bpf: allow struct bpf_wq to be embedded in arraymaps and hashmaps

Currently bpf_wq_cancel_and_free() is just a placeholder as there is
no memory allocation for bpf_wq just yet.

Again, duplication of the bpf_timer approach
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
Link: https://lore.kernel.org/r/20240420-bpf_wq-v2-9-6c986a5a741f@kernel.orgSigned-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -534,6 +534,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
 void bpf_timer_cancel_and_free(void *timer);
+void bpf_wq_cancel_and_free(void *timer);
 void bpf_list_head_free(const struct btf_field *field, void *list_head,
 			struct bpf_spin_lock *spin_lock);
 void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
@@ -2204,6 +2205,7 @@ void bpf_map_free_record(struct bpf_map *map);
 struct btf_record *btf_record_dup(const struct btf_record *rec);
 bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
 void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
+void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj);
 void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
 void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
 

kernel/bpf/arraymap.c

@@ -428,17 +428,21 @@ static void *array_map_vmalloc_addr(struct bpf_array *array)
 	return (void *)round_down((unsigned long)array, PAGE_SIZE);
 }
 
-static void array_map_free_timers(struct bpf_map *map)
+static void array_map_free_timers_wq(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
-	/* We don't reset or free fields other than timer on uref dropping to zero. */
-	if (!btf_record_has_field(map->record, BPF_TIMER))
-		return;
+	/* We don't reset or free fields other than timer and workqueue
+	 * on uref dropping to zero.
+	 */
+	if (btf_record_has_field(map->record, BPF_TIMER))
+		for (i = 0; i < array->map.max_entries; i++)
+			bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i));
 
-	for (i = 0; i < array->map.max_entries; i++)
-		bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i));
+	if (btf_record_has_field(map->record, BPF_WORKQUEUE))
+		for (i = 0; i < array->map.max_entries; i++)
+			bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i));
 }
 
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
@@ -782,7 +786,7 @@ const struct bpf_map_ops array_map_ops = {
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
 	.map_get_next_key = array_map_get_next_key,
-	.map_release_uref = array_map_free_timers,
+	.map_release_uref = array_map_free_timers_wq,
 	.map_lookup_elem = array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,

kernel/bpf/hashtab.c

@@ -240,6 +240,26 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab)
 	}
 }
 
+static void htab_free_prealloced_wq(struct bpf_htab *htab)
+{
+	u32 num_entries = htab->map.max_entries;
+	int i;
+
+	if (!btf_record_has_field(htab->map.record, BPF_WORKQUEUE))
+		return;
+	if (htab_has_extra_elems(htab))
+		num_entries += num_possible_cpus();
+
+	for (i = 0; i < num_entries; i++) {
+		struct htab_elem *elem;
+
+		elem = get_htab_elem(htab, i);
+		bpf_obj_free_workqueue(htab->map.record,
+				       elem->key + round_up(htab->map.key_size, 8));
+		cond_resched();
+	}
+}
+
 static void htab_free_prealloced_fields(struct bpf_htab *htab)
 {
 	u32 num_entries = htab->map.max_entries;
@@ -1495,7 +1515,7 @@ static void delete_all_elements(struct bpf_htab *htab)
 	migrate_enable();
 }
 
-static void htab_free_malloced_timers(struct bpf_htab *htab)
+static void htab_free_malloced_timers_or_wq(struct bpf_htab *htab, bool is_timer)
 {
 	int i;
 
@@ -1507,24 +1527,35 @@ static void htab_free_malloced_timers(struct bpf_htab *htab)
 
 		hlist_nulls_for_each_entry(l, n, head, hash_node) {
 			/* We only free timer on uref dropping to zero */
-			bpf_obj_free_timer(htab->map.record, l->key + round_up(htab->map.key_size, 8));
+			if (is_timer)
+				bpf_obj_free_timer(htab->map.record,
+						   l->key + round_up(htab->map.key_size, 8));
+			else
+				bpf_obj_free_workqueue(htab->map.record,
+						       l->key + round_up(htab->map.key_size, 8));
 		}
 		cond_resched_rcu();
 	}
 	rcu_read_unlock();
 }
 
-static void htab_map_free_timers(struct bpf_map *map)
+static void htab_map_free_timers_and_wq(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 
-	/* We only free timer on uref dropping to zero */
-	if (!btf_record_has_field(htab->map.record, BPF_TIMER))
-		return;
-	if (!htab_is_prealloc(htab))
-		htab_free_malloced_timers(htab);
-	else
-		htab_free_prealloced_timers(htab);
+	/* We only free timer and workqueue on uref dropping to zero */
+	if (btf_record_has_field(htab->map.record, BPF_TIMER)) {
+		if (!htab_is_prealloc(htab))
+			htab_free_malloced_timers_or_wq(htab, true);
+		else
+			htab_free_prealloced_timers(htab);
+	}
+	if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) {
+		if (!htab_is_prealloc(htab))
+			htab_free_malloced_timers_or_wq(htab, false);
+		else
+			htab_free_prealloced_wq(htab);
+	}
 }
 
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
@@ -2260,7 +2291,7 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
-	.map_release_uref = htab_map_free_timers,
+	.map_release_uref = htab_map_free_timers_and_wq,
 	.map_lookup_elem = htab_map_lookup_elem,
 	.map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem,
 	.map_update_elem = htab_map_update_elem,
@@ -2281,7 +2312,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
 	.map_get_next_key = htab_map_get_next_key,
-	.map_release_uref = htab_map_free_timers,
+	.map_release_uref = htab_map_free_timers_and_wq,
 	.map_lookup_elem = htab_lru_map_lookup_elem,
 	.map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem,
 	.map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys,

kernel/bpf/helpers.c

@@ -1468,6 +1468,14 @@ void bpf_timer_cancel_and_free(void *val)
 	kfree_rcu(t, cb.rcu);
 }
 
+/* This function is called by map_delete/update_elem for individual element and
+ * by ops->map_release_uref when the user space reference to a map reaches zero.
+ */
+void bpf_wq_cancel_and_free(void *val)
+{
+	BTF_TYPE_EMIT(struct bpf_wq);
+}
+
 BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
 {
 	unsigned long *kptr = map_value;

kernel/bpf/syscall.c

@@ -661,6 +661,13 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj)
 	bpf_timer_cancel_and_free(obj + rec->timer_off);
 }
 
+void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj)
+{
+	if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_WORKQUEUE)))
+		return;
+	bpf_wq_cancel_and_free(obj + rec->wq_off);
+}
+
 void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
 {
 	const struct btf_field *fields;
@@ -682,6 +689,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
 			bpf_timer_cancel_and_free(field_ptr);
 			break;
 		case BPF_WORKQUEUE:
+			bpf_wq_cancel_and_free(field_ptr);
 			break;
 		case BPF_KPTR_UNREF:
 			WRITE_ONCE(*(u64 *)field_ptr, 0);
@@ -1119,6 +1127,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
 				}
 				break;
 			case BPF_TIMER:
+			case BPF_WORKQUEUE:
 				if (map->map_type != BPF_MAP_TYPE_HASH &&
 				    map->map_type != BPF_MAP_TYPE_LRU_HASH &&
 				    map->map_type != BPF_MAP_TYPE_ARRAY) {