Merge branch 'mt/threaded-grep-in-object-store'

Traditionally, we avoided threaded grep while searching in objects
(as opposed to files in the working tree) as accesses to the object
layer is not thread-safe.  This limitation is getting lifted.

* mt/threaded-grep-in-object-store:
  grep: use no. of cores as the default no. of threads
  grep: move driver pre-load out of critical section
  grep: re-enable threads in non-worktree case
  grep: protect packed_git [re-]initialization
  grep: allow submodule functions to run in parallel
  submodule-config: add skip_if_read option to repo_read_gitmodules()
  grep: replace grep_read_mutex by internal obj read lock
  object-store: allow threaded access to object reading
  replace-object: make replace operations thread-safe
  grep: fix racy calls in grep_objects()
  grep: fix race conditions at grep_submodule()
  grep: fix race conditions on userdiff calls

1 files changed, 37 insertions, 0 deletions

diff --git a/object-store.h b/object-store.h
index 8c53c0d9bf..3a010153b7 100644
--- a/object-store.h
+++ b/object-store.h
@@ -6,6 +6,7 @@
 #include "list.h"
 #include "sha1-array.h"
 #include "strbuf.h"
+#include "thread-utils.h"
 
 struct object_directory {
 	struct object_directory *next;
@@ -125,6 +126,8 @@ struct raw_object_store {
 	 * (see git-replace(1)).
 	 */
 	struct oidmap *replace_map;
+	unsigned replace_map_initialized : 1;
+	pthread_mutex_t replace_mutex; /* protect object replace functions */
 
 	struct commit_graph *commit_graph;
 	unsigned commit_graph_attempted : 1; /* if loading has been attempted */
@@ -257,6 +260,40 @@ int has_loose_object_nonlocal(const struct object_id *);
 
 void assert_oid_type(const struct object_id *oid, enum object_type expect);
 
+/*
+ * Enabling the object read lock allows multiple threads to safely call the
+ * following functions in parallel: repo_read_object_file(), read_object_file(),
+ * read_object_file_extended(), read_object_with_reference(), read_object(),
+ * oid_object_info() and oid_object_info_extended().
+ *
+ * obj_read_lock() and obj_read_unlock() may also be used to protect other
+ * section which cannot execute in parallel with object reading. Since the used
+ * lock is a recursive mutex, these sections can even contain calls to object
+ * reading functions. However, beware that in these cases zlib inflation won't
+ * be performed in parallel, losing performance.
+ *
+ * TODO: oid_object_info_extended()'s call stack has a recursive behavior. If
+ * any of its callees end up calling it, this recursive call won't benefit from
+ * parallel inflation.
+ */
+void enable_obj_read_lock(void);
+void disable_obj_read_lock(void);
+
+extern int obj_read_use_lock;
+extern pthread_mutex_t obj_read_mutex;
+
+static inline void obj_read_lock(void)
+{
+	if(obj_read_use_lock)
+		pthread_mutex_lock(&obj_read_mutex);
+}
+
+static inline void obj_read_unlock(void)
+{
+	if(obj_read_use_lock)
+		pthread_mutex_unlock(&obj_read_mutex);
+}
+
 struct object_info {
 	/* Request */
 	enum object_type *typep;