index: use the checksum to check whether it's been modified

We currently use a timetamp to check whether an index file has been
modified since we last read it, but this is racy. If two updates happen
in the same second and we read after the first one, we won't detect the
second one.

Instead read the SHA-1 checksum of the file, which are its last 20 bytes which
gives us a sure-fire way to detect whether the file has changed since we
last read it.

As we're now keeping track of it, expose an accessor to this data.

3 files changed, 55 insertions, 5 deletions

diff --git a/include/git2/index.h b/include/git2/index.h
index 49bbe1614..7caf3ed78 100644
--- a/include/git2/index.h
+++ b/include/git2/index.h
@@ -274,6 +274,18 @@ GIT_EXTERN(int) git_index_write(git_index *index);
 GIT_EXTERN(const char *) git_index_path(const git_index *index);
 
 /**
+ * Get the checksum of the index
+ *
+ * This checksum is the SHA-1 hash over the index file (except the
+ * last 20 bytes which are the checksum itself). In cases where the
+ * index does not exist on-disk, it will be zeroed out.
+ *
+ * @param index an existing index object
+ * @return a pointer to the checksum of the index
+ */
+GIT_EXTERN(const git_oid *) git_index_checksum(git_index *index);
+
+/**
  * Read a tree into the index file with stats
  *
  * The current index contents will be replaced by the specified tree.
diff --git a/src/index.c b/src/index.c
index a931f048a..ba101ea14 100644
--- a/src/index.c
+++ b/src/index.c
@@ -116,7 +116,7 @@ static int read_header(struct index_header *dest, const void *buffer);
 
 static int parse_index(git_index *index, const char *buffer, size_t buffer_size);
 static bool is_index_extended(git_index *index);
-static int write_index(git_index *index, git_filebuf *file);
+static int write_index(git_oid *checksum, git_index *index, git_filebuf *file);
 
 static void index_entry_free(git_index_entry *entry);
 static void index_entry_reuc_free(git_index_reuc_entry *reuc);
@@ -598,6 +598,38 @@ int git_index_caps(const git_index *index)
 			(index->no_symlinks ? GIT_INDEXCAP_NO_SYMLINKS : 0));
 }
 
+const git_oid *git_index_checksum(git_index *index)
+{
+	return &index->checksum;
+}
+
+/**
+ * Returns 1 for changed, 0 for not changed and <0 for errors
+ */
+static int compare_checksum(git_index *index)
+{
+	int fd, error;
+	ssize_t bytes_read;
+	git_oid checksum = {{ 0 }};
+
+	if ((fd = p_open(index->index_file_path, O_RDONLY)) < 0)
+		return fd;
+
+	if ((error = p_lseek(fd, -20, SEEK_END)) < 0) {
+		p_close(fd);
+		giterr_set(GITERR_OS, "failed to seek to end of file");
+		return -1;
+	}
+
+	bytes_read = p_read(fd, &checksum, GIT_OID_RAWSZ);
+	p_close(fd);
+
+	if (bytes_read < 0)
+		return -1;
+
+	return !!git_oid_cmp(&checksum, &index->checksum);
+}
+
 int git_index_read(git_index *index, int force)
 {
 	int error = 0, updated;
@@ -616,8 +648,8 @@ int git_index_read(git_index *index, int force)
 		return 0;
 	}
 
-	updated = git_futils_filestamp_check(&stamp, index->index_file_path);
-	if (updated < 0) {
+	if ((updated = git_futils_filestamp_check(&stamp, index->index_file_path) < 0) ||
+	    ((updated = compare_checksum(index)) < 0)) {
 		giterr_set(
 			GITERR_INDEX,
 			"Failed to read index: '%s' no longer exists",
@@ -2092,6 +2124,8 @@ static int parse_index(git_index *index, const char *buffer, size_t buffer_size)
 		goto done;
 	}
 
+	git_oid_cpy(&index->checksum, &checksum_calculated);
+
 #undef seek_forward
 
 	/* Entries are stored case-sensitively on disk, so re-sort now if
@@ -2355,7 +2389,7 @@ static int write_tree_extension(git_index *index, git_filebuf *file)
 	return error;
 }
 
-static int write_index(git_index *index, git_filebuf *file)
+static int write_index(git_oid *checksum, git_index *index, git_filebuf *file)
 {
 	git_oid hash_final;
 	struct index_header header;
@@ -2391,6 +2425,7 @@ static int write_index(git_index *index, git_filebuf *file)
 
 	/* get out the hash for all the contents we've appended to the file */
 	git_filebuf_hash(&hash_final, file);
+	git_oid_cpy(checksum, &hash_final);
 
 	/* write it at the end of the file */
 	return git_filebuf_write(file, hash_final.id, GIT_OID_RAWSZ);
@@ -2953,6 +2988,7 @@ int git_indexwriter_init_for_operation(
 int git_indexwriter_commit(git_indexwriter *writer)
 {
 	int error;
+	git_oid checksum = {{ 0 }};
 
 	if (!writer->should_write)
 		return 0;
@@ -2962,7 +2998,7 @@ int git_indexwriter_commit(git_indexwriter *writer)
 
 	git_vector_sort(&writer->index->reuc);
 
-	if ((error = write_index(writer->index, &writer->file)) < 0) {
+	if ((error = write_index(&checksum, writer->index, &writer->file)) < 0) {
 		git_indexwriter_cleanup(writer);
 		return error;
 	}
@@ -2977,6 +3013,7 @@ int git_indexwriter_commit(git_indexwriter *writer)
 	}
 
 	writer->index->on_disk = 1;
+	git_oid_cpy(&writer->index->checksum, &checksum);
 
 	git_index_free(writer->index);
 	writer->index = NULL;
diff --git a/src/index.h b/src/index.h
index 0f6f4e86e..615d703c4 100644
--- a/src/index.h
+++ b/src/index.h
@@ -22,6 +22,7 @@ struct git_index {
 
 	char *index_file_path;
 	git_futils_filestamp stamp;
+	git_oid checksum;   /* checksum at the end of the file */
 
 	git_vector entries;