Re: bpf: use-after-free in array_map_alloc

[Tejun Heo]

Hello,

Can you please test whether this patch resolves the issue?  While
adding support for atomic allocations, I reduced alloc_mutex covered
region too much.

Thanks.

diff --git a/mm/percpu.c b/mm/percpu.c
index 0c59684..bd2df70 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -162,7 +162,7 @@ static struct pcpu_chunk *pcpu_reserved_chunk;
 static int pcpu_reserved_chunk_limit;
 
 static DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
-static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
+static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop, map extension */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
 
@@ -435,6 +435,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
+	lockdep_assert_held(&pcpu_alloc_mutex);
+
 	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
@@ -895,6 +897,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
+	if (!is_atomic)
+		mutex_lock(&pcpu_alloc_mutex);
+
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
@@ -967,12 +972,11 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	if (is_atomic)
 		goto fail;
 
-	mutex_lock(&pcpu_alloc_mutex);
+	lockdep_assert_held(&pcpu_alloc_mutex);
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
 		chunk = pcpu_create_chunk();
 		if (!chunk) {
-			mutex_unlock(&pcpu_alloc_mutex);
 			err = "failed to allocate new chunk";
 			goto fail;
 		}
@@ -983,7 +987,6 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		spin_lock_irqsave(&pcpu_lock, flags);
 	}
 
-	mutex_unlock(&pcpu_alloc_mutex);
 	goto restart;
 
 area_found:
@@ -993,8 +996,6 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	if (!is_atomic) {
 		int page_start, page_end, rs, re;
 
-		mutex_lock(&pcpu_alloc_mutex);
-
 		page_start = PFN_DOWN(off);
 		page_end = PFN_UP(off + size);
 
@@ -1005,7 +1006,6 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
-				mutex_unlock(&pcpu_alloc_mutex);
 				pcpu_free_area(chunk, off, &occ_pages);
 				err = "failed to populate";
 				goto fail_unlock;
@@ -1045,6 +1045,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		/* see the flag handling in pcpu_blance_workfn() */
 		pcpu_atomic_alloc_failed = true;
 		pcpu_schedule_balance_work();
+	} else {
+		mutex_unlock(&pcpu_alloc_mutex);
 	}
 	return NULL;
 }
@@ -1137,6 +1139,8 @@ static void pcpu_balance_workfn(struct work_struct *work)
 	list_for_each_entry_safe(chunk, next, &to_free, list) {
 		int rs, re;
 
+		cancel_work_sync(&chunk->map_extend_work);
+
 		pcpu_for_each_pop_region(chunk, rs, re, 0, pcpu_unit_pages) {
 			pcpu_depopulate_chunk(chunk, rs, re);
 			spin_lock_irq(&pcpu_lock);