block alloc: add validations around cache_entry lifecyle

Add an option (controlled by an environment variable) perform extra
validations on mem_pool allocated cache entries. When set:

  1) Invalidate cache_entry memory when discarding cache_entry.

  2) When discarding index_state struct, verify that all cache_entries
     were allocated from expected mem_pool.

  3) When discarding mem_pools, invalidate mem_pool memory.

This should provide extra checks that mem_pools and their allocated
cache_entries are being used as expected.

Signed-off-by: Jameson Miller <jamill@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 68 insertions, 4 deletions

diff --git a/cache.h b/cache.h
index c1c7e9e65f..a3334a71ca 100644
--- a/cache.h
+++ b/cache.h
@@ -381,6 +381,12 @@ struct cache_entry *make_empty_transient_cache_entry(size_t name_len);
 void discard_cache_entry(struct cache_entry *ce);
 
 /*
+ * Check configuration if we should perform extra validation on cache
+ * entries.
+ */
+int should_validate_cache_entries(void);
+
+/*
  * Duplicate a cache_entry. Allocate memory for the new entry from a
  * memory_pool. Takes into account cache_entry fields that are meant
  * for managing the underlying memory allocation of the cache_entry.
diff --git a/git.c b/git.c
index c2f48d53dd..010898ba6d 100644
--- a/git.c
+++ b/git.c
@@ -414,7 +414,10 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 
 	trace_argv_printf(argv, "trace: built-in: git");
 
+	validate_cache_entries(&the_index);
 	status = p->fn(argc, argv, prefix);
+	validate_cache_entries(&the_index);
+
 	if (status)
 		return status;
 
diff --git a/mem-pool.c b/mem-pool.c
index 139617cb23..a2841a4a9a 100644
--- a/mem-pool.c
+++ b/mem-pool.c
@@ -50,7 +50,7 @@ void mem_pool_init(struct mem_pool **mem_pool, size_t initial_size)
 	*mem_pool = pool;
 }
 
-void mem_pool_discard(struct mem_pool *mem_pool)
+void mem_pool_discard(struct mem_pool *mem_pool, int invalidate_memory)
 {
 	struct mp_block *block, *block_to_free;
 
@@ -59,6 +59,10 @@ void mem_pool_discard(struct mem_pool *mem_pool)
 	{
 		block_to_free = block;
 		block = block->next_block;
+
+		if (invalidate_memory)
+			memset(block_to_free->space, 0xDD, ((char *)block_to_free->end) - ((char *)block_to_free->space));
+
 		free(block_to_free);
 	}
 
diff --git a/mem-pool.h b/mem-pool.h
index adeefdcb28..999d3c3a52 100644
--- a/mem-pool.h
+++ b/mem-pool.h
@@ -29,7 +29,7 @@ void mem_pool_init(struct mem_pool **mem_pool, size_t initial_size);
 /*
  * Discard a memory pool and free all the memory it is responsible for.
  */
-void mem_pool_discard(struct mem_pool *mem_pool);
+void mem_pool_discard(struct mem_pool *mem_pool, int invalidate_memory);
 
 /*
  * Alloc memory from the mem_pool.
diff --git a/read-cache.c b/read-cache.c
index b07369660b..fd67e2e8a4 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -2050,8 +2050,10 @@ int discard_index(struct index_state *istate)
 	 * Cache entries in istate->cache[] should have been allocated
 	 * from the memory pool associated with this index, or from an
 	 * associated split_index. There is no need to free individual
-	 * cache entries.
+	 * cache entries. validate_cache_entries can detect when this
+	 * assertion does not hold.
 	 */
+	validate_cache_entries(istate);
 
 	resolve_undo_clear_index(istate);
 	istate->cache_nr = 0;
@@ -2068,13 +2070,45 @@ int discard_index(struct index_state *istate)
 	istate->untracked = NULL;
 
 	if (istate->ce_mem_pool) {
-		mem_pool_discard(istate->ce_mem_pool);
+		mem_pool_discard(istate->ce_mem_pool, should_validate_cache_entries());
 		istate->ce_mem_pool = NULL;
 	}
 
 	return 0;
 }
 
+/*
+ * Validate the cache entries of this index.
+ * All cache entries associated with this index
+ * should have been allocated by the memory pool
+ * associated with this index, or by a referenced
+ * split index.
+ */
+void validate_cache_entries(const struct index_state *istate)
+{
+	int i;
+
+	if (!should_validate_cache_entries() ||!istate || !istate->initialized)
+		return;
+
+	for (i = 0; i < istate->cache_nr; i++) {
+		if (!istate) {
+			die("internal error: cache entry is not allocated from expected memory pool");
+		} else if (!istate->ce_mem_pool ||
+			!mem_pool_contains(istate->ce_mem_pool, istate->cache[i])) {
+			if (!istate->split_index ||
+				!istate->split_index->base ||
+				!istate->split_index->base->ce_mem_pool ||
+				!mem_pool_contains(istate->split_index->base->ce_mem_pool, istate->cache[i])) {
+				die("internal error: cache entry is not allocated from expected memory pool");
+			}
+		}
+	}
+
+	if (istate->split_index)
+		validate_cache_entries(istate->split_index->base);
+}
+
 int unmerged_index(const struct index_state *istate)
 {
 	int i;
@@ -2878,8 +2912,25 @@ struct cache_entry *dup_cache_entry(const struct cache_entry *ce,
 
 void discard_cache_entry(struct cache_entry *ce)
 {
+	if (ce && should_validate_cache_entries())
+		memset(ce, 0xCD, cache_entry_size(ce->ce_namelen));
+
 	if (ce && ce->mem_pool_allocated)
 		return;
 
 	free(ce);
 }
+
+int should_validate_cache_entries(void)
+{
+	static int validate_index_cache_entries = -1;
+
+	if (validate_index_cache_entries < 0) {
+		if (getenv("GIT_TEST_VALIDATE_INDEX_CACHE_ENTRIES"))
+			validate_index_cache_entries = 1;
+		else
+			validate_index_cache_entries = 0;
+	}
+
+	return validate_index_cache_entries;
+}