* [PATCH iwl-next 1/2] ice: fix TC flower filters matching more than the ip_proto key
2026-09-10 15:48 [PATCH iwl-next 0/2] ice: fix TC flower filter priority violations Petr Oros
@ 2026-09-10 15:48 ` Petr Oros
2026-09-11 20:59 ` Loktionov, Aleksandr
2026-09-10 15:48 ` [PATCH iwl-next 2/2] ice: don't offload drop filters that bypass higher priority filters Petr Oros
1 sibling, 1 reply; 5+ messages in thread
From: Petr Oros @ 2026-09-10 15:48 UTC (permalink / raw)
To: netdev
Cc: Petr Oros, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Priyalee Kushwaha, Kiran Patil, Wojciech Drewek,
Michal Swiatkowski, intel-wired-lan, linux-kernel
ice_parse_cls_flower() stores the ip_proto key from the flow rule but
never programs a matching lookup unless the filter also matches on L4
ports or the L2TPv3 session ID. A filter like:
tc filter add dev $pf ingress protocol ip flower skip_sw \
ip_proto udp action drop
is silently programmed into the hardware as a match on eth_type ipv4
alone and drops every IPv4 packet, not just UDP.
Program the IP protocol match through the protocol field of the IPv4
header lookup and the next header field of the IPv6 header lookup, the
same lookups that are already used for ToS and TTL. The OS default and
comms DDP packages provide no profile that extracts the IPv6 next
header word, so the IPv6 rule programming currently fails with
"Required profiles not found" and the filter falls back to software
evaluation instead of over-matching, and the offload starts working
with a DDP package that can extract it. Note that the lookup matches
the next header byte of the base IPv6 header, so packets carrying
extension headers are not matched in hardware and fall back to
software evaluation, which under-matches only for skip_sw filters.
GTP tunnel and PPPoE filters rewrite the parsed ethertype, the IP
header lookups are not available there, so reject an unconsumed
ip_proto for them instead of silently widening the match. Filters where
ip_proto is implied by an L4 ports or L2TPv3 session ID lookup are not
affected. Based on an earlier unapplied patch from Michal Swiatkowski
that implemented the IPv4 part [1].
Link: https://lore.kernel.org/intel-wired-lan/20240222123956.2393-3-michal.swiatkowski@linux.intel.com/ [1]
Fixes: 0d08a441fb1a ("ice: ndo_setup_tc implementation for PF")
Signed-off-by: Petr Oros <poros@redhat.com>
---
drivers/net/ethernet/intel/ice/ice_tc_lib.c | 37 +++++++++++++++++++--
drivers/net/ethernet/intel/ice/ice_tc_lib.h | 1 +
2 files changed, 35 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index d20357c0412731..fbd8cbad150a98 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -78,7 +78,8 @@ static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_fltr *fltr)
ICE_TC_FLWR_FIELD_DEST_IPV6 | ICE_TC_FLWR_FIELD_SRC_IPV6))
lkups_cnt++;
- if (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL))
+ if (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL |
+ ICE_TC_FLWR_FIELD_IP_PROTO))
lkups_cnt++;
/* are L2TPv3 options specified? */
@@ -552,7 +553,8 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
}
if (headers->l2_key.n_proto == htons(ETH_P_IP) &&
- (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL))) {
+ (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL |
+ ICE_TC_FLWR_FIELD_IP_PROTO))) {
list[i].type = ice_proto_type_from_ipv4(inner);
if (flags & ICE_TC_FLWR_FIELD_IP_TOS) {
@@ -567,11 +569,19 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
headers->l3_mask.ttl;
}
+ if (flags & ICE_TC_FLWR_FIELD_IP_PROTO) {
+ list[i].h_u.ipv4_hdr.protocol =
+ headers->l3_key.ip_proto;
+ list[i].m_u.ipv4_hdr.protocol =
+ headers->l3_mask.ip_proto;
+ }
+
i++;
}
if (headers->l2_key.n_proto == htons(ETH_P_IPV6) &&
- (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL))) {
+ (flags & (ICE_TC_FLWR_FIELD_IP_TOS | ICE_TC_FLWR_FIELD_IP_TTL |
+ ICE_TC_FLWR_FIELD_IP_PROTO))) {
struct ice_ipv6_hdr *hdr_h, *hdr_m;
hdr_h = &list[i].h_u.ipv6_hdr;
@@ -592,6 +602,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
hdr_m->hop_limit = headers->l3_mask.ttl;
}
+ if (flags & ICE_TC_FLWR_FIELD_IP_PROTO) {
+ hdr_h->next_hdr = headers->l3_key.ip_proto;
+ hdr_m->next_hdr = headers->l3_mask.ip_proto;
+ }
+
i++;
}
@@ -1737,6 +1752,9 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
headers->l2_key.n_proto = cpu_to_be16(n_proto_key);
headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask);
headers->l3_key.ip_proto = match.key->ip_proto;
+ headers->l3_mask.ip_proto = match.mask->ip_proto;
+ if (match.mask->ip_proto)
+ fltr->flags |= ICE_TC_FLWR_FIELD_IP_PROTO;
}
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
@@ -1910,6 +1928,19 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi,
}
}
+ if (fltr->flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT |
+ ICE_TC_FLWR_FIELD_SRC_L4_PORT |
+ ICE_TC_FLWR_FIELD_L2TPV3_SESSID))
+ fltr->flags &= ~ICE_TC_FLWR_FIELD_IP_PROTO;
+
+ if ((fltr->flags & ICE_TC_FLWR_FIELD_IP_PROTO) &&
+ headers->l2_key.n_proto != htons(ETH_P_IP) &&
+ headers->l2_key.n_proto != htons(ETH_P_IPV6)) {
+ NL_SET_ERR_MSG_MOD(fltr->extack,
+ "IP protocol match is not supported with GTP or PPPoE");
+ return -EOPNOTSUPP;
+ }
+
/* Ingress filter on representor results in an egress filter in HW
* and vice versa
*/
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index 8a3ab2f22af9ba..752af65e70b7bf 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -38,6 +38,7 @@
#define ICE_TC_FLWR_FIELD_CVLAN_PRIO BIT(28)
#define ICE_TC_FLWR_FIELD_VLAN_TPID BIT(29)
#define ICE_TC_FLWR_FIELD_PFCP_OPTS BIT(30)
+#define ICE_TC_FLWR_FIELD_IP_PROTO BIT(31)
#define ICE_TC_FLOWER_MASK_32 0xFFFFFFFF
--
2.55.0
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH iwl-next 2/2] ice: don't offload drop filters that bypass higher priority filters
2026-09-10 15:48 [PATCH iwl-next 0/2] ice: fix TC flower filter priority violations Petr Oros
2026-09-10 15:48 ` [PATCH iwl-next 1/2] ice: fix TC flower filters matching more than the ip_proto key Petr Oros
@ 2026-09-10 15:48 ` Petr Oros
2026-09-12 8:36 ` Simon Horman
1 sibling, 1 reply; 5+ messages in thread
From: Petr Oros @ 2026-09-10 15:48 UTC (permalink / raw)
To: netdev
Cc: Petr Oros, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Priyalee Kushwaha, Kiran Patil, Wojciech Drewek,
Michal Swiatkowski, intel-wired-lan, linux-kernel
The E810 switch gives drop rules absolute precedence over forwarding
rules regardless of recipe priority (verified on E810 in every
combination of installation order and match specificity). TC however
requires filters to be evaluated in priority order, so when a higher
priority filter stays software-only because its match or action cannot
be offloaded while a lower priority drop filter is offloaded, the
hardware drops packets the higher priority filter should have seen:
tc filter add dev $pf ingress prio 1 protocol ip flower \
ip_proto l2tp action pass
tc filter add dev $pf ingress prio 2 protocol ip flower action drop
The pass filter is rejected (unsupported action), the drop filter is
offloaded and the hardware drops all IPv4 traffic including the L2TP
packets the prio 1 filter should accept.
Track filters that were presented to the driver but not offloaded and
refuse to offload a drop filter when a higher priority filter on the
same device block and direction is software-only or is offloaded with a
forwarding action, which the hardware drop would equally override. The
refused drop filter keeps working in software. Filters are compared
only within one device block since TC priorities are not ordered across
blocks. Filters with skip_sw bypass the check because the user
explicitly requested hardware-only operation and refusing would fail
the filter add entirely, and the tracking applies to the legacy switch
mode only, switchdev pipelines manage rule priorities themselves.
The check does not analyze match overlap, so it is conservative, and it
runs only at drop offload time. A conflicting filter installed after a
drop filter was already offloaded cannot un-offload it, and filters the
driver never saw (added while hw-tc-offload was off) are invisible to
it. Installing filters in priority order with offload enabled avoids
both.
Fixes: 0d08a441fb1a ("ice: ndo_setup_tc implementation for PF")
Signed-off-by: Petr Oros <poros@redhat.com>
---
drivers/net/ethernet/intel/ice/ice.h | 1 +
drivers/net/ethernet/intel/ice/ice_tc_lib.c | 150 +++++++++++++++++++-
drivers/net/ethernet/intel/ice/ice_tc_lib.h | 21 +++
3 files changed, 166 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index db3c7015c56c43..6c596e5a315175 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -643,6 +643,7 @@ struct ice_pf {
*/
u16 num_dmac_chnl_fltrs;
struct hlist_head tc_flower_fltr_list;
+ struct hlist_head tc_sw_fltr_list;
u64 supported_rxdids;
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index fbd8cbad150a98..7cfc8941b7ba57 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -2269,6 +2269,112 @@ ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie)
return NULL;
}
+/**
+ * ice_tc_fltr_is_drop - check if a filter carries a drop action
+ * @cls_flower: offload request describing the filter
+ *
+ * Return: true if any action of the filter is a drop, false otherwise.
+ */
+static bool ice_tc_fltr_is_drop(struct flow_cls_offload *cls_flower)
+{
+ struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower);
+ struct flow_action_entry *act;
+ int i;
+
+ if (cls_flower->classid)
+ return false;
+
+ flow_action_for_each(i, act, &rule->action)
+ if (act->id == FLOW_ACTION_DROP)
+ return true;
+
+ return false;
+}
+
+/**
+ * ice_tc_untrack_sw_fltr - forget a tracked software-only filter
+ * @pf: pointer to PF structure
+ * @cookie: unique filter identifier from the offload request
+ *
+ * Return: true if the filter was tracked, false otherwise.
+ */
+static bool ice_tc_untrack_sw_fltr(struct ice_pf *pf, unsigned long cookie)
+{
+ struct ice_tc_sw_fltr *sw_fltr;
+
+ hlist_for_each_entry(sw_fltr, &pf->tc_sw_fltr_list, node) {
+ if (sw_fltr->cookie != cookie)
+ continue;
+
+ hlist_del(&sw_fltr->node);
+ kfree(sw_fltr);
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * ice_tc_track_sw_fltr - remember a filter that was not offloaded
+ * @pf: pointer to PF structure
+ * @filter_dev: device the filter was requested on
+ * @cls_flower: offload request describing the filter
+ * @direction: block direction the filter was requested for
+ */
+static void ice_tc_track_sw_fltr(struct ice_pf *pf,
+ struct net_device *filter_dev,
+ struct flow_cls_offload *cls_flower,
+ enum ice_eswitch_fltr_direction direction)
+{
+ struct ice_tc_sw_fltr *sw_fltr;
+
+ hlist_for_each_entry(sw_fltr, &pf->tc_sw_fltr_list, node)
+ if (sw_fltr->cookie == cls_flower->cookie)
+ return;
+
+ sw_fltr = kzalloc_obj(*sw_fltr);
+ if (!sw_fltr)
+ return;
+
+ sw_fltr->cookie = cls_flower->cookie;
+ sw_fltr->filter_dev = filter_dev;
+ sw_fltr->prio = cls_flower->common.prio;
+ sw_fltr->direction = direction;
+ sw_fltr->is_drop = ice_tc_fltr_is_drop(cls_flower);
+ hlist_add_head(&sw_fltr->node, &pf->tc_sw_fltr_list);
+}
+
+/**
+ * ice_tc_drop_bypasses_fltr - check if a drop rule would bypass a filter
+ * @pf: pointer to PF structure
+ * @filter_dev: device the drop filter is requested on
+ * @prio: TC priority of the drop filter
+ * @direction: block direction of the drop filter
+ *
+ * Return: true if such a filter exists, false otherwise.
+ */
+static bool
+ice_tc_drop_bypasses_fltr(struct ice_pf *pf, struct net_device *filter_dev,
+ u32 prio, enum ice_eswitch_fltr_direction direction)
+{
+ struct ice_tc_flower_fltr *fltr;
+ struct ice_tc_sw_fltr *sw_fltr;
+
+ hlist_for_each_entry(sw_fltr, &pf->tc_sw_fltr_list, node)
+ if (sw_fltr->filter_dev == filter_dev &&
+ sw_fltr->direction == direction && sw_fltr->prio < prio &&
+ !sw_fltr->is_drop)
+ return true;
+
+ hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node)
+ if (fltr->filter_dev == filter_dev &&
+ fltr->direction == direction && fltr->prio < prio &&
+ fltr->action.fltr_act != ICE_DROP_PACKET)
+ return true;
+
+ return false;
+}
+
/**
* ice_add_cls_flower - add TC flower filters
* @netdev: Pointer to filter device
@@ -2284,14 +2390,24 @@ int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
{
struct netlink_ext_ack *extack = cls_flower->common.extack;
struct net_device *vsi_netdev = vsi->netdev;
+ enum ice_eswitch_fltr_direction direction;
struct ice_tc_flower_fltr *fltr;
struct ice_pf *pf = vsi->back;
+ bool track_sw_fltrs;
int err;
- if (ice_is_reset_in_progress(pf->state))
- return -EBUSY;
- if (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
- return -EINVAL;
+ direction = ingress ? ICE_ESWITCH_FLTR_INGRESS :
+ ICE_ESWITCH_FLTR_EGRESS;
+ track_sw_fltrs = !ice_is_eswitch_mode_switchdev(pf);
+
+ if (ice_is_reset_in_progress(pf->state)) {
+ err = -EBUSY;
+ goto track_sw;
+ }
+ if (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) {
+ err = -EINVAL;
+ goto track_sw;
+ }
if (ice_is_port_repr_netdev(netdev))
vsi_netdev = netdev;
@@ -2304,7 +2420,8 @@ int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
*/
if (netdev == vsi_netdev)
NL_SET_ERR_MSG_MOD(extack, "can't apply TC flower filters, turn ON hw-tc-offload and try again");
- return -EINVAL;
+ err = -EINVAL;
+ goto track_sw;
}
/* avoid duplicate entries, if exists - return error */
@@ -2314,14 +2431,32 @@ int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
return -EEXIST;
}
+ if (track_sw_fltrs && !cls_flower->common.skip_sw &&
+ ice_tc_fltr_is_drop(cls_flower) &&
+ ice_tc_drop_bypasses_fltr(pf, netdev, cls_flower->common.prio,
+ direction)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Drop filter not offloaded because it would bypass a higher priority filter");
+ err = -EOPNOTSUPP;
+ goto track_sw;
+ }
+
/* prep and add TC-flower filter in HW */
err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr, ingress);
if (err)
- return err;
+ goto track_sw;
+
+ fltr->filter_dev = netdev;
+ fltr->prio = cls_flower->common.prio;
/* add filter into an ordered list */
hlist_add_head(&fltr->tc_flower_node, &pf->tc_flower_fltr_list);
return 0;
+
+track_sw:
+ if (track_sw_fltrs && !cls_flower->common.skip_sw)
+ ice_tc_track_sw_fltr(pf, netdev, cls_flower, direction);
+ return err;
}
/**
@@ -2336,6 +2471,9 @@ ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower)
struct ice_pf *pf = vsi->back;
int err;
+ if (ice_tc_untrack_sw_fltr(pf, cls_flower->cookie))
+ return 0;
+
/* find filter */
fltr = ice_find_tc_flower_fltr(pf, cls_flower->cookie);
if (!fltr) {
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index 752af65e70b7bf..37d6f4100ecfbc 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -139,12 +139,33 @@ enum ice_eswitch_fltr_direction {
ICE_ESWITCH_FLTR_EGRESS,
};
+/**
+ * struct ice_tc_sw_fltr - filter presented to the driver but not offloaded
+ * @node: node in the pf->tc_sw_fltr_list
+ * @cookie: unique filter identifier from the offload request
+ * @filter_dev: device the filter was requested on
+ * @prio: TC priority, lower value is evaluated first
+ * @direction: block direction the filter was requested for
+ * @is_drop: the filter carries a drop action
+ */
+struct ice_tc_sw_fltr {
+ struct hlist_node node;
+ unsigned long cookie;
+ struct net_device *filter_dev;
+ u32 prio;
+ enum ice_eswitch_fltr_direction direction;
+ bool is_drop;
+};
+
struct ice_tc_flower_fltr {
struct hlist_node tc_flower_node;
/* cookie becomes filter_rule_id if rule is added successfully */
unsigned long cookie;
+ struct net_device *filter_dev;
+ u32 prio;
+
/* add_adv_rule returns information like recipe ID, rule_id. Store
* those values since they are needed to remove advanced rule
*/
--
2.55.0
^ permalink raw reply [flat|nested] 5+ messages in thread