Merge branch 'jm/cache-entry-from-mem-pool'

For a large tree, the index needs to hold many cache entries
allocated on heap.  These cache entries are now allocated out of a
dedicated memory pool to amortize malloc(3) overhead.

* jm/cache-entry-from-mem-pool:
  block alloc: add validations around cache_entry lifecyle
  block alloc: allocate cache entries from mem_pool
  mem-pool: fill out functionality
  mem-pool: add life cycle management functions
  mem-pool: only search head block for available space
  block alloc: add lifecycle APIs for cache_entry structs
  read-cache: teach make_cache_entry to take object_id
  read-cache: teach refresh_cache_entry to take istate

Author: gitster

apply.c

@@ -4093,12 +4093,12 @@ static int build_fake_ancestor(struct apply_state *state, struct patch *list)
 			return error(_("sha1 information is lacking or useless "
 				       "(%s)."), name);
 
-		ce = make_cache_entry(patch->old_mode, oid.hash, name, 0, 0);
+		ce = make_cache_entry(&result, patch->old_mode, &oid, name, 0, 0);
 		if (!ce)
 			return error(_("make_cache_entry failed for path '%s'"),
 				     name);
 		if (add_index_entry(&result, ce, ADD_CACHE_OK_TO_ADD)) {
-			free(ce);
+			discard_cache_entry(ce);
 			return error(_("could not add %s to temporary index"),
 				     name);
 		}
@@ -4266,9 +4266,8 @@ static int add_index_file(struct apply_state *state,
 	struct stat st;
 	struct cache_entry *ce;
 	int namelen = strlen(path);
-	unsigned ce_size = cache_entry_size(namelen);
 
-	ce = xcalloc(1, ce_size);
+	ce = make_empty_cache_entry(&the_index, namelen);
 	memcpy(ce->name, path, namelen);
 	ce->ce_mode = create_ce_mode(mode);
 	ce->ce_flags = create_ce_flags(0);
@@ -4281,27 +4280,27 @@ static int add_index_file(struct apply_state *state,
 
 		if (!skip_prefix(buf, "Subproject commit ", &s) ||
 		    get_oid_hex(s, &ce->oid)) {
-			free(ce);
-		       return error(_("corrupt patch for submodule %s"), path);
+			discard_cache_entry(ce);
+			return error(_("corrupt patch for submodule %s"), path);
 		}
 	} else {
 		if (!state->cached) {
 			if (lstat(path, &st) < 0) {
-				free(ce);
+				discard_cache_entry(ce);
 				return error_errno(_("unable to stat newly "
 						     "created file '%s'"),
 						   path);
 			}
 			fill_stat_cache_info(ce, &st);
 		}
 		if (write_object_file(buf, size, blob_type, &ce->oid) < 0) {
-			free(ce);
+			discard_cache_entry(ce);
 			return error(_("unable to create backing store "
 				       "for newly created file %s"), path);
 		}
 	}
 	if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD) < 0) {
-		free(ce);
+		discard_cache_entry(ce);
 		return error(_("unable to add cache entry for %s"), path);
 	}
 
@@ -4425,27 +4424,26 @@ static int add_conflicted_stages_file(struct apply_state *state,
 				       struct patch *patch)
 {
 	int stage, namelen;
-	unsigned ce_size, mode;
+	unsigned mode;
 	struct cache_entry *ce;
 
 	if (!state->update_index)
 		return 0;
 	namelen = strlen(patch->new_name);
-	ce_size = cache_entry_size(namelen);
 	mode = patch->new_mode ? patch->new_mode : (S_IFREG | 0644);
 
 	remove_file_from_cache(patch->new_name);
 	for (stage = 1; stage < 4; stage++) {
 		if (is_null_oid(&patch->threeway_stage[stage - 1]))
 			continue;
-		ce = xcalloc(1, ce_size);
+		ce = make_empty_cache_entry(&the_index, namelen);
 		memcpy(ce->name, patch->new_name, namelen);
 		ce->ce_mode = create_ce_mode(mode);
 		ce->ce_flags = create_ce_flags(stage);
 		ce->ce_namelen = namelen;
 		oidcpy(&ce->oid, &patch->threeway_stage[stage - 1]);
 		if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD) < 0) {
-			free(ce);
+			discard_cache_entry(ce);
 			return error(_("unable to add cache entry for %s"),
 				     patch->new_name);
 		}

blame.c

@@ -176,7 +176,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 	struct strbuf buf = STRBUF_INIT;
 	const char *ident;
 	time_t now;
-	int size, len;
+	int len;
 	struct cache_entry *ce;
 	unsigned mode;
 	struct strbuf msg = STRBUF_INIT;
@@ -274,8 +274,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 			/* Let's not bother reading from HEAD tree */
 			mode = S_IFREG | 0644;
 	}
-	size = cache_entry_size(len);
-	ce = xcalloc(1, size);
+	ce = make_empty_cache_entry(&the_index, len);
 	oidcpy(&ce->oid, &origin->blob_oid);
 	memcpy(ce->name, path, len);
 	ce->ce_flags = create_ce_flags(0);

builtin/checkout.c

@@ -79,7 +79,7 @@ static int update_some(const struct object_id *oid, struct strbuf *base,
 		return READ_TREE_RECURSIVE;
 
 	len = base->len + strlen(pathname);
-	ce = xcalloc(1, cache_entry_size(len));
+	ce = make_empty_cache_entry(&the_index, len);
 	oidcpy(&ce->oid, oid);
 	memcpy(ce->name, base->buf, base->len);
 	memcpy(ce->name + base->len, pathname, len - base->len);
@@ -98,7 +98,7 @@ static int update_some(const struct object_id *oid, struct strbuf *base,
 		if (ce->ce_mode == old->ce_mode &&
 		    !oidcmp(&ce->oid, &old->oid)) {
 			old->ce_flags |= CE_UPDATE;
-			free(ce);
+			discard_cache_entry(ce);
 			return 0;
 		}
 	}
@@ -232,11 +232,11 @@ static int checkout_merged(int pos, const struct checkout *state)
 	if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
 		die(_("Unable to add merge result for '%s'"), path);
 	free(result_buf.ptr);
-	ce = make_cache_entry(mode, oid.hash, path, 2, 0);
+	ce = make_transient_cache_entry(mode, &oid, path, 2);
 	if (!ce)
 		die(_("make_cache_entry failed for path '%s'"), path);
 	status = checkout_entry(ce, state, NULL);
-	free(ce);
+	discard_cache_entry(ce);
 	return status;
 }
 

builtin/difftool.c

@@ -322,10 +322,10 @@ static int checkout_path(unsigned mode, struct object_id *oid,
 	struct cache_entry *ce;
 	int ret;
 
-	ce = make_cache_entry(mode, oid->hash, path, 0, 0);
+	ce = make_transient_cache_entry(mode, oid, path, 0);
 	ret = checkout_entry(ce, state, NULL);
 
-	free(ce);
+	discard_cache_entry(ce);
 	return ret;
 }
 
@@ -489,7 +489,7 @@ static int run_dir_diff(const char *extcmd, int symlinks, const char *prefix,
 				 * index.
 				 */
 				struct cache_entry *ce2 =
-					make_cache_entry(rmode, roid.hash,
+					make_cache_entry(&wtindex, rmode, &roid,
 							 dst_path, 0, 0);
 
 				add_index_entry(&wtindex, ce2,

builtin/reset.c

@@ -134,7 +134,7 @@ static void update_index_from_diff(struct diff_queue_struct *q,
 			continue;
 		}
 
-		ce = make_cache_entry(one->mode, one->oid.hash, one->path,
+		ce = make_cache_entry(&the_index, one->mode, &one->oid, one->path,
 				      0, 0);
 		if (!ce)
 			die(_("make_cache_entry failed for path '%s'"),

builtin/update-index.c

@@ -268,15 +268,14 @@ static int process_lstat_error(const char *path, int err)
 
 static int add_one_path(const struct cache_entry *old, const char *path, int len, struct stat *st)
 {
-	int option, size;
+	int option;
 	struct cache_entry *ce;
 
 	/* Was the old index entry already up-to-date? */
 	if (old && !ce_stage(old) && !ce_match_stat(old, st, 0))
 		return 0;
 
-	size = cache_entry_size(len);
-	ce = xcalloc(1, size);
+	ce = make_empty_cache_entry(&the_index, len);
 	memcpy(ce->name, path, len);
 	ce->ce_flags = create_ce_flags(0);
 	ce->ce_namelen = len;
@@ -285,13 +284,13 @@ static int add_one_path(const struct cache_entry *old, const char *path, int len
 
 	if (index_path(&ce->oid, path, st,
 		       info_only ? 0 : HASH_WRITE_OBJECT)) {
-		free(ce);
+		discard_cache_entry(ce);
 		return -1;
 	}
 	option = allow_add ? ADD_CACHE_OK_TO_ADD : 0;
 	option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0;
 	if (add_cache_entry(ce, option)) {
-		free(ce);
+		discard_cache_entry(ce);
 		return error("%s: cannot add to the index - missing --add option?", path);
 	}
 	return 0;
@@ -402,15 +401,14 @@ static int process_path(const char *path, struct stat *st, int stat_errno)
 static int add_cacheinfo(unsigned int mode, const struct object_id *oid,
 			 const char *path, int stage)
 {
-	int size, len, option;
+	int len, option;
 	struct cache_entry *ce;
 
 	if (!verify_path(path, mode))
 		return error("Invalid path '%s'", path);
 
 	len = strlen(path);
-	size = cache_entry_size(len);
-	ce = xcalloc(1, size);
+	ce = make_empty_cache_entry(&the_index, len);
 
 	oidcpy(&ce->oid, oid);
 	memcpy(ce->name, path, len);
@@ -600,7 +598,6 @@ static struct cache_entry *read_one_ent(const char *which,
 {
 	unsigned mode;
 	struct object_id oid;
-	int size;
 	struct cache_entry *ce;
 
 	if (get_tree_entry(ent, path, &oid, &mode)) {
@@ -613,8 +610,7 @@ static struct cache_entry *read_one_ent(const char *which,
 			error("%s: not a blob in %s branch.", path, which);
 		return NULL;
 	}
-	size = cache_entry_size(namelen);
-	ce = xcalloc(1, size);
+	ce = make_empty_cache_entry(&the_index, namelen);
 
 	oidcpy(&ce->oid, &oid);
 	memcpy(ce->name, path, namelen);
@@ -691,8 +687,8 @@ static int unresolve_one(const char *path)
 	error("%s: cannot add their version to the index.", path);
 	ret = -1;
  free_return:
-	free(ce_2);
-	free(ce_3);
+	discard_cache_entry(ce_2);
+	discard_cache_entry(ce_3);
 	return ret;
 }
 
@@ -759,7 +755,7 @@ static int do_reupdate(int ac, const char **av,
 					   ce->name, ce_namelen(ce), 0);
 		if (old && ce->ce_mode == old->ce_mode &&
 		    !oidcmp(&ce->oid, &old->oid)) {
-			free(old);
+			discard_cache_entry(old);
 			continue; /* unchanged */
 		}
 		/* Be careful.  The working tree may not have the
@@ -770,7 +766,7 @@ static int do_reupdate(int ac, const char **av,
 		path = xstrdup(ce->name);
 		update_one(path);
 		free(path);
-		free(old);
+		discard_cache_entry(old);
 		if (save_nr != active_nr)
 			goto redo;
 	}

cache.h

@@ -15,6 +15,7 @@
 #include "path.h"
 #include "sha1-array.h"
 #include "repository.h"
+#include "mem-pool.h"
 
 #include <zlib.h>
 typedef struct git_zstream {
@@ -156,6 +157,7 @@ struct cache_entry {
 	struct stat_data ce_stat_data;
 	unsigned int ce_mode;
 	unsigned int ce_flags;
+	unsigned int mem_pool_allocated;
 	unsigned int ce_namelen;
 	unsigned int index;	/* for link extension */
 	struct object_id oid;
@@ -227,6 +229,7 @@ static inline void copy_cache_entry(struct cache_entry *dst,
 				    const struct cache_entry *src)
 {
 	unsigned int state = dst->ce_flags & CE_HASHED;
+	int mem_pool_allocated = dst->mem_pool_allocated;
 
 	/* Don't copy hash chain and name */
 	memcpy(&dst->ce_stat_data, &src->ce_stat_data,
@@ -235,6 +238,9 @@ static inline void copy_cache_entry(struct cache_entry *dst,
 
 	/* Restore the hash state */
 	dst->ce_flags = (dst->ce_flags & ~CE_HASHED) | state;
+
+	/* Restore the mem_pool_allocated flag */
+	dst->mem_pool_allocated = mem_pool_allocated;
 }
 
 static inline unsigned create_ce_flags(unsigned stage)
@@ -328,6 +334,7 @@ struct index_state {
 	struct untracked_cache *untracked;
 	uint64_t fsmonitor_last_update;
 	struct ewah_bitmap *fsmonitor_dirty;
+	struct mem_pool *ce_mem_pool;
 };
 
 extern struct index_state the_index;
@@ -339,6 +346,60 @@ extern void remove_name_hash(struct index_state *istate, struct cache_entry *ce)
 extern void free_name_hash(struct index_state *istate);
 
 
+/* Cache entry creation and cleanup */
+
+/*
+ * Create cache_entry intended for use in the specified index. Caller
+ * is responsible for discarding the cache_entry with
+ * `discard_cache_entry`.
+ */
+struct cache_entry *make_cache_entry(struct index_state *istate,
+				     unsigned int mode,
+				     const struct object_id *oid,
+				     const char *path,
+				     int stage,
+				     unsigned int refresh_options);
+
+struct cache_entry *make_empty_cache_entry(struct index_state *istate,
+					   size_t name_len);
+
+/*
+ * Create a cache_entry that is not intended to be added to an index.
+ * Caller is responsible for discarding the cache_entry
+ * with `discard_cache_entry`.
+ */
+struct cache_entry *make_transient_cache_entry(unsigned int mode,
+					       const struct object_id *oid,
+					       const char *path,
+					       int stage);
+
+struct cache_entry *make_empty_transient_cache_entry(size_t name_len);
+
+/*
+ * Discard cache entry.
+ */
+void discard_cache_entry(struct cache_entry *ce);
+
+/*
+ * Check configuration if we should perform extra validation on cache
+ * entries.
+ */
+int should_validate_cache_entries(void);
+
+/*
+ * Duplicate a cache_entry. Allocate memory for the new entry from a
+ * memory_pool. Takes into account cache_entry fields that are meant
+ * for managing the underlying memory allocation of the cache_entry.
+ */
+struct cache_entry *dup_cache_entry(const struct cache_entry *ce, struct index_state *istate);
+
+/*
+ * Validate the cache entries in the index.  This is an internal
+ * consistency check that the cache_entry structs are allocated from
+ * the expected memory pool.
+ */
+void validate_cache_entries(const struct index_state *istate);
+
 #ifndef NO_THE_INDEX_COMPATIBILITY_MACROS
 #define active_cache (the_index.cache)
 #define active_nr (the_index.cache_nr)
@@ -698,7 +759,6 @@ extern int remove_file_from_index(struct index_state *, const char *path);
 extern int add_to_index(struct index_state *, const char *path, struct stat *, int flags);
 extern int add_file_to_index(struct index_state *, const char *path, int flags);
 
-extern struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, unsigned int refresh_options);
 extern int chmod_index_entry(struct index_state *, struct cache_entry *ce, char flip);
 extern int ce_same_name(const struct cache_entry *a, const struct cache_entry *b);
 extern void set_object_name_for_intent_to_add_entry(struct cache_entry *ce);
@@ -751,7 +811,7 @@ extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
 #define REFRESH_IGNORE_SUBMODULES	0x0010	/* ignore submodules */
 #define REFRESH_IN_PORCELAIN	0x0020	/* user friendly output, not "needs update" */
 extern int refresh_index(struct index_state *, unsigned int flags, const struct pathspec *pathspec, char *seen, const char *header_msg);
-extern struct cache_entry *refresh_cache_entry(struct cache_entry *, unsigned int);
+extern struct cache_entry *refresh_cache_entry(struct index_state *, struct cache_entry *, unsigned int);
 
 /*
  * Opportunistically update the index but do not complain if we can't.