[git/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;
}

static int write_strbuf(void *user_data, const void *data, size_t len)
{
	struct strbuf *sb = user_data;
	strbuf_add(sb, data, len);
	return len;
}

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_to(si->delete_bitmap, write_strbuf, sb);
	ewah_serialize_to(si->replace_bitmap, write_strbuf, 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 resrved to say "this is a new
	 * entry".
	 */
	for (i = 0; i < base->cache_nr; i++)
		base->cache[i]->index = i + 1;
}

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];
	src->index = pos + 1;
	src->ce_flags |= CE_UPDATE_IN_BASE;
	free(dst);
	dst = 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++) {
		add_index_entry(istate, si->saved_cache[i],
				ADD_CACHE_OK_TO_ADD |
				/*
				 * 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);
				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)) {
			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
96a1d8d3 NTND	44	static int write_strbuf(void user_data, const void data, size_t len)
	45	{
	46	struct strbuf *sb = user_data;
	47	strbuf_add(sb, data, len);
	48	return len;
	49	}
	50
5fc2fc8f NTND	51	int write_link_extension(struct strbuf *sb,
	52	struct index_state *istate)
	53	{
	54	struct split_index *si = istate->split_index;
	55	strbuf_add(sb, si->base_sha1, 20);
96a1d8d3 NTND	56	if (!si->delete_bitmap && !si->replace_bitmap)
	57	return 0;
	58	ewah_serialize_to(si->delete_bitmap, write_strbuf, sb);
	59	ewah_serialize_to(si->replace_bitmap, write_strbuf, sb);
5fc2fc8f NTND	60	return 0;
	61	}
	62
	63	static void mark_base_index_entries(struct index_state *base)
	64	{
	65	int i;
	66	/*
	67	* To keep track of the shared entries between
	68	* istate->base->cache[] and istate->cache[], base entry
	69	* position is stored in each base entry. All positions start
	70	* from 1 instead of 0, which is resrved to say "this is a new
	71	* entry".
	72	*/
	73	for (i = 0; i < base->cache_nr; i++)
	74	base->cache[i]->index = i + 1;
	75	}
	76
76b07b37 NTND	77	static void mark_entry_for_delete(size_t pos, void *data)
	78	{
	79	struct index_state *istate = data;
	80	if (pos >= istate->cache_nr)
	81	die("position for delete %d exceeds base index size %d",
	82	(int)pos, istate->cache_nr);
	83	istate->cache[pos]->ce_flags \|= CE_REMOVE;
	84	istate->split_index->nr_deletions = 1;
	85	}
	86
	87	static void replace_entry(size_t pos, void *data)
	88	{
	89	struct index_state *istate = data;
	90	struct split_index *si = istate->split_index;
	91	struct cache_entry dst, src;
	92	if (pos >= istate->cache_nr)
	93	die("position for replacement %d exceeds base index size %d",
	94	(int)pos, istate->cache_nr);
	95	if (si->nr_replacements >= si->saved_cache_nr)
	96	die("too many replacements (%d vs %d)",
	97	si->nr_replacements, si->saved_cache_nr);
	98	dst = istate->cache[pos];
	99	if (dst->ce_flags & CE_REMOVE)
	100	die("entry %d is marked as both replaced and deleted",
	101	(int)pos);
	102	src = si->saved_cache[si->nr_replacements];
	103	src->index = pos + 1;
	104	src->ce_flags \|= CE_UPDATE_IN_BASE;
	105	free(dst);
	106	dst = src;
	107	si->nr_replacements++;
	108	}
	109
5fc2fc8f NTND	110	void merge_base_index(struct index_state *istate)
	111	{
	112	struct split_index *si = istate->split_index;
76b07b37	113	unsigned int i;
5fc2fc8f NTND	114
5fc2fc8f NTND	115	mark_base_index_entries(si->base);
76b07b37 NTND	116
	117	si->saved_cache = istate->cache;
	118	si->saved_cache_nr = istate->cache_nr;
	119	istate->cache_nr = si->base->cache_nr;
	120	istate->cache = NULL;
	121	istate->cache_alloc = 0;
5fc2fc8f NTND	122	ALLOC_GROW(istate->cache, istate->cache_nr, istate->cache_alloc);
	123	memcpy(istate->cache, si->base->cache,
	124	sizeof(istate->cache) istate->cache_nr);
76b07b37 NTND	125
	126	si->nr_deletions = 0;
	127	si->nr_replacements = 0;
	128	ewah_each_bit(si->replace_bitmap, replace_entry, istate);
	129	ewah_each_bit(si->delete_bitmap, mark_entry_for_delete, istate);
	130	if (si->nr_deletions)
	131	remove_marked_cache_entries(istate);
	132
	133	for (i = si->nr_replacements; i < si->saved_cache_nr; i++) {
	134	add_index_entry(istate, si->saved_cache[i],
	135	ADD_CACHE_OK_TO_ADD \|
	136	/*
	137	* we may have to replay what
	138	* merge-recursive.c:update_stages()
	139	* does, which has this flag on
	140	*/
	141	ADD_CACHE_SKIP_DFCHECK);
	142	si->saved_cache[i] = NULL;
	143	}
	144
	145	ewah_free(si->delete_bitmap);
	146	ewah_free(si->replace_bitmap);
	147	free(si->saved_cache);
	148	si->delete_bitmap = NULL;
	149	si->replace_bitmap = NULL;
	150	si->saved_cache = NULL;
	151	si->saved_cache_nr = 0;
5fc2fc8f NTND	152	}
	153
	154	void prepare_to_write_split_index(struct index_state *istate)
	155	{
	156	struct split_index *si = init_split_index(istate);
96a1d8d3 NTND	157	struct cache_entry *entries = NULL, ce;
	158	int i, nr_entries = 0, nr_alloc = 0;
	159
	160	si->delete_bitmap = ewah_new();
	161	si->replace_bitmap = ewah_new();
	162
	163	if (si->base) {
	164	/* Go through istate->cache[] and mark CE_MATCHED to
	165	* entry with positive index. We'll go through
	166	* base->cache[] later to delete all entries in base
	167	* that are not marked eith either CE_MATCHED or
	168	* CE_UPDATE_IN_BASE. If istate->cache[i] is a
	169	* duplicate, deduplicate it.
	170	*/
	171	for (i = 0; i < istate->cache_nr; i++) {
	172	struct cache_entry *base;
	173	/* namelen is checked separately */
	174	const unsigned int ondisk_flags =
	175	CE_STAGEMASK \| CE_VALID \| CE_EXTENDED_FLAGS;
	176	unsigned int ce_flags, base_flags, ret;
	177	ce = istate->cache[i];
	178	if (!ce->index)
	179	continue;
	180	if (ce->index > si->base->cache_nr) {
	181	ce->index = 0;
	182	continue;
	183	}
	184	ce->ce_flags \|= CE_MATCHED; /* or "shared" */
	185	base = si->base->cache[ce->index - 1];
	186	if (ce == base)
	187	continue;
	188	if (ce->ce_namelen != base->ce_namelen \|\|
	189	strcmp(ce->name, base->name)) {
	190	ce->index = 0;
	191	continue;
	192	}
	193	ce_flags = ce->ce_flags;
	194	base_flags = base->ce_flags;
	195	/* only on-disk flags matter */
	196	ce->ce_flags &= ondisk_flags;
	197	base->ce_flags &= ondisk_flags;
	198	ret = memcmp(&ce->ce_stat_data, &base->ce_stat_data,
	199	offsetof(struct cache_entry, name) -
	200	offsetof(struct cache_entry, ce_stat_data));
	201	ce->ce_flags = ce_flags;
	202	base->ce_flags = base_flags;
	203	if (ret)
	204	ce->ce_flags \|= CE_UPDATE_IN_BASE;
	205	free(base);
	206	si->base->cache[ce->index - 1] = ce;
	207	}
	208	for (i = 0; i < si->base->cache_nr; i++) {
	209	ce = si->base->cache[i];
	210	if ((ce->ce_flags & CE_REMOVE) \|\|
	211	!(ce->ce_flags & CE_MATCHED))
	212	ewah_set(si->delete_bitmap, i);
	213	else if (ce->ce_flags & CE_UPDATE_IN_BASE) {
	214	ewah_set(si->replace_bitmap, i);
	215	ALLOC_GROW(entries, nr_entries+1, nr_alloc);
	216	entries[nr_entries++] = ce;
	217	}
	218	}
	219	}
	220
221	for (i = 0; i < istate->cache_nr; i++) {
222	ce = istate->cache[i];
223	if ((!si->base \|\| !ce->index) && !(ce->ce_flags & CE_REMOVE)) {
224	ALLOC_GROW(entries, nr_entries+1, nr_alloc);
225	entries[nr_entries++] = ce;
226	}
227	ce->ce_flags &= ~CE_MATCHED;
228	}
229
230	/*
231	* take cache[] out temporarily, put entries[] in its place
232	* for writing
233	*/
234	si->saved_cache = istate->cache;
5fc2fc8f	235	si->saved_cache_nr = istate->cache_nr;
96a1d8d3 NTND	236	istate->cache = entries;
96a1d8d3 NTND	237	istate->cache_nr = nr_entries;
5fc2fc8f NTND	238	}
	239
	240	void finish_writing_split_index(struct index_state *istate)
	241	{
	242	struct split_index *si = init_split_index(istate);
96a1d8d3 NTND	243
	244	ewah_free(si->delete_bitmap);
	245	ewah_free(si->replace_bitmap);
	246	si->delete_bitmap = NULL;
	247	si->replace_bitmap = NULL;
	248	free(istate->cache);
	249	istate->cache = si->saved_cache;
5fc2fc8f NTND	250	istate->cache_nr = si->saved_cache_nr;
	251	}
	252
	253	void discard_split_index(struct index_state *istate)
	254	{
	255	struct split_index *si = istate->split_index;
	256	if (!si)
	257	return;
	258	istate->split_index = NULL;
	259	si->refcount--;
	260	if (si->refcount)
	261	return;
	262	if (si->base) {
	263	discard_index(si->base);
	264	free(si->base);
	265	}
	266	free(si);
	267	}
045113a5 NTND	268
	269	void save_or_free_index_entry(struct index_state istate, struct cache_entry ce)
	270	{
	271	if (ce->index &&
	272	istate->split_index &&
	273	istate->split_index->base &&
	274	ce->index <= istate->split_index->base->cache_nr &&
	275	ce == istate->split_index->base->cache[ce->index - 1])
	276	ce->ce_flags \|= CE_REMOVE;
	277	else
	278	free(ce);
	279	}
078a58e8 NTND	280
	281	void replace_index_entry_in_base(struct index_state *istate,
	282	struct cache_entry *old,
	283	struct cache_entry *new)
	284	{
	285	if (old->index &&
	286	istate->split_index &&
	287	istate->split_index->base &&
	288	old->index <= istate->split_index->base->cache_nr) {
	289	new->index = old->index;
	290	if (old != istate->split_index->base->cache[new->index - 1])
	291	free(istate->split_index->base->cache[new->index - 1]);
	292	istate->split_index->base->cache[new->index - 1] = new;
	293	}
	294	}