merge(3p/git): Merge git subtree at v2.29.2 r/1890

This also bumps the stable nixpkgs to 20.09 as of 2020-11-21, because
there is some breakage in the git build related to the netrc
credentials helper which someone has taken care of in nixpkgs.

The stable channel is not used for anything other than git, so this
should be fine.

Change-Id: I3575a19dab09e1e9556cf8231d717de9890484fb

1 files changed, 95 insertions, 8 deletions

diff --git a/third_party/git/object-store.h b/third_party/git/object-store.h
index 7f7b3cdd80..c4fc9dd74e 100644
--- a/third_party/git/object-store.h
+++ b/third_party/git/object-store.h
@@ -4,8 +4,9 @@
 #include "cache.h"
 #include "oidmap.h"
 #include "list.h"
-#include "sha1-array.h"
+#include "oid-array.h"
 #include "strbuf.h"
+#include "thread-utils.h"
 
 struct object_directory {
 	struct object_directory *next;
@@ -60,6 +61,7 @@ struct oid_array *odb_loose_cache(struct object_directory *odb,
 void odb_clear_loose_cache(struct object_directory *odb);
 
 struct packed_git {
+	struct hashmap_entry packmap_ent;
 	struct packed_git *next;
 	struct list_head mru;
 	struct pack_window *windows;
@@ -68,6 +70,7 @@ struct packed_git {
 	size_t index_size;
 	uint32_t num_objects;
 	uint32_t num_bad_objects;
+	uint32_t crc_offset;
 	unsigned char *bad_object_sha1;
 	int index_version;
 	time_t mtime;
@@ -88,6 +91,20 @@ struct packed_git {
 
 struct multi_pack_index;
 
+static inline int pack_map_entry_cmp(const void *unused_cmp_data,
+				     const struct hashmap_entry *entry,
+				     const struct hashmap_entry *entry2,
+				     const void *keydata)
+{
+	const char *key = keydata;
+	const struct packed_git *pg1, *pg2;
+
+	pg1 = container_of(entry, const struct packed_git, packmap_ent);
+	pg2 = container_of(entry2, const struct packed_git, packmap_ent);
+
+	return strcmp(pg1->pack_name, key ? key : pg2->pack_name);
+}
+
 struct raw_object_store {
 	/*
 	 * Set of all object directories; the main directory is first (and
@@ -110,6 +127,8 @@ 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 */
@@ -132,6 +151,12 @@ struct raw_object_store {
 	struct list_head packed_git_mru;
 
 	/*
+	 * A map of packfiles to packed_git structs for tracking which
+	 * packs have been loaded already.
+	 */
+	struct hashmap pack_map;
+
+	/*
 	 * A fast, rough count of the number of objects in the repository.
 	 * These two fields are not meant for direct access. Use
 	 * approximate_object_count() instead.
@@ -177,8 +202,9 @@ static inline void *repo_read_object_file(struct repository *r,
 /* Read and unpack an object file into memory, write memory to an object file */
 int oid_object_info(struct repository *r, const struct object_id *, unsigned long *);
 
-int hash_object_file(const void *buf, unsigned long len,
-		     const char *type, struct object_id *oid);
+int hash_object_file(const struct git_hash_algo *algo, const void *buf,
+		     unsigned long len, const char *type,
+		     struct object_id *oid);
 
 int write_object_file(const void *buf, unsigned long len,
 		      const char *type, struct object_id *oid);
@@ -187,6 +213,14 @@ int hash_object_file_literally(const void *buf, unsigned long len,
 			       const char *type, struct object_id *oid,
 			       unsigned flags);
 
+/*
+ * Add an object file to the in-memory object store, without writing it
+ * to disk.
+ *
+ * Callers are responsible for calling write_object_file to record the
+ * object in persistent storage before writing any other new objects
+ * that reference it.
+ */
 int pretend_object_file(void *, unsigned long, enum object_type,
 			struct object_id *oid);
 
@@ -205,12 +239,33 @@ int read_loose_object(const char *path,
 		      unsigned long *size,
 		      void **contents);
 
+/* Retry packed storage after checking packed and loose storage */
+#define HAS_OBJECT_RECHECK_PACKED 1
+
+/*
+ * Returns 1 if the object exists. This function will not lazily fetch objects
+ * in a partial clone.
+ */
+int has_object(struct repository *r, const struct object_id *oid,
+	       unsigned flags);
+
+/*
+ * These macros and functions are deprecated. If checking existence for an
+ * object that is likely to be missing and/or whose absence is relatively
+ * inconsequential (or is consequential but the caller is prepared to handle
+ * it), use has_object(), which has better defaults (no lazy fetch in a partial
+ * clone and no rechecking of packed storage). In the unlikely event that a
+ * caller needs to assert existence of an object that it fully expects to
+ * exist, and wants to trigger a lazy fetch in a partial clone, use
+ * oid_object_info_extended() with a NULL struct object_info.
+ *
+ * These functions can be removed once all callers have migrated to
+ * has_object() and/or oid_object_info_extended().
+ */
 #ifndef NO_THE_REPOSITORY_COMPATIBILITY_MACROS
 #define has_sha1_file_with_flags(sha1, flags) repo_has_sha1_file_with_flags(the_repository, sha1, flags)
 #define has_sha1_file(sha1) repo_has_sha1_file(the_repository, sha1)
 #endif
-
-/* Same as the above, except for struct object_id. */
 int repo_has_object_file(struct repository *r, const struct object_id *oid);
 int repo_has_object_file_with_flags(struct repository *r,
 				    const struct object_id *oid, int flags);
@@ -228,12 +283,46 @@ 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;
 	unsigned long *sizep;
 	off_t *disk_sizep;
-	unsigned char *delta_base_sha1;
+	struct object_id *delta_base_oid;
 	struct strbuf *type_name;
 	void **contentp;
 
@@ -271,8 +360,6 @@ struct object_info {
 #define OBJECT_INFO_LOOKUP_REPLACE 1
 /* Allow reading from a loose object file of unknown/bogus type */
 #define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2
-/* Do not check cached storage */
-#define OBJECT_INFO_SKIP_CACHED 4
 /* Do not retry packed storage after checking packed and loose storage */
 #define OBJECT_INFO_QUICK 8
 /* Do not check loose object */