From 74b052f8c269ef0b6f61a5ecf04a8568399345d9 Mon Sep 17 00:00:00 2001 From: Matheus Tavares Date: Mon, 28 Sep 2020 21:01:52 -0300 Subject: [PATCH 1/2] packfile: fix race condition on unpack_entry() The third phase of unpack_entry() performs the following sequence in a loop, until all the deltas enumerated in phase one are applied and the entry is fully reconstructed: 1. Add the current base entry to the delta base cache 2. Unpack the next delta 3. Patch the unpacked delta on top of the base When the optional object reading lock is enabled, the above steps will be performed while holding the lock. However, step 2. momentarily releases it so that inflation can be performed in parallel for increased performance. Because the `base` buffer inserted in the cache at 1. is not duplicated, another thread can potentially free() it while the lock is released at 2. (e.g. when there is no space left in the cache to insert another entry). In this case, the later attempt to dereference `base` at 3. will cause a segmentation fault. This problem was observed during a multithreaded git-grep execution on a repository with large objects. To fix the race condition (and later segmentation fault), let's reorder the aforementioned steps so that `base` is only added to the cache at the end. This will prevent the buffer from being released by another thread while it is still in use. An alternative solution which would not require the reordering would be to duplicate `base` before inserting it in the cache. However, as Phil Hord mentioned, memcpy()'ing large bases can negatively affect performance: in his experiments, this alternative approach slowed git-grep down by 10% to 20%. Reported-by: Phil Hord Signed-off-by: Matheus Tavares Signed-off-by: Junio C Hamano --- packfile.c | 41 ++++++++++++++++++++++++----------------- 1 file changed, 24 insertions(+), 17 deletions(-) diff --git a/packfile.c b/packfile.c index 6ab5233613..bfe76b2119 100644 --- a/packfile.c +++ b/packfile.c @@ -1764,12 +1764,10 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset, void *external_base = NULL; unsigned long delta_size, base_size = size; int i; + off_t base_obj_offset = obj_offset; data = NULL; - if (base) - add_delta_base_cache(p, obj_offset, base, base_size, type); - if (!base) { /* * We're probably in deep shit, but let's try to fetch @@ -1807,24 +1805,33 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset, "at offset %"PRIuMAX" from %s", (uintmax_t)curpos, p->pack_name); data = NULL; - free(external_base); - continue; + } else { + data = patch_delta(base, base_size, delta_data, + delta_size, &size); + + /* + * We could not apply the delta; warn the user, but + * keep going. Our failure will be noticed either in + * the next iteration of the loop, or if this is the + * final delta, in the caller when we return NULL. + * Those code paths will take care of making a more + * explicit warning and retrying with another copy of + * the object. + */ + if (!data) + error("failed to apply delta"); } - data = patch_delta(base, base_size, - delta_data, delta_size, - &size); - /* - * We could not apply the delta; warn the user, but keep going. - * Our failure will be noticed either in the next iteration of - * the loop, or if this is the final delta, in the caller when - * we return NULL. Those code paths will take care of making - * a more explicit warning and retrying with another copy of - * the object. + * We delay adding `base` to the cache until the end of the loop + * because unpack_compressed_entry() momentarily releases the + * obj_read_mutex, giving another thread the chance to access + * the cache. Therefore, if `base` was already there, this other + * thread could free() it (e.g. to make space for another entry) + * before we are done using it. */ - if (!data) - error("failed to apply delta"); + if (!external_base) + add_delta_base_cache(p, base_obj_offset, base, base_size, type); free(delta_data); free(external_base); From bda959c4766d73ab435f26f2cc7c8c67b9443f5a Mon Sep 17 00:00:00 2001 From: Matheus Tavares Date: Mon, 28 Sep 2020 21:01:53 -0300 Subject: [PATCH 2/2] packfile: fix memory leak in add_delta_base_cache() When add_delta_base_cache() is called with a base that is already in the cache, no operation is performed. But the check is done after allocating space for a new entry, so we end up leaking memory on the early return. In addition, the caller never free()'s the base as it expects the function to take ownership of it. But the base is not released when we skip insertion, so it also gets leaked. To fix these problems, move the allocation of a new entry further down in add_delta_base_cache(), and free() the base on early return. Signed-off-by: Matheus Tavares Signed-off-by: Junio C Hamano --- packfile.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/packfile.c b/packfile.c index bfe76b2119..06d51eddac 100644 --- a/packfile.c +++ b/packfile.c @@ -1463,7 +1463,7 @@ void clear_delta_base_cache(void) static void add_delta_base_cache(struct packed_git *p, off_t base_offset, void *base, unsigned long base_size, enum object_type type) { - struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent)); + struct delta_base_cache_entry *ent; struct list_head *lru, *tmp; /* @@ -1471,8 +1471,10 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset, * is unpacking the same object, in unpack_entry() (since its phases I * and III might run concurrently across multiple threads). */ - if (in_delta_base_cache(p, base_offset)) + if (in_delta_base_cache(p, base_offset)) { + free(base); return; + } delta_base_cached += base_size; @@ -1484,6 +1486,7 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset, release_delta_base_cache(f); } + ent = xmalloc(sizeof(*ent)); ent->key.p = p; ent->key.base_offset = base_offset; ent->type = type;