[PATCH 14/24] pseudo-merge: scaffolding for reads

From: Taylor Blau <me@ttaylorr.com>
Date: Mar 20, 2024, 22:05 UTC
Message-ID: <7e4d051f37a42e9e44b13acfc60b42fbb2a891b5.1710972293.git.me@ttaylorr.com>
In-Reply-To: <cover.1710972293.git.me@ttaylorr.com>

Implement scaffolding within the new pseudo-merge compilation unit necessary to use the pseudo-merge API from within the pack-bitmap.c machinery.

The core of this scaffolding is two-fold:

  - The `pseudo_merge` structure itself, which represents an individual
    pseudo-merge bitmap. It has fields for both bitmaps, as well as
    metadata about its position within the memory-mapped region, and
    a few extra bits indicating whether or not it is satisfied, and
    which bitmaps(s, if any) have been read, since they are initialized
    lazily.

  - The `pseudo_merge_map` structure, which holds an array of
    pseudo_merges, as well as a pointer to the memory-mapped region
    containing the pseudo-merge serialization from within a .bitmap
    file.

Note that the `bitmap_index` structure is defined statically within the pack-bitmap.o compilation unit, so we can't take in a `struct bitmap_index *`. Instead, wrap the primary components necessary to read the pseudo-merges in this new structure to avoid exposing the implementation details of the `bitmap_index` structure.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 pseudo-merge.c | 10 ++++++++
 pseudo-merge.h | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/pseudo-merge.c b/pseudo-merge.c
index caccef942a1..d18de0a266b 100644
--- a/pseudo-merge.c
+++ b/pseudo-merge.c
@@ -441,3 +441,13 @@ void select_pseudo_merges(struct string_list *list,
 
 	stop_progress(&progress);
 }
+
+void free_pseudo_merge_map(struct pseudo_merge_map *pm)
+{
+	uint32_t i;
+	for (i = 0; i < pm->nr; i++) {
+		ewah_pool_free(pm->v[i].commits);
+		ewah_pool_free(pm->v[i].bitmap);
+	}
+	free(pm->v);
+}
diff --git a/pseudo-merge.h b/pseudo-merge.h
index 81888731864..2f652fc6767 100644
--- a/pseudo-merge.h
+++ b/pseudo-merge.h
@@ -99,4 +99,69 @@ void select_pseudo_merges(struct string_list *list,
 			  uint32_t *pseudo_merges_nr,
 			  unsigned show_progress);
 
+/*
+ * Represents a serialized view of a file containing pseudo-merge(s)
+ * (see Documentation/technical/bitmap-format.txt for a specification
+ * of the format).
+ */
+struct pseudo_merge_map {
+	/*
+	 * An array of pseudo-merge(s), lazily loaded from the .bitmap
+	 * file.
+	 */
+	struct pseudo_merge *v;
+	size_t nr;
+	size_t commits_nr;
+
+	/*
+	 * Pointers into a memory-mapped view of the .bitmap file:
+	 *
+	 *   - map: the beginning of the .bitmap file
+	 *   - commits: the beginning of the pseudo-merge commit index
+	 *   - map_size: the size of the .bitmap file
+	 */
+	const unsigned char *map;
+	const unsigned char *commits;
+
+	size_t map_size;
+};
+
+/*
+ * An individual pseudo-merge, storing a pair of lazily-loaded
+ * bitmaps:
+ *
+ *  - commits: the set of commit(s) that are part of the pseudo-merge
+ *  - bitmap: the set of object(s) reachable from the above set of
+ *    commits.
+ *
+ * The `at` and `bitmap_at` fields are used to store the locations of
+ * each of the above bitmaps in the .bitmap file.
+ */
+struct pseudo_merge {
+	struct ewah_bitmap *commits;
+	struct ewah_bitmap *bitmap;
+
+	off_t at;
+	off_t bitmap_at;
+
+	/*
+	 * `satisfied` indicates whether the given pseudo-merge has been
+	 * used.
+	 *
+	 * `loaded_commits` and `loaded_bitmap` indicate whether the
+	 * respective bitmaps have been loaded and read from the
+	 * .bitmap file.
+	 */
+	unsigned satisfied : 1,
+		 loaded_commits : 1,
+		 loaded_bitmap : 1;
+};
+
+/*
+ * Frees the given pseudo-merge map, releasing any memory held by (a)
+ * parsed EWAH bitmaps, or (b) the array of pseudo-merges itself. Does
+ * not free the memory-mapped view of the .bitmap file.
+ */
+void free_pseudo_merge_map(struct pseudo_merge_map *pm);
+
 #endif

-- 
2.44.0.303.g1dc5e5b124c