[thirdparty/git.git] / split-index.c

#include "cache.h"
#include "split-index.h"
#include "ewah/ewok.h"

struct split_index *init_split_index(struct index_state *istate)
{
	if (!istate->split_index) {
		istate->split_index = xcalloc(1, sizeof(*istate->split_index));
		istate->split_index->refcount = 1;
	}
	return istate->split_index;
}

int read_link_extension(struct index_state *istate,
			 const void *data_, unsigned long sz)
{
	const unsigned char *data = data_;
	struct split_index *si;
	int ret;

	if (sz < 20)
		return error("corrupt link extension (too short)");
	si = init_split_index(istate);
	hashcpy(si->base_sha1, data);
	data += 20;
	sz -= 20;
	if (!sz)
		return 0;
	si->delete_bitmap = ewah_new();
	ret = ewah_read_mmap(si->delete_bitmap, data, sz);
	if (ret < 0)
		return error("corrupt delete bitmap in link extension");
	data += ret;
	sz -= ret;
	si->replace_bitmap = ewah_new();
	ret = ewah_read_mmap(si->replace_bitmap, data, sz);
	if (ret < 0)
		return error("corrupt replace bitmap in link extension");
	if (ret != sz)
		return error("garbage at the end of link extension");
	return 0;
}

int write_link_extension(struct strbuf *sb,
			 struct index_state *istate)
{
	struct split_index *si = istate->split_index;
	strbuf_add(sb, si->base_sha1, 20);
	if (!si->delete_bitmap && !si->replace_bitmap)
		return 0;
	ewah_serialize_strbuf(si->delete_bitmap, sb);
	ewah_serialize_strbuf(si->replace_bitmap, sb);
	return 0;
}

static void mark_base_index_entries(struct index_state *base)
{
	int i;
	/*
	 * To keep track of the shared entries between
	 * istate->base->cache[] and istate->cache[], base entry
	 * position is stored in each base entry. All positions start
	 * from 1 instead of 0, which is reserved to say "this is a new
	 * entry".
	 */
	for (i = 0; i < base->cache_nr; i++)
		base->cache[i]->index = i + 1;
}

void move_cache_to_base_index(struct index_state *istate)
{
	struct split_index *si = istate->split_index;
	int i;

	/*
	 * do not delete old si->base, its index entries may be shared
	 * with istate->cache[]. Accept a bit of leaking here because
	 * this code is only used by short-lived update-index.
	 */
	si->base = xcalloc(1, sizeof(*si->base));
	si->base->version = istate->version;
	/* zero timestamp disables racy test in ce_write_index() */
	si->base->timestamp = istate->timestamp;
	ALLOC_GROW(si->base->cache, istate->cache_nr, si->base->cache_alloc);
	si->base->cache_nr = istate->cache_nr;
	memcpy(si->base->cache, istate->cache,
	       sizeof(*istate->cache) * istate->cache_nr);
	mark_base_index_entries(si->base);
	for (i = 0; i < si->base->cache_nr; i++)
		si->base->cache[i]->ce_flags &= ~CE_UPDATE_IN_BASE;
}

static void mark_entry_for_delete(size_t pos, void *data)
{
	struct index_state *istate = data;
	if (pos >= istate->cache_nr)
		die("position for delete %d exceeds base index size %d",
		    (int)pos, istate->cache_nr);
	istate->cache[pos]->ce_flags |= CE_REMOVE;
	istate->split_index->nr_deletions = 1;
}

static void replace_entry(size_t pos, void *data)
{
	struct index_state *istate = data;
	struct split_index *si = istate->split_index;
	struct cache_entry *dst, *src;

	if (pos >= istate->cache_nr)
		die("position for replacement %d exceeds base index size %d",
		    (int)pos, istate->cache_nr);
	if (si->nr_replacements >= si->saved_cache_nr)
		die("too many replacements (%d vs %d)",
		    si->nr_replacements, si->saved_cache_nr);
	dst = istate->cache[pos];
	if (dst->ce_flags & CE_REMOVE)
		die("entry %d is marked as both replaced and deleted",
		    (int)pos);
	src = si->saved_cache[si->nr_replacements];
	if (ce_namelen(src))
		die("corrupt link extension, entry %d should have "
		    "zero length name", (int)pos);
	src->index = pos + 1;
	src->ce_flags |= CE_UPDATE_IN_BASE;
	src->ce_namelen = dst->ce_namelen;
	copy_cache_entry(dst, src);
	free(src);
	si->nr_replacements++;
}

void merge_base_index(struct index_state *istate)
{
	struct split_index *si = istate->split_index;
	unsigned int i;

	mark_base_index_entries(si->base);

	si->saved_cache	    = istate->cache;
	si->saved_cache_nr  = istate->cache_nr;
	istate->cache_nr    = si->base->cache_nr;
	istate->cache	    = NULL;
	istate->cache_alloc = 0;
	ALLOC_GROW(istate->cache, istate->cache_nr, istate->cache_alloc);
	memcpy(istate->cache, si->base->cache,
	       sizeof(*istate->cache) * istate->cache_nr);

	si->nr_deletions = 0;
	si->nr_replacements = 0;
	ewah_each_bit(si->replace_bitmap, replace_entry, istate);
	ewah_each_bit(si->delete_bitmap, mark_entry_for_delete, istate);
	if (si->nr_deletions)
		remove_marked_cache_entries(istate);

	for (i = si->nr_replacements; i < si->saved_cache_nr; i++) {
		if (!ce_namelen(si->saved_cache[i]))
			die("corrupt link extension, entry %d should "
			    "have non-zero length name", i);
		add_index_entry(istate, si->saved_cache[i],
				ADD_CACHE_OK_TO_ADD |
				ADD_CACHE_KEEP_CACHE_TREE |
				/*
				 * we may have to replay what
				 * merge-recursive.c:update_stages()
				 * does, which has this flag on
				 */
				ADD_CACHE_SKIP_DFCHECK);
		si->saved_cache[i] = NULL;
	}

	ewah_free(si->delete_bitmap);
	ewah_free(si->replace_bitmap);
	free(si->saved_cache);
	si->delete_bitmap  = NULL;
	si->replace_bitmap = NULL;
	si->saved_cache	   = NULL;
	si->saved_cache_nr = 0;
}

void prepare_to_write_split_index(struct index_state *istate)
{
	struct split_index *si = init_split_index(istate);
	struct cache_entry **entries = NULL, *ce;
	int i, nr_entries = 0, nr_alloc = 0;

	si->delete_bitmap = ewah_new();
	si->replace_bitmap = ewah_new();

	if (si->base) {
		/* Go through istate->cache[] and mark CE_MATCHED to
		 * entry with positive index. We'll go through
		 * base->cache[] later to delete all entries in base
		 * that are not marked eith either CE_MATCHED or
		 * CE_UPDATE_IN_BASE. If istate->cache[i] is a
		 * duplicate, deduplicate it.
		 */
		for (i = 0; i < istate->cache_nr; i++) {
			struct cache_entry *base;
			/* namelen is checked separately */
			const unsigned int ondisk_flags =
				CE_STAGEMASK | CE_VALID | CE_EXTENDED_FLAGS;
			unsigned int ce_flags, base_flags, ret;
			ce = istate->cache[i];
			if (!ce->index)
				continue;
			if (ce->index > si->base->cache_nr) {
				ce->index = 0;
				continue;
			}
			ce->ce_flags |= CE_MATCHED; /* or "shared" */
			base = si->base->cache[ce->index - 1];
			if (ce == base)
				continue;
			if (ce->ce_namelen != base->ce_namelen ||
			    strcmp(ce->name, base->name)) {
				ce->index = 0;
				continue;
			}
			ce_flags = ce->ce_flags;
			base_flags = base->ce_flags;
			/* only on-disk flags matter */
			ce->ce_flags   &= ondisk_flags;
			base->ce_flags &= ondisk_flags;
			ret = memcmp(&ce->ce_stat_data, &base->ce_stat_data,
				     offsetof(struct cache_entry, name) -
				     offsetof(struct cache_entry, ce_stat_data));
			ce->ce_flags = ce_flags;
			base->ce_flags = base_flags;
			if (ret)
				ce->ce_flags |= CE_UPDATE_IN_BASE;
			free(base);
			si->base->cache[ce->index - 1] = ce;
		}
		for (i = 0; i < si->base->cache_nr; i++) {
			ce = si->base->cache[i];
			if ((ce->ce_flags & CE_REMOVE) ||
			    !(ce->ce_flags & CE_MATCHED))
				ewah_set(si->delete_bitmap, i);
			else if (ce->ce_flags & CE_UPDATE_IN_BASE) {
				ewah_set(si->replace_bitmap, i);
				ce->ce_flags |= CE_STRIP_NAME;
				ALLOC_GROW(entries, nr_entries+1, nr_alloc);
				entries[nr_entries++] = ce;
			}
		}
	}

	for (i = 0; i < istate->cache_nr; i++) {
		ce = istate->cache[i];
		if ((!si->base || !ce->index) && !(ce->ce_flags & CE_REMOVE)) {
			assert(!(ce->ce_flags & CE_STRIP_NAME));
			ALLOC_GROW(entries, nr_entries+1, nr_alloc);
			entries[nr_entries++] = ce;
		}
		ce->ce_flags &= ~CE_MATCHED;
	}

	/*
	 * take cache[] out temporarily, put entries[] in its place
	 * for writing
	 */
	si->saved_cache = istate->cache;
	si->saved_cache_nr = istate->cache_nr;
	istate->cache = entries;
	istate->cache_nr = nr_entries;
}

void finish_writing_split_index(struct index_state *istate)
{
	struct split_index *si = init_split_index(istate);

	ewah_free(si->delete_bitmap);
	ewah_free(si->replace_bitmap);
	si->delete_bitmap = NULL;
	si->replace_bitmap = NULL;
	free(istate->cache);
	istate->cache = si->saved_cache;
	istate->cache_nr = si->saved_cache_nr;
}

void discard_split_index(struct index_state *istate)
{
	struct split_index *si = istate->split_index;
	if (!si)
		return;
	istate->split_index = NULL;
	si->refcount--;
	if (si->refcount)
		return;
	if (si->base) {
		discard_index(si->base);
		free(si->base);
	}
	free(si);
}

void save_or_free_index_entry(struct index_state *istate, struct cache_entry *ce)
{
	if (ce->index &&
	    istate->split_index &&
	    istate->split_index->base &&
	    ce->index <= istate->split_index->base->cache_nr &&
	    ce == istate->split_index->base->cache[ce->index - 1])
		ce->ce_flags |= CE_REMOVE;
	else
		free(ce);
}

void replace_index_entry_in_base(struct index_state *istate,
				 struct cache_entry *old,
				 struct cache_entry *new)
{
	if (old->index &&
	    istate->split_index &&
	    istate->split_index->base &&
	    old->index <= istate->split_index->base->cache_nr) {
		new->index = old->index;
		if (old != istate->split_index->base->cache[new->index - 1])
			free(istate->split_index->base->cache[new->index - 1]);
		istate->split_index->base->cache[new->index - 1] = new;
	}
}
Commit	Line	Data
5fc2fc8f NTND	1	#include "cache.h"
5fc2fc8f NTND	2	#include "split-index.h"
96a1d8d3	3	#include "ewah/ewok.h"
5fc2fc8f NTND	4
	5	struct split_index init_split_index(struct index_state istate)
	6	{
	7	if (!istate->split_index) {
	8	istate->split_index = xcalloc(1, sizeof(*istate->split_index));
	9	istate->split_index->refcount = 1;
	10	}
	11	return istate->split_index;
	12	}
	13
	14	int read_link_extension(struct index_state *istate,
	15	const void *data_, unsigned long sz)
	16	{
	17	const unsigned char *data = data_;
	18	struct split_index *si;
76b07b37 NTND	19	int ret;
76b07b37 NTND	20
5fc2fc8f NTND	21	if (sz < 20)
	22	return error("corrupt link extension (too short)");
	23	si = init_split_index(istate);
	24	hashcpy(si->base_sha1, data);
	25	data += 20;
	26	sz -= 20;
76b07b37 NTND	27	if (!sz)
	28	return 0;
	29	si->delete_bitmap = ewah_new();
	30	ret = ewah_read_mmap(si->delete_bitmap, data, sz);
	31	if (ret < 0)
	32	return error("corrupt delete bitmap in link extension");
	33	data += ret;
	34	sz -= ret;
	35	si->replace_bitmap = ewah_new();
	36	ret = ewah_read_mmap(si->replace_bitmap, data, sz);
	37	if (ret < 0)
	38	return error("corrupt replace bitmap in link extension");
	39	if (ret != sz)
5fc2fc8f NTND	40	return error("garbage at the end of link extension");
	41	return 0;
	42	}
	43
	44	int write_link_extension(struct strbuf *sb,
	45	struct index_state *istate)
	46	{
	47	struct split_index *si = istate->split_index;
	48	strbuf_add(sb, si->base_sha1, 20);
96a1d8d3 NTND	49	if (!si->delete_bitmap && !si->replace_bitmap)
96a1d8d3 NTND	50	return 0;
be0d9d53 NTND	51	ewah_serialize_strbuf(si->delete_bitmap, sb);
be0d9d53 NTND	52	ewah_serialize_strbuf(si->replace_bitmap, sb);
5fc2fc8f NTND	53	return 0;
	54	}
	55
	56	static void mark_base_index_entries(struct index_state *base)
	57	{
	58	int i;
	59	/*
	60	* To keep track of the shared entries between
	61	* istate->base->cache[] and istate->cache[], base entry
	62	* position is stored in each base entry. All positions start
832c0e5e	63	* from 1 instead of 0, which is reserved to say "this is a new
5fc2fc8f NTND	64	* entry".
	65	*/
	66	for (i = 0; i < base->cache_nr; i++)
	67	base->cache[i]->index = i + 1;
	68	}
	69
c18b80a0 NTND	70	void move_cache_to_base_index(struct index_state *istate)
	71	{
	72	struct split_index *si = istate->split_index;
	73	int i;
	74
	75	/*
	76	* do not delete old si->base, its index entries may be shared
	77	* with istate->cache[]. Accept a bit of leaking here because
	78	* this code is only used by short-lived update-index.
	79	*/
	80	si->base = xcalloc(1, sizeof(*si->base));
	81	si->base->version = istate->version;
	82	/* zero timestamp disables racy test in ce_write_index() */
	83	si->base->timestamp = istate->timestamp;
	84	ALLOC_GROW(si->base->cache, istate->cache_nr, si->base->cache_alloc);
	85	si->base->cache_nr = istate->cache_nr;
	86	memcpy(si->base->cache, istate->cache,
	87	sizeof(istate->cache) istate->cache_nr);
	88	mark_base_index_entries(si->base);
	89	for (i = 0; i < si->base->cache_nr; i++)
	90	si->base->cache[i]->ce_flags &= ~CE_UPDATE_IN_BASE;
	91	}
	92
76b07b37 NTND	93	static void mark_entry_for_delete(size_t pos, void *data)
	94	{
	95	struct index_state *istate = data;
	96	if (pos >= istate->cache_nr)
	97	die("position for delete %d exceeds base index size %d",
	98	(int)pos, istate->cache_nr);
	99	istate->cache[pos]->ce_flags \|= CE_REMOVE;
	100	istate->split_index->nr_deletions = 1;
	101	}
	102
	103	static void replace_entry(size_t pos, void *data)
	104	{
	105	struct index_state *istate = data;
	106	struct split_index *si = istate->split_index;
	107	struct cache_entry dst, src;
b3c96fb1	108
76b07b37 NTND	109	if (pos >= istate->cache_nr)
	110	die("position for replacement %d exceeds base index size %d",
	111	(int)pos, istate->cache_nr);
	112	if (si->nr_replacements >= si->saved_cache_nr)
	113	die("too many replacements (%d vs %d)",
	114	si->nr_replacements, si->saved_cache_nr);
	115	dst = istate->cache[pos];
	116	if (dst->ce_flags & CE_REMOVE)
	117	die("entry %d is marked as both replaced and deleted",
	118	(int)pos);
	119	src = si->saved_cache[si->nr_replacements];
b3c96fb1 NTND	120	if (ce_namelen(src))
	121	die("corrupt link extension, entry %d should have "
	122	"zero length name", (int)pos);
76b07b37 NTND	123	src->index = pos + 1;
76b07b37 NTND	124	src->ce_flags \|= CE_UPDATE_IN_BASE;
b3c96fb1 NTND	125	src->ce_namelen = dst->ce_namelen;
	126	copy_cache_entry(dst, src);
	127	free(src);
76b07b37 NTND	128	si->nr_replacements++;
	129	}
	130
5fc2fc8f NTND	131	void merge_base_index(struct index_state *istate)
	132	{
	133	struct split_index *si = istate->split_index;
76b07b37	134	unsigned int i;
5fc2fc8f NTND	135
5fc2fc8f NTND	136	mark_base_index_entries(si->base);
76b07b37 NTND	137
	138	si->saved_cache = istate->cache;
	139	si->saved_cache_nr = istate->cache_nr;
	140	istate->cache_nr = si->base->cache_nr;
	141	istate->cache = NULL;
	142	istate->cache_alloc = 0;
5fc2fc8f NTND	143	ALLOC_GROW(istate->cache, istate->cache_nr, istate->cache_alloc);
	144	memcpy(istate->cache, si->base->cache,
	145	sizeof(istate->cache) istate->cache_nr);
76b07b37 NTND	146
	147	si->nr_deletions = 0;
	148	si->nr_replacements = 0;
	149	ewah_each_bit(si->replace_bitmap, replace_entry, istate);
	150	ewah_each_bit(si->delete_bitmap, mark_entry_for_delete, istate);
	151	if (si->nr_deletions)
	152	remove_marked_cache_entries(istate);
	153
	154	for (i = si->nr_replacements; i < si->saved_cache_nr; i++) {
b3c96fb1 NTND	155	if (!ce_namelen(si->saved_cache[i]))
	156	die("corrupt link extension, entry %d should "
	157	"have non-zero length name", i);
76b07b37 NTND	158	add_index_entry(istate, si->saved_cache[i],
76b07b37 NTND	159	ADD_CACHE_OK_TO_ADD \|
ce7c614b	160	ADD_CACHE_KEEP_CACHE_TREE \|
76b07b37 NTND	161	/*
	162	* we may have to replay what
	163	* merge-recursive.c:update_stages()
	164	* does, which has this flag on
	165	*/
	166	ADD_CACHE_SKIP_DFCHECK);
	167	si->saved_cache[i] = NULL;
	168	}
	169
	170	ewah_free(si->delete_bitmap);
	171	ewah_free(si->replace_bitmap);
	172	free(si->saved_cache);
	173	si->delete_bitmap = NULL;
	174	si->replace_bitmap = NULL;
	175	si->saved_cache = NULL;
	176	si->saved_cache_nr = 0;
5fc2fc8f NTND	177	}
	178
	179	void prepare_to_write_split_index(struct index_state *istate)
	180	{
	181	struct split_index *si = init_split_index(istate);
96a1d8d3 NTND	182	struct cache_entry *entries = NULL, ce;
	183	int i, nr_entries = 0, nr_alloc = 0;
	184
	185	si->delete_bitmap = ewah_new();
	186	si->replace_bitmap = ewah_new();
	187
	188	if (si->base) {
	189	/* Go through istate->cache[] and mark CE_MATCHED to
	190	* entry with positive index. We'll go through
	191	* base->cache[] later to delete all entries in base
	192	* that are not marked eith either CE_MATCHED or
	193	* CE_UPDATE_IN_BASE. If istate->cache[i] is a
	194	* duplicate, deduplicate it.
	195	*/
	196	for (i = 0; i < istate->cache_nr; i++) {
	197	struct cache_entry *base;
	198	/* namelen is checked separately */
	199	const unsigned int ondisk_flags =
	200	CE_STAGEMASK \| CE_VALID \| CE_EXTENDED_FLAGS;
	201	unsigned int ce_flags, base_flags, ret;
	202	ce = istate->cache[i];
	203	if (!ce->index)
	204	continue;
	205	if (ce->index > si->base->cache_nr) {
	206	ce->index = 0;
	207	continue;
	208	}
	209	ce->ce_flags \|= CE_MATCHED; /* or "shared" */
	210	base = si->base->cache[ce->index - 1];
	211	if (ce == base)
	212	continue;
	213	if (ce->ce_namelen != base->ce_namelen \|\|
	214	strcmp(ce->name, base->name)) {
	215	ce->index = 0;
	216	continue;
	217	}
	218	ce_flags = ce->ce_flags;
	219	base_flags = base->ce_flags;
	220	/* only on-disk flags matter */
	221	ce->ce_flags &= ondisk_flags;
	222	base->ce_flags &= ondisk_flags;
	223	ret = memcmp(&ce->ce_stat_data, &base->ce_stat_data,
	224	offsetof(struct cache_entry, name) -
	225	offsetof(struct cache_entry, ce_stat_data));
	226	ce->ce_flags = ce_flags;
	227	base->ce_flags = base_flags;
	228	if (ret)
	229	ce->ce_flags \|= CE_UPDATE_IN_BASE;
	230	free(base);
	231	si->base->cache[ce->index - 1] = ce;
	232	}
	233	for (i = 0; i < si->base->cache_nr; i++) {
	234	ce = si->base->cache[i];
	235	if ((ce->ce_flags & CE_REMOVE) \|\|
	236	!(ce->ce_flags & CE_MATCHED))
	237	ewah_set(si->delete_bitmap, i);
	238	else if (ce->ce_flags & CE_UPDATE_IN_BASE) {
	239	ewah_set(si->replace_bitmap, i);
b3c96fb1	240	ce->ce_flags \|= CE_STRIP_NAME;
96a1d8d3 NTND	241	ALLOC_GROW(entries, nr_entries+1, nr_alloc);
	242	entries[nr_entries++] = ce;
	243	}
	244	}
	245	}
	246
	247	for (i = 0; i < istate->cache_nr; i++) {
	248	ce = istate->cache[i];
	249	if ((!si->base \|\| !ce->index) && !(ce->ce_flags & CE_REMOVE)) {
b3c96fb1	250	assert(!(ce->ce_flags & CE_STRIP_NAME));
96a1d8d3 NTND	251	ALLOC_GROW(entries, nr_entries+1, nr_alloc);
	252	entries[nr_entries++] = ce;
	253	}
	254	ce->ce_flags &= ~CE_MATCHED;
	255	}
	256
	257	/*
	258	* take cache[] out temporarily, put entries[] in its place
	259	* for writing
	260	*/
	261	si->saved_cache = istate->cache;
5fc2fc8f	262	si->saved_cache_nr = istate->cache_nr;
96a1d8d3 NTND	263	istate->cache = entries;
96a1d8d3 NTND	264	istate->cache_nr = nr_entries;
5fc2fc8f NTND	265	}
	266
	267	void finish_writing_split_index(struct index_state *istate)
	268	{
	269	struct split_index *si = init_split_index(istate);
96a1d8d3 NTND	270
	271	ewah_free(si->delete_bitmap);
	272	ewah_free(si->replace_bitmap);
	273	si->delete_bitmap = NULL;
	274	si->replace_bitmap = NULL;
	275	free(istate->cache);
	276	istate->cache = si->saved_cache;
5fc2fc8f NTND	277	istate->cache_nr = si->saved_cache_nr;
	278	}
	279
	280	void discard_split_index(struct index_state *istate)
	281	{
	282	struct split_index *si = istate->split_index;
	283	if (!si)
	284	return;
	285	istate->split_index = NULL;
	286	si->refcount--;
	287	if (si->refcount)
	288	return;
	289	if (si->base) {
	290	discard_index(si->base);
	291	free(si->base);
	292	}
	293	free(si);
	294	}
045113a5 NTND	295
	296	void save_or_free_index_entry(struct index_state istate, struct cache_entry ce)
	297	{
	298	if (ce->index &&
	299	istate->split_index &&
	300	istate->split_index->base &&
	301	ce->index <= istate->split_index->base->cache_nr &&
	302	ce == istate->split_index->base->cache[ce->index - 1])
	303	ce->ce_flags \|= CE_REMOVE;
	304	else
	305	free(ce);
	306	}
078a58e8 NTND	307
	308	void replace_index_entry_in_base(struct index_state *istate,
	309	struct cache_entry *old,
	310	struct cache_entry *new)
	311	{
	312	if (old->index &&
	313	istate->split_index &&
	314	istate->split_index->base &&
	315	old->index <= istate->split_index->base->cache_nr) {
	316	new->index = old->index;
	317	if (old != istate->split_index->base->cache[new->index - 1])
	318	free(istate->split_index->base->cache[new->index - 1]);
	319	istate->split_index->base->cache[new->index - 1] = new;
	320	}
	321	}