diff options
Diffstat (limited to 'merge-ort.c')
| -rw-r--r-- | merge-ort.c | 1898 |
1 files changed, 1458 insertions, 440 deletions
diff --git a/merge-ort.c b/merge-ort.c index b954f71..eaede6c 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -14,24 +14,36 @@ * "cale", "peedy", or "ins" instead of "ort"?) */ -#include "cache.h" +#include "git-compat-util.h" #include "merge-ort.h" #include "alloc.h" +#include "advice.h" #include "attr.h" -#include "blob.h" #include "cache-tree.h" #include "commit.h" #include "commit-reach.h" #include "diff.h" #include "diffcore.h" #include "dir.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" #include "entry.h" -#include "ll-merge.h" -#include "object-store.h" +#include "merge-ll.h" +#include "match-trees.h" +#include "mem-pool.h" +#include "object-name.h" +#include "object-store-ll.h" +#include "oid-array.h" +#include "path.h" +#include "promisor-remote.h" +#include "read-cache-ll.h" +#include "refs.h" #include "revision.h" +#include "sparse-index.h" #include "strmap.h" -#include "submodule.h" +#include "trace2.h" #include "tree.h" #include "unpack-trees.h" #include "xdiff-interface.h" @@ -61,6 +73,53 @@ struct traversal_callback_data { struct name_entry names[3]; }; +struct deferred_traversal_data { + /* + * possible_trivial_merges: directories to be explored only when needed + * + * possible_trivial_merges is a map of directory names to + * dir_rename_mask. When we detect that a directory is unchanged on + * one side, we can sometimes resolve the directory without recursing + * into it. Renames are the only things that can prevent such an + * optimization. However, for rename sources: + * - If no parent directory needed directory rename detection, then + * no path under such a directory can be a relevant_source. + * and for rename destinations: + * - If no cached rename has a target path under the directory AND + * - If there are no unpaired relevant_sources elsewhere in the + * repository + * then we don't need any path under this directory for a rename + * destination. The only way to know the last item above is to defer + * handling such directories until the end of collect_merge_info(), + * in handle_deferred_entries(). + * + * For each we store dir_rename_mask, since that's the only bit of + * information we need, other than the path, to resume the recursive + * traversal. + */ + struct strintmap possible_trivial_merges; + + /* + * trivial_merges_okay: if trivial directory merges are okay + * + * See possible_trivial_merges above. The "no unpaired + * relevant_sources elsewhere in the repository" is a single boolean + * per merge side, which we store here. Note that while 0 means no, + * 1 only means "maybe" rather than "yes"; we optimistically set it + * to 1 initially and only clear when we determine it is unsafe to + * do trivial directory merges. + */ + unsigned trivial_merges_okay; + + /* + * target_dirs: ancestor directories of rename targets + * + * target_dirs contains all directory names that are an ancestor of + * any rename destination. + */ + struct strset target_dirs; +}; + struct rename_info { /* * All variables that are arrays of size 3 correspond to data tracked @@ -118,6 +177,8 @@ struct rename_info { */ struct strintmap relevant_sources[3]; + struct deferred_traversal_data deferred[3]; + /* * dir_rename_mask: * 0: optimization removing unmodified potential rename source okay @@ -163,6 +224,7 @@ struct rename_info { * MERGE_SIDE2: cached data from side2 can be reused * MERGE_SIDE1: cached data from side1 can be reused * 0: no cached data can be reused + * -1: See redo_after_renames; both sides can be reused. */ int cached_pairs_valid_side; @@ -209,6 +271,28 @@ struct rename_info { struct strset cached_irrelevant[3]; /* + * redo_after_renames: optimization flag for "restarting" the merge + * + * Sometimes it pays to detect renames, cache them, and then + * restart the merge operation from the beginning. The reason for + * this is that when we know where all the renames are, we know + * whether a certain directory has any paths under it affected -- + * and if a directory is not affected then it permits us to do + * trivial tree merging in more cases. Doing trivial tree merging + * prevents the need to run process_entry() on every path + * underneath trees that can be trivially merged, and + * process_entry() is more expensive than collect_merge_info() -- + * plus, the second collect_merge_info() will be much faster since + * it doesn't have to recurse into the relevant trees. + * + * Values for this flag: + * 0 = don't bother, not worth it (or conditions not yet checked) + * 1 = conditions for optimization met, optimization worthwhile + * 2 = we already did it (don't restart merge yet again) + */ + unsigned redo_after_renames; + + /* * needed_limit: value needed for inexact rename detection to run * * If the current rename limit wasn't high enough for inexact @@ -230,8 +314,6 @@ struct merge_options_internal { * * these keys serve to intern all the path strings, which allows * us to do pointer comparison on directory names instead of * strcmp; we just have to be careful to use the interned strings. - * (Technically paths_to_free may track some strings that were - * removed from froms paths.) * * The values of paths: * * either a pointer to a merged_info, or a conflict_info struct @@ -267,23 +349,25 @@ struct merge_options_internal { struct strmap conflicted; /* - * paths_to_free: additional list of strings to free + * pool: memory pool for fast allocation/deallocation * - * If keys are removed from "paths", they are added to paths_to_free - * to ensure they are later freed. We avoid free'ing immediately since - * other places (e.g. conflict_info.pathnames[]) may still be - * referencing these paths. + * We allocate room for lots of filenames and auxiliary data + * structures in merge_options_internal, and it tends to all be + * freed together too. Using a memory pool for these provides a + * nice speedup. */ - struct string_list paths_to_free; + struct mem_pool pool; /* - * output: special messages and conflict notices for various paths + * conflicts: logical conflicts and messages stored by _primary_ path * * This is a map of pathnames (a subset of the keys in "paths" above) - * to strbufs. It gathers various warning/conflict/notice messages - * for later processing. + * to struct string_list, with each item's `util` containing a + * `struct logical_conflict_info`. Note, though, that for each path, + * it only stores the logical conflicts for which that path is the + * primary path; the path might be part of additional conflicts. */ - struct strmap output; + struct strmap conflicts; /* * renames: various data relating to rename detection @@ -313,8 +397,24 @@ struct merge_options_internal { /* call_depth: recursion level counter for merging merge bases */ int call_depth; + + /* field that holds submodule conflict information */ + struct string_list conflicted_submodules; }; +struct conflicted_submodule_item { + char *abbrev; + int flag; +}; + +static void conflicted_submodule_item_free(void *util, const char *str UNUSED) +{ + struct conflicted_submodule_item *item = util; + + free(item->abbrev); + free(item); +} + struct version_info { struct object_id oid; unsigned short mode; @@ -409,6 +509,103 @@ struct conflict_info { unsigned match_mask:3; }; +enum conflict_and_info_types { + /* "Simple" conflicts and informational messages */ + INFO_AUTO_MERGING = 0, + CONFLICT_CONTENTS, /* text file that failed to merge */ + CONFLICT_BINARY, + CONFLICT_FILE_DIRECTORY, + CONFLICT_DISTINCT_MODES, + CONFLICT_MODIFY_DELETE, + + /* Regular rename */ + CONFLICT_RENAME_RENAME, /* same file renamed differently */ + CONFLICT_RENAME_COLLIDES, /* rename/add or two files renamed to 1 */ + CONFLICT_RENAME_DELETE, + + /* Basic directory rename */ + CONFLICT_DIR_RENAME_SUGGESTED, + INFO_DIR_RENAME_APPLIED, + + /* Special directory rename cases */ + INFO_DIR_RENAME_SKIPPED_DUE_TO_RERENAME, + CONFLICT_DIR_RENAME_FILE_IN_WAY, + CONFLICT_DIR_RENAME_COLLISION, + CONFLICT_DIR_RENAME_SPLIT, + + /* Basic submodule */ + INFO_SUBMODULE_FAST_FORWARDING, + CONFLICT_SUBMODULE_FAILED_TO_MERGE, + + /* Special submodule cases broken out from FAILED_TO_MERGE */ + CONFLICT_SUBMODULE_FAILED_TO_MERGE_BUT_POSSIBLE_RESOLUTION, + CONFLICT_SUBMODULE_NOT_INITIALIZED, + CONFLICT_SUBMODULE_HISTORY_NOT_AVAILABLE, + CONFLICT_SUBMODULE_MAY_HAVE_REWINDS, + CONFLICT_SUBMODULE_NULL_MERGE_BASE, + CONFLICT_SUBMODULE_CORRUPT, + + /* Keep this entry _last_ in the list */ + NB_CONFLICT_TYPES, +}; + +/* + * Short description of conflict type, relied upon by external tools. + * + * We can add more entries, but DO NOT change any of these strings. Also, + * Order MUST match conflict_info_and_types. + */ +static const char *type_short_descriptions[] = { + /*** "Simple" conflicts and informational messages ***/ + [INFO_AUTO_MERGING] = "Auto-merging", + [CONFLICT_CONTENTS] = "CONFLICT (contents)", + [CONFLICT_BINARY] = "CONFLICT (binary)", + [CONFLICT_FILE_DIRECTORY] = "CONFLICT (file/directory)", + [CONFLICT_DISTINCT_MODES] = "CONFLICT (distinct modes)", + [CONFLICT_MODIFY_DELETE] = "CONFLICT (modify/delete)", + + /*** Regular rename ***/ + [CONFLICT_RENAME_RENAME] = "CONFLICT (rename/rename)", + [CONFLICT_RENAME_COLLIDES] = "CONFLICT (rename involved in collision)", + [CONFLICT_RENAME_DELETE] = "CONFLICT (rename/delete)", + + /*** Basic directory rename ***/ + [CONFLICT_DIR_RENAME_SUGGESTED] = + "CONFLICT (directory rename suggested)", + [INFO_DIR_RENAME_APPLIED] = "Path updated due to directory rename", + + /*** Special directory rename cases ***/ + [INFO_DIR_RENAME_SKIPPED_DUE_TO_RERENAME] = + "Directory rename skipped since directory was renamed on both sides", + [CONFLICT_DIR_RENAME_FILE_IN_WAY] = + "CONFLICT (file in way of directory rename)", + [CONFLICT_DIR_RENAME_COLLISION] = "CONFLICT(directory rename collision)", + [CONFLICT_DIR_RENAME_SPLIT] = "CONFLICT(directory rename unclear split)", + + /*** Basic submodule ***/ + [INFO_SUBMODULE_FAST_FORWARDING] = "Fast forwarding submodule", + [CONFLICT_SUBMODULE_FAILED_TO_MERGE] = "CONFLICT (submodule)", + + /*** Special submodule cases broken out from FAILED_TO_MERGE ***/ + [CONFLICT_SUBMODULE_FAILED_TO_MERGE_BUT_POSSIBLE_RESOLUTION] = + "CONFLICT (submodule with possible resolution)", + [CONFLICT_SUBMODULE_NOT_INITIALIZED] = + "CONFLICT (submodule not initialized)", + [CONFLICT_SUBMODULE_HISTORY_NOT_AVAILABLE] = + "CONFLICT (submodule history not available)", + [CONFLICT_SUBMODULE_MAY_HAVE_REWINDS] = + "CONFLICT (submodule may have rewinds)", + [CONFLICT_SUBMODULE_NULL_MERGE_BASE] = + "CONFLICT (submodule lacks merge base)", + [CONFLICT_SUBMODULE_CORRUPT] = + "CONFLICT (submodule corrupt)" +}; + +struct logical_conflict_info { + enum conflict_and_info_types type; + struct strvec paths; +}; + /*** Function Grouping: various utility functions ***/ /* @@ -446,60 +643,47 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti, { struct rename_info *renames = &opti->renames; int i; - void (*strmap_func)(struct strmap *, int) = + void (*strmap_clear_func)(struct strmap *, int) = reinitialize ? strmap_partial_clear : strmap_clear; - void (*strintmap_func)(struct strintmap *) = + void (*strintmap_clear_func)(struct strintmap *) = reinitialize ? strintmap_partial_clear : strintmap_clear; - void (*strset_func)(struct strset *) = + void (*strset_clear_func)(struct strset *) = reinitialize ? strset_partial_clear : strset_clear; - /* - * We marked opti->paths with strdup_strings = 0, so that we - * wouldn't have to make another copy of the fullpath created by - * make_traverse_path from setup_path_info(). But, now that we've - * used it and have no other references to these strings, it is time - * to deallocate them. - */ - free_strmap_strings(&opti->paths); - strmap_func(&opti->paths, 1); + strmap_clear_func(&opti->paths, 0); /* * All keys and values in opti->conflicted are a subset of those in * opti->paths. We don't want to deallocate anything twice, so we * don't free the keys and we pass 0 for free_values. */ - strmap_func(&opti->conflicted, 0); - - /* - * opti->paths_to_free is similar to opti->paths; we created it with - * strdup_strings = 0 to avoid making _another_ copy of the fullpath - * but now that we've used it and have no other references to these - * strings, it is time to deallocate them. We do so by temporarily - * setting strdup_strings to 1. - */ - opti->paths_to_free.strdup_strings = 1; - string_list_clear(&opti->paths_to_free, 0); - opti->paths_to_free.strdup_strings = 0; + strmap_clear_func(&opti->conflicted, 0); if (opti->attr_index.cache_nr) /* true iff opt->renormalize */ discard_index(&opti->attr_index); /* Free memory used by various renames maps */ for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) { - strintmap_func(&renames->dirs_removed[i]); - strmap_func(&renames->dir_renames[i], 0); - strintmap_func(&renames->relevant_sources[i]); + strintmap_clear_func(&renames->dirs_removed[i]); + strmap_clear_func(&renames->dir_renames[i], 0); + strintmap_clear_func(&renames->relevant_sources[i]); if (!reinitialize) assert(renames->cached_pairs_valid_side == 0); - if (i != renames->cached_pairs_valid_side) { - strset_func(&renames->cached_target_names[i]); - strmap_func(&renames->cached_pairs[i], 1); - strset_func(&renames->cached_irrelevant[i]); + if (i != renames->cached_pairs_valid_side && + -1 != renames->cached_pairs_valid_side) { + strset_clear_func(&renames->cached_target_names[i]); + strmap_clear_func(&renames->cached_pairs[i], 1); + strset_clear_func(&renames->cached_irrelevant[i]); partial_clear_dir_rename_count(&renames->dir_rename_count[i]); if (!reinitialize) strmap_clear(&renames->dir_rename_count[i], 1); } } + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) { + strintmap_clear_func(&renames->deferred[i].possible_trivial_merges); + strset_clear_func(&renames->deferred[i].target_dirs); + renames->deferred[i].trivial_merges_okay = 1; /* 1 == maybe */ + } renames->cached_pairs_valid_side = 0; renames->dir_rename_mask = 0; @@ -508,45 +692,40 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti, struct strmap_entry *e; /* Release and free each strbuf found in output */ - strmap_for_each_entry(&opti->output, &iter, e) { - struct strbuf *sb = e->value; - strbuf_release(sb); + strmap_for_each_entry(&opti->conflicts, &iter, e) { + struct string_list *list = e->value; + for (int i = 0; i < list->nr; i++) { + struct logical_conflict_info *info = + list->items[i].util; + strvec_clear(&info->paths); + } /* - * While strictly speaking we don't need to free(sb) - * here because we could pass free_values=1 when - * calling strmap_clear() on opti->output, that would - * require strmap_clear to do another - * strmap_for_each_entry() loop, so we just free it - * while we're iterating anyway. + * While strictly speaking we don't need to + * free(conflicts) here because we could pass + * free_values=1 when calling strmap_clear() on + * opti->conflicts, that would require strmap_clear + * to do another strmap_for_each_entry() loop, so we + * just free it while we're iterating anyway. */ - free(sb); + string_list_clear(list, 1); + free(list); } - strmap_clear(&opti->output, 0); + strmap_clear(&opti->conflicts, 0); } + mem_pool_discard(&opti->pool, 0); + + string_list_clear_func(&opti->conflicted_submodules, + conflicted_submodule_item_free); + /* Clean out callback_data as well. */ FREE_AND_NULL(renames->callback_data); renames->callback_data_nr = renames->callback_data_alloc = 0; } -static int err(struct merge_options *opt, const char *err, ...) -{ - va_list params; - struct strbuf sb = STRBUF_INIT; - - strbuf_addstr(&sb, "error: "); - va_start(params, err); - strbuf_vaddf(&sb, err, params); - va_end(params); - - error("%s", sb.buf); - strbuf_release(&sb); - - return -1; -} - static void format_commit(struct strbuf *sb, int indent, + struct repository *repo, struct commit *commit) { struct merge_remote_desc *desc; @@ -560,29 +739,127 @@ static void format_commit(struct strbuf *sb, return; } - format_commit_message(commit, "%h %s", sb, &ctx); + repo_format_commit_message(repo, commit, "%h %s", sb, &ctx); strbuf_addch(sb, '\n'); } -__attribute__((format (printf, 4, 5))) +__attribute__((format (printf, 8, 9))) static void path_msg(struct merge_options *opt, - const char *path, + enum conflict_and_info_types type, int omittable_hint, /* skippable under --remerge-diff */ + const char *primary_path, + const char *other_path_1, /* may be NULL */ + const char *other_path_2, /* may be NULL */ + struct string_list *other_paths, /* may be NULL */ const char *fmt, ...) { va_list ap; - struct strbuf *sb = strmap_get(&opt->priv->output, path); - if (!sb) { - sb = xmalloc(sizeof(*sb)); - strbuf_init(sb, 0); - strmap_put(&opt->priv->output, path, sb); + struct string_list *path_conflicts; + struct logical_conflict_info *info; + struct strbuf buf = STRBUF_INIT; + struct strbuf *dest; + struct strbuf tmp = STRBUF_INIT; + + /* Sanity checks */ + assert(omittable_hint == + !starts_with(type_short_descriptions[type], "CONFLICT") || + type == CONFLICT_DIR_RENAME_SUGGESTED); + if (opt->record_conflict_msgs_as_headers && omittable_hint) + return; /* Do not record mere hints in headers */ + if (opt->priv->call_depth && opt->verbosity < 5) + return; /* Ignore messages from inner merges */ + + /* Ensure path_conflicts (ptr to array of logical_conflict) allocated */ + path_conflicts = strmap_get(&opt->priv->conflicts, primary_path); + if (!path_conflicts) { + path_conflicts = xmalloc(sizeof(*path_conflicts)); + string_list_init_dup(path_conflicts); + strmap_put(&opt->priv->conflicts, primary_path, path_conflicts); } + /* Add a logical_conflict at the end to store info from this call */ + info = xcalloc(1, sizeof(*info)); + info->type = type; + strvec_init(&info->paths); + + /* Handle the list of paths */ + strvec_push(&info->paths, primary_path); + if (other_path_1) + strvec_push(&info->paths, other_path_1); + if (other_path_2) + strvec_push(&info->paths, other_path_2); + if (other_paths) + for (int i = 0; i < other_paths->nr; i++) + strvec_push(&info->paths, other_paths->items[i].string); + + /* Handle message and its format, in normal case */ + dest = (opt->record_conflict_msgs_as_headers ? &tmp : &buf); + va_start(ap, fmt); - strbuf_vaddf(sb, fmt, ap); + if (opt->priv->call_depth) { + strbuf_addchars(dest, ' ', 2); + strbuf_addstr(dest, "From inner merge:"); + strbuf_addchars(dest, ' ', opt->priv->call_depth * 2); + } + strbuf_vaddf(dest, fmt, ap); va_end(ap); - strbuf_addch(sb, '\n'); + /* Handle specialized formatting of message under --remerge-diff */ + if (opt->record_conflict_msgs_as_headers) { + int i_sb = 0, i_tmp = 0; + + /* Start with the specified prefix */ + if (opt->msg_header_prefix) + strbuf_addf(&buf, "%s ", opt->msg_header_prefix); + + /* Copy tmp to sb, adding spaces after newlines */ + strbuf_grow(&buf, buf.len + 2*tmp.len); /* more than sufficient */ + for (; i_tmp < tmp.len; i_tmp++, i_sb++) { + /* Copy next character from tmp to sb */ + buf.buf[buf.len + i_sb] = tmp.buf[i_tmp]; + + /* If we copied a newline, add a space */ + if (tmp.buf[i_tmp] == '\n') + buf.buf[++i_sb] = ' '; + } + /* Update length and ensure it's NUL-terminated */ + buf.len += i_sb; + buf.buf[buf.len] = '\0'; + + strbuf_release(&tmp); + } + string_list_append_nodup(path_conflicts, strbuf_detach(&buf, NULL)) + ->util = info; +} + +static struct diff_filespec *pool_alloc_filespec(struct mem_pool *pool, + const char *path) +{ + /* Similar to alloc_filespec(), but allocate from pool and reuse path */ + struct diff_filespec *spec; + + spec = mem_pool_calloc(pool, 1, sizeof(*spec)); + spec->path = (char*)path; /* spec won't modify it */ + + spec->count = 1; + spec->is_binary = -1; + return spec; +} + +static struct diff_filepair *pool_diff_queue(struct mem_pool *pool, + struct diff_queue_struct *queue, + struct diff_filespec *one, + struct diff_filespec *two) +{ + /* Same code as diff_queue(), except allocate from pool */ + struct diff_filepair *dp; + + dp = mem_pool_calloc(pool, 1, sizeof(*dp)); + dp->one = one; + dp->two = two; + if (queue) + diff_q(queue, dp); + return dp; } /* add a string to a strbuf, but converting "/" to "_" */ @@ -595,13 +872,15 @@ static void add_flattened_path(struct strbuf *out, const char *s) out->buf[i] = '_'; } -static char *unique_path(struct strmap *existing_paths, +static char *unique_path(struct merge_options *opt, const char *path, const char *branch) { + char *ret = NULL; struct strbuf newpath = STRBUF_INIT; int suffix = 0; size_t base_len; + struct strmap *existing_paths = &opt->priv->paths; strbuf_addf(&newpath, "%s~", path); add_flattened_path(&newpath, branch); @@ -612,7 +891,11 @@ static char *unique_path(struct strmap *existing_paths, strbuf_addf(&newpath, "_%d", suffix++); } - return strbuf_detach(&newpath, NULL); + /* Track the new path in our memory pool */ + ret = mem_pool_alloc(&opt->priv->pool, newpath.len + 1); + memcpy(ret, newpath.buf, newpath.len + 1); + strbuf_release(&newpath); + return ret; } /*** Function Grouping: functions related to collect_merge_info() ***/ @@ -713,8 +996,9 @@ static void setup_path_info(struct merge_options *opt, assert(!df_conflict || !resolved); /* df_conflict implies !resolved */ assert(resolved == (merged_version != NULL)); - mi = xcalloc(1, resolved ? sizeof(struct merged_info) : - sizeof(struct conflict_info)); + mi = mem_pool_calloc(&opt->priv->pool, 1, + resolved ? sizeof(struct merged_info) : + sizeof(struct conflict_info)); mi->directory_name = current_dir_name; mi->basename_offset = current_dir_name_len; mi->clean = !!resolved; @@ -765,6 +1049,7 @@ static void add_pair(struct merge_options *opt, int names_idx = is_add ? side : 0; if (is_add) { + assert(match_mask == 0 || match_mask == 6); if (strset_contains(&renames->cached_target_names[side], pathname)) return; @@ -772,6 +1057,8 @@ static void add_pair(struct merge_options *opt, unsigned content_relevant = (match_mask == 0); unsigned location_relevant = (dir_rename_mask == 0x07); + assert(match_mask == 0 || match_mask == 3 || match_mask == 5); + /* * If pathname is found in cached_irrelevant[side] due to * previous pick but for this commit content is relevant, @@ -808,11 +1095,11 @@ static void add_pair(struct merge_options *opt, return; } - one = alloc_filespec(pathname); - two = alloc_filespec(pathname); + one = pool_alloc_filespec(&opt->priv->pool, pathname); + two = pool_alloc_filespec(&opt->priv->pool, pathname); fill_filespec(is_add ? two : one, &names[names_idx].oid, 1, names[names_idx].mode); - diff_queue(&renames->pairs[side], one, two); + pool_diff_queue(&opt->priv->pool, &renames->pairs[side], one, two); } static void collect_rename_info(struct merge_options *opt, @@ -1003,7 +1290,7 @@ static int collect_merge_info_callback(int n, len = traverse_path_len(info, p->pathlen); /* +1 in both of the following lines to include the NUL byte */ - fullpath = xmalloc(len + 1); + fullpath = mem_pool_alloc(&opt->priv->pool, len + 1); make_traverse_path(fullpath, len + 1, info, p->path, p->pathlen); /* @@ -1014,20 +1301,67 @@ static int collect_merge_info_callback(int n, if (side1_matches_mbase && side2_matches_mbase) { /* mbase, side1, & side2 all match; use mbase as resolution */ setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, - names, names+0, mbase_null, 0, + names, names+0, mbase_null, 0 /* df_conflict */, + filemask, dirmask, 1 /* resolved */); + return mask; + } + + /* + * If the sides match, and all three paths are present and are + * files, then we can take either as the resolution. We can't do + * this with trees, because there may be rename sources from the + * merge_base. + */ + if (sides_match && filemask == 0x07) { + /* use side1 (== side2) version as resolution */ + setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, + names, names+1, side1_null, 0, filemask, dirmask, 1); return mask; } /* - * Gather additional information used in rename detection. + * If side1 matches mbase and all three paths are present and are + * files, then we can use side2 as the resolution. We cannot + * necessarily do so this for trees, because there may be rename + * destinations within side2. + */ + if (side1_matches_mbase && filemask == 0x07) { + /* use side2 version as resolution */ + setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, + names, names+2, side2_null, 0, + filemask, dirmask, 1); + return mask; + } + + /* Similar to above but swapping sides 1 and 2 */ + if (side2_matches_mbase && filemask == 0x07) { + /* use side1 version as resolution */ + setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, + names, names+1, side1_null, 0, + filemask, dirmask, 1); + return mask; + } + + /* + * Sometimes we can tell that a source path need not be included in + * rename detection -- namely, whenever either + * side1_matches_mbase && side2_null + * or + * side2_matches_mbase && side1_null + * However, we call collect_rename_info() even in those cases, + * because exact renames are cheap and would let us remove both a + * source and destination path. We'll cull the unneeded sources + * later. */ collect_rename_info(opt, names, dirname, fullpath, filemask, dirmask, match_mask); /* - * Record information about the path so we can resolve later in - * process_entries. + * None of the special cases above matched, so we have a + * provisional conflict. (Rename detection might allow us to + * unconflict some more cases, but that comes later so all we can + * do now is record the different non-null file hashes.) */ setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, names, NULL, 0, df_conflict, filemask, dirmask, 0); @@ -1042,8 +1376,36 @@ static int collect_merge_info_callback(int n, struct tree_desc t[3]; void *buf[3] = {NULL, NULL, NULL}; const char *original_dir_name; - int i, ret; + int i, ret, side; + /* + * Check for whether we can avoid recursing due to one side + * matching the merge base. The side that does NOT match is + * the one that might have a rename destination we need. + */ + assert(!side1_matches_mbase || !side2_matches_mbase); + side = side1_matches_mbase ? MERGE_SIDE2 : + side2_matches_mbase ? MERGE_SIDE1 : MERGE_BASE; + if (filemask == 0 && (dirmask == 2 || dirmask == 4)) { + /* + * Also defer recursing into new directories; set up a + * few variables to let us do so. + */ + ci->match_mask = (7 - dirmask); + side = dirmask / 2; + } + if (renames->dir_rename_mask != 0x07 && + side != MERGE_BASE && + renames->deferred[side].trivial_merges_okay && + !strset_contains(&renames->deferred[side].target_dirs, + pi.string)) { + strintmap_set(&renames->deferred[side].possible_trivial_merges, + pi.string, renames->dir_rename_mask); + renames->dir_rename_mask = prev_dir_rename_mask; + return mask; + } + + /* We need to recurse */ ci->match_mask &= filemask; newinfo = *info; newinfo.prev = info; @@ -1097,6 +1459,192 @@ static int collect_merge_info_callback(int n, return mask; } +static void resolve_trivial_directory_merge(struct conflict_info *ci, int side) +{ + VERIFY_CI(ci); + assert((side == 1 && ci->match_mask == 5) || + (side == 2 && ci->match_mask == 3)); + oidcpy(&ci->merged.result.oid, &ci->stages[side].oid); + ci->merged.result.mode = ci->stages[side].mode; + ci->merged.is_null = is_null_oid(&ci->stages[side].oid); + ci->match_mask = 0; + ci->merged.clean = 1; /* (ci->filemask == 0); */ +} + +static int handle_deferred_entries(struct merge_options *opt, + struct traverse_info *info) +{ + struct rename_info *renames = &opt->priv->renames; + struct hashmap_iter iter; + struct strmap_entry *entry; + int side, ret = 0; + int path_count_before, path_count_after = 0; + + path_count_before = strmap_get_size(&opt->priv->paths); + for (side = MERGE_SIDE1; side <= MERGE_SIDE2; side++) { + unsigned optimization_okay = 1; + struct strintmap copy; + + /* Loop over the set of paths we need to know rename info for */ + strset_for_each_entry(&renames->relevant_sources[side], + &iter, entry) { + char *rename_target, *dir, *dir_marker; + struct strmap_entry *e; + + /* + * If we don't know delete/rename info for this path, + * then we need to recurse into all trees to get all + * adds to make sure we have it. + */ + if (strset_contains(&renames->cached_irrelevant[side], + entry->key)) + continue; + e = strmap_get_entry(&renames->cached_pairs[side], + entry->key); + if (!e) { + optimization_okay = 0; + break; + } + + /* If this is a delete, we have enough info already */ + rename_target = e->value; + if (!rename_target) + continue; + + /* If we already walked the rename target, we're good */ + if (strmap_contains(&opt->priv->paths, rename_target)) + continue; + + /* + * Otherwise, we need to get a list of directories that + * will need to be recursed into to get this + * rename_target. + */ + dir = xstrdup(rename_target); + while ((dir_marker = strrchr(dir, '/'))) { + *dir_marker = '\0'; + if (strset_contains(&renames->deferred[side].target_dirs, + dir)) + break; + strset_add(&renames->deferred[side].target_dirs, + dir); + } + free(dir); + } + renames->deferred[side].trivial_merges_okay = optimization_okay; + /* + * We need to recurse into any directories in + * possible_trivial_merges[side] found in target_dirs[side]. + * But when we recurse, we may need to queue up some of the + * subdirectories for possible_trivial_merges[side]. Since + * we can't safely iterate through a hashmap while also adding + * entries, move the entries into 'copy', iterate over 'copy', + * and then we'll also iterate anything added into + * possible_trivial_merges[side] once this loop is done. + */ + copy = renames->deferred[side].possible_trivial_merges; + strintmap_init_with_options(&renames->deferred[side].possible_trivial_merges, + 0, + &opt->priv->pool, + 0); + strintmap_for_each_entry(©, &iter, entry) { + const char *path = entry->key; + unsigned dir_rename_mask = (intptr_t)entry->value; + struct conflict_info *ci; + unsigned dirmask; + struct tree_desc t[3]; + void *buf[3] = {NULL,}; + int i; + + ci = strmap_get(&opt->priv->paths, path); + VERIFY_CI(ci); + dirmask = ci->dirmask; + + if (optimization_okay && + !strset_contains(&renames->deferred[side].target_dirs, + path)) { + resolve_trivial_directory_merge(ci, side); + continue; + } + + info->name = path; + info->namelen = strlen(path); + info->pathlen = info->namelen + 1; + + for (i = 0; i < 3; i++, dirmask >>= 1) { + if (i == 1 && ci->match_mask == 3) + t[1] = t[0]; + else if (i == 2 && ci->match_mask == 5) + t[2] = t[0]; + else if (i == 2 && ci->match_mask == 6) + t[2] = t[1]; + else { + const struct object_id *oid = NULL; + if (dirmask & 1) + oid = &ci->stages[i].oid; + buf[i] = fill_tree_descriptor(opt->repo, + t+i, oid); + } + } + + ci->match_mask &= ci->filemask; + opt->priv->current_dir_name = path; + renames->dir_rename_mask = dir_rename_mask; + if (renames->dir_rename_mask == 0 || + renames->dir_rename_mask == 0x07) + ret = traverse_trees(NULL, 3, t, info); + else + ret = traverse_trees_wrapper(NULL, 3, t, info); + + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) + free(buf[i]); + + if (ret < 0) + return ret; + } + strintmap_clear(©); + strintmap_for_each_entry(&renames->deferred[side].possible_trivial_merges, + &iter, entry) { + const char *path = entry->key; + struct conflict_info *ci; + + ci = strmap_get(&opt->priv->paths, path); + VERIFY_CI(ci); + + assert(renames->deferred[side].trivial_merges_okay && + !strset_contains(&renames->deferred[side].target_dirs, + path)); + resolve_trivial_directory_merge(ci, side); + } + if (!optimization_okay || path_count_after) + path_count_after = strmap_get_size(&opt->priv->paths); + } + if (path_count_after) { + /* + * The choice of wanted_factor here does not affect + * correctness, only performance. When the + * path_count_after / path_count_before + * ratio is high, redoing after renames is a big + * performance boost. I suspect that redoing is a wash + * somewhere near a value of 2, and below that redoing will + * slow things down. I applied a fudge factor and picked + * 3; see the commit message when this was introduced for + * back of the envelope calculations for this ratio. + */ + const int wanted_factor = 3; + + /* We should only redo collect_merge_info one time */ + assert(renames->redo_after_renames == 0); + + if (path_count_after / path_count_before >= wanted_factor) { + renames->redo_after_renames = 1; + renames->cached_pairs_valid_side = -1; + } + } else if (renames->redo_after_renames == 2) + renames->redo_after_renames = 0; + return ret; +} + static int collect_merge_info(struct merge_options *opt, struct tree *merge_base, struct tree *side1, @@ -1113,15 +1661,19 @@ static int collect_merge_info(struct merge_options *opt, info.data = opt; info.show_all_errors = 1; - parse_tree(merge_base); - parse_tree(side1); - parse_tree(side2); - init_tree_desc(t + 0, merge_base->buffer, merge_base->size); - init_tree_desc(t + 1, side1->buffer, side1->size); - init_tree_desc(t + 2, side2->buffer, side2->size); + if (parse_tree(merge_base) < 0 || + parse_tree(side1) < 0 || + parse_tree(side2) < 0) + return -1; + init_tree_desc(t + 0, &merge_base->object.oid, + merge_base->buffer, merge_base->size); + init_tree_desc(t + 1, &side1->object.oid, side1->buffer, side1->size); + init_tree_desc(t + 2, &side2->object.oid, side2->buffer, side2->size); trace2_region_enter("merge", "traverse_trees", opt->repo); ret = traverse_trees(NULL, 3, t, &info); + if (ret == 0) + ret = handle_deferred_entries(opt, &info); trace2_region_leave("merge", "traverse_trees", opt->repo); return ret; @@ -1153,7 +1705,6 @@ static int find_first_merges(struct repository *repo, xsnprintf(merged_revision, sizeof(merged_revision), "^%s", oid_to_hex(&a->object.oid)); repo_init_revisions(repo, &revs, NULL); - rev_opts.submodule = path; /* FIXME: can't handle linked worktrees in submodules yet */ revs.single_worktree = path != NULL; setup_revisions(ARRAY_SIZE(rev_args)-1, rev_args, &revs, &rev_opts); @@ -1163,7 +1714,14 @@ static int find_first_merges(struct repository *repo, die("revision walk setup failed"); while ((commit = get_revision(&revs)) != NULL) { struct object *o = &(commit->object); - if (in_merge_bases(b, commit)) + int ret = repo_in_merge_bases(repo, b, commit); + + if (ret < 0) { + object_array_clear(&merges); + release_revisions(&revs); + return ret; + } + if (ret > 0) add_object_array(o, NULL, &merges); } reset_revision_walk(); @@ -1178,9 +1736,17 @@ static int find_first_merges(struct repository *repo, contains_another = 0; for (j = 0; j < merges.nr; j++) { struct commit *m2 = (struct commit *) merges.objects[j].item; - if (i != j && in_merge_bases(m2, m1)) { - contains_another = 1; - break; + if (i != j) { + int ret = repo_in_merge_bases(repo, m2, m1); + if (ret < 0) { + object_array_clear(&merges); + release_revisions(&revs); + return ret; + } + if (ret > 0) { + contains_another = 1; + break; + } } } @@ -1189,6 +1755,7 @@ static int find_first_merges(struct repository *repo, } object_array_clear(&merges); + release_revisions(&revs); return result->nr; } @@ -1199,65 +1766,123 @@ static int merge_submodule(struct merge_options *opt, const struct object_id *b, struct object_id *result) { + struct repository subrepo; + struct strbuf sb = STRBUF_INIT; + int ret = 0, ret2; struct commit *commit_o, *commit_a, *commit_b; int parent_count; struct object_array merges; - struct strbuf sb = STRBUF_INIT; int i; int search = !opt->priv->call_depth; + int sub_not_initialized = 1; + int sub_flag = CONFLICT_SUBMODULE_FAILED_TO_MERGE; /* store fallback answer in result in case we fail */ oidcpy(result, opt->priv->call_depth ? o : a); /* we can not handle deletion conflicts */ - if (is_null_oid(o)) - return 0; - if (is_null_oid(a)) - return 0; - if (is_null_oid(b)) - return 0; + if (is_null_oid(a) || is_null_oid(b)) + BUG("submodule deleted on one side; this should be handled outside of merge_submodule()"); - if (add_submodule_odb(path)) { - path_msg(opt, path, 0, + if ((sub_not_initialized = repo_submodule_init(&subrepo, + opt->repo, path, null_oid()))) { + path_msg(opt, CONFLICT_SUBMODULE_NOT_INITIALIZED, 0, + path, NULL, NULL, NULL, _("Failed to merge submodule %s (not checked out)"), path); - return 0; + sub_flag = CONFLICT_SUBMODULE_NOT_INITIALIZED; + goto cleanup; + } + + if (is_null_oid(o)) { + path_msg(opt, CONFLICT_SUBMODULE_NULL_MERGE_BASE, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s (no merge base)"), + path); + goto cleanup; } - if (!(commit_o = lookup_commit_reference(opt->repo, o)) || - !(commit_a = lookup_commit_reference(opt->repo, a)) || - !(commit_b = lookup_commit_reference(opt->repo, b))) { - path_msg(opt, path, 0, + if (!(commit_o = lookup_commit_reference(&subrepo, o)) || + !(commit_a = lookup_commit_reference(&subrepo, a)) || + !(commit_b = lookup_commit_reference(&subrepo, b))) { + path_msg(opt, CONFLICT_SUBMODULE_HISTORY_NOT_AVAILABLE, 0, + path, NULL, NULL, NULL, _("Failed to merge submodule %s (commits not present)"), path); - return 0; + sub_flag = CONFLICT_SUBMODULE_HISTORY_NOT_AVAILABLE; + goto cleanup; } /* check whether both changes are forward */ - if (!in_merge_bases(commit_o, commit_a) || - !in_merge_bases(commit_o, commit_b)) { - path_msg(opt, path, 0, + ret2 = repo_in_merge_bases(&subrepo, commit_o, commit_a); + if (ret2 < 0) { + path_msg(opt, CONFLICT_SUBMODULE_CORRUPT, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s " + "(repository corrupt)"), + path); + ret = -1; + goto cleanup; + } + if (ret2 > 0) + ret2 = repo_in_merge_bases(&subrepo, commit_o, commit_b); + if (ret2 < 0) { + path_msg(opt, CONFLICT_SUBMODULE_CORRUPT, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s " + "(repository corrupt)"), + path); + ret = -1; + goto cleanup; + } + if (!ret2) { + path_msg(opt, CONFLICT_SUBMODULE_MAY_HAVE_REWINDS, 0, + path, NULL, NULL, NULL, _("Failed to merge submodule %s " "(commits don't follow merge-base)"), path); - return 0; + goto cleanup; } /* Case #1: a is contained in b or vice versa */ - if (in_merge_bases(commit_a, commit_b)) { + ret2 = repo_in_merge_bases(&subrepo, commit_a, commit_b); + if (ret2 < 0) { + path_msg(opt, CONFLICT_SUBMODULE_CORRUPT, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s " + "(repository corrupt)"), + path); + ret = -1; + goto cleanup; + } + if (ret2 > 0) { oidcpy(result, b); - path_msg(opt, path, 1, + path_msg(opt, INFO_SUBMODULE_FAST_FORWARDING, 1, + path, NULL, NULL, NULL, _("Note: Fast-forwarding submodule %s to %s"), path, oid_to_hex(b)); - return 1; + ret = 1; + goto cleanup; } - if (in_merge_bases(commit_b, commit_a)) { + ret2 = repo_in_merge_bases(&subrepo, commit_b, commit_a); + if (ret2 < 0) { + path_msg(opt, CONFLICT_SUBMODULE_CORRUPT, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s " + "(repository corrupt)"), + path); + ret = -1; + goto cleanup; + } + if (ret2 > 0) { oidcpy(result, a); - path_msg(opt, path, 1, + path_msg(opt, INFO_SUBMODULE_FAST_FORWARDING, 1, + path, NULL, NULL, NULL, _("Note: Fast-forwarding submodule %s to %s"), path, oid_to_hex(a)); - return 1; + ret = 1; + goto cleanup; } /* @@ -1269,44 +1894,67 @@ static int merge_submodule(struct merge_options *opt, /* Skip the search if makes no sense to the calling context. */ if (!search) - return 0; + goto cleanup; /* find commit which merges them */ - parent_count = find_first_merges(opt->repo, path, commit_a, commit_b, + parent_count = find_first_merges(&subrepo, path, commit_a, commit_b, &merges); switch (parent_count) { + case -1: + path_msg(opt, CONFLICT_SUBMODULE_CORRUPT, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s " + "(repository corrupt)"), + path); + ret = -1; + break; case 0: - path_msg(opt, path, 0, _("Failed to merge submodule %s"), path); + path_msg(opt, CONFLICT_SUBMODULE_FAILED_TO_MERGE, 0, + path, NULL, NULL, NULL, + _("Failed to merge submodule %s"), path); break; case 1: - format_commit(&sb, 4, + format_commit(&sb, 4, &subrepo, (struct commit *)merges.objects[0].item); - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_SUBMODULE_FAILED_TO_MERGE_BUT_POSSIBLE_RESOLUTION, 0, + path, NULL, NULL, NULL, _("Failed to merge submodule %s, but a possible merge " - "resolution exists:\n%s\n"), + "resolution exists: %s"), path, sb.buf); - path_msg(opt, path, 1, - _("If this is correct simply add it to the index " - "for example\n" - "by using:\n\n" - " git update-index --cacheinfo 160000 %s \"%s\"\n\n" - "which will accept this suggestion.\n"), - oid_to_hex(&merges.objects[0].item->oid), path); strbuf_release(&sb); break; default: for (i = 0; i < merges.nr; i++) - format_commit(&sb, 4, + format_commit(&sb, 4, &subrepo, (struct commit *)merges.objects[i].item); - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_SUBMODULE_FAILED_TO_MERGE_BUT_POSSIBLE_RESOLUTION, 0, + path, NULL, NULL, NULL, _("Failed to merge submodule %s, but multiple " "possible merges exist:\n%s"), path, sb.buf); strbuf_release(&sb); } object_array_clear(&merges); - return 0; +cleanup: + if (!opt->priv->call_depth && !ret) { + struct string_list *csub = &opt->priv->conflicted_submodules; + struct conflicted_submodule_item *util; + const char *abbrev; + + util = xmalloc(sizeof(*util)); + util->flag = sub_flag; + util->abbrev = NULL; + if (!sub_not_initialized) { + abbrev = repo_find_unique_abbrev(&subrepo, b, DEFAULT_ABBREV); + util->abbrev = xstrdup(abbrev); + } + string_list_append(csub, path)->util = util; + } + + if (!sub_not_initialized) + repo_clear(&subrepo); + return ret; } static void initialize_attr_index(struct merge_options *opt) @@ -1321,6 +1969,7 @@ static void initialize_attr_index(struct merge_options *opt) struct index_state *attr_index = &opt->priv->attr_index; struct cache_entry *ce; + attr_index->repo = opt->repo; attr_index->initialized = 1; if (!opt->renormalize) @@ -1376,9 +2025,9 @@ static int merge_3way(struct merge_options *opt, mmbuffer_t *result_buf) { mmfile_t orig, src1, src2; - struct ll_merge_options ll_opts = {0}; + struct ll_merge_options ll_opts = LL_MERGE_OPTIONS_INIT; char *base, *name1, *name2; - int merge_status; + enum ll_merge_result merge_status; if (!opt->priv->attr_index.initialized) initialize_attr_index(opt); @@ -1386,6 +2035,7 @@ static int merge_3way(struct merge_options *opt, ll_opts.renormalize = opt->renormalize; ll_opts.extra_marker_size = extra_marker_size; ll_opts.xdl_opts = opt->xdl_opts; + ll_opts.conflict_style = opt->conflict_style; if (opt->priv->call_depth) { ll_opts.virtual_ancestor = 1; @@ -1422,6 +2072,11 @@ static int merge_3way(struct merge_options *opt, merge_status = ll_merge(result_buf, path, &orig, base, &src1, name1, &src2, name2, &opt->priv->attr_index, &ll_opts); + if (merge_status == LL_MERGE_BINARY_CONFLICT) + path_msg(opt, CONFLICT_BINARY, 0, + path, NULL, NULL, NULL, + "warning: Cannot merge binary files: %s (%s vs. %s)", + path, name1, name2); free(base); free(name1); @@ -1450,7 +2105,7 @@ static int handle_content_merge(struct merge_options *opt, * the three blobs to merge on various sides of history. * * extra_marker_size is the amount to extend conflict markers in - * ll_merge; this is neeed if we have content merges of content + * ll_merge; this is needed if we have content merges of content * merges, which happens for example with rename/rename(2to1) and * rename/add conflicts. */ @@ -1519,19 +2174,19 @@ static int handle_content_merge(struct merge_options *opt, &result_buf); if ((merge_status < 0) || !result_buf.ptr) - ret = err(opt, _("Failed to execute internal merge")); + ret = error(_("failed to execute internal merge")); if (!ret && write_object_file(result_buf.ptr, result_buf.size, - blob_type, &result->oid)) - ret = err(opt, _("Unable to add %s to database"), - path); + OBJ_BLOB, &result->oid)) + ret = error(_("unable to add %s to database"), path); free(result_buf.ptr); if (ret) return -1; clean &= (merge_status == 0); - path_msg(opt, path, 1, _("Auto-merging %s"), path); + path_msg(opt, INFO_AUTO_MERGING, 1, path, NULL, NULL, NULL, + _("Auto-merging %s"), path); } else if (S_ISGITLINK(a->mode)) { int two_way = ((S_IFMT & o->mode) != (S_IFMT & a->mode)); clean = merge_submodule(opt, pathnames[0], @@ -1653,7 +2308,7 @@ static char *handle_path_level_conflicts(struct merge_options *opt, * to ensure that's the case. */ c_info = strmap_get(collisions, new_path); - if (c_info == NULL) + if (!c_info) BUG("c_info is NULL"); /* @@ -1669,21 +2324,24 @@ static char *handle_path_level_conflicts(struct merge_options *opt, c_info->reported_already = 1; strbuf_add_separated_string_list(&collision_paths, ", ", &c_info->source_files); - path_msg(opt, new_path, 0, - _("CONFLICT (implicit dir rename): Existing file/dir " - "at %s in the way of implicit directory rename(s) " - "putting the following path(s) there: %s."), - new_path, collision_paths.buf); + path_msg(opt, CONFLICT_DIR_RENAME_FILE_IN_WAY, 0, + new_path, NULL, NULL, &c_info->source_files, + _("CONFLICT (implicit dir rename): Existing " + "file/dir at %s in the way of implicit " + "directory rename(s) putting the following " + "path(s) there: %s."), + new_path, collision_paths.buf); clean = 0; } else if (c_info->source_files.nr > 1) { c_info->reported_already = 1; strbuf_add_separated_string_list(&collision_paths, ", ", &c_info->source_files); - path_msg(opt, new_path, 0, - _("CONFLICT (implicit dir rename): Cannot map more " - "than one path to %s; implicit directory renames " - "tried to put these paths there: %s"), - new_path, collision_paths.buf); + path_msg(opt, CONFLICT_DIR_RENAME_COLLISION, 0, + new_path, NULL, NULL, &c_info->source_files, + _("CONFLICT (implicit dir rename): Cannot map " + "more than one path to %s; implicit directory " + "renames tried to put these paths there: %s"), + new_path, collision_paths.buf); clean = 0; } @@ -1737,13 +2395,14 @@ static void get_provisional_directory_renames(struct merge_options *opt, continue; if (bad_max == max) { - path_msg(opt, source_dir, 0, - _("CONFLICT (directory rename split): " - "Unclear where to rename %s to; it was " - "renamed to multiple other directories, with " - "no destination getting a majority of the " - "files."), - source_dir); + path_msg(opt, CONFLICT_DIR_RENAME_SPLIT, 0, + source_dir, NULL, NULL, NULL, + _("CONFLICT (directory rename split): " + "Unclear where to rename %s to; it was " + "renamed to multiple other directories, " + "with no destination getting a majority of " + "the files."), + source_dir); *clean = 0; } else { strmap_put(&renames->dir_renames[side], @@ -1836,7 +2495,7 @@ static void compute_collisions(struct strmap *collisions, free(new_path); } else { CALLOC_ARRAY(collision_info, 1); - string_list_init(&collision_info->source_files, 0); + string_list_init_nodup(&collision_info->source_files); strmap_put(collisions, new_path, collision_info); } string_list_insert(&collision_info->source_files, @@ -1844,6 +2503,27 @@ static void compute_collisions(struct strmap *collisions, } } +static void free_collisions(struct strmap *collisions) +{ + struct hashmap_iter iter; + struct strmap_entry *entry; + + /* Free each value in the collisions map */ + strmap_for_each_entry(collisions, &iter, entry) { + struct collision_info *info = entry->value; + string_list_clear(&info->source_files, 0); + } + /* + * In compute_collisions(), we set collisions.strdup_strings to 0 + * so that we wouldn't have to make another copy of the new_path + * allocated by apply_dir_rename(). But now that we've used them + * and have no other references to these strings, it is time to + * deallocate them. + */ + free_strmap_strings(collisions); + strmap_clear(collisions, 1); +} + static char *check_for_directory_rename(struct merge_options *opt, const char *path, unsigned side_index, @@ -1852,18 +2532,23 @@ static char *check_for_directory_rename(struct merge_options *opt, struct strmap *collisions, int *clean_merge) { - char *new_path = NULL; + char *new_path; struct strmap_entry *rename_info; - struct strmap_entry *otherinfo = NULL; + struct strmap_entry *otherinfo; const char *new_dir; + int other_side = 3 - side_index; + /* + * Cases where we don't have or don't want a directory rename for + * this path. + */ if (strmap_empty(dir_renames)) - return new_path; + return NULL; + if (strmap_get(&collisions[other_side], path)) + return NULL; rename_info = check_dir_renamed(path, dir_renames); if (!rename_info) - return new_path; - /* old_dir = rename_info->key; */ - new_dir = rename_info->value; + return NULL; /* * This next part is a little weird. We do not want to do an @@ -1889,9 +2574,11 @@ static char *check_for_directory_rename(struct merge_options *opt, * As it turns out, this also prevents N-way transient rename * confusion; See testcases 9c and 9d of t6043. */ + new_dir = rename_info->value; /* old_dir = rename_info->key; */ otherinfo = strmap_get_entry(dir_rename_exclusions, new_dir); if (otherinfo) { - path_msg(opt, rename_info->key, 1, + path_msg(opt, INFO_DIR_RENAME_SKIPPED_DUE_TO_RERENAME, 1, + rename_info->key, path, new_dir, NULL, _("WARNING: Avoiding applying %s -> %s rename " "to %s, because %s itself was renamed."), rename_info->key, new_dir, path, new_dir); @@ -1899,7 +2586,8 @@ static char *check_for_directory_rename(struct merge_options *opt, } new_path = handle_path_level_conflicts(opt, path, side_index, - rename_info, collisions); + rename_info, + &collisions[side_index]); *clean_merge &= (new_path != NULL); return new_path; @@ -1947,12 +2635,17 @@ static void apply_directory_rename_modifications(struct merge_options *opt, VERIFY_CI(ci); /* Find parent directories missing from opt->priv->paths */ - cur_path = new_path; + cur_path = mem_pool_strdup(&opt->priv->pool, new_path); + free((char*)new_path); + new_path = (char *)cur_path; + while (1) { /* Find the parent directory of cur_path */ char *last_slash = strrchr(cur_path, '/'); if (last_slash) { - parent_name = xstrndup(cur_path, last_slash - cur_path); + parent_name = mem_pool_strndup(&opt->priv->pool, + cur_path, + last_slash - cur_path); } else { parent_name = opt->priv->toplevel_dir; break; @@ -1961,7 +2654,6 @@ static void apply_directory_rename_modifications(struct merge_options *opt, /* Look it up in opt->priv->paths */ entry = strmap_get_entry(&opt->priv->paths, parent_name); if (entry) { - free((char*)parent_name); parent_name = entry->key; /* reuse known pointer */ break; } @@ -1988,16 +2680,41 @@ static void apply_directory_rename_modifications(struct merge_options *opt, parent_name = cur_dir; } - /* - * We are removing old_path from opt->priv->paths. old_path also will - * eventually need to be freed, but it may still be used by e.g. - * ci->pathnames. So, store it in another string-list for now. - */ - string_list_append(&opt->priv->paths_to_free, old_path); - assert(ci->filemask == 2 || ci->filemask == 4); - assert(ci->dirmask == 0); - strmap_remove(&opt->priv->paths, old_path, 0); + assert(ci->dirmask == 0 || ci->dirmask == 1); + if (ci->dirmask == 0) + strmap_remove(&opt->priv->paths, old_path, 0); + else { + /* + * This file exists on one side, but we still had a directory + * at the old location that we can't remove until after + * processing all paths below it. So, make a copy of ci in + * new_ci and only put the file information into it. + */ + new_ci = mem_pool_calloc(&opt->priv->pool, 1, sizeof(*new_ci)); + memcpy(new_ci, ci, sizeof(*ci)); + assert(!new_ci->match_mask); + new_ci->dirmask = 0; + new_ci->stages[1].mode = 0; + oidcpy(&new_ci->stages[1].oid, null_oid()); + + /* + * Now that we have the file information in new_ci, make sure + * ci only has the directory information. + */ + ci->filemask = 0; + ci->merged.clean = 1; + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + if (ci->dirmask & (1 << i)) + continue; + /* zero out any entries related to files */ + ci->stages[i].mode = 0; + oidcpy(&ci->stages[i].oid, null_oid()); + } + + /* Now we want to focus on new_ci, so reassign ci to it. */ + ci = new_ci; + } branch_with_new_path = (ci->filemask == 2) ? opt->branch1 : opt->branch2; branch_with_dir_rename = (ci->filemask == 2) ? opt->branch2 : opt->branch1; @@ -2028,21 +2745,22 @@ static void apply_directory_rename_modifications(struct merge_options *opt, new_ci->stages[index].mode = ci->stages[index].mode; oidcpy(&new_ci->stages[index].oid, &ci->stages[index].oid); - free(ci); ci = new_ci; } if (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE) { /* Notify user of updated path */ if (pair->status == 'A') - path_msg(opt, new_path, 1, + path_msg(opt, INFO_DIR_RENAME_APPLIED, 1, + new_path, old_path, NULL, NULL, _("Path updated: %s added in %s inside a " "directory that was renamed in %s; moving " "it to %s."), old_path, branch_with_new_path, branch_with_dir_rename, new_path); else - path_msg(opt, new_path, 1, + path_msg(opt, INFO_DIR_RENAME_APPLIED, 1, + new_path, old_path, NULL, NULL, _("Path updated: %s renamed to %s in %s, " "inside a directory that was renamed in %s; " "moving it to %s."), @@ -2055,7 +2773,8 @@ static void apply_directory_rename_modifications(struct merge_options *opt, */ ci->path_conflict = 1; if (pair->status == 'A') - path_msg(opt, new_path, 0, + path_msg(opt, CONFLICT_DIR_RENAME_SUGGESTED, 1, + new_path, old_path, NULL, NULL, _("CONFLICT (file location): %s added in %s " "inside a directory that was renamed in %s, " "suggesting it should perhaps be moved to " @@ -2063,7 +2782,8 @@ static void apply_directory_rename_modifications(struct merge_options *opt, old_path, branch_with_new_path, branch_with_dir_rename, new_path); else - path_msg(opt, new_path, 0, + path_msg(opt, CONFLICT_DIR_RENAME_SUGGESTED, 1, + new_path, old_path, NULL, NULL, _("CONFLICT (file location): %s renamed to %s " "in %s, inside a directory that was renamed " "in %s, suggesting it should perhaps be " @@ -2181,6 +2901,8 @@ static int process_renames(struct merge_options *opt, pathnames, 1 + 2 * opt->priv->call_depth, &merged); + if (clean_merge < 0) + return -1; if (!clean_merge && merged.mode == side1->stages[1].mode && oideq(&merged.oid, &side1->stages[1].oid)) @@ -2219,7 +2941,8 @@ static int process_renames(struct merge_options *opt, * and remove the setting of base->path_conflict to 1. */ base->path_conflict = 1; - path_msg(opt, oldpath, 0, + path_msg(opt, CONFLICT_RENAME_RENAME, 0, + pathnames[0], pathnames[1], pathnames[2], NULL, _("CONFLICT (rename/rename): %s renamed to " "%s in %s and to %s in %s."), pathnames[0], @@ -2289,7 +3012,7 @@ static int process_renames(struct merge_options *opt, struct version_info merged; struct conflict_info *base, *side1, *side2; - unsigned clean; + int clean; pathnames[0] = oldpath; pathnames[other_source_index] = oldpath; @@ -2310,11 +3033,14 @@ static int process_renames(struct merge_options *opt, pathnames, 1 + 2 * opt->priv->call_depth, &merged); + if (clean < 0) + return -1; memcpy(&newinfo->stages[target_index], &merged, sizeof(merged)); if (!clean) { - path_msg(opt, newpath, 0, + path_msg(opt, CONFLICT_RENAME_COLLIDES, 0, + newpath, oldpath, NULL, NULL, _("CONFLICT (rename involved in " "collision): rename of %s -> %s has " "content conflicts AND collides " @@ -2333,7 +3059,8 @@ static int process_renames(struct merge_options *opt, */ newinfo->path_conflict = 1; - path_msg(opt, newpath, 0, + path_msg(opt, CONFLICT_RENAME_DELETE, 0, + newpath, oldpath, NULL, NULL, _("CONFLICT (rename/delete): %s renamed " "to %s in %s, but deleted in %s."), oldpath, newpath, rename_branch, delete_branch); @@ -2357,7 +3084,8 @@ static int process_renames(struct merge_options *opt, } else if (source_deleted) { /* rename/delete */ newinfo->path_conflict = 1; - path_msg(opt, newpath, 0, + path_msg(opt, CONFLICT_RENAME_DELETE, 0, + newpath, oldpath, NULL, NULL, _("CONFLICT (rename/delete): %s renamed" " to %s in %s, but deleted in %s."), oldpath, newpath, @@ -2456,10 +3184,23 @@ static void use_cached_pairs(struct merge_options *opt, if (!new_name) new_name = old_name; + /* + * cached_pairs has *copies* of old_name and new_name, + * because it has to persist across merges. Since + * pool_alloc_filespec() will just re-use the existing + * filenames, which will also get re-used by + * opt->priv->paths if they become renames, and then + * get freed at the end of the merge, that would leave + * the copy in cached_pairs dangling. Avoid this by + * making a copy here. + */ + old_name = mem_pool_strdup(&opt->priv->pool, old_name); + new_name = mem_pool_strdup(&opt->priv->pool, new_name); + /* We don't care about oid/mode, only filenames and status */ - one = alloc_filespec(old_name); - two = alloc_filespec(new_name); - diff_queue(pairs, one, two); + one = pool_alloc_filespec(&opt->priv->pool, old_name); + two = pool_alloc_filespec(&opt->priv->pool, new_name); + pool_diff_queue(&opt->priv->pool, pairs, one, two); pairs->queue[pairs->nr-1]->status = entry->value ? 'R' : 'D'; } } @@ -2533,9 +3274,9 @@ static int compare_pairs(const void *a_, const void *b_) return strcmp(a->one->path, b->one->path); } -/* Call diffcore_rename() to compute which files have changed on given side */ -static void detect_regular_renames(struct merge_options *opt, - unsigned side_index) +/* Call diffcore_rename() to update deleted/added pairs into rename pairs */ +static int detect_regular_renames(struct merge_options *opt, + unsigned side_index) { struct diff_options diff_opts; struct rename_info *renames = &opt->priv->renames; @@ -2548,7 +3289,7 @@ static void detect_regular_renames(struct merge_options *opt, * side had directory renames. */ resolve_diffpair_statuses(&renames->pairs[side_index]); - return; + return 0; } partial_clear_dir_rename_count(&renames->dir_rename_count[side_index]); @@ -2558,7 +3299,7 @@ static void detect_regular_renames(struct merge_options *opt, diff_opts.detect_rename = DIFF_DETECT_RENAME; diff_opts.rename_limit = opt->rename_limit; if (opt->rename_limit <= 0) - diff_opts.rename_limit = 1000; + diff_opts.rename_limit = 7000; diff_opts.rename_score = opt->rename_score; diff_opts.show_rename_progress = opt->show_rename_progress; diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; @@ -2567,6 +3308,7 @@ static void detect_regular_renames(struct merge_options *opt, diff_queued_diff = renames->pairs[side_index]; trace2_region_enter("diff", "diffcore_rename", opt->repo); diffcore_rename_extended(&diff_opts, + &opt->priv->pool, &renames->relevant_sources[side_index], &renames->dirs_removed[side_index], &renames->dir_rename_count[side_index], @@ -2574,6 +3316,8 @@ static void detect_regular_renames(struct merge_options *opt, trace2_region_leave("diff", "diffcore_rename", opt->repo); resolve_diffpair_statuses(&diff_queued_diff); + if (diff_opts.needed_rename_limit > 0) + renames->redo_after_renames = 0; if (diff_opts.needed_rename_limit > renames->needed_limit) renames->needed_limit = diff_opts.needed_rename_limit; @@ -2583,27 +3327,28 @@ static void detect_regular_renames(struct merge_options *opt, diff_queued_diff.nr = 0; diff_queued_diff.queue = NULL; diff_flush(&diff_opts); + + return 1; } /* - * Get information of all renames which occurred in 'side_pairs', discarding - * non-renames. + * Get information of all renames which occurred in 'side_pairs', making use + * of any implicit directory renames in side_dir_renames (also making use of + * implicit directory renames rename_exclusions as needed by + * check_for_directory_rename()). Add all (updated) renames into result. */ static int collect_renames(struct merge_options *opt, struct diff_queue_struct *result, unsigned side_index, + struct strmap *collisions, struct strmap *dir_renames_for_side, struct strmap *rename_exclusions) { int i, clean = 1; - struct strmap collisions; struct diff_queue_struct *side_pairs; - struct hashmap_iter iter; - struct strmap_entry *entry; struct rename_info *renames = &opt->priv->renames; side_pairs = &renames->pairs[side_index]; - compute_collisions(&collisions, dir_renames_for_side, side_pairs); for (i = 0; i < side_pairs->nr; ++i) { struct diff_filepair *p = side_pairs->queue[i]; @@ -2611,7 +3356,7 @@ static int collect_renames(struct merge_options *opt, if (p->status != 'A' && p->status != 'R') { possibly_cache_new_pair(renames, p, side_index, NULL); - diff_free_filepair(p); + pool_diff_free_filepair(&opt->priv->pool, p); continue; } @@ -2619,12 +3364,12 @@ static int collect_renames(struct merge_options *opt, side_index, dir_renames_for_side, rename_exclusions, - &collisions, + collisions, &clean); possibly_cache_new_pair(renames, p, side_index, new_path); if (p->status != 'R' && !new_path) { - diff_free_filepair(p); + pool_diff_free_filepair(&opt->priv->pool, p); continue; } @@ -2645,39 +3390,44 @@ static int collect_renames(struct merge_options *opt, result->queue[result->nr++] = p; } - /* Free each value in the collisions map */ - strmap_for_each_entry(&collisions, &iter, entry) { - struct collision_info *info = entry->value; - string_list_clear(&info->source_files, 0); - } - /* - * In compute_collisions(), we set collisions.strdup_strings to 0 - * so that we wouldn't have to make another copy of the new_path - * allocated by apply_dir_rename(). But now that we've used them - * and have no other references to these strings, it is time to - * deallocate them. - */ - free_strmap_strings(&collisions); - strmap_clear(&collisions, 1); return clean; } -static int detect_and_process_renames(struct merge_options *opt, - struct tree *merge_base, - struct tree *side1, - struct tree *side2) +static int detect_and_process_renames(struct merge_options *opt) { - struct diff_queue_struct combined; + struct diff_queue_struct combined = { 0 }; struct rename_info *renames = &opt->priv->renames; - int need_dir_renames, s, clean = 1; + struct strmap collisions[3]; + int need_dir_renames, s, i, clean = 1; + unsigned detection_run = 0; - memset(&combined, 0, sizeof(combined)); if (!possible_renames(renames)) goto cleanup; trace2_region_enter("merge", "regular renames", opt->repo); - detect_regular_renames(opt, MERGE_SIDE1); - detect_regular_renames(opt, MERGE_SIDE2); + detection_run |= detect_regular_renames(opt, MERGE_SIDE1); + detection_run |= detect_regular_renames(opt, MERGE_SIDE2); + if (renames->needed_limit) { + renames->cached_pairs_valid_side = 0; + renames->redo_after_renames = 0; + } + if (renames->redo_after_renames && detection_run) { + int i, side; + struct diff_filepair *p; + + /* Cache the renames, we found */ + for (side = MERGE_SIDE1; side <= MERGE_SIDE2; side++) { + for (i = 0; i < renames->pairs[side].nr; ++i) { + p = renames->pairs[side].queue[i]; + possibly_cache_new_pair(renames, p, side, NULL); + } + } + + /* Restart the merge with the cached renames */ + renames->redo_after_renames = 2; + trace2_region_leave("merge", "regular renames", opt->repo); + goto cleanup; + } use_cached_pairs(opt, &renames->cached_pairs[1], &renames->pairs[1]); use_cached_pairs(opt, &renames->cached_pairs[2], &renames->pairs[2]); trace2_region_leave("merge", "regular renames", opt->repo); @@ -2697,12 +3447,22 @@ static int detect_and_process_renames(struct merge_options *opt, ALLOC_GROW(combined.queue, renames->pairs[1].nr + renames->pairs[2].nr, combined.alloc); + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) { + int other_side = 3 - i; + compute_collisions(&collisions[i], + &renames->dir_renames[other_side], + &renames->pairs[i]); + } clean &= collect_renames(opt, &combined, MERGE_SIDE1, + collisions, &renames->dir_renames[2], &renames->dir_renames[1]); clean &= collect_renames(opt, &combined, MERGE_SIDE2, + collisions, &renames->dir_renames[1], &renames->dir_renames[2]); + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) + free_collisions(&collisions[i]); STABLE_QSORT(combined.queue, combined.nr, compare_pairs); trace2_region_leave("merge", "directory renames", opt->repo); @@ -2724,7 +3484,7 @@ cleanup: side_pairs = &renames->pairs[s]; for (i = 0; i < side_pairs->nr; ++i) { struct diff_filepair *p = side_pairs->queue[i]; - diff_free_filepair(p); + pool_diff_free_filepair(&opt->priv->pool, p); } } @@ -2734,58 +3494,81 @@ simple_cleanup: free(renames->pairs[s].queue); DIFF_QUEUE_CLEAR(&renames->pairs[s]); } - if (combined.nr) { - int i; - for (i = 0; i < combined.nr; i++) - diff_free_filepair(combined.queue[i]); - free(combined.queue); - } + for (i = 0; i < combined.nr; i++) + pool_diff_free_filepair(&opt->priv->pool, combined.queue[i]); + free(combined.queue); return clean; } /*** Function Grouping: functions related to process_entries() ***/ -static int string_list_df_name_compare(const char *one, const char *two) +static int sort_dirs_next_to_their_children(const char *one, const char *two) { - int onelen = strlen(one); - int twolen = strlen(two); + unsigned char c1, c2; + /* - * Here we only care that entries for D/F conflicts are - * adjacent, in particular with the file of the D/F conflict - * appearing before files below the corresponding directory. - * The order of the rest of the list is irrelevant for us. + * Here we only care that entries for directories appear adjacent + * to and before files underneath the directory. We can achieve + * that by pretending to add a trailing slash to every file and + * then sorting. In other words, we do not want the natural + * sorting of + * foo + * foo.txt + * foo/bar + * Instead, we want "foo" to sort as though it were "foo/", so that + * we instead get + * foo.txt + * foo + * foo/bar + * To achieve this, we basically implement our own strcmp, except that + * if we get to the end of either string instead of comparing NUL to + * another character, we compare '/' to it. + * + * If this unusual "sort as though '/' were appended" perplexes + * you, perhaps it will help to note that this is not the final + * sort. write_tree() will sort again without the trailing slash + * magic, but just on paths immediately under a given tree. * - * To achieve this, we sort with df_name_compare and provide - * the mode S_IFDIR so that D/F conflicts will sort correctly. - * We use the mode S_IFDIR for everything else for simplicity, - * since in other cases any changes in their order due to - * sorting cause no problems for us. + * The reason to not use df_name_compare directly was that it was + * just too expensive (we don't have the string lengths handy), so + * it was reimplemented. */ - int cmp = df_name_compare(one, onelen, S_IFDIR, - two, twolen, S_IFDIR); + /* - * Now that 'foo' and 'foo/bar' compare equal, we have to make sure - * that 'foo' comes before 'foo/bar'. + * NOTE: This function will never be called with two equal strings, + * because it is used to sort the keys of a strmap, and strmaps have + * unique keys by construction. That simplifies our c1==c2 handling + * below. */ - if (cmp) - return cmp; - return onelen - twolen; + + while (*one && (*one == *two)) { + one++; + two++; + } + + c1 = *one ? *one : '/'; + c2 = *two ? *two : '/'; + + if (c1 == c2) { + /* Getting here means one is a leading directory of the other */ + return (*one) ? 1 : -1; + } else + return c1 - c2; } -static int read_oid_strbuf(struct merge_options *opt, - const struct object_id *oid, +static int read_oid_strbuf(const struct object_id *oid, struct strbuf *dst) { void *buf; enum object_type type; unsigned long size; - buf = read_object_file(oid, &type, &size); + buf = repo_read_object_file(the_repository, oid, &type, &size); if (!buf) - return err(opt, _("cannot read object %s"), oid_to_hex(oid)); + return error(_("cannot read object %s"), oid_to_hex(oid)); if (type != OBJ_BLOB) { free(buf); - return err(opt, _("object %s is not a blob"), oid_to_hex(oid)); + return error(_("object %s is not a blob"), oid_to_hex(oid)); } strbuf_attach(dst, buf, size, size + 1); return 0; @@ -2809,8 +3592,8 @@ static int blob_unchanged(struct merge_options *opt, if (oideq(&base->oid, &side->oid)) return 1; - if (read_oid_strbuf(opt, &base->oid, &basebuf) || - read_oid_strbuf(opt, &side->oid, &sidebuf)) + if (read_oid_strbuf(&base->oid, &basebuf) || + read_oid_strbuf(&side->oid, &sidebuf)) goto error_return; /* * Note: binary | is used so that both renormalizations are @@ -2882,15 +3665,15 @@ static int tree_entry_order(const void *a_, const void *b_) b->string, strlen(b->string), bmi->result.mode); } -static void write_tree(struct object_id *result_oid, - struct string_list *versions, - unsigned int offset, - size_t hash_size) +static int write_tree(struct object_id *result_oid, + struct string_list *versions, + unsigned int offset, + size_t hash_size) { size_t maxlen = 0, extra; unsigned int nr; struct strbuf buf = STRBUF_INIT; - int i; + int i, ret = 0; assert(offset <= versions->nr); nr = versions->nr - offset; @@ -2916,8 +3699,10 @@ static void write_tree(struct object_id *result_oid, } /* Write this object file out, and record in result_oid */ - write_object_file(buf.buf, buf.len, tree_type, result_oid); + if (write_object_file(buf.buf, buf.len, OBJ_TREE, result_oid)) + ret = -1; strbuf_release(&buf); + return ret; } static void record_entry_for_tree(struct directory_versions *dir_metadata, @@ -2936,13 +3721,13 @@ static void record_entry_for_tree(struct directory_versions *dir_metadata, basename)->util = &mi->result; } -static void write_completed_directory(struct merge_options *opt, - const char *new_directory_name, - struct directory_versions *info) +static int write_completed_directory(struct merge_options *opt, + const char *new_directory_name, + struct directory_versions *info) { const char *prev_dir; struct merged_info *dir_info = NULL; - unsigned int offset; + unsigned int offset, ret = 0; /* * Some explanation of info->versions and info->offsets... @@ -3028,7 +3813,7 @@ static void write_completed_directory(struct merge_options *opt, * strcmp here.) */ if (new_directory_name == info->last_directory) - return; + return 0; /* * If we are just starting (last_directory is NULL), or last_directory @@ -3050,7 +3835,7 @@ static void write_completed_directory(struct merge_options *opt, */ string_list_append(&info->offsets, info->last_directory)->util = (void*)offset; - return; + return 0; } /* @@ -3080,8 +3865,9 @@ static void write_completed_directory(struct merge_options *opt, */ dir_info->is_null = 0; dir_info->result.mode = S_IFDIR; - write_tree(&dir_info->result.oid, &info->versions, offset, - opt->repo->hash_algo->rawsz); + if (write_tree(&dir_info->result.oid, &info->versions, offset, + opt->repo->hash_algo->rawsz) < 0) + ret = -1; } /* @@ -3109,13 +3895,15 @@ static void write_completed_directory(struct merge_options *opt, /* And, of course, we need to update last_directory to match. */ info->last_directory = new_directory_name; info->last_directory_len = strlen(info->last_directory); + + return ret; } /* Per entry merge function */ -static void process_entry(struct merge_options *opt, - const char *path, - struct conflict_info *ci, - struct directory_versions *dir_metadata) +static int process_entry(struct merge_options *opt, + const char *path, + struct conflict_info *ci, + struct directory_versions *dir_metadata) { int df_file_index = 0; @@ -3129,7 +3917,7 @@ static void process_entry(struct merge_options *opt, record_entry_for_tree(dir_metadata, path, &ci->merged); if (ci->filemask == 0) /* nothing else to handle */ - return; + return 0; assert(ci->df_conflict); } @@ -3176,7 +3964,7 @@ static void process_entry(struct merge_options *opt, */ if (ci->filemask == 1) { ci->filemask = 0; - return; + return 0; } /* @@ -3184,7 +3972,8 @@ static void process_entry(struct merge_options *opt, * the directory to remain here, so we need to move this * path to some new location. */ - CALLOC_ARRAY(new_ci, 1); + new_ci = mem_pool_calloc(&opt->priv->pool, 1, sizeof(*new_ci)); + /* We don't really want new_ci->merged.result copied, but it'll * be overwritten below so it doesn't matter. We also don't * want any directory mode/oid values copied, but we'll zero @@ -3209,10 +3998,11 @@ static void process_entry(struct merge_options *opt, */ df_file_index = (ci->dirmask & (1 << 1)) ? 2 : 1; branch = (df_file_index == 1) ? opt->branch1 : opt->branch2; - path = unique_path(&opt->priv->paths, path, branch); + path = unique_path(opt, path, branch); strmap_put(&opt->priv->paths, path, new_ci); - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_FILE_DIRECTORY, 0, + path, old_path, NULL, NULL, _("CONFLICT (file/directory): directory in the way " "of %s from %s; moving it to %s instead."), old_path, branch, path); @@ -3237,7 +4027,7 @@ static void process_entry(struct merge_options *opt, * above. */ if (ci->match_mask) { - ci->merged.clean = 1; + ci->merged.clean = !ci->df_conflict && !ci->path_conflict; if (ci->match_mask == 6) { /* stages[1] == stages[2] */ ci->merged.result.mode = ci->stages[1].mode; @@ -3249,6 +4039,8 @@ static void process_entry(struct merge_options *opt, ci->merged.result.mode = ci->stages[side].mode; ci->merged.is_null = !ci->merged.result.mode; + if (ci->merged.is_null) + ci->merged.clean = 1; oidcpy(&ci->merged.result.oid, &ci->stages[side].oid); assert(othermask == 2 || othermask == 4); @@ -3274,7 +4066,8 @@ static void process_entry(struct merge_options *opt, const char *a_path = NULL, *b_path = NULL; int rename_a = 0, rename_b = 0; - new_ci = xmalloc(sizeof(*new_ci)); + new_ci = mem_pool_alloc(&opt->priv->pool, + sizeof(*new_ci)); if (S_ISREG(a_mode)) rename_a = 1; @@ -3285,15 +4078,23 @@ static void process_entry(struct merge_options *opt, rename_b = 1; } + if (rename_a) + a_path = unique_path(opt, path, opt->branch1); + if (rename_b) + b_path = unique_path(opt, path, opt->branch2); + if (rename_a && rename_b) { - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_DISTINCT_MODES, 0, + path, a_path, b_path, NULL, _("CONFLICT (distinct types): %s had " "different types on each side; " "renamed both of them so each can " "be recorded somewhere."), path); } else { - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_DISTINCT_MODES, 0, + path, rename_a ? a_path : b_path, + NULL, NULL, _("CONFLICT (distinct types): %s had " "different types on each side; " "renamed one of them so each can be " @@ -3330,30 +4131,15 @@ static void process_entry(struct merge_options *opt, /* Insert entries into opt->priv_paths */ assert(rename_a || rename_b); - if (rename_a) { - a_path = unique_path(&opt->priv->paths, - path, opt->branch1); + if (rename_a) strmap_put(&opt->priv->paths, a_path, ci); - } - if (rename_b) - b_path = unique_path(&opt->priv->paths, - path, opt->branch2); - else + if (!rename_b) b_path = path; strmap_put(&opt->priv->paths, b_path, new_ci); - if (rename_a && rename_b) { + if (rename_a && rename_b) strmap_remove(&opt->priv->paths, path, 0); - /* - * We removed path from opt->priv->paths. path - * will also eventually need to be freed, but - * it may still be used by e.g. ci->pathnames. - * So, store it in another string-list for now. - */ - string_list_append(&opt->priv->paths_to_free, - path); - } /* * Do special handling for b_path since process_entry() @@ -3373,7 +4159,7 @@ static void process_entry(struct merge_options *opt, } else if (ci->filemask >= 6) { /* Need a two-way or three-way content merge */ struct version_info merged_file; - unsigned clean_merge; + int clean_merge; struct version_info *o = &ci->stages[0]; struct version_info *a = &ci->stages[1]; struct version_info *b = &ci->stages[2]; @@ -3382,6 +4168,8 @@ static void process_entry(struct merge_options *opt, ci->pathnames, opt->priv->call_depth * 2, &merged_file); + if (clean_merge < 0) + return -1; ci->merged.clean = clean_merge && !ci->df_conflict && !ci->path_conflict; ci->merged.result.mode = merged_file.mode; @@ -3399,7 +4187,8 @@ static void process_entry(struct merge_options *opt, reason = _("add/add"); if (S_ISGITLINK(merged_file.mode)) reason = _("submodule"); - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_CONTENTS, 0, + path, NULL, NULL, NULL, _("CONFLICT (%s): Merge conflict in %s"), reason, path); } @@ -3419,8 +4208,22 @@ static void process_entry(struct merge_options *opt, if (opt->renormalize && blob_unchanged(opt, &ci->stages[0], &ci->stages[side], path)) { - ci->merged.is_null = 1; - ci->merged.clean = 1; + if (!ci->path_conflict) { + /* + * Blob unchanged after renormalization, so + * there's no modify/delete conflict after all; + * we can just remove the file. + */ + ci->merged.is_null = 1; + ci->merged.clean = 1; + /* + * file goes away => even if there was a + * directory/file conflict there isn't one now. + */ + ci->df_conflict = 0; + } else { + /* rename/delete, so conflict remains */ + } } else if (ci->path_conflict && oideq(&ci->stages[0].oid, &ci->stages[side].oid)) { /* @@ -3429,7 +4232,8 @@ static void process_entry(struct merge_options *opt, * since the contents were not modified. */ } else { - path_msg(opt, path, 0, + path_msg(opt, CONFLICT_MODIFY_DELETE, 0, + path, NULL, NULL, NULL, _("CONFLICT (modify/delete): %s deleted in %s " "and modified in %s. Version %s of %s left " "in tree."), @@ -3447,6 +4251,7 @@ static void process_entry(struct merge_options *opt, ci->merged.is_null = 1; ci->merged.result.mode = 0; oidcpy(&ci->merged.result.oid, null_oid()); + assert(!ci->df_conflict); ci->merged.clean = !ci->path_conflict; } @@ -3457,11 +4262,62 @@ static void process_entry(struct merge_options *opt, */ if (!ci->merged.clean) strmap_put(&opt->priv->conflicted, path, ci); + + /* Record metadata for ci->merged in dir_metadata */ record_entry_for_tree(dir_metadata, path, &ci->merged); + return 0; } -static void process_entries(struct merge_options *opt, - struct object_id *result_oid) +static void prefetch_for_content_merges(struct merge_options *opt, + struct string_list *plist) +{ + struct string_list_item *e; + struct oid_array to_fetch = OID_ARRAY_INIT; + + if (opt->repo != the_repository || !repo_has_promisor_remote(the_repository)) + return; + + for (e = &plist->items[plist->nr-1]; e >= plist->items; --e) { + /* char *path = e->string; */ + struct conflict_info *ci = e->util; + int i; + + /* Ignore clean entries */ + if (ci->merged.clean) + continue; + + /* Ignore entries that don't need a content merge */ + if (ci->match_mask || ci->filemask < 6 || + !S_ISREG(ci->stages[1].mode) || + !S_ISREG(ci->stages[2].mode) || + oideq(&ci->stages[1].oid, &ci->stages[2].oid)) + continue; + + /* Also don't need content merge if base matches either side */ + if (ci->filemask == 7 && + S_ISREG(ci->stages[0].mode) && + (oideq(&ci->stages[0].oid, &ci->stages[1].oid) || + oideq(&ci->stages[0].oid, &ci->stages[2].oid))) + continue; + + for (i = 0; i < 3; i++) { + unsigned side_mask = (1 << i); + struct version_info *vi = &ci->stages[i]; + + if ((ci->filemask & side_mask) && + S_ISREG(vi->mode) && + oid_object_info_extended(opt->repo, &vi->oid, NULL, + OBJECT_INFO_FOR_PREFETCH)) + oid_array_append(&to_fetch, &vi->oid); + } + } + + promisor_remote_get_direct(opt->repo, to_fetch.oid, to_fetch.nr); + oid_array_clear(&to_fetch); +} + +static int process_entries(struct merge_options *opt, + struct object_id *result_oid) { struct hashmap_iter iter; struct strmap_entry *e; @@ -3470,11 +4326,12 @@ static void process_entries(struct merge_options *opt, struct directory_versions dir_metadata = { STRING_LIST_INIT_NODUP, STRING_LIST_INIT_NODUP, NULL, 0 }; + int ret = 0; trace2_region_enter("merge", "process_entries setup", opt->repo); if (strmap_empty(&opt->priv->paths)) { oidcpy(result_oid, opt->repo->hash_algo->empty_tree); - return; + return 0; } /* Hack to pre-allocate plist to the desired size */ @@ -3490,7 +4347,7 @@ static void process_entries(struct merge_options *opt, trace2_region_leave("merge", "plist copy", opt->repo); trace2_region_enter("merge", "plist special sort", opt->repo); - plist.cmp = string_list_df_name_compare; + plist.cmp = sort_dirs_next_to_their_children; string_list_sort(&plist); trace2_region_leave("merge", "plist special sort", opt->repo); @@ -3506,6 +4363,7 @@ static void process_entries(struct merge_options *opt, * the way when it is time to process the file at the same path). */ trace2_region_enter("merge", "processing", opt->repo); + prefetch_for_content_merges(opt, &plist); for (entry = &plist.items[plist.nr-1]; entry >= plist.items; --entry) { char *path = entry->string; /* @@ -3515,13 +4373,19 @@ static void process_entries(struct merge_options *opt, */ struct merged_info *mi = entry->util; - write_completed_directory(opt, mi->directory_name, - &dir_metadata); + if (write_completed_directory(opt, mi->directory_name, + &dir_metadata) < 0) { + ret = -1; + goto cleanup; + } if (mi->clean) record_entry_for_tree(&dir_metadata, path, mi); else { struct conflict_info *ci = (struct conflict_info *)mi; - process_entry(opt, path, ci, &dir_metadata); + if (process_entry(opt, path, ci, &dir_metadata) < 0) { + ret = -1; + goto cleanup; + }; } } trace2_region_leave("merge", "processing", opt->repo); @@ -3529,19 +4393,23 @@ static void process_entries(struct merge_options *opt, trace2_region_enter("merge", "process_entries cleanup", opt->repo); if (dir_metadata.offsets.nr != 1 || (uintptr_t)dir_metadata.offsets.items[0].util != 0) { - printf("dir_metadata.offsets.nr = %d (should be 1)\n", - dir_metadata.offsets.nr); + printf("dir_metadata.offsets.nr = %"PRIuMAX" (should be 1)\n", + (uintmax_t)dir_metadata.offsets.nr); printf("dir_metadata.offsets.items[0].util = %u (should be 0)\n", (unsigned)(uintptr_t)dir_metadata.offsets.items[0].util); fflush(stdout); BUG("dir_metadata accounting completely off; shouldn't happen"); } - write_tree(result_oid, &dir_metadata.versions, 0, - opt->repo->hash_algo->rawsz); + if (write_tree(result_oid, &dir_metadata.versions, 0, + opt->repo->hash_algo->rawsz) < 0) + ret = -1; +cleanup: string_list_clear(&plist, 0); string_list_clear(&dir_metadata.versions, 0); string_list_clear(&dir_metadata.offsets, 0); trace2_region_leave("merge", "process_entries cleanup", opt->repo); + + return ret; } /*** Function Grouping: functions related to merge_switch_to_result() ***/ @@ -3577,20 +4445,16 @@ static int checkout(struct merge_options *opt, unpack_opts.quiet = 0; /* FIXME: sequencer might want quiet? */ unpack_opts.verbose_update = (opt->verbosity > 2); unpack_opts.fn = twoway_merge; - if (1/* FIXME: opts->overwrite_ignore*/) { - CALLOC_ARRAY(unpack_opts.dir, 1); - unpack_opts.dir->flags |= DIR_SHOW_IGNORED; - setup_standard_excludes(unpack_opts.dir); - } - parse_tree(prev); - init_tree_desc(&trees[0], prev->buffer, prev->size); - parse_tree(next); - init_tree_desc(&trees[1], next->buffer, next->size); + unpack_opts.preserve_ignored = 0; /* FIXME: !opts->overwrite_ignore */ + if (parse_tree(prev) < 0) + return -1; + init_tree_desc(&trees[0], &prev->object.oid, prev->buffer, prev->size); + if (parse_tree(next) < 0) + return -1; + init_tree_desc(&trees[1], &next->object.oid, next->buffer, next->size); ret = unpack_trees(2, trees, &unpack_opts); clear_unpack_trees_porcelain(&unpack_opts); - dir_clear(unpack_opts.dir); - FREE_AND_NULL(unpack_opts.dir); return ret; } @@ -3606,6 +4470,21 @@ static int record_conflicted_index_entries(struct merge_options *opt) if (strmap_empty(&opt->priv->conflicted)) return 0; + /* + * We are in a conflicted state. These conflicts might be inside + * sparse-directory entries, so check if any entries are outside + * of the sparse-checkout cone preemptively. + * + * We set original_cache_nr below, but that might change if + * index_name_pos() calls ask for paths within sparse directories. + */ + strmap_for_each_entry(&opt->priv->conflicted, &iter, e) { + if (!path_in_sparse_checkout(e->key, index)) { + ensure_full_index(index); + break; + } + } + /* If any entries have skip_worktree set, we'll have to check 'em out */ state.force = 1; state.quiet = 1; @@ -3613,7 +4492,7 @@ static int record_conflicted_index_entries(struct merge_options *opt) state.istate = index; original_cache_nr = index->cache_nr; - /* Put every entry from paths into plist, then sort */ + /* Append every entry from conflicted into index, then sort */ strmap_for_each_entry(&opt->priv->conflicted, &iter, e) { const char *path = e->key; struct conflict_info *ci = e->value; @@ -3656,22 +4535,8 @@ static int record_conflicted_index_entries(struct merge_options *opt) * the CE_SKIP_WORKTREE bit and manually write those * files to the working disk here. */ - if (ce_skip_worktree(ce)) { - struct stat st; - - if (!lstat(path, &st)) { - char *new_name = unique_path(&opt->priv->paths, - path, - "cruft"); - - path_msg(opt, path, 1, - _("Note: %s not up to date and in way of checking out conflicted version; old copy renamed to %s"), - path, new_name); - errs |= rename(path, new_name); - free(new_name); - } + if (ce_skip_worktree(ce)) errs |= checkout_entry(ce, &state, NULL, NULL); - } /* * Mark this cache entry for removal and instead add @@ -3713,6 +4578,152 @@ static int record_conflicted_index_entries(struct merge_options *opt) return errs; } +static void print_submodule_conflict_suggestion(struct string_list *csub) { + struct string_list_item *item; + struct strbuf msg = STRBUF_INIT; + struct strbuf tmp = STRBUF_INIT; + struct strbuf subs = STRBUF_INIT; + + if (!csub->nr) + return; + + strbuf_add_separated_string_list(&subs, " ", csub); + for_each_string_list_item(item, csub) { + struct conflicted_submodule_item *util = item->util; + + /* + * NEEDSWORK: The steps to resolve these errors deserve a more + * detailed explanation than what is currently printed below. + */ + if (util->flag == CONFLICT_SUBMODULE_NOT_INITIALIZED || + util->flag == CONFLICT_SUBMODULE_HISTORY_NOT_AVAILABLE) + continue; + + /* + * TRANSLATORS: This is a line of advice to resolve a merge + * conflict in a submodule. The first argument is the submodule + * name, and the second argument is the abbreviated id of the + * commit that needs to be merged. For example: + * - go to submodule (mysubmodule), and either merge commit abc1234" + */ + strbuf_addf(&tmp, _(" - go to submodule (%s), and either merge commit %s\n" + " or update to an existing commit which has merged those changes\n"), + item->string, util->abbrev); + } + + /* + * TRANSLATORS: This is a detailed message for resolving submodule + * conflicts. The first argument is string containing one step per + * submodule. The second is a space-separated list of submodule names. + */ + strbuf_addf(&msg, + _("Recursive merging with submodules currently only supports trivial cases.\n" + "Please manually handle the merging of each conflicted submodule.\n" + "This can be accomplished with the following steps:\n" + "%s" + " - come back to superproject and run:\n\n" + " git add %s\n\n" + " to record the above merge or update\n" + " - resolve any other conflicts in the superproject\n" + " - commit the resulting index in the superproject\n"), + tmp.buf, subs.buf); + + advise_if_enabled(ADVICE_SUBMODULE_MERGE_CONFLICT, "%s", msg.buf); + + strbuf_release(&subs); + strbuf_release(&tmp); + strbuf_release(&msg); +} + +void merge_display_update_messages(struct merge_options *opt, + int detailed, + struct merge_result *result) +{ + struct merge_options_internal *opti = result->priv; + struct hashmap_iter iter; + struct strmap_entry *e; + struct string_list olist = STRING_LIST_INIT_NODUP; + + if (opt->record_conflict_msgs_as_headers) + BUG("Either display conflict messages or record them as headers, not both"); + + trace2_region_enter("merge", "display messages", opt->repo); + + /* Hack to pre-allocate olist to the desired size */ + ALLOC_GROW(olist.items, strmap_get_size(&opti->conflicts), + olist.alloc); + + /* Put every entry from output into olist, then sort */ + strmap_for_each_entry(&opti->conflicts, &iter, e) { + string_list_append(&olist, e->key)->util = e->value; + } + string_list_sort(&olist); + + /* Iterate over the items, printing them */ + for (int path_nr = 0; path_nr < olist.nr; ++path_nr) { + struct string_list *conflicts = olist.items[path_nr].util; + for (int i = 0; i < conflicts->nr; i++) { + struct logical_conflict_info *info = + conflicts->items[i].util; + + if (detailed) { + printf("%lu", (unsigned long)info->paths.nr); + putchar('\0'); + for (int n = 0; n < info->paths.nr; n++) { + fputs(info->paths.v[n], stdout); + putchar('\0'); + } + fputs(type_short_descriptions[info->type], + stdout); + putchar('\0'); + } + puts(conflicts->items[i].string); + if (detailed) + putchar('\0'); + } + } + string_list_clear(&olist, 0); + + print_submodule_conflict_suggestion(&opti->conflicted_submodules); + + /* Also include needed rename limit adjustment now */ + diff_warn_rename_limit("merge.renamelimit", + opti->renames.needed_limit, 0); + + trace2_region_leave("merge", "display messages", opt->repo); +} + +void merge_get_conflicted_files(struct merge_result *result, + struct string_list *conflicted_files) +{ + struct hashmap_iter iter; + struct strmap_entry *e; + struct merge_options_internal *opti = result->priv; + + strmap_for_each_entry(&opti->conflicted, &iter, e) { + const char *path = e->key; + struct conflict_info *ci = e->value; + int i; + + VERIFY_CI(ci); + + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + struct stage_info *si; + + if (!(ci->filemask & (1ul << i))) + continue; + + si = xmalloc(sizeof(*si)); + si->stage = i+1; + si->mode = ci->stages[i].mode; + oidcpy(&si->oid, &ci->stages[i].oid); + string_list_append(conflicted_files, path)->util = si; + } + } + /* string_list_sort() uses a stable sort, so we're good */ + string_list_sort(conflicted_files); +} + void merge_switch_to_result(struct merge_options *opt, struct tree *head, struct merge_result *result, @@ -3721,13 +4732,12 @@ void merge_switch_to_result(struct merge_options *opt, { assert(opt->priv == NULL); if (result->clean >= 0 && update_worktree_and_index) { - const char *filename; - FILE *fp; - trace2_region_enter("merge", "checkout", opt->repo); if (checkout(opt, head, result->tree)) { /* failure to function */ result->clean = -1; + merge_finalize(opt, result); + trace2_region_leave("merge", "checkout", opt->repo); return; } trace2_region_leave("merge", "checkout", opt->repo); @@ -3738,52 +4748,30 @@ void merge_switch_to_result(struct merge_options *opt, /* failure to function */ opt->priv = NULL; result->clean = -1; + merge_finalize(opt, result); + trace2_region_leave("merge", "record_conflicted", + opt->repo); return; } opt->priv = NULL; trace2_region_leave("merge", "record_conflicted", opt->repo); trace2_region_enter("merge", "write_auto_merge", opt->repo); - filename = git_path_auto_merge(opt->repo); - fp = xfopen(filename, "w"); - fprintf(fp, "%s\n", oid_to_hex(&result->tree->object.oid)); - fclose(fp); - trace2_region_leave("merge", "write_auto_merge", opt->repo); - } - - if (display_update_msgs) { - struct merge_options_internal *opti = result->priv; - struct hashmap_iter iter; - struct strmap_entry *e; - struct string_list olist = STRING_LIST_INIT_NODUP; - int i; - - trace2_region_enter("merge", "display messages", opt->repo); - - /* Hack to pre-allocate olist to the desired size */ - ALLOC_GROW(olist.items, strmap_get_size(&opti->output), - olist.alloc); - - /* Put every entry from output into olist, then sort */ - strmap_for_each_entry(&opti->output, &iter, e) { - string_list_append(&olist, e->key)->util = e->value; - } - string_list_sort(&olist); - - /* Iterate over the items, printing them */ - for (i = 0; i < olist.nr; ++i) { - struct strbuf *sb = olist.items[i].util; - - printf("%s", sb->buf); + if (refs_update_ref(get_main_ref_store(opt->repo), "", "AUTO_MERGE", + &result->tree->object.oid, NULL, REF_NO_DEREF, + UPDATE_REFS_MSG_ON_ERR)) { + /* failure to function */ + opt->priv = NULL; + result->clean = -1; + merge_finalize(opt, result); + trace2_region_leave("merge", "write_auto_merge", + opt->repo); + return; } - string_list_clear(&olist, 0); - - /* Also include needed rename limit adjustment now */ - diff_warn_rename_limit("merge.renamelimit", - opti->renames.needed_limit, 0); - - trace2_region_leave("merge", "display messages", opt->repo); + trace2_region_leave("merge", "write_auto_merge", opt->repo); } + if (display_update_msgs) + merge_display_update_messages(opt, /* detailed */ 0, result); merge_finalize(opt, result); } @@ -3791,14 +4779,14 @@ void merge_switch_to_result(struct merge_options *opt, void merge_finalize(struct merge_options *opt, struct merge_result *result) { - struct merge_options_internal *opti = result->priv; - if (opt->renormalize) git_attr_set_direction(GIT_ATTR_CHECKIN); assert(opt->priv == NULL); - clear_or_reinit_internal_opts(opti, 0); - FREE_AND_NULL(opti); + if (result->priv) { + clear_or_reinit_internal_opts(result->priv, 0); + FREE_AND_NULL(result->priv); + } } /*** Function Grouping: helper functions for merge_incore_*() ***/ @@ -3841,6 +4829,7 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) { struct rename_info *renames; int i; + struct mem_pool *pool = NULL; /* Sanity checks on opt */ trace2_region_enter("merge", "sanity checks", opt->repo); @@ -3858,6 +4847,9 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) assert(opt->recursive_variant >= MERGE_VARIANT_NORMAL && opt->recursive_variant <= MERGE_VARIANT_THEIRS); + if (opt->msg_header_prefix) + assert(opt->record_conflict_msgs_as_headers); + /* * detect_renames, verbosity, buffer_output, and obuf are ignored * fields that were used by "recursive" rather than "ort" -- but @@ -3899,6 +4891,7 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) trace2_region_enter("merge", "allocate/init", opt->repo); if (opt->priv) { clear_or_reinit_internal_opts(opt->priv, 1); + string_list_init_nodup(&opt->priv->conflicted_submodules); trace2_region_leave("merge", "allocate/init", opt->repo); return; } @@ -3906,9 +4899,11 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) /* Initialization of various renames fields */ renames = &opt->priv->renames; + mem_pool_init(&opt->priv->pool, 0); + pool = &opt->priv->pool; for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) { strintmap_init_with_options(&renames->dirs_removed[i], - NOT_RELEVANT, NULL, 0); + NOT_RELEVANT, pool, 0); strmap_init_with_options(&renames->dir_rename_count[i], NULL, 1); strmap_init_with_options(&renames->dir_renames[i], @@ -3922,7 +4917,7 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) */ strintmap_init_with_options(&renames->relevant_sources[i], -1 /* explicitly invalid */, - NULL, 0); + pool, 0); strmap_init_with_options(&renames->cached_pairs[i], NULL, 1); strset_init_with_options(&renames->cached_irrelevant[i], @@ -3930,32 +4925,37 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) strset_init_with_options(&renames->cached_target_names[i], NULL, 0); } + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) { + strintmap_init_with_options(&renames->deferred[i].possible_trivial_merges, + 0, pool, 0); + strset_init_with_options(&renames->deferred[i].target_dirs, + pool, 1); + renames->deferred[i].trivial_merges_okay = 1; /* 1 == maybe */ + } /* * Although we initialize opt->priv->paths with strdup_strings=0, * that's just to avoid making yet another copy of an allocated * string. Putting the entry into paths means we are taking - * ownership, so we will later free it. paths_to_free is similar. + * ownership, so we will later free it. * * In contrast, conflicted just has a subset of keys from paths, so * we don't want to free those (it'd be a duplicate free). */ - strmap_init_with_options(&opt->priv->paths, NULL, 0); - strmap_init_with_options(&opt->priv->conflicted, NULL, 0); - string_list_init(&opt->priv->paths_to_free, 0); + strmap_init_with_options(&opt->priv->paths, pool, 0); + strmap_init_with_options(&opt->priv->conflicted, pool, 0); /* - * keys & strbufs in output will sometimes need to outlive "paths", - * so it will have a copy of relevant keys. It's probably a small - * subset of the overall paths that have special output. + * keys & string_lists in conflicts will sometimes need to outlive + * "paths", so it will have a copy of relevant keys. It's probably + * a small subset of the overall paths that have special output. */ - strmap_init(&opt->priv->output); + strmap_init(&opt->priv->conflicts); trace2_region_leave("merge", "allocate/init", opt->repo); } -static void merge_check_renames_reusable(struct merge_options *opt, - struct merge_result *result, +static void merge_check_renames_reusable(struct merge_result *result, struct tree *merge_base, struct tree *side1, struct tree *side2) @@ -4018,13 +5018,14 @@ static void merge_ort_nonrecursive_internal(struct merge_options *opt, opt->subtree_shift); } +redo: trace2_region_enter("merge", "collect_merge_info", opt->repo); if (collect_merge_info(opt, merge_base, side1, side2) != 0) { /* * TRANSLATORS: The %s arguments are: 1) tree hash of a merge * base, and 2-3) the trees for the two trees we're merging. */ - err(opt, _("collecting merge info failed for trees %s, %s, %s"), + error(_("collecting merge info failed for trees %s, %s, %s"), oid_to_hex(&merge_base->object.oid), oid_to_hex(&side1->object.oid), oid_to_hex(&side2->object.oid)); @@ -4034,18 +5035,31 @@ static void merge_ort_nonrecursive_internal(struct merge_options *opt, trace2_region_leave("merge", "collect_merge_info", opt->repo); trace2_region_enter("merge", "renames", opt->repo); - result->clean = detect_and_process_renames(opt, merge_base, - side1, side2); + result->clean = detect_and_process_renames(opt); trace2_region_leave("merge", "renames", opt->repo); + if (opt->priv->renames.redo_after_renames == 2) { + trace2_region_enter("merge", "reset_maps", opt->repo); + clear_or_reinit_internal_opts(opt->priv, 1); + trace2_region_leave("merge", "reset_maps", opt->repo); + goto redo; + } trace2_region_enter("merge", "process_entries", opt->repo); - process_entries(opt, &working_tree_oid); + if (process_entries(opt, &working_tree_oid) < 0) + result->clean = -1; trace2_region_leave("merge", "process_entries", opt->repo); /* Set return values */ - result->tree = parse_tree_indirect(&working_tree_oid); - /* existence of conflicted entries implies unclean */ - result->clean &= strmap_empty(&opt->priv->conflicted); + result->path_messages = &opt->priv->conflicts; + + if (result->clean >= 0) { + result->tree = parse_tree_indirect(&working_tree_oid); + if (!result->tree) + die(_("unable to read tree (%s)"), + oid_to_hex(&working_tree_oid)); + /* existence of conflicted entries implies unclean */ + result->clean &= strmap_empty(&opt->priv->conflicted); + } if (!opt->priv->call_depth) { result->priv = opt->priv; result->_properly_initialized = RESULT_INITIALIZED; @@ -4062,19 +5076,23 @@ static void merge_ort_internal(struct merge_options *opt, struct commit *h2, struct merge_result *result) { - struct commit_list *iter; + struct commit *next; struct commit *merged_merge_bases; const char *ancestor_name; struct strbuf merge_base_abbrev = STRBUF_INIT; if (!merge_bases) { - merge_bases = get_merge_bases(h1, h2); + if (repo_get_merge_bases(the_repository, h1, h2, + &merge_bases) < 0) { + result->clean = -1; + return; + } /* See merge-ort.h:merge_incore_recursive() declaration NOTE */ merge_bases = reverse_commit_list(merge_bases); } merged_merge_bases = pop_commit(&merge_bases); - if (merged_merge_bases == NULL) { + if (!merged_merge_bases) { /* if there is no common ancestor, use an empty tree */ struct tree *tree; @@ -4091,7 +5109,8 @@ static void merge_ort_internal(struct merge_options *opt, ancestor_name = merge_base_abbrev.buf; } - for (iter = merge_bases; iter; iter = iter->next) { + for (next = pop_commit(&merge_bases); next; + next = pop_commit(&merge_bases)) { const char *saved_b1, *saved_b2; struct commit *prev = merged_merge_bases; @@ -4108,7 +5127,7 @@ static void merge_ort_internal(struct merge_options *opt, saved_b2 = opt->branch2; opt->branch1 = "Temporary merge branch 1"; opt->branch2 = "Temporary merge branch 2"; - merge_ort_internal(opt, NULL, prev, iter->item, result); + merge_ort_internal(opt, NULL, prev, next, result); if (result->clean < 0) return; opt->branch1 = saved_b1; @@ -4119,8 +5138,7 @@ static void merge_ort_internal(struct merge_options *opt, result->tree, "merged tree"); commit_list_insert(prev, &merged_merge_bases->parents); - commit_list_insert(iter->item, - &merged_merge_bases->parents->next); + commit_list_insert(next, &merged_merge_bases->parents->next); clear_or_reinit_internal_opts(opt->priv, 1); } @@ -4146,7 +5164,7 @@ void merge_incore_nonrecursive(struct merge_options *opt, trace2_region_enter("merge", "merge_start", opt->repo); assert(opt->ancestor != NULL); - merge_check_renames_reusable(opt, result, merge_base, side1, side2); + merge_check_renames_reusable(result, merge_base, side1, side2); merge_start(opt, result); /* * Record the trees used in this merge, so if there's a next merge in |