midx-write: only load initialized packs

The fill_packs_from_midx() method was refactored in fcb2205b77 (midx:
implement support for writing incremental MIDX chains, 2024-08-06) to
allow for preferred packfiles and incremental multi-pack-indexes.
However, this led to some conditions that can cause improperly
initialized memory in the context's list of packfiles.

The conditions caring about the preferred pack name or the incremental
flag are currently necessary to load a packfile. But the context is
still being populated with pack_info structs based on the packfile array
for the existing multi-pack-index even if prepare_midx_pack() isn't
called.

Add a new test that breaks under --stress when compiled with
SANITIZE=address. The chosen number of 100 packfiles was selected to get
the --stress output to fail about 50% of the time, while 50 packfiles
could not get a failure in most --stress runs.

The test case is marked as EXPENSIVE not only because of the number of
packfiles it creates, but because some CI environments were reporting
errors during the test that I could not reproduce, specifically around
being unable to open the packfiles or their pack-indexes.

When it fails under SANITIZE=address, it provides the following error:

AddressSanitizer:DEADLYSIGNAL
=================================================================
==3263517==ERROR: AddressSanitizer: SEGV on unknown address 0x000000000027
==3263517==The signal is caused by a READ memory access.
==3263517==Hint: address points to the zero page.
    #0 0x562d5d82d1fb in close_pack_windows packfile.c:299
    #1 0x562d5d82d3ab in close_pack packfile.c:354
    #2 0x562d5d7bfdb4 in write_midx_internal midx-write.c:1490
    #3 0x562d5d7c7aec in midx_repack midx-write.c:1795
    #4 0x562d5d46fff6 in cmd_multi_pack_index builtin/multi-pack-index.c:305
    ...

This failure stack trace is disconnected from the real fix because the bad
pointers are accessed later when closing the packfiles from the context.

There are a few different aspects to this fix that are worth noting:

 1. We return to the previous behavior of fill_packs_from_midx to not
    rely on the incremental flag or existence of a preferred pack.

 2. The behavior to scan all layers of an incremental midx is kept, so
    this is not a full revert of the change.

 3. We skip allocating more room in the pack_info array if the pack
    fails prepare_midx_pack().

 4. The method has always returned 0 for success and 1 for failure, but
    the condition checking for error added a check for a negative result
    for failure, so that is now updated.

 5. The call to open_pack_index() is removed, but this is needed later
    in the case of a preferred pack. That call is moved to immediately
    before its result is needed (checking for the object count).

Signed-off-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/midx-write.c b/midx-write.c
index ba4a94950a8314ce303125f983176208d1a019a1..8203b50da1e29075225250e5f43acdf5f9ae9b67 100644 (file)
--- a/midx-write.c
+++ b/midx-write.c
@@ -938,8 +938,7 @@ cleanup:
        return result;
 }
 
-static int fill_packs_from_midx(struct write_midx_context *ctx,
-                               const char *preferred_pack_name, uint32_t flags)
+static int fill_packs_from_midx(struct write_midx_context *ctx)
 {
        struct multi_pack_index *m;
 
@@ -947,30 +946,11 @@ static int fill_packs_from_midx(struct write_midx_context *ctx,
                uint32_t i;
 
                for (i = 0; i < m->num_packs; i++) {
-                       ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc);
-
-                       /*
-                        * If generating a reverse index, need to have
-                        * packed_git's loaded to compare their
-                        * mtimes and object count.
-                        *
-                        * If a preferred pack is specified, need to
-                        * have packed_git's loaded to ensure the chosen
-                        * preferred pack has a non-zero object count.
-                        */
-                       if (flags & MIDX_WRITE_REV_INDEX ||
-                           preferred_pack_name) {
-                               if (prepare_midx_pack(ctx->repo, m,
-                                                     m->num_packs_in_base + i)) {
-                                       error(_("could not load pack"));
-                                       return 1;
-                               }
-
-                               if (open_pack_index(m->packs[i]))
-                                       die(_("could not open index for %s"),
-                                           m->packs[i]->pack_name);
-                       }
+                       if (prepare_midx_pack(ctx->repo, m,
+                                             m->num_packs_in_base + i))
+                               return error(_("could not load pack"));
 
+                       ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc);
                        fill_pack_info(&ctx->info[ctx->nr++], m->packs[i],
                                       m->pack_names[i],
                                       m->num_packs_in_base + i);
@@ -1141,8 +1121,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir,
                        ctx.num_multi_pack_indexes_before++;
                        m = m->base_midx;
                }
-       } else if (ctx.m && fill_packs_from_midx(&ctx, preferred_pack_name,
-                                                flags) < 0) {
+       } else if (ctx.m && fill_packs_from_midx(&ctx)) {
                goto cleanup;
        }
 
@@ -1204,6 +1183,13 @@ static int write_midx_internal(struct repository *r, const char *object_dir,
                struct packed_git *oldest = ctx.info[ctx.preferred_pack_idx].p;
                ctx.preferred_pack_idx = 0;
 
+               /*
+                * Attempt opening the pack index to populate num_objects.
+                * Ignore failiures as they can be expected and are not
+                * fatal during this selection time.
+                */
+               open_pack_index(oldest);
+
                if (packs_to_drop && packs_to_drop->nr)
                        BUG("cannot write a MIDX bitmap during expiration");
 
@@ -1218,6 +1204,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir,
 
                        if (!oldest->num_objects || p->mtime < oldest->mtime) {
                                oldest = p;
+                               open_pack_index(oldest);
                                ctx.preferred_pack_idx = i;
                        }
                }
@@ -1241,6 +1228,11 @@ static int write_midx_internal(struct repository *r, const char *object_dir,
 
        if (ctx.preferred_pack_idx > -1) {
                struct packed_git *preferred = ctx.info[ctx.preferred_pack_idx].p;
+
+               if (open_pack_index(preferred))
+                       die(_("failed to open preferred pack %s"),
+                           ctx.info[ctx.preferred_pack_idx].pack_name);
+
                if (!preferred->num_objects) {
                        error(_("cannot select preferred pack %s with no objects"),
                              preferred->pack_name);

diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index bd75dea9501ed7ba98fd23ed24da8843022383b7..49705c62a25202c87535695b3b672cd614d0afdf 100755 (executable)
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -989,6 +989,23 @@ test_expect_success 'repack --batch-size=0 repacks everything' '
        )
 '
 
+test_expect_success EXPENSIVE 'repack/expire with many packs' '
+       cp -r dup many &&
+       (
+               cd many &&
+
+               for i in $(test_seq 1 100)
+               do
+                       test_commit extra$i &&
+                       git maintenance run --task=loose-objects || return 1
+               done &&
+
+               git multi-pack-index write &&
+               git multi-pack-index repack &&
+               git multi-pack-index expire
+       )
+'
+
 test_expect_success 'repack --batch-size=<large> repacks everything' '
        (
                cd dup2 &&