selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata
Subsystems (4)
PATCH 1/1 selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata
The existing timestamping_enable() is a no-op because it applies to the socket-related path that we are not verifying here anymore. (but still leaving the code around hoping we can have xdp->skb path verified here as well)
poll: 1 (0)
xsk_ring_cons__peek: 1
0xf64788: rx_desc[0]->addr=100000000008000 addr=8100 comp_addr=8000
rx_hash: 3697961069
rx_timestamp: 1674657672142214773 (sec:1674657672.1422) XDP RX-time: 1674657709561774876 (sec:1674657709.5618) delta sec:37.4196 AF_XDP time: 1674657709561871034 (sec:1674657709.5619) delta
sec:0.0001 (96.158 usec)
0xf64788: complete idx=8 addr=8000
Also, maybe something to archive here, see [0] for Jesper's note about NIC vs host clock delta.
0: https://lore.kernel.org/bpf/[email protected]/
--- tools/testing/selftests/bpf/xdp_hw_metadata.c | 28 ++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-)
tools/testing/selftests/bpf/xdp_hw_metadata.c +27 -1
@@ -24,6 +24,7 @@#include <linux/net_tstamp.h> #include <linux/udp.h> #include <linux/sockios.h> +#include <linux/net_tstamp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h>
@@ -278,13 +279,36 @@ static int rxq_num(const char *ifname) ret =ioctl (fd,SIOCETHTOOL , &ifr);if (ret <0 ) -error (-1 , errno,"socket" ); +error (-1 , errno,"ioctl(SIOCETHTOOL)" );close (fd);return ch.rx_count + ch.combined_count; } +static void hwtstamp_enable (const char *ifname) +{ +struct hwtstamp_config cfg = { + .rx_filter =HWTSTAMP_FILTER_ALL , + }; + +struct ifreq ifr = { + .ifr_data = (void *)&cfg, + }; +strcpy (ifr.ifr_name, ifname); +int fd, ret; + + fd =socket (AF_UNIX ,SOCK_DGRAM ,0 ); +if (fd <0 ) +error (-1 , errno,"socket" ); + + ret =ioctl (fd,SIOCSHWTSTAMP , &ifr); +if (ret <0 ) +error (-1 , errno,"ioctl(SIOCSHWTSTAMP)" ); + +close (fd); +} +static void cleanup (void ) {LIBBPF_OPTS (bpf_xdp_attach_opts, opts);
@@ -341,6 +365,8 @@ int main(int argc, char *argv[])printf ("rxq: %d\n" , rxq); +hwtstamp_enable (ifname); + rx_xsk =malloc (sizeof (struct xsk ) * rxq);if (!rx_xsk)error (-1 ,ENOMEM ,"malloc" );
Signature · 1 line
2.39.1.456.gfc5497dd1b-goog
Martin KaFai Lau
reviewerQuoted 79 lines · Stanislav Fomichev
The existing
timestamping_enable()is a no-op because it applies to the socket-related path that we are not verifying here anymore. (but still leaving the code around hoping we can havexdp->skbpath verified here as well)poll: 1 (0) xsk_ring_cons__peek: 1 0xf64788: rx_desc[0]->addr=100000000008000 addr=8100 comp_addr=8000 rx_hash: 3697961069 rx_timestamp: 1674657672142214773 (sec:1674657672.1422) XDP RX-time: 1674657709561774876 (sec:1674657709.5618) delta sec:37.4196 AF_XDP time: 1674657709561871034 (sec:1674657709.5619) deltasec:0.0001 (96.158 usec)
0xf64788: complete idx=8 addr=8000Also, maybe something to archive here, see [0] for Jesper's note about NIC vs host clock delta.
0: https://lore.kernel.org/bpf/[email protected]/
Fixes 297a3f124155 ("selftests/bpf: Simple program to dump XDP RX metadata")Reported-by Jesper Dangaard Brouer <[email protected]>Signed-off-by Stanislav Fomichev <[email protected]>--- tools/testing/selftests/bpf/xdp_hw_metadata.c | 28 ++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-)tools/testing/selftests/bpf/xdp_hw_metadata.c +25
-1@@ -24,6 +24,7 @@#include <linux/net_tstamp.h> #include <linux/udp.h> #include <linux/sockios.h> +#include <linux/net_tstamp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h> @@ -278,13 +279,36 @@ static int rxq_num(const char *ifname) ret =ioctl (fd,SIOCETHTOOL , &ifr);if (ret <0 ) -error (-1 , errno,"socket" ); +error (-1 , errno,"ioctl(SIOCETHTOOL)" );close (fd);return ch.rx_count + ch.combined_count; } +static void hwtstamp_enable (const char *ifname) +{ +struct hwtstamp_config cfg = { + .rx_filter =HWTSTAMP_FILTER_ALL , + }; + +struct ifreq ifr = { + .ifr_data = (void *)&cfg, + }; +strcpy (ifr.ifr_name, ifname); +int fd, ret; + + fd =socket (AF_UNIX ,SOCK_DGRAM ,0 ); +if (fd <0 ) +error (-1 , errno,"socket" ); + + ret =ioctl (fd,SIOCSHWTSTAMP , &ifr); +if (ret <0 ) +error (-1 , errno,"ioctl(SIOCSHWTSTAMP)" ); + +close (fd); +} +static void cleanup (void ) {LIBBPF_OPTS (bpf_xdp_attach_opts, opts);
tools/testing/selftests/bpf/xdp_hw_metadata.c int main(int argc, char *argv[]) · line 368
Quoted 4 lines
tools/testing/selftests/bpf/xdp_hw_metadata.c +1
-0@@ -341,6 +365,8 @@ int main(int argc, char *argv[])printf ("rxq: %d\n" , rxq); +hwtstamp_enable (ifname);
Will it to restore to the earlier setting when the process exits?
Quoted 82 lines · Martin KaFai Lau
Quoted 80 lines · Stanislav Fomichev
The existing
timestamping_enable()is a no-op because it applies to the socket-related path that we are not verifying here anymore. (but still leaving the code around hoping we can havexdp->skbpath verified here as well)poll: 1 (0) xsk_ring_cons__peek: 1 0xf64788: rx_desc[0]->addr=100000000008000 addr=8100 comp_addr=8000 rx_hash: 3697961069 rx_timestamp: 1674657672142214773 (sec:1674657672.1422) XDP RX-time: 1674657709561774876 (sec:1674657709.5618) delta sec:37.4196 AF_XDP time: 1674657709561871034 (sec:1674657709.5619) deltasec:0.0001 (96.158 usec)
0xf64788: complete idx=8 addr=8000Also, maybe something to archive here, see [0] for Jesper's note about NIC vs host clock delta.
0: https://lore.kernel.org/bpf/[email protected]/
Fixes 297a3f124155 ("selftests/bpf: Simple program to dump XDP RX metadata")Reported-by Jesper Dangaard Brouer <[email protected]>Signed-off-by Stanislav Fomichev <[email protected]>--- tools/testing/selftests/bpf/xdp_hw_metadata.c | 28 ++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-)tools/testing/selftests/bpf/xdp_hw_metadata.c +25
-1@@ -24,6 +24,7 @@#include <linux/net_tstamp.h> #include <linux/udp.h> #include <linux/sockios.h> +#include <linux/net_tstamp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h> @@ -278,13 +279,36 @@ static int rxq_num(const char *ifname) ret =ioctl (fd,SIOCETHTOOL , &ifr);if (ret <0 ) -error (-1 , errno,"socket" ); +error (-1 , errno,"ioctl(SIOCETHTOOL)" );close (fd);return ch.rx_count + ch.combined_count; } +static void hwtstamp_enable (const char *ifname) +{ +struct hwtstamp_config cfg = { + .rx_filter =HWTSTAMP_FILTER_ALL , + }; + +struct ifreq ifr = { + .ifr_data = (void *)&cfg, + }; +strcpy (ifr.ifr_name, ifname); +int fd, ret; + + fd =socket (AF_UNIX ,SOCK_DGRAM ,0 ); +if (fd <0 ) +error (-1 , errno,"socket" ); + + ret =ioctl (fd,SIOCSHWTSTAMP , &ifr); +if (ret <0 ) +error (-1 , errno,"ioctl(SIOCSHWTSTAMP)" ); + +close (fd); +} +static void cleanup (void ) {LIBBPF_OPTS (bpf_xdp_attach_opts, opts);@@ -341,6 +365,8 @@ int main(int argc, char *argv[])
Quoted 5 lines
tools/testing/selftests/bpf/xdp_hw_metadata.c int main(int argc, char *argv[]) · line 368
Quoted 3 lines
tools/testing/selftests/bpf/xdp_hw_metadata.c +1
-0printf ("rxq: %d\n" , rxq); +hwtstamp_enable (ifname);Will it to restore to the earlier setting when the process exits?
Nope, do you think we should? Probably a good idea, let me add that...
Quoted 5 lines · Stanislav Fomichev
The existing
timestamping_enable()is a no-op because it applies to the socket-related path that we are not verifying here anymore. (but still leaving the code around hoping we can havexdp->skbpath verified here as well)
Quoted 7 lines
poll: 1 (0) xsk_ring_cons__peek: 1 0xf64788: rx_desc[0]->addr=100000000008000 addr=8100 comp_addr=8000 rx_hash: 3697961069 rx_timestamp: 1674657672142214773 (sec:1674657672.1422) XDP RX-time: 1674657709561774876 (sec:1674657709.5618) delta sec:37.4196 AF_XDP time: 1674657709561871034 (sec:1674657709.5619) delta sec:0.0001 (96.158 usec)
This output contains some extra output data, which is not part of current upstream.
I will soon submit an RFC-patch with this extra output to discuss and figure out what timestamp type we want/expect HW to provide.
Quoted 7 lines
0xf64788: complete idx=8 addr=8000Also, maybe something to archive here, see [0] for Jesper's note about NIC vs host clock delta.
--Jesper