1_Update(&c, hdr, hdrlen); +	} else +		sha1 = NULL; +	if (type == OBJ_BLOB && size > big_file_threshold) +		buf = fixed_buf; +	else +		buf = xmallocz(size);  	memset(&stream, 0, sizeof(stream));  	git_inflate_init(&stream);  	stream.next_out = buf; -	stream.avail_out = size; +	stream.avail_out = buf == fixed_buf ? sizeof(fixed_buf) : size;  	do { +		unsigned char *last_out = stream.next_out;  		stream.next_in = fill(1);  		stream.avail_in = input_len;  		status = git_inflate(&stream, 0);  		use(input_len - stream.avail_in); +		if (sha1) +			git_SHA1_Update(&c, last_out, stream.next_out - last_out); +		if (buf == fixed_buf) { +			stream.next_out = buf; +			stream.avail_out = sizeof(fixed_buf); +		}  	} while (status == Z_OK);  	if (stream.total_out != size || status != Z_STREAM_END) -		bad_object(offset, "inflate returned %d", status); +		bad_object(offset, _("inflate returned %d"), status);  	git_inflate_end(&stream); -	return buf; +	if (sha1) +		git_SHA1_Final(sha1, &c); +	return buf == fixed_buf ? NULL : buf;  } -static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base) +static void *unpack_raw_entry(struct object_entry *obj, +			      off_t *ofs_offset, +			      unsigned char *ref_sha1, +			      unsigned char *sha1)  {  	unsigned char *p;  	unsigned long size, c; @@ -316,11 +508,10 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_  	switch (obj->type) {  	case OBJ_REF_DELTA: -		hashcpy(delta_base->sha1, fill(20)); +		hashcpy(ref_sha1, fill(20));  		use(20);  		break;  	case OBJ_OFS_DELTA: -		memset(delta_base, 0, sizeof(*delta_base));  		p = fill(1);  		c = *p;  		use(1); @@ -328,15 +519,15 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_  		while (c & 128) {  			base_offset += 1;  			if (!base_offset || MSB(base_offset, 7)) -				bad_object(obj->idx.offset, "offset value overflow for delta base object"); +				bad_object(obj->idx.offset, _("offset value overflow for delta base object"));  			p = fill(1);  			c = *p;  			use(1);  			base_offset = (base_offset << 7) + (c & 127);  		} -		delta_base->offset = obj->idx.offset - base_offset; -		if (delta_base->offset <= 0 || delta_base->offset >= obj->idx.offset) -			bad_object(obj->idx.offset, "delta base offset is out of bound"); +		*ofs_offset = obj->idx.offset - base_offset; +		if (*ofs_offset <= 0 || *ofs_offset >= obj->idx.offset) +			bad_object(obj->idx.offset, _("delta base offset is out of bound"));  		break;  	case OBJ_COMMIT:  	case OBJ_TREE: @@ -344,16 +535,18 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_  	case OBJ_TAG:  		break;  	default: -		bad_object(obj->idx.offset, "unknown object type %d", obj->type); +		bad_object(obj->idx.offset, _("unknown object type %d"), obj->type);  	}  	obj->hdr_size = consumed_bytes - obj->idx.offset; -	data = unpack_entry_data(obj->idx.offset, obj->size); +	data = unpack_entry_data(obj->idx.offset, obj->size, obj->type, sha1);  	obj->idx.crc32 = input_crc32;  	return data;  } -static void *get_data_from_pack(struct object_entry *obj) +static void *unpack_data(struct object_entry *obj, +			 int (*consume)(const unsigned char *, unsigned long, void *), +			 void *cb_data)  {  	off_t from = obj[0].idx.offset + obj[0].hdr_size;  	unsigned long len = obj[1].idx.offset - from; @@ -361,171 +554,371 @@ static void *get_data_from_pack(struct object_entry *obj)  	git_zstream stream;  	int status; -	data = xmalloc(obj->size); +	data = xmallocz(consume ? 64*1024 : obj->size);  	inbuf = xmalloc((len < 64*1024) ? len : 64*1024);  	memset(&stream, 0, sizeof(stream));  	git_inflate_init(&stream);  	stream.next_out = data; -	stream.avail_out = obj->size; +	stream.avail_out = consume ? 64*1024 : obj->size;  	do {  		ssize_t n = (len < 64*1024) ? len : 64*1024; -		n = pread(pack_fd, inbuf, n, from); +		n = xpread(get_thread_data()->pack_fd, inbuf, n, from);  		if (n < 0) -			die_errno("cannot pread pack file"); +			die_errno(_("cannot pread pack file"));  		if (!n) -			die("premature end of pack file, %lu bytes missing", len); +			die(Q_("premature end of pack file, %lu byte missing", +			       "premature end of pack file, %lu bytes missing", +			       len), +			    len);  		from += n;  		len -= n;  		stream.next_in = inbuf;  		stream.avail_in = n; -		status = git_inflate(&stream, 0); +		if (!consume) +			status = git_inflate(&stream, 0); +		else { +			do { +				status = git_inflate(&stream, 0); +				if (consume(data, stream.next_out - data, cb_data)) { +					free(inbuf); +					free(data); +					return NULL; +				} +				stream.next_out = data; +				stream.avail_out = 64*1024; +			} while (status == Z_OK && stream.avail_in); +		}  	} while (len && status == Z_OK && !stream.avail_in);  	/* This has been inflated OK when first encountered, so... */  	if (status != Z_STREAM_END || stream.total_out != obj->size) -		die("serious inflate inconsistency"); +		die(_("serious inflate inconsistency"));  	git_inflate_end(&stream);  	free(inbuf); +	if (consume) { +		free(data); +		data = NULL; +	}  	return data;  } -static int compare_delta_bases(const union delta_base *base1, -			       const union delta_base *base2, -			       enum object_type type1, -			       enum object_type type2) +static void *get_data_from_pack(struct object_entry *obj) +{ +	return unpack_data(obj, NULL, NULL); +} + +static int compare_ofs_delta_bases(off_t offset1, off_t offset2, +				   enum object_type type1, +				   enum object_type type2) +{ +	int cmp = type1 - type2; +	if (cmp) +		return cmp; +	return offset1 < offset2 ? -1 : +	       offset1 > offset2 ?  1 : +	       0; +} + +static int find_ofs_delta(const off_t offset, enum object_type type) +{ +	int first = 0, last = nr_ofs_deltas; + +	while (first < last) { +		int next = (first + last) / 2; +		struct ofs_delta_entry *delta = &ofs_deltas[next]; +		int cmp; + +		cmp = compare_ofs_delta_bases(offset, delta->offset, +					      type, objects[delta->obj_no].type); +		if (!cmp) +			return next; +		if (cmp < 0) { +			last = next; +			continue; +		} +		first = next+1; +	} +	return -first-1; +} + +static void find_ofs_delta_children(off_t offset, +				    int *first_index, int *last_index, +				    enum object_type type) +{ +	int first = find_ofs_delta(offset, type); +	int last = first; +	int end = nr_ofs_deltas - 1; + +	if (first < 0) { +		*first_index = 0; +		*last_index = -1; +		return; +	} +	while (first > 0 && ofs_deltas[first - 1].offset == offset) +		--first; +	while (last < end && ofs_deltas[last + 1].offset == offset) +		++last; +	*first_index = first; +	*last_index = last; +} + +static int compare_ref_delta_bases(const unsigned char *sha1, +				   const unsigned char *sha2, +				   enum object_type type1, +				   enum object_type type2)  {  	int cmp = type1 - type2;  	if (cmp)  		return cmp; -	return memcmp(base1, base2, UNION_BASE_SZ); +	return hashcmp(sha1, sha2);  } -static int find_delta(const union delta_base *base, enum object_type type) +static int find_ref_delta(const unsigned char *sha1, enum object_type type)  { -	int first = 0, last = nr_deltas; - -        while (first < last) { -                int next = (first + last) / 2; -                struct delta_entry *delta = &deltas[next]; -                int cmp; - -		cmp = compare_delta_bases(base, &delta->base, -					  type, objects[delta->obj_no].type); -                if (!cmp) -                        return next; -                if (cmp < 0) { -                        last = next; -                        continue; -                } -                first = next+1; -        } -        return -first-1; +	int first = 0, last = nr_ref_deltas; + +	while (first < last) { +		int next = (first + last) / 2; +		struct ref_delta_entry *delta = &ref_deltas[next]; +		int cmp; + +		cmp = compare_ref_delta_bases(sha1, delta->sha1, +					      type, objects[delta->obj_no].type); +		if (!cmp) +			return next; +		if (cmp < 0) { +			last = next; +			continue; +		} +		first = next+1; +	} +	return -first-1;  } -static void find_delta_children(const union delta_base *base, -				int *first_index, int *last_index, -				enum object_type type) +static void find_ref_delta_children(const unsigned char *sha1, +				    int *first_index, int *last_index, +				    enum object_type type)  { -	int first = find_delta(base, type); +	int first = find_ref_delta(sha1, type);  	int last = first; -	int end = nr_deltas - 1; +	int end = nr_ref_deltas - 1;  	if (first < 0) {  		*first_index = 0;  		*last_index = -1;  		return;  	} -	while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ)) +	while (first > 0 && !hashcmp(ref_deltas[first - 1].sha1, sha1))  		--first; -	while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ)) +	while (last < end && !hashcmp(ref_deltas[last + 1].sha1, sha1))  		++last;  	*first_index = first;  	*last_index = last;  } -static void sha1_object(const void *data, unsigned long size, -			enum object_type type, unsigned char *sha1) +struct compare_data { +	struct object_entry *entry; +	struct git_istream *st; +	unsigned char *buf; +	unsigned long buf_size; +}; + +static int compare_objects(const unsigned char *buf, unsigned long size, +			   void *cb_data) +{ +	struct compare_data *data = cb_data; + +	if (data->buf_size < size) { +		free(data->buf); +		data->buf = xmalloc(size); +		data->buf_size = size; +	} + +	while (size) { +		ssize_t len = read_istream(data->st, data->buf, size); +		if (len == 0) +			die(_("SHA1 COLLISION FOUND WITH %s !"), +			    sha1_to_hex(data->entry->idx.sha1)); +		if (len < 0) +			die(_("unable to read %s"), +			    sha1_to_hex(data->entry->idx.sha1)); +		if (memcmp(buf, data->buf, len)) +			die(_("SHA1 COLLISION FOUND WITH %s !"), +			    sha1_to_hex(data->entry->idx.sha1)); +		size -= len; +		buf += len; +	} +	return 0; +} + +static int check_collison(struct object_entry *entry) +{ +	struct compare_data data; +	enum object_type type; +	unsigned long size; + +	if (entry->size <= big_file_threshold || entry->type != OBJ_BLOB) +		return -1; + +	memset(&data, 0, sizeof(data)); +	data.entry = entry; +	data.st = open_istream(entry->idx.sha1, &type, &size, NULL); +	if (!data.st) +		return -1; +	if (size != entry->size || type != entry->type) +		die(_("SHA1 COLLISION FOUND WITH %s !"), +		    sha1_to_hex(entry->idx.sha1)); +	unpack_data(entry, compare_objects, &data); +	close_istream(data.st); +	free(data.buf); +	return 0; +} + +static void sha1_object(const void *data, struct object_entry *obj_entry, +			unsigned long size, enum object_type type, +			const unsigned char *sha1)  { -	hash_sha1_file(data, size, typename(type), sha1); -	if (has_sha1_file(sha1)) { +	void *new_data = NULL; +	int collision_test_needed; + +	assert(data || obj_entry); + +	read_lock(); +	collision_test_needed = has_sha1_file_with_flags(sha1, HAS_SHA1_QUICK); +	read_unlock(); + +	if (collision_test_needed && !data) { +		read_lock(); +		if (!check_collison(obj_entry)) +			collision_test_needed = 0; +		read_unlock(); +	} +	if (collision_test_needed) {  		void *has_data;  		enum object_type has_type;  		unsigned long has_size; +		read_lock(); +		has_type = sha1_object_info(sha1, &has_size); +		if (has_type != type || has_size != size) +			die(_("SHA1 COLLISION FOUND WITH %s !"), sha1_to_hex(sha1));  		has_data = read_sha1_file(sha1, &has_type, &has_size); +		read_unlock(); +		if (!data) +			data = new_data = get_data_from_pack(obj_entry);  		if (!has_data) -			die("cannot read existing object %s", sha1_to_hex(sha1)); +			die(_("cannot read existing object %s"), sha1_to_hex(sha1));  		if (size != has_size || type != has_type ||  		    memcmp(data, has_data, size) != 0) -			die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1)); +			die(_("SHA1 COLLISION FOUND WITH %s !"), sha1_to_hex(sha1));  		free(has_data);  	} +  	if (strict) { +		read_lock();  		if (type == OBJ_BLOB) {  			struct blob *blob = lookup_blob(sha1);  			if (blob)  				blob->object.flags |= FLAG_CHECKED;  			else -				die("invalid blob object %s", sha1_to_hex(sha1)); +				die(_("invalid blob object %s"), sha1_to_hex(sha1));  		} else {  			struct object *obj;  			int eaten;  			void *buf = (void *) data; +			assert(data && "data can only be NULL for large _blobs_"); +  			/*  			 * we do not need to free the memory here, as the  			 * buf is deleted by the caller.  			 */  			obj = parse_object_buffer(sha1, type, size, buf, &eaten);  			if (!obj) -				die("invalid %s", typename(type)); -			if (fsck_object(obj, 1, fsck_error_function)) -				die("Error in object"); -			if (fsck_walk(obj, mark_link, NULL)) -				die("Not all child objects of %s are reachable", sha1_to_hex(obj->sha1)); +				die(_("invalid %s"), typename(type)); +			if (do_fsck_object && +			    fsck_object(obj, buf, size, &fsck_options)) +				die(_("Error in object")); +			if (fsck_walk(obj, NULL, &fsck_options)) +				die(_("Not all child objects of %s are reachable"), sha1_to_hex(obj->sha1));  			if (obj->type == OBJ_TREE) {  				struct tree *item = (struct tree *) obj;  				item->buffer = NULL; +				obj->parsed = 0;  			}  			if (obj->type == OBJ_COMMIT) {  				struct commit *commit = (struct commit *) obj; -				commit->buffer = NULL; +				if (detach_commit_buffer(commit, NULL) != data) +					die("BUG: parse_object_buffer transmogrified our buffer");  			}  			obj->flags |= FLAG_CHECKED;  		} +		read_unlock();  	} -} -static int is_delta_type(enum object_type type) -{ -	return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA); +	free(new_data);  } +/* + * This function is part of find_unresolved_deltas(). There are two + * walkers going in the opposite ways. + * + * The first one in find_unresolved_deltas() traverses down from + * parent node to children, deflating nodes along the way. However, + * memory for deflated nodes is limited by delta_base_cache_limit, so + * at some point parent node's deflated content may be freed. + * + * The second walker is this function, which goes from current node up + * to top parent if necessary to deflate the node. In normal + * situation, its parent node would be already deflated, so it just + * needs to apply delta. + * + * In the worst case scenario, parent node is no longer deflated because + * we're running out of delta_base_cache_limit; we need to re-deflate + * parents, possibly up to the top base. + * + * All deflated objects here are subject to be freed if we exceed + * delta_base_cache_limit, just like in find_unresolved_deltas(), we + * just need to make sure the last node is not freed. + */  static void *get_base_data(struct base_data *c)  {  	if (!c->data) {  		struct object_entry *obj = c->obj; +		struct base_data **delta = NULL; +		int delta_nr = 0, delta_alloc = 0; -		if (is_delta_type(obj->type)) { -			void *base = get_base_data(c->base); -			void *raw = get_data_from_pack(obj); +		while (is_delta_type(c->obj->type) && !c->data) { +			ALLOC_GROW(delta, delta_nr + 1, delta_alloc); +			delta[delta_nr++] = c; +			c = c->base; +		} +		if (!delta_nr) { +			c->data = get_data_from_pack(obj); +			c->size = obj->size; +			get_thread_data()->base_cache_used += c->size; +			prune_base_data(c); +		} +		for (; delta_nr > 0; delta_nr--) { +			void *base, *raw; +			c = delta[delta_nr - 1]; +			obj = c->obj; +			base = get_base_data(c->base); +			raw = get_data_from_pack(obj);  			c->data = patch_delta(  				base, c->base->size,  				raw, obj->size,  				&c->size);  			free(raw);  			if (!c->data) -				bad_object(obj->idx.offset, "failed to apply delta"); -		} else { -			c->data = get_data_from_pack(obj); -			c->size = obj->size; +				bad_object(obj->idx.offset, _("failed to apply delta")); +			get_thread_data()->base_cache_used += c->size; +			prune_base_data(c);  		} - -		base_cache_used += c->size; -		prune_base_data(c); +		free(delta);  	}  	return c->data;  } @@ -535,11 +928,16 @@ static void resolve_delta(struct object_entry *delta_obj,  {  	void *base_data, *delta_data; -	delta_obj->real_type = base->obj->real_type; -	delta_obj->delta_depth = base->obj->delta_depth + 1; -	if (deepest_delta < delta_obj->delta_depth) -		deepest_delta = delta_obj->delta_depth; -	delta_obj->base_object_no = base->obj - objects; +	if (show_stat) { +		int i = delta_obj - objects; +		int j = base->obj - objects; +		obj_stat[i].delta_depth = obj_stat[j].delta_depth + 1; +		deepest_delta_lock(); +		if (deepest_delta < obj_stat[i].delta_depth) +			deepest_delta = obj_stat[i].delta_depth; +		deepest_delta_unlock(); +		obj_stat[i].base_object_no = j; +	}  	delta_data = get_data_from_pack(delta_obj);  	base_data = get_base_data(base);  	result->obj = delta_obj; @@ -547,104 +945,198 @@ static void resolve_delta(struct object_entry *delta_obj,  				   delta_data, delta_obj->size, &result->size);  	free(delta_data);  	if (!result->data) -		bad_object(delta_obj->idx.offset, "failed to apply delta"); -	sha1_object(result->data, result->size, delta_obj->real_type, +		bad_object(delta_obj->idx.offset, _("failed to apply delta")); +	hash_sha1_file(result->data, result->size, +		       typename(delta_obj->real_type), delta_obj->idx.sha1); +	sha1_object(result->data, NULL, result->size, delta_obj->real_type,  		    delta_obj->idx.sha1); +	counter_lock();  	nr_resolved_deltas++; +	counter_unlock();  } -static void find_unresolved_deltas(struct base_data *base, -				   struct base_data *prev_base) +/* + * Standard boolean compare-and-swap: atomically check whether "*type" is + * "want"; if so, swap in "set" and return true. Otherwise, leave it untouched + * and return false. + */ +static int compare_and_swap_type(signed char *type, +				 enum object_type want, +				 enum object_type set)  { -	int i, ref_first, ref_last, ofs_first, ofs_last; +	enum object_type old; -	/* -	 * This is a recursive function. Those brackets should help reducing -	 * stack usage by limiting the scope of the delta_base union. -	 */ -	{ -		union delta_base base_spec; +	type_cas_lock(); +	old = *type; +	if (old == want) +		*type = set; +	type_cas_unlock(); -		hashcpy(base_spec.sha1, base->obj->idx.sha1); -		find_delta_children(&base_spec, -				    &ref_first, &ref_last, OBJ_REF_DELTA); +	return old == want; +} -		memset(&base_spec, 0, sizeof(base_spec)); -		base_spec.offset = base->obj->idx.offset; -		find_delta_children(&base_spec, -				    &ofs_first, &ofs_last, OBJ_OFS_DELTA); -	} +static struct base_data *find_unresolved_deltas_1(struct base_data *base, +						  struct base_data *prev_base) +{ +	if (base->ref_last == -1 && base->ofs_last == -1) { +		find_ref_delta_children(base->obj->idx.sha1, +					&base->ref_first, &base->ref_last, +					OBJ_REF_DELTA); + +		find_ofs_delta_children(base->obj->idx.offset, +					&base->ofs_first, &base->ofs_last, +					OBJ_OFS_DELTA); + +		if (base->ref_last == -1 && base->ofs_last == -1) { +			free(base->data); +			return NULL; +		} -	if (ref_last == -1 && ofs_last == -1) { -		free(base->data); -		return; +		link_base_data(prev_base, base);  	} -	link_base_data(prev_base, base); +	if (base->ref_first <= base->ref_last) { +		struct object_entry *child = objects + ref_deltas[base->ref_first].obj_no; +		struct base_data *result = alloc_base_data(); -	for (i = ref_first; i <= ref_last; i++) { -		struct object_entry *child = objects + deltas[i].obj_no; -		struct base_data result; +		if (!compare_and_swap_type(&child->real_type, OBJ_REF_DELTA, +					   base->obj->real_type)) +			die("BUG: child->real_type != OBJ_REF_DELTA"); -		assert(child->real_type == OBJ_REF_DELTA); -		resolve_delta(child, base, &result); -		if (i == ref_last && ofs_last == -1) +		resolve_delta(child, base, result); +		if (base->ref_first == base->ref_last && base->ofs_last == -1)  			free_base_data(base); -		find_unresolved_deltas(&result, base); + +		base->ref_first++; +		return result;  	} -	for (i = ofs_first; i <= ofs_last; i++) { -		struct object_entry *child = objects + deltas[i].obj_no; -		struct base_data result; +	if (base->ofs_first <= base->ofs_last) { +		struct object_entry *child = objects + ofs_deltas[base->ofs_first].obj_no; +		struct base_data *result = alloc_base_data();  		assert(child->real_type == OBJ_OFS_DELTA); -		resolve_delta(child, base, &result); -		if (i == ofs_last) +		child->real_type = base->obj->real_type; +		resolve_delta(child, base, result); +		if (base->ofs_first == base->ofs_last)  			free_base_data(base); -		find_unresolved_deltas(&result, base); + +		base->ofs_first++; +		return result;  	}  	unlink_base_data(base); +	return NULL; +} + +static void find_unresolved_deltas(struct base_data *base) +{ +	struct base_data *new_base, *prev_base = NULL; +	for (;;) { +		new_base = find_unresolved_deltas_1(base, prev_base); + +		if (new_base) { +			prev_base = base; +			base = new_base; +		} else { +			free(base); +			base = prev_base; +			if (!base) +				return; +			prev_base = base->base; +		} +	}  } -static int compare_delta_entry(const void *a, const void *b) +static int compare_ofs_delta_entry(const void *a, const void *b)  { -	const struct delta_entry *delta_a = a; -	const struct delta_entry *delta_b = b; +	const struct ofs_delta_entry *delta_a = a; +	const struct ofs_delta_entry *delta_b = b; -	/* group by type (ref vs ofs) and then by value (sha-1 or offset) */ -	return compare_delta_bases(&delta_a->base, &delta_b->base, -				   objects[delta_a->obj_no].type, -				   objects[delta_b->obj_no].type); +	return delta_a->offset < delta_b->offset ? -1 : +	       delta_a->offset > delta_b->offset ?  1 : +	       0;  } -/* Parse all objects and return the pack content SHA1 hash */ +static int compare_ref_delta_entry(const void *a, const void *b) +{ +	const struct ref_delta_entry *delta_a = a; +	const struct ref_delta_entry *delta_b = b; + +	return hashcmp(delta_a->sha1, delta_b->sha1); +} + +static void resolve_base(struct object_entry *obj) +{ +	struct base_data *base_obj = alloc_base_data(); +	base_obj->obj = obj; +	base_obj->data = NULL; +	find_unresolved_deltas(base_obj); +} + +#ifndef NO_PTHREADS +static void *threaded_second_pass(void *data) +{ +	set_thread_data(data); +	for (;;) { +		int i; +		counter_lock(); +		display_progress(progress, nr_resolved_deltas); +		counter_unlock(); +		work_lock(); +		while (nr_dispatched < nr_objects && +		       is_delta_type(objects[nr_dispatched].type)) +			nr_dispatched++; +		if (nr_dispatched >= nr_objects) { +			work_unlock(); +			break; +		} +		i = nr_dispatched++; +		work_unlock(); + +		resolve_base(&objects[i]); +	} +	return NULL; +} +#endif + +/* + * First pass: + * - find locations of all objects; + * - calculate SHA1 of all non-delta objects; + * - remember base (SHA1 or offset) for all deltas. + */  static void parse_pack_objects(unsigned char *sha1)  { -	int i; -	struct delta_entry *delta = deltas; +	int i, nr_delays = 0; +	struct ofs_delta_entry *ofs_delta = ofs_deltas; +	unsigned char ref_delta_sha1[20];  	struct stat st; -	/* -	 * First pass: -	 * - find locations of all objects; -	 * - calculate SHA1 of all non-delta objects; -	 * - remember base (SHA1 or offset) for all deltas. -	 */  	if (verbose)  		progress = start_progress( -				from_stdin ? "Receiving objects" : "Indexing objects", +				from_stdin ? _("Receiving objects") : _("Indexing objects"),  				nr_objects);  	for (i = 0; i < nr_objects; i++) {  		struct object_entry *obj = &objects[i]; -		void *data = unpack_raw_entry(obj, &delta->base); +		void *data = unpack_raw_entry(obj, &ofs_delta->offset, +					      ref_delta_sha1, obj->idx.sha1);  		obj->real_type = obj->type; -		if (is_delta_type(obj->type)) { -			nr_deltas++; -			delta->obj_no = i; -			delta++; +		if (obj->type == OBJ_OFS_DELTA) { +			nr_ofs_deltas++; +			ofs_delta->obj_no = i; +			ofs_delta++; +		} else if (obj->type == OBJ_REF_DELTA) { +			ALLOC_GROW(ref_deltas, nr_ref_deltas + 1, ref_deltas_alloc); +			hashcpy(ref_deltas[nr_ref_deltas].sha1, ref_delta_sha1); +			ref_deltas[nr_ref_deltas].obj_no = i; +			nr_ref_deltas++; +		} else if (!data) { +			/* large blobs, check later */ +			obj->real_type = OBJ_BAD; +			nr_delays++;  		} else -			sha1_object(data, obj->size, obj->type, obj->idx.sha1); +			sha1_object(data, NULL, obj->size, obj->type, obj->idx.sha1);  		free(data);  		display_progress(progress, i+1);  	} @@ -655,53 +1147,135 @@ static void parse_pack_objects(unsigned char *sha1)  	flush();  	git_SHA1_Final(sha1, &input_ctx);  	if (hashcmp(fill(20), sha1)) -		die("pack is corrupted (SHA1 mismatch)"); +		die(_("pack is corrupted (SHA1 mismatch)"));  	use(20);  	/* If input_fd is a file, we should have reached its end now. */  	if (fstat(input_fd, &st)) -		die_errno("cannot fstat packfile"); +		die_errno(_("cannot fstat packfile"));  	if (S_ISREG(st.st_mode) &&  			lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size) -		die("pack has junk at the end"); +		die(_("pack has junk at the end")); + +	for (i = 0; i < nr_objects; i++) { +		struct object_entry *obj = &objects[i]; +		if (obj->real_type != OBJ_BAD) +			continue; +		obj->real_type = obj->type; +		sha1_object(NULL, obj, obj->size, obj->type, obj->idx.sha1); +		nr_delays--; +	} +	if (nr_delays) +		die(_("confusion beyond insanity in parse_pack_objects()")); +} + +/* + * Second pass: + * - for all non-delta objects, look if it is used as a base for + *   deltas; + * - if used as a base, uncompress the object and apply all deltas, + *   recursively checking if the resulting object is used as a base + *   for some more deltas. + */ +static void resolve_deltas(void) +{ +	int i; -	if (!nr_deltas) +	if (!nr_ofs_deltas && !nr_ref_deltas)  		return;  	/* Sort deltas by base SHA1/offset for fast searching */ -	qsort(deltas, nr_deltas, sizeof(struct delta_entry), -	      compare_delta_entry); +	qsort(ofs_deltas, nr_ofs_deltas, sizeof(struct ofs_delta_entry), +	      compare_ofs_delta_entry); +	qsort(ref_deltas, nr_ref_deltas, sizeof(struct ref_delta_entry), +	      compare_ref_delta_entry); -	/* -	 * Second pass: -	 * - for all non-delta objects, look if it is used as a base for -	 *   deltas; -	 * - if used as a base, uncompress the object and apply all deltas, -	 *   recursively checking if the resulting object is used as a base -	 *   for some more deltas. -	 */  	if (verbose) -		progress = start_progress("Resolving deltas", nr_deltas); +		progress = start_progress(_("Resolving deltas"), +					  nr_ref_deltas + nr_ofs_deltas); + +#ifndef NO_PTHREADS +	nr_dispatched = 0; +	if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) { +		init_thread(); +		for (i = 0; i < nr_threads; i++) { +			int ret = pthread_create(&thread_data[i].thread, NULL, +						 threaded_second_pass, thread_data + i); +			if (ret) +				die(_("unable to create thread: %s"), +				    strerror(ret)); +		} +		for (i = 0; i < nr_threads; i++) +			pthread_join(thread_data[i].thread, NULL); +		cleanup_thread(); +		return; +	} +#endif +  	for (i = 0; i < nr_objects; i++) {  		struct object_entry *obj = &objects[i]; -		struct base_data base_obj;  		if (is_delta_type(obj->type))  			continue; -		base_obj.obj = obj; -		base_obj.data = NULL; -		find_unresolved_deltas(&base_obj, NULL); +		resolve_base(obj);  		display_progress(progress, nr_resolved_deltas);  	}  } +/* + * Third pass: + * - append objects to convert thin pack to full pack if required + * - write the final 20-byte SHA-1 + */ +static void fix_unresolved_deltas(struct sha1file *f); +static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_sha1) +{ +	if (nr_ref_deltas + nr_ofs_deltas == nr_resolved_deltas) { +		stop_progress(&progress); +		/* Flush remaining pack final 20-byte SHA1. */ +		flush(); +		return; +	} + +	if (fix_thin_pack) { +		struct sha1file *f; +		unsigned char read_sha1[20], tail_sha1[20]; +		struct strbuf msg = STRBUF_INIT; +		int nr_unresolved = nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas; +		int nr_objects_initial = nr_objects; +		if (nr_unresolved <= 0) +			die(_("confusion beyond insanity")); +		REALLOC_ARRAY(objects, nr_objects + nr_unresolved + 1); +		memset(objects + nr_objects + 1, 0, +		       nr_unresolved * sizeof(*objects)); +		f = sha1fd(output_fd, curr_pack); +		fix_unresolved_deltas(f); +		strbuf_addf(&msg, _("completed with %d local objects"), +			    nr_objects - nr_objects_initial); +		stop_progress_msg(&progress, msg.buf); +		strbuf_release(&msg); +		sha1close(f, tail_sha1, 0); +		hashcpy(read_sha1, pack_sha1); +		fixup_pack_header_footer(output_fd, pack_sha1, +					 curr_pack, nr_objects, +					 read_sha1, consumed_bytes-20); +		if (hashcmp(read_sha1, tail_sha1) != 0) +			die(_("Unexpected tail checksum for %s " +			      "(disk corruption?)"), curr_pack); +	} +	if (nr_ofs_deltas + nr_ref_deltas != nr_resolved_deltas) +		die(Q_("pack has %d unresolved delta", +		       "pack has %d unresolved deltas", +		       nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas), +		    nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas); +} +  static int write_compressed(struct sha1file *f, void *in, unsigned int size)  {  	git_zstream stream;  	int status;  	unsigned char outbuf[4096]; -	memset(&stream, 0, sizeof(stream));  	git_deflate_init(&stream, zlib_compression_level);  	stream.next_in = in;  	stream.avail_in = size; @@ -714,7 +1288,7 @@ static int write_compressed(struct sha1file *f, void *in, unsigned int size)  	} while (status == Z_OK);  	if (status != Z_STREAM_END) -		die("unable to deflate appended object (%d)", status); +		die(_("unable to deflate appended object (%d)"), status);  	size = stream.total_out;  	git_deflate_end(&stream);  	return size; @@ -752,15 +1326,15 @@ static struct object_entry *append_obj_to_pack(struct sha1file *f,  static int delta_pos_compare(const void *_a, const void *_b)  { -	struct delta_entry *a = *(struct delta_entry **)_a; -	struct delta_entry *b = *(struct delta_entry **)_b; +	struct ref_delta_entry *a = *(struct ref_delta_entry **)_a; +	struct ref_delta_entry *b = *(struct ref_delta_entry **)_b;  	return a->obj_no - b->obj_no;  } -static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved) +static void fix_unresolved_deltas(struct sha1file *f)  { -	struct delta_entry **sorted_by_pos; -	int i, n = 0; +	struct ref_delta_entry **sorted_by_pos; +	int i;  	/*  	 * Since many unresolved deltas may well be themselves base objects @@ -772,31 +1346,28 @@ static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved)  	 * before deltas depending on them, a good heuristic is to start  	 * resolving deltas in the same order as their position in the pack.  	 */ -	sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos)); -	for (i = 0; i < nr_deltas; i++) { -		if (objects[deltas[i].obj_no].real_type != OBJ_REF_DELTA) -			continue; -		sorted_by_pos[n++] = &deltas[i]; -	} -	qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare); +	sorted_by_pos = xmalloc(nr_ref_deltas * sizeof(*sorted_by_pos)); +	for (i = 0; i < nr_ref_deltas; i++) +		sorted_by_pos[i] = &ref_deltas[i]; +	qsort(sorted_by_pos, nr_ref_deltas, sizeof(*sorted_by_pos), delta_pos_compare); -	for (i = 0; i < n; i++) { -		struct delta_entry *d = sorted_by_pos[i]; +	for (i = 0; i < nr_ref_deltas; i++) { +		struct ref_delta_entry *d = sorted_by_pos[i];  		enum object_type type; -		struct base_data base_obj; +		struct base_data *base_obj = alloc_base_data();  		if (objects[d->obj_no].real_type != OBJ_REF_DELTA)  			continue; -		base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size); -		if (!base_obj.data) +		base_obj->data = read_sha1_file(d->sha1, &type, &base_obj->size); +		if (!base_obj->data)  			continue; -		if (check_sha1_signature(d->base.sha1, base_obj.data, -				base_obj.size, typename(type))) -			die("local object %s is corrupt", sha1_to_hex(d->base.sha1)); -		base_obj.obj = append_obj_to_pack(f, d->base.sha1, -					base_obj.data, base_obj.size, type); -		find_unresolved_deltas(&base_obj, NULL); +		if (check_sha1_signature(d->sha1, base_obj->data, +				base_obj->size, typename(type))) +			die(_("local object %s is corrupt"), sha1_to_hex(d->sha1)); +		base_obj->obj = append_obj_to_pack(f, d->sha1, +					base_obj->data, base_obj->size, type); +		find_unresolved_deltas(base_obj);  		display_progress(progress, nr_resolved_deltas);  	}  	free(sorted_by_pos); @@ -817,7 +1388,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,  		fsync_or_die(output_fd, curr_pack_name);  		err = close(output_fd);  		if (err) -			die_errno("error while closing pack file"); +			die_errno(_("error while closing pack file"));  	}  	if (keep_msg) { @@ -830,16 +1401,16 @@ static void final(const char *final_pack_name, const char *curr_pack_name,  		if (keep_fd < 0) {  			if (errno != EEXIST) -				die_errno("cannot write keep file '%s'", -					  keep_name); +				die_errno(_("cannot write keep file '%s'"), +					  keep_name ? keep_name : name);  		} else {  			if (keep_msg_len > 0) {  				write_or_die(keep_fd, keep_msg, keep_msg_len);  				write_or_die(keep_fd, "\n", 1);  			}  			if (close(keep_fd) != 0) -				die_errno("cannot close written keep file '%s'", -				    keep_name); +				die_errno(_("cannot close written keep file '%s'"), +					  keep_name ? keep_name : name);  			report = "keep";  		}  	} @@ -850,8 +1421,8 @@ static void final(const char *final_pack_name, const char *curr_pack_name,  				 get_object_directory(), sha1_to_hex(sha1));  			final_pack_name = name;  		} -		if (move_temp_to_file(curr_pack_name, final_pack_name)) -			die("cannot store pack file"); +		if (finalize_object_file(curr_pack_name, final_pack_name)) +			die(_("cannot store pack file"));  	} else if (from_stdin)  		chmod(final_pack_name, 0444); @@ -861,8 +1432,8 @@ static void final(const char *final_pack_name, const char *curr_pack_name,  				 get_object_directory(), sha1_to_hex(sha1));  			final_index_name = name;  		} -		if (move_temp_to_file(curr_index_name, final_index_name)) -			die("cannot store index file"); +		if (finalize_object_file(curr_index_name, final_index_name)) +			die(_("cannot store index file"));  	} else  		chmod(final_index_name, 0444); @@ -895,7 +1466,19 @@ static int git_index_pack_config(const char *k, const char *v, void *cb)  	if (!strcmp(k, "pack.indexversion")) {  		opts->version = git_config_int(k, v);  		if (opts->version > 2) -			die("bad pack.indexversion=%"PRIu32, opts->version); +			die(_("bad pack.indexversion=%"PRIu32), opts->version); +		return 0; +	} +	if (!strcmp(k, "pack.threads")) { +		nr_threads = git_config_int(k, v); +		if (nr_threads < 0) +			die(_("invalid number of threads specified (%d)"), +			    nr_threads); +#ifdef NO_PTHREADS +		if (nr_threads != 1) +			warning(_("no threads support, ignoring %s"), k); +		nr_threads = 1; +#endif  		return 0;  	}  	return git_default_config(k, v, cb); @@ -951,9 +1534,9 @@ static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)  	struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);  	if (!p) -		die("Cannot open existing pack file '%s'", pack_name); +		die(_("Cannot open existing pack file '%s'"), pack_name);  	if (open_pack_index(p)) -		die("Cannot open existing pack idx file for '%s'", pack_name); +		die(_("Cannot open existing pack idx file for '%s'"), pack_name);  	/* Read the attributes from the existing idx file */  	opts->version = p->index_version; @@ -974,7 +1557,7 @@ static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)  static void show_pack_info(int stat_only)  { -	int i, baseobjects = nr_objects - nr_deltas; +	int i, baseobjects = nr_objects - nr_ref_deltas - nr_ofs_deltas;  	unsigned long *chain_histogram = NULL;  	if (deepest_delta) @@ -984,7 +1567,7 @@ static void show_pack_info(int stat_only)  		struct object_entry *obj = &objects[i];  		if (is_delta_type(obj->type)) -			chain_histogram[obj->delta_depth - 1]++; +			chain_histogram[obj_stat[i].delta_depth - 1]++;  		if (stat_only)  			continue;  		printf("%s %-6s %lu %lu %"PRIuMAX, @@ -993,45 +1576,51 @@ static void show_pack_info(int stat_only)  		       (unsigned long)(obj[1].idx.offset - obj->idx.offset),  		       (uintmax_t)obj->idx.offset);  		if (is_delta_type(obj->type)) { -			struct object_entry *bobj = &objects[obj->base_object_no]; -			printf(" %u %s", obj->delta_depth, sha1_to_hex(bobj->idx.sha1)); +			struct object_entry *bobj = &objects[obj_stat[i].base_object_no]; +			printf(" %u %s", obj_stat[i].delta_depth, sha1_to_hex(bobj->idx.sha1));  		}  		putchar('\n');  	}  	if (baseobjects) -		printf("non delta: %d object%s\n", -		       baseobjects, baseobjects > 1 ? "s" : ""); +		printf_ln(Q_("non delta: %d object", +			     "non delta: %d objects", +			     baseobjects), +			  baseobjects);  	for (i = 0; i < deepest_delta; i++) {  		if (!chain_histogram[i])  			continue; -		printf("chain length = %d: %lu object%s\n", -		       i + 1, -		       chain_histogram[i], -		       chain_histogram[i] > 1 ? "s" : ""); +		printf_ln(Q_("chain length = %d: %lu object", +			     "chain length = %d: %lu objects", +			     chain_histogram[i]), +			  i + 1, +			  chain_histogram[i]);  	}  }  int cmd_index_pack(int argc, const char **argv, const char *prefix)  { -	int i, fix_thin_pack = 0, verify = 0, stat_only = 0, stat = 0; -	const char *curr_pack, *curr_index; +	int i, fix_thin_pack = 0, verify = 0, stat_only = 0; +	const char *curr_index;  	const char *index_name = NULL, *pack_name = NULL;  	const char *keep_name = NULL, *keep_msg = NULL; -	char *index_name_buf = NULL, *keep_name_buf = NULL; +	struct strbuf index_name_buf = STRBUF_INIT, +		      keep_name_buf = STRBUF_INIT;  	struct pack_idx_entry **idx_objects;  	struct pack_idx_option opts;  	unsigned char pack_sha1[20]; +	unsigned foreign_nr = 1;	/* zero is a "good" value, assume bad */  	if (argc == 2 && !strcmp(argv[1], "-h"))  		usage(index_pack_usage); -	read_replace_refs = 0; +	check_replace_refs = 0; +	fsck_options.walk = mark_link;  	reset_pack_idx_option(&opts);  	git_config(git_index_pack_config, &opts);  	if (prefix && chdir(prefix)) -		die("Cannot come back to cwd"); +		die(_("Cannot come back to cwd"));  	for (i = 1; i < argc; i++) {  		const char *arg = argv[i]; @@ -1043,20 +1632,39 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)  				fix_thin_pack = 1;  			} else if (!strcmp(arg, "--strict")) {  				strict = 1; +				do_fsck_object = 1; +			} else if (skip_prefix(arg, "--strict=", &arg)) { +				strict = 1; +				do_fsck_object = 1; +				fsck_set_msg_types(&fsck_options, arg); +			} else if (!strcmp(arg, "--check-self-contained-and-connected")) { +				strict = 1; +				check_self_contained_and_connected = 1;  			} else if (!strcmp(arg, "--verify")) {  				verify = 1;  			} else if (!strcmp(arg, "--verify-stat")) {  				verify = 1; -				stat = 1; +				show_stat = 1;  			} else if (!strcmp(arg, "--verify-stat-only")) {  				verify = 1; -				stat = 1; +				show_stat = 1;  				stat_only = 1;  			} else if (!strcmp(arg, "--keep")) {  				keep_msg = ""; -			} else if (!prefixcmp(arg, "--keep=")) { +			} else if (starts_with(arg, "--keep=")) {  				keep_msg = arg + 7; -			} else if (!prefixcmp(arg, "--pack_header=")) { +			} else if (starts_with(arg, "--threads=")) { +				char *end; +				nr_threads = strtoul(arg+10, &end, 0); +				if (!arg[10] || *end || nr_threads < 0) +					usage(index_pack_usage); +#ifdef NO_PTHREADS +				if (nr_threads != 1) +					warning(_("no threads support, " +						  "ignoring %s"), arg); +				nr_threads = 1; +#endif +			} else if (starts_with(arg, "--pack_header=")) {  				struct pack_header *hdr;  				char *c; @@ -1064,10 +1672,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)  				hdr->hdr_signature = htonl(PACK_SIGNATURE);  				hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));  				if (*c != ',') -					die("bad %s", arg); +					die(_("bad %s"), arg);  				hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));  				if (*c) -					die("bad %s", arg); +					die(_("bad %s"), arg);  				input_len = sizeof(*hdr);  			} else if (!strcmp(arg, "-v")) {  				verbose = 1; @@ -1075,15 +1683,15 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)  				if (index_name || (i+1) >= argc)  					usage(index_pack_usage);  				index_name = argv[++i]; -			} else if (!prefixcmp(arg, "--index-version=")) { +			} else if (starts_with(arg, "--index-version=")) {  				char *c;  				opts.version = strtoul(arg + 16, &c, 10);  				if (opts.version > 2) -					die("bad %s", arg); +					die(_("bad %s"), arg);  				if (*c == ',')  					opts.off32_limit = strtoul(c+1, &c, 0);  				if (*c || opts.off32_limit & 0x80000000) -					die("bad %s", arg); +					die(_("bad %s"), arg);  			} else  				usage(index_pack_usage);  			continue; @@ -1097,80 +1705,58 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)  	if (!pack_name && !from_stdin)  		usage(index_pack_usage);  	if (fix_thin_pack && !from_stdin) -		die("--fix-thin cannot be used without --stdin"); +		die(_("--fix-thin cannot be used without --stdin"));  	if (!index_name && pack_name) { -		int len = strlen(pack_name); -		if (!has_extension(pack_name, ".pack")) -			die("packfile name '%s' does not end with '.pack'", +		size_t len; +		if (!strip_suffix(pack_name, ".pack", &len)) +			die(_("packfile name '%s' does not end with '.pack'"),  			    pack_name); -		index_name_buf = xmalloc(len); -		memcpy(index_name_buf, pack_name, len - 5); -		strcpy(index_name_buf + len - 5, ".idx"); -		index_name = index_name_buf; +		strbuf_add(&index_name_buf, pack_name, len); +		strbuf_addstr(&index_name_buf, ".idx"); +		index_name = index_name_buf.buf;  	}  	if (keep_msg && !keep_name && pack_name) { -		int len = strlen(pack_name); -		if (!has_extension(pack_name, ".pack")) -			die("packfile name '%s' does not end with '.pack'", +		size_t len; +		if (!strip_suffix(pack_name, ".pack", &len)) +			die(_("packfile name '%s' does not end with '.pack'"),  			    pack_name); -		keep_name_buf = xmalloc(len); -		memcpy(keep_name_buf, pack_name, len - 5); -		strcpy(keep_name_buf + len - 5, ".keep"); -		keep_name = keep_name_buf; +		strbuf_add(&keep_name_buf, pack_name, len); +		strbuf_addstr(&keep_name_buf, ".idx"); +		keep_name = keep_name_buf.buf;  	}  	if (verify) {  		if (!index_name) -			die("--verify with no packfile name given"); +			die(_("--verify with no packfile name given"));  		read_idx_option(&opts, index_name);  		opts.flags |= WRITE_IDX_VERIFY | WRITE_IDX_STRICT;  	}  	if (strict)  		opts.flags |= WRITE_IDX_STRICT; +#ifndef NO_PTHREADS +	if (!nr_threads) { +		nr_threads = online_cpus(); +		/* An experiment showed that more threads does not mean faster */ +		if (nr_threads > 3) +			nr_threads = 3; +	} +#endif +  	curr_pack = open_pack_file(pack_name);  	parse_pack_header();  	objects = xcalloc(nr_objects + 1, sizeof(struct object_entry)); -	deltas = xcalloc(nr_objects, sizeof(struct delta_entry)); +	if (show_stat) +		obj_stat = xcalloc(nr_objects + 1, sizeof(struct object_stat)); +	ofs_deltas = xcalloc(nr_objects, sizeof(struct ofs_delta_entry));  	parse_pack_objects(pack_sha1); -	if (nr_deltas == nr_resolved_deltas) { -		stop_progress(&progress); -		/* Flush remaining pack final 20-byte SHA1. */ -		flush(); -	} else { -		if (fix_thin_pack) { -			struct sha1file *f; -			unsigned char read_sha1[20], tail_sha1[20]; -			char msg[48]; -			int nr_unresolved = nr_deltas - nr_resolved_deltas; -			int nr_objects_initial = nr_objects; -			if (nr_unresolved <= 0) -				die("confusion beyond insanity"); -			objects = xrealloc(objects, -					   (nr_objects + nr_unresolved + 1) -					   * sizeof(*objects)); -			f = sha1fd(output_fd, curr_pack); -			fix_unresolved_deltas(f, nr_unresolved); -			sprintf(msg, "completed with %d local objects", -				nr_objects - nr_objects_initial); -			stop_progress_msg(&progress, msg); -			sha1close(f, tail_sha1, 0); -			hashcpy(read_sha1, pack_sha1); -			fixup_pack_header_footer(output_fd, pack_sha1, -						 curr_pack, nr_objects, -						 read_sha1, consumed_bytes-20); -			if (hashcmp(read_sha1, tail_sha1) != 0) -				die("Unexpected tail checksum for %s " -				    "(disk corruption?)", curr_pack); -		} -		if (nr_deltas != nr_resolved_deltas) -			die("pack has %d unresolved deltas", -			    nr_deltas - nr_resolved_deltas); -	} -	free(deltas); +	resolve_deltas(); +	conclude_pack(fix_thin_pack, curr_pack, pack_sha1); +	free(ofs_deltas); +	free(ref_deltas);  	if (strict) -		check_objects(); +		foreign_nr = check_objects(); -	if (stat) +	if (show_stat)  		show_pack_info(stat_only);  	idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *)); @@ -1187,12 +1773,18 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)  	else  		close(input_fd);  	free(objects); -	free(index_name_buf); -	free(keep_name_buf); +	strbuf_release(&index_name_buf); +	strbuf_release(&keep_name_buf);  	if (pack_name == NULL)  		free((void *) curr_pack);  	if (index_name == NULL)  		free((void *) curr_index); +	/* +	 * Let the caller know this pack is not self contained +	 */ +	if (check_self_contained_and_connected && foreign_nr) +		return 1; +  	return 0;  } | 
