git/bisect.c

#include "cache.h"
#include "commit.h"
#include "diff.h"
#include "revision.h"
#include "refs.h"
#include "list-objects.h"
#include "quote.h"
#include "sha1-lookup.h"
#include "run-command.h"
#include "bisect.h"

struct sha1_array {
	unsigned char (*sha1)[20];
	int sha1_nr;
	int sha1_alloc;
	int sorted;
};

static struct sha1_array good_revs;
static struct sha1_array skipped_revs;

static const unsigned char *current_bad_sha1;

struct argv_array {
	const char **argv;
	int argv_nr;
	int argv_alloc;
};

static const char *argv_diff_tree[] = {"diff-tree", "--pretty", NULL, NULL};
static const char *argv_checkout[] = {"checkout", "-q", NULL, "--", NULL};
static const char *argv_show_branch[] = {"show-branch", NULL, NULL};

/* bits #0-15 in revision.h */

#define COUNTED		(1u<<16)

/*
 * This is a truly stupid algorithm, but it's only
 * used for bisection, and we just don't care enough.
 *
 * We care just barely enough to avoid recursing for
 * non-merge entries.
 */
static int count_distance(struct commit_list *entry)
{
	int nr = 0;

	while (entry) {
		struct commit *commit = entry->item;
		struct commit_list *p;

		if (commit->object.flags & (UNINTERESTING | COUNTED))
			break;
		if (!(commit->object.flags & TREESAME))
			nr++;
		commit->object.flags |= COUNTED;
		p = commit->parents;
		entry = p;
		if (p) {
			p = p->next;
			while (p) {
				nr += count_distance(p);
				p = p->next;
			}
		}
	}

	return nr;
}

static void clear_distance(struct commit_list *list)
{
	while (list) {
		struct commit *commit = list->item;
		commit->object.flags &= ~COUNTED;
		list = list->next;
	}
}

#define DEBUG_BISECT 0

static inline int weight(struct commit_list *elem)
{
	return *((int*)(elem->item->util));
}

static inline void weight_set(struct commit_list *elem, int weight)
{
	*((int*)(elem->item->util)) = weight;
}

static int count_interesting_parents(struct commit *commit)
{
	struct commit_list *p;
	int count;

	for (count = 0, p = commit->parents; p; p = p->next) {
		if (p->item->object.flags & UNINTERESTING)
			continue;
		count++;
	}
	return count;
}

static inline int halfway(struct commit_list *p, int nr)
{
	/*
	 * Don't short-cut something we are not going to return!
	 */
	if (p->item->object.flags & TREESAME)
		return 0;
	if (DEBUG_BISECT)
		return 0;
	/*
	 * 2 and 3 are halfway of 5.
	 * 3 is halfway of 6 but 2 and 4 are not.
	 */
	switch (2 * weight(p) - nr) {
	case -1: case 0: case 1:
		return 1;
	default:
		return 0;
	}
}

#if !DEBUG_BISECT
#define show_list(a,b,c,d) do { ; } while (0)
#else
static void show_list(const char *debug, int counted, int nr,
		      struct commit_list *list)
{
	struct commit_list *p;

	fprintf(stderr, "%s (%d/%d)\n", debug, counted, nr);

	for (p = list; p; p = p->next) {
		struct commit_list *pp;
		struct commit *commit = p->item;
		unsigned flags = commit->object.flags;
		enum object_type type;
		unsigned long size;
		char *buf = read_sha1_file(commit->object.sha1, &type, &size);
		char *ep, *sp;

		fprintf(stderr, "%c%c%c ",
			(flags & TREESAME) ? ' ' : 'T',
			(flags & UNINTERESTING) ? 'U' : ' ',
			(flags & COUNTED) ? 'C' : ' ');
		if (commit->util)
			fprintf(stderr, "%3d", weight(p));
		else
			fprintf(stderr, "---");
		fprintf(stderr, " %.*s", 8, sha1_to_hex(commit->object.sha1));
		for (pp = commit->parents; pp; pp = pp->next)
			fprintf(stderr, " %.*s", 8,
				sha1_to_hex(pp->item->object.sha1));

		sp = strstr(buf, "\n\n");
		if (sp) {
			sp += 2;
			for (ep = sp; *ep && *ep != '\n'; ep++)
				;
			fprintf(stderr, " %.*s", (int)(ep - sp), sp);
		}
		fprintf(stderr, "\n");
	}
}
#endif /* DEBUG_BISECT */

static struct commit_list *best_bisection(struct commit_list *list, int nr)
{
	struct commit_list *p, *best;
	int best_distance = -1;

	best = list;
	for (p = list; p; p = p->next) {
		int distance;
		unsigned flags = p->item->object.flags;

		if (flags & TREESAME)
			continue;
		distance = weight(p);
		if (nr - distance < distance)
			distance = nr - distance;
		if (distance > best_distance) {
			best = p;
			best_distance = distance;
		}
	}

	return best;
}

struct commit_dist {
	struct commit *commit;
	int distance;
};

static int compare_commit_dist(const void *a_, const void *b_)
{
	struct commit_dist *a, *b;

	a = (struct commit_dist *)a_;
	b = (struct commit_dist *)b_;
	if (a->distance != b->distance)
		return b->distance - a->distance; /* desc sort */
	return hashcmp(a->commit->object.sha1, b->commit->object.sha1);
}

static struct commit_list *best_bisection_sorted(struct commit_list *list, int nr)
{
	struct commit_list *p;
	struct commit_dist *array = xcalloc(nr, sizeof(*array));
	int cnt, i;

	for (p = list, cnt = 0; p; p = p->next) {
		int distance;
		unsigned flags = p->item->object.flags;

		if (flags & TREESAME)
			continue;
		distance = weight(p);
		if (nr - distance < distance)
			distance = nr - distance;
		array[cnt].commit = p->item;
		array[cnt].distance = distance;
		cnt++;
	}
	qsort(array, cnt, sizeof(*array), compare_commit_dist);
	for (p = list, i = 0; i < cnt; i++) {
		struct name_decoration *r = xmalloc(sizeof(*r) + 100);
		struct object *obj = &(array[i].commit->object);

		sprintf(r->name, "dist=%d", array[i].distance);
		r->next = add_decoration(&name_decoration, obj, r);
		p->item = array[i].commit;
		p = p->next;
	}
	if (p)
		p->next = NULL;
	free(array);
	return list;
}

/*
 * zero or positive weight is the number of interesting commits it can
 * reach, including itself.  Especially, weight = 0 means it does not
 * reach any tree-changing commits (e.g. just above uninteresting one
 * but traversal is with pathspec).
 *
 * weight = -1 means it has one parent and its distance is yet to
 * be computed.
 *
 * weight = -2 means it has more than one parent and its distance is
 * unknown.  After running count_distance() first, they will get zero
 * or positive distance.
 */
static struct commit_list *do_find_bisection(struct commit_list *list,
					     int nr, int *weights,
					     int find_all)
{
	int n, counted;
	struct commit_list *p;

	counted = 0;

	for (n = 0, p = list; p; p = p->next) {
		struct commit *commit = p->item;
		unsigned flags = commit->object.flags;

		p->item->util = &weights[n++];
		switch (count_interesting_parents(commit)) {
		case 0:
			if (!(flags & TREESAME)) {
				weight_set(p, 1);
				counted++;
				show_list("bisection 2 count one",
					  counted, nr, list);
			}
			/*
			 * otherwise, it is known not to reach any
			 * tree-changing commit and gets weight 0.
			 */
			break;
		case 1:
			weight_set(p, -1);
			break;
		default:
			weight_set(p, -2);
			break;
		}
	}

	show_list("bisection 2 initialize", counted, nr, list);

	/*
	 * If you have only one parent in the resulting set
	 * then you can reach one commit more than that parent
	 * can reach.  So we do not have to run the expensive
	 * count_distance() for single strand of pearls.
	 *
	 * However, if you have more than one parents, you cannot
	 * just add their distance and one for yourself, since
	 * they usually reach the same ancestor and you would
	 * end up counting them twice that way.
	 *
	 * So we will first count distance of merges the usual
	 * way, and then fill the blanks using cheaper algorithm.
	 */
	for (p = list; p; p = p->next) {
		if (p->item->object.flags & UNINTERESTING)
			continue;
		if (weight(p) != -2)
			continue;
		weight_set(p, count_distance(p));
		clear_distance(list);

		/* Does it happen to be at exactly half-way? */
		if (!find_all && halfway(p, nr))
			return p;
		counted++;
	}

	show_list("bisection 2 count_distance", counted, nr, list);

	while (counted < nr) {
		for (p = list; p; p = p->next) {
			struct commit_list *q;
			unsigned flags = p->item->object.flags;

			if (0 <= weight(p))
				continue;
			for (q = p->item->parents; q; q = q->next) {
				if (q->item->object.flags & UNINTERESTING)
					continue;
				if (0 <= weight(q))
					break;
			}
			if (!q)
				continue;

			/*
			 * weight for p is unknown but q is known.
			 * add one for p itself if p is to be counted,
			 * otherwise inherit it from q directly.
			 */
			if (!(flags & TREESAME)) {
				weight_set(p, weight(q)+1);
				counted++;
				show_list("bisection 2 count one",
					  counted, nr, list);
			}
			else
				weight_set(p, weight(q));

			/* Does it happen to be at exactly half-way? */
			if (!find_all && halfway(p, nr))
				return p;
		}
	}

	show_list("bisection 2 counted all", counted, nr, list);

	if (!find_all)
		return best_bisection(list, nr);
	else
		return best_bisection_sorted(list, nr);
}

struct commit_list *find_bisection(struct commit_list *list,
					  int *reaches, int *all,
					  int find_all)
{
	int nr, on_list;
	struct commit_list *p, *best, *next, *last;
	int *weights;

	show_list("bisection 2 entry", 0, 0, list);

	/*
	 * Count the number of total and tree-changing items on the
	 * list, while reversing the list.
	 */
	for (nr = on_list = 0, last = NULL, p = list;
	     p;
	     p = next) {
		unsigned flags = p->item->object.flags;

		next = p->next;
		if (flags & UNINTERESTING)
			continue;
		p->next = last;
		last = p;
		if (!(flags & TREESAME))
			nr++;
		on_list++;
	}
	list = last;
	show_list("bisection 2 sorted", 0, nr, list);

	*all = nr;
	weights = xcalloc(on_list, sizeof(*weights));

	/* Do the real work of finding bisection commit. */
	best = do_find_bisection(list, nr, weights, find_all);
	if (best) {
		if (!find_all)
			best->next = NULL;
		*reaches = weight(best);
	}
	free(weights);
	return best;
}

static void argv_array_push(struct argv_array *array, const char *string)
{
	ALLOC_GROW(array->argv, array->argv_nr + 1, array->argv_alloc);
	array->argv[array->argv_nr++] = string;
}

static void argv_array_push_sha1(struct argv_array *array,
				 const unsigned char *sha1,
				 const char *format)
{
	struct strbuf buf = STRBUF_INIT;
	strbuf_addf(&buf, format, sha1_to_hex(sha1));
	argv_array_push(array, strbuf_detach(&buf, NULL));
}

static void sha1_array_push(struct sha1_array *array,
			    const unsigned char *sha1)
{
	ALLOC_GROW(array->sha1, array->sha1_nr + 1, array->sha1_alloc);
	hashcpy(array->sha1[array->sha1_nr++], sha1);
}

static int register_ref(const char *refname, const unsigned char *sha1,
			int flags, void *cb_data)
{
	if (!strcmp(refname, "bad")) {
		current_bad_sha1 = sha1;
	} else if (!prefixcmp(refname, "good-")) {
		sha1_array_push(&good_revs, sha1);
	} else if (!prefixcmp(refname, "skip-")) {
		sha1_array_push(&skipped_revs, sha1);
	}

	return 0;
}

static int read_bisect_refs(void)
{
	return for_each_ref_in("refs/bisect/", register_ref, NULL);
}

void read_bisect_paths(struct argv_array *array)
{
	struct strbuf str = STRBUF_INIT;
	const char *filename = git_path("BISECT_NAMES");
	FILE *fp = fopen(filename, "r");

	if (!fp)
		die("Could not open file '%s': %s", filename, strerror(errno));

	while (strbuf_getline(&str, fp, '\n') != EOF) {
		char *quoted;
		int res;

		strbuf_trim(&str);
		quoted = strbuf_detach(&str, NULL);
		res = sq_dequote_to_argv(quoted, &array->argv,
					 &array->argv_nr, &array->argv_alloc);
		if (res)
			die("Badly quoted content in file '%s': %s",
			    filename, quoted);
	}

	strbuf_release(&str);
	fclose(fp);
}

static int array_cmp(const void *a, const void *b)
{
	return hashcmp(a, b);
}

static void sort_sha1_array(struct sha1_array *array)
{
	qsort(array->sha1, array->sha1_nr, sizeof(*array->sha1), array_cmp);

	array->sorted = 1;
}

static const unsigned char *sha1_access(size_t index, void *table)
{
	unsigned char (*array)[20] = table;
	return array[index];
}

static int lookup_sha1_array(struct sha1_array *array,
			     const unsigned char *sha1)
{
	if (!array->sorted)
		sort_sha1_array(array);

	return sha1_pos(sha1, array->sha1, array->sha1_nr, sha1_access);
}

static char *join_sha1_array_hex(struct sha1_array *array, char delim)
{
	struct strbuf joined_hexs = STRBUF_INIT;
	int i;

	for (i = 0; i < array->sha1_nr; i++) {
		strbuf_addstr(&joined_hexs, sha1_to_hex(array->sha1[i]));
		if (i + 1 < array->sha1_nr)
			strbuf_addch(&joined_hexs, delim);
	}

	return strbuf_detach(&joined_hexs, NULL);
}

struct commit_list *filter_skipped(struct commit_list *list,
				   struct commit_list **tried,
				   int show_all)
{
	struct commit_list *filtered = NULL, **f = &filtered;

	*tried = NULL;

	if (!skipped_revs.sha1_nr)
		return list;

	while (list) {
		struct commit_list *next = list->next;
		list->next = NULL;
		if (0 <= lookup_sha1_array(&skipped_revs,
					   list->item->object.sha1)) {
			/* Move current to tried list */
			*tried = list;
			tried = &list->next;
		} else {
			if (!show_all)
				return list;
			/* Move current to filtered list */
			*f = list;
			f = &list->next;
		}
		list = next;
	}

	return filtered;
}

static void bisect_rev_setup(struct rev_info *revs, const char *prefix)
{
	struct argv_array rev_argv = { NULL, 0, 0 };
	int i;

	init_revisions(revs, prefix);
	revs->abbrev = 0;
	revs->commit_format = CMIT_FMT_UNSPECIFIED;

	/* rev_argv.argv[0] will be ignored by setup_revisions */
	argv_array_push(&rev_argv, xstrdup("bisect_rev_setup"));
	argv_array_push_sha1(&rev_argv, current_bad_sha1, "%s");
	for (i = 0; i < good_revs.sha1_nr; i++)
		argv_array_push_sha1(&rev_argv, good_revs.sha1[i], "^%s");
	argv_array_push(&rev_argv, xstrdup("--"));
	read_bisect_paths(&rev_argv);
	argv_array_push(&rev_argv, NULL);

	setup_revisions(rev_argv.argv_nr, rev_argv.argv, revs, NULL);
	revs->limited = 1;
}

static void bisect_common(struct rev_info *revs, int *reaches, int *all)
{
	if (prepare_revision_walk(revs))
		die("revision walk setup failed");
	if (revs->tree_objects)
		mark_edges_uninteresting(revs->commits, revs, NULL);

	revs->commits = find_bisection(revs->commits, reaches, all,
				       !!skipped_revs.sha1_nr);
}

static void exit_if_skipped_commits(struct commit_list *tried,
				    const unsigned char *bad)
{
	if (!tried)
		return;

	printf("There are only 'skip'ped commits left to test.\n"
	       "The first bad commit could be any of:\n");
	print_commit_list(tried, "%s\n", "%s\n");
	if (bad)
		printf("%s\n", sha1_to_hex(bad));
	printf("We cannot bisect more!\n");
	exit(2);
}

static int is_expected_rev(const unsigned char *sha1)
{
	const char *filename = git_path("BISECT_EXPECTED_REV");
	struct stat st;
	struct strbuf str = STRBUF_INIT;
	FILE *fp;
	int res = 0;

	if (stat(filename, &st) || !S_ISREG(st.st_mode))
		return 0;

	fp = fopen(filename, "r");
	if (!fp)
		return 0;

	if (strbuf_getline(&str, fp, '\n') != EOF)
		res = !strcmp(str.buf, sha1_to_hex(sha1));

	strbuf_release(&str);
	fclose(fp);

	return res;
}

static void mark_expected_rev(char *bisect_rev_hex)
{
	int len = strlen(bisect_rev_hex);
	const char *filename = git_path("BISECT_EXPECTED_REV");
	int fd = open(filename, O_CREAT | O_TRUNC | O_WRONLY, 0600);

	if (fd < 0)
		die("could not create file '%s': %s",
		    filename, strerror(errno));

	bisect_rev_hex[len] = '\n';
	write_or_die(fd, bisect_rev_hex, len + 1);
	bisect_rev_hex[len] = '\0';

	if (close(fd) < 0)
		die("closing file %s: %s", filename, strerror(errno));
}

static int bisect_checkout(char *bisect_rev_hex)
{
	int res;

	mark_expected_rev(bisect_rev_hex);

	argv_checkout[2] = bisect_rev_hex;
	res = run_command_v_opt(argv_checkout, RUN_GIT_CMD);
	if (res)
		exit(res);

	argv_show_branch[1] = bisect_rev_hex;
	return run_command_v_opt(argv_show_branch, RUN_GIT_CMD);
}

static struct commit *get_commit_reference(const unsigned char *sha1)
{
	struct commit *r = lookup_commit_reference(sha1);
	if (!r)
		die("Not a valid commit name %s", sha1_to_hex(sha1));
	return r;
}

static struct commit **get_bad_and_good_commits(int *rev_nr)
{
	int len = 1 + good_revs.sha1_nr;
	struct commit **rev = xmalloc(len * sizeof(*rev));
	int i, n = 0;

	rev[n++] = get_commit_reference(current_bad_sha1);
	for (i = 0; i < good_revs.sha1_nr; i++)
		rev[n++] = get_commit_reference(good_revs.sha1[i]);
	*rev_nr = n;

	return rev;
}

static void handle_bad_merge_base(void)
{
	if (is_expected_rev(current_bad_sha1)) {
		char *bad_hex = sha1_to_hex(current_bad_sha1);
		char *good_hex = join_sha1_array_hex(&good_revs, ' ');

		fprintf(stderr, "The merge base %s is bad.\n"
			"This means the bug has been fixed "
			"between %s and [%s].\n",
			bad_hex, bad_hex, good_hex);

		exit(3);
	}

	fprintf(stderr, "Some good revs are not ancestor of the bad rev.\n"
		"git bisect cannot work properly in this case.\n"
		"Maybe you mistake good and bad revs?\n");
	exit(1);
}

void handle_skipped_merge_base(const unsigned char *mb)
{
	char *mb_hex = sha1_to_hex(mb);
	char *bad_hex = sha1_to_hex(current_bad_sha1);
	char *good_hex = join_sha1_array_hex(&good_revs, ' ');

	fprintf(stderr, "Warning: the merge base between %s and [%s] "
		"must be skipped.\n"
		"So we cannot be sure the first bad commit is "
		"between %s and %s.\n"
		"We continue anyway.\n",
		bad_hex, good_hex, mb_hex, bad_hex);
	free(good_hex);
}

/*
 * "check_merge_bases" checks that merge bases are not "bad".
 *
 * - If one is "bad", it means the user assumed something wrong
 * and we must exit with a non 0 error code.
 * - If one is "good", that's good, we have nothing to do.
 * - If one is "skipped", we can't know but we should warn.
 * - If we don't know, we should check it out and ask the user to test.
 */
static void check_merge_bases(void)
{
	struct commit_list *result;
	int rev_nr;
	struct commit **rev = get_bad_and_good_commits(&rev_nr);

	result = get_merge_bases_many(rev[0], rev_nr - 1, rev + 1, 0);

	for (; result; result = result->next) {
		const unsigned char *mb = result->item->object.sha1;
		if (!hashcmp(mb, current_bad_sha1)) {
			handle_bad_merge_base();
		} else if (0 <= lookup_sha1_array(&good_revs, mb)) {
			continue;
		} else if (0 <= lookup_sha1_array(&skipped_revs, mb)) {
			handle_skipped_merge_base(mb);
		} else {
			printf("Bisecting: a merge base must be tested\n");
			exit(bisect_checkout(sha1_to_hex(mb)));
		}
	}

	free(rev);
	free_commit_list(result);
}

/*
 * We use the convention that exiting with an exit code 10 means that
 * the bisection process finished successfully.
 * In this case the calling shell script should exit 0.
 */
int bisect_next_exit(const char *prefix)
{
	struct rev_info revs;
	struct commit_list *tried;
	int reaches = 0, all = 0, nr;
	const unsigned char *bisect_rev;
	char bisect_rev_hex[41];

	if (read_bisect_refs())
		die("reading bisect refs failed");

	bisect_rev_setup(&revs, prefix);

	bisect_common(&revs, &reaches, &all);

	revs.commits = filter_skipped(revs.commits, &tried, 0);

	if (!revs.commits) {
		/*
		 * We should exit here only if the "bad"
		 * commit is also a "skip" commit.
		 */
		exit_if_skipped_commits(tried, NULL);

		printf("%s was both good and bad\n",
		       sha1_to_hex(current_bad_sha1));
		exit(1);
	}

	bisect_rev = revs.commits->item->object.sha1;
	memcpy(bisect_rev_hex, sha1_to_hex(bisect_rev), 41);

	if (!hashcmp(bisect_rev, current_bad_sha1)) {
		exit_if_skipped_commits(tried, current_bad_sha1);
		printf("%s is first bad commit\n", bisect_rev_hex);
		argv_diff_tree[2] = bisect_rev_hex;
		run_command_v_opt(argv_diff_tree, RUN_GIT_CMD);
		/* This means the bisection process succeeded. */
		exit(10);
	}

	nr = all - reaches - 1;
	printf("Bisecting: %d revisions left to test after this "
	       "(roughly %d steps)\n", nr, estimate_bisect_steps(all));

	return bisect_checkout(bisect_rev_hex);
}