All of lore.kernel.org
 help / color / mirror / Atom feed
From: Maxim Mikityanskiy <maximmi@mellanox.com>
To: "Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>
Cc: "bpf@vger.kernel.org" <bpf@vger.kernel.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"David S. Miller" <davem@davemloft.net>,
	Saeed Mahameed <saeedm@mellanox.com>, Jonathan Lemon <bsd@fb.com>,
	Tariq Toukan <tariqt@mellanox.com>,
	Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
	Yonghong Song <yhs@fb.com>,
	Jakub Kicinski <jakub.kicinski@netronome.com>,
	Maciej Fijalkowski <maciejromanfijalkowski@gmail.com>,
	Maxim Mikityanskiy <maximmi@mellanox.com>
Subject: [PATCH bpf-next v4 13/17] net/mlx5e: XDP_TX from UMEM support
Date: Wed, 12 Jun 2019 15:57:00 +0000	[thread overview]
Message-ID: <20190612155605.22450-14-maximmi@mellanox.com> (raw)
In-Reply-To: <20190612155605.22450-1-maximmi@mellanox.com>

When an XDP program returns XDP_TX, and the RQ is XSK-enabled, it
requires careful handling, because convert_to_xdp_frame creates a new
page and copies the data there, while our driver expects the xdp_frame
to point to the same memory as the xdp_buff. Handle this case
separately: map the page, and in the end unmap it and call
xdp_return_frame.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  | 50 ++++++++++++++++---
 1 file changed, 42 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index b3e118fc4521..1364bdff702c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -69,14 +69,48 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 	xdptxd.data = xdpf->data;
 	xdptxd.len  = xdpf->len;
 
-	xdpi.mode = MLX5E_XDP_XMIT_MODE_PAGE;
+	if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) {
+		/* The xdp_buff was in the UMEM and was copied into a newly
+		 * allocated page. The UMEM page was returned via the ZCA, and
+		 * this new page has to be mapped at this point and has to be
+		 * unmapped and returned via xdp_return_frame on completion.
+		 */
+
+		/* Prevent double recycling of the UMEM page. Even in case this
+		 * function returns false, the xdp_buff shouldn't be recycled,
+		 * as it was already done in xdp_convert_zc_to_xdp_frame.
+		 */
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
+
+		xdpi.mode = MLX5E_XDP_XMIT_MODE_FRAME;
 
-	dma_addr = di->addr + (xdpf->data - (void *)xdpf);
-	dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len, DMA_TO_DEVICE);
+		dma_addr = dma_map_single(sq->pdev, xdptxd.data, xdptxd.len,
+					  DMA_TO_DEVICE);
+		if (dma_mapping_error(sq->pdev, dma_addr)) {
+			xdp_return_frame(xdpf);
+			return false;
+		}
 
-	xdptxd.dma_addr = dma_addr;
-	xdpi.page.rq = rq;
-	xdpi.page.di = *di;
+		xdptxd.dma_addr     = dma_addr;
+		xdpi.frame.xdpf     = xdpf;
+		xdpi.frame.dma_addr = dma_addr;
+	} else {
+		/* Driver assumes that convert_to_xdp_frame returns an xdp_frame
+		 * that points to the same memory region as the original
+		 * xdp_buff. It allows to map the memory only once and to use
+		 * the DMA_BIDIRECTIONAL mode.
+		 */
+
+		xdpi.mode = MLX5E_XDP_XMIT_MODE_PAGE;
+
+		dma_addr = di->addr + (xdpf->data - (void *)xdpf);
+		dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len,
+					   DMA_TO_DEVICE);
+
+		xdptxd.dma_addr = dma_addr;
+		xdpi.page.rq    = rq;
+		xdpi.page.di    = *di;
+	}
 
 	return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi);
 }
@@ -298,13 +332,13 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 
 		switch (xdpi.mode) {
 		case MLX5E_XDP_XMIT_MODE_FRAME:
-			/* XDP_REDIRECT */
+			/* XDP_TX from the XSK RQ and XDP_REDIRECT */
 			dma_unmap_single(sq->pdev, xdpi.frame.dma_addr,
 					 xdpi.frame.xdpf->len, DMA_TO_DEVICE);
 			xdp_return_frame(xdpi.frame.xdpf);
 			break;
 		case MLX5E_XDP_XMIT_MODE_PAGE:
-			/* XDP_TX */
+			/* XDP_TX from the regular RQ */
 			mlx5e_page_release(xdpi.page.rq, &xdpi.page.di, recycle);
 			break;
 		default:
-- 
2.19.1


  parent reply	other threads:[~2019-06-12 15:57 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-12 15:56 [PATCH bpf-next v4 00/17] AF_XDP infrastructure improvements and mlx5e support Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 01/17] net/mlx5e: Attach/detach XDP program safely Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 02/17] xsk: Add API to check for available entries in FQ Maxim Mikityanskiy
2019-06-13 12:50   ` Björn Töpel
2019-06-12 15:56 ` [PATCH bpf-next v4 03/17] xsk: Add getsockopt XDP_OPTIONS Maxim Mikityanskiy
2019-06-13 12:50   ` Björn Töpel
2019-06-12 15:56 ` [PATCH bpf-next v4 04/17] libbpf: Support " Maxim Mikityanskiy
2019-06-13 12:51   ` Björn Töpel
2019-06-12 15:56 ` [PATCH bpf-next v4 05/17] xsk: Change the default frame size to 4096 and allow controlling it Maxim Mikityanskiy
2019-06-12 20:10   ` Jakub Kicinski
2019-06-13 14:01     ` Maxim Mikityanskiy
2019-06-13 17:29       ` Jakub Kicinski
2019-06-14 13:25         ` Maxim Mikityanskiy
2019-06-15  1:40           ` Jakub Kicinski
2019-06-18 12:00             ` Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 06/17] xsk: Return the whole xdp_desc from xsk_umem_consume_tx Maxim Mikityanskiy
2019-06-13 12:48   ` Björn Töpel
2019-06-12 15:56 ` [PATCH bpf-next v4 07/17] libbpf: Support drivers with non-combined channels Maxim Mikityanskiy
2019-06-12 20:23   ` Jakub Kicinski
2019-06-13 12:41     ` Björn Töpel
2019-06-13 17:34       ` Jakub Kicinski
2019-06-13 14:01     ` Maxim Mikityanskiy
2019-06-13 14:45       ` Maciej Fijalkowski
2019-06-14 13:25         ` Maxim Mikityanskiy
2019-06-14 17:15           ` Maciej Fijalkowski
2019-06-14 19:50             ` Björn Töpel
2019-06-18 12:00             ` Maxim Mikityanskiy
2019-06-13 18:09       ` Jakub Kicinski
2019-06-14 13:25         ` Maxim Mikityanskiy
2019-06-15  2:12           ` Jakub Kicinski
2019-06-12 15:56 ` [PATCH bpf-next v4 08/17] net/mlx5e: Replace deprecated PCI_DMA_TODEVICE Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 09/17] net/mlx5e: Calculate linear RX frag size considering XSK Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 10/17] net/mlx5e: Allow ICO SQ to be used by multiple RQs Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 11/17] net/mlx5e: Refactor struct mlx5e_xdp_info Maxim Mikityanskiy
2019-06-12 15:56 ` [PATCH bpf-next v4 12/17] net/mlx5e: Share the XDP SQ for XDP_TX between RQs Maxim Mikityanskiy
2019-06-12 15:57 ` Maxim Mikityanskiy [this message]
2019-06-12 15:57 ` [PATCH bpf-next v4 14/17] net/mlx5e: Consider XSK in XDP MTU limit calculation Maxim Mikityanskiy
2019-06-12 15:57 ` [PATCH bpf-next v4 15/17] net/mlx5e: Encapsulate open/close queues into a function Maxim Mikityanskiy
2019-06-12 15:57 ` [PATCH bpf-next v4 16/17] net/mlx5e: Move queue param structs to en/params.h Maxim Mikityanskiy
2019-06-12 15:57 ` [PATCH bpf-next v4 17/17] net/mlx5e: Add XSK zero-copy support Maxim Mikityanskiy
2019-06-15 15:42   ` Jakub Kicinski
2019-06-18 12:00     ` Maxim Mikityanskiy
2019-06-12 19:10 ` [PATCH bpf-next v4 00/17] AF_XDP infrastructure improvements and mlx5e support Jonathan Lemon
2019-06-12 20:48 ` Jakub Kicinski
2019-06-13 12:58   ` Björn Töpel
2019-06-13 14:01     ` Maxim Mikityanskiy
2019-06-13 14:11       ` Björn Töpel
2019-06-13 14:53         ` Björn Töpel
2019-06-13 14:01   ` Maxim Mikityanskiy

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=20190612155605.22450-14-maximmi@mellanox.com \
    --to=maximmi@mellanox.com \
    --cc=ast@kernel.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=bsd@fb.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=jakub.kicinski@netronome.com \
    --cc=kafai@fb.com \
    --cc=maciejromanfijalkowski@gmail.com \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=songliubraving@fb.com \
    --cc=tariqt@mellanox.com \
    --cc=yhs@fb.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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.