* [patch net-next v2 4/9] net: sched: cls_flower: change fl_init_dissector to accept mask and dissector
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
This function is going to be used for templates as well, so we need to
pass the pointer separately.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_flower.c | 39 ++++++++++++++++++++-------------------
1 file changed, 20 insertions(+), 19 deletions(-)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0e8991e49860..0f753260594d 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -795,47 +795,48 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask)
FL_KEY_SET(keys, cnt, id, member); \
} while(0);
-static void fl_init_dissector(struct fl_flow_mask *mask)
+static void fl_init_dissector(struct flow_dissector *dissector,
+ struct fl_flow_key *mask)
{
struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
size_t cnt = 0;
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_PORTS, tp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IP, ip);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_TCP, tcp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ICMP, icmp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ARP, arp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_MPLS, mpls);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_VLAN, vlan);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
- if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) ||
- FL_KEY_IS_MASKED(&mask->key, enc_ipv6))
+ if (FL_KEY_IS_MASKED(mask, enc_ipv4) ||
+ FL_KEY_IS_MASKED(mask, enc_ipv6))
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
enc_control);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
- skb_flow_dissector_init(&mask->dissector, keys, cnt);
+ skb_flow_dissector_init(dissector, keys, cnt);
}
static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
@@ -854,7 +855,7 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
if (err)
goto errout_free;
- fl_init_dissector(newmask);
+ fl_init_dissector(&newmask->dissector, &newmask->key);
INIT_LIST_HEAD_RCU(&newmask->filters);
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 5/9] net: sched: cls_flower: implement chain templates
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Use the previously introduced template extension and implement
callback to create, destroy and dump chain template. The existing
parsing and dumping functions are re-used. Also, check if newly added
filters fit the template if it is set.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
v1->v2:
- rebase on top of the reoffload pathset
---
net/sched/cls_flower.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 106 insertions(+), 1 deletion(-)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0f753260594d..8bcd40756a2d 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -70,6 +70,13 @@ struct fl_flow_mask {
struct list_head list;
};
+struct fl_flow_tmplt {
+ struct fl_flow_key dummy_key;
+ struct fl_flow_key mask;
+ struct flow_dissector dissector;
+ struct tcf_chain *chain;
+};
+
struct cls_fl_head {
struct rhashtable ht;
struct list_head masks;
@@ -145,6 +152,23 @@ static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key,
*lmkey++ = *lkey++ & *lmask++;
}
+static bool fl_mask_fits_tmplt(struct fl_flow_tmplt *tmplt,
+ struct fl_flow_mask *mask)
+{
+ const long *lmask = fl_key_get_start(&mask->key, mask);
+ const long *ltmplt;
+ int i;
+
+ if (!tmplt)
+ return true;
+ ltmplt = fl_key_get_start(&tmplt->mask, mask);
+ for (i = 0; i < fl_mask_range(mask); i += sizeof(long)) {
+ if (~*ltmplt++ & *lmask++)
+ return false;
+ }
+ return true;
+}
+
static void fl_clear_masked_range(struct fl_flow_key *key,
struct fl_flow_mask *mask)
{
@@ -904,6 +928,7 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
struct cls_fl_filter *f, struct fl_flow_mask *mask,
unsigned long base, struct nlattr **tb,
struct nlattr *est, bool ovr,
+ struct fl_flow_tmplt *tmplt,
struct netlink_ext_ack *extack)
{
int err;
@@ -924,6 +949,11 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
fl_mask_update_range(mask);
fl_set_masked_key(&f->mkey, &f->key, mask);
+ if (!fl_mask_fits_tmplt(tmplt, mask)) {
+ NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template");
+ return -EINVAL;
+ }
+
return 0;
}
@@ -934,6 +964,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct fl_flow_tmplt *tmplt = tmplt_priv;
struct cls_fl_filter *fold = *arg;
struct cls_fl_filter *fnew;
struct nlattr **tb;
@@ -990,7 +1021,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
}
err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr,
- extack);
+ tmplt, extack);
if (err)
goto errout_idr;
@@ -1132,6 +1163,52 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
return 0;
}
+static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
+ struct nlattr **tca,
+ struct netlink_ext_ack *extack)
+{
+ struct fl_flow_tmplt *tmplt;
+ struct nlattr **tb;
+ int err;
+
+ if (!tca[TCA_OPTIONS])
+ return ERR_PTR(-EINVAL);
+
+ tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
+ if (!tb)
+ return ERR_PTR(-ENOBUFS);
+ err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
+ fl_policy, NULL);
+ if (err)
+ goto errout_tb;
+
+ tmplt = kzalloc(sizeof(*tmplt), GFP_KERNEL);
+ if (!tmplt)
+ goto errout_tb;
+ tmplt->chain = chain;
+ err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack);
+ if (err)
+ goto errout_tmplt;
+ kfree(tb);
+
+ fl_init_dissector(&tmplt->dissector, &tmplt->mask);
+
+ return tmplt;
+
+errout_tmplt:
+ kfree(tmplt);
+errout_tb:
+ kfree(tb);
+ return ERR_PTR(err);
+}
+
+static void fl_tmplt_destroy(void *tmplt_priv)
+{
+ struct fl_flow_tmplt *tmplt = tmplt_priv;
+
+ kfree(tmplt);
+}
+
static int fl_dump_key_val(struct sk_buff *skb,
void *val, int val_type,
void *mask, int mask_type, int len)
@@ -1478,6 +1555,31 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
return -1;
}
+static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv)
+{
+ struct fl_flow_tmplt *tmplt = tmplt_priv;
+ struct fl_flow_key *key, *mask;
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ key = &tmplt->dummy_key;
+ mask = &tmplt->mask;
+
+ if (fl_dump_key(skb, net, key, mask))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+
+ return skb->len;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
+}
+
static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
{
struct cls_fl_filter *f = fh;
@@ -1498,6 +1600,9 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {
.reoffload = fl_reoffload,
.dump = fl_dump,
.bind_class = fl_bind_class,
+ .tmplt_create = fl_tmplt_create,
+ .tmplt_destroy = fl_tmplt_destroy,
+ .tmplt_dump = fl_tmplt_dump,
.owner = THIS_MODULE,
};
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 6/9] net: sched: cls_flower: propagate chain teplate creation and destruction to drivers
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Introduce a couple of flower offload commands in order to propagate
template creation/destruction events down to device drivers.
Drivers may use this information to prepare HW in an optimal way
for future filter insertions.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
v1->v2:
- remove leftover extack arg in fl_hw_create_tmplt()
- rebase on top of the reoffload pathset
---
include/net/pkt_cls.h | 2 ++
net/sched/cls_flower.c | 39 +++++++++++++++++++++++++++++++++++++++
2 files changed, 41 insertions(+)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 4070b8eb6d14..ce671ca5d331 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -720,6 +720,8 @@ enum tc_fl_command {
TC_CLSFLOWER_REPLACE,
TC_CLSFLOWER_DESTROY,
TC_CLSFLOWER_STATS,
+ TC_CLSFLOWER_TMPLT_CREATE,
+ TC_CLSFLOWER_TMPLT_DESTROY,
};
struct tc_cls_flower_offload {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 8bcd40756a2d..f827356bb2cb 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1163,6 +1163,42 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
return 0;
}
+static void fl_hw_create_tmplt(struct tcf_chain *chain,
+ struct fl_flow_tmplt *tmplt)
+{
+ struct tc_cls_flower_offload cls_flower = {};
+ struct tcf_block *block = chain->block;
+ struct tcf_exts dummy_exts = { 0, };
+
+ cls_flower.common.chain_index = chain->index;
+ cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE;
+ cls_flower.cookie = (unsigned long) tmplt;
+ cls_flower.dissector = &tmplt->dissector;
+ cls_flower.mask = &tmplt->mask;
+ cls_flower.key = &tmplt->dummy_key;
+ cls_flower.exts = &dummy_exts;
+
+ /* We don't care if driver (any of them) fails to handle this
+ * call. It serves just as a hint for it.
+ */
+ tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
+ &cls_flower, false);
+}
+
+static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
+ struct fl_flow_tmplt *tmplt)
+{
+ struct tc_cls_flower_offload cls_flower = {};
+ struct tcf_block *block = chain->block;
+
+ cls_flower.common.chain_index = chain->index;
+ cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY;
+ cls_flower.cookie = (unsigned long) tmplt;
+
+ tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
+ &cls_flower, false);
+}
+
static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
struct nlattr **tca,
struct netlink_ext_ack *extack)
@@ -1193,6 +1229,8 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
fl_init_dissector(&tmplt->dissector, &tmplt->mask);
+ fl_hw_create_tmplt(chain, tmplt);
+
return tmplt;
errout_tmplt:
@@ -1206,6 +1244,7 @@ static void fl_tmplt_destroy(void *tmplt_priv)
{
struct fl_flow_tmplt *tmplt = tmplt_priv;
+ fl_hw_destroy_tmplt(tmplt->chain, tmplt);
kfree(tmplt);
}
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 7/9] mlxsw: spectrum: Implement chain template hinting
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Since cld_flower provides information about the filter template for
specific chain, use this information in order to prepare a region.
Use the template to find out what elements are going to be used
and pass that down to mlxsw_sp_acl_tcam_group_add(). Later on, when the
first filter is inserted, the mlxsw_sp_acl_tcam_group_use_patterns()
function would use this element usage information instead of looking
up a pattern.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 5 +++
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 12 +++++-
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 12 ++++--
.../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 25 ++++++++++--
.../net/ethernet/mellanox/mlxsw/spectrum_flower.c | 44 ++++++++++++++++++++--
5 files changed, 86 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 52437363766a..155db238e65a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1441,6 +1441,11 @@ mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_acl_block *acl_block,
return 0;
case TC_CLSFLOWER_STATS:
return mlxsw_sp_flower_stats(mlxsw_sp, acl_block, f);
+ case TC_CLSFLOWER_TMPLT_CREATE:
+ return mlxsw_sp_flower_tmplt_create(mlxsw_sp, acl_block, f);
+ case TC_CLSFLOWER_TMPLT_DESTROY:
+ mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, acl_block, f);
+ return 0;
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4a519d8edec8..b0a8e611e730 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -459,7 +459,8 @@ enum mlxsw_sp_acl_profile {
struct mlxsw_sp_acl_profile_ops {
size_t ruleset_priv_size;
int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
- void *priv, void *ruleset_priv);
+ void *priv, void *ruleset_priv,
+ struct mlxsw_afk_element_usage *tmplt_elusage);
void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
struct mlxsw_sp_port *mlxsw_sp_port,
@@ -514,7 +515,8 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_ruleset *
mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_block *block, u32 chain_index,
- enum mlxsw_sp_acl_profile profile);
+ enum mlxsw_sp_acl_profile profile,
+ struct mlxsw_afk_element_usage *tmplt_elusage);
void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_ruleset *ruleset);
u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset);
@@ -594,6 +596,12 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_block *block,
struct tc_cls_flower_offload *f);
+int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_block *block,
+ struct tc_cls_flower_offload *f);
+void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_block *block,
+ struct tc_cls_flower_offload *f);
/* spectrum_qdisc.c */
int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 79b1fa27a9a4..ea42605c451d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -319,7 +319,8 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_acl_ruleset *
mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_block *block, u32 chain_index,
- const struct mlxsw_sp_acl_profile_ops *ops)
+ const struct mlxsw_sp_acl_profile_ops *ops,
+ struct mlxsw_afk_element_usage *tmplt_elusage)
{
struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
struct mlxsw_sp_acl_ruleset *ruleset;
@@ -339,7 +340,8 @@ mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
if (err)
goto err_rhashtable_init;
- err = ops->ruleset_add(mlxsw_sp, acl->priv, ruleset->priv);
+ err = ops->ruleset_add(mlxsw_sp, acl->priv, ruleset->priv,
+ tmplt_elusage);
if (err)
goto err_ops_ruleset_add;
@@ -421,7 +423,8 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_ruleset *
mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_block *block, u32 chain_index,
- enum mlxsw_sp_acl_profile profile)
+ enum mlxsw_sp_acl_profile profile,
+ struct mlxsw_afk_element_usage *tmplt_elusage)
{
const struct mlxsw_sp_acl_profile_ops *ops;
struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
@@ -436,7 +439,8 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_acl_ruleset_ref_inc(ruleset);
return ruleset;
}
- return mlxsw_sp_acl_ruleset_create(mlxsw_sp, block, chain_index, ops);
+ return mlxsw_sp_acl_ruleset_create(mlxsw_sp, block, chain_index, ops,
+ tmplt_elusage);
}
void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index ad1b548e3cac..d6e4e00dfd3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -157,6 +157,8 @@ struct mlxsw_sp_acl_tcam_group {
struct mlxsw_sp_acl_tcam_group_ops *ops;
const struct mlxsw_sp_acl_tcam_pattern *patterns;
unsigned int patterns_count;
+ bool tmplt_elusage_set;
+ struct mlxsw_afk_element_usage tmplt_elusage;
};
struct mlxsw_sp_acl_tcam_region {
@@ -216,13 +218,19 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_tcam *tcam,
struct mlxsw_sp_acl_tcam_group *group,
const struct mlxsw_sp_acl_tcam_pattern *patterns,
- unsigned int patterns_count)
+ unsigned int patterns_count,
+ struct mlxsw_afk_element_usage *tmplt_elusage)
{
int err;
group->tcam = tcam;
group->patterns = patterns;
group->patterns_count = patterns_count;
+ if (tmplt_elusage) {
+ group->tmplt_elusage_set = true;
+ memcpy(&group->tmplt_elusage, tmplt_elusage,
+ sizeof(group->tmplt_elusage));
+ }
INIT_LIST_HEAD(&group->region_list);
err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
if (err)
@@ -431,6 +439,15 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
const struct mlxsw_sp_acl_tcam_pattern *pattern;
int i;
+ /* In case the template is set, we don't have to look up the pattern
+ * and just use the template.
+ */
+ if (group->tmplt_elusage_set) {
+ memcpy(out, &group->tmplt_elusage, sizeof(*out));
+ WARN_ON(!mlxsw_afk_element_usage_subset(elusage, out));
+ return;
+ }
+
for (i = 0; i < group->patterns_count; i++) {
pattern = &group->patterns[i];
mlxsw_afk_element_usage_fill(out, pattern->elements,
@@ -1019,14 +1036,16 @@ struct mlxsw_sp_acl_tcam_flower_rule {
static int
mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
- void *priv, void *ruleset_priv)
+ void *priv, void *ruleset_priv,
+ struct mlxsw_afk_element_usage *tmplt_elusage)
{
struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
struct mlxsw_sp_acl_tcam *tcam = priv;
return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
mlxsw_sp_acl_tcam_patterns,
- MLXSW_SP_ACL_TCAM_PATTERNS_COUNT);
+ MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+ tmplt_elusage);
}
static void
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 89dbf569dff5..f34b410e5048 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -401,7 +401,7 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
f->common.chain_index,
- MLXSW_SP_ACL_PROFILE_FLOWER);
+ MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
if (IS_ERR(ruleset))
return PTR_ERR(ruleset);
@@ -445,7 +445,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
f->common.chain_index,
- MLXSW_SP_ACL_PROFILE_FLOWER);
+ MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
if (IS_ERR(ruleset))
return;
@@ -471,7 +471,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
f->common.chain_index,
- MLXSW_SP_ACL_PROFILE_FLOWER);
+ MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
if (WARN_ON(IS_ERR(ruleset)))
return -EINVAL;
@@ -493,3 +493,41 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
return err;
}
+
+int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_block *block,
+ struct tc_cls_flower_offload *f)
+{
+ struct mlxsw_sp_acl_ruleset *ruleset;
+ struct mlxsw_sp_acl_rule_info rulei;
+ int err;
+
+ memset(&rulei, 0, sizeof(rulei));
+ err = mlxsw_sp_flower_parse(mlxsw_sp, block, &rulei, f);
+ if (err)
+ return err;
+ ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
+ f->common.chain_index,
+ MLXSW_SP_ACL_PROFILE_FLOWER,
+ &rulei.values.elusage);
+ if (IS_ERR(ruleset))
+ return PTR_ERR(ruleset);
+ /* keep the reference to the ruleset */
+ return 0;
+}
+
+void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_block *block,
+ struct tc_cls_flower_offload *f)
+{
+ struct mlxsw_sp_acl_ruleset *ruleset;
+
+ ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
+ f->common.chain_index,
+ MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
+ if (IS_ERR(ruleset))
+ return;
+ /* put the reference to the ruleset kept in create */
+ mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+ mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+}
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 8/9] selftests: forwarding: move shblock tc support check to a separate helper
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
The shared block support is only needed for tc_shblock.sh. No need to
require that for other test.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
tools/testing/selftests/net/forwarding/lib.sh | 3 +++
tools/testing/selftests/net/forwarding/tc_shblocks.sh | 2 ++
2 files changed, 5 insertions(+)
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 1dfdf14894e2..df589ac1eac0 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -28,7 +28,10 @@ check_tc_version()
echo "SKIP: iproute2 too old; tc is missing JSON support"
exit 1
fi
+}
+check_tc_shblock_support()
+{
tc filter help 2>&1 | grep block &> /dev/null
if [[ $? -ne 0 ]]; then
echo "SKIP: iproute2 too old; tc is missing shared block support"
diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
index b5b917203815..9826a446e2c0 100755
--- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh
+++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
@@ -105,6 +105,8 @@ cleanup()
ip link set $swp2 address $swp2origmac
}
+check_tc_shblock_support
+
trap cleanup EXIT
setup_prepare
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 9/9] selftests: forwarding: add tests for TC chain templates
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Add basic sanity tests for TC chain templates.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
v1->v2:
- adjust to the userspace cmdline changes
---
tools/testing/selftests/net/forwarding/lib.sh | 9 ++
.../selftests/net/forwarding/tc_chaintemplates.sh | 160 +++++++++++++++++++++
2 files changed, 169 insertions(+)
create mode 100755 tools/testing/selftests/net/forwarding/tc_chaintemplates.sh
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index df589ac1eac0..20be128709b1 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -39,6 +39,15 @@ check_tc_shblock_support()
fi
}
+check_tc_chaintemplate_support()
+{
+ tc help 2>&1|grep chaintemplate &> /dev/null
+ if [[ $? -ne 0 ]]; then
+ echo "SKIP: iproute2 too old; tc is missing chain template support"
+ exit 1
+ fi
+}
+
if [[ "$(id -u)" -ne 0 ]]; then
echo "SKIP: need root privileges"
exit 0
diff --git a/tools/testing/selftests/net/forwarding/tc_chaintemplates.sh b/tools/testing/selftests/net/forwarding/tc_chaintemplates.sh
new file mode 100755
index 000000000000..fb47ea1e30e0
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_chaintemplates.sh
@@ -0,0 +1,160 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="template_create_destroy template_filter_fits \
+ template_create_nonempty template_destroy_nonempty"
+NUM_NETIFS=2
+source tc_common.sh
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/24
+ tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2 192.0.2.2/24
+}
+
+template_create_destroy()
+{
+ RET=0
+
+ tc chaintemplate add dev $h2 ingress protocol ip \
+ flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF
+ check_err $? "Failed to create template for default chain"
+
+ tc chaintemplate add dev $h2 ingress chain 1 protocol ip \
+ flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF
+ check_err $? "Failed to create template for chain 1"
+
+ tc chaintemplate del dev $h2 ingress
+ check_err $? "Failed to destroy template for default chain"
+
+ tc chaintemplate del dev $h2 ingress chain 1
+ check_err $? "Failed to destroy template for chain 1"
+
+ log_test "template create destroy"
+}
+
+template_filter_fits()
+{
+ RET=0
+
+ tc chaintemplate add dev $h2 ingress protocol ip \
+ flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+ tc chaintemplate add dev $h2 ingress chain 1 protocol ip \
+ flower src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 1101 \
+ flower dst_mac $h2mac action drop
+ check_err $? "Failed to insert filter which fits template"
+
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 1102 \
+ flower src_mac $h2mac action drop &> /dev/null
+ check_fail $? "Incorrectly succeded to insert filter which does not template"
+
+ tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \
+ flower src_mac $h2mac action drop
+ check_err $? "Failed to insert filter which fits template"
+
+ tc filter add dev $h2 ingress chain 1protocol ip pref 1 handle 1102 \
+ flower dst_mac $h2mac action drop &> /dev/null
+ check_fail $? "Incorrectly succeded to insert filter which does not template"
+
+ tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \
+ flower &> /dev/null
+ tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \
+ flower &> /dev/null
+
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 1102 \
+ flower &> /dev/null
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 1101 \
+ flower &> /dev/null
+
+ tc chaintemplate del dev $h2 ingress chain 1
+ tc chaintemplate del dev $h2 ingress
+
+ log_test "template filter fits"
+}
+
+template_create_nonempty()
+{
+ RET=0
+
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 1101 \
+ flower dst_mac $h2mac action drop
+ tc chaintemplate add dev $h2 ingress protocol ip \
+ flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+ check_fail $? "Incorrectly succeded to create template for non-empty chain"
+
+ tc chaintemplate del dev $h2 ingress &> /dev/null
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 1101 flower
+
+ log_test "template create non-empty"
+}
+
+template_destroy_nonempty()
+{
+ RET=0
+
+ tc chaintemplate add dev $h2 ingress protocol ip \
+ flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 1101 \
+ flower dst_mac $h2mac action drop
+
+ tc chaintemplate del dev $h2 ingress &> /dev/null
+ check_fail $? "Incorrectly succeded to destroy template for non-empty chain"
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 1101 flower
+ tc chaintemplate del dev $h2 ingress &> /dev/null
+ check_err $? "Failed to destroy template for empty chain"
+
+ log_test "template destroy non-empty"
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ h2=${NETIFS[p2]}
+ h1mac=$(mac_get $h1)
+ h2mac=$(mac_get $h2)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+check_tc_chaintemplate_support
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
--
2.14.4
^ permalink raw reply related
* [PATCH v3 net-next 0/5] Fixes coding style in xilinx_emaclite.c
From: Radhey Shyam Pandey @ 2018-06-28 13:11 UTC (permalink / raw)
To: davem, michal.simek, radhey.shyam.pandey, joe, andrew
Cc: netdev, linux-kernel, linux-arm-kernel
This patchset fixes checkpatch and kernel-doc warnings in
xilinx emaclite driver. No functional change.
Changes from v2:
-In 2/5 patch refactor if-else to make failure path return early.
-In 2/5 patch coalesce the format onto a single line and add the
missing space after the comma.
Radhey Shyam Pandey (5):
net: emaclite: Use __func__ instead of hardcoded name
net: emaclite: Simplify if-else statements
net: emaclite: update kernel-doc comments
net: emaclite: Fix block comments style
net: emaclite: Remove unnecessary spaces
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 112 ++++++++++++++-----------
1 files changed, 64 insertions(+), 48 deletions(-)
^ permalink raw reply
* [PATCH v3 net-next 1/5] net: emaclite: Use __func__ instead of hardcoded name
From: Radhey Shyam Pandey @ 2018-06-28 13:11 UTC (permalink / raw)
To: davem, michal.simek, radhey.shyam.pandey, joe, andrew
Cc: netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <1530191510-10310-1-git-send-email-radhey.shyam.pandey@xilinx.com>
Switch hardcoded function name with a reference to __func__ making
the code more maintainable. Address below checkpatch warning:
WARNING: Prefer using '"%s...", __func__' to using 'xemaclite_mdio_read',
this function's name, in a string
+ "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
WARNING: Prefer using '"%s...", __func__' to using 'xemaclite_mdio_write',
this function's name, in a string
+ "xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
Changes from v2:
- None
---
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 2a0c06e..0544134 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -757,7 +757,7 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
dev_dbg(&lp->ndev->dev,
- "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
+ "%s(phy_id=%i, reg=%x) == %x\n", __func__,
phy_id, reg, rc);
return rc;
@@ -780,7 +780,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
u32 ctrl_reg;
dev_dbg(&lp->ndev->dev,
- "xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
+ "%s(phy_id=%i, reg=%x, val=%x)\n", __func__,
phy_id, reg, val);
if (xemaclite_mdio_wait(lp))
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 2/5] net: emaclite: Simplify if-else statements
From: Radhey Shyam Pandey @ 2018-06-28 13:11 UTC (permalink / raw)
To: davem, michal.simek, radhey.shyam.pandey, joe, andrew
Cc: netdev, linux-kernel, linux-arm-kernel
In-Reply-To: <1530191510-10310-1-git-send-email-radhey.shyam.pandey@xilinx.com>
Remove else as it is not required with if doing a return.
It also coalesce the format onto a single line and add the
missing space after the comma. Fixes below checkpatch warning-
WARNING: else is not generally useful after a break or return
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
Changes from v2:
- Refactor to make failure path return early as suggested
by Joe Perches <joe@perches.com>
- Coalesce the format onto a single line as suggested by
by Joe Perches <joe@perches.com>
---
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 34 +++++++++++-------------
1 files changed, 16 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 0544134..b2c7afe 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -564,19 +564,18 @@ static void xemaclite_tx_handler(struct net_device *dev)
struct net_local *lp = netdev_priv(dev);
dev->stats.tx_packets++;
- if (lp->deferred_skb) {
- if (xemaclite_send_data(lp,
- (u8 *) lp->deferred_skb->data,
- lp->deferred_skb->len) != 0)
- return;
- else {
- dev->stats.tx_bytes += lp->deferred_skb->len;
- dev_kfree_skb_irq(lp->deferred_skb);
- lp->deferred_skb = NULL;
- netif_trans_update(dev); /* prevent tx timeout */
- netif_wake_queue(dev);
- }
- }
+ if (!lp->deferred_skb)
+ return;
+
+ if (xemaclite_send_data(lp, (u8 *) lp->deferred_skb->data,
+ lp->deferred_skb->len))
+ return;
+
+ dev->stats.tx_bytes += lp->deferred_skb->len;
+ dev_kfree_skb_irq(lp->deferred_skb);
+ lp->deferred_skb = NULL;
+ netif_trans_update(dev); /* prevent tx timeout */
+ netif_wake_queue(dev);
}
/**
@@ -1052,13 +1051,12 @@ static bool get_bool(struct platform_device *ofdev, const char *s)
{
u32 *p = (u32 *)of_get_property(ofdev->dev.of_node, s, NULL);
- if (p) {
- return (bool)*p;
- } else {
- dev_warn(&ofdev->dev, "Parameter %s not found,"
- "defaulting to false\n", s);
+ if (!p) {
+ dev_warn(&ofdev->dev, "Parameter %s not found, defaulting to false\n", s);
return false;
}
+
+ return (bool)*p;
}
static const struct net_device_ops xemaclite_netdev_ops;
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 3/5] net: emaclite: update kernel-doc comments
From: Radhey Shyam Pandey @ 2018-06-28 13:11 UTC (permalink / raw)
To: davem, michal.simek, radhey.shyam.pandey, joe, andrew
Cc: netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <1530191510-10310-1-git-send-email-radhey.shyam.pandey@xilinx.com>
This patch fixes below kernel-doc warnings:
Function parameter or member 'maxlen' not described in 'xemaclite_recv_data'
Function parameter or member 'address'not described in 'xemaclite_set_mac_address'
Excess function parameter 'addr' description in 'xemaclite_set_mac_address'
No description found for return value of 'xemaclite_interrupt'
No description found for return value of 'xemaclite_mdio_write'
Function parameter or member 'dev' not described in 'xemaclite_mdio_setup'
Excess function parameter 'ofdev' description in 'xemaclite_mdio_setup'
No description found for return value of 'xemaclite_open'
No description found for return value of 'xemaclite_close'
Excess function parameter 'match' description in 'xemaclite_of_probe'
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
---
Changes from v2:
- None
---
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 15 ++++++++++++---
1 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index b2c7afe..a17f0b6 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -369,6 +369,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
* xemaclite_recv_data - Receive a frame
* @drvdata: Pointer to the Emaclite device private data
* @data: Address where the data is to be received
+ * @maxlen: Maximum supported ethernet packet length
*
* This function is intended to be called from the interrupt context or
* with a wrapper which waits for the receive frame to be available.
@@ -488,7 +489,7 @@ static void xemaclite_update_address(struct net_local *drvdata,
/**
* xemaclite_set_mac_address - Set the MAC address for this device
* @dev: Pointer to the network device instance
- * @addr: Void pointer to the sockaddr structure
+ * @address: Void pointer to the sockaddr structure
*
* This function copies the HW address from the sockaddr strucutre to the
* net_device structure and updates the address in HW.
@@ -638,6 +639,8 @@ static void xemaclite_rx_handler(struct net_device *dev)
* @dev_id: Void pointer to the network device instance used as callback
* reference
*
+ * Return: IRQ_HANDLED
+ *
* This function handles the Tx and Rx interrupts of the EmacLite device.
*/
static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
@@ -771,6 +774,8 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
*
* This function waits till the device is ready to accept a new MDIO
* request and then writes the val to the MDIO Write Data register.
+ *
+ * Return: 0 upon success or a negative error upon failure
*/
static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
u16 val)
@@ -804,7 +809,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
/**
* xemaclite_mdio_setup - Register mii_bus for the Emaclite device
* @lp: Pointer to the Emaclite device private data
- * @ofdev: Pointer to OF device structure
+ * @dev: Pointer to OF device structure
*
* This function enables MDIO bus in the Emaclite device and registers a
* mii_bus.
@@ -904,6 +909,9 @@ static void xemaclite_adjust_link(struct net_device *ndev)
* This function sets the MAC address, requests an IRQ and enables interrupts
* for the Emaclite device and starts the Tx queue.
* It also connects to the phy device, if MDIO is included in Emaclite device.
+ *
+ * Return: 0 on success. -ENODEV, if PHY cannot be connected.
+ * Non-zero error value on failure.
*/
static int xemaclite_open(struct net_device *dev)
{
@@ -974,6 +982,8 @@ static int xemaclite_open(struct net_device *dev)
* This function stops the Tx queue, disables interrupts and frees the IRQ for
* the Emaclite device.
* It also disconnects the phy device associated with the Emaclite device.
+ *
+ * Return: 0, always.
*/
static int xemaclite_close(struct net_device *dev)
{
@@ -1064,7 +1074,6 @@ static bool get_bool(struct platform_device *ofdev, const char *s)
/**
* xemaclite_of_probe - Probe method for the Emaclite device.
* @ofdev: Pointer to OF device structure
- * @match: Pointer to the structure used for matching a device
*
* This function probes for the Emaclite device in the device tree.
* It initializes the driver data structure and the hardware, sets the MAC
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 4/5] net: emaclite: Fix block comments style
From: Radhey Shyam Pandey @ 2018-06-28 13:11 UTC (permalink / raw)
To: davem, michal.simek, radhey.shyam.pandey, joe, andrew
Cc: netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <1530191510-10310-1-git-send-email-radhey.shyam.pandey@xilinx.com>
This patch fixes below checkpatch warnings-
WARNING: Block comments use a trailing */ on a separate line
WARNING: Block comments use * on subsequent lines
WARNING: networking block comments don't use an empty /* line,
use /* Comment
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
---
Changes from v2:
- None
---
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 34 +++++++++++++++---------
1 files changed, 21 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index a17f0b6..f96c920 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -70,7 +70,8 @@
#define XEL_TSR_XMIT_IE_MASK 0x00000008 /* Tx interrupt enable bit */
#define XEL_TSR_XMIT_ACTIVE_MASK 0x80000000 /* Buffer is active, SW bit
* only. This is not documented
- * in the HW spec */
+ * in the HW spec
+ */
/* Define for programming the MAC address into the EmacLite */
#define XEL_TSR_PROG_MAC_ADDR (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_PROGRAM_MASK)
@@ -336,7 +337,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
drvdata->next_tx_buf_to_use ^= XEL_BUFFER_OFFSET;
} else if (drvdata->tx_ping_pong != 0) {
/* If the expected buffer is full, try the other buffer,
- * if it is configured in HW */
+ * if it is configured in HW
+ */
addr = (void __iomem __force *)((u32 __force)addr ^
XEL_BUFFER_OFFSET);
@@ -357,7 +359,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
/* Update the Tx Status Register to indicate that there is a
* frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
* is used by the interrupt handler to check whether a frame
- * has been transmitted */
+ * has been transmitted
+ */
reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
@@ -395,7 +398,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
/* The instance is out of sync, try other buffer if other
* buffer is configured, return 0 otherwise. If the instance is
* out of sync, do not update the 'next_rx_buf_to_use' since it
- * will correct on subsequent calls */
+ * will correct on subsequent calls
+ */
if (drvdata->rx_ping_pong != 0)
addr = (void __iomem __force *)((u32 __force)addr ^
XEL_BUFFER_OFFSET);
@@ -409,13 +413,15 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
return 0; /* No data was available */
}
- /* Get the protocol type of the ethernet frame that arrived */
+ /* Get the protocol type of the ethernet frame that arrived
+ */
proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
XEL_RPLR_LENGTH_MASK);
/* Check if received ethernet frame is a raw ethernet frame
- * or an IP packet or an ARP packet */
+ * or an IP packet or an ARP packet
+ */
if (proto_type > ETH_DATA_LEN) {
if (proto_type == ETH_P_IP) {
@@ -431,7 +437,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
length = XEL_ARP_PACKET_SIZE + ETH_HLEN + ETH_FCS_LEN;
else
/* Field contains type other than IP or ARP, use max
- * frame size and let user parse it */
+ * frame size and let user parse it
+ */
length = ETH_FRAME_LEN + ETH_FCS_LEN;
} else
/* Use the length in the frame, plus the header and trailer */
@@ -602,11 +609,11 @@ static void xemaclite_rx_handler(struct net_device *dev)
return;
}
- /*
- * A new skb should have the data halfword aligned, but this code is
+ /* A new skb should have the data halfword aligned, but this code is
* here just in case that isn't true. Calculate how many
* bytes we should reserve to get the data to start on a word
- * boundary */
+ * boundary
+ */
align = BUFFER_ALIGN(skb->data);
if (align)
skb_reserve(skb, align);
@@ -708,8 +715,8 @@ static int xemaclite_mdio_wait(struct net_local *lp)
unsigned long end = jiffies + 2;
/* wait for the MDIO interface to not be busy or timeout
- after some time.
- */
+ * after some time.
+ */
while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
XEL_MDIOCTRL_MDIOSTS_MASK) {
if (time_before_eq(end, jiffies)) {
@@ -1029,7 +1036,8 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev)
if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) {
/* If the Emaclite Tx buffer is busy, stop the Tx queue and
* defer the skb for transmission during the ISR, after the
- * current transmission is complete */
+ * current transmission is complete
+ */
netif_stop_queue(dev);
lp->deferred_skb = new_skb;
/* Take the time stamp now, since we can't do this in an ISR. */
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 5/5] net: emaclite: Remove unnecessary spaces
From: Radhey Shyam Pandey @ 2018-06-28 13:11 UTC (permalink / raw)
To: davem, michal.simek, radhey.shyam.pandey, joe, andrew
Cc: netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <1530191510-10310-1-git-send-email-radhey.shyam.pandey@xilinx.com>
This patch fixes below checkpatch checks-
CHECK: spaces preferred around that '*' (ctx:VxV)
CHECK: No space is necessary after a cast
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
---
Changes from v2:
- None
---
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 27 +++++++++++++------------
1 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index f96c920..42f1f51 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -95,11 +95,11 @@
-#define TX_TIMEOUT (60*HZ) /* Tx timeout is 60 seconds. */
+#define TX_TIMEOUT (60 * HZ) /* Tx timeout is 60 seconds. */
#define ALIGNMENT 4
/* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
-#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
+#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32)adr)) % ALIGNMENT)
#ifdef __BIG_ENDIAN
#define xemaclite_readl ioread32be
@@ -239,8 +239,8 @@ static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr,
/* Set up to output the remaining data */
align_buffer = 0;
- to_u8_ptr = (u8 *) &align_buffer;
- from_u8_ptr = (u8 *) from_u16_ptr;
+ to_u8_ptr = (u8 *)&align_buffer;
+ from_u8_ptr = (u8 *)from_u16_ptr;
/* Output the remaining data */
for (; length > 0; length--)
@@ -273,7 +273,7 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
u32 align_buffer;
from_u32_ptr = src_ptr;
- to_u16_ptr = (u16 *) dest_ptr;
+ to_u16_ptr = (u16 *)dest_ptr;
for (; length > 3; length -= 4) {
/* Copy each word into the temporary buffer */
@@ -289,9 +289,9 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
u8 *to_u8_ptr, *from_u8_ptr;
/* Set up to read the remaining data */
- to_u8_ptr = (u8 *) to_u16_ptr;
+ to_u8_ptr = (u8 *)to_u16_ptr;
align_buffer = *from_u32_ptr++;
- from_u8_ptr = (u8 *) &align_buffer;
+ from_u8_ptr = (u8 *)&align_buffer;
/* Read the remaining data */
for (; length > 0; length--)
@@ -351,7 +351,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
return -1; /* Buffer was full, return failure */
/* Write the frame to the buffer */
- xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
+ xemaclite_aligned_write(data, (u32 __force *)addr, byte_count);
xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
addr + XEL_TPLR_OFFSET);
@@ -448,7 +448,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
length = maxlen;
/* Read from the EmacLite device */
- xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
+ xemaclite_aligned_read((u32 __force *)(addr + XEL_RXBUFF_OFFSET),
data, length);
/* Acknowledge the frame */
@@ -479,7 +479,7 @@ static void xemaclite_update_address(struct net_local *drvdata,
/* Determine the expected Tx buffer address */
addr = drvdata->base_addr + drvdata->next_tx_buf_to_use;
- xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
+ xemaclite_aligned_write(address_ptr, (u32 __force *)addr, ETH_ALEN);
xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
@@ -572,10 +572,11 @@ static void xemaclite_tx_handler(struct net_device *dev)
struct net_local *lp = netdev_priv(dev);
dev->stats.tx_packets++;
+
if (!lp->deferred_skb)
return;
- if (xemaclite_send_data(lp, (u8 *) lp->deferred_skb->data,
+ if (xemaclite_send_data(lp, (u8 *)lp->deferred_skb->data,
lp->deferred_skb->len))
return;
@@ -620,7 +621,7 @@ static void xemaclite_rx_handler(struct net_device *dev)
skb_reserve(skb, 2);
- len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
+ len = xemaclite_recv_data(lp, (u8 *)skb->data, len);
if (!len) {
dev->stats.rx_errors++;
@@ -1033,7 +1034,7 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev)
new_skb = orig_skb;
spin_lock_irqsave(&lp->reset_lock, flags);
- if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) {
+ if (xemaclite_send_data(lp, (u8 *)new_skb->data, len) != 0) {
/* If the Emaclite Tx buffer is busy, stop the Tx queue and
* defer the skb for transmission during the ISR, after the
* current transmission is complete
--
1.7.1
^ permalink raw reply related
* [patch iproute2/net-next v2] tc: introduce support for chain templates
From: Jiri Pirko @ 2018-06-28 13:10 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
v1->v2:
- moved the template handling
from "tc filter template" to "tc chaintemplate"
---
include/uapi/linux/rtnetlink.h | 7 +++
man/man8/tc.8 | 26 ++++++++++
tc/tc.c | 5 +-
tc/tc_common.h | 1 +
tc/tc_filter.c | 106 ++++++++++++++++++++++++++++++-----------
tc/tc_monitor.c | 5 +-
6 files changed, 121 insertions(+), 29 deletions(-)
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index c3a7d8ecc7b9..dddb05e5cca8 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -150,6 +150,13 @@ enum {
RTM_NEWCACHEREPORT = 96,
#define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT
+ RTM_NEWCHAINTMPLT = 100,
+#define RTM_NEWCHAINTMPLT RTM_NEWCHAINTMPLT
+ RTM_DELCHAINTMPLT,
+#define RTM_DELCHAINTMPLT RTM_DELCHAINTMPLT
+ RTM_GETCHAINTMPLT,
+#define RTM_GETCHAINTMPLT RTM_GETCHAINTMPLT
+
__RTM_MAX,
#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1)
};
diff --git a/man/man8/tc.8 b/man/man8/tc.8
index 840880fbdba6..3eee1aceaae4 100644
--- a/man/man8/tc.8
+++ b/man/man8/tc.8
@@ -58,6 +58,22 @@ tc \- show / manipulate traffic control settings
.B flowid
\fIflow-id\fR
+.B tc
+.RI "[ " OPTIONS " ]"
+.B chaintemplate [ add | delete | get ] dev
+\fIDEV\fR
+.B [ parent
+\fIqdisc-id\fR
+.B | root ]\fR filtertype
+[ filtertype specific parameters ]
+
+.B tc
+.RI "[ " OPTIONS " ]"
+.B chaintemplate [ add | delete | get ] block
+\fIBLOCK_INDEX\fR filtertype
+[ filtertype specific parameters ]
+
+
.B tc
.RI "[ " OPTIONS " ]"
.RI "[ " FORMAT " ]"
@@ -80,6 +96,16 @@ tc \- show / manipulate traffic control settings
.RI "[ " OPTIONS " ]"
.B filter show block
\fIBLOCK_INDEX\fR
+.P
+.B tc
+.RI "[ " OPTIONS " ]"
+.B chaintemplate show dev
+\fIDEV\fR
+.P
+.B tc
+.RI "[ " OPTIONS " ]"
+.B chaintemplate show block
+\fIBLOCK_INDEX\fR
.P
.B tc
diff --git a/tc/tc.c b/tc/tc.c
index 0d223281ba25..8a0592c45800 100644
--- a/tc/tc.c
+++ b/tc/tc.c
@@ -197,7 +197,8 @@ static void usage(void)
fprintf(stderr,
"Usage: tc [ OPTIONS ] OBJECT { COMMAND | help }\n"
" tc [-force] -batch filename\n"
- "where OBJECT := { qdisc | class | filter | action | monitor | exec }\n"
+ "where OBJECT := { qdisc | class | filter | chaintemplate |\n"
+ " action | monitor | exec }\n"
" OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] | -r[aw] |\n"
" -o[neline] | -j[son] | -p[retty] | -c[olor]\n"
" -b[atch] [filename] | -n[etns] name |\n"
@@ -212,6 +213,8 @@ static int do_cmd(int argc, char **argv, void *buf, size_t buflen)
return do_class(argc-1, argv+1);
if (matches(*argv, "filter") == 0)
return do_filter(argc-1, argv+1, buf, buflen);
+ if (matches(*argv, "chaintemplate") == 0)
+ return do_chaintmplt(argc-1, argv+1, buf, buflen);
if (matches(*argv, "actions") == 0)
return do_action(argc-1, argv+1, buf, buflen);
if (matches(*argv, "monitor") == 0)
diff --git a/tc/tc_common.h b/tc/tc_common.h
index 49c24616c2c3..16cefe896109 100644
--- a/tc/tc_common.h
+++ b/tc/tc_common.h
@@ -8,6 +8,7 @@ extern struct rtnl_handle rth;
extern int do_qdisc(int argc, char **argv);
extern int do_class(int argc, char **argv);
extern int do_filter(int argc, char **argv, void *buf, size_t buflen);
+extern int do_chaintmplt(int argc, char **argv, void *buf, size_t buflen);
extern int do_action(int argc, char **argv, void *buf, size_t buflen);
extern int do_tcmonitor(int argc, char **argv);
extern int do_exec(int argc, char **argv);
diff --git a/tc/tc_filter.c b/tc/tc_filter.c
index c5bb0bffe19b..df0ce853fbcc 100644
--- a/tc/tc_filter.c
+++ b/tc/tc_filter.c
@@ -39,12 +39,21 @@ static void usage(void)
"\n"
" tc filter show [ dev STRING ] [ root | ingress | egress | parent CLASSID ]\n"
" tc filter show [ block BLOCK_INDEX ]\n"
+ " tc chaintemplate [ add | del | get | show ] [ dev STRING ]\n"
+ " tc chaintemplate [ add | del | get | show ] [ block BLOCK_INDEX ] ]\n"
"Where:\n"
"FILTER_TYPE := { rsvp | u32 | bpf | fw | route | etc. }\n"
"FILTERID := ... format depends on classifier, see there\n"
"OPTIONS := ... try tc filter add <desired FILTER_KIND> help\n");
}
+static void chaintmplt_usage(void)
+{
+ fprintf(stderr,
+ "Usage: tc chaintemplate [ add | del | get | show ] [ dev STRING ]\n"
+ " tc chaintemplate [ add | del | get | show ] [ block BLOCK_INDEX ] ]\n");
+}
+
struct tc_filter_req {
struct nlmsghdr n;
struct tcmsg t;
@@ -85,7 +94,8 @@ static int tc_filter_modify(int cmd, unsigned int flags, int argc, char **argv,
req->n.nlmsg_type = cmd;
req->t.tcm_family = AF_UNSPEC;
- if (cmd == RTM_NEWTFILTER && flags & NLM_F_CREATE)
+ if ((cmd == RTM_NEWTFILTER || cmd == RTM_NEWCHAINTMPLT) &&
+ flags & NLM_F_CREATE)
protocol = htons(ETH_P_ALL);
while (argc > 0) {
@@ -261,7 +271,10 @@ int print_filter(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
if (n->nlmsg_type != RTM_NEWTFILTER &&
n->nlmsg_type != RTM_GETTFILTER &&
- n->nlmsg_type != RTM_DELTFILTER) {
+ n->nlmsg_type != RTM_DELTFILTER &&
+ n->nlmsg_type != RTM_NEWCHAINTMPLT &&
+ n->nlmsg_type != RTM_GETCHAINTMPLT &&
+ n->nlmsg_type != RTM_DELCHAINTMPLT) {
fprintf(stderr, "Not a filter(cmd %d)\n", n->nlmsg_type);
return 0;
}
@@ -280,20 +293,26 @@ int print_filter(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
open_json_object(NULL);
- if (n->nlmsg_type == RTM_DELTFILTER)
+ if (n->nlmsg_type == RTM_DELTFILTER || n->nlmsg_type == RTM_DELCHAINTMPLT)
print_bool(PRINT_ANY, "deleted", "deleted ", true);
- if (n->nlmsg_type == RTM_NEWTFILTER &&
+ if ((n->nlmsg_type == RTM_NEWTFILTER ||
+ n->nlmsg_type == RTM_NEWCHAINTMPLT) &&
(n->nlmsg_flags & NLM_F_CREATE) &&
!(n->nlmsg_flags & NLM_F_EXCL))
print_bool(PRINT_ANY, "replaced", "replaced ", true);
- if (n->nlmsg_type == RTM_NEWTFILTER &&
+ if ((n->nlmsg_type == RTM_NEWTFILTER ||
+ n->nlmsg_type == RTM_NEWCHAINTMPLT) &&
(n->nlmsg_flags & NLM_F_CREATE) &&
(n->nlmsg_flags & NLM_F_EXCL))
print_bool(PRINT_ANY, "added", "added ", true);
- print_string(PRINT_FP, NULL, "filter ", NULL);
+ if (n->nlmsg_type == RTM_NEWTFILTER ||
+ n->nlmsg_type == RTM_DELTFILTER)
+ print_string(PRINT_FP, NULL, "filter ", NULL);
+ else
+ print_string(PRINT_FP, NULL, "chaintemplate ", NULL);
if (t->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
if (!filter_block_index ||
filter_block_index != t->tcm_block_index)
@@ -317,7 +336,9 @@ int print_filter(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
}
}
- if (t->tcm_info) {
+ if (t->tcm_info && (n->nlmsg_type == RTM_NEWTFILTER ||
+ n->nlmsg_type == RTM_DELTFILTER ||
+ n->nlmsg_type == RTM_GETTFILTER)) {
f_proto = TC_H_MIN(t->tcm_info);
__u32 prio = TC_H_MAJ(t->tcm_info)>>16;
@@ -496,17 +517,19 @@ static int tc_filter_get(int cmd, unsigned int flags, int argc, char **argv)
argc--; argv++;
}
- if (!protocol_set) {
- fprintf(stderr, "Must specify filter protocol\n");
- return -1;
- }
+ if (cmd == RTM_GETTFILTER) {
+ if (!protocol_set) {
+ fprintf(stderr, "Must specify filter protocol\n");
+ return -1;
+ }
- if (!prio) {
- fprintf(stderr, "Must specify filter priority\n");
- return -1;
- }
+ if (!prio) {
+ fprintf(stderr, "Must specify filter priority\n");
+ return -1;
+ }
- req.t.tcm_info = TC_H_MAKE(prio<<16, protocol);
+ req.t.tcm_info = TC_H_MAKE(prio<<16, protocol);
+ }
if (chain_index_set)
addattr32(&req.n, sizeof(req), TCA_CHAIN, chain_index);
@@ -516,11 +539,13 @@ static int tc_filter_get(int cmd, unsigned int flags, int argc, char **argv)
return -1;
}
- if (k[0])
- addattr_l(&req.n, sizeof(req), TCA_KIND, k, strlen(k)+1);
- else {
- fprintf(stderr, "Must specify filter type\n");
- return -1;
+ if (cmd == RTM_GETTFILTER) {
+ if (k[0])
+ addattr_l(&req.n, sizeof(req), TCA_KIND, k, strlen(k)+1);
+ else {
+ fprintf(stderr, "Must specify filter type\n");
+ return -1;
+ }
}
if (d[0]) {
@@ -539,10 +564,11 @@ static int tc_filter_get(int cmd, unsigned int flags, int argc, char **argv)
return -1;
}
- if (q->parse_fopt(q, fhandle, argc, argv, &req.n))
+ if (cmd == RTM_GETTFILTER &&
+ q->parse_fopt(q, fhandle, argc, argv, &req.n))
return 1;
- if (!fhandle) {
+ if (!fhandle && cmd == RTM_GETTFILTER) {
fprintf(stderr, "Must specify filter \"handle\"\n");
return -1;
}
@@ -569,7 +595,7 @@ static int tc_filter_get(int cmd, unsigned int flags, int argc, char **argv)
return 0;
}
-static int tc_filter_list(int argc, char **argv)
+static int tc_filter_list(int cmd, int argc, char **argv)
{
struct {
struct nlmsghdr n;
@@ -577,7 +603,7 @@ static int tc_filter_list(int argc, char **argv)
char buf[MAX_MSG];
} req = {
.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
- .n.nlmsg_type = RTM_GETTFILTER,
+ .n.nlmsg_type = cmd,
.t.tcm_parent = TC_H_UNSPEC,
.t.tcm_family = AF_UNSPEC,
};
@@ -725,7 +751,7 @@ static int tc_filter_list(int argc, char **argv)
int do_filter(int argc, char **argv, void *buf, size_t buflen)
{
if (argc < 1)
- return tc_filter_list(0, NULL);
+ return tc_filter_list(RTM_GETTFILTER, 0, NULL);
if (matches(*argv, "add") == 0)
return tc_filter_modify(RTM_NEWTFILTER, NLM_F_EXCL|NLM_F_CREATE,
argc-1, argv+1, buf, buflen);
@@ -742,7 +768,7 @@ int do_filter(int argc, char **argv, void *buf, size_t buflen)
return tc_filter_get(RTM_GETTFILTER, 0, argc-1, argv+1);
if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0
|| matches(*argv, "lst") == 0)
- return tc_filter_list(argc-1, argv+1);
+ return tc_filter_list(RTM_GETTFILTER, argc-1, argv+1);
if (matches(*argv, "help") == 0) {
usage();
return 0;
@@ -751,3 +777,29 @@ int do_filter(int argc, char **argv, void *buf, size_t buflen)
*argv);
return -1;
}
+
+int do_chaintmplt(int argc, char **argv, void *buf, size_t buflen)
+{
+ if (argc < 1)
+ return tc_filter_list(RTM_GETCHAINTMPLT, 0, NULL);
+ if (matches(*argv, "add") == 0) {
+ return tc_filter_modify(RTM_NEWCHAINTMPLT, NLM_F_EXCL | NLM_F_CREATE,
+ argc - 1, argv + 1, buf, buflen);
+ } else if (matches(*argv, "delete") == 0) {
+ return tc_filter_modify(RTM_DELCHAINTMPLT, 0,
+ argc - 1, argv + 1, buf, buflen);
+ } else if (matches(*argv, "get") == 0) {
+ return tc_filter_get(RTM_GETCHAINTMPLT, 0,
+ argc - 1, argv + 1);
+ } else if (matches(*argv, "list") == 0 || matches(*argv, "show") == 0 ||
+ matches(*argv, "lst") == 0) {
+ return tc_filter_list(RTM_GETCHAINTMPLT, argc - 1, argv + 1);
+ } else if (matches(*argv, "help") == 0) {
+ chaintmplt_usage();
+ return 0;
+ }
+ fprintf(stderr, "Command \"%s\" is unknown, try \"tc chaintemplate help\".\n",
+ *argv);
+ return -1;
+}
+
diff --git a/tc/tc_monitor.c b/tc/tc_monitor.c
index 077b138d1ec5..33633837432c 100644
--- a/tc/tc_monitor.c
+++ b/tc/tc_monitor.c
@@ -43,7 +43,10 @@ static int accept_tcmsg(const struct sockaddr_nl *who,
if (timestamp)
print_timestamp(fp);
- if (n->nlmsg_type == RTM_NEWTFILTER || n->nlmsg_type == RTM_DELTFILTER) {
+ if (n->nlmsg_type == RTM_NEWTFILTER ||
+ n->nlmsg_type == RTM_DELTFILTER ||
+ n->nlmsg_type == RTM_NEWCHAINTMPLT ||
+ n->nlmsg_type == RTM_DELCHAINTMPLT) {
print_filter(who, n, arg);
return 0;
}
--
2.14.4
^ permalink raw reply related
* Re: [PATCH v2 net-next 0/6] net sched actions: code style cleanup and fixes
From: David Miller @ 2018-06-28 13:12 UTC (permalink / raw)
To: mrv; +Cc: netdev, kernel, jhs, xiyou.wangcong, jiri
In-Reply-To: <1530120815-13736-1-git-send-email-mrv@mojatatu.com>
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:29 -0400
> The patchset fixes a few code stylistic issues and typos, as well as one
> detected by sparse semantic checker tool.
>
> No functional changes introduced.
>
> Patch 1 & 2 fix coding style bits caught by the checkpatch.pl script
> Patch 3 fixes an issue with a shadowed variable
> Patch 4 adds sizeof() operator instead of magic number for buffer length
> Patch 5 fixes typos in diagnostics messages
> Patch 6 explicitly sets unsigned char for bitwise operation
>
> v2:
> - submit for net-next
> - added Reviewed-by tags
> - use u8* instead of char* as per Davide Caratti suggestion
Series applied.
^ permalink raw reply
* Re: [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: Jamal Hadi Salim @ 2018-06-28 13:13 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, xiyou.wangcong, jakub.kicinski, simon.horman, john.hurley,
dsahern, mlxsw
In-Reply-To: <20180626080000.12964-1-jiri@resnulli.us>
On 26/06/18 03:59 AM, Jiri Pirko wrote:
> From: Jiri Pirko <jiri@mellanox.com>
>
> For the TC clsact offload these days, some of HW drivers need
> to hold a magic ball. The reason is, with the first inserted rule inside
> HW they need to guess what fields will be used for the matching. If
> later on this guess proves to be wrong and user adds a filter with a
> different field to match, there's a problem. Mlxsw resolves it now with
> couple of patterns. Those try to cover as many match fields as possible.
> This aproach is far from optimal, both performance-wise and scale-wise.
> Also, there is a combination of filters that in certain order won't
> succeed.
>
>
> Most of the time, when user inserts filters in chain, he knows right away
> how the filters are going to look like - what type and option will they
> have. For example, he knows that he will only insert filters of type
> flower matching destination IP address. He can specify a template that
> would cover all the filters in the chain.
>
Is this just restricted to hardware offload? Example it will make sense
for u32 in s/ware as well (i.e flexible TCAM like TCAM based
classification). i.e it is possible that rules the user enters
end up being worst case a linked list lookup, yes? And allocating
space for a tuple that is not in use is a waste of space.
If yes, then I would reword the above as something like:
For very flexible classifiers such as TCAM based ones,
one could add arbitrary tuple rules which tend to be inefficient both
from a space and lookup performance. One approach, taken by Mlxsw,
is to assume a multi filter tuple arrangement which is inefficient
from a space perspective when the user-specified rules dont make
use of pre-provisioned tuple space.
Typically users already know what tuples are of interest to them:
for example for ipv4 route lookup purposes they may just want to
lookup destination IP with a specified mask etc.
This feature allows user to provide good hints to the classifier to
optimize.
> This patchset is providing the possibility to user to provide such
> template to kernel and propagate it all the way down to device
> drivers.
>
> See the examples below.
>
> Create dummy device with clsact first:
> # ip link add type dummy
> # tc qdisc add dev dummy0 clsact
>
> There is no template assigned by default:
> # tc filter template show dev dummy0 ingress
>
> Add a template of type flower allowing to insert rules matching on last
> 2 bytes of destination mac address:
> # tc filter template add dev dummy0 ingress proto ip flower dst_mac 00:00:00:00:00:00/00:00:00:00:FF:FF
>
> The template is now showed in the list:
> # tc filter template show dev dummy0 ingress
> filter flower chain 0
> dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
> eth_type ipv4
>
> Add another template, this time for chain number 22:
> # tc filter template add dev dummy0 ingress proto ip chain 22 flower dst_ip 0.0.0.0/16
> # tc filter template show dev dummy0 ingress
> filter flower chain 0
> dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
> eth_type ipv4
> filter flower chain 22
> eth_type ipv4
> dst_ip 0.0.0.0/16
>
> Add a filter that fits the template:
> # tc filter add dev dummy0 ingress proto ip flower dst_mac aa:bb:cc:dd:ee:ff/00:00:00:00:00:0F action drop
>
> Addition of filters that does not fit the template would fail:
> # tc filter add dev dummy0 ingress proto ip flower dst_mac aa:11:22:33:44:55/00:00:00:FF:00:00 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
> # tc filter add dev dummy0 ingress proto ip flower dst_ip 10.0.0.1 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
>
> Additions of filters to chain 22:
> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/8 action drop
> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/24 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
>
> Removal of a template from non-empty chain would fail:
> # tc filter template del dev dummy0 ingress
> Error: The chain is not empty, unable to delete template.
> We have an error talking to the kernel, -1
>
> Once the chain is flushed, the template could be removed:
> # tc filter del dev dummy0 ingress
> # tc filter template del dev dummy0 ingress
>
BTW: unlike the other comments on this - I think the syntax above
is fine ;-> Chain are already either explicitly or are implicitly
(case of chain 0) specified.
Assuming that one cant add a new template to a chain if it already
has at least one filter (even if no template has been added).
I like it - it may help making u32 more friendly to humans in some
cases.
cheers,
jamal
^ permalink raw reply
* Re: [PATCH v2 net-next 0/2] net: preserve sock reference when scrubbing the skb.
From: David Miller @ 2018-06-28 13:20 UTC (permalink / raw)
To: xiyou.wangcong; +Cc: fbl, netdev, eric.dumazet, pabeni, fw, netfilter-devel
In-Reply-To: <CAM_iQpXnfc8uA10EK2X7B=vB_uWayeGw=M5F-_uygu7aPvCjRw@mail.gmail.com>
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 27 Jun 2018 12:39:01 -0700
> Let me rephrase why I don't like this patchset:
Cong, I don't think you are seeing the situation clearly and
I am certainly going to apply this patch series even in the
face of your objections.
Suggesting that solving the lack of back pressure on a UDP
socket caused by this problem by using cgroups or cpu
usage controllers is just complete and utter madness.
^ permalink raw reply
* Re: [PATCH v2 net-next 0/2] net: preserve sock reference when scrubbing the skb.
From: David Miller @ 2018-06-28 13:21 UTC (permalink / raw)
To: fbl; +Cc: netdev, eric.dumazet, pabeni, fw, netfilter-devel
In-Reply-To: <20180627133426.3858-1-fbl@redhat.com>
From: Flavio Leitner <fbl@redhat.com>
Date: Wed, 27 Jun 2018 10:34:24 -0300
> The sock reference is lost when scrubbing the packet and that breaks
> TSQ (TCP Small Queues) and XPS (Transmit Packet Steering) causing
> performance impacts of about 50% in a single TCP stream when crossing
> network namespaces.
>
> XPS breaks because the queue mapping stored in the socket is not
> available, so another random queue might be selected when the stack
> needs to transmit something like a TCP ACK, or TCP Retransmissions.
> That causes packet re-ordering and/or performance issues.
>
> TSQ breaks because it orphans the packet while it is still in the
> host, so packets are queued contributing to the buffer bloat problem.
>
> Preserving the sock reference fixes both issues. The socket is
> orphaned anyways in the receiving path before any relevant action,
> but the transmit side needs some extra checking included in the
> first patch.
>
> The first patch will update netfilter to check if the socket
> netns is local before use it.
>
> The second patch removes the skb_orphan() from the skb_scrub_packet()
> and improve the documentation.
>
> ChangeLog:
> - split into two (Eric)
> - addressed Paolo's offline feedback to swap the checks in xt_socket.c
> to preserve original behavior.
> - improved ip-sysctl.txt (reported by Cong)
Series applied, thanks Flavio.
^ permalink raw reply
* Re: [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: Jiri Pirko @ 2018-06-28 13:22 UTC (permalink / raw)
To: Jamal Hadi Salim
Cc: netdev, davem, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw
In-Reply-To: <a0885166-cad9-f21d-32d7-3000c0083384@mojatatu.com>
Thu, Jun 28, 2018 at 03:13:30PM CEST, jhs@mojatatu.com wrote:
>
>On 26/06/18 03:59 AM, Jiri Pirko wrote:
>> From: Jiri Pirko <jiri@mellanox.com>
>>
>> For the TC clsact offload these days, some of HW drivers need
>> to hold a magic ball. The reason is, with the first inserted rule inside
>> HW they need to guess what fields will be used for the matching. If
>> later on this guess proves to be wrong and user adds a filter with a
>> different field to match, there's a problem. Mlxsw resolves it now with
>> couple of patterns. Those try to cover as many match fields as possible.
>> This aproach is far from optimal, both performance-wise and scale-wise.
>> Also, there is a combination of filters that in certain order won't
>> succeed.
>>
>>
>> Most of the time, when user inserts filters in chain, he knows right away
>> how the filters are going to look like - what type and option will they
>> have. For example, he knows that he will only insert filters of type
>> flower matching destination IP address. He can specify a template that
>> would cover all the filters in the chain.
>>
>
>Is this just restricted to hardware offload? Example it will make sense
>for u32 in s/ware as well (i.e flexible TCAM like TCAM based
>classification). i.e it is possible that rules the user enters
>end up being worst case a linked list lookup, yes? And allocating
>space for a tuple that is not in use is a waste of space.
I'm afraid I don't understand clearly what you say. This is not
restricted to hw offload. The templates apply to all filters, no matter
if they are offloaded or not.
>
>If yes, then I would reword the above as something like:
>
>For very flexible classifiers such as TCAM based ones,
>one could add arbitrary tuple rules which tend to be inefficient both
>from a space and lookup performance. One approach, taken by Mlxsw,
>is to assume a multi filter tuple arrangement which is inefficient
>from a space perspective when the user-specified rules dont make
>use of pre-provisioned tuple space.
>Typically users already know what tuples are of interest to them:
>for example for ipv4 route lookup purposes they may just want to
>lookup destination IP with a specified mask etc.
>This feature allows user to provide good hints to the classifier to
>optimize.
>
>
>> This patchset is providing the possibility to user to provide such
>> template to kernel and propagate it all the way down to device
>> drivers.
>>
>> See the examples below.
>>
>> Create dummy device with clsact first:
>> # ip link add type dummy
>> # tc qdisc add dev dummy0 clsact
>>
>> There is no template assigned by default:
>> # tc filter template show dev dummy0 ingress
>>
>> Add a template of type flower allowing to insert rules matching on last
>> 2 bytes of destination mac address:
>> # tc filter template add dev dummy0 ingress proto ip flower dst_mac 00:00:00:00:00:00/00:00:00:00:FF:FF
>>
>> The template is now showed in the list:
>> # tc filter template show dev dummy0 ingress
>> filter flower chain 0
>> dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
>> eth_type ipv4
>>
>> Add another template, this time for chain number 22:
>> # tc filter template add dev dummy0 ingress proto ip chain 22 flower dst_ip 0.0.0.0/16
>> # tc filter template show dev dummy0 ingress
>> filter flower chain 0
>> dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
>> eth_type ipv4
>> filter flower chain 22
>> eth_type ipv4
>> dst_ip 0.0.0.0/16
>>
>> Add a filter that fits the template:
>> # tc filter add dev dummy0 ingress proto ip flower dst_mac aa:bb:cc:dd:ee:ff/00:00:00:00:00:0F action drop
>>
>> Addition of filters that does not fit the template would fail:
>> # tc filter add dev dummy0 ingress proto ip flower dst_mac aa:11:22:33:44:55/00:00:00:FF:00:00 action drop
>> Error: Mask does not fit the template.
>> We have an error talking to the kernel, -1
>> # tc filter add dev dummy0 ingress proto ip flower dst_ip 10.0.0.1 action drop
>> Error: Mask does not fit the template.
>> We have an error talking to the kernel, -1
>>
>> Additions of filters to chain 22:
>> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/8 action drop
>> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1 action drop
>> Error: Mask does not fit the template.
>> We have an error talking to the kernel, -1
>> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/24 action drop
>> Error: Mask does not fit the template.
>> We have an error talking to the kernel, -1
>>
>> Removal of a template from non-empty chain would fail:
>> # tc filter template del dev dummy0 ingress
>> Error: The chain is not empty, unable to delete template.
>> We have an error talking to the kernel, -1
>>
>> Once the chain is flushed, the template could be removed:
>> # tc filter del dev dummy0 ingress
>> # tc filter template del dev dummy0 ingress
>>
>
>BTW: unlike the other comments on this - I think the syntax above
>is fine ;-> Chain are already either explicitly or are implicitly
>(case of chain 0) specified.
>
>Assuming that one cant add a new template to a chain if it already
>has at least one filter (even if no template has been added).
>
>I like it - it may help making u32 more friendly to humans in some
>cases.
>
>cheers,
>jamal
^ permalink raw reply
* Re: [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: Jiri Pirko @ 2018-06-28 13:24 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
Oh, this is v3 already. The changelog should be:
---
v2->v3:
- patch 5:
- rebase on top of the reoffload pathset
- patch 6:
- rebase on top of the reoffload pathset
- patch 9:
- adjust to the userspace cmdline changes
v1->v2:
- patch 6:
- remove leftover extack arg in fl_hw_create_tmplt()
^ permalink raw reply
* [PATCH net v2] net: phy: DP83TC811: Fix diabling interrupts
From: Dan Murphy @ 2018-06-28 13:32 UTC (permalink / raw)
To: andrew, f.fainelli; +Cc: netdev, linux-kernel, Dan Murphy
Fix a bug where INT_STAT1 was written twice and
INT_STAT2 was ignored when disabling interrupts.
Fixes: b753a9faaf9a ("net: phy: DP83TC811: Introduce support for the DP83TC811 phy")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Dan Murphy <dmurphy@ti.com>
---
v2 - Updated commit message to add the Fixes - http://lists.openwall.net/netdev/2018/06/28/110
drivers/net/phy/dp83tc811.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 081d99aa3985..49ac678eb2dc 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -222,7 +222,7 @@ static int dp83811_config_intr(struct phy_device *phydev)
if (err < 0)
return err;
- err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+ err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
}
return err;
--
2.17.0.582.gccdcbd54c
^ permalink raw reply related
* Re: [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: Jamal Hadi Salim @ 2018-06-28 13:54 UTC (permalink / raw)
To: Jiri Pirko
Cc: netdev, davem, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw
In-Reply-To: <20180628132241.GA2177@nanopsycho.orion>
On 28/06/18 09:22 AM, Jiri Pirko wrote:
> Thu, Jun 28, 2018 at 03:13:30PM CEST, jhs@mojatatu.com wrote:
>>
>> On 26/06/18 03:59 AM, Jiri Pirko wrote:
>>> From: Jiri Pirko <jiri@mellanox.com>
>>>
>>> For the TC clsact offload these days, some of HW drivers need
>>> to hold a magic ball. The reason is, with the first inserted rule inside
>>> HW they need to guess what fields will be used for the matching. If
>>> later on this guess proves to be wrong and user adds a filter with a
>>> different field to match, there's a problem. Mlxsw resolves it now with
>>> couple of patterns. Those try to cover as many match fields as possible.
>>> This aproach is far from optimal, both performance-wise and scale-wise.
>>> Also, there is a combination of filters that in certain order won't
>>> succeed.
>>>
>>>
>>> Most of the time, when user inserts filters in chain, he knows right away
>>> how the filters are going to look like - what type and option will they
>>> have. For example, he knows that he will only insert filters of type
>>> flower matching destination IP address. He can specify a template that
>>> would cover all the filters in the chain.
>>>
>>
>> Is this just restricted to hardware offload? Example it will make sense
>> for u32 in s/ware as well (i.e flexible TCAM like TCAM based
>> classification). i.e it is possible that rules the user enters
>> end up being worst case a linked list lookup, yes? And allocating
>> space for a tuple that is not in use is a waste of space.
>
> I'm afraid I don't understand clearly what you say.
Well - I was trying to understand what you said ;->
I think what you are getting at is two issues:
a) space in the tcams - if the user is just going to enter
rules which use one tuple (dst ip for example) the hardware
would be better off told that this is the case so it doesnt
allocate space in anticipation that someone is going to
specify src ip later on.
b) lookup speed in tcams - without the template hint a
selection of rules may end up looking like a linked list
which is not optimal for lookup
> This is not
> restricted to hw offload. The templates apply to all filters, no matter
> if they are offloaded or not.
>
Do you save anything with flower(in s/w) if you only added a template
with say dst ip/mask? I can see it will make sense for u32 which is more
flexible and protocol independent.
cheers,
jamal
^ permalink raw reply
* Re: [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: Jiri Pirko @ 2018-06-28 14:17 UTC (permalink / raw)
To: Jamal Hadi Salim
Cc: netdev, davem, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw
In-Reply-To: <d0d49f73-ae37-effc-7d11-1092a215c20d@mojatatu.com>
Thu, Jun 28, 2018 at 03:54:17PM CEST, jhs@mojatatu.com wrote:
>On 28/06/18 09:22 AM, Jiri Pirko wrote:
>> Thu, Jun 28, 2018 at 03:13:30PM CEST, jhs@mojatatu.com wrote:
>> >
>> > On 26/06/18 03:59 AM, Jiri Pirko wrote:
>> > > From: Jiri Pirko <jiri@mellanox.com>
>> > >
>> > > For the TC clsact offload these days, some of HW drivers need
>> > > to hold a magic ball. The reason is, with the first inserted rule inside
>> > > HW they need to guess what fields will be used for the matching. If
>> > > later on this guess proves to be wrong and user adds a filter with a
>> > > different field to match, there's a problem. Mlxsw resolves it now with
>> > > couple of patterns. Those try to cover as many match fields as possible.
>> > > This aproach is far from optimal, both performance-wise and scale-wise.
>> > > Also, there is a combination of filters that in certain order won't
>> > > succeed.
>> > >
>> > >
>> > > Most of the time, when user inserts filters in chain, he knows right away
>> > > how the filters are going to look like - what type and option will they
>> > > have. For example, he knows that he will only insert filters of type
>> > > flower matching destination IP address. He can specify a template that
>> > > would cover all the filters in the chain.
>> > >
>> >
>> > Is this just restricted to hardware offload? Example it will make sense
>> > for u32 in s/ware as well (i.e flexible TCAM like TCAM based
>> > classification). i.e it is possible that rules the user enters
>> > end up being worst case a linked list lookup, yes? And allocating
>> > space for a tuple that is not in use is a waste of space.
>>
>> I'm afraid I don't understand clearly what you say.
>
>Well - I was trying to understand what you said ;->
>
>I think what you are getting at is two issues:
>a) space in the tcams - if the user is just going to enter
>rules which use one tuple (dst ip for example) the hardware
>would be better off told that this is the case so it doesnt
>allocate space in anticipation that someone is going to
>specify src ip later on.
Yes.
>b) lookup speed in tcams - without the template hint a
>selection of rules may end up looking like a linked list
>which is not optimal for lookup
Well. Not really, but wider keys have bigger overheads in general. So
the motivation is to have the keys as small as possible for both
performance and capacity reasons.
>
>> This is not
>> restricted to hw offload. The templates apply to all filters, no matter
>> if they are offloaded or not.
>>
>
>Do you save anything with flower(in s/w) if you only added a template
>with say dst ip/mask? I can see it will make sense for u32 which is more
>flexible and protocol independent.
No benefit for flower s/w path at this point. Perhaps the hashtables
could be organized in more optimal way with the hint. I didn't look at
it.
>
>cheers,
>jamal
^ permalink raw reply
* Re: [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: David Ahern @ 2018-06-28 14:18 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
On 6/28/18 7:08 AM, Jiri Pirko wrote:
> Create dummy device with clsact first:
> # ip link add type dummy
> # tc qdisc add dev dummy0 clsact
>
> There is no template assigned by default:
> # tc chaintemplate show dev dummy0 ingress
>
> Add a template of type flower allowing to insert rules matching on last
> 2 bytes of destination mac address:
> # tc chaintemplate add dev dummy0 ingress proto ip flower dst_mac 00:00:00:00:00:00/00:00:00:00:FF:FF
>
> The template is now showed in the list:
> # tc chaintemplate show dev dummy0 ingress
> chaintemplate flower chain 0
> dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
> eth_type ipv4
>
> Add another template, this time for chain number 22:
> # tc chaintemplate add dev dummy0 ingress proto ip chain 22 flower dst_ip 0.0.0.0/16
> # tc chaintemplate show dev dummy0 ingress
> chaintemplate flower chain 0
> dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
> eth_type ipv4
> chaintemplate flower chain 22
> eth_type ipv4
> dst_ip 0.0.0.0/16
>
> Add a filter that fits the template:
> # tc filter add dev dummy0 ingress proto ip flower dst_mac aa:bb:cc:dd:ee:ff/00:00:00:00:00:0F action drop
>
> Addition of filters that does not fit the template would fail:
> # tc filter add dev dummy0 ingress proto ip flower dst_mac aa:11:22:33:44:55/00:00:00:FF:00:00 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
> # tc filter add dev dummy0 ingress proto ip flower dst_ip 10.0.0.1 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
>
> Additions of filters to chain 22:
> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/8 action drop
> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
> # tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/24 action drop
> Error: Mask does not fit the template.
> We have an error talking to the kernel, -1
>
> Removal of a template from non-empty chain would fail:
> # tc chaintemplate del dev dummy0 ingress
> Error: The chain is not empty, unable to delete template.
> We have an error talking to the kernel, -1
Why this restriction? It's a template, so why can't it be removed
regardless of whether there are filters?
>
> Once the chain is flushed, the template could be removed:
> # tc filter del dev dummy0 ingress
> # tc chaintemplate del dev dummy0 ingress
>
^ permalink raw reply
* Re: [RFC PATCH 00/11] OVS eBPF datapath.
From: William Tu @ 2018-06-28 14:19 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: <dev-yBygre7rU0TnMu66kgdUjQ@public.gmane.org>,
Tom Herbert via iovisor-dev, Linux Kernel Network Developers
In-Reply-To: <20180628030023.pkgdu4brun3jy2bz-+o4/htvd0TCa6kscz5V53/3mLCh9rsb+VpNB7YpNyf8@public.gmane.org>
Hi Alexei,
Thanks a lot for the feedback!
On Wed, Jun 27, 2018 at 8:00 PM, Alexei Starovoitov
<alexei.starovoitov-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
> On Sat, Jun 23, 2018 at 05:16:32AM -0700, William Tu wrote:
>>
>> Discussion
>> ==========
>> We are still actively working on finishing the feature, currently
>> the basic forwarding and tunnel feature work, but still under
>> heavy debugging and development. The purpose of this RFC is to
>> get some early feedbacks and direction for finishing the complete
>> features in existing kernel's OVS datapath (the net/openvswitch/*).
>
> Thank you for sharing the patches.
>
>> Three major issues we are worried:
>> a. Megaflow support in BPF.
>> b. Connection Tracking support in BPF.
>
> my opinion on the above two didn't change.
> To recap:
> A. Non scalable megaflow map is no go. I'd like to see packet classification
> algorithm like hicuts or efficuts to be implemented instead, since it can be
> shared by generic bpf, bpftiler, ovs and likely others.
We did try the decision tree approach using dpdk's acl lib. The lookup
speed is 6 times faster than the magaflow using tuple space.
However, the update/insertion requires rebuilding/re-balancing the decision
tree so it's way too slow. I think hicuts or efficuts suffers the same issue.
So decision tree algos are scalable only for lookup operation due to its
optimization over tree depth, but not scalable under
update/insert/delete operations.
On customer's system we see megaflow update/insert rate around 10 rules/sec,
this makes decision tree unusable, unless we invent something to optimize the
update/insert time or incremental update of these decision tree algo.
Now my backup plan is to implement megaflow in BPF.
> B. instead of helpers to interface with conntrack the way ovs did, I prefer
> a generic conntrack mechanism that can be used out of xdp too
>
OK. We will work on this direction.
>> c. Verifier limitation.
>
> Not sure what limitations you're concerned about.
>
Mostly related to stack. The flow key OVS uses (struct sw_flow_key)
is 464 byte. We trim a lot, now around 300 byte, but still huge, considering
the BPF's stack limit is 512 byte.
We can always break the large program then tail call, but sometimes
the register spills on the stack, and when restore, the states is gone
and verifier fails. This is more difficult for us to work around.
Below is an example:
----
at 203: r7 is a const and store on stack (r10 - 248)
at 250: r2 reads (r10 - 248) back.
at 251: fails the verifier
from 27 to 201: R0=map_value(id=0,off=0,ks=4,vs=4352,imm=0)
R7=inv(id=0,umax_value=31,var_off=(0x0; 0x1f))
R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
201: (7b) *(u64 *)(r10 -256) = r0
202: (27) r7 *= 136
203: (7b) *(u64 *)(r10 -248) = r7
204: (bf) r6 = r0
205: (0f) r6 += r7
206: (b7) r8 = 2
207: (15) if r6 == 0x0 goto pc+93
R0=map_value(id=0,off=0,ks=4,vs=4352,imm=0)
R6=map_value(id=0,off=0,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R7=inv(id=0,umax_value=4216,var_off=(0x0; 0x1ff8)) R8=inv2
R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1 fp-256=map_value
208: (b7) r1 = 681061
209: (63) *(u32 *)(r10 -200) = r1
210: (18) r1 = 0x6b73616d20746573
212: (7b) *(u64 *)(r10 -208) = r1
213: (bf) r1 = r10
214: (07) r1 += -208
215: (b7) r2 = 12
216: (85) call bpf_trace_printk#6
217: (bf) r7 = r6
218: (07) r7 += 8
219: (61) r1 = *(u32 *)(r6 +8)
R0=inv(id=0) R6=map_value(id=0,off=0,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R7_w=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value
220: (15) if r1 == 0x7 goto pc+82
R0=inv(id=0) R1=inv(id=0,umax_value=4294967295,var_off=(0x0;
0xffffffff)) R6=map_value(id=0,off=0,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value
221: (55) if r1 != 0x4 goto pc+228
R0=inv(id=0) R1=inv4
R6=map_value(id=0,off=0,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value
222: (61) r1 = *(u32 *)(r9 +80)
223: (7b) *(u64 *)(r10 -264) = r1
224: (61) r6 = *(u32 *)(r9 +76)
225: (b7) r1 = 0
226: (73) *(u8 *)(r10 -198) = r1
227: (b7) r1 = 2674
228: (6b) *(u16 *)(r10 -200) = r1
229: (18) r1 = 0x6568746520746573
231: (7b) *(u64 *)(r10 -208) = r1
232: (bf) r1 = r10
233: (07) r1 += -208
234: (b7) r2 = 11
235: (85) call bpf_trace_printk#6
236: (bf) r1 = r6
237: (07) r1 += 14
238: (79) r2 = *(u64 *)(r10 -264)
239: (2d) if r1 > r2 goto pc+61
R0=inv(id=0) R1=pkt(id=0,off=14,r=14,imm=0)
R2=pkt_end(id=0,off=0,imm=0) R6=pkt(id=0,off=0,r=14,imm=0)
R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value fp-264=pkt_end
240: (71) r1 = *(u8 *)(r7 +10)
R0=inv(id=0) R1_w=pkt(id=0,off=14,r=14,imm=0)
R2=pkt_end(id=0,off=0,imm=0) R6=pkt(id=0,off=0,r=14,imm=0)
R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value fp-264=pkt_end
241: (73) *(u8 *)(r6 +0) = r1
242: (71) r1 = *(u8 *)(r7 +11)
R0=inv(id=0) R1_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))
R2=pkt_end(id=0,off=0,imm=0) R6=pkt(id=0,off=0,r=14,imm=0)
R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value fp-264=pkt_end
243: (73) *(u8 *)(r6 +1) = r1
244: (71) r1 = *(u8 *)(r7 +12)
R0=inv(id=0) R1_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))
R2=pkt_end(id=0,off=0,imm=0) R6=pkt(id=0,off=0,r=14,imm=0)
R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value fp-264=pkt_end
245: (73) *(u8 *)(r6 +2) = r1
246: (71) r1 = *(u8 *)(r7 +13)
R0=inv(id=0) R1_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))
R2=pkt_end(id=0,off=0,imm=0) R6=pkt(id=0,off=0,r=14,imm=0)
R7=map_value(id=0,off=8,ks=4,vs=4352,umax_value=4216,var_off=(0x0;
0x1ff8)) R8=inv2 R9=ctx(id=0,off=0,imm=0) R10=fp0,call_-1
fp-256=map_value fp-264=pkt_end
247: (73) *(u8 *)(r6 +3) = r1
248: (79) r4 = *(u64 *)(r10 -256)
249: (bf) r1 = r4
250: (79) r2 = *(u64 *)(r10 -248)
251: (0f) r1 += r2
math between map_value pointer and register with unbounded min value
is not allowed
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#1355): https://lists.iovisor.org/g/iovisor-dev/message/1355
Mute This Topic: https://lists.iovisor.org/mt/22656941/1132507
Group Owner: iovisor-dev+owner-9jONkmmOlFHEE9lA1F8Ukti2O/JbrIOy@public.gmane.org
Unsubscribe: https://lists.iovisor.org/g/iovisor-dev/unsub [glki-iovisor-dev@m.gmane.org]
-=-=-=-=-=-=-=-=-=-=-=-
^ permalink raw reply
* [RFC] replace ->get_poll_head with a waitqueue pointer in struct file
From: Christoph Hellwig @ 2018-06-28 14:20 UTC (permalink / raw)
To: Alexander Viro; +Cc: Linus Torvalds, linux-fsdevel, netdev, lkp
Introducing the new poll methods showed up a regression in the
will-it-scale ltp tests. One reason for that is that indirect function
calls are very expensive now with the spectre mitigations. I'm waiting
for better numbers, but this series has shown a 5% improvements in the
ops per second so far, while for the get_poll_head addition we had
regressions of 3.7% or 8.8% depending on the measurement.
This series removes the get_poll_head method again and instead stores an
optional wait_queue_head pointer in struct file, on which the poll_mask
method can be used if it is set. The only complication is the networking
poll code which not only does some interesting gymnastics to get at the
wait queue pointer, but also has a mode to to hardware polling before
waiting for an even from poll or epoll. Because of that this series has
a few net prep patches that need careful review.
^ permalink raw reply
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