Netdev Archive on lore.kernel.org
 help / color / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: sameehj@amazon.com
Cc: thomas.petazzoni@bootlin.com,
	"Lorenzo Bianconi" <lorenzo@kernel.org>,
	"Jesper Dangaard Brouer" <brouer@redhat.com>,
	netdev@vger.kernel.org, bpf@vger.kernel.org, zorik@amazon.com,
	akiyano@amazon.com, gtzalik@amazon.com,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	"Daniel Borkmann" <borkmann@iogearbox.net>,
	"Alexei Starovoitov" <alexei.starovoitov@gmail.com>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Alexander Duyck" <alexander.duyck@gmail.com>,
	"Jeff Kirsher" <jeffrey.t.kirsher@intel.com>,
	"David Ahern" <dsahern@gmail.com>,
	"Willem de Bruijn" <willemdebruijn.kernel@gmail.com>,
	"Ilias Apalodimas" <ilias.apalodimas@linaro.org>,
	"Lorenzo Bianconi" <lorenzo@kernel.org>,
	"Saeed Mahameed" <saeedm@mellanox.com>,
	steffen.klassert@secunet.com
Subject: [PATCH net-next v2 04/33] mvneta: add XDP frame size to driver
Date: Thu, 30 Apr 2020 13:20:41 +0200
Message-ID: <158824564171.2172139.3559237147160461915.stgit@firesoul> (raw)
In-Reply-To: <158824557985.2172139.4173570969543904434.stgit@firesoul>

This marvell driver mvneta uses PAGE_SIZE frames, which makes it
really easy to convert.  Driver updates rxq and now frame_sz
once per NAPI call.

This driver takes advantage of page_pool PP_FLAG_DMA_SYNC_DEV that
can help reduce the number of cache-lines that need to be flushed
when doing DMA sync for_device. Due to xdp_adjust_tail can grow the
area accessible to the by the CPU (can possibly write into), then max
sync length *after* bpf_prog_run_xdp() needs to be taken into account.

For XDP_TX action the driver is smart and does DMA-sync. When growing
tail this is still safe, because page_pool have DMA-mapped the entire
page size.

Cc: thomas.petazzoni@bootlin.com
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 drivers/net/ethernet/marvell/mvneta.c |   25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 51889770958d..37947949345c 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2148,12 +2148,17 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	       struct bpf_prog *prog, struct xdp_buff *xdp,
 	       struct mvneta_stats *stats)
 {
-	unsigned int len;
+	unsigned int len, sync;
+	struct page *page;
 	u32 ret, act;
 
 	len = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
 	act = bpf_prog_run_xdp(prog, xdp);
 
+	/* Due xdp_adjust_tail: DMA sync for_device cover max len CPU touch */
+	sync = xdp->data_end - xdp->data_hard_start - pp->rx_offset_correction;
+	sync = max(sync, len);
+
 	switch (act) {
 	case XDP_PASS:
 		stats->xdp_pass++;
@@ -2164,9 +2169,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		err = xdp_do_redirect(pp->dev, xdp, prog);
 		if (unlikely(err)) {
 			ret = MVNETA_XDP_DROPPED;
-			page_pool_put_page(rxq->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(rxq->page_pool, page, sync, true);
 		} else {
 			ret = MVNETA_XDP_REDIR;
 			stats->xdp_redirect++;
@@ -2175,10 +2179,10 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	}
 	case XDP_TX:
 		ret = mvneta_xdp_xmit_back(pp, xdp);
-		if (ret != MVNETA_XDP_TX)
-			page_pool_put_page(rxq->page_pool,
-					   virt_to_head_page(xdp->data), len,
-					   true);
+		if (ret != MVNETA_XDP_TX) {
+			page = virt_to_head_page(xdp->data);
+			page_pool_put_page(rxq->page_pool, page, sync, true);
+		}
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -2187,8 +2191,8 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 		trace_xdp_exception(pp->dev, prog, act);
 		/* fall through */
 	case XDP_DROP:
-		page_pool_put_page(rxq->page_pool,
-				   virt_to_head_page(xdp->data), len, true);
+		page = virt_to_head_page(xdp->data);
+		page_pool_put_page(rxq->page_pool, page, sync, true);
 		ret = MVNETA_XDP_DROPPED;
 		stats->xdp_drop++;
 		break;
@@ -2320,6 +2324,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(pp->xdp_prog);
 	xdp_buf.rxq = &rxq->xdp_rxq;
+	xdp_buf.frame_sz = PAGE_SIZE;
 
 	/* Fairness NAPI loop */
 	while (rx_proc < budget && rx_proc < rx_todo) {



  parent reply index

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <158824557985.2172139.4173570969543904434.stgit@firesoul>
2020-04-30 11:20 ` [PATCH net-next v2 01/33] xdp: add frame size to xdp_buff Jesper Dangaard Brouer
2020-04-30 11:20 ` [PATCH net-next v2 02/33] bnxt: add XDP frame size to driver Jesper Dangaard Brouer
2020-04-30 11:20 ` [PATCH net-next v2 03/33] sfc: add XDP frame size Jesper Dangaard Brouer
2020-04-30 11:20 ` Jesper Dangaard Brouer [this message]
2020-04-30 11:20 ` [PATCH net-next v2 05/33] net: netsec: Add support for " Jesper Dangaard Brouer
2020-04-30 11:20 ` [PATCH net-next v2 06/33] net: XDP-generic determining " Jesper Dangaard Brouer
2020-04-30 11:20 ` [PATCH net-next v2 07/33] xdp: xdp_frame add member frame_sz and handle in convert_to_xdp_frame Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 08/33] xdp: cpumap redirect use frame_sz and increase skb_tailroom Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 09/33] veth: adjust hard_start offset on redirect XDP frames Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 10/33] veth: xdp using frame_sz in veth driver Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 11/33] dpaa2-eth: add XDP frame size Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 12/33] hv_netvsc: add XDP frame size to driver Jesper Dangaard Brouer
2020-04-30 14:20   ` Haiyang Zhang
2020-05-01 14:47     ` Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 13/33] qlogic/qede: " Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 14/33] net: ethernet: ti: add XDP frame size to driver cpsw Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 15/33] ena: add XDP frame size to amazon NIC driver Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 16/33] mlx4: add XDP frame size and adjust max XDP MTU Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 17/33] net: thunderx: add XDP frame size Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 18/33] nfp: add XDP frame size to netronome driver Jesper Dangaard Brouer
2020-04-30 11:21 ` [PATCH net-next v2 19/33] tun: add XDP frame size Jesper Dangaard Brouer
2020-05-06 20:32   ` Michael S. Tsirkin
2020-04-30 11:22 ` [PATCH net-next v2 20/33] vhost_net: also populate " Jesper Dangaard Brouer
2020-05-06  6:41   ` Jason Wang
2020-05-06  6:49     ` Jason Wang
2020-05-06 20:33   ` Michael S. Tsirkin
2020-04-30 11:22 ` [PATCH net-next v2 21/33] virtio_net: add XDP frame size in two code paths Jesper Dangaard Brouer
2020-05-06 20:34   ` Michael S. Tsirkin
2020-05-08  2:05     ` Jason Wang
2020-05-08  7:21       ` Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 22/33] ixgbe: fix XDP redirect on archs with PAGE_SIZE above 4K Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 23/33] ixgbe: add XDP frame size to driver Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 24/33] ixgbevf: add XDP frame size to VF driver Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 25/33] i40e: add XDP frame size to driver Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 26/33] ice: " Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 27/33] xdp: for Intel AF_XDP drivers add XDP frame_sz Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 28/33] mlx5: rx queue setup time determine frame_sz for XDP Jesper Dangaard Brouer
2020-04-30 17:07   ` Tariq Toukan
2020-04-30 17:12     ` Tariq Toukan
2020-05-01 12:32       ` Jesper Dangaard Brouer
2020-05-08 10:49         ` Jesper Dangaard Brouer
2020-05-01 13:01     ` Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 29/33] xdp: allow bpf_xdp_adjust_tail() to grow packet size Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 30/33] xdp: clear grow memory in bpf_xdp_adjust_tail() Jesper Dangaard Brouer
2020-04-30 11:22 ` [PATCH net-next v2 31/33] bpf: add xdp.frame_sz in bpf_prog_test_run_xdp() Jesper Dangaard Brouer
2020-04-30 11:23 ` [PATCH net-next v2 32/33] selftests/bpf: adjust BPF selftest for xdp_adjust_tail Jesper Dangaard Brouer
2020-04-30 11:23 ` [PATCH net-next v2 33/33] selftests/bpf: xdp_adjust_tail add grow tail tests Jesper Dangaard Brouer

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=158824564171.2172139.3559237147160461915.stgit@firesoul \
    --to=brouer@redhat.com \
    --cc=akiyano@amazon.com \
    --cc=alexander.duyck@gmail.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=borkmann@iogearbox.net \
    --cc=bpf@vger.kernel.org \
    --cc=dsahern@gmail.com \
    --cc=gtzalik@amazon.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jeffrey.t.kirsher@intel.com \
    --cc=john.fastabend@gmail.com \
    --cc=lorenzo@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=sameehj@amazon.com \
    --cc=steffen.klassert@secunet.com \
    --cc=thomas.petazzoni@bootlin.com \
    --cc=toke@redhat.com \
    --cc=willemdebruijn.kernel@gmail.com \
    --cc=zorik@amazon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Netdev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/netdev/0 netdev/git/0.git
	git clone --mirror https://lore.kernel.org/netdev/1 netdev/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 netdev netdev/ https://lore.kernel.org/netdev \
		netdev@vger.kernel.org
	public-inbox-index netdev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.netdev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git