Commit 10d1b0e4 authored by Daniel Borkmann's avatar Daniel Borkmann
Browse files

Merge branch 'xdp-ice-mbuf' 



Maciej Fijalkowski says:

====================
Although this work started as an effort to add multi-buffer XDP support
to ice driver, as usual it turned out that some other side stuff needed
to be addressed, so let me give you an overview.

First patch adjusts legacy-rx in a way that it will be possible to refer
to skb_shared_info being at the end of the buffer when gathering up
frame fragments within xdp_buff.

Then, patches 2-9 prepare ice driver in a way that actual multi-buffer
patches will be easier to swallow.

10 and 11 are the meat. What is worth mentioning is that this set
actually *fixes* things as patch 11 removes the logic based on
next_dd/rs and we previously stepped away from this for ice_xmit_zc().
Currently, AF_XDP ZC XDP_TX workload is off as there are two cleaning
sides that can be triggered and two of them work on different internal
logic. This set unifies that and allows us to improve the performance by
2x with a trick on the last (13) patch.

12th is a simple cleanup of no longer fields from Tx ring.

I might be wrong but I have not seen anyone reporting performance impact
among patches that add XDP multi-buffer support to a particular driver.
Numbers below were gathered via xdp_rxq_info and xdp_redirect_map on
1500 MTU:

XDP_DROP      +1%
XDP_PASS      -1,2%
XDP_TX        -0,5%
XDP_REDIRECT  -3,3%

Cherry on top, which is not directly related to mbuf support (last
patch):

XDP_TX ZC +126%

Target the we agreed on was to not degrade performance for any action by
anything that would be over 5%, so our goal was met. Basically this set
keeps the performance where it was. Redirect is slower due to more
frequent tail bumps.
====================

Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Reviewed-by: default avatarAlexander Lobakin <alexandr.lobakin@intel.com>
parents c1a3daf7 a24b4c6e

drivers/net/ethernet/intel/ice/ice_base.c

+12 −9
Original line number Diff line number Diff line
@@ -355,9 +355,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) 
{

	if (ice_ring_uses_build_skb(rx_ring))

		return ICE_SKB_PAD;

	else if (ice_is_xdp_ena_vsi(rx_ring->vsi))

		return XDP_PACKET_HEADROOM;



	return 0;

}
@@ -495,7 +492,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) 
int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)

{

	struct device *dev = ice_pf_to_dev(ring->vsi->back);

	u16 num_bufs = ICE_DESC_UNUSED(ring);

	u32 num_bufs = ICE_RX_DESC_UNUSED(ring);

	int err;



	ring->rx_buf_len = ring->vsi->rx_buf_len;
@@ -503,8 +500,10 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) 
	if (ring->vsi->type == ICE_VSI_PF) {

		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))

			/* coverity[check_return] */

			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,

					 ring->q_index, ring->q_vector->napi.napi_id);

			__xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,

					   ring->q_index,

					   ring->q_vector->napi.napi_id,

					   ring->vsi->rx_buf_len);



		ring->xsk_pool = ice_xsk_pool(ring);

		if (ring->xsk_pool) {
@@ -524,9 +523,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) 
		} else {

			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))

				/* coverity[check_return] */

				xdp_rxq_info_reg(&ring->xdp_rxq,

				__xdp_rxq_info_reg(&ring->xdp_rxq,

						   ring->netdev,

						 ring->q_index, ring->q_vector->napi.napi_id);

						   ring->q_index,

						   ring->q_vector->napi.napi_id,

						   ring->vsi->rx_buf_len);



			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,

							 MEM_TYPE_PAGE_SHARED,
@@ -536,6 +537,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) 
		}

	}



	xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);

	ring->xdp.data = NULL;

	err = ice_setup_rx_ctx(ring);

	if (err) {

		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",

drivers/net/ethernet/intel/ice/ice_ethtool.c

+1 −3
Original line number Diff line number Diff line
@@ -3046,8 +3046,6 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, 
		/* clone ring and setup updated count */

		xdp_rings[i] = *vsi->xdp_rings[i];

		xdp_rings[i].count = new_tx_cnt;

		xdp_rings[i].next_dd = ICE_RING_QUARTER(&xdp_rings[i]) - 1;

		xdp_rings[i].next_rs = ICE_RING_QUARTER(&xdp_rings[i]) - 1;

		xdp_rings[i].desc = NULL;

		xdp_rings[i].tx_buf = NULL;

		err = ice_setup_tx_ring(&xdp_rings[i]);
@@ -3092,7 +3090,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, 


		/* allocate Rx buffers */

		err = ice_alloc_rx_bufs(&rx_rings[i],

					ICE_DESC_UNUSED(&rx_rings[i]));

					ICE_RX_DESC_UNUSED(&rx_rings[i]));

rx_unwind:

		if (err) {

			while (i) {

drivers/net/ethernet/intel/ice/ice_lib.c

+2 −6
Original line number Diff line number Diff line
@@ -1992,8 +1992,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi) 
void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)

{

	if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) {

		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;

		vsi->rx_buf_len = ICE_RXBUF_2048;

		vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX;

		vsi->rx_buf_len = ICE_RXBUF_1664;

#if (PAGE_SIZE < 8192)

	} else if (!ICE_2K_TOO_SMALL_WITH_PADDING &&

		   (vsi->netdev->mtu <= ETH_DATA_LEN)) {
@@ -2002,11 +2002,7 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) 
#endif

	} else {

		vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX;

#if (PAGE_SIZE < 8192)

		vsi->rx_buf_len = ICE_RXBUF_3072;

#else

		vsi->rx_buf_len = ICE_RXBUF_2048;

#endif

	}

}

drivers/net/ethernet/intel/ice/ice_main.c

+28 −19
Original line number Diff line number Diff line
@@ -2570,8 +2570,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) 
		xdp_ring->netdev = NULL;

		xdp_ring->dev = dev;

		xdp_ring->count = vsi->num_tx_desc;

		xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1;

		xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1;

		WRITE_ONCE(vsi->xdp_rings[i], xdp_ring);

		if (ice_setup_tx_ring(xdp_ring))

			goto free_xdp_rings;
@@ -2862,6 +2860,18 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) 
	return 0;

}



/**

 * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP

 * @vsi: Pointer to VSI structure

 */

static int ice_max_xdp_frame_size(struct ice_vsi *vsi)

{

	if (test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))

		return ICE_RXBUF_1664;

	else

		return ICE_RXBUF_3072;

}



/**

 * ice_xdp_setup_prog - Add or remove XDP eBPF program

 * @vsi: VSI to setup XDP for
@@ -2872,14 +2882,17 @@ static int 
ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,

		   struct netlink_ext_ack *extack)

{

	int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;

	unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;

	bool if_running = netif_running(vsi->netdev);

	int ret = 0, xdp_ring_err = 0;



	if (frame_size > vsi->rx_buf_len) {

		NL_SET_ERR_MSG_MOD(extack, "MTU too large for loading XDP");

	if (prog && !prog->aux->xdp_has_frags) {

		if (frame_size > ice_max_xdp_frame_size(vsi)) {

			NL_SET_ERR_MSG_MOD(extack,

					   "MTU is too large for linear frames and XDP prog does not support frags");

			return -EOPNOTSUPP;

		}

	}



	/* need to stop netdev while setting up the program for Rx rings */

	if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
@@ -7330,18 +7343,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) 
	dev_err(dev, "Rebuild failed, unload and reload driver\n");

}



/**

 * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP

 * @vsi: Pointer to VSI structure

 */

static int ice_max_xdp_frame_size(struct ice_vsi *vsi)

{

	if (PAGE_SIZE >= 8192 || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags))

		return ICE_RXBUF_2048 - XDP_PACKET_HEADROOM;

	else

		return ICE_RXBUF_3072;

}



/**

 * ice_change_mtu - NDO callback to change the MTU

 * @netdev: network interface device structure
@@ -7354,6 +7355,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) 
	struct ice_netdev_priv *np = netdev_priv(netdev);

	struct ice_vsi *vsi = np->vsi;

	struct ice_pf *pf = vsi->back;

	struct bpf_prog *prog;

	u8 count = 0;

	int err = 0;
@@ -7362,7 +7364,8 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) 
		return 0;

	}



	if (ice_is_xdp_ena_vsi(vsi)) {

	prog = vsi->xdp_prog;

	if (prog && !prog->aux->xdp_has_frags) {

		int frame_size = ice_max_xdp_frame_size(vsi);



		if (new_mtu + ICE_ETH_PKT_HDR_PAD > frame_size) {
@@ -7370,6 +7373,12 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) 
				   frame_size - ICE_ETH_PKT_HDR_PAD);

			return -EINVAL;

		}

	} else if (test_bit(ICE_FLAG_LEGACY_RX, pf->flags)) {

		if (new_mtu + ICE_ETH_PKT_HDR_PAD > ICE_MAX_FRAME_LEGACY_RX) {

			netdev_err(netdev, "Too big MTU for legacy-rx; Max is %d\n",

				   ICE_MAX_FRAME_LEGACY_RX - ICE_ETH_PKT_HDR_PAD);

			return -EINVAL;

		}

	}



	/* if a reset is in progress, wait for some time for it to complete */

drivers/net/ethernet/intel/ice/ice_txrx.c

+219 −189

File changed.

Preview size limit exceeded, changes collapsed.