* Re: [PATCH 1/2] proc: revalidate directories created with proc_net_mkdir()
From: Alexey Dobriyan @ 2019-07-07 8:03 UTC (permalink / raw)
To: Al Viro; +Cc: davem, netdev, Per.Hallsmark
In-Reply-To: <20190707010317.GR17978@ZenIV.linux.org.uk>
On Sun, Jul 07, 2019 at 02:03:20AM +0100, Al Viro wrote:
> On Sat, Jul 06, 2019 at 07:52:02PM +0300, Alexey Dobriyan wrote:
> > +struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode,
> > + struct proc_dir_entry **parent, void *data)
>
> Two underscores, please...
Second underscore is more typing, I never understood it.
> > + parent->nlink++;
> > + pde = proc_register(parent, pde);
> > + if (!pde)
> > + parent->nlink++;
>
> Really?
And ->nlink is a separate bug.
^ permalink raw reply
* [PATCH net-next v4 2/4] net/flow_dissector: add connection tracking dissection
From: Paul Blakey @ 2019-07-07 8:03 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562486612-22770-1-git-send-email-paulb@mellanox.com>
Retreives connection tracking zone, mark, label, and state from
a SKB.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/linux/skbuff.h | 10 ++++++++++
include/net/flow_dissector.h | 15 +++++++++++++++
net/core/flow_dissector.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 69 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b5d427b..1dcb674 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1324,6 +1324,16 @@ void skb_flow_dissect_meta(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container);
+/* Gets a skb connection tracking info, ctinfo map should be a
+ * a map of mapsize to translate enum ip_conntrack_info states
+ * to user states.
+ */
+void
+skb_flow_dissect_ct(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
+ u16 *ctinfo_map,
+ size_t mapsize);
void
skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 02478e4..90bd210 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -208,6 +208,20 @@ struct flow_dissector_key_meta {
int ingress_ifindex;
};
+/**
+ * struct flow_dissector_key_ct:
+ * @ct_state: conntrack state after converting with map
+ * @ct_mark: conttrack mark
+ * @ct_zone: conntrack zone
+ * @ct_labels: conntrack labels
+ */
+struct flow_dissector_key_ct {
+ u16 ct_state;
+ u16 ct_zone;
+ u32 ct_mark;
+ u32 ct_labels[4];
+};
+
enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -234,6 +248,7 @@ enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */
FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */
FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */
+ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
FLOW_DISSECTOR_KEY_MAX,
};
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 01ad60b..3e6fedb 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -27,6 +27,10 @@
#include <scsi/fc/fc_fcoe.h>
#include <uapi/linux/batadv_packet.h>
#include <linux/bpf.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_labels.h>
+#endif
static DEFINE_MUTEX(flow_dissector_mutex);
@@ -232,6 +236,46 @@ void skb_flow_dissect_meta(const struct sk_buff *skb,
}
void
+skb_flow_dissect_ct(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container,
+ u16 *ctinfo_map,
+ size_t mapsize)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ struct flow_dissector_key_ct *key;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn_labels *cl;
+ struct nf_conn *ct;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT))
+ return;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return;
+
+ key = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_CT,
+ target_container);
+
+ if (ctinfo < mapsize)
+ key->ct_state = ctinfo_map[ctinfo];
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)
+ key->ct_zone = ct->zone.id;
+#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
+ key->ct_mark = ct->mark;
+#endif
+
+ cl = nf_ct_labels_find(ct);
+ if (cl)
+ memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels));
+#endif /* CONFIG_NF_CONNTRACK */
+}
+EXPORT_SYMBOL(skb_flow_dissect_ct);
+
+void
skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v4 3/4] net/sched: cls_flower: Add matching on conntrack info
From: Paul Blakey @ 2019-07-07 8:03 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562486612-22770-1-git-send-email-paulb@mellanox.com>
New matches for conntrack mark, label, zone, and state.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/uapi/linux/pkt_cls.h | 16 ++++++
net/sched/cls_flower.c | 127 +++++++++++++++++++++++++++++++++++++++++--
2 files changed, 138 insertions(+), 5 deletions(-)
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 7c9d701..6992df1 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -536,12 +536,28 @@ enum {
TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */
TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */
+ TCA_FLOWER_KEY_CT_STATE, /* u16 */
+ TCA_FLOWER_KEY_CT_STATE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_MARK, /* u32 */
+ TCA_FLOWER_KEY_CT_MARK_MASK, /* u32 */
+ TCA_FLOWER_KEY_CT_LABELS, /* u128 */
+ TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */
+
__TCA_FLOWER_MAX,
};
#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
enum {
+ TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */
+};
+
+enum {
TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
* TCA_FLOWER_KEY_ENC_OPT_GENEVE_
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index ce2e9b1..d90ec2c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -26,6 +26,8 @@
#include <net/dst.h>
#include <net/dst_metadata.h>
+#include <uapi/linux/netfilter/nf_conntrack_common.h>
+
struct fl_flow_key {
struct flow_dissector_key_meta meta;
struct flow_dissector_key_control control;
@@ -54,6 +56,7 @@ struct fl_flow_key {
struct flow_dissector_key_enc_opts enc_opts;
struct flow_dissector_key_ports tp_min;
struct flow_dissector_key_ports tp_max;
+ struct flow_dissector_key_ct ct;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -272,14 +275,27 @@ static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
return __fl_lookup(mask, mkey);
}
+static u16 fl_ct_info_to_flower_map[] = {
+ [IP_CT_ESTABLISHED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED,
+ [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED,
+ [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED,
+ [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED,
+ [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_NEW,
+};
+
static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_fl_head *head = rcu_dereference_bh(tp->root);
- struct cls_fl_filter *f;
- struct fl_flow_mask *mask;
- struct fl_flow_key skb_key;
struct fl_flow_key skb_mkey;
+ struct fl_flow_key skb_key;
+ struct fl_flow_mask *mask;
+ struct cls_fl_filter *f;
list_for_each_entry_rcu(mask, &head->masks, list) {
fl_clear_masked_range(&skb_key, mask);
@@ -290,6 +306,9 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
*/
skb_key.basic.n_proto = skb->protocol;
skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
+ skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
+ fl_ct_info_to_flower_map,
+ ARRAY_SIZE(fl_ct_info_to_flower_map));
skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
fl_set_masked_key(&skb_mkey, &skb_key, mask);
@@ -704,6 +723,16 @@ static void *fl_get(struct tcf_proto *tp, u32 handle)
[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED },
[TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_CT_STATE] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_STATE_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_ZONE] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_ZONE_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_CT_MARK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_CT_MARK_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_CT_LABELS] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
};
static const struct nla_policy
@@ -725,11 +754,11 @@ static void fl_set_key_val(struct nlattr **tb,
{
if (!tb[val_type])
return;
- memcpy(val, nla_data(tb[val_type]), len);
+ nla_memcpy(val, tb[val_type], len);
if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type])
memset(mask, 0xff, len);
else
- memcpy(mask, nla_data(tb[mask_type]), len);
+ nla_memcpy(mask, tb[mask_type], len);
}
static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
@@ -1015,6 +1044,51 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
return 0;
}
+static int fl_set_key_ct(struct nlattr **tb,
+ struct flow_dissector_key_ct *key,
+ struct flow_dissector_key_ct *mask,
+ struct netlink_ext_ack *extack)
+{
+ if (tb[TCA_FLOWER_KEY_CT_STATE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK)) {
+ NL_SET_ERR_MSG(extack, "Conntrack isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE,
+ &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
+ sizeof(key->ct_state));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_ZONE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
+ NL_SET_ERR_MSG(extack, "Conntrack zones isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE,
+ &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK,
+ sizeof(key->ct_zone));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_MARK]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
+ NL_SET_ERR_MSG(extack, "Conntrack mark isn't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK,
+ &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK,
+ sizeof(key->ct_mark));
+ }
+ if (tb[TCA_FLOWER_KEY_CT_LABELS]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
+ NL_SET_ERR_MSG(extack, "Conntrack labels aren't enabled");
+ return -EOPNOTSUPP;
+ }
+ fl_set_key_val(tb, key->ct_labels, TCA_FLOWER_KEY_CT_LABELS,
+ mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK,
+ sizeof(key->ct_labels));
+ }
+
+ return 0;
+}
+
static int fl_set_key(struct net *net, struct nlattr **tb,
struct fl_flow_key *key, struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -1224,6 +1298,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
return ret;
}
+ ret = fl_set_key_ct(tb, &key->ct, &mask->ct, extack);
+ if (ret)
+ return ret;
+
if (tb[TCA_FLOWER_KEY_FLAGS])
ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
@@ -1324,6 +1402,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_CT, ct);
skb_flow_dissector_init(dissector, keys, cnt);
}
@@ -2078,6 +2158,40 @@ static int fl_dump_key_geneve_opt(struct sk_buff *skb,
return -EMSGSIZE;
}
+static int fl_dump_key_ct(struct sk_buff *skb,
+ struct flow_dissector_key_ct *key,
+ struct flow_dissector_key_ct *mask)
+{
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK) &&
+ fl_dump_key_val(skb, &key->ct_state, TCA_FLOWER_KEY_CT_STATE,
+ &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
+ sizeof(key->ct_state)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ fl_dump_key_val(skb, &key->ct_zone, TCA_FLOWER_KEY_CT_ZONE,
+ &mask->ct_zone, TCA_FLOWER_KEY_CT_ZONE_MASK,
+ sizeof(key->ct_zone)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
+ fl_dump_key_val(skb, &key->ct_mark, TCA_FLOWER_KEY_CT_MARK,
+ &mask->ct_mark, TCA_FLOWER_KEY_CT_MARK_MASK,
+ sizeof(key->ct_mark)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
+ fl_dump_key_val(skb, &key->ct_labels, TCA_FLOWER_KEY_CT_LABELS,
+ &mask->ct_labels, TCA_FLOWER_KEY_CT_LABELS_MASK,
+ sizeof(key->ct_labels)))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
struct flow_dissector_key_enc_opts *enc_opts)
{
@@ -2311,6 +2425,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts))
goto nla_put_failure;
+ if (fl_dump_key_ct(skb, &key->ct, &mask->ct))
+ goto nla_put_failure;
+
if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
goto nla_put_failure;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v4 1/4] net/sched: Introduce action ct
From: Paul Blakey @ 2019-07-07 8:03 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562486612-22770-1-git-send-email-paulb@mellanox.com>
Allow sending a packet to conntrack module for connection tracking.
The packet will be marked with conntrack connection's state, and
any metadata such as conntrack mark and label. This state metadata
can later be matched against with tc classifers, for example with the
flower classifier as below.
In addition to committing new connections the user can optionally
specific a zone to track within, set a mark/label and configure nat
with an address range and port range.
Usage is as follows:
$ tc qdisc add dev ens1f0_0 ingress
$ tc qdisc add dev ens1f0_1 ingress
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 2
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_state +trk+new \
action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 1 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_0
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Changelog:
V3->V4:
Added strict_start_type for act_ct policy
V2->V3:
Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c
V1->V2:
Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max
Refactored NAT_PORT_MIN_MAX range handling as well
Added ipv4/ipv6 defragmentation
Removed extra skb pull push of nw offset in exectute nat
Refactored tcf_ct_skb_network_trim after pull
Removed TCA_ACT_CT define
---
include/net/flow_offload.h | 5 +
include/net/tc_act/tc_ct.h | 63 +++
include/uapi/linux/pkt_cls.h | 1 +
include/uapi/linux/tc_act/tc_ct.h | 41 ++
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/act_ct.c | 979 ++++++++++++++++++++++++++++++++++++++
net/sched/cls_api.c | 5 +
8 files changed, 1106 insertions(+)
create mode 100644 include/net/tc_act/tc_ct.h
create mode 100644 include/uapi/linux/tc_act/tc_ct.h
create mode 100644 net/sched/act_ct.c
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 36127c1..a09e256 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -129,6 +129,7 @@ enum flow_action_id {
FLOW_ACTION_QUEUE,
FLOW_ACTION_SAMPLE,
FLOW_ACTION_POLICE,
+ FLOW_ACTION_CT,
};
/* This is mirroring enum pedit_header_type definition for easy mapping between
@@ -178,6 +179,10 @@ struct flow_action_entry {
s64 burst;
u64 rate_bytes_ps;
} police;
+ struct { /* FLOW_ACTION_CT */
+ int action;
+ u16 zone;
+ } ct;
};
};
diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h
new file mode 100644
index 0000000..bdc20ab
--- /dev/null
+++ b/include/net/tc_act/tc_ct.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_TC_CT_H
+#define __NET_TC_CT_H
+
+#include <net/act_api.h>
+#include <uapi/linux/tc_act/tc_ct.h>
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_conntrack_labels.h>
+
+struct tcf_ct_params {
+ struct nf_conn *tmpl;
+ u16 zone;
+
+ u32 mark;
+ u32 mark_mask;
+
+ u32 labels[NF_CT_LABELS_MAX_SIZE / sizeof(u32)];
+ u32 labels_mask[NF_CT_LABELS_MAX_SIZE / sizeof(u32)];
+
+ struct nf_nat_range2 range;
+ bool ipv4_range;
+
+ u16 ct_action;
+
+ struct rcu_head rcu;
+};
+
+struct tcf_ct {
+ struct tc_action common;
+ struct tcf_ct_params __rcu *params;
+};
+
+#define to_ct(a) ((struct tcf_ct *)a)
+#define to_ct_params(a) ((struct tcf_ct_params *) \
+ rtnl_dereference((to_ct(a)->params)))
+
+static inline uint16_t tcf_ct_zone(const struct tc_action *a)
+{
+ return to_ct_params(a)->zone;
+}
+
+static inline int tcf_ct_action(const struct tc_action *a)
+{
+ return to_ct_params(a)->ct_action;
+}
+
+#else
+static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }
+static inline int tcf_ct_action(const struct tc_action *a) { return 0; }
+#endif /* CONFIG_NF_CONNTRACK */
+
+static inline bool is_tcf_ct(const struct tc_action *a)
+{
+#if defined(CONFIG_NET_CLS_ACT) && IS_ENABLED(CONFIG_NF_CONNTRACK)
+ if (a->ops && a->ops->id == TCA_ID_CT)
+ return true;
+#endif
+ return false;
+}
+
+#endif /* __NET_TC_CT_H */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 8cc6b67..7c9d701 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -106,6 +106,7 @@ enum tca_id {
TCA_ID_SAMPLE = TCA_ACT_SAMPLE,
/* other actions go here */
TCA_ID_CTINFO,
+ TCA_ID_CT,
__TCA_ID_MAX = 255
};
diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h
new file mode 100644
index 0000000..5fb1d7a
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ct.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CT_H
+#define __UAPI_TC_CT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_CT_UNSPEC,
+ TCA_CT_PARMS,
+ TCA_CT_TM,
+ TCA_CT_ACTION, /* u16 */
+ TCA_CT_ZONE, /* u16 */
+ TCA_CT_MARK, /* u32 */
+ TCA_CT_MARK_MASK, /* u32 */
+ TCA_CT_LABELS, /* u128 */
+ TCA_CT_LABELS_MASK, /* u128 */
+ TCA_CT_NAT_IPV4_MIN, /* be32 */
+ TCA_CT_NAT_IPV4_MAX, /* be32 */
+ TCA_CT_NAT_IPV6_MIN, /* struct in6_addr */
+ TCA_CT_NAT_IPV6_MAX, /* struct in6_addr */
+ TCA_CT_NAT_PORT_MIN, /* be16 */
+ TCA_CT_NAT_PORT_MAX, /* be16 */
+ TCA_CT_PAD,
+ __TCA_CT_MAX
+};
+
+#define TCA_CT_MAX (__TCA_CT_MAX - 1)
+
+#define TCA_CT_ACT_COMMIT (1 << 0)
+#define TCA_CT_ACT_FORCE (1 << 1)
+#define TCA_CT_ACT_CLEAR (1 << 2)
+#define TCA_CT_ACT_NAT (1 << 3)
+#define TCA_CT_ACT_NAT_SRC (1 << 4)
+#define TCA_CT_ACT_NAT_DST (1 << 5)
+
+struct tc_ct {
+ tc_gen;
+};
+
+#endif /* __UAPI_TC_CT_H */
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 360fdd3..ff90a71 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -929,6 +929,17 @@ config NET_ACT_TUNNEL_KEY
To compile this code as a module, choose M here: the
module will be called act_tunnel_key.
+config NET_ACT_CT
+ tristate "connection tracking tc action"
+ depends on NET_CLS_ACT && NF_CONNTRACK
+ help
+ Say Y here to allow sending the packets to conntrack module.
+
+ If unsure, say N.
+
+ To compile this code as a module, choose M here: the
+ module will be called act_ct.
+
config NET_IFE_SKBMARK
tristate "Support to encoding decoding skb mark on IFE action"
depends on NET_ACT_IFE
diff --git a/net/sched/Makefile b/net/sched/Makefile
index d54bfcb..23d2202 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o
obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o
obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o
obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o
+obj-$(CONFIG_NET_ACT_CT) += act_ct.o
obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o
obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o
obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
new file mode 100644
index 0000000..9b9f8a7
--- /dev/null
+++ b/net/sched/act_ct.c
@@ -0,0 +1,979 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* -
+ * net/sched/act_ct.c Connection Tracking action
+ *
+ * Authors: Paul Blakey <paulb@mellanox.com>
+ * Yossi Kuperman <yossiku@mellanox.com>
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_cls.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/act_api.h>
+#include <net/ip.h>
+#include <net/ipv6_frag.h>
+#include <uapi/linux/tc_act/tc_ct.h>
+#include <net/tc_act/tc_ct.h>
+
+#include <linux/netfilter/nf_nat.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+
+static struct tc_action_ops act_ct_ops;
+static unsigned int ct_net_id;
+
+struct tc_ct_action_net {
+ struct tc_action_net tn; /* Must be first */
+ bool labels;
+};
+
+/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
+static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
+ u16 zone_id, bool force)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return false;
+ if (!net_eq(net, read_pnet(&ct->ct_net)))
+ return false;
+ if (nf_ct_zone(ct)->id != zone_id)
+ return false;
+
+ /* Force conntrack entry direction. */
+ if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
+ nf_conntrack_put(&ct->ct_general);
+ nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+
+ if (nf_ct_is_confirmed(ct))
+ nf_ct_kill(ct);
+
+ return false;
+ }
+
+ return true;
+}
+
+/* Trim the skb to the length specified by the IP/IPv6 header,
+ * removing any trailing lower-layer padding. This prepares the skb
+ * for higher-layer processing that assumes skb->len excludes padding
+ * (such as nf_ip_checksum). The caller needs to pull the skb to the
+ * network header, and ensure ip_hdr/ipv6_hdr points to valid data.
+ */
+static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)
+{
+ unsigned int len;
+ int err;
+
+ switch (family) {
+ case NFPROTO_IPV4:
+ len = ntohs(ip_hdr(skb)->tot_len);
+ break;
+ case NFPROTO_IPV6:
+ len = sizeof(struct ipv6hdr)
+ + ntohs(ipv6_hdr(skb)->payload_len);
+ break;
+ default:
+ len = skb->len;
+ }
+
+ err = pskb_trim_rcsum(skb, len);
+
+ return err;
+}
+
+static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
+{
+ u8 family = NFPROTO_UNSPEC;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ family = NFPROTO_IPV4;
+ break;
+ case htons(ETH_P_IPV6):
+ family = NFPROTO_IPV6;
+ break;
+ default:
+ break;
+ }
+
+ return family;
+}
+
+static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag)
+{
+ unsigned int len;
+
+ len = skb_network_offset(skb) + sizeof(struct iphdr);
+ if (unlikely(skb->len < len))
+ return -EINVAL;
+ if (unlikely(!pskb_may_pull(skb, len)))
+ return -ENOMEM;
+
+ *frag = ip_is_fragment(ip_hdr(skb));
+ return 0;
+}
+
+static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
+{
+ unsigned int flags = 0, len, payload_ofs = 0;
+ unsigned short frag_off;
+ int nexthdr;
+
+ len = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+ if (unlikely(skb->len < len))
+ return -EINVAL;
+ if (unlikely(!pskb_may_pull(skb, len)))
+ return -ENOMEM;
+
+ nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags);
+ if (unlikely(nexthdr < 0))
+ return -EPROTO;
+
+ *frag = flags & IP6_FH_F_FRAG;
+ return 0;
+}
+
+static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
+ u8 family, u16 zone)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+ int err = 0;
+ bool frag;
+
+ /* Previously seen (loopback)? Ignore. */
+ ct = nf_ct_get(skb, &ctinfo);
+ if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
+ return 0;
+
+ if (family == NFPROTO_IPV4)
+ err = tcf_ct_ipv4_is_fragment(skb, &frag);
+ else
+ err = tcf_ct_ipv6_is_fragment(skb, &frag);
+ if (err || !frag)
+ return err;
+
+ skb_get(skb);
+
+ if (family == NFPROTO_IPV4) {
+ enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
+
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ local_bh_disable();
+ err = ip_defrag(net, skb, user);
+ local_bh_enable();
+ if (err && err != -EINPROGRESS)
+ goto out_free;
+ } else { /* NFPROTO_IPV6 */
+ enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
+
+ memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
+ err = nf_ct_frag6_gather(net, skb, user);
+ if (err && err != -EINPROGRESS)
+ goto out_free;
+ }
+
+ skb_clear_hash(skb);
+ skb->ignore_df = 1;
+ return err;
+
+out_free:
+ kfree_skb(skb);
+ return err;
+}
+
+static void tcf_ct_params_free(struct rcu_head *head)
+{
+ struct tcf_ct_params *params = container_of(head,
+ struct tcf_ct_params, rcu);
+
+ if (params->tmpl)
+ nf_conntrack_put(¶ms->tmpl->ct_general);
+ kfree(params);
+}
+
+#if IS_ENABLED(CONFIG_NF_NAT)
+/* Modelled after nf_nat_ipv[46]_fn().
+ * range is only used for new, uninitialized NAT state.
+ * Returns either NF_ACCEPT or NF_DROP.
+ */
+static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo,
+ const struct nf_nat_range2 *range,
+ enum nf_nat_manip_type maniptype)
+{
+ int hooknum, err = NF_ACCEPT;
+
+ /* See HOOK2MANIP(). */
+ if (maniptype == NF_NAT_MANIP_SRC)
+ hooknum = NF_INET_LOCAL_IN; /* Source NAT */
+ else
+ hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
+
+ switch (ctinfo) {
+ case IP_CT_RELATED:
+ case IP_CT_RELATED_REPLY:
+ if (skb->protocol == htons(ETH_P_IP) &&
+ ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+ if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+ hooknum))
+ err = NF_DROP;
+ goto out;
+ } else if (IS_ENABLED(CONFIG_IPV6) &&
+ skb->protocol == htons(ETH_P_IPV6)) {
+ __be16 frag_off;
+ u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+ int hdrlen = ipv6_skip_exthdr(skb,
+ sizeof(struct ipv6hdr),
+ &nexthdr, &frag_off);
+
+ if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+ if (!nf_nat_icmpv6_reply_translation(skb, ct,
+ ctinfo,
+ hooknum,
+ hdrlen))
+ err = NF_DROP;
+ goto out;
+ }
+ }
+ /* Non-ICMP, fall thru to initialize if needed. */
+ /* fall through */
+ case IP_CT_NEW:
+ /* Seen it before? This can happen for loopback, retrans,
+ * or local packets.
+ */
+ if (!nf_nat_initialized(ct, maniptype)) {
+ /* Initialize according to the NAT action. */
+ err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
+ /* Action is set up to establish a new
+ * mapping.
+ */
+ ? nf_nat_setup_info(ct, range, maniptype)
+ : nf_nat_alloc_null_binding(ct, hooknum);
+ if (err != NF_ACCEPT)
+ goto out;
+ }
+ break;
+
+ case IP_CT_ESTABLISHED:
+ case IP_CT_ESTABLISHED_REPLY:
+ break;
+
+ default:
+ err = NF_DROP;
+ goto out;
+ }
+
+ err = nf_nat_packet(ct, ctinfo, hooknum, skb);
+out:
+ return err;
+}
+#endif /* CONFIG_NF_NAT */
+
+static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
+ u32 new_mark;
+
+ if (!mask)
+ return;
+
+ new_mark = mark | (ct->mark & ~(mask));
+ if (ct->mark != new_mark) {
+ ct->mark = new_mark;
+ if (nf_ct_is_confirmed(ct))
+ nf_conntrack_event_cache(IPCT_MARK, ct);
+ }
+#endif
+}
+
+static void tcf_ct_act_set_labels(struct nf_conn *ct,
+ u32 *labels,
+ u32 *labels_m)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)
+ size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels);
+
+ if (!memchr_inv(labels_m, 0, labels_sz))
+ return;
+
+ nf_connlabels_replace(ct, labels, labels_m, 4);
+#endif
+}
+
+static int tcf_ct_act_nat(struct sk_buff *skb,
+ struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo,
+ int ct_action,
+ struct nf_nat_range2 *range,
+ bool commit)
+{
+#if IS_ENABLED(CONFIG_NF_NAT)
+ enum nf_nat_manip_type maniptype;
+
+ if (!(ct_action & TCA_CT_ACT_NAT))
+ return NF_ACCEPT;
+
+ /* Add NAT extension if not confirmed yet. */
+ if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
+ return NF_DROP; /* Can't NAT. */
+
+ if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&
+ (ctinfo != IP_CT_RELATED || commit)) {
+ /* NAT an established or related connection like before. */
+ if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
+ /* This is the REPLY direction for a connection
+ * for which NAT was applied in the forward
+ * direction. Do the reverse NAT.
+ */
+ maniptype = ct->status & IPS_SRC_NAT
+ ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
+ else
+ maniptype = ct->status & IPS_SRC_NAT
+ ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
+ } else if (ct_action & TCA_CT_ACT_NAT_SRC) {
+ maniptype = NF_NAT_MANIP_SRC;
+ } else if (ct_action & TCA_CT_ACT_NAT_DST) {
+ maniptype = NF_NAT_MANIP_DST;
+ } else {
+ return NF_ACCEPT;
+ }
+
+ return ct_nat_execute(skb, ct, ctinfo, range, maniptype);
+#else
+ return NF_ACCEPT;
+#endif
+}
+
+static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
+ struct tcf_result *res)
+{
+ struct net *net = dev_net(skb->dev);
+ bool cached, commit, clear, force;
+ enum ip_conntrack_info ctinfo;
+ struct tcf_ct *c = to_ct(a);
+ struct nf_conn *tmpl = NULL;
+ struct nf_hook_state state;
+ int nh_ofs, err, retval;
+ struct tcf_ct_params *p;
+ struct nf_conn *ct;
+ u8 family;
+
+ p = rcu_dereference_bh(c->params);
+
+ retval = READ_ONCE(c->tcf_action);
+ commit = p->ct_action & TCA_CT_ACT_COMMIT;
+ clear = p->ct_action & TCA_CT_ACT_CLEAR;
+ force = p->ct_action & TCA_CT_ACT_FORCE;
+ tmpl = p->tmpl;
+
+ if (clear) {
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct) {
+ nf_conntrack_put(&ct->ct_general);
+ nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+ }
+
+ goto out;
+ }
+
+ family = tcf_ct_skb_nf_family(skb);
+ if (family == NFPROTO_UNSPEC)
+ goto drop;
+
+ /* The conntrack module expects to be working at L3.
+ * We also try to pull the IPv4/6 header to linear area
+ */
+ nh_ofs = skb_network_offset(skb);
+ skb_pull_rcsum(skb, nh_ofs);
+ err = tcf_ct_handle_fragments(net, skb, family, p->zone);
+ if (err == -EINPROGRESS) {
+ retval = TC_ACT_STOLEN;
+ goto out;
+ }
+ if (err)
+ goto drop;
+
+ err = tcf_ct_skb_network_trim(skb, family);
+ if (err)
+ goto drop;
+
+ /* If we are recirculating packets to match on ct fields and
+ * committing with a separate ct action, then we don't need to
+ * actually run the packet through conntrack twice unless it's for a
+ * different zone.
+ */
+ cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
+ if (!cached) {
+ /* Associate skb with specified zone. */
+ if (tmpl) {
+ ct = nf_ct_get(skb, &ctinfo);
+ if (skb_nfct(skb))
+ nf_conntrack_put(skb_nfct(skb));
+ nf_conntrack_get(&tmpl->ct_general);
+ nf_ct_set(skb, tmpl, IP_CT_NEW);
+ }
+
+ state.hook = NF_INET_PRE_ROUTING;
+ state.net = net;
+ state.pf = family;
+ err = nf_conntrack_in(skb, &state);
+ if (err != NF_ACCEPT)
+ goto out_push;
+ }
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ goto out_push;
+ nf_ct_deliver_cached_events(ct);
+
+ err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit);
+ if (err != NF_ACCEPT)
+ goto drop;
+
+ if (commit) {
+ tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
+ tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
+
+ /* This will take care of sending queued events
+ * even if the connection is already confirmed.
+ */
+ nf_conntrack_confirm(skb);
+ }
+
+out_push:
+ skb_push_rcsum(skb, nh_ofs);
+
+out:
+ bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb);
+ return retval;
+
+drop:
+ qstats_drop_inc(this_cpu_ptr(a->cpu_qstats));
+ return TC_ACT_SHOT;
+}
+
+static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
+ [TCA_CT_UNSPEC] = { .strict_start_type = TCA_CT_UNSPEC + 1 },
+ [TCA_CT_ACTION] = { .type = NLA_U16 },
+ [TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) },
+ [TCA_CT_ZONE] = { .type = NLA_U16 },
+ [TCA_CT_MARK] = { .type = NLA_U32 },
+ [TCA_CT_MARK_MASK] = { .type = NLA_U32 },
+ [TCA_CT_LABELS] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_CT_LABELS_MASK] = { .type = NLA_BINARY,
+ .len = 128 / BITS_PER_BYTE },
+ [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 },
+ [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 },
+ [TCA_CT_NAT_IPV6_MIN] = { .type = NLA_EXACT_LEN,
+ .len = sizeof(struct in6_addr) },
+ [TCA_CT_NAT_IPV6_MAX] = { .type = NLA_EXACT_LEN,
+ .len = sizeof(struct in6_addr) },
+ [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
+ [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
+};
+
+static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
+ struct tc_ct *parm,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct nf_nat_range2 *range;
+
+ if (!(p->ct_action & TCA_CT_ACT_NAT))
+ return 0;
+
+ if (!IS_ENABLED(CONFIG_NF_NAT)) {
+ NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel");
+ return -EOPNOTSUPP;
+ }
+
+ if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
+ return 0;
+
+ if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
+ (p->ct_action & TCA_CT_ACT_NAT_DST)) {
+ NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
+ return -EOPNOTSUPP;
+ }
+
+ range = &p->range;
+ if (tb[TCA_CT_NAT_IPV4_MIN]) {
+ struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX];
+
+ p->ipv4_range = true;
+ range->flags |= NF_NAT_RANGE_MAP_IPS;
+ range->min_addr.ip =
+ nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]);
+
+ range->max_addr.ip = max_attr ?
+ nla_get_in_addr(max_attr) :
+ range->min_addr.ip;
+ } else if (tb[TCA_CT_NAT_IPV6_MIN]) {
+ struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX];
+
+ p->ipv4_range = false;
+ range->flags |= NF_NAT_RANGE_MAP_IPS;
+ range->min_addr.in6 =
+ nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]);
+
+ range->max_addr.in6 = max_attr ?
+ nla_get_in6_addr(max_attr) :
+ range->min_addr.in6;
+ }
+
+ if (tb[TCA_CT_NAT_PORT_MIN]) {
+ range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+ range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]);
+
+ range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ?
+ nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) :
+ range->min_proto.all;
+ }
+
+ return 0;
+}
+
+static void tcf_ct_set_key_val(struct nlattr **tb,
+ void *val, int val_type,
+ void *mask, int mask_type,
+ int len)
+{
+ if (!tb[val_type])
+ return;
+ nla_memcpy(val, tb[val_type], len);
+
+ if (!mask)
+ return;
+
+ if (mask_type == TCA_CT_UNSPEC || !tb[mask_type])
+ memset(mask, 0xff, len);
+ else
+ nla_memcpy(mask, tb[mask_type], len);
+}
+
+static int tcf_ct_fill_params(struct net *net,
+ struct tcf_ct_params *p,
+ struct tc_ct *parm,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
+ struct nf_conntrack_zone zone;
+ struct nf_conn *tmpl;
+ int err;
+
+ p->zone = NF_CT_DEFAULT_ZONE_ID;
+
+ tcf_ct_set_key_val(tb,
+ &p->ct_action, TCA_CT_ACTION,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->ct_action));
+
+ if (p->ct_action & TCA_CT_ACT_CLEAR)
+ return 0;
+
+ err = tcf_ct_fill_params_nat(p, parm, tb, extack);
+ if (err)
+ return err;
+
+ if (tb[TCA_CT_MARK]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
+ NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled.");
+ return -EOPNOTSUPP;
+ }
+ tcf_ct_set_key_val(tb,
+ &p->mark, TCA_CT_MARK,
+ &p->mark_mask, TCA_CT_MARK_MASK,
+ sizeof(p->mark));
+ }
+
+ if (tb[TCA_CT_LABELS]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
+ NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled.");
+ return -EOPNOTSUPP;
+ }
+
+ if (!tn->labels) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length");
+ return -EOPNOTSUPP;
+ }
+ tcf_ct_set_key_val(tb,
+ p->labels, TCA_CT_LABELS,
+ p->labels_mask, TCA_CT_LABELS_MASK,
+ sizeof(p->labels));
+ }
+
+ if (tb[TCA_CT_ZONE]) {
+ if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
+ NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled.");
+ return -EOPNOTSUPP;
+ }
+
+ tcf_ct_set_key_val(tb,
+ &p->zone, TCA_CT_ZONE,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->zone));
+ }
+
+ if (p->zone == NF_CT_DEFAULT_ZONE_ID)
+ return 0;
+
+ nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0);
+ tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL);
+ if (!tmpl) {
+ NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
+ return -ENOMEM;
+ }
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+ nf_conntrack_get(&tmpl->ct_general);
+ p->tmpl = tmpl;
+
+ return 0;
+}
+
+static int tcf_ct_init(struct net *net, struct nlattr *nla,
+ struct nlattr *est, struct tc_action **a,
+ int replace, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_action_net *tn = net_generic(net, ct_net_id);
+ struct tcf_ct_params *params = NULL;
+ struct nlattr *tb[TCA_CT_MAX + 1];
+ struct tcf_chain *goto_ch = NULL;
+ struct tc_ct *parm;
+ struct tcf_ct *c;
+ int err, res = 0;
+
+ if (!nla) {
+ NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_CT_PARMS]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters");
+ return -EINVAL;
+ }
+ parm = nla_data(tb[TCA_CT_PARMS]);
+
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+
+ if (!err) {
+ err = tcf_idr_create(tn, parm->index, est, a,
+ &act_ct_ops, bind, true);
+ if (err) {
+ tcf_idr_cleanup(tn, parm->index);
+ return err;
+ }
+ res = ACT_P_CREATED;
+ } else {
+ if (bind)
+ return 0;
+
+ if (!replace) {
+ tcf_idr_release(*a, bind);
+ return -EEXIST;
+ }
+ }
+ err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+ if (err < 0)
+ goto cleanup;
+
+ c = to_ct(*a);
+
+ params = kzalloc(sizeof(*params), GFP_KERNEL);
+ if (unlikely(!params)) {
+ err = -ENOMEM;
+ goto cleanup;
+ }
+
+ err = tcf_ct_fill_params(net, params, parm, tb, extack);
+ if (err)
+ goto cleanup;
+
+ spin_lock_bh(&c->tcf_lock);
+ goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+ rcu_swap_protected(c->params, params, lockdep_is_held(&c->tcf_lock));
+ spin_unlock_bh(&c->tcf_lock);
+
+ if (goto_ch)
+ tcf_chain_put_by_act(goto_ch);
+ if (params)
+ kfree_rcu(params, rcu);
+ if (res == ACT_P_CREATED)
+ tcf_idr_insert(tn, *a);
+
+ return res;
+
+cleanup:
+ if (goto_ch)
+ tcf_chain_put_by_act(goto_ch);
+ kfree(params);
+ tcf_idr_release(*a, bind);
+ return err;
+}
+
+static void tcf_ct_cleanup(struct tc_action *a)
+{
+ struct tcf_ct_params *params;
+ struct tcf_ct *c = to_ct(a);
+
+ params = rcu_dereference_protected(c->params, 1);
+ if (params)
+ call_rcu(¶ms->rcu, tcf_ct_params_free);
+}
+
+static int tcf_ct_dump_key_val(struct sk_buff *skb,
+ void *val, int val_type,
+ void *mask, int mask_type,
+ int len)
+{
+ int err;
+
+ if (mask && !memchr_inv(mask, 0, len))
+ return 0;
+
+ err = nla_put(skb, val_type, len, val);
+ if (err)
+ return err;
+
+ if (mask_type != TCA_CT_UNSPEC) {
+ err = nla_put(skb, mask_type, len, mask);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
+{
+ struct nf_nat_range2 *range = &p->range;
+
+ if (!(p->ct_action & TCA_CT_ACT_NAT))
+ return 0;
+
+ if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
+ return 0;
+
+ if (range->flags & NF_NAT_RANGE_MAP_IPS) {
+ if (p->ipv4_range) {
+ if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN,
+ range->min_addr.ip))
+ return -1;
+ if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX,
+ range->max_addr.ip))
+ return -1;
+ } else {
+ if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN,
+ &range->min_addr.in6))
+ return -1;
+ if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX,
+ &range->max_addr.in6))
+ return -1;
+ }
+ }
+
+ if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
+ if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN,
+ range->min_proto.all))
+ return -1;
+ if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX,
+ range->max_proto.all))
+ return -1;
+ }
+
+ return 0;
+}
+
+static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
+ int bind, int ref)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ struct tcf_ct *c = to_ct(a);
+ struct tcf_ct_params *p;
+
+ struct tc_ct opt = {
+ .index = c->tcf_index,
+ .refcnt = refcount_read(&c->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&c->tcf_bindcnt) - bind,
+ };
+ struct tcf_t t;
+
+ spin_lock_bh(&c->tcf_lock);
+ p = rcu_dereference_protected(c->params,
+ lockdep_is_held(&c->tcf_lock));
+ opt.action = c->tcf_action;
+
+ if (tcf_ct_dump_key_val(skb,
+ &p->ct_action, TCA_CT_ACTION,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->ct_action)))
+ goto nla_put_failure;
+
+ if (p->ct_action & TCA_CT_ACT_CLEAR)
+ goto skip_dump;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
+ tcf_ct_dump_key_val(skb,
+ &p->mark, TCA_CT_MARK,
+ &p->mark_mask, TCA_CT_MARK_MASK,
+ sizeof(p->mark)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
+ tcf_ct_dump_key_val(skb,
+ p->labels, TCA_CT_LABELS,
+ p->labels_mask, TCA_CT_LABELS_MASK,
+ sizeof(p->labels)))
+ goto nla_put_failure;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ tcf_ct_dump_key_val(skb,
+ &p->zone, TCA_CT_ZONE,
+ NULL, TCA_CT_UNSPEC,
+ sizeof(p->zone)))
+ goto nla_put_failure;
+
+ if (tcf_ct_dump_nat(skb, p))
+ goto nla_put_failure;
+
+skip_dump:
+ if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ tcf_tm_dump(&t, &c->tcf_tm);
+ if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD))
+ goto nla_put_failure;
+ spin_unlock_bh(&c->tcf_lock);
+
+ return skb->len;
+nla_put_failure:
+ spin_unlock_bh(&c->tcf_lock);
+ nlmsg_trim(skb, b);
+ return -1;
+}
+
+static int tcf_ct_walker(struct net *net, struct sk_buff *skb,
+ struct netlink_callback *cb, int type,
+ const struct tc_action_ops *ops,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_action_net *tn = net_generic(net, ct_net_id);
+
+ return tcf_generic_walker(tn, skb, cb, type, ops, extack);
+}
+
+static int tcf_ct_search(struct net *net, struct tc_action **a, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, ct_net_id);
+
+ return tcf_idr_search(tn, a, index);
+}
+
+static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
+ u64 lastuse, bool hw)
+{
+ struct tcf_ct *c = to_ct(a);
+
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+
+ if (hw)
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+ bytes, packets);
+ c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
+}
+
+static struct tc_action_ops act_ct_ops = {
+ .kind = "ct",
+ .id = TCA_ID_CT,
+ .owner = THIS_MODULE,
+ .act = tcf_ct_act,
+ .dump = tcf_ct_dump,
+ .init = tcf_ct_init,
+ .cleanup = tcf_ct_cleanup,
+ .walk = tcf_ct_walker,
+ .lookup = tcf_ct_search,
+ .stats_update = tcf_stats_update,
+ .size = sizeof(struct tcf_ct),
+};
+
+static __net_init int ct_init_net(struct net *net)
+{
+ unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8;
+ struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
+
+ if (nf_connlabels_get(net, n_bits - 1)) {
+ tn->labels = false;
+ pr_err("act_ct: Failed to set connlabels length");
+ } else {
+ tn->labels = true;
+ }
+
+ return tc_action_net_init(&tn->tn, &act_ct_ops);
+}
+
+static void __net_exit ct_exit_net(struct list_head *net_list)
+{
+ struct net *net;
+
+ rtnl_lock();
+ list_for_each_entry(net, net_list, exit_list) {
+ struct tc_ct_action_net *tn = net_generic(net, ct_net_id);
+
+ if (tn->labels)
+ nf_connlabels_put(net);
+ }
+ rtnl_unlock();
+
+ tc_action_net_exit(net_list, ct_net_id);
+}
+
+static struct pernet_operations ct_net_ops = {
+ .init = ct_init_net,
+ .exit_batch = ct_exit_net,
+ .id = &ct_net_id,
+ .size = sizeof(struct tc_ct_action_net),
+};
+
+static int __init ct_init_module(void)
+{
+ return tcf_register_action(&act_ct_ops, &ct_net_ops);
+}
+
+static void __exit ct_cleanup_module(void)
+{
+ tcf_unregister_action(&act_ct_ops, &ct_net_ops);
+}
+
+module_init(ct_init_module);
+module_exit(ct_cleanup_module);
+MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>");
+MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
+MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
+MODULE_DESCRIPTION("Connection tracking action");
+MODULE_LICENSE("GPL v2");
+
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ad36bbc..4a7331c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -35,6 +35,7 @@
#include <net/tc_act/tc_police.h>
#include <net/tc_act/tc_sample.h>
#include <net/tc_act/tc_skbedit.h>
+#include <net/tc_act/tc_ct.h>
extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
@@ -3266,6 +3267,10 @@ int tc_setup_flow_action(struct flow_action *flow_action,
entry->police.burst = tcf_police_tcfp_burst(act);
entry->police.rate_bytes_ps =
tcf_police_rate_bytes_ps(act);
+ } else if (is_tcf_ct(act)) {
+ entry->id = FLOW_ACTION_CT;
+ entry->ct.action = tcf_ct_action(act);
+ entry->ct.zone = tcf_ct_zone(act);
} else {
goto err_out;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v4 4/4] tc-tests: Add tc action ct tests
From: Paul Blakey @ 2019-07-07 8:03 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit,
Marcelo Ricardo Leitner
In-Reply-To: <1562486612-22770-1-git-send-email-paulb@mellanox.com>
Add 13 tests ensuring the command line is doing what is supposed to do.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
---
.../selftests/tc-testing/tc-tests/actions/ct.json | 314 +++++++++++++++++++++
1 file changed, 314 insertions(+)
create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
new file mode 100644
index 0000000..62b82fe
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
@@ -0,0 +1,314 @@
+[
+ {
+ "id": "696a",
+ "name": "Add simple ct action",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 0 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "9f20",
+ "name": "Add ct clear action",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct clear index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct clear pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "5bea",
+ "name": "Try ct with zone",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 404 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "d5d6",
+ "name": "Try ct with zone, commit",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 commit index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 404 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "029f",
+ "name": "Try ct with zone, commit, mark",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 commit mark 0x42 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit mark 66 zone 404 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "a58d",
+ "name": "Try ct with zone, commit, mark, nat",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct zone 404 commit mark 0x42 nat src addr 5.5.5.7 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit mark 66 zone 404 nat src addr 5.5.5.7 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "901b",
+ "name": "Try ct with full nat ipv4 range syntax",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit nat src addr 5.5.5.7-5.5.6.0 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 0 nat src addr 5.5.5.7-5.5.6.0 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "072b",
+ "name": "Try ct with full nat ipv6 syntax",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit nat src addr 2001::1 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 0 nat src addr 2001::1 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "3420",
+ "name": "Try ct with full nat ipv6 range syntax",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit nat src addr 2001::1-2001::10 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit zone 0 nat src addr 2001::1-2001::10 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "4470",
+ "name": "Try ct with full nat ipv6 range syntax + force",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct commit force nat src addr 2001::1-2001::10 port 1000-2000 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct commit force zone 0 nat src addr 2001::1-2001::10 port 1000-2000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "5d88",
+ "name": "Try ct with label",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct label 123123 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 0 label 12312300000000000000000000000000 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "04d4",
+ "name": "Try ct with label with mask",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct label 12312300000000000000000000000001/ffffffff000000000000000000000001 index 44",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct zone 0 label 12312300000000000000000000000001/ffffffff000000000000000000000001 pipe.*index 44 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ },
+ {
+ "id": "9751",
+ "name": "Try ct with mark + mask",
+ "category": [
+ "actions",
+ "ct"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ct",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ct mark 0x42/0xf0 index 42",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action ct",
+ "matchPattern": "action order [0-9]*: ct mark 66/0xf0 zone 0 pipe.*index 42 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ct"
+ ]
+ }
+]
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v4 0/4] net/sched: Introduce tc connection tracking
From: Paul Blakey @ 2019-07-07 8:03 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
Hi,
This patch series add connection tracking capabilities in tc sw datapath.
It does so via a new tc action, called act_ct, and new tc flower classifier matching
on conntrack state, mark and label.
Usage is as follows:
$ tc qdisc add dev ens1f0_0 ingress
$ tc qdisc add dev ens1f0_1 ingress
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 2
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_state +trk+new \
action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 1 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_0
The pattern used in the design here closely resembles OvS, as the plan is to also offload
OvS conntrack rules to tc. OvS datapath rules uses it's recirculation mechanism to send
specific packets to conntrack, and return with the new conntrack state (ct_state) on some other recirc_id
to be matched again (we use goto chain for this).
This results in the following OvS datapath rules:
recirc_id(0),in_port(ens1f0_0),ct_state(-trk),... actions:ct(zone=2),recirc(2)
recirc_id(2),in_port(ens1f0_0),ct_state(+new+trk),ct_mark(0xbb),... actions:ct(commit,zone=2,nat(src=5.5.5.7),mark=0xbb),ens1f0_1
recirc_id(2),in_port(ens1f0_0),ct_state(+est+trk),ct_mark(0xbb),... actions:ct(zone=2,nat),ens1f0_1
recirc_id(1),in_port(ens1f0_1),ct_state(-trk),... actions:ct(zone=2),recirc(1)
recirc_id(1),in_port(ens1f0_1),ct_state(+est+trk),... actions:ct(zone=2,nat),ens1f0_0
Changelog:
See individual patches.
Paul Blakey (4):
net/sched: Introduce action ct
net/flow_dissector: add connection tracking dissection
net/sched: cls_flower: Add matching on conntrack info
tc-tests: Add tc action ct tests
include/linux/skbuff.h | 10 +
include/net/flow_dissector.h | 15 +
include/net/flow_offload.h | 5 +
include/net/tc_act/tc_ct.h | 64 ++
include/uapi/linux/pkt_cls.h | 17 +
include/uapi/linux/tc_act/tc_ct.h | 41 +
net/core/flow_dissector.c | 44 +
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/act_ct.c | 978 +++++++++++++++++++++
net/sched/cls_api.c | 5 +
net/sched/cls_flower.c | 127 ++-
.../selftests/tc-testing/tc-tests/actions/ct.json | 314 +++++++
13 files changed, 1627 insertions(+), 5 deletions(-)
create mode 100644 include/net/tc_act/tc_ct.h
create mode 100644 include/uapi/linux/tc_act/tc_ct.h
create mode 100644 net/sched/act_ct.c
create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
--
1.8.3.1
^ permalink raw reply
* [PATCH iproute2-next 7/7] devlink: Add man page for devlink-trap
From: Ido Schimmel @ 2019-07-07 8:02 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
man/man8/devlink-monitor.8 | 3 +-
man/man8/devlink-trap.8 | 166 +++++++++++++++++++++++++++++++++++++
man/man8/devlink.8 | 11 ++-
3 files changed, 178 insertions(+), 2 deletions(-)
create mode 100644 man/man8/devlink-trap.8
diff --git a/man/man8/devlink-monitor.8 b/man/man8/devlink-monitor.8
index 13fe641dc8f5..84f0442aa272 100644
--- a/man/man8/devlink-monitor.8
+++ b/man/man8/devlink-monitor.8
@@ -21,7 +21,7 @@ command is the first in the command line and then the object list.
.I OBJECT-LIST
is the list of object types that we want to monitor.
It may contain
-.BR dev ", " port ".
+.BR dev ", " port ", " trap ", " trap-group ", " trap-report .
.B devlink
opens Devlink Netlink socket, listens on it and dumps state changes.
@@ -31,6 +31,7 @@ opens Devlink Netlink socket, listens on it and dumps state changes.
.BR devlink-dev (8),
.BR devlink-sb (8),
.BR devlink-port (8),
+.BR devlink-trap (8),
.br
.SH AUTHOR
diff --git a/man/man8/devlink-trap.8 b/man/man8/devlink-trap.8
new file mode 100644
index 000000000000..8877df484749
--- /dev/null
+++ b/man/man8/devlink-trap.8
@@ -0,0 +1,166 @@
+.TH DEVLINK\-TRAP 8 "11 June 2019" "iproute2" "Linux"
+.SH NAME
+devlink-trap \- devlink trap configuration
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B devlink
+.RI "[ " OPTIONS " ]"
+.B trap
+.RI "{ " COMMAND " |"
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-v\fR[\fIerbose\fR] |
+\fB\-s\fR[\fItatistics\fR] }
+
+.ti -8
+.B "devlink trap show"
+.RI "[ " DEV
+.B trap
+.IR TRAP " ]"
+
+.ti -8
+.BI "devlink trap set " DEV " trap " TRAP
+.RB "[ " report " { " true " | " false " } ]"
+.br
+.RB "[ " action " { " trap " | " drop " } ]"
+
+.ti -8
+.B "devlink trap group show"
+.RI "[ " DEV
+.B group
+.IR GROUP " ]"
+
+.ti -8
+.BI "devlink trap group set " DEV " group " GROUP
+.RB "[ " report " { " true " | " false " } ]"
+.br
+.RB "[ " action " { " trap " | " drop " } ]"
+
+.ti -8
+.B devlink trap help
+
+.SH "DESCRIPTION"
+.SS devlink trap show - display available packet traps and their attributes
+
+.PP
+.I "DEV"
+- specifies the devlink device from which to show packet traps.
+If this argument is omitted all packet traps of all devices are listed.
+
+.PP
+.BI "trap " TRAP
+- specifies the packet trap.
+Only applicable if a devlink device is also specified.
+
+.SS devlink trap set - set attributes of a packet trap
+
+.PP
+.I "DEV"
+- specifies the devlink device the packet trap belongs to.
+
+.PP
+.BI "trap " TRAP
+- specifies the packet trap.
+
+.TP
+.BR report " { " true " | " false " } "
+whether to report trapped packets to user space or not.
+
+.TP
+.BR action " { " trap " | " drop " } "
+packet trap action.
+
+.I trap
+- the sole copy of the packet is sent to the CPU.
+
+.I drop
+- the packet is dropped by the underlying device and a copy is not sent to the CPU.
+
+.SS devlink trap group show - display available packet trap groups and their attributes
+
+.PP
+.I "DEV"
+- specifies the devlink device from which to show packet trap groups.
+If this argument is omitted all packet trap groups of all devices are listed.
+
+.PP
+.BI "group " GROUP
+- specifies the packet trap group.
+Only applicable if a devlink device is also specified.
+
+.SS devlink trap group set - set attributes of a packet trap group
+
+.PP
+.I "DEV"
+- specifies the devlink device the packet trap group belongs to.
+
+.PP
+.BI "group " GROUP
+- specifies the packet trap group.
+
+.TP
+.BR report " { " true " | " false " } "
+whether to report trapped packets from traps member in the trap group to user
+space or not.
+
+.TP
+.BR action " { " trap " | " drop " } "
+packet trap action. The action is set for all the packet traps member in the
+trap group. The actions of non-drop traps cannot be changed and are thus
+skipped.
+
+.SH "EXAMPLES"
+.PP
+devlink trap show
+.RS 4
+List available packet traps.
+.RE
+.PP
+devlink trap group show
+.RS 4
+List available packet trap groups.
+.RE
+.PP
+devlink -vs trap show pci/0000:01:00.0 trap source_mac_is_multicast
+.RS 4
+Show attributes and statistics of a specific packet trap.
+.RE
+.PP
+devlink -s trap group show pci/0000:01:00.0 group l2_drops
+.RS 4
+Show attributes and statistics of a specific packet trap group.
+.RE
+.PP
+devlink trap set pci/0000:01:00.0 trap source_mac_is_multicast action trap
+.RS 4
+Set the action of a specific packet trap to 'trap'.
+.RE
+.PP
+devlink trap set pci/0000:01:00.0 trap source_mac_is_multicast report true
+.RS 4
+Set the report status a specific packet trap to 'true'.
+.RE
+.PP
+devlink trap group set pci/0000:01:00.0 group l2_drops report true
+.RS 4
+Set the report status a specific packet trap group to 'true'.
+.RE
+.PP
+devlink -v monitor trap-report
+.RS 4
+Monitor trapped packets.
+
+.SH SEE ALSO
+.BR devlink (8),
+.BR devlink-dev (8),
+.BR devlink-monitor (8),
+.br
+
+.SH AUTHOR
+Ido Schimmel <idosch@mellanox.com>
diff --git a/man/man8/devlink.8 b/man/man8/devlink.8
index 13d4dcd908b3..12d489440a3d 100644
--- a/man/man8/devlink.8
+++ b/man/man8/devlink.8
@@ -7,7 +7,7 @@ devlink \- Devlink tool
.in +8
.ti -8
.B devlink
-.RI "[ " OPTIONS " ] { " dev | port | monitor | sb | resource | region | health " } { " COMMAND " | "
+.RI "[ " OPTIONS " ] { " dev | port | monitor | sb | resource | region | health | trap " } { " COMMAND " | "
.BR help " }"
.sp
@@ -51,6 +51,10 @@ When combined with -j generate a pretty JSON output.
.BR "\-v" , " --verbose"
Turn on verbose output.
+.TP
+.BR "\-s" , " --statistics"
+Output statistics.
+
.SS
.I OBJECT
@@ -82,6 +86,10 @@ Turn on verbose output.
.B health
- devlink reporting and recovery
+.TP
+.B trap
+- devlink trap configuration
+
.SS
.I COMMAND
@@ -114,6 +122,7 @@ Exit status is 0 if command was successful or a positive integer upon failure.
.BR devlink-resource (8),
.BR devlink-region (8),
.BR devlink-health (8),
+.BR devlink-trap (8),
.br
.SH REPORTING BUGS
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 6/7] devlink: Add fflush() to print functions
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Similar to commit 09e0528cf977 ("ip: mroute: add fflush to
print_mroute"), we need to add fflush() to the print functions to get
the following to work:
# devlink mon &> log
Without it, stdout output is buffered and not written to the disk.
This is useful when writing tests that rely on devlink-monitor output.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
devlink/devlink.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index 817b74259ec3..6fa3be69ff1a 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -58,6 +58,7 @@ static int g_new_line_count;
} \
fprintf(stdout, ##args); \
g_new_line_count = 0; \
+ fflush(stdout); \
} while (0)
#define pr_out_sp(num, args...) \
@@ -66,6 +67,7 @@ static int g_new_line_count;
if (ret < num) \
fprintf(stdout, "%*s", num - ret, ""); \
g_new_line_count = 0; \
+ fflush(stdout); \
} while (0)
static int g_indent_level;
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 5/7] devlink: Set NETLINK_NO_ENOBUFS when monitoring events
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
If we lost an event, there is nothing we can do in order to recover it.
Set above mentioned socket option on the netlink socket when monitoring
devlink events, so that `devlink monitor` will not abort in case we are
not draining the receive buffer fast enough.
The number of events we lost can be retrieved using:
# cat /proc/net/netlink | grep `pidof devlink` | awk '{ print $9 }'
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
devlink/devlink.c | 22 +++++++++++++++++++++-
devlink/mnlg.c | 12 ++++++++++++
devlink/mnlg.h | 2 ++
3 files changed, 35 insertions(+), 1 deletion(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index b9fce850ee00..817b74259ec3 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -140,6 +140,19 @@ static int _mnlg_socket_group_add(struct mnlg_socket *nlg,
return 0;
}
+static int _mnlg_socket_setsockopt(struct mnlg_socket *nlg, int type,
+ void *buf, socklen_t len)
+{
+ int err;
+
+ err = mnlg_socket_setsockopt(nlg, type, buf, len);
+ if (err < 0) {
+ pr_err("Failed to call mnlg_socket_setsockopt\n");
+ return -errno;
+ }
+ return 0;
+}
+
struct ifname_map {
struct list_head list;
char *bus_name;
@@ -4020,7 +4033,7 @@ static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
static int cmd_mon_show(struct dl *dl)
{
- int err;
+ int err, one = 1;
unsigned int index = 0;
const char *cur_obj;
@@ -4035,6 +4048,13 @@ static int cmd_mon_show(struct dl *dl)
return -EINVAL;
}
}
+ /* It is possible to lose some events if we are not draining the socket
+ * receive buffer fast enough. Keep processing events and do not abort.
+ */
+ err = _mnlg_socket_setsockopt(dl->nlg, NETLINK_NO_ENOBUFS, &one,
+ sizeof(one));
+ if (err)
+ return err;
err = _mnlg_socket_group_add(dl->nlg, DEVLINK_GENL_MCGRP_CONFIG_NAME);
if (err)
return err;
diff --git a/devlink/mnlg.c b/devlink/mnlg.c
index ee125df042f0..23e6e794b508 100644
--- a/devlink/mnlg.c
+++ b/devlink/mnlg.c
@@ -231,6 +231,18 @@ int mnlg_socket_group_add(struct mnlg_socket *nlg, const char *group_name)
return 0;
}
+int mnlg_socket_setsockopt(struct mnlg_socket *nlg, int type, void *buf,
+ socklen_t len)
+{
+ int err;
+
+ err = mnl_socket_setsockopt(nlg->nl, type, buf, len);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
static int get_family_id_attr_cb(const struct nlattr *attr, void *data)
{
const struct nlattr **tb = data;
diff --git a/devlink/mnlg.h b/devlink/mnlg.h
index 4d1babf3b4c2..49154215729e 100644
--- a/devlink/mnlg.h
+++ b/devlink/mnlg.h
@@ -21,6 +21,8 @@ struct nlmsghdr *mnlg_msg_prepare(struct mnlg_socket *nlg, uint8_t cmd,
int mnlg_socket_send(struct mnlg_socket *nlg, const struct nlmsghdr *nlh);
int mnlg_socket_recv_run(struct mnlg_socket *nlg, mnl_cb_t data_cb, void *data);
int mnlg_socket_group_add(struct mnlg_socket *nlg, const char *group_name);
+int mnlg_socket_setsockopt(struct mnlg_socket *nlg, int type, void *buf,
+ socklen_t len);
struct mnlg_socket *mnlg_socket_open(const char *family_name, uint8_t version);
void mnlg_socket_close(struct mnlg_socket *nlg);
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 4/7] devlink: Add devlink trap monitor support
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
According to the reporting state of individual traps, a notification is
sent to user space about each trapped packet. Allow the user to monitor
such events by having iproute2 subscribe to the
'DEVLINK_GENL_MCGRP_TRAP_NAME' group. An error is not returned in case
subscription failed in order not to cause regression with old kernels
and new iproute2.
When '-v' is specified trap metadata (e.g., input port) is also shown.
Example:
# devlink -jvp mon trap-report
[trap-report,report]
"netdevsim/netdevsim10": {
"name": "blackhole_route",
"type": "drop",
"group": "l3_drops",
"length": 146,
"timestamp": "Tue May 28 13:03:09 2019 801360651 nsec",
"input_port": {
"netdevsim/netdevsim10/0": {
"type": "eth",
"netdev": "eth0"
}
}
}
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
devlink/devlink.c | 79 +++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 77 insertions(+), 2 deletions(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index ad62b6162f0b..b9fce850ee00 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -3849,6 +3849,7 @@ static const char *cmd_name(uint8_t cmd)
case DEVLINK_CMD_TRAP_GROUP_SET: return "set";
case DEVLINK_CMD_TRAP_GROUP_NEW: return "new";
case DEVLINK_CMD_TRAP_GROUP_DEL: return "del";
+ case DEVLINK_CMD_TRAP_REPORT: return "report";
default: return "<unknown cmd>";
}
}
@@ -3887,6 +3888,8 @@ static const char *cmd_obj(uint8_t cmd)
case DEVLINK_CMD_TRAP_GROUP_NEW:
case DEVLINK_CMD_TRAP_GROUP_DEL:
return "trap-group";
+ case DEVLINK_CMD_TRAP_REPORT:
+ return "trap-report";
default: return "<unknown obj>";
}
}
@@ -3914,6 +3917,7 @@ static bool cmd_filter_check(struct dl *dl, uint8_t cmd)
static void pr_out_region(struct dl *dl, struct nlattr **tb);
static void pr_out_trap(struct dl *dl, struct nlattr **tb, bool array);
static void pr_out_trap_group(struct dl *dl, struct nlattr **tb, bool array);
+static void pr_out_trap_report(struct dl *dl, struct nlattr **tb);
static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
{
@@ -3998,6 +4002,18 @@ static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
pr_out_mon_header(genl->cmd);
pr_out_trap_group(dl, tb, false);
break;
+ case DEVLINK_CMD_TRAP_REPORT:
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_TYPE] ||
+ !tb[DEVLINK_ATTR_TRAP_GROUP_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_PAYLOAD] ||
+ !tb[DEVLINK_ATTR_TRAP_TIMESTAMP])
+ return MNL_CB_ERROR;
+ pr_out_mon_header(genl->cmd);
+ pr_out_trap_report(dl, tb);
+ break;
}
return MNL_CB_OK;
}
@@ -4013,7 +4029,8 @@ static int cmd_mon_show(struct dl *dl)
strcmp(cur_obj, "dev") != 0 &&
strcmp(cur_obj, "port") != 0 &&
strcmp(cur_obj, "trap") != 0 &&
- strcmp(cur_obj, "trap-group") != 0) {
+ strcmp(cur_obj, "trap-group") != 0 &&
+ strcmp(cur_obj, "trap-report") != 0) {
pr_err("Unknown object \"%s\"\n", cur_obj);
return -EINVAL;
}
@@ -4021,6 +4038,10 @@ static int cmd_mon_show(struct dl *dl)
err = _mnlg_socket_group_add(dl->nlg, DEVLINK_GENL_MCGRP_CONFIG_NAME);
if (err)
return err;
+ /* Do not bail in order to be compatible with old kernels that do not
+ * support this multicast group.
+ */
+ mnlg_socket_group_add(dl->nlg, DEVLINK_GENL_MCGRP_TRAP_NAME);
err = _mnlg_socket_recv_run(dl->nlg, cmd_mon_show_cb, dl);
if (err)
return err;
@@ -4030,7 +4051,7 @@ static int cmd_mon_show(struct dl *dl)
static void cmd_mon_help(void)
{
pr_err("Usage: devlink monitor [ all | OBJECT-LIST ]\n"
- "where OBJECT-LIST := { dev | port | trap | trap-group }\n");
+ "where OBJECT-LIST := { dev | port | trap | trap-group | trap-report }\n");
}
static int cmd_mon(struct dl *dl)
@@ -6486,6 +6507,60 @@ static const char *trap_metadata_name(const struct nlattr *attr)
return "<unknown metadata type>";
}
}
+
+static void pr_out_trap_report_timestamp(struct dl *dl,
+ const struct nlattr *attr)
+{
+ struct timespec *ts;
+ struct tm *tm;
+ char buf[80];
+ char *tstr;
+
+ ts = mnl_attr_get_payload(attr);
+ tm = localtime(&ts->tv_sec);
+
+ tstr = asctime(tm);
+ tstr[strlen(tstr) - 1] = 0;
+ snprintf(buf, sizeof(buf), "%s %09ld nsec", tstr, ts->tv_nsec);
+
+ pr_out_str(dl, "timestamp", buf);
+}
+
+static void pr_out_trap_report_port(struct dl *dl, struct nlattr *attr,
+ const char *name, struct nlattr **tb)
+{
+ int err;
+
+ if (!dl->verbose)
+ return;
+
+ err = mnl_attr_parse_nested(attr, attr_cb, tb);
+ if (err != MNL_CB_OK)
+ return;
+
+ pr_out_object_start(dl, name);
+ pr_out_port(dl, tb);
+ pr_out_object_end(dl);
+}
+
+static void pr_out_trap_report(struct dl *dl, struct nlattr **tb)
+{
+ uint8_t type = mnl_attr_get_u8(tb[DEVLINK_ATTR_TRAP_TYPE]);
+
+ __pr_out_handle_start(dl, tb, true, false);
+ pr_out_str(dl, "name", mnl_attr_get_str(tb[DEVLINK_ATTR_TRAP_NAME]));
+ pr_out_str(dl, "type", trap_type_name(type));
+ pr_out_str(dl, "group",
+ mnl_attr_get_str(tb[DEVLINK_ATTR_TRAP_GROUP_NAME]));
+ pr_out_uint(dl, "length",
+ mnl_attr_get_payload_len(tb[DEVLINK_ATTR_TRAP_PAYLOAD]));
+ pr_out_trap_report_timestamp(dl, tb[DEVLINK_ATTR_TRAP_TIMESTAMP]);
+ if (tb[DEVLINK_ATTR_TRAP_IN_PORT])
+ pr_out_trap_report_port(dl, tb[DEVLINK_ATTR_TRAP_IN_PORT],
+ "input_port", tb);
+ pr_out_handle_end(dl);
+}
+
static void pr_out_trap_metadata(struct dl *dl, struct nlattr *attr)
{
struct nlattr *attr_metadata;
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 3/7] devlink: Add devlink trap group set and show commands
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
These commands are similar to the trap set and show commands, but
operate on a trap group and not individual traps. Example:
# devlink trap group set netdevsim/netdevsim10 group l3_drops action trap report true
# devlink -jps trap group show netdevsim/netdevsim10 group l3_drops
{
"trap_group": {
"netdevsim/netdevsim10": [ {
"name": "l3_drops",
"generic": true,
"stats": {
"rx": {
"bytes": 0,
"packets": 0
}
}
} ]
}
}
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
devlink/devlink.c | 136 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 134 insertions(+), 2 deletions(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index 90f41cbd2a9c..ad62b6162f0b 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -214,6 +214,7 @@ static void ifname_map_free(struct ifname_map *ifname_map)
#define DL_OPT_TRAP_NAME BIT(29)
#define DL_OPT_TRAP_REPORT BIT(30)
#define DL_OPT_TRAP_ACTION BIT(31)
+#define DL_OPT_TRAP_GROUP_NAME BIT(32)
struct dl_opts {
uint64_t present; /* flags of present items */
@@ -251,6 +252,7 @@ struct dl_opts {
uint64_t reporter_graceful_period;
bool reporter_auto_recover;
const char *trap_name;
+ const char *trap_group_name;
bool trap_report;
enum devlink_trap_action trap_action;
};
@@ -1075,6 +1077,7 @@ static const struct dl_args_metadata dl_args_required[] = {
{DL_OPT_REGION_LENGTH, "Region length value expected."},
{DL_OPT_HEALTH_REPORTER_NAME, "Reporter's name is expected."},
{DL_OPT_TRAP_NAME, "Trap's name is expected."},
+ {DL_OPT_TRAP_GROUP_NAME, "Trap group's name is expected."},
};
static int dl_args_finding_required_validate(uint64_t o_required,
@@ -1371,6 +1374,13 @@ static int dl_argv_parse(struct dl *dl, uint64_t o_required,
if (err)
return err;
o_found |= DL_OPT_TRAP_NAME;
+ } else if (dl_argv_match(dl, "group") &&
+ (o_all & DL_OPT_TRAP_GROUP_NAME)) {
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &opts->trap_group_name);
+ if (err)
+ return err;
+ o_found |= DL_OPT_TRAP_GROUP_NAME;
} else if (dl_argv_match(dl, "report") &&
(o_all & DL_OPT_TRAP_REPORT)) {
dl_arg_inc(dl);
@@ -1506,6 +1516,9 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
if (opts->present & DL_OPT_TRAP_NAME)
mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME,
opts->trap_name);
+ if (opts->present & DL_OPT_TRAP_GROUP_NAME)
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME,
+ opts->trap_group_name);
if (opts->present & DL_OPT_TRAP_REPORT)
mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_REPORT_ENABLED,
opts->trap_report);
@@ -3832,6 +3845,10 @@ static const char *cmd_name(uint8_t cmd)
case DEVLINK_CMD_TRAP_SET: return "set";
case DEVLINK_CMD_TRAP_NEW: return "new";
case DEVLINK_CMD_TRAP_DEL: return "del";
+ case DEVLINK_CMD_TRAP_GROUP_GET: return "get";
+ case DEVLINK_CMD_TRAP_GROUP_SET: return "set";
+ case DEVLINK_CMD_TRAP_GROUP_NEW: return "new";
+ case DEVLINK_CMD_TRAP_GROUP_DEL: return "del";
default: return "<unknown cmd>";
}
}
@@ -3865,6 +3882,11 @@ static const char *cmd_obj(uint8_t cmd)
case DEVLINK_CMD_TRAP_NEW:
case DEVLINK_CMD_TRAP_DEL:
return "trap";
+ case DEVLINK_CMD_TRAP_GROUP_GET:
+ case DEVLINK_CMD_TRAP_GROUP_SET:
+ case DEVLINK_CMD_TRAP_GROUP_NEW:
+ case DEVLINK_CMD_TRAP_GROUP_DEL:
+ return "trap-group";
default: return "<unknown obj>";
}
}
@@ -3891,6 +3913,7 @@ static bool cmd_filter_check(struct dl *dl, uint8_t cmd)
static void pr_out_region(struct dl *dl, struct nlattr **tb);
static void pr_out_trap(struct dl *dl, struct nlattr **tb, bool array);
+static void pr_out_trap_group(struct dl *dl, struct nlattr **tb, bool array);
static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
{
@@ -3963,6 +3986,18 @@ static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
pr_out_mon_header(genl->cmd);
pr_out_trap(dl, tb, false);
break;
+ case DEVLINK_CMD_TRAP_GROUP_GET: /* fall through */
+ case DEVLINK_CMD_TRAP_GROUP_SET: /* fall through */
+ case DEVLINK_CMD_TRAP_GROUP_NEW: /* fall through */
+ case DEVLINK_CMD_TRAP_GROUP_DEL:
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_GROUP_NAME] ||
+ !tb[DEVLINK_ATTR_STATS])
+ return MNL_CB_ERROR;
+ pr_out_mon_header(genl->cmd);
+ pr_out_trap_group(dl, tb, false);
+ break;
}
return MNL_CB_OK;
}
@@ -3977,7 +4012,8 @@ static int cmd_mon_show(struct dl *dl)
if (strcmp(cur_obj, "all") != 0 &&
strcmp(cur_obj, "dev") != 0 &&
strcmp(cur_obj, "port") != 0 &&
- strcmp(cur_obj, "trap") != 0) {
+ strcmp(cur_obj, "trap") != 0 &&
+ strcmp(cur_obj, "trap-group") != 0) {
pr_err("Unknown object \"%s\"\n", cur_obj);
return -EINVAL;
}
@@ -3994,7 +4030,7 @@ static int cmd_mon_show(struct dl *dl)
static void cmd_mon_help(void)
{
pr_err("Usage: devlink monitor [ all | OBJECT-LIST ]\n"
- "where OBJECT-LIST := { dev | port | trap }\n");
+ "where OBJECT-LIST := { dev | port | trap | trap-group }\n");
}
static int cmd_mon(struct dl *dl)
@@ -6509,6 +6545,9 @@ static void cmd_trap_help(void)
pr_err("Usage: devlink trap set DEV trap TRAP [ report { true | false } ]\n");
pr_err(" [ action { trap | drop } ]\n");
pr_err(" devlink trap show [ DEV trap TRAP ]\n");
+ pr_err(" devlink trap group set DEV group GROUP [ report { true | false } ]\n");
+ pr_err(" [ action { trap | drop } ]\n");
+ pr_err(" devlink trap group show [ DEV group GROUP ]\n");
}
static int cmd_trap_show(struct dl *dl)
@@ -6552,6 +6591,96 @@ static int cmd_trap_set(struct dl *dl)
return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
}
+static void pr_out_trap_group(struct dl *dl, struct nlattr **tb, bool array)
+{
+ if (array)
+ pr_out_handle_start_arr(dl, tb);
+ else
+ __pr_out_handle_start(dl, tb, true, false);
+
+ pr_out_str(dl, "name",
+ mnl_attr_get_str(tb[DEVLINK_ATTR_TRAP_GROUP_NAME]));
+ pr_out_bool(dl, "generic", !!tb[DEVLINK_ATTR_TRAP_GENERIC]);
+ pr_out_stats(dl, tb[DEVLINK_ATTR_STATS]);
+ pr_out_handle_end(dl);
+}
+
+static int cmd_trap_group_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+ struct dl *dl = data;
+
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_GROUP_NAME] || !tb[DEVLINK_ATTR_STATS])
+ return MNL_CB_ERROR;
+
+ pr_out_trap_group(dl, tb, true);
+
+ return MNL_CB_OK;
+}
+
+static int cmd_trap_group_show(struct dl *dl)
+{
+ uint16_t flags = NLM_F_REQUEST | NLM_F_ACK;
+ struct nlmsghdr *nlh;
+ int err;
+
+ if (dl_argc(dl) == 0)
+ flags |= NLM_F_DUMP;
+
+ nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_TRAP_GROUP_GET, flags);
+
+ if (dl_argc(dl) > 0) {
+ err = dl_argv_parse_put(nlh, dl,
+ DL_OPT_HANDLE | DL_OPT_TRAP_GROUP_NAME,
+ 0);
+ if (err)
+ return err;
+ }
+
+ pr_out_section_start(dl, "trap_group");
+ err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_trap_group_show_cb, dl);
+ pr_out_section_end(dl);
+
+ return err;
+}
+
+static int cmd_trap_group_set(struct dl *dl)
+{
+ struct nlmsghdr *nlh;
+ int err;
+
+ nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_TRAP_GROUP_SET,
+ NLM_F_REQUEST | NLM_F_ACK);
+
+ err = dl_argv_parse_put(nlh, dl,
+ DL_OPT_HANDLE | DL_OPT_TRAP_GROUP_NAME,
+ DL_OPT_TRAP_REPORT | DL_OPT_TRAP_ACTION);
+ if (err)
+ return err;
+
+ return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
+static int cmd_trap_group(struct dl *dl)
+{
+ if (dl_argv_match(dl, "help")) {
+ cmd_trap_help();
+ return 0;
+ } else if (dl_argv_match(dl, "show") ||
+ dl_argv_match(dl, "list") || dl_no_arg(dl)) {
+ dl_arg_inc(dl);
+ return cmd_trap_group_show(dl);
+ } else if (dl_argv_match(dl, "set")) {
+ dl_arg_inc(dl);
+ return cmd_trap_group_set(dl);
+ }
+ pr_err("Command \"%s\" not found\n", dl_argv(dl));
+ return -ENOENT;
+}
+
static int cmd_trap(struct dl *dl)
{
if (dl_argv_match(dl, "help")) {
@@ -6564,6 +6693,9 @@ static int cmd_trap(struct dl *dl)
} else if (dl_argv_match(dl, "set")) {
dl_arg_inc(dl);
return cmd_trap_set(dl);
+ } else if (dl_argv_match(dl, "group")) {
+ dl_arg_inc(dl);
+ return cmd_trap_group(dl);
}
pr_err("Command \"%s\" not found\n", dl_argv(dl));
return -ENOENT;
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 2/7] devlink: Add devlink trap set and show commands
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
The trap set command allows the user to set the action and reporting
state of an individual trap. Example:
# devlink trap set netdevsim/netdevsim10 trap blackhole_route action trap report true
The trap show command allows the user to get the current status of an
individual trap or a dump of all traps in case one is not specified.
When '-s' is specified the trap's statistics are shown. When '-v' is
specified the metadata types the trap can provide are shown. Example:
# devlink -jvps trap show netdevsim/netdevsim10 trap blackhole_route
{
"trap": {
"netdevsim/netdevsim10": [ {
"name": "blackhole_route",
"type": "drop",
"generic": true,
"report": true,
"action": "trap",
"group": "l3_drops",
"metadata": [ "input_port" ],
"stats": {
"rx": {
"bytes": 0,
"packets": 0
}
}
} ]
}
}
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
devlink/devlink.c | 313 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 308 insertions(+), 5 deletions(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index f631c8241a24..90f41cbd2a9c 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -211,6 +211,9 @@ static void ifname_map_free(struct ifname_map *ifname_map)
#define DL_OPT_HEALTH_REPORTER_NAME BIT(27)
#define DL_OPT_HEALTH_REPORTER_GRACEFUL_PERIOD BIT(27)
#define DL_OPT_HEALTH_REPORTER_AUTO_RECOVER BIT(28)
+#define DL_OPT_TRAP_NAME BIT(29)
+#define DL_OPT_TRAP_REPORT BIT(30)
+#define DL_OPT_TRAP_ACTION BIT(31)
struct dl_opts {
uint64_t present; /* flags of present items */
@@ -247,6 +250,9 @@ struct dl_opts {
const char *reporter_name;
uint64_t reporter_graceful_period;
bool reporter_auto_recover;
+ const char *trap_name;
+ bool trap_report;
+ enum devlink_trap_action trap_action;
};
struct dl {
@@ -260,6 +266,7 @@ struct dl {
bool json_output;
bool pretty_output;
bool verbose;
+ bool stats;
struct {
bool present;
char *bus_name;
@@ -414,6 +421,22 @@ static const enum mnl_attr_data_type devlink_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT] = MNL_TYPE_U64,
[DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS] = MNL_TYPE_U64,
[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = MNL_TYPE_U64,
+ [DEVLINK_ATTR_STATS] = MNL_TYPE_NESTED,
+ [DEVLINK_ATTR_TRAP_NAME] = MNL_TYPE_STRING,
+ [DEVLINK_ATTR_TRAP_REPORT_ENABLED] = MNL_TYPE_U8,
+ [DEVLINK_ATTR_TRAP_ACTION] = MNL_TYPE_U8,
+ [DEVLINK_ATTR_TRAP_TYPE] = MNL_TYPE_U8,
+ [DEVLINK_ATTR_TRAP_GENERIC] = MNL_TYPE_FLAG,
+ [DEVLINK_ATTR_TRAP_METADATA] = MNL_TYPE_NESTED,
+ [DEVLINK_ATTR_TRAP_TIMESTAMP] = MNL_TYPE_BINARY,
+ [DEVLINK_ATTR_TRAP_IN_PORT] = MNL_TYPE_NESTED,
+ [DEVLINK_ATTR_TRAP_GROUP_NAME] = MNL_TYPE_STRING,
+};
+
+static const enum mnl_attr_data_type
+devlink_stats_policy[DEVLINK_ATTR_STATS_MAX + 1] = {
+ [DEVLINK_ATTR_STATS_RX_PACKETS] = MNL_TYPE_U64,
+ [DEVLINK_ATTR_STATS_RX_BYTES] = MNL_TYPE_U64,
};
static int attr_cb(const struct nlattr *attr, void *data)
@@ -432,6 +455,25 @@ static int attr_cb(const struct nlattr *attr, void *data)
return MNL_CB_OK;
}
+static int attr_stats_cb(const struct nlattr *attr, void *data)
+{
+ const struct nlattr **tb = data;
+ int type;
+
+ /* Allow the tool to work on top of newer kernels that might contain
+ * more attributes.
+ */
+ if (mnl_attr_type_valid(attr, DEVLINK_ATTR_STATS_MAX) < 0)
+ return MNL_CB_OK;
+
+ type = mnl_attr_get_type(attr);
+ if (mnl_attr_validate(attr, devlink_stats_policy[type]) < 0)
+ return MNL_CB_ERROR;
+
+ tb[type] = attr;
+ return MNL_CB_OK;
+}
+
static int ifname_map_cb(const struct nlmsghdr *nlh, void *data)
{
struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
@@ -992,6 +1034,20 @@ static int param_cmode_get(const char *cmodestr,
return 0;
}
+static int trap_action_get(const char *actionstr,
+ enum devlink_trap_action *p_action)
+{
+ if (strcmp(actionstr, "drop") == 0) {
+ *p_action = DEVLINK_TRAP_ACTION_DROP;
+ } else if (strcmp(actionstr, "trap") == 0) {
+ *p_action = DEVLINK_TRAP_ACTION_TRAP;
+ } else {
+ pr_err("Unknown trap action \"%s\"\n", actionstr);
+ return -EINVAL;
+ }
+ return 0;
+}
+
struct dl_args_metadata {
uint64_t o_flag;
char err_msg[DL_ARGS_REQUIRED_MAX_ERR_LEN];
@@ -1018,6 +1074,7 @@ static const struct dl_args_metadata dl_args_required[] = {
{DL_OPT_REGION_ADDRESS, "Region address value expected."},
{DL_OPT_REGION_LENGTH, "Region length value expected."},
{DL_OPT_HEALTH_REPORTER_NAME, "Reporter's name is expected."},
+ {DL_OPT_TRAP_NAME, "Trap's name is expected."},
};
static int dl_args_finding_required_validate(uint64_t o_required,
@@ -1307,6 +1364,32 @@ static int dl_argv_parse(struct dl *dl, uint64_t o_required,
if (err)
return err;
o_found |= DL_OPT_HEALTH_REPORTER_AUTO_RECOVER;
+ } else if (dl_argv_match(dl, "trap") &&
+ (o_all & DL_OPT_TRAP_NAME)) {
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &opts->trap_name);
+ if (err)
+ return err;
+ o_found |= DL_OPT_TRAP_NAME;
+ } else if (dl_argv_match(dl, "report") &&
+ (o_all & DL_OPT_TRAP_REPORT)) {
+ dl_arg_inc(dl);
+ err = dl_argv_bool(dl, &opts->trap_report);
+ if (err)
+ return err;
+ o_found |= DL_OPT_TRAP_REPORT;
+ } else if (dl_argv_match(dl, "action") &&
+ (o_all & DL_OPT_TRAP_ACTION)) {
+ const char *actionstr;
+
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &actionstr);
+ if (err)
+ return err;
+ err = trap_action_get(actionstr, &opts->trap_action);
+ if (err)
+ return err;
+ o_found |= DL_OPT_TRAP_ACTION;
} else {
pr_err("Unknown option \"%s\"\n", dl_argv(dl));
return -EINVAL;
@@ -1420,6 +1503,15 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
if (opts->present & DL_OPT_HEALTH_REPORTER_AUTO_RECOVER)
mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER,
opts->reporter_auto_recover);
+ if (opts->present & DL_OPT_TRAP_NAME)
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME,
+ opts->trap_name);
+ if (opts->present & DL_OPT_TRAP_REPORT)
+ mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_REPORT_ENABLED,
+ opts->trap_report);
+ if (opts->present & DL_OPT_TRAP_ACTION)
+ mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION,
+ opts->trap_action);
}
@@ -1926,6 +2018,30 @@ static void pr_out_entry_end(struct dl *dl)
__pr_out_newline();
}
+static void pr_out_stats(struct dl *dl, struct nlattr *nla_stats)
+{
+ struct nlattr *tb[DEVLINK_ATTR_STATS_MAX + 1] = {};
+ int err;
+
+ if (!dl->stats)
+ return;
+
+ err = mnl_attr_parse_nested(nla_stats, attr_stats_cb, tb);
+ if (err != MNL_CB_OK)
+ return;
+
+ pr_out_object_start(dl, "stats");
+ pr_out_object_start(dl, "rx");
+ if (tb[DEVLINK_ATTR_STATS_RX_BYTES])
+ pr_out_u64(dl, "bytes",
+ mnl_attr_get_u64(tb[DEVLINK_ATTR_STATS_RX_BYTES]));
+ if (tb[DEVLINK_ATTR_STATS_RX_PACKETS])
+ pr_out_u64(dl, "packets",
+ mnl_attr_get_u64(tb[DEVLINK_ATTR_STATS_RX_PACKETS]));
+ pr_out_object_end(dl);
+ pr_out_object_end(dl);
+}
+
static const char *param_cmode_name(uint8_t cmode)
{
switch (cmode) {
@@ -3712,6 +3828,10 @@ static const char *cmd_name(uint8_t cmd)
case DEVLINK_CMD_REGION_SET: return "set";
case DEVLINK_CMD_REGION_NEW: return "new";
case DEVLINK_CMD_REGION_DEL: return "del";
+ case DEVLINK_CMD_TRAP_GET: return "get";
+ case DEVLINK_CMD_TRAP_SET: return "set";
+ case DEVLINK_CMD_TRAP_NEW: return "new";
+ case DEVLINK_CMD_TRAP_DEL: return "del";
default: return "<unknown cmd>";
}
}
@@ -3740,6 +3860,11 @@ static const char *cmd_obj(uint8_t cmd)
case DEVLINK_CMD_REGION_NEW:
case DEVLINK_CMD_REGION_DEL:
return "region";
+ case DEVLINK_CMD_TRAP_GET:
+ case DEVLINK_CMD_TRAP_SET:
+ case DEVLINK_CMD_TRAP_NEW:
+ case DEVLINK_CMD_TRAP_DEL:
+ return "trap";
default: return "<unknown obj>";
}
}
@@ -3765,6 +3890,7 @@ static bool cmd_filter_check(struct dl *dl, uint8_t cmd)
}
static void pr_out_region(struct dl *dl, struct nlattr **tb);
+static void pr_out_trap(struct dl *dl, struct nlattr **tb, bool array);
static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
{
@@ -3820,6 +3946,23 @@ static int cmd_mon_show_cb(const struct nlmsghdr *nlh, void *data)
pr_out_mon_header(genl->cmd);
pr_out_region(dl, tb);
break;
+ case DEVLINK_CMD_TRAP_GET: /* fall through */
+ case DEVLINK_CMD_TRAP_SET: /* fall through */
+ case DEVLINK_CMD_TRAP_NEW: /* fall through */
+ case DEVLINK_CMD_TRAP_DEL:
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_TYPE] ||
+ !tb[DEVLINK_ATTR_TRAP_REPORT_ENABLED] ||
+ !tb[DEVLINK_ATTR_TRAP_ACTION] ||
+ !tb[DEVLINK_ATTR_TRAP_GROUP_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_METADATA] ||
+ !tb[DEVLINK_ATTR_STATS])
+ return MNL_CB_ERROR;
+ pr_out_mon_header(genl->cmd);
+ pr_out_trap(dl, tb, false);
+ break;
}
return MNL_CB_OK;
}
@@ -3833,7 +3976,8 @@ static int cmd_mon_show(struct dl *dl)
while ((cur_obj = dl_argv_index(dl, index++))) {
if (strcmp(cur_obj, "all") != 0 &&
strcmp(cur_obj, "dev") != 0 &&
- strcmp(cur_obj, "port") != 0) {
+ strcmp(cur_obj, "port") != 0 &&
+ strcmp(cur_obj, "trap") != 0) {
pr_err("Unknown object \"%s\"\n", cur_obj);
return -EINVAL;
}
@@ -3850,7 +3994,7 @@ static int cmd_mon_show(struct dl *dl)
static void cmd_mon_help(void)
{
pr_err("Usage: devlink monitor [ all | OBJECT-LIST ]\n"
- "where OBJECT-LIST := { dev | port }\n");
+ "where OBJECT-LIST := { dev | port | trap }\n");
}
static int cmd_mon(struct dl *dl)
@@ -6273,12 +6417,164 @@ static int cmd_health(struct dl *dl)
return -ENOENT;
}
+static const char *trap_type_name(uint8_t type)
+{
+ switch (type) {
+ case DEVLINK_TRAP_TYPE_DROP:
+ return "drop";
+ case DEVLINK_TRAP_TYPE_EXCEPTION:
+ return "exception";
+ default:
+ return "<unknown type>";
+ }
+}
+
+static const char *trap_action_name(uint8_t action)
+{
+ switch (action) {
+ case DEVLINK_TRAP_ACTION_DROP:
+ return "drop";
+ case DEVLINK_TRAP_ACTION_TRAP:
+ return "trap";
+ default:
+ return "<unknown action>";
+ }
+}
+
+static const char *trap_metadata_name(const struct nlattr *attr)
+{
+ switch (attr->nla_type) {
+ case DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT:
+ return "input_port";
+ default:
+ return "<unknown metadata type>";
+ }
+}
+static void pr_out_trap_metadata(struct dl *dl, struct nlattr *attr)
+{
+ struct nlattr *attr_metadata;
+
+ pr_out_array_start(dl, "metadata");
+ mnl_attr_for_each_nested(attr_metadata, attr)
+ pr_out_str_value(dl, trap_metadata_name(attr_metadata));
+ pr_out_array_end(dl);
+}
+
+static void pr_out_trap(struct dl *dl, struct nlattr **tb, bool array)
+{
+ uint8_t action = mnl_attr_get_u8(tb[DEVLINK_ATTR_TRAP_ACTION]);
+ uint8_t type = mnl_attr_get_u8(tb[DEVLINK_ATTR_TRAP_TYPE]);
+
+ if (array)
+ pr_out_handle_start_arr(dl, tb);
+ else
+ __pr_out_handle_start(dl, tb, true, false);
+
+ pr_out_str(dl, "name", mnl_attr_get_str(tb[DEVLINK_ATTR_TRAP_NAME]));
+ pr_out_str(dl, "type", trap_type_name(type));
+ pr_out_bool(dl, "generic", !!tb[DEVLINK_ATTR_TRAP_GENERIC]);
+ pr_out_bool(dl, "report",
+ !!mnl_attr_get_u8(tb[DEVLINK_ATTR_TRAP_REPORT_ENABLED]));
+ pr_out_str(dl, "action", trap_action_name(action));
+ pr_out_str(dl, "group",
+ mnl_attr_get_str(tb[DEVLINK_ATTR_TRAP_GROUP_NAME]));
+ if (dl->verbose)
+ pr_out_trap_metadata(dl, tb[DEVLINK_ATTR_TRAP_METADATA]);
+ pr_out_stats(dl, tb[DEVLINK_ATTR_STATS]);
+ pr_out_handle_end(dl);
+}
+
+static int cmd_trap_show_cb(const struct nlmsghdr *nlh, void *data)
+{
+ struct genlmsghdr *genl = mnl_nlmsg_get_payload(nlh);
+ struct nlattr *tb[DEVLINK_ATTR_MAX + 1] = {};
+ struct dl *dl = data;
+
+ mnl_attr_parse(nlh, sizeof(*genl), attr_cb, tb);
+ if (!tb[DEVLINK_ATTR_BUS_NAME] || !tb[DEVLINK_ATTR_DEV_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_NAME] || !tb[DEVLINK_ATTR_TRAP_TYPE] ||
+ !tb[DEVLINK_ATTR_TRAP_REPORT_ENABLED] ||
+ !tb[DEVLINK_ATTR_TRAP_ACTION] ||
+ !tb[DEVLINK_ATTR_TRAP_GROUP_NAME] ||
+ !tb[DEVLINK_ATTR_TRAP_METADATA] || !tb[DEVLINK_ATTR_STATS])
+ return MNL_CB_ERROR;
+
+ pr_out_trap(dl, tb, true);
+
+ return MNL_CB_OK;
+}
+
+static void cmd_trap_help(void)
+{
+ pr_err("Usage: devlink trap set DEV trap TRAP [ report { true | false } ]\n");
+ pr_err(" [ action { trap | drop } ]\n");
+ pr_err(" devlink trap show [ DEV trap TRAP ]\n");
+}
+
+static int cmd_trap_show(struct dl *dl)
+{
+ uint16_t flags = NLM_F_REQUEST | NLM_F_ACK;
+ struct nlmsghdr *nlh;
+ int err;
+
+ if (dl_argc(dl) == 0)
+ flags |= NLM_F_DUMP;
+
+ nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_TRAP_GET, flags);
+
+ if (dl_argc(dl) > 0) {
+ err = dl_argv_parse_put(nlh, dl,
+ DL_OPT_HANDLE | DL_OPT_TRAP_NAME, 0);
+ if (err)
+ return err;
+ }
+
+ pr_out_section_start(dl, "trap");
+ err = _mnlg_socket_sndrcv(dl->nlg, nlh, cmd_trap_show_cb, dl);
+ pr_out_section_end(dl);
+
+ return err;
+}
+
+static int cmd_trap_set(struct dl *dl)
+{
+ struct nlmsghdr *nlh;
+ int err;
+
+ nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_TRAP_SET,
+ NLM_F_REQUEST | NLM_F_ACK);
+
+ err = dl_argv_parse_put(nlh, dl, DL_OPT_HANDLE | DL_OPT_TRAP_NAME,
+ DL_OPT_TRAP_REPORT | DL_OPT_TRAP_ACTION);
+ if (err)
+ return err;
+
+ return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
+static int cmd_trap(struct dl *dl)
+{
+ if (dl_argv_match(dl, "help")) {
+ cmd_trap_help();
+ return 0;
+ } else if (dl_argv_match(dl, "show") ||
+ dl_argv_match(dl, "list") || dl_no_arg(dl)) {
+ dl_arg_inc(dl);
+ return cmd_trap_show(dl);
+ } else if (dl_argv_match(dl, "set")) {
+ dl_arg_inc(dl);
+ return cmd_trap_set(dl);
+ }
+ pr_err("Command \"%s\" not found\n", dl_argv(dl));
+ return -ENOENT;
+}
+
static void help(void)
{
pr_err("Usage: devlink [ OPTIONS ] OBJECT { COMMAND | help }\n"
" devlink [ -f[orce] ] -b[atch] filename\n"
- "where OBJECT := { dev | port | sb | monitor | dpipe | resource | region | health }\n"
- " OPTIONS := { -V[ersion] | -n[o-nice-names] | -j[son] | -p[retty] | -v[erbose] }\n");
+ "where OBJECT := { dev | port | sb | monitor | dpipe | resource | region | health | trap }\n"
+ " OPTIONS := { -V[ersion] | -n[o-nice-names] | -j[son] | -p[retty] | -v[erbose] -s[tatistics] }\n");
}
static int dl_cmd(struct dl *dl, int argc, char **argv)
@@ -6313,6 +6609,9 @@ static int dl_cmd(struct dl *dl, int argc, char **argv)
} else if (dl_argv_match(dl, "health")) {
dl_arg_inc(dl);
return cmd_health(dl);
+ } else if (dl_argv_match(dl, "trap")) {
+ dl_arg_inc(dl);
+ return cmd_trap(dl);
}
pr_err("Object \"%s\" not found\n", dl_argv(dl));
return -ENOENT;
@@ -6422,6 +6721,7 @@ int main(int argc, char **argv)
{ "json", no_argument, NULL, 'j' },
{ "pretty", no_argument, NULL, 'p' },
{ "verbose", no_argument, NULL, 'v' },
+ { "statistics", no_argument, NULL, 's' },
{ NULL, 0, NULL, 0 }
};
const char *batch_file = NULL;
@@ -6437,7 +6737,7 @@ int main(int argc, char **argv)
return EXIT_FAILURE;
}
- while ((opt = getopt_long(argc, argv, "Vfb:njpv",
+ while ((opt = getopt_long(argc, argv, "Vfb:njpvs",
long_options, NULL)) >= 0) {
switch (opt) {
@@ -6463,6 +6763,9 @@ int main(int argc, char **argv)
case 'v':
dl->verbose = true;
break;
+ case 's':
+ dl->stats = true;
+ break;
default:
pr_err("Unknown option.\n");
help();
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 1/7] devlink: Increase number of supported options
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080200.3699-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Currently, the number of supported options is capped at 32 which is a
problem given we are about to add a few more and go over the limit.
Increase the limit to 64 options.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
devlink/devlink.c | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index 559f624e3666..f631c8241a24 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -213,7 +213,7 @@ static void ifname_map_free(struct ifname_map *ifname_map)
#define DL_OPT_HEALTH_REPORTER_AUTO_RECOVER BIT(28)
struct dl_opts {
- uint32_t present; /* flags of present items */
+ uint64_t present; /* flags of present items */
char *bus_name;
char *dev_name;
uint32_t port_index;
@@ -713,7 +713,7 @@ static int dl_argv_handle_port(struct dl *dl, char **p_bus_name,
static int dl_argv_handle_both(struct dl *dl, char **p_bus_name,
char **p_dev_name, uint32_t *p_port_index,
- uint32_t *p_handle_bit)
+ uint64_t *p_handle_bit)
{
char *str = dl_argv_next(dl);
unsigned int slash_count;
@@ -993,7 +993,7 @@ static int param_cmode_get(const char *cmodestr,
}
struct dl_args_metadata {
- uint32_t o_flag;
+ uint64_t o_flag;
char err_msg[DL_ARGS_REQUIRED_MAX_ERR_LEN];
};
@@ -1020,10 +1020,10 @@ static const struct dl_args_metadata dl_args_required[] = {
{DL_OPT_HEALTH_REPORTER_NAME, "Reporter's name is expected."},
};
-static int dl_args_finding_required_validate(uint32_t o_required,
- uint32_t o_found)
+static int dl_args_finding_required_validate(uint64_t o_required,
+ uint64_t o_found)
{
- uint32_t o_flag;
+ uint64_t o_flag;
int i;
for (i = 0; i < ARRAY_SIZE(dl_args_required); i++) {
@@ -1036,16 +1036,16 @@ static int dl_args_finding_required_validate(uint32_t o_required,
return 0;
}
-static int dl_argv_parse(struct dl *dl, uint32_t o_required,
- uint32_t o_optional)
+static int dl_argv_parse(struct dl *dl, uint64_t o_required,
+ uint64_t o_optional)
{
struct dl_opts *opts = &dl->opts;
- uint32_t o_all = o_required | o_optional;
- uint32_t o_found = 0;
+ uint64_t o_all = o_required | o_optional;
+ uint64_t o_found = 0;
int err;
if (o_required & DL_OPT_HANDLE && o_required & DL_OPT_HANDLEP) {
- uint32_t handle_bit;
+ uint64_t handle_bit;
err = dl_argv_handle_both(dl, &opts->bus_name, &opts->dev_name,
&opts->port_index, &handle_bit);
@@ -1424,7 +1424,7 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
}
static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
- uint32_t o_required, uint32_t o_optional)
+ uint64_t o_required, uint64_t o_optional)
{
int err;
--
2.20.1
^ permalink raw reply related
* [PATCH iproute2-next 0/7] Add devlink-trap support
From: Ido Schimmel @ 2019-07-07 8:01 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
This patchset adds devlink-trap support in iproute2.
Patch #1 increases the number of options devlink can handle.
Patches #2-#4 gradually add support for all devlink-trap commands.
Patches #5-#6 perform small tweaks in devlink code.
Patch #7 adds a man page for devlink-trap.
See individual commit messages for example usage and output.
Ido Schimmel (7):
devlink: Increase number of supported options
devlink: Add devlink trap set and show commands
devlink: Add devlink trap group set and show commands
devlink: Add devlink trap monitor support
devlink: Set NETLINK_NO_ENOBUFS when monitoring events
devlink: Add fflush() to print functions
devlink: Add man page for devlink-trap
devlink/devlink.c | 568 +++++++++++++++++++++++++++++++++++--
devlink/mnlg.c | 12 +
devlink/mnlg.h | 2 +
man/man8/devlink-monitor.8 | 3 +-
man/man8/devlink-trap.8 | 166 +++++++++++
man/man8/devlink.8 | 11 +-
6 files changed, 742 insertions(+), 20 deletions(-)
create mode 100644 man/man8/devlink-trap.8
--
2.20.1
^ permalink raw reply
* [PATCH net-next 11/11] mlxsw: spectrum: Add devlink-trap support
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Register supported packet traps (layer 2 drops only, currently) and
associated trap group with devlink during driver initialization. The
code is placed in a new file (spectrum_trap.c) to which the existing
packet traps will be moved to once they are exposed via devlink.
The amount of traffic generated by these packet drop traps is capped at
700Kpps to ensure the CPU is not overwhelmed by incoming packets.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/Makefile | 2 +-
drivers/net/ethernet/mellanox/mlxsw/core.c | 52 ++++
drivers/net/ethernet/mellanox/mlxsw/core.h | 9 +
.../net/ethernet/mellanox/mlxsw/spectrum.c | 17 ++
.../net/ethernet/mellanox/mlxsw/spectrum.h | 13 +
.../ethernet/mellanox/mlxsw/spectrum_trap.c | 270 ++++++++++++++++++
6 files changed, 362 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 171b36bd8a4e..0e86a581d45b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -29,7 +29,7 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \
spectrum_mr_tcam.o spectrum_mr.o \
spectrum_qdisc.o spectrum_span.o \
spectrum_nve.o spectrum_nve_vxlan.o \
- spectrum_dpipe.o
+ spectrum_dpipe.o spectrum_trap.o
mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o
mlxsw_spectrum-$(CONFIG_PTP_1588_CLOCK) += spectrum_ptp.o
obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 6ec07ecfb5f6..963a2b4b61b1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1017,6 +1017,54 @@ static int mlxsw_devlink_flash_update(struct devlink *devlink,
component, extack);
}
+static int mlxsw_devlink_trap_init(struct devlink *devlink,
+ const struct devlink_trap *trap,
+ void *trap_ctx)
+{
+ struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+ struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+ if (!mlxsw_driver->trap_init)
+ return -EOPNOTSUPP;
+ return mlxsw_driver->trap_init(mlxsw_core, trap, trap_ctx);
+}
+
+static void mlxsw_devlink_trap_fini(struct devlink *devlink,
+ const struct devlink_trap *trap,
+ void *trap_ctx)
+{
+ struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+ struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+ if (!mlxsw_driver->trap_fini)
+ return;
+ mlxsw_driver->trap_fini(mlxsw_core, trap, trap_ctx);
+}
+
+static int mlxsw_devlink_trap_action_set(struct devlink *devlink,
+ const struct devlink_trap *trap,
+ enum devlink_trap_action action)
+{
+ struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+ struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+ if (!mlxsw_driver->trap_action_set)
+ return -EOPNOTSUPP;
+ return mlxsw_driver->trap_action_set(mlxsw_core, trap, action);
+}
+
+static int
+mlxsw_devlink_trap_group_init(struct devlink *devlink,
+ const struct devlink_trap_group *group)
+{
+ struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+ struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+ if (!mlxsw_driver->trap_group_init)
+ return -EOPNOTSUPP;
+ return mlxsw_driver->trap_group_init(mlxsw_core, group);
+}
+
static const struct devlink_ops mlxsw_devlink_ops = {
.reload = mlxsw_devlink_core_bus_device_reload,
.port_type_set = mlxsw_devlink_port_type_set,
@@ -1034,6 +1082,10 @@ static const struct devlink_ops mlxsw_devlink_ops = {
.sb_occ_tc_port_bind_get = mlxsw_devlink_sb_occ_tc_port_bind_get,
.info_get = mlxsw_devlink_info_get,
.flash_update = mlxsw_devlink_flash_update,
+ .trap_init = mlxsw_devlink_trap_init,
+ .trap_fini = mlxsw_devlink_trap_fini,
+ .trap_action_set = mlxsw_devlink_trap_action_set,
+ .trap_group_init = mlxsw_devlink_trap_group_init,
};
static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 19cea16c30bb..b65a17d49e43 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -292,6 +292,15 @@ struct mlxsw_driver {
int (*flash_update)(struct mlxsw_core *mlxsw_core,
const char *file_name, const char *component,
struct netlink_ext_ack *extack);
+ int (*trap_init)(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap, void *trap_ctx);
+ void (*trap_fini)(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap, void *trap_ctx);
+ int (*trap_action_set)(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap,
+ enum devlink_trap_action action);
+ int (*trap_group_init)(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap_group *group);
void (*txhdr_construct)(struct sk_buff *skb,
const struct mlxsw_tx_info *tx_info);
int (*resources_register)(struct mlxsw_core *mlxsw_core);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ce285fbeebd3..c7e1c32b8af2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4635,6 +4635,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
goto err_traps_init;
}
+ err = mlxsw_sp_devlink_traps_init(mlxsw_sp);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize devlink traps\n");
+ goto err_devlink_traps_init;
+ }
+
err = mlxsw_sp_buffers_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize buffers\n");
@@ -4768,6 +4774,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
err_lag_init:
mlxsw_sp_buffers_fini(mlxsw_sp);
err_buffers_init:
+ mlxsw_sp_devlink_traps_fini(mlxsw_sp);
+err_devlink_traps_init:
mlxsw_sp_traps_fini(mlxsw_sp);
err_traps_init:
mlxsw_sp_fids_fini(mlxsw_sp);
@@ -4840,6 +4848,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_lag_fini(mlxsw_sp);
mlxsw_sp_buffers_fini(mlxsw_sp);
+ mlxsw_sp_devlink_traps_fini(mlxsw_sp);
mlxsw_sp_traps_fini(mlxsw_sp);
mlxsw_sp_fids_fini(mlxsw_sp);
mlxsw_sp_kvdl_fini(mlxsw_sp);
@@ -5201,6 +5210,10 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
.sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get,
.sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get,
.flash_update = mlxsw_sp_flash_update,
+ .trap_init = mlxsw_sp_trap_init,
+ .trap_fini = mlxsw_sp_trap_fini,
+ .trap_action_set = mlxsw_sp_trap_action_set,
+ .trap_group_init = mlxsw_sp_trap_group_init,
.txhdr_construct = mlxsw_sp_txhdr_construct,
.resources_register = mlxsw_sp1_resources_register,
.kvd_sizes_get = mlxsw_sp_kvd_sizes_get,
@@ -5231,6 +5244,10 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
.sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get,
.sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get,
.flash_update = mlxsw_sp_flash_update,
+ .trap_init = mlxsw_sp_trap_init,
+ .trap_fini = mlxsw_sp_trap_fini,
+ .trap_action_set = mlxsw_sp_trap_action_set,
+ .trap_group_init = mlxsw_sp_trap_group_init,
.txhdr_construct = mlxsw_sp_txhdr_construct,
.resources_register = mlxsw_sp2_resources_register,
.params_register = mlxsw_sp2_params_register,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index abbb563db440..d0f96fa7cf9d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -950,4 +950,17 @@ void mlxsw_sp_port_nve_fini(struct mlxsw_sp_port *mlxsw_sp_port);
int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp);
+/* spectrum_trap.c */
+int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap, void *trap_ctx);
+void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap, void *trap_ctx);
+int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap,
+ enum devlink_trap_action action);
+int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap_group *group);
+
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
new file mode 100644
index 000000000000..bf9f74838577
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -0,0 +1,270 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <net/devlink.h>
+#include <uapi/linux/devlink.h>
+
+#include "core.h"
+#include "reg.h"
+#include "spectrum.h"
+
+#define MLXSW_SP_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT
+
+static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port,
+ void *priv);
+
+#define MLXSW_SP_TRAP_DROP(_id, _group_id) \
+ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \
+ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
+ MLXSW_SP_TRAP_METADATA)
+
+#define MLXSW_SP_RXL_DISCARD(_id, _group_id) \
+ MLXSW_RXL(mlxsw_sp_rx_drop_listener, DISCARD_##_id, DISCARD, false, \
+ SP_##_group_id, DISCARD)
+
+static struct devlink_trap mlxsw_sp_traps_arr[] = {
+ MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS),
+ MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS),
+ MLXSW_SP_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS),
+ MLXSW_SP_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS),
+ MLXSW_SP_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS),
+ MLXSW_SP_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS),
+};
+
+static struct mlxsw_listener mlxsw_sp_listeners_arr[] = {
+ MLXSW_SP_RXL_DISCARD(ING_PACKET_SMAC_MC, L2_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(ING_SWITCH_VTAG_ALLOW, L2_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(ING_SWITCH_VLAN, L2_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(ING_SWITCH_STP, L2_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_UC, L2_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_MC_NULL, L2_DISCARDS),
+ MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_LB, L2_DISCARDS),
+};
+
+/* Mapping between hardware trap and devlink trap. Multiple hardware traps can
+ * be mapped to the same devlink trap. Order is according to
+ * 'mlxsw_sp_listeners_arr'.
+ */
+static u16 mlxsw_sp_listener_devlink_map[] = {
+ DEVLINK_TRAP_GENERIC_ID_SMAC_MC,
+ DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH,
+ DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER,
+ DEVLINK_TRAP_GENERIC_ID_INGRESS_STP_FILTER,
+ DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST,
+ DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST,
+ DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER,
+};
+
+static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+ u8 local_port,
+ struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ struct mlxsw_sp_port_pcpu_stats *pcpu_stats;
+
+ if (unlikely(!mlxsw_sp_port)) {
+ dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n",
+ local_port);
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ skb->dev = mlxsw_sp_port->dev;
+
+ pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats);
+ u64_stats_update_begin(&pcpu_stats->syncp);
+ pcpu_stats->rx_packets++;
+ pcpu_stats->rx_bytes += skb->len;
+ u64_stats_update_end(&pcpu_stats->syncp);
+
+ return 0;
+}
+
+static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port,
+ void *trap_ctx)
+{
+ struct devlink_port *in_devlink_port;
+ struct mlxsw_sp_port *mlxsw_sp_port;
+ struct mlxsw_sp *mlxsw_sp;
+ struct devlink *devlink;
+
+ mlxsw_sp = devlink_trap_ctx_priv(trap_ctx);
+ mlxsw_sp_port = mlxsw_sp->ports[local_port];
+
+ if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port))
+ return;
+
+ devlink = priv_to_devlink(mlxsw_sp->core);
+ in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core,
+ local_port);
+ devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port);
+ consume_skb(skb);
+}
+
+int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+ if (WARN_ON(ARRAY_SIZE(mlxsw_sp_listener_devlink_map) !=
+ ARRAY_SIZE(mlxsw_sp_listeners_arr)))
+ return -EINVAL;
+
+ return devlink_traps_register(devlink, mlxsw_sp_traps_arr,
+ ARRAY_SIZE(mlxsw_sp_traps_arr),
+ mlxsw_sp);
+}
+
+void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+ devlink_traps_unregister(devlink, mlxsw_sp_traps_arr,
+ ARRAY_SIZE(mlxsw_sp_traps_arr));
+}
+
+int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap, void *trap_ctx)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) {
+ struct mlxsw_listener *listener;
+ int err;
+
+ if (mlxsw_sp_listener_devlink_map[i] != trap->id)
+ continue;
+ listener = &mlxsw_sp_listeners_arr[i];
+
+ err = mlxsw_core_trap_register(mlxsw_core, listener, trap_ctx);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap, void *trap_ctx)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) {
+ struct mlxsw_listener *listener;
+
+ if (mlxsw_sp_listener_devlink_map[i] != trap->id)
+ continue;
+ listener = &mlxsw_sp_listeners_arr[i];
+
+ mlxsw_core_trap_unregister(mlxsw_core, listener, trap_ctx);
+ }
+}
+
+int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap *trap,
+ enum devlink_trap_action action)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) {
+ enum mlxsw_reg_hpkt_action hw_action;
+ struct mlxsw_listener *listener;
+ int err;
+
+ if (mlxsw_sp_listener_devlink_map[i] != trap->id)
+ continue;
+ listener = &mlxsw_sp_listeners_arr[i];
+
+ switch (action) {
+ case DEVLINK_TRAP_ACTION_DROP:
+ hw_action = MLXSW_REG_HPKT_ACTION_DISCARD;
+ break;
+ case DEVLINK_TRAP_ACTION_TRAP:
+ /* Drop traps need to use TRAP_EXCEPTION, so that an
+ * error is counted.
+ */
+ hw_action = MLXSW_REG_HPKT_ACTION_TRAP_EXCEPTION_TO_CPU;
+ if (trap->type != DEVLINK_TRAP_TYPE_DROP)
+ hw_action = MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ err = mlxsw_core_trap_action_set(mlxsw_core, listener,
+ hw_action);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+#define MLXSW_SP_DISCARD_POLICER_ID (MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1)
+
+static int
+mlxsw_sp_trap_group_policer_init(struct mlxsw_sp *mlxsw_sp,
+ const struct devlink_trap_group *group)
+{
+ enum mlxsw_reg_qpcr_ir_units ir_units;
+ char qpcr_pl[MLXSW_REG_QPCR_LEN];
+ u16 policer_id;
+ u8 burst_size;
+ bool is_bytes;
+ u32 rate;
+
+ switch (group->id) {
+ case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS:
+ policer_id = MLXSW_SP_DISCARD_POLICER_ID;
+ ir_units = MLXSW_REG_QPCR_IR_UNITS_M;
+ is_bytes = false;
+ rate = 700 * 1024; /* 700Kpps */
+ burst_size = 7;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ mlxsw_reg_qpcr_pack(qpcr_pl, policer_id, ir_units, is_bytes, rate,
+ burst_size);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl);
+}
+
+static int
+__mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp,
+ const struct devlink_trap_group *group)
+{
+ char htgt_pl[MLXSW_REG_HTGT_LEN];
+ u8 priority, tc, group_id;
+ u16 policer_id;
+
+ switch (group->id) {
+ case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS:
+ group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS;
+ policer_id = MLXSW_SP_DISCARD_POLICER_ID;
+ priority = 0;
+ tc = 1;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ mlxsw_reg_htgt_pack(htgt_pl, group_id, policer_id, priority, tc);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl);
+}
+
+int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core,
+ const struct devlink_trap_group *group)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+ int err;
+
+ err = mlxsw_sp_trap_group_policer_init(mlxsw_sp, group);
+ if (err)
+ return err;
+
+ err = __mlxsw_sp_trap_group_init(mlxsw_sp, group);
+ if (err)
+ return err;
+
+ return 0;
+}
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 10/11] mlxsw: Add trap group for layer 2 discards
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Discard trap groups are defined in a different enum so that they could
all share the same policer ID: MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 55211218ec1a..22138d15079f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5422,6 +5422,14 @@ enum mlxsw_reg_htgt_trap_group {
MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
+
+ __MLXSW_REG_HTGT_TRAP_GROUP_MAX,
+ MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
+};
+
+enum mlxsw_reg_htgt_discard_trap_group {
+ MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX,
+ MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS,
};
/* reg_htgt_trap_group
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 09/11] mlxsw: Add layer 2 discard trap IDs
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Add the trap IDs used to report layer 2 drops.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/trap.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 19202bdb5105..7618f084cae9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -66,6 +66,13 @@ enum {
MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD,
MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
+ MLXSW_TRAP_ID_DISCARD_ING_PACKET_SMAC_MC = 0x140,
+ MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VTAG_ALLOW = 0x148,
+ MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VLAN = 0x149,
+ MLXSW_TRAP_ID_DISCARD_ING_SWITCH_STP = 0x14A,
+ MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_UC = 0x150,
+ MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_MC_NULL = 0x151,
+ MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_LB = 0x152,
MLXSW_TRAP_ID_ACL0 = 0x1C0,
/* Multicast trap used for routes with trap action */
MLXSW_TRAP_ID_ACL1 = 0x1C1,
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 08/11] mlxsw: reg: Add new trap action
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Subsequent patches will add discard traps support in mlxsw. The driver
cannot configure such traps with a normal trap action, but need to use
exception trap action, which also increments an error counter.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index ead36702549a..55211218ec1a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5559,6 +5559,7 @@ enum mlxsw_reg_hpkt_action {
MLXSW_REG_HPKT_ACTION_DISCARD,
MLXSW_REG_HPKT_ACTION_SOFT_DISCARD,
MLXSW_REG_HPKT_ACTION_TRAP_AND_SOFT_DISCARD,
+ MLXSW_REG_HPKT_ACTION_TRAP_EXCEPTION_TO_CPU,
};
/* reg_hpkt_action
@@ -5569,6 +5570,7 @@ enum mlxsw_reg_hpkt_action {
* 3 - Discard.
* 4 - Soft discard (allow other traps to act on the packet).
* 5 - Trap and soft discard (allow other traps to overwrite this trap).
+ * 6 - Trap to CPU (CPU receives sole copy) and count it as error.
* Access: RW
*
* Note: Must be set to 0 (forward) for event trap IDs, as they are already
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 07/11] mlxsw: core: Add API to set trap action
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Up until now the action of a trap was never changed during its lifetime.
This is going to change by subsequent patches that will allow devlink to
control the action of certain traps.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/core.c | 12 ++++++++++++
drivers/net/ethernet/mellanox/mlxsw/core.h | 3 +++
2 files changed, 15 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 17ceac7505e5..6ec07ecfb5f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1477,6 +1477,18 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core,
}
EXPORT_SYMBOL(mlxsw_core_trap_unregister);
+int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_listener *listener,
+ enum mlxsw_reg_hpkt_action action)
+{
+ char hpkt_pl[MLXSW_REG_HPKT_LEN];
+
+ mlxsw_reg_hpkt_pack(hpkt_pl, action, listener->trap_id,
+ listener->trap_group, listener->is_ctrl);
+ return mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl);
+}
+EXPORT_SYMBOL(mlxsw_core_trap_action_set);
+
static u64 mlxsw_core_tid_get(struct mlxsw_core *mlxsw_core)
{
return atomic64_inc_return(&mlxsw_core->emad.tid);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 8efcff4b59cb..19cea16c30bb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -128,6 +128,9 @@ int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core,
void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core,
const struct mlxsw_listener *listener,
void *priv);
+int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_listener *listener,
+ enum mlxsw_reg_hpkt_action action);
typedef void mlxsw_reg_trans_cb_t(struct mlxsw_core *mlxsw_core, char *payload,
size_t payload_len, unsigned long cb_priv);
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 06/11] Documentation: Add description of netdevsim traps
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
.../networking/devlink-trap-netdevsim.rst | 20 +++++++++++++++++++
Documentation/networking/devlink-trap.rst | 11 ++++++++++
Documentation/networking/index.rst | 1 +
drivers/net/netdevsim/dev.c | 3 +++
4 files changed, 35 insertions(+)
create mode 100644 Documentation/networking/devlink-trap-netdevsim.rst
diff --git a/Documentation/networking/devlink-trap-netdevsim.rst b/Documentation/networking/devlink-trap-netdevsim.rst
new file mode 100644
index 000000000000..b721c9415473
--- /dev/null
+++ b/Documentation/networking/devlink-trap-netdevsim.rst
@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+Devlink Trap netdevsim
+======================
+
+Driver-specific Traps
+=====================
+
+.. list-table:: List of Driver-specific Traps Registered by ``netdevsim``
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``fid_miss``
+ - ``exception``
+ - When a packet enters the device it is classified to a filtering
+ indentifier (FID) based on the ingress port and VLAN. This trap is used
+ to trap packets for which a FID could not be found
diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink-trap.rst
index 4a4fd42f5372..906cdeb0d1f3 100644
--- a/Documentation/networking/devlink-trap.rst
+++ b/Documentation/networking/devlink-trap.rst
@@ -153,6 +153,17 @@ be added to the following table:
- Traps packets that the device decided to drop because they could not be
enqueued to a transmission queue which is full
+Driver-specific Packet Traps
+============================
+
+Device drivers can register driver-specific packet traps, but these must be
+clearly documented. Such traps can correspond to device-specific exceptions and
+help debug packet drops caused by these exceptions. The following list includes
+links to the description of driver-specific traps registered by various device
+drivers:
+
+ * :doc:`/devlink-trap-netdevsim`
+
Generic Packet Trap Groups
==========================
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 86a814e4d450..37eabc17894c 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -15,6 +15,7 @@ Contents:
dsa/index
devlink-info-versions
devlink-trap
+ devlink-trap-netdevsim
ieee802154
kapi
z8530book
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 2d8c60c3326c..2892b3154940 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -218,6 +218,9 @@ struct nsim_trap_data {
spinlock_t trap_lock; /* Protects trap_items_arr */
};
+/* All driver-specific traps must be documented in
+ * Documentation/networking/devlink-trap-netdevsim.rst
+ */
enum {
NSIM_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX,
NSIM_TRAP_ID_FID_MISS,
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 05/11] netdevsim: Add devlink-trap support
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Have netdevsim register its trap groups and traps with devlink during
initialization and periodically report trapped packets to devlink core.
Since netdevsim is not a real device, the trapped packets are emulated
using a workqueue that periodically reports a UDP packet with a random
5-tuple from each active packet trap and from each running netdev.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/netdevsim/dev.c | 270 +++++++++++++++++++++++++++++-
drivers/net/netdevsim/netdevsim.h | 1 +
2 files changed, 270 insertions(+), 1 deletion(-)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index c5c417a3c0ce..2d8c60c3326c 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -17,11 +17,21 @@
#include <linux/debugfs.h>
#include <linux/device.h>
+#include <linux/etherdevice.h>
+#include <linux/inet.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/random.h>
+#include <linux/workqueue.h>
+#include <linux/random.h>
#include <linux/rtnetlink.h>
#include <net/devlink.h>
+#include <net/ip.h>
+#include <uapi/linux/devlink.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/udp.h>
#include "netdevsim.h"
@@ -196,6 +206,205 @@ static int nsim_dev_resources_register(struct devlink *devlink)
return err;
}
+struct nsim_trap_item {
+ void *trap_ctx;
+ enum devlink_trap_action action;
+};
+
+struct nsim_trap_data {
+ struct delayed_work trap_report_dw;
+ struct nsim_trap_item *trap_items_arr;
+ struct nsim_dev *nsim_dev;
+ spinlock_t trap_lock; /* Protects trap_items_arr */
+};
+
+enum {
+ NSIM_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX,
+ NSIM_TRAP_ID_FID_MISS,
+};
+
+#define NSIM_TRAP_NAME_FID_MISS "fid_miss"
+
+#define NSIM_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT
+
+#define NSIM_TRAP_DROP(_id, _group_id) \
+ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \
+ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
+ NSIM_TRAP_METADATA)
+#define NSIM_TRAP_EXCEPTION(_id, _group_id) \
+ DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \
+ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
+ NSIM_TRAP_METADATA)
+#define NSIM_TRAP_DRIVER_EXCEPTION(_id, _group_id) \
+ DEVLINK_TRAP_DRIVER(EXCEPTION, TRAP, NSIM_TRAP_ID_##_id, \
+ NSIM_TRAP_NAME_##_id, \
+ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \
+ NSIM_TRAP_METADATA)
+
+static const struct devlink_trap nsim_traps_arr[] = {
+ NSIM_TRAP_DROP(SMAC_MC, L2_DROPS),
+ NSIM_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS),
+ NSIM_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS),
+ NSIM_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS),
+ NSIM_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS),
+ NSIM_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS),
+ NSIM_TRAP_DRIVER_EXCEPTION(FID_MISS, L2_DROPS),
+ NSIM_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS),
+ NSIM_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS),
+ NSIM_TRAP_DROP(TAIL_DROP, BUFFER_DROPS),
+};
+
+#define NSIM_TRAP_L4_DATA_LEN 100
+
+static struct sk_buff *nsim_dev_trap_skb_build(void)
+{
+ int tot_len, data_len = NSIM_TRAP_L4_DATA_LEN;
+ struct sk_buff *skb;
+ struct udphdr *udph;
+ struct ethhdr *eth;
+ struct iphdr *iph;
+
+ skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+ tot_len = sizeof(struct iphdr) + sizeof(struct udphdr) + data_len;
+
+ eth = skb_put(skb, sizeof(struct ethhdr));
+ eth_random_addr(eth->h_dest);
+ eth_random_addr(eth->h_source);
+ eth->h_proto = htons(ETH_P_IP);
+ skb->protocol = htons(ETH_P_IP);
+
+ iph = skb_put(skb, sizeof(struct iphdr));
+ iph->protocol = IPPROTO_UDP;
+ iph->saddr = in_aton("192.0.2.1");
+ iph->daddr = in_aton("198.51.100.1");
+ iph->version = 0x4;
+ iph->frag_off = 0;
+ iph->ihl = 0x5;
+ iph->tot_len = htons(tot_len);
+ ip_send_check(iph);
+
+ udph = skb_put_zero(skb, sizeof(struct udphdr) + data_len);
+ get_random_bytes(&udph->source, sizeof(u16));
+ get_random_bytes(&udph->dest, sizeof(u16));
+ udph->len = htons(sizeof(struct udphdr) + data_len);
+
+ return skb;
+}
+
+static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port)
+{
+ struct nsim_dev *nsim_dev = nsim_dev_port->ns->nsim_dev;
+ struct nsim_trap_data *nsim_trap_data = nsim_dev->trap_data;
+ struct devlink *devlink = priv_to_devlink(nsim_dev);
+ int i;
+
+ spin_lock(&nsim_trap_data->trap_lock);
+ for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) {
+ struct nsim_trap_item *nsim_trap_item;
+ struct sk_buff *skb;
+
+ nsim_trap_item = &nsim_trap_data->trap_items_arr[i];
+ if (nsim_trap_item->action == DEVLINK_TRAP_ACTION_DROP)
+ continue;
+
+ skb = nsim_dev_trap_skb_build();
+ if (!skb)
+ continue;
+ skb->dev = nsim_dev_port->ns->netdev;
+
+ devlink_trap_report(devlink, skb, nsim_trap_item->trap_ctx,
+ &nsim_dev_port->devlink_port);
+ consume_skb(skb);
+ }
+ spin_unlock(&nsim_trap_data->trap_lock);
+}
+
+#define NSIM_TRAP_REPORT_INTERVAL_MS 100
+
+static void nsim_dev_trap_report_work(struct work_struct *work)
+{
+ struct nsim_trap_data *nsim_trap_data;
+ struct nsim_dev_port *nsim_dev_port;
+ struct nsim_dev *nsim_dev;
+
+ nsim_trap_data = container_of(work, struct nsim_trap_data,
+ trap_report_dw.work);
+ nsim_dev = nsim_trap_data->nsim_dev;
+
+ /* For each running port and enabled packet trap, generate a UDP
+ * packet with a random 5-tuple and report it.
+ */
+ mutex_lock(&nsim_dev->port_list_lock);
+ list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) {
+ if (!netif_running(nsim_dev_port->ns->netdev))
+ continue;
+
+ nsim_dev_trap_report(nsim_dev_port);
+ }
+ mutex_unlock(&nsim_dev->port_list_lock);
+
+ schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw,
+ msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS));
+}
+
+static int nsim_dev_traps_init(struct devlink *devlink)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(devlink);
+ struct nsim_trap_data *nsim_trap_data;
+ int err;
+
+ nsim_trap_data = kzalloc(sizeof(*nsim_trap_data), GFP_KERNEL);
+ if (!nsim_trap_data)
+ return -ENOMEM;
+
+ nsim_trap_data->trap_items_arr = kcalloc(ARRAY_SIZE(nsim_traps_arr),
+ sizeof(struct nsim_trap_item),
+ GFP_KERNEL);
+ if (!nsim_trap_data->trap_items_arr) {
+ err = -ENOMEM;
+ goto err_trap_data_free;
+ }
+
+ /* The lock is used to protect the action state of the registered
+ * traps. The value is written by user and read in delayed work when
+ * iterating over all the traps.
+ */
+ spin_lock_init(&nsim_trap_data->trap_lock);
+ nsim_trap_data->nsim_dev = nsim_dev;
+ nsim_dev->trap_data = nsim_trap_data;
+
+ err = devlink_traps_register(devlink, nsim_traps_arr,
+ ARRAY_SIZE(nsim_traps_arr), NULL);
+ if (err)
+ goto err_trap_items_free;
+
+ INIT_DELAYED_WORK(&nsim_dev->trap_data->trap_report_dw,
+ nsim_dev_trap_report_work);
+ schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw,
+ msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS));
+
+ return 0;
+
+err_trap_items_free:
+ kfree(nsim_trap_data->trap_items_arr);
+err_trap_data_free:
+ kfree(nsim_trap_data);
+ return err;
+}
+
+static void nsim_dev_traps_exit(struct devlink *devlink)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(devlink);
+
+ cancel_delayed_work_sync(&nsim_dev->trap_data->trap_report_dw);
+ devlink_traps_unregister(devlink, nsim_traps_arr,
+ ARRAY_SIZE(nsim_traps_arr));
+ kfree(nsim_dev->trap_data->trap_items_arr);
+ kfree(nsim_dev->trap_data);
+}
+
static int nsim_dev_reload(struct devlink *devlink,
struct netlink_ext_ack *extack)
{
@@ -262,9 +471,61 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name,
return 0;
}
+static struct nsim_trap_item *
+nsim_dev_trap_item_lookup(struct nsim_dev *nsim_dev, u16 trap_id)
+{
+ struct nsim_trap_data *nsim_trap_data = nsim_dev->trap_data;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) {
+ if (nsim_traps_arr[i].id == trap_id)
+ return &nsim_trap_data->trap_items_arr[i];
+ }
+
+ return NULL;
+}
+
+static int nsim_dev_devlink_trap_init(struct devlink *devlink,
+ const struct devlink_trap *trap,
+ void *trap_ctx)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(devlink);
+ struct nsim_trap_item *nsim_trap_item;
+
+ nsim_trap_item = nsim_dev_trap_item_lookup(nsim_dev, trap->id);
+ if (WARN_ON(!nsim_trap_item))
+ return -ENOENT;
+
+ nsim_trap_item->trap_ctx = trap_ctx;
+ nsim_trap_item->action = trap->init_action;
+
+ return 0;
+}
+
+static int
+nsim_dev_devlink_trap_action_set(struct devlink *devlink,
+ const struct devlink_trap *trap,
+ enum devlink_trap_action action)
+{
+ struct nsim_dev *nsim_dev = devlink_priv(devlink);
+ struct nsim_trap_item *nsim_trap_item;
+
+ nsim_trap_item = nsim_dev_trap_item_lookup(nsim_dev, trap->id);
+ if (WARN_ON(!nsim_trap_item))
+ return -ENOENT;
+
+ spin_lock(&nsim_dev->trap_data->trap_lock);
+ nsim_trap_item->action = action;
+ spin_unlock(&nsim_dev->trap_data->trap_lock);
+
+ return 0;
+}
+
static const struct devlink_ops nsim_dev_devlink_ops = {
.reload = nsim_dev_reload,
.flash_update = nsim_dev_flash_update,
+ .trap_init = nsim_dev_devlink_trap_init,
+ .trap_action_set = nsim_dev_devlink_trap_action_set,
};
static struct nsim_dev *
@@ -299,10 +560,14 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count)
if (err)
goto err_resources_unregister;
- err = nsim_dev_debugfs_init(nsim_dev);
+ err = nsim_dev_traps_init(devlink);
if (err)
goto err_dl_unregister;
+ err = nsim_dev_debugfs_init(nsim_dev);
+ if (err)
+ goto err_traps_exit;
+
err = nsim_bpf_dev_init(nsim_dev);
if (err)
goto err_debugfs_exit;
@@ -311,6 +576,8 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count)
err_debugfs_exit:
nsim_dev_debugfs_exit(nsim_dev);
+err_traps_exit:
+ nsim_dev_traps_exit(devlink);
err_dl_unregister:
devlink_unregister(devlink);
err_resources_unregister:
@@ -328,6 +595,7 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev)
nsim_bpf_dev_exit(nsim_dev);
nsim_dev_debugfs_exit(nsim_dev);
+ nsim_dev_traps_exit(devlink);
devlink_unregister(devlink);
devlink_resources_unregister(devlink, NULL);
nsim_fib_destroy(nsim_dev->fib_data);
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 79c05af2a7c0..a3dd73ae252e 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -145,6 +145,7 @@ struct nsim_dev_port {
struct nsim_dev {
struct nsim_bus_dev *nsim_bus_dev;
struct nsim_fib_data *fib_data;
+ struct nsim_trap_data *trap_data;
struct dentry *ddir;
struct dentry *ports_ddir;
struct bpf_offload_dev *bpf_dev;
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 04/11] Documentation: Add devlink-trap documentation
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Add initial documentation of the devlink-trap mechanism, explaining the
background, motivation and the semantics of the interface.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
Documentation/networking/devlink-trap.rst | 179 ++++++++++++++++++++++
Documentation/networking/index.rst | 1 +
include/net/devlink.h | 6 +
3 files changed, 186 insertions(+)
create mode 100644 Documentation/networking/devlink-trap.rst
diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink-trap.rst
new file mode 100644
index 000000000000..4a4fd42f5372
--- /dev/null
+++ b/Documentation/networking/devlink-trap.rst
@@ -0,0 +1,179 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+Devlink Trap
+============
+
+Background
+==========
+
+Devices capable of offloading the kernel's datapath and perform functions such
+as bridging and routing must also be able to send specific packets to the
+kernel (i.e., the CPU) for processing.
+
+For example, a device acting as a multicast-aware bridge must be able to send
+IGMP membership reports to the kernel for processing by the bridge module.
+Without processing such packets, the bridge module could never populate its
+MDB.
+
+As another example, consider a device acting as router which has received an IP
+packet with a TTL of 1. Upon routing the packet the device must send it to the
+kernel so that it will route it as well and generate an ICMP Time Exceeded
+error datagram. Without letting the kernel route such packets itself, utilities
+such as ``traceroute`` could never work.
+
+The fundamental ability of sending certain packets to the kernel for processing
+is called "packet trapping".
+
+Overview
+========
+
+The ``devlink-trap`` mechanism allows capable device drivers to register their
+supported packet traps with ``devlink`` and report trapped packets to
+``devlink`` for further analysis.
+
+Upon receiving trapped packets, ``devlink`` will perform a per-trap packets and
+bytes accounting and potentially report the packet to user space via a netlink
+event along with all the provided metadata (e.g., trap reason, timestamp, input
+port). This is especially useful for drop traps (see :ref:`Trap-Types`)
+as it allows users to obtain further visibility into packet drops that would
+otherwise be invisible.
+
+The following diagram provides a general overview of ``devlink-trap``::
+
+ Netlink event: Packet w/ metadata
+ ^
+ |
+ Userspace |
+ +---------------------------------------------------+
+ Kernel |
+ |
+ +----+----+
+ | | Kernel's Rx path
+ | devlink | (non-drop traps)
+ | |
+ +----^----+ ^
+ | |
+ +-----------+
+ |
+ +-------+-------+
+ | |
+ | Device driver |
+ | |
+ +-------^-------+
+ Kernel |
+ +---------------------------------------------------+
+ Hardware |
+ | Trapped packet
+ |
+ +--+---+
+ | |
+ | ASIC |
+ | |
+ +------+
+
+.. _Trap-Types:
+
+Trap Types
+==========
+
+The ``devlink-trap`` mechanism supports the following packet trap types:
+
+ * ``drop``: Trapped packets were dropped by the underlying device. Packets
+ are only processed by ``devlink`` and not injected to the kernel's Rx path.
+ The trap action (see :ref:`Trap-Actions`) can be changed.
+ * ``exception``: Trapped packets were not forwarded as intended by the
+ underlying device due to an exception (e.g., TTL error, missing neighbour
+ entry) and trapped to the control plane for resolution. Packets are
+ processed by ``devlink`` and injected to the kernel's Rx path. Changing the
+ action of such traps is not allowed, as it can easily break the control
+ plane.
+
+.. _Trap-Actions:
+
+Trap Actions
+============
+
+The ``devlink-trap`` mechanism supports the following packet trap actions:
+
+ * ``trap``: The sole copy of the packet is sent to the CPU.
+ * ``drop``: The packet is dropped by the underlying device and a copy is not
+ sent to the CPU.
+
+Generic Packet Traps
+====================
+
+Generic packet traps are used to describe traps that trap well-defined packets
+or packets that are trapped due to well-defined conditions (e.g., TTL error).
+Such traps can be shared by multiple device drivers and their description must
+be added to the following table:
+
+.. list-table:: List of Generic Packet Traps
+ :widths: 5 5 90
+
+ * - Name
+ - Type
+ - Description
+ * - ``source_mac_is_multicast``
+ - ``drop``
+ - Traps incoming packets that the device decided to drop because of a
+ multicast source MAC
+ * - ``vlan_tag_mismatch``
+ - ``drop``
+ - Traps incoming packets that the device decided to drop in case of VLAN
+ tag mismatch: The ingress bridge port is not configured with a PVID and
+ the packet is untagged or prio-tagged
+ * - ``ingress_vlan_filter``
+ - ``drop``
+ - Traps incoming packets that the device decided to drop in case they are
+ tagged with a VLAN that is not configured on the ingress bridge port
+ * - ``ingress_spanning_tree_filter``
+ - ``drop``
+ - Traps incoming packets that the device decided to drop in case the STP
+ state of the ingress bridge port is not "forwarding"
+ * - ``port_list_is_empty``
+ - ``drop``
+ - Traps packets that the device decided to drop in case they need to be
+ flooded and the flood list is empty
+ * - ``port_loopback_filter``
+ - ``drop``
+ - Traps packets that the device decided to drop in case after layer 2
+ forwarding the only port from which they should be transmitted through
+ is the port from which they were received
+ * - ``blackhole_route``
+ - ``drop``
+ - Traps packets that the device decided to drop in case they hit a
+ blackhole route
+ * - ``ttl_value_is_too_small``
+ - ``exception``
+ - Traps unicast packets that should be forwarded by the device whose TTL
+ was decremented to 0 or less
+ * - ``tail_drop``
+ - ``drop``
+ - Traps packets that the device decided to drop because they could not be
+ enqueued to a transmission queue which is full
+
+Generic Packet Trap Groups
+==========================
+
+Generic packet trap groups are used to aggregate logically related packet
+traps. These groups allow the user to batch operations such as setting the
+trap action and report state of all member traps. In addition, ``devlink-trap``
+can report aggregated per-group packets and bytes statistics, in case per-trap
+statistics are too narrow. The description of these groups must be added to the
+following table:
+
+.. list-table:: List of Generic Packet Trap Groups
+ :widths: 10 90
+
+ * - Name
+ - Description
+ * - ``l2_drops``
+ - Contains packet traps for packets that were dropped by the device during
+ layer 2 forwarding (i.e., bridge)
+ * - ``l3_drops``
+ - Contains packet traps for packets that were dropped by the device or hit
+ an exception (e.g., TTL error) during layer 3 forwarding
+ * - ``buffer_drops``
+ - Contains packet traps for packets that were dropped by the device due to
+ an enqueue decision
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index a46fca264bee..86a814e4d450 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -14,6 +14,7 @@ Contents:
device_drivers/index
dsa/index
devlink-info-versions
+ devlink-trap
ieee802154
kapi
z8530book
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 9121eb45b1c0..5a578750f6b4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -520,6 +520,9 @@ struct devlink_trap {
u32 metadata_cap;
};
+/* All traps must be documented in
+ * Documentation/networking/devlink-trap.rst
+ */
enum devlink_trap_generic_id {
DEVLINK_TRAP_GENERIC_ID_SMAC_MC,
DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH,
@@ -536,6 +539,9 @@ enum devlink_trap_generic_id {
DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1,
};
+/* All trap groups must be documented in
+ * Documentation/networking/devlink-trap.rst
+ */
enum devlink_trap_group_generic_id {
DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS,
DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS,
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 03/11] devlink: Add generic packet traps and groups
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Add generic packet traps and groups that can report dropped packets as
well as exceptions such as TTL error.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/devlink.h | 40 ++++++++++++++++++++++++++++++++++++++++
net/core/devlink.c | 12 ++++++++++++
2 files changed, 52 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 22614d3a742a..9121eb45b1c0 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -521,18 +521,58 @@ struct devlink_trap {
};
enum devlink_trap_generic_id {
+ DEVLINK_TRAP_GENERIC_ID_SMAC_MC,
+ DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH,
+ DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER,
+ DEVLINK_TRAP_GENERIC_ID_INGRESS_STP_FILTER,
+ DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST,
+ DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER,
+ DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE,
+ DEVLINK_TRAP_GENERIC_ID_TTL_ERROR,
+ DEVLINK_TRAP_GENERIC_ID_TAIL_DROP,
+
/* Add new generic trap IDs above */
__DEVLINK_TRAP_GENERIC_ID_MAX,
DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1,
};
enum devlink_trap_group_generic_id {
+ DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS,
+
/* Add new generic trap group IDs above */
__DEVLINK_TRAP_GROUP_GENERIC_ID_MAX,
DEVLINK_TRAP_GROUP_GENERIC_ID_MAX =
__DEVLINK_TRAP_GROUP_GENERIC_ID_MAX - 1,
};
+#define DEVLINK_TRAP_GENERIC_NAME_SMAC_MC \
+ "source_mac_is_multicast"
+#define DEVLINK_TRAP_GENERIC_NAME_VLAN_TAG_MISMATCH \
+ "vlan_tag_mismatch"
+#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_VLAN_FILTER \
+ "ingress_vlan_filter"
+#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_STP_FILTER \
+ "ingress_spanning_tree_filter"
+#define DEVLINK_TRAP_GENERIC_NAME_EMPTY_TX_LIST \
+ "port_list_is_empty"
+#define DEVLINK_TRAP_GENERIC_NAME_PORT_LOOPBACK_FILTER \
+ "port_loopback_filter"
+#define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_ROUTE \
+ "blackhole_route"
+#define DEVLINK_TRAP_GENERIC_NAME_TTL_ERROR \
+ "ttl_value_is_too_small"
+#define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \
+ "tail_drop"
+
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
+ "l2_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_DROPS \
+ "l3_drops"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BUFFER_DROPS \
+ "buffer_drops"
+
#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \
{ \
.type = DEVLINK_TRAP_TYPE_##_type, \
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 44a850ec3d5f..172ede6ba1b1 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -7414,6 +7414,15 @@ EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
}
static const struct devlink_trap devlink_trap_generic[] = {
+ DEVLINK_TRAP(SMAC_MC, DROP),
+ DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP),
+ DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP),
+ DEVLINK_TRAP(INGRESS_STP_FILTER, DROP),
+ DEVLINK_TRAP(EMPTY_TX_LIST, DROP),
+ DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP),
+ DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP),
+ DEVLINK_TRAP(TTL_ERROR, EXCEPTION),
+ DEVLINK_TRAP(TAIL_DROP, DROP),
};
#define DEVLINK_TRAP_GROUP(_id) \
@@ -7423,6 +7432,9 @@ static const struct devlink_trap devlink_trap_generic[] = {
}
static const struct devlink_trap_group devlink_trap_group_generic[] = {
+ DEVLINK_TRAP_GROUP(L2_DROPS),
+ DEVLINK_TRAP_GROUP(L3_DROPS),
+ DEVLINK_TRAP_GROUP(BUFFER_DROPS),
};
static int devlink_trap_generic_verify(const struct devlink_trap *trap)
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 02/11] devlink: Add packet trap infrastructure
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Add the basic packet trap infrastructure that allows device drivers to
register their supported packet traps and trap groups with devlink.
Each driver is expected to provide basic information about each
supported trap, such as name and ID, but also the supported metadata
types that will accompany each packet trapped via the trap. The
currently supported metadata type is just the input port, but more will
be added in the future. For example, output port and traffic class.
Trap groups allow users to set the reporting state as well as the action
of all member traps. In addition, users can retrieve per-group
statistics in case per-trap statistics are too narrow. In the future,
the trap group object can be extended with more attributes, such as
policer settings which will limit the amount of traffic generated by
member traps towards the CPU.
Beside registering their packet traps with devlink, drivers are also
expected to report trapped packets to devlink along with relevant
metadata. devlink will maintain packets and bytes statistics for each
packet trap and will potentially report the trapped packet with its
metadata to userspace via a new generic netlink multicast group.
The interface towards the drivers is simple and allows devlink to set
the action of the trap. Currently, only two actions are supported:
'trap' and 'drop'. When set to 'trap', the device is expected to provide
the sole copy of the packet to the driver which will pass it to devlink.
When set to 'drop', the device is expected to drop the packet and not
send a copy to the driver. In the future, more actions can be added,
such as 'mirror'.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/devlink.h | 129 ++++
include/uapi/linux/devlink.h | 68 ++
net/core/devlink.c | 1251 +++++++++++++++++++++++++++++++++-
3 files changed, 1443 insertions(+), 5 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 6625ea068d5e..22614d3a742a 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -14,6 +14,7 @@
#include <linux/netdevice.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
+#include <linux/refcount.h>
#include <net/net_namespace.h>
#include <uapi/linux/devlink.h>
@@ -31,6 +32,8 @@ struct devlink {
struct list_head reporter_list;
struct mutex reporters_lock; /* protects reporter_list */
struct devlink_dpipe_headers *dpipe_headers;
+ struct list_head trap_list;
+ struct list_head trap_group_list;
const struct devlink_ops *ops;
struct device *dev;
possible_net_t _net;
@@ -477,6 +480,89 @@ struct devlink_health_reporter_ops {
struct devlink_fmsg *fmsg);
};
+/**
+ * struct devlink_trap_group - Immutable packet trap group attributes.
+ * @name: Trap group name.
+ * @id: Trap group identifier.
+ * @generic: Whether the trap group is generic or not.
+ *
+ * Describes immutable attributes of packet trap groups that drivers register
+ * with devlink.
+ */
+struct devlink_trap_group {
+ const char *name;
+ u16 id;
+ bool generic;
+};
+
+#define DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT BIT(0)
+
+/**
+ * struct devlink_trap - Immutable packet trap attributes.
+ * @type: Trap type.
+ * @init_action: Initial trap action.
+ * @generic: Whether the trap is generic or not.
+ * @id: Trap identifier.
+ * @name: Trap name.
+ * @group: Immutable packet trap group attributes.
+ * @metadata_cap: Metadata types that can be provided by the trap.
+ *
+ * Describes immutable attributes of packet traps that drivers register with
+ * devlink.
+ */
+struct devlink_trap {
+ enum devlink_trap_type type;
+ enum devlink_trap_action init_action;
+ bool generic;
+ u16 id;
+ const char *name;
+ struct devlink_trap_group group;
+ u32 metadata_cap;
+};
+
+enum devlink_trap_generic_id {
+ /* Add new generic trap IDs above */
+ __DEVLINK_TRAP_GENERIC_ID_MAX,
+ DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1,
+};
+
+enum devlink_trap_group_generic_id {
+ /* Add new generic trap group IDs above */
+ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX,
+ DEVLINK_TRAP_GROUP_GENERIC_ID_MAX =
+ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX - 1,
+};
+
+#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \
+ { \
+ .type = DEVLINK_TRAP_TYPE_##_type, \
+ .init_action = DEVLINK_TRAP_ACTION_##_init_action, \
+ .generic = true, \
+ .id = DEVLINK_TRAP_GENERIC_ID_##_id, \
+ .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \
+ .group = _group, \
+ .metadata_cap = _metadata_cap, \
+ }
+
+#define DEVLINK_TRAP_DRIVER(_type, _init_action, _id, _name, _group, \
+ _metadata_cap) \
+ { \
+ .type = DEVLINK_TRAP_TYPE_##_type, \
+ .init_action = DEVLINK_TRAP_ACTION_##_init_action, \
+ .generic = false, \
+ .id = _id, \
+ .name = _name, \
+ .group = _group, \
+ .metadata_cap = _metadata_cap, \
+ }
+
+#define DEVLINK_TRAP_GROUP_GENERIC(_id) \
+ { \
+ .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \
+ .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \
+ .generic = true, \
+ }
+
struct devlink_ops {
int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
int (*port_type_set)(struct devlink_port *devlink_port,
@@ -538,6 +624,38 @@ struct devlink_ops {
int (*flash_update)(struct devlink *devlink, const char *file_name,
const char *component,
struct netlink_ext_ack *extack);
+ /**
+ * @trap_init: Trap initialization function.
+ *
+ * Should be used by device drivers to initialize the trap in the
+ * underlying device. Drivers should also store the provided trap
+ * context, so that they could efficiently pass it to
+ * devlink_trap_report() when the trap is triggered.
+ */
+ int (*trap_init)(struct devlink *devlink,
+ const struct devlink_trap *trap, void *trap_ctx);
+ /**
+ * @trap_fini: Trap de-initialization function.
+ *
+ * Should be used by device drivers to de-initialize the trap in the
+ * underlying device.
+ */
+ void (*trap_fini)(struct devlink *devlink,
+ const struct devlink_trap *trap, void *trap_ctx);
+ /**
+ * @trap_action_set: Trap action set function.
+ */
+ int (*trap_action_set)(struct devlink *devlink,
+ const struct devlink_trap *trap,
+ enum devlink_trap_action action);
+ /**
+ * @trap_group_init: Trap group initialization function.
+ *
+ * Should be used by device drivers to initialize the trap group in the
+ * underlying device.
+ */
+ int (*trap_group_init)(struct devlink *devlink,
+ const struct devlink_trap_group *group);
};
static inline void *devlink_priv(struct devlink *devlink)
@@ -747,6 +865,17 @@ void devlink_flash_update_status_notify(struct devlink *devlink,
unsigned long done,
unsigned long total);
+int devlink_traps_register(struct devlink *devlink,
+ const struct devlink_trap *traps,
+ size_t traps_count, void *priv);
+void devlink_traps_unregister(struct devlink *devlink,
+ const struct devlink_trap *traps,
+ size_t traps_count);
+void devlink_trap_report(struct devlink *devlink,
+ struct sk_buff *skb, void *trap_ctx,
+ struct devlink_port *in_devlink_port);
+void *devlink_trap_ctx_priv(void *trap_ctx);
+
#if IS_ENABLED(CONFIG_NET_DEVLINK)
void devlink_compat_running_version(struct net_device *dev,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 5287b42c181f..c1c0a6e2a71a 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -16,6 +16,7 @@
#define DEVLINK_GENL_NAME "devlink"
#define DEVLINK_GENL_VERSION 0x1
#define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
+#define DEVLINK_GENL_MCGRP_TRAP_NAME "trap"
enum devlink_command {
/* don't change the order or add anything between, this is ABI! */
@@ -107,6 +108,17 @@ enum devlink_command {
DEVLINK_CMD_FLASH_UPDATE_END, /* notification only */
DEVLINK_CMD_FLASH_UPDATE_STATUS, /* notification only */
+ DEVLINK_CMD_TRAP_GET, /* can dump */
+ DEVLINK_CMD_TRAP_SET,
+ DEVLINK_CMD_TRAP_NEW,
+ DEVLINK_CMD_TRAP_DEL,
+ DEVLINK_CMD_TRAP_REPORT,
+
+ DEVLINK_CMD_TRAP_GROUP_GET, /* can dump */
+ DEVLINK_CMD_TRAP_GROUP_SET,
+ DEVLINK_CMD_TRAP_GROUP_NEW,
+ DEVLINK_CMD_TRAP_GROUP_DEL,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -186,6 +198,47 @@ enum devlink_param_fw_load_policy_value {
DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH,
};
+enum {
+ DEVLINK_ATTR_STATS_RX_PACKETS,
+ DEVLINK_ATTR_STATS_RX_BYTES,
+
+ __DEVLINK_ATTR_STATS_MAX,
+ DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1
+};
+
+/**
+ * enum devlink_trap_action - Packet trap action.
+ * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
+ * sent to the CPU.
+ * @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU.
+ */
+enum devlink_trap_action {
+ DEVLINK_TRAP_ACTION_DROP,
+ DEVLINK_TRAP_ACTION_TRAP,
+};
+
+/**
+ * enum devlink_trap_type - Packet trap type.
+ * @DEVLINK_TRAP_TYPE_DROP: Trap reason is a drop. Trapped packets are only
+ * processed by devlink and not injected to the
+ * kernel's Rx path.
+ * @DEVLINK_TRAP_TYPE_EXCEPTION: Trap reason is an exception. Packet was not
+ * forwarded as intended due to an exception
+ * (e.g., missing neighbour entry) and trapped to
+ * control plane for resolution. Trapped packets
+ * are processed by devlink and injected to
+ * the kernel's Rx path.
+ */
+enum devlink_trap_type {
+ DEVLINK_TRAP_TYPE_DROP,
+ DEVLINK_TRAP_TYPE_EXCEPTION,
+};
+
+enum {
+ /* Trap can report input port as metadata */
+ DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT,
+};
+
enum devlink_attr {
/* don't change the order or add anything between, this is ABI! */
DEVLINK_ATTR_UNSPEC,
@@ -337,6 +390,21 @@ enum devlink_attr {
DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, /* u64 */
DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, /* u64 */
+ DEVLINK_ATTR_STATS, /* nested */
+
+ DEVLINK_ATTR_TRAP_NAME, /* string */
+ DEVLINK_ATTR_TRAP_REPORT_ENABLED, /* u8 */
+ /* enum devlink_trap_action */
+ DEVLINK_ATTR_TRAP_ACTION, /* u8 */
+ /* enum devlink_trap_type */
+ DEVLINK_ATTR_TRAP_TYPE, /* u8 */
+ DEVLINK_ATTR_TRAP_GENERIC, /* flag */
+ DEVLINK_ATTR_TRAP_METADATA, /* nested */
+ DEVLINK_ATTR_TRAP_TIMESTAMP, /* struct timespec */
+ DEVLINK_ATTR_TRAP_IN_PORT, /* nested */
+ DEVLINK_ATTR_TRAP_PAYLOAD, /* binary */
+ DEVLINK_ATTR_TRAP_GROUP_NAME, /* string */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 755a9a32015e..44a850ec3d5f 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -18,6 +18,8 @@
#include <linux/spinlock.h>
#include <linux/refcount.h>
#include <linux/workqueue.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/timekeeping.h>
#include <rdma/ib_verbs.h>
#include <net/netlink.h>
#include <net/genetlink.h>
@@ -449,10 +451,12 @@ static struct genl_family devlink_nl_family;
enum devlink_multicast_groups {
DEVLINK_MCGRP_CONFIG,
+ DEVLINK_MCGRP_TRAP,
};
static const struct genl_multicast_group devlink_nl_mcgrps[] = {
[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
+ [DEVLINK_MCGRP_TRAP] = { .name = DEVLINK_GENL_MCGRP_TRAP_NAME },
};
static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
@@ -570,14 +574,14 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
goto nla_put_failure;
- spin_lock(&devlink_port->type_lock);
+ spin_lock_bh(&devlink_port->type_lock);
if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&
nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,
devlink_port->desired_type))
goto nla_put_failure_type_locked;
if (devlink_nl_port_type_fill(msg, devlink_port))
goto nla_put_failure_type_locked;
- spin_unlock(&devlink_port->type_lock);
+ spin_unlock_bh(&devlink_port->type_lock);
if (devlink_nl_port_attrs_put(msg, devlink_port))
goto nla_put_failure;
@@ -585,7 +589,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
return 0;
nla_put_failure_type_locked:
- spin_unlock(&devlink_port->type_lock);
+ spin_unlock_bh(&devlink_port->type_lock);
nla_put_failure:
genlmsg_cancel(msg, hdr);
return -EMSGSIZE;
@@ -5146,6 +5150,623 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
return 0;
}
+struct devlink_stats {
+ u64 rx_bytes;
+ u64 rx_packets;
+ struct u64_stats_sync syncp;
+};
+
+/**
+ * struct devlink_trap_group_item - Packet trap group attributes.
+ * @group: Immutable packet trap group attributes.
+ * @refcount: Number of trap items using the group.
+ * @list: trap_group_list member.
+ * @stats: Trap group statistics.
+ *
+ * Describes packet trap group attributes. Created by devlink during trap
+ * registration.
+ */
+struct devlink_trap_group_item {
+ const struct devlink_trap_group *group;
+ refcount_t refcount;
+ struct list_head list;
+ struct devlink_stats __percpu *stats;
+};
+
+/**
+ * struct devlink_trap_item - Packet trap attributes.
+ * @trap: Immutable packet trap attributes.
+ * @group_item: Associated group item.
+ * @list: trap_list member.
+ * @report: Whether to report trapped packets or not.
+ * @action: Trap action.
+ * @stats: Trap statistics.
+ * @priv: Driver private information.
+ *
+ * Describes both mutable and immutable packet trap attributes. Created by
+ * devlink during trap registration and used for all trap related operations.
+ */
+struct devlink_trap_item {
+ const struct devlink_trap *trap;
+ struct devlink_trap_group_item *group_item;
+ struct list_head list;
+ bool report;
+ enum devlink_trap_action action;
+ struct devlink_stats __percpu *stats;
+ void *priv;
+};
+
+static struct devlink_trap_item *
+devlink_trap_item_lookup(struct devlink *devlink, const char *name)
+{
+ struct devlink_trap_item *trap_item;
+
+ list_for_each_entry(trap_item, &devlink->trap_list, list) {
+ if (!strcmp(trap_item->trap->name, name))
+ return trap_item;
+ }
+
+ return NULL;
+}
+
+static struct devlink_trap_item *
+devlink_trap_item_get_from_info(struct devlink *devlink,
+ struct genl_info *info)
+{
+ struct nlattr *attr;
+
+ if (!info->attrs[DEVLINK_ATTR_TRAP_NAME])
+ return NULL;
+ attr = info->attrs[DEVLINK_ATTR_TRAP_NAME];
+
+ return devlink_trap_item_lookup(devlink, nla_data(attr));
+}
+
+static int
+devlink_trap_action_get_from_info(struct genl_info *info,
+ enum devlink_trap_action *p_trap_action)
+{
+ u8 val;
+
+ val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]);
+ switch (val) {
+ case DEVLINK_TRAP_ACTION_DROP: /* fall-through */
+ case DEVLINK_TRAP_ACTION_TRAP:
+ *p_trap_action = val;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int devlink_trap_metadata_put(struct sk_buff *msg,
+ const struct devlink_trap *trap)
+{
+ struct nlattr *attr;
+
+ attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA);
+ if (!attr)
+ return -EMSGSIZE;
+
+ if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) &&
+ nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT))
+ goto nla_put_failure;
+
+ nla_nest_end(msg, attr);
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, attr);
+ return -EMSGSIZE;
+}
+
+static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats,
+ struct devlink_stats *stats)
+{
+ int i;
+
+ memset(stats, 0, sizeof(*stats));
+ for_each_possible_cpu(i) {
+ struct devlink_stats *cpu_stats;
+ u64 rx_packets, rx_bytes;
+ unsigned int start;
+
+ cpu_stats = per_cpu_ptr(trap_stats, i);
+ do {
+ start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
+ rx_packets = cpu_stats->rx_packets;
+ rx_bytes = cpu_stats->rx_bytes;
+ } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
+
+ stats->rx_packets += rx_packets;
+ stats->rx_bytes += rx_bytes;
+ }
+}
+
+static int devlink_trap_stats_put(struct sk_buff *msg,
+ struct devlink_stats __percpu *trap_stats)
+{
+ struct devlink_stats stats;
+ struct nlattr *attr;
+
+ devlink_trap_stats_read(trap_stats, &stats);
+
+ attr = nla_nest_start(msg, DEVLINK_ATTR_STATS);
+ if (!attr)
+ return -EMSGSIZE;
+
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS,
+ stats.rx_packets, DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+
+ if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES,
+ stats.rx_bytes, DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+
+ nla_nest_end(msg, attr);
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(msg, attr);
+ return -EMSGSIZE;
+}
+
+static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink,
+ const struct devlink_trap_item *trap_item,
+ enum devlink_command cmd, u32 portid, u32 seq,
+ int flags)
+{
+ struct devlink_trap_group_item *group_item = trap_item->group_item;
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto nla_put_failure;
+
+ if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
+ group_item->group->name))
+ goto nla_put_failure;
+
+ if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name))
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type))
+ goto nla_put_failure;
+
+ if (trap_item->trap->generic &&
+ nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC))
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_REPORT_ENABLED,
+ trap_item->report))
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action))
+ goto nla_put_failure;
+
+ err = devlink_trap_metadata_put(msg, trap_item->trap);
+ if (err)
+ goto nla_put_failure;
+
+ err = devlink_trap_stats_put(msg, trap_item->stats);
+ if (err)
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct netlink_ext_ack *extack = info->extack;
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_trap_item *trap_item;
+ struct sk_buff *msg;
+ int err;
+
+ if (list_empty(&devlink->trap_list))
+ return -EOPNOTSUPP;
+
+ trap_item = devlink_trap_item_get_from_info(devlink, info);
+ if (!trap_item) {
+ NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap");
+ return -ENOENT;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_trap_fill(msg, devlink, trap_item,
+ DEVLINK_CMD_TRAP_NEW, info->snd_portid,
+ info->snd_seq, 0);
+ if (err)
+ goto err_trap_fill;
+
+ return genlmsg_reply(msg, info);
+
+err_trap_fill:
+ nlmsg_free(msg);
+ return err;
+}
+
+static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_trap_item *trap_item;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ int idx = 0;
+ int err;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(trap_item, &devlink->trap_list, list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_trap_fill(msg, devlink, trap_item,
+ DEVLINK_CMD_TRAP_NEW,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI);
+ if (err) {
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+static int __devlink_trap_action_set(struct devlink *devlink,
+ struct devlink_trap_item *trap_item,
+ enum devlink_trap_action trap_action,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ if (trap_item->action != trap_action &&
+ trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) {
+ NL_SET_ERR_MSG_MOD(extack, "Cannot change action of non-drop traps. Skipping");
+ return 0;
+ }
+
+ err = devlink->ops->trap_action_set(devlink, trap_item->trap,
+ trap_action);
+ if (err)
+ return err;
+
+ trap_item->action = trap_action;
+
+ return 0;
+}
+
+static int devlink_trap_action_set(struct devlink *devlink,
+ struct devlink_trap_item *trap_item,
+ struct genl_info *info)
+{
+ enum devlink_trap_action trap_action;
+ int err;
+
+ if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION])
+ return 0;
+
+ err = devlink_trap_action_get_from_info(info, &trap_action);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action");
+ return -EINVAL;
+ }
+
+ return __devlink_trap_action_set(devlink, trap_item, trap_action,
+ info->extack);
+}
+
+static void devlink_trap_report_set(struct devlink *devlink,
+ struct devlink_trap_item *trap_item,
+ struct genl_info *info)
+{
+ bool report;
+
+ if (!info->attrs[DEVLINK_ATTR_TRAP_REPORT_ENABLED])
+ return;
+
+ report = !!nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_REPORT_ENABLED]);
+ trap_item->report = report;
+}
+
+static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct netlink_ext_ack *extack = info->extack;
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_trap_item *trap_item;
+ int err;
+
+ if (list_empty(&devlink->trap_list))
+ return -EOPNOTSUPP;
+
+ trap_item = devlink_trap_item_get_from_info(devlink, info);
+ if (!trap_item) {
+ NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap");
+ return -ENOENT;
+ }
+
+ err = devlink_trap_action_set(devlink, trap_item, info);
+ if (err)
+ return err;
+
+ devlink_trap_report_set(devlink, trap_item, info);
+
+ return 0;
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_lookup(struct devlink *devlink, const char *name)
+{
+ struct devlink_trap_group_item *group_item;
+
+ list_for_each_entry(group_item, &devlink->trap_group_list, list) {
+ if (!strcmp(group_item->group->name, name))
+ return group_item;
+ }
+
+ return NULL;
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_get_from_info(struct devlink *devlink,
+ struct genl_info *info)
+{
+ char *name;
+
+ if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME])
+ return NULL;
+ name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]);
+
+ return devlink_trap_group_item_lookup(devlink, name);
+}
+
+static int
+devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink,
+ const struct devlink_trap_group_item *group_item,
+ enum devlink_command cmd, u32 portid, u32 seq,
+ int flags)
+{
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto nla_put_failure;
+
+ if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
+ group_item->group->name))
+ goto nla_put_failure;
+
+ if (group_item->group->generic &&
+ nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC))
+ goto nla_put_failure;
+
+ err = devlink_trap_stats_put(msg, group_item->stats);
+ if (err)
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct netlink_ext_ack *extack = info->extack;
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_trap_group_item *group_item;
+ struct sk_buff *msg;
+ int err;
+
+ if (list_empty(&devlink->trap_group_list))
+ return -EOPNOTSUPP;
+
+ group_item = devlink_trap_group_item_get_from_info(devlink, info);
+ if (!group_item) {
+ NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group");
+ return -ENOENT;
+ }
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ err = devlink_nl_trap_group_fill(msg, devlink, group_item,
+ DEVLINK_CMD_TRAP_GROUP_NEW,
+ info->snd_portid, info->snd_seq, 0);
+ if (err)
+ goto err_trap_group_fill;
+
+ return genlmsg_reply(msg, info);
+
+err_trap_group_fill:
+ nlmsg_free(msg);
+ return err;
+}
+
+static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ enum devlink_command cmd = DEVLINK_CMD_TRAP_GROUP_NEW;
+ struct devlink_trap_group_item *group_item;
+ u32 portid = NETLINK_CB(cb->skb).portid;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ int idx = 0;
+ int err;
+
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ continue;
+ mutex_lock(&devlink->lock);
+ list_for_each_entry(group_item, &devlink->trap_group_list,
+ list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ err = devlink_nl_trap_group_fill(msg, devlink,
+ group_item, cmd,
+ portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI);
+ if (err) {
+ mutex_unlock(&devlink->lock);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->lock);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+static int
+__devlink_trap_group_action_set(struct devlink *devlink,
+ struct devlink_trap_group_item *group_item,
+ enum devlink_trap_action trap_action,
+ struct netlink_ext_ack *extack)
+{
+ const char *group_name = group_item->group->name;
+ struct devlink_trap_item *trap_item;
+ int err;
+
+ list_for_each_entry(trap_item, &devlink->trap_list, list) {
+ if (strcmp(trap_item->trap->group.name, group_name))
+ continue;
+ err = __devlink_trap_action_set(devlink, trap_item,
+ trap_action, extack);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int
+devlink_trap_group_action_set(struct devlink *devlink,
+ struct devlink_trap_group_item *group_item,
+ struct genl_info *info)
+{
+ enum devlink_trap_action trap_action;
+ int err;
+
+ if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION])
+ return 0;
+
+ err = devlink_trap_action_get_from_info(info, &trap_action);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action");
+ return -EINVAL;
+ }
+
+ err = __devlink_trap_group_action_set(devlink, group_item, trap_action,
+ info->extack);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static void
+__devlink_trap_group_report_set(struct devlink *devlink,
+ struct devlink_trap_group_item *group_item,
+ bool report)
+{
+ const char *group_name = group_item->group->name;
+ struct devlink_trap_item *trap_item;
+
+ list_for_each_entry(trap_item, &devlink->trap_list, list) {
+ if (strcmp(trap_item->trap->group.name, group_name))
+ continue;
+ trap_item->report = report;
+ }
+}
+
+static void
+devlink_trap_group_report_set(struct devlink *devlink,
+ struct devlink_trap_group_item *group_item,
+ struct genl_info *info)
+{
+ bool report;
+
+ if (!info->attrs[DEVLINK_ATTR_TRAP_REPORT_ENABLED])
+ return;
+
+ report = !!nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_REPORT_ENABLED]);
+ __devlink_trap_group_report_set(devlink, group_item, report);
+}
+
+static int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct netlink_ext_ack *extack = info->extack;
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_trap_group_item *group_item;
+ int err;
+
+ if (list_empty(&devlink->trap_group_list))
+ return -EOPNOTSUPP;
+
+ group_item = devlink_trap_group_item_get_from_info(devlink, info);
+ if (!group_item) {
+ NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group");
+ return -ENOENT;
+ }
+
+ err = devlink_trap_group_action_set(devlink, group_item, info);
+ if (err)
+ return err;
+
+ devlink_trap_group_report_set(devlink, group_item, info);
+
+ return 0;
+}
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -5176,6 +5797,10 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_TRAP_REPORT_ENABLED] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -5475,6 +6100,32 @@ static const struct genl_ops devlink_nl_ops[] = {
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_TRAP_GET,
+ .doit = devlink_nl_cmd_trap_get_doit,
+ .dumpit = devlink_nl_cmd_trap_get_dumpit,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_TRAP_SET,
+ .doit = devlink_nl_cmd_trap_set_doit,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_TRAP_GROUP_GET,
+ .doit = devlink_nl_cmd_trap_group_get_doit,
+ .dumpit = devlink_nl_cmd_trap_group_get_dumpit,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_TRAP_GROUP_SET,
+ .doit = devlink_nl_cmd_trap_group_set_doit,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
@@ -5520,6 +6171,8 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
INIT_LIST_HEAD(&devlink->param_list);
INIT_LIST_HEAD(&devlink->region_list);
INIT_LIST_HEAD(&devlink->reporter_list);
+ INIT_LIST_HEAD(&devlink->trap_list);
+ INIT_LIST_HEAD(&devlink->trap_group_list);
mutex_init(&devlink->lock);
mutex_init(&devlink->reporters_lock);
return devlink;
@@ -5566,6 +6219,8 @@ void devlink_free(struct devlink *devlink)
{
mutex_destroy(&devlink->reporters_lock);
mutex_destroy(&devlink->lock);
+ WARN_ON(!list_empty(&devlink->trap_group_list));
+ WARN_ON(!list_empty(&devlink->trap_list));
WARN_ON(!list_empty(&devlink->reporter_list));
WARN_ON(!list_empty(&devlink->region_list));
WARN_ON(!list_empty(&devlink->param_list));
@@ -5670,10 +6325,10 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port,
if (WARN_ON(!devlink_port->registered))
return;
devlink_port_type_warn_cancel(devlink_port);
- spin_lock(&devlink_port->type_lock);
+ spin_lock_bh(&devlink_port->type_lock);
devlink_port->type = type;
devlink_port->type_dev = type_dev;
- spin_unlock(&devlink_port->type_lock);
+ spin_unlock_bh(&devlink_port->type_lock);
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
@@ -6751,6 +7406,592 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
}
EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
+#define DEVLINK_TRAP(_id, _type) \
+ { \
+ .type = DEVLINK_TRAP_TYPE_##_type, \
+ .id = DEVLINK_TRAP_GENERIC_ID_##_id, \
+ .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \
+ }
+
+static const struct devlink_trap devlink_trap_generic[] = {
+};
+
+#define DEVLINK_TRAP_GROUP(_id) \
+ { \
+ .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \
+ .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \
+ }
+
+static const struct devlink_trap_group devlink_trap_group_generic[] = {
+};
+
+static int devlink_trap_generic_verify(const struct devlink_trap *trap)
+{
+ if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX)
+ return -EINVAL;
+
+ if (strcmp(trap->name, devlink_trap_generic[trap->id].name))
+ return -EINVAL;
+
+ if (trap->type != devlink_trap_generic[trap->id].type)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int devlink_trap_driver_verify(const struct devlink_trap *trap)
+{
+ int i;
+
+ if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) {
+ if (!strcmp(trap->name, devlink_trap_generic[i].name))
+ return -EEXIST;
+ }
+
+ return 0;
+}
+
+static int devlink_trap_verify(const struct devlink_trap *trap)
+{
+ if (!trap || !trap->name || !trap->group.name)
+ return -EINVAL;
+
+ if (trap->generic)
+ return devlink_trap_generic_verify(trap);
+ else
+ return devlink_trap_driver_verify(trap);
+}
+
+static int
+devlink_trap_group_generic_verify(const struct devlink_trap_group *group)
+{
+ if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX)
+ return -EINVAL;
+
+ if (strcmp(group->name, devlink_trap_group_generic[group->id].name))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int
+devlink_trap_group_driver_verify(const struct devlink_trap_group *group)
+{
+ int i;
+
+ if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) {
+ if (!strcmp(group->name, devlink_trap_group_generic[i].name))
+ return -EEXIST;
+ }
+
+ return 0;
+}
+
+static int devlink_trap_group_verify(const struct devlink_trap_group *group)
+{
+ if (group->generic)
+ return devlink_trap_group_generic_verify(group);
+ else
+ return devlink_trap_group_driver_verify(group);
+}
+
+static void
+devlink_trap_group_notify(struct devlink *devlink,
+ const struct devlink_trap_group_item *group_item,
+ enum devlink_command cmd)
+{
+ struct sk_buff *msg;
+ int err;
+
+ WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW &&
+ cmd != DEVLINK_CMD_TRAP_GROUP_DEL);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0,
+ 0);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_create(struct devlink *devlink,
+ const struct devlink_trap_group *group)
+{
+ struct devlink_trap_group_item *group_item;
+ int err;
+
+ err = devlink_trap_group_verify(group);
+ if (err)
+ return ERR_PTR(err);
+
+ group_item = kzalloc(sizeof(*group_item), GFP_KERNEL);
+ if (!group_item)
+ return ERR_PTR(-ENOMEM);
+
+ group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats);
+ if (!group_item->stats) {
+ err = -ENOMEM;
+ goto err_stats_alloc;
+ }
+
+ group_item->group = group;
+ refcount_set(&group_item->refcount, 1);
+
+ if (devlink->ops->trap_group_init) {
+ err = devlink->ops->trap_group_init(devlink, group);
+ if (err)
+ goto err_group_init;
+ }
+
+ list_add_tail(&group_item->list, &devlink->trap_group_list);
+ devlink_trap_group_notify(devlink, group_item,
+ DEVLINK_CMD_TRAP_GROUP_NEW);
+
+ return group_item;
+
+err_group_init:
+ free_percpu(group_item->stats);
+err_stats_alloc:
+ kfree(group_item);
+ return ERR_PTR(err);
+}
+
+static void
+devlink_trap_group_item_destroy(struct devlink *devlink,
+ struct devlink_trap_group_item *group_item)
+{
+ devlink_trap_group_notify(devlink, group_item,
+ DEVLINK_CMD_TRAP_GROUP_DEL);
+ list_del(&group_item->list);
+ free_percpu(group_item->stats);
+ kfree(group_item);
+}
+
+static struct devlink_trap_group_item *
+devlink_trap_group_item_get(struct devlink *devlink,
+ const struct devlink_trap_group *group)
+{
+ struct devlink_trap_group_item *group_item;
+
+ group_item = devlink_trap_group_item_lookup(devlink, group->name);
+ if (group_item) {
+ refcount_inc(&group_item->refcount);
+ return group_item;
+ }
+
+ return devlink_trap_group_item_create(devlink, group);
+}
+
+static void
+devlink_trap_group_item_put(struct devlink *devlink,
+ struct devlink_trap_group_item *group_item)
+{
+ if (!refcount_dec_and_test(&group_item->refcount))
+ return;
+
+ devlink_trap_group_item_destroy(devlink, group_item);
+}
+
+static int
+devlink_trap_item_group_link(struct devlink *devlink,
+ struct devlink_trap_item *trap_item)
+{
+ struct devlink_trap_group_item *group_item;
+
+ group_item = devlink_trap_group_item_get(devlink,
+ &trap_item->trap->group);
+ if (IS_ERR(group_item))
+ return PTR_ERR(group_item);
+
+ trap_item->group_item = group_item;
+
+ return 0;
+}
+
+static void
+devlink_trap_item_group_unlink(struct devlink *devlink,
+ struct devlink_trap_item *trap_item)
+{
+ devlink_trap_group_item_put(devlink, trap_item->group_item);
+}
+
+static void devlink_trap_notify(struct devlink *devlink,
+ const struct devlink_trap_item *trap_item,
+ enum devlink_command cmd)
+{
+ struct sk_buff *msg;
+ int err;
+
+ WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW &&
+ cmd != DEVLINK_CMD_TRAP_DEL);
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int
+devlink_trap_register(struct devlink *devlink,
+ const struct devlink_trap *trap, void *priv)
+{
+ struct devlink_trap_item *trap_item;
+ int err;
+
+ if (devlink_trap_item_lookup(devlink, trap->name))
+ return -EEXIST;
+
+ trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL);
+ if (!trap_item)
+ return -ENOMEM;
+
+ trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats);
+ if (!trap_item->stats) {
+ err = -ENOMEM;
+ goto err_stats_alloc;
+ }
+
+ trap_item->trap = trap;
+ trap_item->report = false;
+ trap_item->action = trap->init_action;
+ trap_item->priv = priv;
+
+ err = devlink_trap_item_group_link(devlink, trap_item);
+ if (err)
+ goto err_group_link;
+
+ err = devlink->ops->trap_init(devlink, trap, trap_item);
+ if (err)
+ goto err_trap_init;
+
+ list_add_tail(&trap_item->list, &devlink->trap_list);
+ devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW);
+
+ return 0;
+
+err_trap_init:
+ devlink_trap_item_group_unlink(devlink, trap_item);
+err_group_link:
+ free_percpu(trap_item->stats);
+err_stats_alloc:
+ kfree(trap_item);
+ return err;
+}
+
+static void devlink_trap_unregister(struct devlink *devlink,
+ const struct devlink_trap *trap)
+{
+ struct devlink_trap_item *trap_item;
+
+ trap_item = devlink_trap_item_lookup(devlink, trap->name);
+ if (WARN_ON_ONCE(!trap_item))
+ return;
+
+ devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL);
+ list_del(&trap_item->list);
+ if (devlink->ops->trap_fini)
+ devlink->ops->trap_fini(devlink, trap, trap_item);
+ devlink_trap_item_group_unlink(devlink, trap_item);
+ free_percpu(trap_item->stats);
+ kfree(trap_item);
+}
+
+static void devlink_trap_disable(struct devlink *devlink,
+ const struct devlink_trap *trap)
+{
+ struct devlink_trap_item *trap_item;
+
+ trap_item = devlink_trap_item_lookup(devlink, trap->name);
+ if (WARN_ON_ONCE(!trap_item))
+ return;
+
+ devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP);
+ trap_item->action = DEVLINK_TRAP_ACTION_DROP;
+}
+
+/**
+ * devlink_traps_register - Register packet traps with devlink.
+ * @devlink: devlink.
+ * @traps: Packet traps.
+ * @traps_count: Count of provided packet traps.
+ * @priv: Driver private information.
+ *
+ * Return: Non-zero value on failure.
+ */
+int devlink_traps_register(struct devlink *devlink,
+ const struct devlink_trap *traps,
+ size_t traps_count, void *priv)
+{
+ int i, err;
+
+ if (!devlink->ops->trap_init || !devlink->ops->trap_action_set)
+ return -EINVAL;
+
+ mutex_lock(&devlink->lock);
+ for (i = 0; i < traps_count; i++) {
+ const struct devlink_trap *trap = &traps[i];
+
+ err = devlink_trap_verify(trap);
+ if (err)
+ goto err_trap_verify;
+
+ err = devlink_trap_register(devlink, trap, priv);
+ if (err)
+ goto err_trap_register;
+ }
+ mutex_unlock(&devlink->lock);
+
+ return 0;
+
+err_trap_register:
+err_trap_verify:
+ for (i--; i >= 0; i--)
+ devlink_trap_unregister(devlink, &traps[i]);
+ mutex_unlock(&devlink->lock);
+ return err;
+}
+EXPORT_SYMBOL_GPL(devlink_traps_register);
+
+/**
+ * devlink_traps_unregister - Unregister packet traps from devlink.
+ * @devlink: devlink.
+ * @traps: Packet traps.
+ * @traps_count: Count of provided packet traps.
+ */
+void devlink_traps_unregister(struct devlink *devlink,
+ const struct devlink_trap *traps,
+ size_t traps_count)
+{
+ int i;
+
+ mutex_lock(&devlink->lock);
+ /* Make sure we do not have any packets in-flight while unregistering
+ * traps by disabling all of them and waiting for a grace period.
+ */
+ for (i = traps_count - 1; i >= 0; i--)
+ devlink_trap_disable(devlink, &traps[i]);
+ synchronize_rcu();
+ for (i = traps_count - 1; i >= 0; i--)
+ devlink_trap_unregister(devlink, &traps[i]);
+ mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_traps_unregister);
+
+static void
+devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats,
+ size_t skb_len)
+{
+ struct devlink_stats *stats;
+
+ stats = this_cpu_ptr(trap_stats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_bytes += skb_len;
+ stats->rx_packets++;
+ u64_stats_update_end(&stats->syncp);
+}
+
+static size_t devlink_nl_trap_in_port_size(void)
+{
+ /* DEVLINK_ATTR_TRAP_IN_PORT nest */
+ return nla_total_size(0) +
+ /* DEVLINK_ATTR_PORT_INDEX */
+ nla_total_size(sizeof(u32)) +
+ /* DEVLINK_ATTR_PORT_TYPE */
+ nla_total_size(sizeof(u16)) +
+ /* DEVLINK_ATTR_PORT_NETDEV_IFINDEX */
+ nla_total_size(sizeof(u32)) +
+ /* DEVLINK_ATTR_PORT_{NETDEV, IBDEV}_NAME */
+ nla_total_size(max_t(int, IFNAMSIZ, IB_DEVICE_NAME_MAX) + 1);
+}
+
+static size_t
+devlink_nl_trap_report_size(struct devlink *devlink,
+ const struct devlink_trap_item *trap_item,
+ size_t skb_len)
+{
+ size_t size = nlmsg_msg_size(GENL_HDRLEN + devlink_nl_family.hdrsize);
+ struct devlink_trap_group_item *group_item = trap_item->group_item;
+
+ return NLMSG_ALIGN(size) +
+ /* DEVLINK_ATTR_BUS_NAME */
+ nla_total_size(strlen(devlink->dev->bus->name) + 1) +
+ /* DEVLINK_ATTR_DEV_NAME */
+ nla_total_size(strlen(dev_name(devlink->dev)) + 1) +
+ /* DEVLINK_ATTR_TRAP_GROUP_NAME */
+ nla_total_size(strlen(group_item->group->name) + 1) +
+ /* DEVLINK_ATTR_TRAP_NAME */
+ nla_total_size(strlen(trap_item->trap->name) + 1) +
+ /* DEVLINK_ATTR_TRAP_TYPE */
+ nla_total_size(sizeof(u8)) +
+ /* DEVLINK_ATTR_TRAP_TIMESTAMP */
+ nla_total_size(sizeof(struct timespec)) +
+ /* DEVLINK_ATTR_TRAP_IN_PORT */
+ devlink_nl_trap_in_port_size() +
+ /* DEVLINK_ATTR_TRAP_PAYLOAD */
+ nla_total_size(skb_len);
+}
+
+static int
+devlink_nl_trap_report_in_port_put(struct sk_buff *msg,
+ const struct devlink_trap *trap,
+ struct devlink_port *in_devlink_port)
+{
+ struct nlattr *attr;
+
+ if (!(trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT))
+ return 0;
+
+ attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_IN_PORT);
+ if (!attr)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, in_devlink_port->index))
+ goto nla_put_failure;
+
+ spin_lock(&in_devlink_port->type_lock);
+
+ if (devlink_nl_port_type_fill(msg, in_devlink_port))
+ goto unlock_nla_put_failure;
+
+ spin_unlock(&in_devlink_port->type_lock);
+
+ nla_nest_end(msg, attr);
+
+ return 0;
+
+unlock_nla_put_failure:
+ spin_unlock(&in_devlink_port->type_lock);
+nla_put_failure:
+ nla_nest_cancel(msg, attr);
+ return -EMSGSIZE;
+}
+
+static int
+devlink_nl_trap_report_fill(struct sk_buff *msg, struct devlink *devlink,
+ const struct devlink_trap_item *trap_item,
+ struct sk_buff *skb,
+ struct devlink_port *in_devlink_port)
+{
+ struct devlink_trap_group_item *group_item = trap_item->group_item;
+ struct timespec ts = ktime_to_timespec(ktime_get_real());
+ const struct devlink_trap *trap = trap_item->trap;
+ struct nlattr *attr;
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0,
+ DEVLINK_CMD_TRAP_REPORT);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto nla_put_failure;
+
+ if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME,
+ group_item->group->name))
+ goto nla_put_failure;
+
+ if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap->name))
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap->type))
+ goto nla_put_failure;
+
+ if (nla_put(msg, DEVLINK_ATTR_TRAP_TIMESTAMP, sizeof(ts), &ts))
+ goto nla_put_failure;
+
+ err = devlink_nl_trap_report_in_port_put(msg, trap, in_devlink_port);
+ if (err)
+ goto nla_put_failure;
+
+ attr = skb_put(msg, nla_total_size(skb->len));
+ attr->nla_type = DEVLINK_ATTR_TRAP_PAYLOAD;
+ attr->nla_len = nla_attr_size(skb->len);
+ if (skb_copy_bits(skb, 0, nla_data(attr), skb->len))
+ goto nla_put_failure;
+
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+/**
+ * devlink_trap_report - Report trapped packet to user space.
+ * @devlink: devlink.
+ * @skb: Trapped packet.
+ * @trap_ctx: Trap context.
+ * @in_devlink_port: Input devlink port.
+ */
+void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
+ void *trap_ctx, struct devlink_port *in_devlink_port)
+{
+ struct devlink_trap_item *trap_item = trap_ctx;
+ struct sk_buff *msg;
+ int err;
+
+ devlink_trap_stats_update(trap_item->stats, skb->len);
+ devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
+
+ if (!trap_item->report)
+ return;
+
+ msg = nlmsg_new(devlink_nl_trap_report_size(devlink, trap_item,
+ skb->len), GFP_ATOMIC);
+ if (!msg)
+ return;
+
+ err = devlink_nl_trap_report_fill(msg, devlink, trap_item, skb,
+ in_devlink_port);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_TRAP, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(devlink_trap_report);
+
+/**
+ * devlink_trap_ctx_priv - Trap context to driver private information.
+ * @trap_ctx: Trap context.
+ *
+ * Return: Driver private information passed during registration.
+ */
+void *devlink_trap_ctx_priv(void *trap_ctx)
+{
+ struct devlink_trap_item *trap_item = trap_ctx;
+
+ return trap_item->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv);
+
static void __devlink_compat_running_version(struct devlink *devlink,
char *buf, size_t len)
{
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 01/11] devlink: Create helper to fill port type information
From: Ido Schimmel @ 2019-07-07 7:58 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
The function that fills port attributes in a netlink message fills the
port type attributes together with other attributes such as the device
handle.
The port type attributes will also need to be filled for trapped packets
by a subsequent patch.
Prevent code duplication and create a helper that can be used from both
places.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/core/devlink.c | 49 +++++++++++++++++++++++++++-------------------
1 file changed, 29 insertions(+), 20 deletions(-)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 89c533778135..755a9a32015e 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -527,6 +527,33 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
return 0;
}
+static int devlink_nl_port_type_fill(struct sk_buff *msg,
+ const struct devlink_port *devlink_port)
+{
+ if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
+ return -EMSGSIZE;
+
+ if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
+ struct net_device *netdev = devlink_port->type_dev;
+
+ if (netdev &&
+ (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
+ netdev->ifindex) ||
+ nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
+ netdev->name)))
+ return -EMSGSIZE;
+ } else if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
+ struct ib_device *ibdev = devlink_port->type_dev;
+
+ if (ibdev &&
+ nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,
+ ibdev->name))
+ return -EMSGSIZE;
+ }
+
+ return 0;
+}
+
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_port *devlink_port,
enum devlink_command cmd, u32 portid,
@@ -544,30 +571,12 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
goto nla_put_failure;
spin_lock(&devlink_port->type_lock);
- if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
- goto nla_put_failure_type_locked;
if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&
nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,
devlink_port->desired_type))
goto nla_put_failure_type_locked;
- if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
- struct net_device *netdev = devlink_port->type_dev;
-
- if (netdev &&
- (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
- netdev->ifindex) ||
- nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
- netdev->name)))
- goto nla_put_failure_type_locked;
- }
- if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
- struct ib_device *ibdev = devlink_port->type_dev;
-
- if (ibdev &&
- nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,
- ibdev->name))
- goto nla_put_failure_type_locked;
- }
+ if (devlink_nl_port_type_fill(msg, devlink_port))
+ goto nla_put_failure_type_locked;
spin_unlock(&devlink_port->type_lock);
if (devlink_nl_port_attrs_put(msg, devlink_port))
goto nla_put_failure;
--
2.20.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox