net/tls: Replace TLS_RX_SYNC_RUNNING with RCU

RCU synchronization is guaranteed to finish in finite time, unlike a
busy loop that polls a flag. This patch is a preparation for the bugfix
in the next patch, where the same synchronize_net() call will also be
used to sync with the TX datapath.
Signed-off-by: NMaxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: NTariq Toukan <tariqt@nvidia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/net/tls.h

@@ -193,7 +193,6 @@ struct tls_offload_context_tx {
 	(sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)
 
 enum tls_context_flags {
-	TLS_RX_SYNC_RUNNING = 0,
 	/* Unlike RX where resync is driven entirely by the core in TX only
 	 * the driver knows when things went out of sync, so we need the flag
 	 * to be atomic.

net/tls/tls_device.c

@@ -680,15 +680,13 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx,
 	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
 	struct net_device *netdev;
 
-	if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags)))
-		return;
-
 	trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type);
+	rcu_read_lock();
 	netdev = READ_ONCE(tls_ctx->netdev);
 	if (netdev)
 		netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn,
 						   TLS_OFFLOAD_CTX_DIR_RX);
-	clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags);
+	rcu_read_unlock();
 	TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC);
 }
 
@@ -1300,9 +1298,7 @@ static int tls_device_down(struct net_device *netdev)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_RX);
 		WRITE_ONCE(ctx->netdev, NULL);
-		smp_mb__before_atomic(); /* pairs with test_and_set_bit() */
-		while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags))
-			usleep_range(10, 200);
+		synchronize_net();
 		dev_put(netdev);
 		list_del_init(&ctx->list);