summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/devmap.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/devmap.c')
-rw-r--r--kernel/bpf/devmap.c29
1 files changed, 16 insertions, 13 deletions
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index de630f980282..58bdca5d978a 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -190,10 +190,12 @@ static void dev_map_free(struct bpf_map *map)
/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
- * disconnected from events. Wait for outstanding critical sections in
- * these programs to complete. The rcu critical section only guarantees
- * no further reads against netdev_map. It does __not__ ensure pending
- * flush operations (if any) are complete.
+ * disconnected from events. The following synchronize_rcu() guarantees
+ * both rcu read critical sections complete and waits for
+ * preempt-disable regions (NAPI being the relevant context here) so we
+ * are certain there will be no further reads against the netdev_map and
+ * all flush operations are complete. Flush operations can only be done
+ * from NAPI context for this reason.
*/
spin_lock(&dev_map_lock);
@@ -263,7 +265,8 @@ struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
struct hlist_head *head = dev_map_index_hash(dtab, key);
struct bpf_dtab_netdev *dev;
- hlist_for_each_entry_rcu(dev, head, index_hlist)
+ hlist_for_each_entry_rcu(dev, head, index_hlist,
+ lockdep_is_held(&dtab->index_lock))
if (dev->idx == key)
return dev;
@@ -363,16 +366,17 @@ error:
* from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
* net device can be torn down. On devmap tear down we ensure the flush list
* is empty before completing to ensure all flush operations have completed.
+ * When drivers update the bpf program they may need to ensure any flush ops
+ * are also complete. Using synchronize_rcu or call_rcu will suffice for this
+ * because both wait for napi context to exit.
*/
void __dev_flush(void)
{
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq, *tmp;
- rcu_read_lock();
list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
bq_xmit_all(bq, XDP_XMIT_FLUSH);
- rcu_read_unlock();
}
/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
@@ -502,12 +506,11 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key)
return -EINVAL;
/* Use call_rcu() here to ensure any rcu critical sections have
- * completed, but this does not guarantee a flush has happened
- * yet. Because driver side rcu_read_lock/unlock only protects the
- * running XDP program. However, for pending flush operations the
- * dev and ctx are stored in another per cpu map. And additionally,
- * the driver tear down ensures all soft irqs are complete before
- * removing the net device in the case of dev_put equals zero.
+ * completed as well as any flush operations because call_rcu
+ * will wait for preempt-disable region to complete, NAPI in this
+ * context. And additionally, the driver tear down ensures all
+ * soft irqs are complete before removing the net device in the
+ * case of dev_put equals zero.
*/
old_dev = xchg(&dtab->netdev_map[k], NULL);
if (old_dev)