[LibreQoS] Fwd: [PATCH bpf-next 05/11] veth: Support rx timestamp metadata for xdp

Dave Taht dave.taht at gmail.com
Wed Nov 16 15:16:03 EST 2022

We presently timestamp in cake. Faster to have the hw do it.

---------- Forwarded message ---------
From: Stanislav Fomichev <sdf at google.com>
Date: Mon, Nov 14, 2022, 7:13 PM
Subject: [PATCH bpf-next 05/11] veth: Support rx timestamp metadata for xdp
To: <bpf at vger.kernel.org>
Cc: <ast at kernel.org>, <daniel at iogearbox.net>, <andrii at kernel.org>, <
martin.lau at linux.dev>, <song at kernel.org>, <yhs at fb.com>, <
john.fastabend at gmail.com>, <kpsingh at kernel.org>, <sdf at google.com>, <
haoluo at google.com>, <jolsa at kernel.org>, David Ahern <dsahern at gmail.com>,
Jakub Kicinski <kuba at kernel.org>, Willem de Bruijn <willemb at google.com>,
Jesper Dangaard Brouer <brouer at redhat.com>, Anatoly Burakov <
anatoly.burakov at intel.com>, Alexander Lobakin <alexandr.lobakin at intel.com>,
Magnus Karlsson <magnus.karlsson at gmail.com>, Maryam Tahhan <
mtahhan at redhat.com>, <xdp-hints at xdp-project.net>, <netdev at vger.kernel.org>

The goal is to enable end-to-end testing of the metadata
for AF_XDP. Current rx_timestamp kfunc returns current
time which should be enough to exercise this new functionality.

Cc: John Fastabend <john.fastabend at gmail.com>
Cc: David Ahern <dsahern at gmail.com>
Cc: Martin KaFai Lau <martin.lau at linux.dev>
Cc: Jakub Kicinski <kuba at kernel.org>
Cc: Willem de Bruijn <willemb at google.com>
Cc: Jesper Dangaard Brouer <brouer at redhat.com>
Cc: Anatoly Burakov <anatoly.burakov at intel.com>
Cc: Alexander Lobakin <alexandr.lobakin at intel.com>
Cc: Magnus Karlsson <magnus.karlsson at gmail.com>
Cc: Maryam Tahhan <mtahhan at redhat.com>
Cc: xdp-hints at xdp-project.net
Cc: netdev at vger.kernel.org
Signed-off-by: Stanislav Fomichev <sdf at google.com>
 drivers/net/veth.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 2a4592780141..c626580a2294 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -25,6 +25,7 @@
 #include <linux/filter.h>
 #include <linux/ptr_ring.h>
 #include <linux/bpf_trace.h>
+#include <linux/bpf_patch.h>
 #include <linux/net_tstamp.h>

 #define DRV_NAME       "veth"
@@ -1659,6 +1660,18 @@ static int veth_xdp(struct net_device *dev, struct
netdev_bpf *xdp)

+static void veth_unroll_kfunc(const struct bpf_prog *prog, u32 func_id,
+                             struct bpf_patch *patch)
+       if (func_id ==
+               /* return true; */
+               bpf_patch_append(patch, BPF_MOV64_IMM(BPF_REG_0, 1));
+       } else if (func_id ==
xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP)) {
+               /* return ktime_get_mono_fast_ns(); */
+               bpf_patch_append(patch,
+       }
 static const struct net_device_ops veth_netdev_ops = {
        .ndo_init            = veth_dev_init,
        .ndo_open            = veth_open,
@@ -1678,6 +1691,7 @@ static const struct net_device_ops veth_netdev_ops = {
        .ndo_bpf                = veth_xdp,
        .ndo_xdp_xmit           = veth_ndo_xdp_xmit,
        .ndo_get_peer_dev       = veth_peer_dev,
+       .ndo_unroll_kfunc       = veth_unroll_kfunc,

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/libreqos/attachments/20221116/34314d9f/attachment.html>

More information about the LibreQoS mailing list