From 752b1c8d8b409f2b03e61e153696689ee081bf07 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 5 Dec 2024 16:40:55 +0100 Subject: [PATCH 01/16] vxlan: Bump error counters for header mismatches The VXLAN driver so far has not increased the error counters for packets that set reserved bits. It does so for other packet errors, so do it for this case as well. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/d096084167d56706d620afe5136cf37a2d34d1b9.1733412063.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index e50f4cb70193..92832a396ab7 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1721,6 +1721,10 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) * little more security in adding extensions to VXLAN. */ reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; + DEV_STATS_INC(vxlan->dev, rx_frame_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } -- 2.51.0 From bb16786ed6fdff3a67ba33ed928ae138fd4254b5 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 5 Dec 2024 16:40:56 +0100 Subject: [PATCH 02/16] vxlan: vxlan_rcv(): Drop unparsed The code currently validates the VXLAN header in two ways: first by comparing it with the set of reserved bits, constructed ahead of time during the netdevice construction; and second by gradually clearing the bits off a separate copy of VXLAN header, "unparsed". Drop the latter validation method. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/4559f16c5664c189b3a4ee6f5da91f552ad4821c.1733412063.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_core.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 92832a396ab7..ff5684a2103a 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1670,7 +1670,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) const struct vxlanhdr *vh; struct vxlan_dev *vxlan; struct vxlan_sock *vs; - struct vxlanhdr unparsed; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); @@ -1685,7 +1684,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) if (reason) goto drop; - unparsed = *vxlan_hdr(skb); vh = vxlan_hdr(skb); /* VNI flag always required to be set */ if (!(vh->vx_flags & VXLAN_HF_VNI)) { @@ -1695,8 +1693,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) /* Return non vxlan pkt */ goto drop; } - unparsed.vx_flags &= ~VXLAN_HF_VNI; - unparsed.vx_vni &= ~VXLAN_VNI_MASK; vs = rcu_dereference_sk_user_data(sk); if (!vs) @@ -1731,7 +1727,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) if (vxlan->cfg.flags & VXLAN_F_GPE) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto drop; - unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS; raw_proto = true; } @@ -1745,8 +1740,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) reason = vxlan_remcsum(skb, vxlan->cfg.flags); if (unlikely(reason)) goto drop; - unparsed.vx_flags &= ~VXLAN_HF_RCO; - unparsed.vx_vni &= VXLAN_VNI_MASK; } if (vxlan_collect_metadata(vs)) { @@ -1769,19 +1762,12 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) memset(md, 0, sizeof(*md)); } - if (vxlan->cfg.flags & VXLAN_F_GBP) { + if (vxlan->cfg.flags & VXLAN_F_GBP) vxlan_parse_gbp_hdr(skb, vxlan->cfg.flags, md); - unparsed.vx_flags &= ~VXLAN_GBP_USED_BITS; - } /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ - if (unparsed.vx_flags || unparsed.vx_vni) { - reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; - goto drop; - } - if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) -- 2.51.0 From 6c11379b104e3718135fd7fc37bb254b41e4cf65 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 5 Dec 2024 16:40:57 +0100 Subject: [PATCH 03/16] vxlan: Add an attribute to make VXLAN header validation configurable The set of bits that the VXLAN netdevice currently considers reserved is defined by the features enabled at the netdevice construction. In order to make this configurable, add an attribute, IFLA_VXLAN_RESERVED_BITS. The payload is a pair of big-endian u32's covering the VXLAN header. This is validated against the set of flags used by the various enabled VXLAN features, and attempts to override bits used by an enabled feature are bounced. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/c657275e5ceed301e62c69fe8e559e32909442e2.1733412063.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/vxlan/vxlan_core.c | 53 +++++++++++++++++++++++++++++----- include/uapi/linux/if_link.h | 1 + 2 files changed, 47 insertions(+), 7 deletions(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index ff5684a2103a..43cf672b7b9f 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -3428,6 +3428,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), + [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -4315,13 +4316,44 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], used_bits.vx_flags |= VXLAN_GPE_USED_BITS; } - /* For backwards compatibility, only allow reserved fields to be - * used by VXLAN extensions if explicitly requested. - */ - conf->reserved_bits = (struct vxlanhdr) { - .vx_flags = ~used_bits.vx_flags, - .vx_vni = ~used_bits.vx_vni, - }; + if (data[IFLA_VXLAN_RESERVED_BITS]) { + struct vxlanhdr reserved_bits; + + if (changelink) { + NL_SET_ERR_MSG_ATTR(extack, + data[IFLA_VXLAN_RESERVED_BITS], + "Cannot change reserved_bits"); + return -EOPNOTSUPP; + } + + nla_memcpy(&reserved_bits, data[IFLA_VXLAN_RESERVED_BITS], + sizeof(reserved_bits)); + if (used_bits.vx_flags & reserved_bits.vx_flags || + used_bits.vx_vni & reserved_bits.vx_vni) { + __be64 ub_be64, rb_be64; + + memcpy(&ub_be64, &used_bits, sizeof(ub_be64)); + memcpy(&rb_be64, &reserved_bits, sizeof(rb_be64)); + + NL_SET_ERR_MSG_ATTR_FMT(extack, + data[IFLA_VXLAN_RESERVED_BITS], + "Used bits %#018llx cannot overlap reserved bits %#018llx", + be64_to_cpu(ub_be64), + be64_to_cpu(rb_be64)); + return -EINVAL; + } + + conf->reserved_bits = reserved_bits; + } else { + /* For backwards compatibility, only allow reserved fields to be + * used by VXLAN extensions if explicitly requested. + */ + conf->reserved_bits = (struct vxlanhdr) { + .vx_flags = ~used_bits.vx_flags, + .vx_vni = ~used_bits.vx_vni, + }; + } + if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, VXLAN_F_REMCSUM_NOPARTIAL, changelink, @@ -4506,6 +4538,8 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ + /* IFLA_VXLAN_RESERVED_BITS */ + nla_total_size(sizeof(struct vxlanhdr)) + 0; } @@ -4608,6 +4642,11 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; + if (nla_put(skb, IFLA_VXLAN_RESERVED_BITS, + sizeof(vxlan->cfg.reserved_bits), + &vxlan->cfg.reserved_bits)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 2575e0cd9b48..77730c340c8f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1394,6 +1394,7 @@ enum { IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ IFLA_VXLAN_LOCALBYPASS, IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ + IFLA_VXLAN_RESERVED_BITS, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) -- 2.51.0 From 8653eb21d68c6882ce5716b04379431817310b85 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 5 Dec 2024 16:40:58 +0100 Subject: [PATCH 04/16] selftests: net: lib: Rename ip_link_master() to ip_link_set_master() Let's have a verb in that function name to make it clearer what's going on. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/fbf7c53a429b340b9cff5831280ea8c305a224f9.1733412063.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fdb_notify.sh | 6 +++--- tools/testing/selftests/net/lib.sh | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh index c03151e7791c..c159230c9b62 100755 --- a/tools/testing/selftests/net/fdb_notify.sh +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -49,7 +49,7 @@ test_dup_vxlan_self() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan" dev vx self dst 192.0.2.1 do_test_dup del "vxlan" dev vx self dst 192.0.2.1 @@ -59,7 +59,7 @@ test_dup_vxlan_master() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan master" dev vx master do_test_dup del "vxlan master" dev vx master @@ -79,7 +79,7 @@ test_dup_macvlan_master() ip_link_add br up type bridge vlan_filtering 1 ip_link_add dd up type dummy ip_link_add mv up link dd type macvlan mode passthru - ip_link_master mv br + ip_link_set_master mv br do_test_dup add "macvlan master" dev mv self do_test_dup del "macvlan master" dev mv self diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8994fec1c38f..5ea6537acd2b 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -451,7 +451,7 @@ ip_link_add() defer ip link del dev "$name" } -ip_link_master() +ip_link_set_master() { local member=$1; shift local master=$1; shift -- 2.51.0 From d76ccb2ec368c8a44f64839140cd253c19f6a79a Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 5 Dec 2024 16:40:59 +0100 Subject: [PATCH 05/16] selftests: net: lib: Add several autodefer helpers Add ip_link_set_addr(), ip_link_set_up(), ip_addr_add() and ip_route_add() to the suite of helpers that automatically schedule a corresponding cleanup. When setting a new MAC, one needs to remember the old address first. Move mac_get() from forwarding/ to that end. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/add6bcbe30828fd01363266df20c338cf13aaf25.1733412063.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/lib.sh | 7 ---- tools/testing/selftests/net/lib.sh | 39 +++++++++++++++++++ 2 files changed, 39 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7337f398f9cc..1fd40bada694 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -932,13 +932,6 @@ packets_rate() echo $(((t1 - t0) / interval)) } -mac_get() -{ - local if_name=$1 - - ip -j link show dev $if_name | jq -r '.[]["address"]' -} - ether_addr_to_u64() { local addr="$1" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 5ea6537acd2b..2cd5c743b2d9 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -435,6 +435,13 @@ xfail_on_veth() fi } +mac_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["address"]' +} + kill_process() { local pid=$1; shift @@ -459,3 +466,35 @@ ip_link_set_master() ip link set dev "$member" master "$master" defer ip link set dev "$member" nomaster } + +ip_link_set_addr() +{ + local name=$1; shift + local addr=$1; shift + + local old_addr=$(mac_get "$name") + ip link set dev "$name" address "$addr" + defer ip link set dev "$name" address "$old_addr" +} + +ip_link_set_up() +{ + local name=$1; shift + + ip link set dev "$name" up + defer ip link set dev "$name" down +} + +ip_addr_add() +{ + local name=$1; shift + + ip addr add dev "$name" "$@" + defer ip addr del dev "$name" "$@" +} + +ip_route_add() +{ + ip route add "$@" + defer ip route del "$@" +} -- 2.51.0 From d84b5dccf3ebdeeabef910d1c19b931c84f67884 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 5 Dec 2024 16:41:00 +0100 Subject: [PATCH 06/16] selftests: forwarding: Add a selftest for the new reserved_bits UAPI Run VXLAN packets through a gateway. Flip individual bits of the packet and/or reserved bits of the gateway, and check that the gateway treats the packets as expected. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/388bef3c30ebc887d4e64cd86a362e2df2f2d2e1.1733412063.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/forwarding/Makefile | 1 + .../net/forwarding/vxlan_reserved.sh | 352 ++++++++++++++++++ 2 files changed, 353 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/vxlan_reserved.sh diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 7d885cff8d79..00bde7b6f39e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -105,6 +105,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ + vxlan_reserved.sh \ vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh new file mode 100755 index 000000000000..46c31794b91b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh @@ -0,0 +1,352 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|--------------------------------+ +# | SW | | +# | +--|------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +---------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +--|----------------------------------+ +# | +# +--|----------------------------------+ +# | | | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# | VRP2 (vrf) | +# +-------------------------------------+ + +: ${VXPORT:=4789} +: ${ALL_TESTS:=" + default_test + plain_test + reserved_0_test + reserved_10_test + reserved_31_test + reserved_56_test + reserved_63_test + "} + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + defer simple_if_fini $h1 192.0.2.1/28 + + tc qdisc add dev $h1 clsact + defer tc qdisc del dev $h1 clsact + + tc filter add dev $h1 ingress pref 77 \ + prot ip flower skip_hw ip_proto icmp action drop + defer tc filter del dev $h1 ingress pref 77 +} + +switch_create() +{ + ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip_link_set_addr br1 $(mac_get $swp1) + ip_link_set_up br1 + + ip_link_set_up $rp1 + ip_addr_add $rp1 192.0.2.17/28 + ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18 + + ip_link_set_master $swp1 br1 + ip_link_set_up $swp1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + defer simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + h1_create + switch_create + + vrp2_create +} + +vxlan_header_bytes() +{ + local vni=$1; shift + local -a extra_bits=("$@") + local -a bits + local i + + for ((i=0; i < 64; i++)); do + bits[i]=0 + done + + # Bit 4 is the I flag and is always on. + bits[4]=1 + + for i in ${extra_bits[@]}; do + bits[i]=1 + done + + # Bits 32..55 carry the VNI + local mask=0x800000 + for ((i=0; i < 24; i++)); do + bits[$((i + 32))]=$(((vni & mask) != 0)) + ((mask >>= 1)) + done + + local bytes + for ((i=0; i < 8; i++)); do + local byte=0 + local j + for ((j=0; j < 8; j++)); do + local bit=${bits[8 * i + j]} + ((byte += bit << (7 - j))) + done + bytes+=$(printf %02x $byte): + done + + echo ${bytes%:} +} + +neg_bytes() +{ + local bytes=$1; shift + + local -A neg=([0]=f [1]=e [2]=d [3]=c [4]=b [5]=a [6]=9 [7]=8 + [8]=7 [9]=6 [a]=5 [b]=4 [c]=3 [d]=2 [e]=1 [f]=0 [:]=:) + local out + local i + + for ((i=0; i < ${#bytes}; i++)); do + local c=${bytes:$i:1} + out+=${neg[$c]} + done + echo $out +} + +vxlan_ping_do() +{ + local count=$1; shift + local dev=$1; shift + local next_hop_mac=$1; shift + local dest_ip=$1; shift + local dest_mac=$1; shift + local vni=$1; shift + local reserved_bits=$1; shift + + local vxlan_header=$(vxlan_header_bytes $vni $reserved_bits) + + $MZ $dev -c $count -d 100msec -q \ + -b $next_hop_mac -B $dest_ip \ + -t udp sp=23456,dp=$VXPORT,p=$(: + )"$vxlan_header:"$( : VXLAN + )"$dest_mac:"$( : ETH daddr + )"00:11:22:33:44:55:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"00:00:"$( : IP header csum + )"$(ipv4_to_bytes 192.0.2.3):"$( : IP saddr + )"$(ipv4_to_bytes 192.0.2.1):"$( : IP daddr + )"08:"$( : ICMP type + )"00:"$( : ICMP code + )"8b:f2:"$( : ICMP csum + )"1f:6a:"$( : ICMP request identifier + )"00:01:"$( : ICMP request seq. number + )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload + )"6d:74:0b:00:00:00:00:00:"$( : + )"10:11:12:13:14:15:16:17:"$( : + )"18:19:1a:1b:1c:1d:1e:1f:"$( : + )"20:21:22:23:24:25:26:27:"$( : + )"28:29:2a:2b:2c:2d:2e:2f:"$( : + )"30:31:32:33:34:35:36:37" +} + +vxlan_device_add() +{ + ip_link_add vx1 up type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 100 "$@" + ip_link_set_master vx1 br1 +} + +vxlan_all_reserved_bits() +{ + local i + + for ((i=0; i < 64; i++)); do + if ((i == 4 || i >= 32 && i < 56)); then + continue + fi + echo $i + done +} + +vxlan_ping_vanilla() +{ + vxlan_ping_do 10 $rp2 $(mac_get $rp1) 192.0.2.17 $(mac_get $h1) 1000 +} + +vxlan_ping_reserved() +{ + for bit in $(vxlan_all_reserved_bits); do + vxlan_ping_do 1 $rp2 $(mac_get $rp1) \ + 192.0.2.17 $(mac_get $h1) 1000 "$bit" + ((n++)) + done +} + +vxlan_ping_test() +{ + local what=$1; shift + local get_stat=$1; shift + local expect=$1; shift + + RET=0 + + local t0=$($get_stat) + + "$@" + check_err $? "Failure when running $@" + + local t1=$($get_stat) + local delta=$((t1 - t0)) + + ((expect == delta)) + check_err $? "Expected to capture $expect packets, got $delta." + + log_test "$what" +} + +__default_test_do() +{ + local n_allowed_bits=$1; shift + local what=$1; shift + + vxlan_ping_test "$what: clean packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + 10 vxlan_ping_vanilla + + local t0=$(link_stats_get vx1 rx errors) + vxlan_ping_test "$what: mangled packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + $n_allowed_bits vxlan_ping_reserved + local t1=$(link_stats_get vx1 rx errors) + + RET=0 + local expect=$((39 - n_allowed_bits)) + local delta=$((t1 - t0)) + ((expect == delta)) + check_err $? "Expected $expect error packets, got $delta." + log_test "$what: drops reported" +} + +default_test_do() +{ + vxlan_device_add + __default_test_do 0 "Default" +} + +default_test() +{ + in_defer_scope \ + default_test_do +} + +plain_test_do() +{ + vxlan_device_add reserved_bits 0xf7ffffff000000ff + __default_test_do 0 "reserved_bits 0xf7ffffff000000ff" +} + +plain_test() +{ + in_defer_scope \ + plain_test_do +} + +reserved_test() +{ + local bit=$1; shift + + local allowed_bytes=$(vxlan_header_bytes 0xffffff $bit) + local reserved_bytes=$(neg_bytes $allowed_bytes) + local reserved_bits=${reserved_bytes//:/} + + vxlan_device_add reserved_bits 0x$reserved_bits + __default_test_do 1 "reserved_bits 0x$reserved_bits" +} + +reserved_0_test() +{ + in_defer_scope \ + reserved_test 0 +} + +reserved_10_test() +{ + in_defer_scope \ + reserved_test 10 +} + +reserved_31_test() +{ + in_defer_scope \ + reserved_test 31 +} + +reserved_56_test() +{ + in_defer_scope \ + reserved_test 56 +} + +reserved_63_test() +{ + in_defer_scope \ + reserved_test 63 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS -- 2.51.0 From 8a241ef9b9b86afc087e5b3e4a95cb60f9ee796c Mon Sep 17 00:00:00 2001 From: Shinas Rasheed Date: Thu, 5 Dec 2024 22:41:34 -0800 Subject: [PATCH 07/16] octeon_ep: add ndo ops for VFs in PF driver These APIs are needed to support applications that use netlink to get VF information from a PF driver. Signed-off-by: Shinas Rasheed Link: https://patch.msgid.link/20241206064135.2331790-1-srasheed@marvell.com Signed-off-by: Jakub Kicinski --- .../ethernet/marvell/octeon_ep/octep_main.c | 39 +++++++++++++++++++ .../ethernet/marvell/octeon_ep/octep_main.h | 1 + .../marvell/octeon_ep/octep_pfvf_mbox.c | 23 ++++++++++- .../marvell/octeon_ep/octep_pfvf_mbox.h | 6 ++- 4 files changed, 65 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 549436efc204..3a9825883d79 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1137,6 +1137,43 @@ static int octep_set_features(struct net_device *dev, netdev_features_t features return err; } +static int octep_get_vf_config(struct net_device *dev, int vf, + struct ifla_vf_info *ivi) +{ + struct octep_device *oct = netdev_priv(dev); + + ivi->vf = vf; + ether_addr_copy(ivi->mac, oct->vf_info[vf].mac_addr); + ivi->spoofchk = true; + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + ivi->trusted = false; + + return 0; +} + +static int octep_set_vf_mac(struct net_device *dev, int vf, u8 *mac) +{ + struct octep_device *oct = netdev_priv(dev); + int err; + + if (!is_valid_ether_addr(mac)) { + dev_err(&oct->pdev->dev, "Invalid MAC Address %pM\n", mac); + return -EADDRNOTAVAIL; + } + + dev_dbg(&oct->pdev->dev, "set vf-%d mac to %pM\n", vf, mac); + ether_addr_copy(oct->vf_info[vf].mac_addr, mac); + oct->vf_info[vf].flags |= OCTEON_PFVF_FLAG_MAC_SET_BY_PF; + + err = octep_ctrl_net_set_mac_addr(oct, vf, mac, true); + if (err) + dev_err(&oct->pdev->dev, + "Set VF%d MAC address failed via host control Mbox\n", + vf); + + return err; +} + static const struct net_device_ops octep_netdev_ops = { .ndo_open = octep_open, .ndo_stop = octep_stop, @@ -1146,6 +1183,8 @@ static const struct net_device_ops octep_netdev_ops = { .ndo_set_mac_address = octep_set_mac, .ndo_change_mtu = octep_change_mtu, .ndo_set_features = octep_set_features, + .ndo_get_vf_config = octep_get_vf_config, + .ndo_set_vf_mac = octep_set_vf_mac }; /** diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h index fee59e0e0138..3b56916af468 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h @@ -220,6 +220,7 @@ struct octep_iface_link_info { /* The Octeon VF device specific info data structure.*/ struct octep_pfvf_info { u8 mac_addr[ETH_ALEN]; + u32 flags; u32 mbox_version; }; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c index e6eb98d70f3c..ebecdd29f3bd 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c @@ -156,12 +156,23 @@ static void octep_pfvf_set_mac_addr(struct octep_device *oct, u32 vf_id, { int err; + if (oct->vf_info[vf_id].flags & OCTEON_PFVF_FLAG_MAC_SET_BY_PF) { + dev_err(&oct->pdev->dev, + "VF%d attempted to override administrative set MAC address\n", + vf_id); + rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; + return; + } + err = octep_ctrl_net_set_mac_addr(oct, vf_id, cmd.s_set_mac.mac_addr, true); if (err) { rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; - dev_err(&oct->pdev->dev, "Set VF MAC address failed via host control Mbox\n"); + dev_err(&oct->pdev->dev, "Set VF%d MAC address failed via host control Mbox\n", + vf_id); return; } + + ether_addr_copy(oct->vf_info[vf_id].mac_addr, cmd.s_set_mac.mac_addr); rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; } @@ -171,10 +182,18 @@ static void octep_pfvf_get_mac_addr(struct octep_device *oct, u32 vf_id, { int err; + if (oct->vf_info[vf_id].flags & OCTEON_PFVF_FLAG_MAC_SET_BY_PF) { + dev_dbg(&oct->pdev->dev, "VF%d MAC address set by PF\n", vf_id); + ether_addr_copy(rsp->s_set_mac.mac_addr, + oct->vf_info[vf_id].mac_addr); + rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; + return; + } err = octep_ctrl_net_get_mac_addr(oct, vf_id, rsp->s_set_mac.mac_addr); if (err) { rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; - dev_err(&oct->pdev->dev, "Get VF MAC address failed via host control Mbox\n"); + dev_err(&oct->pdev->dev, "Get VF%d MAC address failed via host control Mbox\n", + vf_id); return; } rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h index 0dc6eead292a..386a095a99bc 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.h @@ -8,8 +8,6 @@ #ifndef _OCTEP_PFVF_MBOX_H_ #define _OCTEP_PFVF_MBOX_H_ -/* VF flags */ -#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF BIT_ULL(0) /* PF has set VF MAC address */ #define OCTEON_SDP_16K_HW_FRS 16380UL #define OCTEON_SDP_64K_HW_FRS 65531UL @@ -23,6 +21,10 @@ enum octep_pfvf_mbox_version { #define OCTEP_PFVF_MBOX_VERSION_CURRENT OCTEP_PFVF_MBOX_VERSION_V2 +/* VF flags */ +/* PF has set VF MAC address */ +#define OCTEON_PFVF_FLAG_MAC_SET_BY_PF BIT(0) + enum octep_pfvf_mbox_opcode { OCTEP_PFVF_MBOX_CMD_VERSION, OCTEP_PFVF_MBOX_CMD_SET_MTU, -- 2.51.0 From 070927427d82debf5797e60c96165f2666c0bc42 Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Sat, 7 Dec 2024 00:21:39 +0500 Subject: [PATCH 08/16] net: renesas: rswitch: do not deinit disabled ports In rswitch_ether_port_init_all(), only enabled ports are initialized. Then, rswitch_ether_port_deinit_all() shall also only deinitialize enabled ports. Signed-off-by: Nikita Yushchenko Reviewed-by: Michal Swiatkowski Link: https://patch.msgid.link/20241206192140.1714-1-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/renesas/rswitch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 8d18dae4d8fb..3ba4a605f7cf 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1527,7 +1527,7 @@ static void rswitch_ether_port_deinit_all(struct rswitch_private *priv) { unsigned int i; - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + rswitch_for_each_enabled_port(priv, i) { phy_exit(priv->rdev[i]->serdes); rswitch_ether_port_deinit_one(priv->rdev[i]); } -- 2.51.0 From 32fd46f5b69e9a2e1206d576359e533e5b7c4694 Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Sat, 7 Dec 2024 00:21:40 +0500 Subject: [PATCH 09/16] net: renesas: rswitch: remove speed from gwca structure This field is set but never used. GWCA is rswitch CPU interface module which connects rswitch to the host over AXI bus. Speed of the switch ports is not anyhow related to GWCA operation. Signed-off-by: Nikita Yushchenko Reviewed-by: Michal Swiatkowski Link: https://patch.msgid.link/20241206192140.1714-2-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/renesas/rswitch.c | 3 --- drivers/net/ethernet/renesas/rswitch.h | 1 - 2 files changed, 4 deletions(-) diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 3ba4a605f7cf..b754cc96e268 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1901,9 +1901,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index if (err < 0) goto out_get_params; - if (rdev->priv->gwca.speed < rdev->etha->speed) - rdev->priv->gwca.speed = rdev->etha->speed; - err = rswitch_rxdmac_alloc(ndev); if (err < 0) goto out_rxdmac; diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 72e3ff596d31..303883369b94 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -993,7 +993,6 @@ struct rswitch_gwca { DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; - int speed; }; #define NUM_QUEUES_PER_NDEV 2 -- 2.51.0 From 31cdd8418234e70043abd26894b57eb201489cba Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:42:58 +0100 Subject: [PATCH 10/16] net: stmmac: Fix CSR divider comment The comment in declaration of STMMAC_CSR_250_300M incorrectly describes the constant as '/* MDC = clk_scr_i/122 */' but the DWC Ether QOS Handbook version 5.20a says it is CSR clock/124. Signed-off-by: Jan Petrous (OSS) Reviewed-by: Jacob Keller Reviewed-by: Russell King (Oracle) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-1-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- include/linux/stmmac.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d79ff252cfdc..75cbfb576358 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -33,7 +33,7 @@ #define STMMAC_CSR_20_35M 0x2 /* MDC = clk_scr_i/16 */ #define STMMAC_CSR_35_60M 0x3 /* MDC = clk_scr_i/26 */ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ -#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */ +#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/124 */ /* MTL algorithms identifiers */ #define MTL_TX_ALGORITHM_WRR 0x0 -- 2.51.0 From c8fab05d021dfc04401102f9fa1de07fc8f75d8d Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:42:59 +0100 Subject: [PATCH 11/16] net: stmmac: Extend CSR calc support Add support for CSR clock range up to 800 MHz. Reviewed-by: Jacob Keller Reviewed-by: Russell King (Oracle) Signed-off-by: Jan Petrous (OSS) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-2-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 ++ drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++++ include/linux/stmmac.h | 2 ++ 3 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 1367fa5c9b8e..70d601f45481 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -257,6 +257,8 @@ struct stmmac_safety_stats { #define CSR_F_150M 150000000 #define CSR_F_250M 250000000 #define CSR_F_300M 300000000 +#define CSR_F_500M 500000000 +#define CSR_F_800M 800000000 #define MAC_CSR_H_FRQ_MASK 0x20 diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9b262cdad60b..3cb7ad6ccc4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -325,6 +325,10 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv) priv->clk_csr = STMMAC_CSR_150_250M; else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M)) priv->clk_csr = STMMAC_CSR_250_300M; + else if ((clk_rate >= CSR_F_300M) && (clk_rate < CSR_F_500M)) + priv->clk_csr = STMMAC_CSR_300_500M; + else if ((clk_rate >= CSR_F_500M) && (clk_rate < CSR_F_800M)) + priv->clk_csr = STMMAC_CSR_500_800M; } if (priv->plat->flags & STMMAC_FLAG_HAS_SUN8I) { diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 75cbfb576358..865d0fe26f98 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -34,6 +34,8 @@ #define STMMAC_CSR_35_60M 0x3 /* MDC = clk_scr_i/26 */ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ #define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/124 */ +#define STMMAC_CSR_300_500M 0x6 /* MDC = clk_scr_i/204 */ +#define STMMAC_CSR_500_800M 0x7 /* MDC = clk_scr_i/324 */ /* MTL algorithms identifiers */ #define MTL_TX_ALGORITHM_WRR 0x0 -- 2.51.0 From cb09f61a9ab84369c62f2ef7f8a2b797f596f6d1 Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:43:00 +0100 Subject: [PATCH 12/16] net: stmmac: Fix clock rate variables size The clock API clk_get_rate() returns unsigned long value. Expand affected members of stmmac platform data and convert the stmmac_clk_csr_set() and dwmac4_core_init() methods to defining the unsigned long clk_rate local variables. Reviewed-by: Andrew Lunn Reviewed-by: Serge Semin Reviewed-by: Russell King (Oracle) Signed-off-by: Jan Petrous (OSS) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-3-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- include/linux/stmmac.h | 6 +++--- 5 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 901a3c1959fa..2a5b38723635 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -777,7 +777,7 @@ static void ethqos_ptp_clk_freq_config(struct stmmac_priv *priv) netdev_err(priv->dev, "Failed to max out clk_ptp_ref: %d\n", err); plat_dat->clk_ptp_rate = clk_get_rate(plat_dat->clk_ptp_ref); - netdev_dbg(priv->dev, "PTP rate %d\n", plat_dat->clk_ptp_rate); + netdev_dbg(priv->dev, "PTP rate %lu\n", plat_dat->clk_ptp_rate); } static int qcom_ethqos_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index c25781874aa7..c36f90a782c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -27,7 +27,7 @@ static void dwmac4_core_init(struct mac_device_info *hw, struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONFIG); - u32 clk_rate; + unsigned long clk_rate; value |= GMAC_CORE_INIT; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3cb7ad6ccc4e..d45fd7a3acd5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -301,7 +301,7 @@ static void stmmac_global_err(struct stmmac_priv *priv) */ static void stmmac_clk_csr_set(struct stmmac_priv *priv) { - u32 clk_rate; + unsigned long clk_rate; clk_rate = clk_get_rate(priv->plat->stmmac_clk); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3ac32444e492..06e07e6e180b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -640,7 +640,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dev_info(&pdev->dev, "PTP uses main clock\n"); } else { plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref); - dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate); + dev_dbg(&pdev->dev, "PTP rate %lu\n", plat->clk_ptp_rate); } plat->stmmac_rst = devm_reset_control_get_optional(&pdev->dev, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 865d0fe26f98..c9878a612e53 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -252,8 +252,8 @@ struct plat_stmmacenet_data { struct clk *stmmac_clk; struct clk *pclk; struct clk *clk_ptp_ref; - unsigned int clk_ptp_rate; - unsigned int clk_ref_rate; + unsigned long clk_ptp_rate; + unsigned long clk_ref_rate; unsigned int mult_fact_100ns; s32 ptp_max_adj; u32 cdc_error_adj; @@ -265,7 +265,7 @@ struct plat_stmmacenet_data { int mac_port_sel_speed; int has_xgmac; u8 vlan_fail_q; - unsigned int eee_usecs_rate; + unsigned long eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; int msi_mac_vec; -- 2.51.0 From 386aa60abdb600a4e5ad818e6dba171685942e54 Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:43:01 +0100 Subject: [PATCH 13/16] net: phy: Add helper for mapping RGMII link speed to clock rate The RGMII interface supports three data rates: 10/100 Mbps and 1 Gbps. These speeds correspond to clock frequencies of 2.5/25 MHz and 125 MHz, respectively. Many Ethernet drivers, including glues in stmmac, follow a similar pattern of converting RGMII speed to clock frequency. To simplify code, define the helper rgmii_clock(speed) to convert connection speed to clock frequency. Suggested-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Signed-off-by: Jan Petrous (OSS) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-4-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/include/linux/phy.h b/include/linux/phy.h index bb157136351e..e597a32cc787 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -298,6 +298,29 @@ static inline const char *phy_modes(phy_interface_t interface) } } +/** + * rgmii_clock - map link speed to the clock rate + * @speed: link speed value + * + * Description: maps RGMII supported link speeds + * into the clock rates. + * + * Returns: clock rate or negative errno + */ +static inline long rgmii_clock(int speed) +{ + switch (speed) { + case SPEED_10: + return 2500000; + case SPEED_100: + return 25000000; + case SPEED_1000: + return 125000000; + default: + return -EINVAL; + } +} + #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 -- 2.51.0 From 37b66c483e4c8a72cd1fd22f8ced05cc40f9e128 Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:43:02 +0100 Subject: [PATCH 14/16] net: dwmac-dwc-qos-eth: Use helper rgmii_clock Utilize a new helper function rgmii_clock(). Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Signed-off-by: Jan Petrous (OSS) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-5-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 83290e707df5..bd4eb187f8c6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -181,24 +181,19 @@ static void dwc_qos_remove(struct platform_device *pdev) static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode) { struct tegra_eqos *eqos = priv; - unsigned long rate = 125000000; bool needs_calibration = false; + long rate = 125000000; u32 value; int err; switch (speed) { case SPEED_1000: - needs_calibration = true; - rate = 125000000; - break; - case SPEED_100: needs_calibration = true; - rate = 25000000; - break; + fallthrough; case SPEED_10: - rate = 2500000; + rate = rgmii_clock(speed); break; default: -- 2.51.0 From 839b75ea4d940f810650a2ce11c91d94c5f01aa3 Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:43:03 +0100 Subject: [PATCH 15/16] net: dwmac-imx: Use helper rgmii_clock Utilize a new helper function rgmii_clock(). Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Signed-off-by: Jan Petrous (OSS) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-6-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 641f3cd019a3..43e0fbba4f77 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -186,7 +186,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod { struct plat_stmmacenet_data *plat_dat; struct imx_priv_data *dwmac = priv; - unsigned long rate; + long rate; int err; plat_dat = dwmac->plat_dat; @@ -196,17 +196,8 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod (plat_dat->mac_interface == PHY_INTERFACE_MODE_MII)) return; - switch (speed) { - case SPEED_1000: - rate = 125000000; - break; - case SPEED_100: - rate = 25000000; - break; - case SPEED_10: - rate = 2500000; - break; - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dwmac->dev, "invalid speed %u\n", speed); return; } -- 2.51.0 From 8470bfc835154a80774e5ab0e46969f196c0dba1 Mon Sep 17 00:00:00 2001 From: "Jan Petrous (OSS)" Date: Thu, 5 Dec 2024 17:43:04 +0100 Subject: [PATCH 16/16] net: dwmac-intel-plat: Use helper rgmii_clock Utilize a new helper function rgmii_clock(). When in, remove dead code in kmb_eth_fix_mac_speed(). Reviewed-by: Andrew Lunn Signed-off-by: Jan Petrous (OSS) Reviewed-by: Russell King (Oracle) Link: https://patch.msgid.link/20241205-upstream_s32cc_gmac-v8-7-ec1d180df815@oss.nxp.com Signed-off-by: Jakub Kicinski --- .../stmicro/stmmac/dwmac-intel-plat.c | 22 ++++--------------- 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index d94f0a150e93..ddee6154d40b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -31,27 +31,13 @@ struct intel_dwmac_data { static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) { struct intel_dwmac *dwmac = priv; - unsigned long rate; + long rate; int ret; - rate = clk_get_rate(dwmac->tx_clk); - - switch (speed) { - case SPEED_1000: - rate = 125000000; - break; - - case SPEED_100: - rate = 25000000; - break; - - case SPEED_10: - rate = 2500000; - break; - - default: + rate = rgmii_clock(speed); + if (rate < 0) { dev_err(dwmac->dev, "Invalid speed\n"); - break; + return; } ret = clk_set_rate(dwmac->tx_clk, rate); -- 2.51.0