net/mlx4_en: add page recycle to prepare rx ring for tx support

The mlx4 driver by default allocates order-3 pages for the ring to
consume in multiple fragments. When the device has an xdp program, this
behavior will prevent tx actions since the page must be re-mapped in
TODEVICE mode, which cannot be done if the page is still shared.

Start by making the allocator configurable based on whether xdp is
running, such that order-0 pages are always used and never shared.

Since this will stress the page allocator, add a simple page cache to
each rx ring. Pages in the cache are left dma-mapped, and in drop-only
stress tests the page allocator is eliminated from the perf report.

Note that setting an xdp program will now require the rings to be
reconfigured.

Before:
 26.91%  ksoftirqd/0  [mlx4_en]         [k] mlx4_en_process_rx_cq
 17.88%  ksoftirqd/0  [mlx4_en]         [k] mlx4_en_alloc_frags
  6.00%  ksoftirqd/0  [mlx4_en]         [k] mlx4_en_free_frag
  4.49%  ksoftirqd/0  [kernel.vmlinux]  [k] get_page_from_freelist
  3.21%  swapper      [kernel.vmlinux]  [k] intel_idle
  2.73%  ksoftirqd/0  [kernel.vmlinux]  [k] bpf_map_lookup_elem
  2.57%  swapper      [mlx4_en]         [k] mlx4_en_process_rx_cq

After:
 31.72%  swapper      [kernel.vmlinux]       [k] intel_idle
  8.79%  swapper      [mlx4_en]              [k] mlx4_en_process_rx_cq
  7.54%  swapper      [kernel.vmlinux]       [k] poll_idle
  6.36%  swapper      [mlx4_core]            [k] mlx4_eq_int
  4.21%  swapper      [kernel.vmlinux]       [k] tasklet_action
  4.03%  swapper      [kernel.vmlinux]       [k] cpuidle_enter_state
  3.43%  swapper      [mlx4_en]              [k] mlx4_en_prepare_rx_desc
  2.18%  swapper      [kernel.vmlinux]       [k] native_irq_return_iret
  1.37%  swapper      [kernel.vmlinux]       [k] menu_select
  1.09%  swapper      [kernel.vmlinux]       [k] bpf_map_lookup_elem

Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 37 insertions, 1 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index c34a33d5ff4e..47ae2a211300 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2529,12 +2529,33 @@ static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 m
 static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
 	struct bpf_prog *old_prog;
 	int xdp_ring_num;
+	int port_up = 0;
+	int err;
 	int i;
 
 	xdp_ring_num = prog ? ALIGN(priv->rx_ring_num, MLX4_EN_NUM_UP) : 0;
 
+	/* No need to reconfigure buffers when simply swapping the
+	 * program for a new one.
+	 */
+	if (priv->xdp_ring_num == xdp_ring_num) {
+		if (prog) {
+			prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+		}
+		for (i = 0; i < priv->rx_ring_num; i++) {
+			/* This xchg is paired with READ_ONCE in the fastpath */
+			old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
+			if (old_prog)
+				bpf_prog_put(old_prog);
+		}
+		return 0;
+	}
+
 	if (priv->num_frags > 1) {
 		en_err(priv, "Cannot set XDP if MTU requires multiple frags\n");
 		return -EOPNOTSUPP;
@@ -2546,15 +2567,30 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 			return PTR_ERR(prog);
 	}
 
+	mutex_lock(&mdev->state_lock);
+	if (priv->port_up) {
+		port_up = 1;
+		mlx4_en_stop_port(dev, 1);
+	}
+
 	priv->xdp_ring_num = xdp_ring_num;
 
-	/* This xchg is paired with READ_ONCE in the fast path */
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		old_prog = xchg(&priv->rx_ring[i]->xdp_prog, prog);
 		if (old_prog)
 			bpf_prog_put(old_prog);
 	}
 
+	if (port_up) {
+		err = mlx4_en_start_port(dev);
+		if (err) {
+			en_err(priv, "Failed starting port %d for XDP change\n",
+			       priv->port);
+			queue_work(mdev->workqueue, &priv->watchdog_task);
+		}
+	}
+
+	mutex_unlock(&mdev->state_lock);
 	return 0;
 }