@@ -1278,6 +1278,225 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port,
}
EXPORT_SYMBOL(ocelot_fdb_dump);
+static void ocelot_populate_l2_ptp_trap_key(struct ocelot_vcap_filter *trap)
+{
+ trap->key_type = OCELOT_VCAP_KEY_ETYPE;
+ *(__be16 *)trap->key.etype.etype.value = htons(ETH_P_1588);
+ *(__be16 *)trap->key.etype.etype.mask = htons(0xffff);
+}
+
+static void
+ocelot_populate_ipv4_ptp_event_trap_key(struct ocelot_vcap_filter *trap)
+{
+ trap->key_type = OCELOT_VCAP_KEY_IPV4;
+ trap->key.ipv4.dport.value = PTP_EV_PORT;
+ trap->key.ipv4.dport.mask = 0xffff;
+}
+
+static void
+ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap)
+{
+ trap->key_type = OCELOT_VCAP_KEY_IPV6;
+ trap->key.ipv6.dport.value = PTP_EV_PORT;
+ trap->key.ipv6.dport.mask = 0xffff;
+}
+
+static void
+ocelot_populate_ipv4_ptp_general_trap_key(struct ocelot_vcap_filter *trap)
+{
+ trap->key_type = OCELOT_VCAP_KEY_IPV4;
+ trap->key.ipv4.dport.value = PTP_GEN_PORT;
+ trap->key.ipv4.dport.mask = 0xffff;
+}
+
+static void
+ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap)
+{
+ trap->key_type = OCELOT_VCAP_KEY_IPV6;
+ trap->key.ipv6.dport.value = PTP_GEN_PORT;
+ trap->key.ipv6.dport.mask = 0xffff;
+}
+
+static int ocelot_trap_add(struct ocelot *ocelot, int port,
+ unsigned long cookie,
+ void (*populate)(struct ocelot_vcap_filter *f))
+{
+ struct ocelot_vcap_block *block_vcap_is2;
+ struct ocelot_vcap_filter *trap;
+ bool new = false;
+ int err;
+
+ block_vcap_is2 = &ocelot->block[VCAP_IS2];
+
+ trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie,
+ false);
+ if (!trap) {
+ trap = kzalloc(sizeof(*trap), GFP_KERNEL);
+ if (!trap)
+ return -ENOMEM;
+
+ populate(trap);
+ trap->prio = 1;
+ trap->id.cookie = cookie;
+ trap->id.tc_offload = false;
+ trap->block_id = VCAP_IS2;
+ trap->type = OCELOT_VCAP_FILTER_OFFLOAD;
+ trap->lookup = 0;
+ trap->action.cpu_copy_ena = true;
+ trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY;
+ trap->action.port_mask = 0;
+ new = true;
+ }
+
+ trap->ingress_port_mask |= BIT(port);
+
+ if (new)
+ err = ocelot_vcap_filter_add(ocelot, trap, NULL);
+ else
+ err = ocelot_vcap_filter_replace(ocelot, trap);
+ if (err) {
+ trap->ingress_port_mask &= ~BIT(port);
+ if (!trap->ingress_port_mask)
+ kfree(trap);
+ return err;
+ }
+
+ return 0;
+}
+
+static int ocelot_trap_del(struct ocelot *ocelot, int port,
+ unsigned long cookie)
+{
+ struct ocelot_vcap_block *block_vcap_is2;
+ struct ocelot_vcap_filter *trap;
+
+ block_vcap_is2 = &ocelot->block[VCAP_IS2];
+
+ trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie,
+ false);
+ if (!trap)
+ return 0;
+
+ trap->ingress_port_mask &= ~BIT(port);
+ if (!trap->ingress_port_mask)
+ return ocelot_vcap_filter_del(ocelot, trap);
+
+ return ocelot_vcap_filter_replace(ocelot, trap);
+}
+
+static int ocelot_l2_ptp_trap_add(struct ocelot *ocelot, int port)
+{
+ unsigned long l2_cookie = ocelot->num_phys_ports + 1;
+
+ return ocelot_trap_add(ocelot, port, l2_cookie,
+ ocelot_populate_l2_ptp_trap_key);
+}
+
+static int ocelot_l2_ptp_trap_del(struct ocelot *ocelot, int port)
+{
+ unsigned long l2_cookie = ocelot->num_phys_ports + 1;
+
+ return ocelot_trap_del(ocelot, port, l2_cookie);
+}
+
+static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port)
+{
+ unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2;
+ unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3;
+ int err;
+
+ err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie,
+ ocelot_populate_ipv4_ptp_event_trap_key);
+ if (err)
+ return err;
+
+ err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie,
+ ocelot_populate_ipv4_ptp_general_trap_key);
+ if (err)
+ ocelot_trap_del(ocelot, port, ipv4_ev_cookie);
+
+ return err;
+}
+
+static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port)
+{
+ unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2;
+ unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3;
+ int err;
+
+ err = ocelot_trap_del(ocelot, port, ipv4_ev_cookie);
+ err |= ocelot_trap_del(ocelot, port, ipv4_gen_cookie);
+ return err;
+}
+
+static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port)
+{
+ unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4;
+ unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5;
+ int err;
+
+ err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie,
+ ocelot_populate_ipv6_ptp_event_trap_key);
+ if (err)
+ return err;
+
+ err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie,
+ ocelot_populate_ipv6_ptp_general_trap_key);
+ if (err)
+ ocelot_trap_del(ocelot, port, ipv6_ev_cookie);
+
+ return err;
+}
+
+static int ocelot_ipv6_ptp_trap_del(struct ocelot *ocelot, int port)
+{
+ unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4;
+ unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5;
+ int err;
+
+ err = ocelot_trap_del(ocelot, port, ipv6_ev_cookie);
+ err |= ocelot_trap_del(ocelot, port, ipv6_gen_cookie);
+ return err;
+}
+
+static int ocelot_setup_ptp_traps(struct ocelot *ocelot, int port,
+ bool l2, bool l4)
+{
+ int err;
+
+ if (l2)
+ err = ocelot_l2_ptp_trap_add(ocelot, port);
+ else
+ err = ocelot_l2_ptp_trap_del(ocelot, port);
+ if (err)
+ return err;
+
+ if (l4) {
+ err = ocelot_ipv4_ptp_trap_add(ocelot, port);
+ if (err)
+ goto err_ipv4;
+
+ err = ocelot_ipv6_ptp_trap_add(ocelot, port);
+ if (err)
+ goto err_ipv6;
+ } else {
+ err = ocelot_ipv4_ptp_trap_del(ocelot, port);
+
+ err |= ocelot_ipv6_ptp_trap_del(ocelot, port);
+ }
+ if (err)
+ return err;
+
+ return 0;
+
+err_ipv6:
+ ocelot_ipv4_ptp_trap_del(ocelot, port);
+err_ipv4:
+ if (l2)
+ ocelot_l2_ptp_trap_del(ocelot, port);
+ return err;
+}
+
int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr)
{
return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config,
@@ -1288,7 +1507,9 @@ EXPORT_SYMBOL(ocelot_hwstamp_get);
int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
{
struct ocelot_port *ocelot_port = ocelot->ports[port];
+ bool l2 = false, l4 = false;
struct hwtstamp_config cfg;
+ int err;
if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
return -EFAULT;
@@ -1323,19 +1544,37 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ l4 = true;
+ break;
case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ l2 = true;
+ break;
case HWTSTAMP_FILTER_PTP_V2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
- cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ l2 = true;
+ l4 = true;
break;
default:
mutex_unlock(&ocelot->ptp_lock);
return -ERANGE;
}
+ err = ocelot_setup_ptp_traps(ocelot, port, l2, l4);
+ if (err)
+ return err;
+
+ if (l2 && l4)
+ cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ else if (l2)
+ cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+ else if (l4)
+ cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+ else
+ cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+
/* Commit back the result & save it */
memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg));
mutex_unlock(&ocelot->ptp_lock);
IEEE 1588 support was declared too soon for the Ocelot switch. Out of reset, this switch does not apply any special treatment for PTP packets, i.e. when an event message is received, the natural tendency is to forward it by MAC DA/VLAN ID. This poses a problem when the ingress port is under a bridge, since user space application stacks (written primarily for endpoint ports, not switches) like ptp4l expect that PTP messages are always received on AF_PACKET / AF_INET sockets (depending on the PTP transport being used), and never being autonomously forwarded. Any forwarding, if necessary (for example in Transparent Clock mode) is handled in software by ptp4l. Having the hardware forward these packets too will cause duplicates which will confuse endpoints connected to these switches. So PTP over L2 barely works, in the sense that PTP packets reach the CPU port, but they reach it via flooding, and therefore reach lots of other unwanted destinations too. But PTP over IPv4/IPv6 does not work at all. This is because the Ocelot switch have a separate destination port mask for unknown IP multicast (which PTP over IP is) flooding compared to unknown non-IP multicast (which PTP over L2 is) flooding. Specifically, the driver allows the CPU port to be in the PGID_MC port group, but not in PGID_MCIPV4 and PGID_MCIPV6. There are several presentations from Allan Nielsen which explain that the embedded MIPS CPU on Ocelot switches is not very powerful at all, so every penny they could save by not allowing flooding to the CPU port module matters. Unknown IP multicast did not make it. The de facto consensus is that when a switch is PTP-aware and an application stack for PTP is running, switches should have some sort of trapping mechanism for PTP packets, to extract them from the hardware data path. This avoids both problems: (a) PTP packets are no longer flooded to unwanted destinations (b) PTP over IP packets are no longer denied from reaching the CPU since they arrive there via a trap and not via flooding It is not the first time when this change is attempted. Last time, the feedback from Allan Nielsen and Andrew Lunn was that the traps should not be installed by default, and that PTP-unaware switching may be desired for some use cases: https://patchwork.ozlabs.org/project/netdev/patch/20190813025214.18601-5-yangbo.lu@nxp.com/ To address that feedback, the present patch adds the necessary packet traps according to the RX filter configuration transmitted by user space through the SIOCSHWTSTAMP ioctl. Trapping is done via VCAP IS2, where we keep 5 filters, which are amended each time RX timestamping is enabled or disabled on a port: - 1 for PTP over L2 - 2 for PTP over IPv4 (UDP ports 319 and 320) - 2 for PTP over IPv6 (UDP ports 319 and 320) The cookie by which these filters (invisible to tc) are identified is strategically chosen such that it does not collide with the filters used for the ocelot-8021q tagging protocol by the Felix driver, or with the MRP traps set up by the Ocelot library. Other alternatives were considered, like patching user space to do something, but there are so many ways in which PTP packets could be made to reach the CPU, generically speaking, that "do what?" is a very valid question. The ptp4l program from the linuxptp stack already attempts to do something: it calls setsockopt(IP_ADD_MEMBERSHIP) (and PACKET_ADD_MEMBERSHIP, respectively) which translates in both cases into a dev_mc_add() on the interface, in the kernel: https://github.com/richardcochran/linuxptp/blob/v3.1.1/udp.c#L73 https://github.com/richardcochran/linuxptp/blob/v3.1.1/raw.c Reality shows that this is not sufficient in case the interface belongs to a switchdev driver, as dev_mc_add() does not show the intention to trap a packet to the CPU, but rather the intention to not drop it (it is strictly for RX filtering, same as promiscuous does not mean to send all traffic to the CPU, but to not drop traffic with unknown MAC DA). This topic is a can of worms in itself, and it would be great if user space could just stay out of it. On the other hand, setting up PTP traps privately within the driver is not new by any stretch of the imagination: https://elixir.bootlin.com/linux/v5.16-rc2/source/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c#L833 https://elixir.bootlin.com/linux/v5.16-rc2/source/drivers/net/dsa/hirschmann/hellcreek.c#L1050 https://elixir.bootlin.com/linux/v5.16-rc2/source/include/linux/dsa/sja1105.h#L21 So this is the approach taken here as well. The difference here being that we prepare and destroy the traps per port, dynamically at runtime, as opposed to driver init time, because apparently, PTP-unaware forwarding is a use case. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Reported-by: Po Liu <po.liu@nxp.com> Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Acked-by: Richard Cochran <richardcochran@gmail.com> --- drivers/net/ethernet/mscc/ocelot.c | 241 ++++++++++++++++++++++++++++- 1 file changed, 240 insertions(+), 1 deletion(-)