Files
linux/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
Jesper Dangaard Brouer bb32347876 selftests/bpf: xdp_hw_metadata track more timestamps
To correlate the hardware RX timestamp with something, add tracking of
two software timestamps both clock source CLOCK_TAI (see description in
man clock_gettime(2)).

XDP metadata is extended with xdp_timestamp for capturing when XDP
received the packet. Populated with BPF helper bpf_ktime_get_tai_ns(). I
could not find a BPF helper for getting CLOCK_REALTIME, which would have
been preferred. In userspace when AF_XDP sees the packet another
software timestamp is recorded via clock_gettime() also clock source
CLOCK_TAI.

Example output shortly after loading igc driver:

  poll: 1 (0) skip=1 fail=0 redir=2
  xsk_ring_cons__peek: 1
  0x12557a8: rx_desc[1]->addr=100000000009000 addr=9100 comp_addr=9000
  rx_hash: 0x82A96531 with RSS type:0x1
  rx_timestamp:  1681740540304898909 (sec:1681740540.3049)
  XDP RX-time:   1681740577304958316 (sec:1681740577.3050) delta sec:37.0001 (37000059.407 usec)
  AF_XDP time:   1681740577305051315 (sec:1681740577.3051) delta sec:0.0001 (92.999 usec)
  0x12557a8: complete idx=9 addr=9000

The first observation is that the 37 sec difference between RX HW vs XDP
timestamps, which indicate hardware is likely clock source
CLOCK_REALTIME, because (as of this writing) CLOCK_TAI is initialised
with a 37 sec offset.

The 93 usec (microsec) difference between XDP vs AF_XDP userspace is the
userspace wakeup time. On this hardware it was caused by CPU idle sleep
states, which can be reduced by tuning /dev/cpu_dma_latency.

View current requested/allowed latency bound via:
  hexdump --format '"%d\n"' /dev/cpu_dma_latency

More explanation of the output and how this can be used to identify
clock drift for the HW clock can be seen here[1]:

[1] https://github.com/xdp-project/xdp-project/blob/master/areas/hints/xdp_hints_kfuncs02_driver_igc.org

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Song Yoong Siang <yoong.siang.song@intel.com>
Link: https://lore.kernel.org/bpf/168182466298.616355.2544377890818617459.stgit@firesoul
2023-04-27 18:42:30 +02:00

94 lines
2.3 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <vmlinux.h>
#include "xdp_metadata.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
struct {
__uint(type, BPF_MAP_TYPE_XSKMAP);
__uint(max_entries, 256);
__type(key, __u32);
__type(value, __u32);
} xsk SEC(".maps");
__u64 pkts_skip = 0;
__u64 pkts_fail = 0;
__u64 pkts_redir = 0;
extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
__u64 *timestamp) __ksym;
extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
enum xdp_rss_hash_type *rss_type) __ksym;
SEC("xdp")
int rx(struct xdp_md *ctx)
{
void *data, *data_meta, *data_end;
struct ipv6hdr *ip6h = NULL;
struct ethhdr *eth = NULL;
struct udphdr *udp = NULL;
struct iphdr *iph = NULL;
struct xdp_meta *meta;
int err;
data = (void *)(long)ctx->data;
data_end = (void *)(long)ctx->data_end;
eth = data;
if (eth + 1 < data_end) {
if (eth->h_proto == bpf_htons(ETH_P_IP)) {
iph = (void *)(eth + 1);
if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP)
udp = (void *)(iph + 1);
}
if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
ip6h = (void *)(eth + 1);
if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP)
udp = (void *)(ip6h + 1);
}
if (udp && udp + 1 > data_end)
udp = NULL;
}
if (!udp) {
__sync_add_and_fetch(&pkts_skip, 1);
return XDP_PASS;
}
/* Forwarding UDP:9091 to AF_XDP */
if (udp->dest != bpf_htons(9091)) {
__sync_add_and_fetch(&pkts_skip, 1);
return XDP_PASS;
}
err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
if (err) {
__sync_add_and_fetch(&pkts_fail, 1);
return XDP_PASS;
}
data = (void *)(long)ctx->data;
data_meta = (void *)(long)ctx->data_meta;
meta = data_meta;
if (meta + 1 > data) {
__sync_add_and_fetch(&pkts_fail, 1);
return XDP_PASS;
}
err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp);
if (!err)
meta->xdp_timestamp = bpf_ktime_get_tai_ns();
else
meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
if (err < 0)
meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */
__sync_add_and_fetch(&pkts_redir, 1);
return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
}
char _license[] SEC("license") = "GPL";