Merge branch 'ps/reftable-detach'

Isolates the reftable subsystem from the rest of Git's codebase by
using fewer pieces of Git's infrastructure.

* ps/reftable-detach:
  reftable/system: provide thin wrapper for lockfile subsystem
  reftable/stack: drop only use of `get_locked_file_path()`
  reftable/system: provide thin wrapper for tempfile subsystem
  reftable/stack: stop using `fsync_component()` directly
  reftable/system: stop depending on "hash.h"
  reftable: explicitly handle hash format IDs
  reftable/system: move "dir.h" to its only user

Author: gitster

Makefile

@@ -2722,6 +2722,7 @@ REFTABLE_OBJS += reftable/pq.o
 REFTABLE_OBJS += reftable/reader.o
 REFTABLE_OBJS += reftable/record.o
 REFTABLE_OBJS += reftable/stack.o
+REFTABLE_OBJS += reftable/system.o
 REFTABLE_OBJS += reftable/tree.o
 REFTABLE_OBJS += reftable/writer.o
 

refs/reftable-backend.c

@@ -15,6 +15,7 @@
 #include "../object.h"
 #include "../path.h"
 #include "../refs.h"
+#include "../reftable/reftable-basics.h"
 #include "../reftable/reftable-stack.h"
 #include "../reftable/reftable-record.h"
 #include "../reftable/reftable-error.h"
@@ -23,6 +24,7 @@
 #include "../setup.h"
 #include "../strmap.h"
 #include "../trace2.h"
+#include "../write-or-die.h"
 #include "parse.h"
 #include "refs-internal.h"
 
@@ -272,6 +274,11 @@ static int reftable_be_config(const char *var, const char *value,
 	return 0;
 }
 
+static int reftable_be_fsync(int fd)
+{
+	return fsync_component(FSYNC_COMPONENT_REFERENCE, fd);
+}
+
 static struct ref_store *reftable_be_init(struct repository *repo,
 					  const char *gitdir,
 					  unsigned int store_flags)
@@ -289,11 +296,21 @@ static struct ref_store *reftable_be_init(struct repository *repo,
 	refs->store_flags = store_flags;
 	refs->log_all_ref_updates = repo_settings_get_log_all_ref_updates(repo);
 
-	refs->write_options.hash_id = repo->hash_algo->format_id;
+	switch (repo->hash_algo->format_id) {
+	case GIT_SHA1_FORMAT_ID:
+		refs->write_options.hash_id = REFTABLE_HASH_SHA1;
+		break;
+	case GIT_SHA256_FORMAT_ID:
+		refs->write_options.hash_id = REFTABLE_HASH_SHA256;
+		break;
+	default:
+		BUG("unknown hash algorithm %d", repo->hash_algo->format_id);
+	}
 	refs->write_options.default_permissions = calc_shared_perm(0666 & ~mask);
 	refs->write_options.disable_auto_compact =
 		!git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1);
 	refs->write_options.lock_timeout_ms = 100;
+	refs->write_options.fsync = reftable_be_fsync;
 
 	git_config(reftable_be_config, &refs->write_options);
 

reftable/basics.c

@@ -271,14 +271,15 @@ int common_prefix_size(struct reftable_buf *a, struct reftable_buf *b)
 	return p;
 }
 
-int hash_size(uint32_t id)
+int hash_size(enum reftable_hash id)
 {
+	if (!id)
+		return REFTABLE_HASH_SIZE_SHA1;
 	switch (id) {
-	case 0:
-	case GIT_SHA1_FORMAT_ID:
-		return GIT_SHA1_RAWSZ;
-	case GIT_SHA256_FORMAT_ID:
-		return GIT_SHA256_RAWSZ;
+	case REFTABLE_HASH_SHA1:
+		return REFTABLE_HASH_SIZE_SHA1;
+	case REFTABLE_HASH_SHA256:
+		return REFTABLE_HASH_SIZE_SHA256;
 	}
 	abort();
 }

reftable/basics.h

@@ -148,6 +148,14 @@ char *reftable_strdup(const char *str);
 /* Find the longest shared prefix size of `a` and `b` */
 int common_prefix_size(struct reftable_buf *a, struct reftable_buf *b);
 
-int hash_size(uint32_t id);
+int hash_size(enum reftable_hash id);
+
+/*
+ * Format IDs that identify the hash function used by a reftable. Note that
+ * these constants end up on disk and thus mustn't change. The format IDs are
+ * "sha1" and "s256" in big endian, respectively.
+ */
+#define REFTABLE_FORMAT_ID_SHA1   ((uint32_t) 0x73686131)
+#define REFTABLE_FORMAT_ID_SHA256 ((uint32_t) 0x73323536)
 
 #endif

reftable/merged.c

@@ -181,7 +181,7 @@ static void iterator_from_merged_iter(struct reftable_iterator *it,
 
 int reftable_merged_table_new(struct reftable_merged_table **dest,
 			      struct reftable_reader **readers, size_t n,
-			      uint32_t hash_id)
+			      enum reftable_hash hash_id)
 {
 	struct reftable_merged_table *m = NULL;
 	uint64_t last_max = 0;
@@ -293,7 +293,7 @@ int reftable_merged_table_init_log_iterator(struct reftable_merged_table *mt,
 	return merged_table_init_iter(mt, it, BLOCK_TYPE_LOG);
 }
 
-uint32_t reftable_merged_table_hash_id(struct reftable_merged_table *mt)
+enum reftable_hash reftable_merged_table_hash_id(struct reftable_merged_table *mt)
 {
 	return mt->hash_id;
 }

reftable/merged.h

@@ -10,11 +10,12 @@ license that can be found in the LICENSE file or at
 #define MERGED_H
 
 #include "system.h"
+#include "reftable-basics.h"
 
 struct reftable_merged_table {
 	struct reftable_reader **readers;
 	size_t readers_len;
-	uint32_t hash_id;
+	enum reftable_hash hash_id;
 
 	/* If unset, produce deletions. This is useful for compaction. For the
 	 * full stack, deletions should be produced. */

reftable/reader.c

@@ -67,7 +67,7 @@ static int reader_get_block(struct reftable_reader *r,
 	return block_source_read_block(&r->source, dest, off, sz);
 }
 
-uint32_t reftable_reader_hash_id(struct reftable_reader *r)
+enum reftable_hash reftable_reader_hash_id(struct reftable_reader *r)
 {
 	return r->hash_id;
 }
@@ -107,18 +107,20 @@ static int parse_footer(struct reftable_reader *r, uint8_t *footer,
 	f += 8;
 
 	if (r->version == 1) {
-		r->hash_id = GIT_SHA1_FORMAT_ID;
+		r->hash_id = REFTABLE_HASH_SHA1;
 	} else {
-		r->hash_id = get_be32(f);
-		switch (r->hash_id) {
-		case GIT_SHA1_FORMAT_ID:
+		switch (get_be32(f)) {
+		case REFTABLE_FORMAT_ID_SHA1:
+			r->hash_id = REFTABLE_HASH_SHA1;
 			break;
-		case GIT_SHA256_FORMAT_ID:
+		case REFTABLE_FORMAT_ID_SHA256:
+			r->hash_id = REFTABLE_HASH_SHA256;
 			break;
 		default:
 			err = REFTABLE_FORMAT_ERROR;
 			goto done;
 		}
+
 		f += 4;
 	}
 

reftable/reader.h

@@ -37,8 +37,8 @@ struct reftable_reader {
 	/* Size of the file, excluding the footer. */
 	uint64_t size;
 
-	/* 'sha1' for SHA1, 's256' for SHA-256 */
-	uint32_t hash_id;
+	/* The hash function used for ref records. */
+	enum reftable_hash hash_id;
 
 	uint32_t block_size;
 	uint64_t min_update_index;

reftable/reftable-basics.h

@@ -11,6 +11,19 @@
 
 #include <stddef.h>
 
+/*
+ * Hash functions understood by the reftable library. Note that the values are
+ * arbitrary and somewhat random such that we can easily detect cases where the
+ * hash hasn't been properly set up.
+ */
+enum reftable_hash {
+	REFTABLE_HASH_SHA1   = 89,
+	REFTABLE_HASH_SHA256 = 247,
+};
+#define REFTABLE_HASH_SIZE_SHA1   20
+#define REFTABLE_HASH_SIZE_SHA256 32
+#define REFTABLE_HASH_SIZE_MAX    REFTABLE_HASH_SIZE_SHA256
+
 /* Overrides the functions to use for memory management. */
 void reftable_set_alloc(void *(*malloc)(size_t),
 			void *(*realloc)(void *, size_t), void (*free)(void *));

reftable/reftable-merged.h

@@ -34,7 +34,7 @@ struct reftable_reader;
  */
 int reftable_merged_table_new(struct reftable_merged_table **dest,
 			      struct reftable_reader **readers, size_t n,
-			      uint32_t hash_id);
+			      enum reftable_hash hash_id);
 
 /* Initialize a merged table iterator for reading refs. */
 int reftable_merged_table_init_ref_iterator(struct reftable_merged_table *mt,
@@ -56,6 +56,6 @@ reftable_merged_table_min_update_index(struct reftable_merged_table *mt);
 void reftable_merged_table_free(struct reftable_merged_table *m);
 
 /* return the hash ID of the merged table. */
-uint32_t reftable_merged_table_hash_id(struct reftable_merged_table *m);
+enum reftable_hash reftable_merged_table_hash_id(struct reftable_merged_table *m);
 
 #endif