* [PATCH bpf-next] selftests: bpf: test_lwt_ip_encap: add negative tests.
From: Peter Oskolkov @ 2019-02-15 23:49 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, netdev
Cc: Peter Oskolkov, David Ahern, Peter Oskolkov
As requested by David Ahern:
- add negative tests (no routes, explicitly unreachable destinations)
to exercize error handling code paths;
- do not exit on test failures, but instead print a summary of
passed/failed tests at the end.
Future patches will add TSO and VRF tests.
Signed-off-by: Peter Oskolkov <posk@google.com>
---
.../selftests/bpf/test_lwt_ip_encap.sh | 111 ++++++++++++++----
1 file changed, 88 insertions(+), 23 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
index 4ca714e23ab0..612632c1425f 100755
--- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
+++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
@@ -38,8 +38,6 @@
# ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
# ping replies go DST->SRC directly
-set -e # exit on error
-
if [[ $EUID -ne 0 ]]; then
echo "This script must be run as root"
echo "FAIL"
@@ -76,8 +74,37 @@ readonly IPv6_GRE="fb10::1"
readonly IPv6_SRC=$IPv6_1
readonly IPv6_DST=$IPv6_4
-setup() {
-set -e # exit on error
+TEST_STATUS=0
+TESTS_SUCCEEDED=0
+TESTS_FAILED=0
+
+process_test_results()
+{
+ if [[ "${TEST_STATUS}" -eq 0 ]] ; then
+ echo "PASS"
+ TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1))
+ else
+ echo "FAIL"
+ TESTS_FAILED=$((TESTS_FAILED+1))
+ fi
+}
+
+print_test_summary_and_exit()
+{
+ echo "passed tests: ${TESTS_SUCCEEDED}"
+ echo "failed tests: ${TESTS_FAILED}"
+ if [ "${TESTS_FAILED}" -eq "0" ] ; then
+ exit 0
+ else
+ exit 1
+ fi
+}
+
+setup()
+{
+ set -e # exit on error
+ TEST_STATUS=0
+
# create devices and namespaces
ip netns add "${NS1}"
ip netns add "${NS2}"
@@ -178,7 +205,7 @@ set -e # exit on error
# configure IPv4 GRE device in NS3, and a route to it via the "bottom" route
ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255
ip -netns ${NS3} link set gre_dev up
- ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev
+ ip -netns ${NS3} addr add ${IPv4_GRE} nodad dev gre_dev
ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6}
ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8}
@@ -194,9 +221,13 @@ set -e # exit on error
ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
+
+ sleep 1 # reduce flakiness
+ set +e
}
-cleanup() {
+cleanup()
+{
ip netns del ${NS1} 2> /dev/null
ip netns del ${NS2} 2> /dev/null
ip netns del ${NS3} 2> /dev/null
@@ -204,12 +235,28 @@ cleanup() {
trap cleanup EXIT
-test_ping() {
+remove_routes_to_gredev()
+{
+ ip -netns ${NS1} route del ${IPv4_GRE} dev veth5
+ ip -netns ${NS2} route del ${IPv4_GRE} dev veth7
+ ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5
+ ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7
+}
+
+add_unreachable_routes_to_gredev()
+{
+ ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32
+ ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32
+ ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128
+ ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128
+}
+
+test_ping()
+{
local readonly PROTO=$1
local readonly EXPECTED=$2
local RET=0
- set +e
if [ "${PROTO}" == "IPv4" ] ; then
ip netns exec ${NS1} ping -c 1 -W 1 -I ${IPv4_SRC} ${IPv4_DST} 2>&1 > /dev/null
RET=$?
@@ -217,29 +264,26 @@ test_ping() {
ip netns exec ${NS1} ping6 -c 1 -W 6 -I ${IPv6_SRC} ${IPv6_DST} 2>&1 > /dev/null
RET=$?
else
- echo "test_ping: unknown PROTO: ${PROTO}"
- exit 1
+ echo " test_ping: unknown PROTO: ${PROTO}"
+ TEST_STATUS=1
fi
- set -e
if [ "0" != "${RET}" ]; then
RET=1
fi
if [ "${EXPECTED}" != "${RET}" ] ; then
- echo "FAIL: test_ping: ${RET}"
- exit 1
+ echo " test_ping failed: expected: ${EXPECTED}; got ${RET}"
+ TEST_STATUS=1
fi
}
-test_egress() {
+test_egress()
+{
local readonly ENCAP=$1
echo "starting egress ${ENCAP} encap test"
setup
- # need to wait a bit for IPv6 to autoconf, otherwise
- # ping6 sometimes fails with "unable to bind to address"
-
# by default, pings work
test_ping IPv4 0
test_ping IPv6 0
@@ -258,16 +302,28 @@ test_egress() {
ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1
ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1
else
- echo "FAIL: unknown encap ${ENCAP}"
+ echo " unknown encap ${ENCAP}"
+ TEST_STATUS=1
fi
test_ping IPv4 0
test_ping IPv6 0
+ # a negative test: remove routes to GRE devices: ping fails
+ remove_routes_to_gredev
+ test_ping IPv4 1
+ test_ping IPv6 1
+
+ # another negative test
+ add_unreachable_routes_to_gredev
+ test_ping IPv4 1
+ test_ping IPv6 1
+
cleanup
- echo "PASS"
+ process_test_results
}
-test_ingress() {
+test_ingress()
+{
local readonly ENCAP=$1
echo "starting ingress ${ENCAP} encap test"
setup
@@ -298,14 +354,23 @@ test_ingress() {
test_ping IPv4 0
test_ping IPv6 0
+ # a negative test: remove routes to GRE devices: ping fails
+ remove_routes_to_gredev
+ test_ping IPv4 1
+ test_ping IPv6 1
+
+ # another negative test
+ add_unreachable_routes_to_gredev
+ test_ping IPv4 1
+ test_ping IPv6 1
+
cleanup
- echo "PASS"
+ process_test_results
}
test_egress IPv4
test_egress IPv6
-
test_ingress IPv4
test_ingress IPv6
-echo "all tests passed"
+print_test_summary_and_exit
--
2.21.0.rc0.258.g878e2cd30e-goog
^ permalink raw reply related
* Re: [PATCH net-next v4 10/17] net: sched: refactor tp insert/delete for concurrent execution
From: Cong Wang @ 2019-02-15 23:17 UTC (permalink / raw)
To: Vlad Buslov
Cc: Linux Kernel Network Developers, Jamal Hadi Salim, Jiri Pirko,
David Miller, Alexei Starovoitov, Daniel Borkmann
In-Reply-To: <20190211085548.7190-11-vladbu@mellanox.com>
On Mon, Feb 11, 2019 at 12:56 AM Vlad Buslov <vladbu@mellanox.com> wrote:
> +static bool tcf_proto_is_empty(struct tcf_proto *tp)
> +{
> + struct tcf_walker walker = { .fn = walker_noop, };
> +
> + if (tp->ops->walk) {
> + tp->ops->walk(tp, &walker);
> + return !walker.stop;
> + }
> + return true;
> +}
> +
> +static bool tcf_proto_check_delete(struct tcf_proto *tp)
> +{
> + spin_lock(&tp->lock);
> + if (tcf_proto_is_empty(tp))
> + tp->deleting = true;
> + spin_unlock(&tp->lock);
> + return tp->deleting;
If you use this spinlock for walking each tp data structure,
why it is not needed for adding to/deleting filters from each
tp?
^ permalink raw reply
* [PATCH RFC 5/5] net/sched: act_gact: validate the control action inside init()
From: Davide Caratti @ 2019-02-15 23:06 UTC (permalink / raw)
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: David S. Miller, Vlad Buslov, Paolo Abeni, netdev
In-Reply-To: <cover.1550271080.git.dcaratti@redhat.com>
Don't overwrite act_gact data if the control control action is not valid,
to prevent loosing the previous configuration in case validation failed.
Not doing that caused NULL dereference in the data path if 'goto chain'
is used.
Tested with:
# ./tdc.py -c gact
Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain")
Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
net/sched/act_gact.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 727bbca9534b..530e8bb8f94d 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -20,6 +20,7 @@
#include <linux/init.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
#include <linux/tc_act/tc_gact.h>
#include <net/tc_act/tc_gact.h>
@@ -61,6 +62,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
struct nlattr *tb[TCA_GACT_MAX + 1];
+ struct tcf_chain *newchain = NULL;
struct tc_gact *parm;
struct tcf_gact *gact;
int ret = 0;
@@ -116,10 +118,15 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
return err;
}
+ err = tcf_action_check_ctrlact(parm->action, tp, &newchain, extack);
+ if (unlikely(err)) {
+ ret = err;
+ goto error;
+ }
gact = to_gact(*a);
spin_lock_bh(&gact->tcf_lock);
- gact->tcf_action = parm->action;
+ tcf_action_set_ctrlact(*a, parm->action, newchain);
#ifdef CONFIG_GACT_PROB
if (p_parm) {
gact->tcfg_paction = p_parm->paction;
@@ -135,7 +142,13 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
+end:
return ret;
+error:
+ if (newchain)
+ tcf_chain_put_by_act(newchain);
+ tcf_idr_release(*a, bind);
+ goto end;
}
static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
--
2.20.1
^ permalink raw reply related
* [PATCH RFC 4/5] net/sched: act_csum: validate the control action inside init()
From: Davide Caratti @ 2019-02-15 23:06 UTC (permalink / raw)
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: David S. Miller, Vlad Buslov, Paolo Abeni, netdev
In-Reply-To: <cover.1550271080.git.dcaratti@redhat.com>
Don't overwrite act_csum data if the control control action is not valid,
to prevent loosing the previous configuration in case validation failed.
Not doing that caused NULL dereference in the data path if 'goto chain'
is used.
Tested with:
# ./tdc.py -c csum
Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain")
Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
net/sched/act_csum.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 1ae120c9ab02..bf0940156886 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -33,6 +33,7 @@
#include <net/sctp/checksum.h>
#include <net/act_api.h>
+#include <net/pkt_cls.h>
#include <linux/tc_act/tc_csum.h>
#include <net/tc_act/tc_csum.h>
@@ -52,6 +53,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
struct tc_action_net *tn = net_generic(net, csum_net_id);
struct tcf_csum_params *params_new;
struct nlattr *tb[TCA_CSUM_MAX + 1];
+ struct tcf_chain *newchain = NULL;
struct tc_csum *parm;
struct tcf_csum *p;
int ret = 0, err;
@@ -87,17 +89,23 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
return err;
}
+ err = tcf_action_check_ctrlact(parm->action, tp, &newchain, extack);
+ if (unlikely(err)) {
+ ret = err;
+ goto error;
+ }
+
p = to_tcf_csum(*a);
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
- tcf_idr_release(*a, bind);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto error;
}
params_new->update_flags = parm->update_flags;
spin_lock_bh(&p->tcf_lock);
- p->tcf_action = parm->action;
+ tcf_action_set_ctrlact(*a, parm->action, newchain);
rcu_swap_protected(p->params, params_new,
lockdep_is_held(&p->tcf_lock));
spin_unlock_bh(&p->tcf_lock);
@@ -108,7 +116,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
+end:
return ret;
+error:
+ if (newchain)
+ tcf_chain_put_by_act(newchain);
+ tcf_idr_release(*a, bind);
+ goto end;
}
/**
--
2.20.1
^ permalink raw reply related
* [PATCH RFC 3/5] net/sched: act_bpf: validate the control action inside init()
From: Davide Caratti @ 2019-02-15 23:06 UTC (permalink / raw)
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: David S. Miller, Vlad Buslov, Paolo Abeni, netdev
In-Reply-To: <cover.1550271080.git.dcaratti@redhat.com>
Don't overwrite act_bpf data if the control control action is not valid,
to prevent loosing the previous configuration in case validation failed.
Not doing that caused NULL dereference in the data path if 'goto chain'
is used.
Tested with:
# ./tdc.py -c bpf
Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain")
Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
net/sched/act_bpf.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 88a729bdab25..e2c2ba5faeb3 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -17,6 +17,7 @@
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
#include <linux/tc_act/tc_bpf.h>
#include <net/tc_act/tc_bpf.h>
@@ -282,6 +283,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
{
struct tc_action_net *tn = net_generic(net, bpf_net_id);
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+ struct tcf_chain *newchain = NULL;
struct tcf_bpf_cfg cfg, old;
struct tc_act_bpf *parm;
struct tcf_bpf *prog;
@@ -323,6 +325,10 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
return ret;
}
+ ret = tcf_action_check_ctrlact(parm->action, tp, &newchain, extack);
+ if (ret < 0)
+ goto out;
+
is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
is_ebpf = tb[TCA_ACT_BPF_FD];
@@ -350,7 +356,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
if (cfg.bpf_num_ops)
prog->bpf_num_ops = cfg.bpf_num_ops;
- prog->tcf_action = parm->action;
+ tcf_action_set_ctrlact(*act, parm->action, newchain);
rcu_assign_pointer(prog->filter, cfg.filter);
spin_unlock_bh(&prog->tcf_lock);
@@ -364,6 +370,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
return res;
out:
+ if (newchain)
+ tcf_chain_put_by_act(newchain);
tcf_idr_release(*act, bind);
return ret;
--
2.20.1
^ permalink raw reply related
* [PATCH RFC 2/5] net/sched: prepare TC actions to properly validate the control action
From: Davide Caratti @ 2019-02-15 23:06 UTC (permalink / raw)
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: David S. Miller, Vlad Buslov, Paolo Abeni, netdev
In-Reply-To: <cover.1550271080.git.dcaratti@redhat.com>
- add tcf_action_check_ctrlact(), and pass a pointer to struct tcf_proto
in each actions's init() function, to allow validation of 'goto chain'
control action.
- add tcf_action_set_ctrlact(), to set the control action, release the
previous 'goto_chain' handle and replace it with the new one.
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
include/net/act_api.h | 9 +++++-
net/sched/act_api.c | 58 ++++++++++++++++++++++++++++++++++++--
net/sched/act_bpf.c | 2 +-
net/sched/act_connmark.c | 1 +
net/sched/act_csum.c | 2 +-
net/sched/act_gact.c | 2 +-
net/sched/act_ife.c | 2 +-
net/sched/act_ipt.c | 11 ++++----
net/sched/act_mirred.c | 1 +
net/sched/act_nat.c | 3 +-
net/sched/act_pedit.c | 2 +-
net/sched/act_police.c | 1 +
net/sched/act_sample.c | 2 +-
net/sched/act_simple.c | 2 +-
net/sched/act_skbedit.c | 1 +
net/sched/act_skbmod.c | 1 +
net/sched/act_tunnel_key.c | 1 +
net/sched/act_vlan.c | 2 +-
18 files changed, 86 insertions(+), 17 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index dbc795ec659e..55a8d44ac0c7 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -90,7 +90,7 @@ struct tc_action_ops {
int (*lookup)(struct net *net, struct tc_action **a, u32 index);
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act, int ovr,
- int bind, bool rtnl_held,
+ int bind, bool rtnl_held, struct tcf_proto *tp,
struct netlink_ext_ack *extack);
int (*walk)(struct net *, struct sk_buff *,
struct netlink_callback *, int,
@@ -181,6 +181,13 @@ int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
+int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
+ struct tcf_chain **handle,
+ struct netlink_ext_ack *extack);
+
+void tcf_action_set_ctrlact(struct tc_action *p, int action,
+ struct tcf_chain *goto_chain);
+
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 91d79fac8cb2..088b0d846bde 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -71,6 +71,60 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
call_rcu(&old->rcu, tcf_free_cookie_rcu);
}
+int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
+ struct tcf_chain **handle,
+ struct netlink_ext_ack *extack)
+{
+ int opcode = TC_ACT_EXT_OPCODE(action), ret = -EINVAL;
+ u32 chain_index;
+
+ if (!opcode)
+ ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0;
+ else if (opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC)
+ ret = 0;
+ if (ret) {
+ NL_SET_ERR_MSG(extack, "invalid control action");
+ goto end;
+ }
+
+ if (TC_ACT_EXT_CMP(action, TC_ACT_GOTO_CHAIN)) {
+ chain_index = action & TC_ACT_EXT_VAL_MASK;
+ if (!tp) {
+ ret = -EINVAL;
+ NL_SET_ERR_MSG(extack,
+ "can't use goto_chain with NULL proto");
+ goto end;
+ }
+ if (!handle) {
+ ret = -EINVAL;
+ NL_SET_ERR_MSG(extack,
+ "can't put goto_chain on NULL handle");
+ goto end;
+ }
+ *handle = tcf_chain_get_by_act(tp->chain->block, chain_index);
+ if (!*handle) {
+ ret = -ENOMEM;
+ NL_SET_ERR_MSG(extack,
+ "can't allocate goto_chain handle");
+ }
+ }
+end:
+ return ret;
+}
+EXPORT_SYMBOL(tcf_action_check_ctrlact);
+
+void tcf_action_set_ctrlact(struct tc_action *p, int action,
+ struct tcf_chain *goto_chain)
+{
+ struct tcf_chain *old;
+
+ old = xchg(&p->goto_chain, goto_chain);
+ if (old)
+ tcf_chain_put_by_act(old);
+ p->tcfa_action = action;
+}
+EXPORT_SYMBOL(tcf_action_set_ctrlact);
+
/* XXX: For standalone actions, we don't need a RCU grace period either, because
* actions are always connected to filters and filters are already destroyed in
* RCU callbacks, so after a RCU grace period actions are already disconnected
@@ -890,10 +944,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
/* backward compatibility for policer */
if (name == NULL)
err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
- rtnl_held, extack);
+ rtnl_held, tp, extack);
else
err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
- extack);
+ tp, extack);
if (err < 0)
goto err_mod;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c7633843e223..88a729bdab25 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -278,7 +278,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act,
int replace, int bind, bool rtnl_held,
- struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, bpf_net_id);
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 8475913f2070..30c4c109c80c 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -97,6 +97,7 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
static int tcf_connmark_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 3dc25b7806d7..1ae120c9ab02 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -46,7 +46,7 @@ static struct tc_action_ops act_csum_ops;
static int tcf_csum_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, bool rtnl_held,
+ int bind, bool rtnl_held, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index b61c20ebb314..727bbca9534b 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -57,7 +57,7 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
static int tcf_gact_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
struct nlattr *tb[TCA_GACT_MAX + 1];
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 30b63fa23ee2..9b2eb941e093 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -469,7 +469,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
static int tcf_ife_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ife_net_id);
struct nlattr *tb[TCA_IFE_MAX + 1];
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8af6c11d2482..4b3c844ca988 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -97,7 +97,8 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- const struct tc_action_ops *ops, int ovr, int bind)
+ const struct tc_action_ops *ops, int ovr, int bind,
+ struct tcf_proto *tp)
{
struct tc_action_net *tn = net_generic(net, id);
struct nlattr *tb[TCA_IPT_MAX + 1];
@@ -206,20 +207,20 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
static int tcf_ipt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, bool rtnl_held,
+ int bind, bool rtnl_held, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
- bind);
+ bind, tp);
}
static int tcf_xt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, bool unlocked,
+ int bind, bool unlocked, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
- bind);
+ bind, tp);
}
static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index c8cf4d10c435..69dda57f1097 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -94,6 +94,7 @@ static struct tc_action_ops act_mirred_ops;
static int tcf_mirred_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index c5c1e23add77..526c4c99bcce 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -38,7 +38,8 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
struct tc_action **a, int ovr, int bind,
- bool rtnl_held, struct netlink_ext_ack *extack)
+ bool rtnl_held, struct tcf_proto *tp,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, nat_net_id);
struct nlattr *tb[TCA_NAT_MAX + 1];
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 2b372a06b432..1c7a0db7b466 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -138,7 +138,7 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
static int tcf_pedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
struct nlattr *tb[TCA_PEDIT_MAX + 1];
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index ec8ec55e0fe8..a444dd78a244 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -83,6 +83,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
static int tcf_police_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
int ret = 0, tcfp_result = TC_ACT_OK, err, size;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 1a0c682fd734..b2154edcb535 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -37,7 +37,7 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, bool rtnl_held,
+ int bind, bool rtnl_held, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 902957beceb3..640ee5b785dc 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -80,7 +80,7 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
static int tcf_simp_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, simp_net_id);
struct nlattr *tb[TCA_DEF_MAX + 1];
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 64dba3708fce..9fc8cfdd35b1 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -96,6 +96,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 59710a183bd3..35572d0e4576 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -82,6 +82,7 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 8b43fe0130f7..c4adc53e0fb4 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -209,6 +209,7 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p)
static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
+ struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 93fdaf707313..80fd0e238a10 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -105,7 +105,7 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
static int tcf_vlan_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
struct nlattr *tb[TCA_VLAN_MAX + 1];
--
2.20.1
^ permalink raw reply related
* [PATCH RFC 1/5] net/sched: fix refcount leak when 'goto_chain' is used
From: Davide Caratti @ 2019-02-15 23:06 UTC (permalink / raw)
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: David S. Miller, Vlad Buslov, Paolo Abeni, netdev
In-Reply-To: <cover.1550271080.git.dcaratti@redhat.com>
when replacing valid 'goto chain' actions with another valid 'goto chain'
action, the kernel leaks chain->action_refcnt and chain->refcnt. Since we
unconditionally take the refcount again, if the control action is a 'goto
chain', we can just drop them after ->init() has ended successfully.
Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
net/sched/act_api.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index d4b8355737d8..91d79fac8cb2 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -907,6 +907,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (err != ACT_P_CREATED)
module_put(a_o->owner);
+ if (a->goto_chain) {
+ tcf_action_goto_chain_fini(a);
+ a->goto_chain = NULL;
+ }
+
if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
err = tcf_action_goto_chain_init(a, tp);
if (err) {
--
2.20.1
^ permalink raw reply related
* [PATCH RFC 0/5] net/sched: validate the control action with all the other parameters
From: Davide Caratti @ 2019-02-15 23:06 UTC (permalink / raw)
To: Jamal Hadi Salim, Cong Wang, Jiri Pirko
Cc: David S. Miller, Vlad Buslov, Paolo Abeni, netdev
currently, the kernel checks for bad values of the control action in
tcf_action_init_1(), after a successful call to the action's init()
function. This causes three bad behaviors:
1. the "half configuration"
if the action is overwritten, the new configuration data are
applied successfully
# tc action add action gact drop index 100
# tc action replace action gact goto chain 66 index 100 \
> cookie aabbccdd
Error: Failed to init TC action chain
We have an error talking to the kernel
# tc action show action gact
total acts 1
action order 0: gact action goto chain 66
random type none pass val 0
index 100 ref 1 bind 0
cookie aabbccdd
2. a "refcount leak that makes kmemleak complain"
when a valid 'goto chain' action is overwritten with another 'goto chain'
action, the kernel leaks two refcounts.
# tc chain add dev dd0 chain 42 ingress protocol ip flower \
> ip_proto tcp action drop
# tc chain add dev dd0 chain 43 ingress protocol ip flower \
> ip_proto udp action drop
# tc filter add dev dd0 ingress matchall \
> action goto chain 42 index 66
# tc action replace action gact goto chain 43 index 66
Error: Failed to init TC action chain.
We have an error talking to the kernel
# echo scan >/sys/kernel/debug/kmemleak
<...>
unreferenced object 0xffff93c0ee09f000 (size 1024):
comm "tc", pid 2565, jiffies 4295339808 (age 65.426s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 08 00 06 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<000000009b63f92d>] tc_ctl_chain+0x3d2/0x4c0
[<00000000683a8d72>] rtnetlink_rcv_msg+0x263/0x2d0
[<00000000ddd88f8e>] netlink_rcv_skb+0x4a/0x110
[<000000006126a348>] netlink_unicast+0x1a0/0x250
[<00000000b3340877>] netlink_sendmsg+0x2c1/0x3c0
[<00000000a25a2171>] sock_sendmsg+0x36/0x40
[<00000000f19ee1ec>] ___sys_sendmsg+0x280/0x2f0
[<00000000d0422042>] __sys_sendmsg+0x5e/0xa0
[<000000007a6c61f9>] do_syscall_64+0x5b/0x180
[<00000000ccd07542>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[<0000000013eaa334>] 0xffffffffffffffff
3. a "kernel crash in the traffic plane"
when an action is overwritten with an invalid 'goto chain' action,
packets hitting the new rule will trigger a NULL pointer dereference:
# tc qdisc add dev crash0 clsact
# tc filter add dev crash0 egress matchall action csum icmp index 6
# tc action replace action csum icmp goto chain 42 index 6 cookie c1a0c1a0
# ping 1.2.3.4 -Icrash0
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
#PF error: [normal kernel read fault]
PGD 0 P4D 0
Oops: 0000 [#1] SMP PTI
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.0.0-rc4.splash #516
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
RIP: 0010:tcf_action_exec+0xb5/0x100
Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3
RSP: 0018:ffff99933da03be0 EFLAGS: 00010246
RAX: 000000002000002a RBX: ffff99933c463300 RCX: 0000000000003a00
RDX: 0000000000000000 RSI: ffff9992ebda2828 RDI: ffff9992ebda2818
RBP: ffff99933da03c80 R08: 0000000032250000 R09: 0000000000000003
R10: 000000000000003f R11: 0000000000000028 R12: ffff9992ed22c100
R13: ffff9992ed22c108 R14: 0000000000000001 R15: ffff9993339919c0
FS: 0000000000000000(0000) GS:ffff99933da00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000005a0e004 CR4: 00000000001606f0
Call Trace:
<IRQ>
tcf_classify+0x58/0x110
__dev_queue_xmit+0x407/0x890
? ip6_finish_output2+0x366/0x590
ip6_finish_output2+0x366/0x590
? ip6_output+0x68/0x110
ip6_output+0x68/0x110
? nf_hook.constprop.35+0x79/0xc0
mld_sendpack+0x16f/0x220
mld_ifc_timer_expire+0x195/0x2c0
? igmp6_timer_handler+0x70/0x70
call_timer_fn+0x2b/0x130
run_timer_softirq+0x3e8/0x440
? tick_sched_timer+0x37/0x70
__do_softirq+0xe3/0x2f5
irq_exit+0xf0/0x100
smp_apic_timer_interrupt+0x6c/0x130
apic_timer_interrupt+0xf/0x20
</IRQ>
RIP: 0010:native_safe_halt+0x2/0x10
Code: 74 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90
RSP: 0018:ffffffff8be03e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
RAX: ffffffff8b417730 RBX: 0000000000000000 RCX: 7ffffb503267b27c
RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff99933da1d240
RBP: 0000000000000000 R08: 000c515677542b91 R09: 0000000000000000
R10: ffffb312c0cffd98 R11: 0000000000000001 R12: 0000000000000000
all these three problems can be fixed if we validate the control action
in the init() function, in the same way as we are already doing for all
the other parameters.
- patch 1 is a temporary fix for problem 2), but it's reverted at the
end of the series
- we need to refcount and unrefcount chains within init(): patch 2
extends the init() prototype to correctly handle 'goto chain' control
actions.
- patch 3 to [n] fix all the actions, providing a proper error path in
case of bad control action, thus providing a fix for problems 1), 2)
and 3)
- patch [n+1] removes two if statements in tcf_action_init_1() causing
the above problems:
if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
....
}
and
if (!tcf_action_valid(a->tcfa_action)) {
....
}
as they are not not needed anymore, and for the same reason reverts
patch 1.
This RFC series fixes only csum, bpf and gact - so it stops with n=5.
In case there are not objections, I will prepare a series fixing all
the actions and send it targeting the 'net' tree (or also 'net-next',
this behavior is reproducible since the first introduction of 'goto
action').
Any feedback is appreciated, thank you in advance!
Davide Caratti (5):
net/sched: fix refcount leak when 'goto_chain' is used
net/sched: prepare TC actions to properly validate the control action
net/sched: act_bpf: validate the control action inside init()
net/sched: act_csum: validate the control action inside init()
net/sched: act_gact: validate the control action inside init()
include/net/act_api.h | 9 +++++-
net/sched/act_api.c | 63 ++++++++++++++++++++++++++++++++++++--
net/sched/act_bpf.c | 12 ++++++--
net/sched/act_connmark.c | 1 +
net/sched/act_csum.c | 22 ++++++++++---
net/sched/act_gact.c | 17 ++++++++--
net/sched/act_ife.c | 2 +-
net/sched/act_ipt.c | 11 ++++---
net/sched/act_mirred.c | 1 +
net/sched/act_nat.c | 3 +-
net/sched/act_pedit.c | 2 +-
net/sched/act_police.c | 1 +
net/sched/act_sample.c | 2 +-
net/sched/act_simple.c | 2 +-
net/sched/act_skbedit.c | 1 +
net/sched/act_skbmod.c | 1 +
net/sched/act_tunnel_key.c | 1 +
net/sched/act_vlan.c | 2 +-
18 files changed, 131 insertions(+), 22 deletions(-)
--
2.20.1
^ permalink raw reply
* Re: [PATCH bpf-next v2] bpf: make LWTUNNEL_BPF dependent on INET
From: Randy Dunlap @ 2019-02-15 22:55 UTC (permalink / raw)
To: Peter Oskolkov, Alexei Starovoitov, Daniel Borkmann, netdev
Cc: Peter Oskolkov
In-Reply-To: <20190215175135.35549-1-posk@google.com>
On 2/15/19 9:51 AM, Peter Oskolkov wrote:
> Lightweight tunnels are L3 constructs that are used with IP/IP6.
>
> For example, lwtunnel_xmit is called from ip_output.c and
> ip6_output.c only.
>
> Make the dependency explicit at least for LWT-BPF, as now they
> call into IP routing.
>
> V2: added "Reported-by" below.
>
> Reported-by: Randy Dunlap <rdunlap@infradead.org>
> Signed-off-by: Peter Oskolkov <posk@google.com>
Yes, that works. Thanks.
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
> ---
> net/Kconfig | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/Kconfig b/net/Kconfig
> index 5cb9de1aaf88..62da6148e9f8 100644
> --- a/net/Kconfig
> +++ b/net/Kconfig
> @@ -403,7 +403,7 @@ config LWTUNNEL
>
> config LWTUNNEL_BPF
> bool "Execute BPF program as route nexthop action"
> - depends on LWTUNNEL
> + depends on LWTUNNEL && INET
> default y if LWTUNNEL=y
> ---help---
> Allows to run BPF programs as a nexthop action following a route
>
--
~Randy
^ permalink raw reply
* [PATCH net-next v2 0/9] net: Get rid of switchdev_port_attr_get()
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
Hi all,
This patch series splits the removal of the switchdev_ops that was
proposed a few times before and first tackles the easy part which is the
removal of the single call to switchdev_port_attr_get() within the
bridge code.
As suggestd by Ido, this patch series adds a
SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS which is used in the same
context as the caller of switchdev_port_attr_set(), so not deferred, and
then the operation is carried out in deferred context with setting a
support bridge port flag.
Follow-up patches will do the switchdev_ops removal after introducing
the proper helpers for the switchdev blocking notifier to work across
stacked devices (unlike the previous submissions).
Changes in v2:
- differentiate callers not supporting switchdev_port_attr_set() from
the driver not being able to support specific bridge flags
- pass "mask" instead of "flags" for the PRE_BRIDGE_FLAGS check
- skip prepare phase for PRE_BRIDGE_FLAGS
- corrected documentation a bit more
- tested bridge_vlan_aware.sh with veth/VRF
Florian Fainelli (9):
Documentation: networking: switchdev: Update port parent ID section
net: switchdev: Add PORT_PRE_BRIDGE_FLAGS
mlxsw: spectrum: Handle PORT_PRE_BRIDGE_FLAGS
staging: fsl-dpaa2: ethsw: Handle PORT_PRE_BRIDGE_FLAGS
net: dsa: Add setter for SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS
rocker: Check Handle PORT_PRE_BRIDGE_FLAGS
net: bridge: Stop calling switchdev_port_attr_get()
net: Remove SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT
net: Get rid of switchdev_port_attr_get()
Documentation/networking/switchdev.txt | 16 ++--
.../mellanox/mlxsw/spectrum_switchdev.c | 38 +++++-----
drivers/net/ethernet/rocker/rocker_main.c | 75 +++++++++++--------
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 32 ++++----
include/net/switchdev.h | 13 +---
net/bridge/br_switchdev.c | 11 ++-
net/dsa/dsa_priv.h | 6 ++
net/dsa/port.c | 17 +++++
net/dsa/slave.c | 24 +++---
9 files changed, 128 insertions(+), 104 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH net-next v2 2/9] net: switchdev: Add PORT_PRE_BRIDGE_FLAGS
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
In preparation for removing switchdev_port_attr_get(), introduce
PORT_PRE_BRIDGE_FLAGS which will be called through
switchdev_port_attr_set(), in the caller's context (possibly atomic) and
which must be checked by the switchdev driver in order to return whether
the operation is supported or not.
This is entirely analoguous to how the BRIDGE_FLAGS_SUPPORT works,
except it goes through a set() instead of get().
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/net/switchdev.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 5e87b54c5dc5..de72b0a3867f 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -46,6 +46,7 @@ enum switchdev_attr_id {
SWITCHDEV_ATTR_ID_PORT_STP_STATE,
SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
+ SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS,
SWITCHDEV_ATTR_ID_PORT_MROUTER,
SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING,
@@ -61,7 +62,7 @@ struct switchdev_attr {
void (*complete)(struct net_device *dev, int err, void *priv);
union {
u8 stp_state; /* PORT_STP_STATE */
- unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */
+ unsigned long brport_flags; /* PORT_{PRE}_BRIDGE_FLAGS */
unsigned long brport_flags_support; /* PORT_BRIDGE_FLAGS_SUPPORT */
bool mrouter; /* PORT_MROUTER */
clock_t ageing_time; /* BRIDGE_AGEING_TIME */
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 1/9] Documentation: networking: switchdev: Update port parent ID section
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
Update the section about switchdev drivers having to implement a
switchdev_port_attr_get() function to return
SWITCHDEV_ATTR_ID_PORT_PARENT_ID since that is no longer valid after
commit bccb30254a4a ("net: Get rid of
SWITCHDEV_ATTR_ID_PORT_PARENT_ID").
Fixes: bccb30254a4a ("net: Get rid of SWITCHDEV_ATTR_ID_PORT_PARENT_ID")
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
Documentation/networking/switchdev.txt | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index f3244d87512a..ea90243340a9 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -92,11 +92,11 @@ device.
Switch ID
^^^^^^^^^
-The switchdev driver must implement the switchdev op switchdev_port_attr_get
-for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same
-physical ID for each port of a switch. The ID must be unique between switches
-on the same system. The ID does not need to be unique between switches on
-different systems.
+The switchdev driver must implement the net_device operation
+ndo_get_port_parent_id for each port netdev, returning the same physical ID for
+each port of a switch. The ID must be unique between switches on the same
+system. The ID does not need to be unique between switches on different
+systems.
The switch ID is used to locate ports on a switch and to know if aggregated
ports belong to the same switch.
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 5/9] net: dsa: Add setter for SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
In preparation for removing SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
add support for a function that processes the
SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS and
SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS attributes and returns not
supported for any flag set, since DSA does not currently support
toggling those bridge port attributes (yet).
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/dsa/dsa_priv.h | 6 ++++++
net/dsa/port.c | 17 +++++++++++++++++
net/dsa/slave.c | 9 +++++++++
3 files changed, 32 insertions(+)
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 1f4972dab9f2..3d58dc4f4d46 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -150,6 +150,12 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
struct switchdev_trans *trans);
int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock,
struct switchdev_trans *trans);
+int dsa_port_bridge_port_pre_flags_set(struct dsa_port *dp,
+ unsigned long brport_flags,
+ struct switchdev_trans *trans);
+int dsa_port_bridge_port_flags_set(struct dsa_port *dp,
+ unsigned long brport_flags,
+ struct switchdev_trans *trans);
int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr,
u16 vid);
int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 2d7e01b23572..c67a329d4414 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -177,6 +177,23 @@ int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock,
return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info);
}
+int dsa_port_bridge_port_pre_flags_set(struct dsa_port *dp,
+ unsigned long brport_flags,
+ struct switchdev_trans *trans)
+{
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ return -EINVAL;
+}
+
+int dsa_port_bridge_port_flags_set(struct dsa_port *dp,
+ unsigned long brport_flags,
+ struct switchdev_trans *trans)
+{
+ return -EOPNOTSUPP;
+}
+
int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr,
u16 vid)
{
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 2e5e7c04821b..d3370e840956 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -295,6 +295,15 @@ static int dsa_slave_port_attr_set(struct net_device *dev,
case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
ret = dsa_port_ageing_time(dp, attr->u.ageing_time, trans);
break;
+ case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+ ret = dsa_port_bridge_port_pre_flags_set(dp,
+ attr->u.brport_flags,
+ trans);
+ break;
+ case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+ ret = dsa_port_bridge_port_flags_set(dp, attr->u.brport_flags,
+ trans);
+ break;
default:
ret = -EOPNOTSUPP;
break;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 3/9] mlxsw: spectrum: Handle PORT_PRE_BRIDGE_FLAGS
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
In preparation for getting rid of switchdev_port_attr_get(), have mlxsw
check for the bridge flags being set through switchdev_port_attr_set()
when the SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS attribute identifier is
used.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
.../mellanox/mlxsw/spectrum_switchdev.c | 22 ++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 1f492b7dbea8..8cdc0fe17a2e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -595,10 +595,25 @@ mlxsw_sp_bridge_port_learning_set(struct mlxsw_sp_port *mlxsw_sp_port,
return err;
}
+static int mlxsw_sp_port_attr_br_pre_flags_set(struct mlxsw_sp_port
+ *mlxsw_sp_port,
+ struct switchdev_trans *trans,
+ unsigned long brport_flags)
+{
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ if (brport_flags & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD))
+ return -EINVAL;
+
+ return 0;
+}
+
static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
struct switchdev_trans *trans,
struct net_device *orig_dev,
- unsigned long brport_flags)
+ unsigned long brport_flags,
+ bool pre_set)
{
struct mlxsw_sp_bridge_port *bridge_port;
int err;
@@ -841,6 +856,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
attr->orig_dev,
attr->u.stp_state);
break;
+ case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+ err = mlxsw_sp_port_attr_br_pre_flags_set(mlxsw_sp_port,
+ trans,
+ attr->u.brport_flags);
+ break;
case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, trans,
attr->orig_dev,
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 6/9] rocker: Check Handle PORT_PRE_BRIDGE_FLAGS
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
In preparation for getting rid of switchdev_port_attr_get(), have rocker
check for the bridge flags being set through switchdev_port_attr_set()
with the SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS attribute identifier.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/rocker/rocker_main.c | 56 ++++++++++++++++++-----
1 file changed, 44 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 5ce8d5aba603..2102e449c037 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1566,34 +1566,62 @@ static int rocker_world_port_attr_stp_state_set(struct rocker_port *rocker_port,
}
static int
-rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
- unsigned long brport_flags,
- struct switchdev_trans *trans)
+rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port *
+ rocker_port,
+ unsigned long *
+ p_brport_flags_support)
{
struct rocker_world_ops *wops = rocker_port->rocker->wops;
+ if (!wops->port_attr_bridge_flags_support_get)
+ return -EOPNOTSUPP;
+ return wops->port_attr_bridge_flags_support_get(rocker_port,
+ p_brport_flags_support);
+}
+
+static int
+rocker_world_port_attr_bridge_pre_flags_set(struct rocker_port *rocker_port,
+ unsigned long brport_flags,
+ struct switchdev_trans *trans)
+{
+ struct rocker_world_ops *wops = rocker_port->rocker->wops;
+ unsigned long brport_flags_s;
+ int err;
+
if (!wops->port_attr_bridge_flags_set)
return -EOPNOTSUPP;
if (switchdev_trans_ph_prepare(trans))
return 0;
- return wops->port_attr_bridge_flags_set(rocker_port, brport_flags,
- trans);
+ err = rocker_world_port_attr_bridge_flags_support_get(rocker_port,
+ &brport_flags_s);
+ if (err)
+ return err;
+
+ if (brport_flags & ~brport_flags_s)
+ return -EINVAL;
+
+ return 0;
}
static int
-rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port *
- rocker_port,
- unsigned long *
- p_brport_flags_support)
+rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
+ unsigned long brport_flags,
+ struct switchdev_trans *trans)
{
struct rocker_world_ops *wops = rocker_port->rocker->wops;
+ unsigned long brport_flags_s;
+ int err;
- if (!wops->port_attr_bridge_flags_support_get)
+ if (!wops->port_attr_bridge_flags_set)
return -EOPNOTSUPP;
- return wops->port_attr_bridge_flags_support_get(rocker_port,
- p_brport_flags_support);
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ return wops->port_attr_bridge_flags_set(rocker_port, brport_flags,
+ trans);
}
static int
@@ -2074,6 +2102,10 @@ static int rocker_port_attr_set(struct net_device *dev,
attr->u.stp_state,
trans);
break;
+ case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+ err = rocker_world_port_attr_bridge_pre_flags_set(rocker_port,
+ attr->u.brport_flags,
+ trans);
case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
err = rocker_world_port_attr_bridge_flags_set(rocker_port,
attr->u.brport_flags,
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 4/9] staging: fsl-dpaa2: ethsw: Handle PORT_PRE_BRIDGE_FLAGS
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
In preparation for removing SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
handle the SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS attribute and check
that the bridge port flags being configured are supported.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 1b3943b71254..640fd6834be1 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -666,6 +666,19 @@ static int port_attr_stp_state_set(struct net_device *netdev,
return ethsw_port_set_stp_state(port_priv, state);
}
+static int port_attr_br_flags_pre_set(struct net_device *netdev,
+ struct switchdev_trans *trans,
+ unsigned long flags)
+{
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ if (flags & ~(BR_LEARNING | BR_FLOOD))
+ return -EINVAL;
+
+ return 0;
+}
+
static int port_attr_br_flags_set(struct net_device *netdev,
struct switchdev_trans *trans,
unsigned long flags)
@@ -698,6 +711,10 @@ static int swdev_port_attr_set(struct net_device *netdev,
err = port_attr_stp_state_set(netdev, trans,
attr->u.stp_state);
break;
+ case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+ err = port_attr_br_flags_pre_set(netdev, trans,
+ attr->u.brport_flags);
+ break;
case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
err = port_attr_br_flags_set(netdev, trans,
attr->u.brport_flags);
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 7/9] net: bridge: Stop calling switchdev_port_attr_get()
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
Now that all switchdev drivers have been converted to check the
SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS flags and report flags that they
do not support accordingly, we can migrate the bridge code to try to set
that attribute first, check the results and then do the actual setting.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/bridge/br_switchdev.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index db9e8ab96d48..af57c4a2b78a 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -64,21 +64,19 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
{
struct switchdev_attr attr = {
.orig_dev = p->dev,
- .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
+ .id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS,
+ .u.brport_flags = mask,
};
int err;
if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD)
return 0;
- err = switchdev_port_attr_get(p->dev, &attr);
+ err = switchdev_port_attr_set(p->dev, &attr);
if (err == -EOPNOTSUPP)
return 0;
- if (err)
- return err;
- /* Check if specific bridge flag attribute offload is supported */
- if (!(attr.u.brport_flags_support & mask)) {
+ if (err) {
br_warn(p->br, "bridge flag offload is not supported %u(%s)\n",
(unsigned int)p->port_no, p->dev->name);
return -EOPNOTSUPP;
@@ -87,6 +85,7 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p,
attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS;
attr.flags = SWITCHDEV_F_DEFER;
attr.u.brport_flags = flags;
+
err = switchdev_port_attr_set(p->dev, &attr);
if (err) {
br_warn(p->br, "error setting offload flag on port %u(%s)\n",
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 9/9] net: Get rid of switchdev_port_attr_get()
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
With the bridge no longer calling switchdev_port_attr_get() to obtain
the supported bridge port flags from a driver but instead trying to set
the bridge port flags directly and relying on driver to reject
unsupported configurations, we can effectively get rid of
switchdev_port_attr_get() entirely since this was the only place where
it was called.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
Documentation/networking/switchdev.txt | 2 +-
drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 7 -------
drivers/net/ethernet/rocker/rocker_main.c | 7 -------
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 7 -------
include/net/switchdev.h | 8 --------
net/dsa/slave.c | 7 -------
6 files changed, 1 insertion(+), 37 deletions(-)
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index b764568deabf..633dd1fd81b7 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -233,7 +233,7 @@ the bridge's FDB. It's possible, but not optimal, to enable learning on the
device port and on the bridge port, and disable learning_sync.
To support learning, the driver implements switchdev op
-switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_ID_BRIDGE_FLAGS.
+switchdev_port_attr_set for SWITCHDEV_ATTR_PORT_ID_{PRE}_BRIDGE_FLAGS.
FDB Ageing
^^^^^^^^^^
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 2311ef8554d9..d0fcc36f2188 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -431,12 +431,6 @@ static void mlxsw_sp_bridge_vlan_put(struct mlxsw_sp_bridge_vlan *bridge_vlan)
mlxsw_sp_bridge_vlan_destroy(bridge_vlan);
}
-static int mlxsw_sp_port_attr_get(struct net_device *dev,
- struct switchdev_attr *attr)
-{
- return -EOPNOTSUPP;
-}
-
static int
mlxsw_sp_port_bridge_vlan_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
struct mlxsw_sp_bridge_vlan *bridge_vlan,
@@ -1949,7 +1943,6 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
}
static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
- .switchdev_port_attr_get = mlxsw_sp_port_attr_get,
.switchdev_port_attr_set = mlxsw_sp_port_attr_set,
};
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 107fcbec3234..68d8f33113a5 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2071,12 +2071,6 @@ static const struct net_device_ops rocker_port_netdev_ops = {
* swdev interface
********************/
-static int rocker_port_attr_get(struct net_device *dev,
- struct switchdev_attr *attr)
-{
- return -EOPNOTSUPP;
-}
-
static int rocker_port_attr_set(struct net_device *dev,
const struct switchdev_attr *attr,
struct switchdev_trans *trans)
@@ -2153,7 +2147,6 @@ static int rocker_port_obj_del(struct net_device *dev,
}
static const struct switchdev_ops rocker_port_switchdev_ops = {
- .switchdev_port_attr_get = rocker_port_attr_get,
.switchdev_port_attr_set = rocker_port_attr_set,
};
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index e71bc7ed363e..7557f994ef06 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -640,12 +640,6 @@ static void ethsw_teardown_irqs(struct fsl_mc_device *sw_dev)
fsl_mc_free_irqs(sw_dev);
}
-static int swdev_port_attr_get(struct net_device *netdev,
- struct switchdev_attr *attr)
-{
- return -EOPNOTSUPP;
-}
-
static int port_attr_stp_state_set(struct net_device *netdev,
struct switchdev_trans *trans,
u8 state)
@@ -935,7 +929,6 @@ static int swdev_port_obj_del(struct net_device *netdev,
}
static const struct switchdev_ops ethsw_port_switchdev_ops = {
- .switchdev_port_attr_get = swdev_port_attr_get,
.switchdev_port_attr_set = swdev_port_attr_set,
};
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 0f352019ef99..45310ddf2d7e 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -179,8 +179,6 @@ switchdev_notifier_info_to_extack(const struct switchdev_notifier_info *info)
#ifdef CONFIG_NET_SWITCHDEV
void switchdev_deferred_process(void);
-int switchdev_port_attr_get(struct net_device *dev,
- struct switchdev_attr *attr);
int switchdev_port_attr_set(struct net_device *dev,
const struct switchdev_attr *attr);
int switchdev_port_obj_add(struct net_device *dev,
@@ -225,12 +223,6 @@ static inline void switchdev_deferred_process(void)
{
}
-static inline int switchdev_port_attr_get(struct net_device *dev,
- struct switchdev_attr *attr)
-{
- return -EOPNOTSUPP;
-}
-
static inline int switchdev_port_attr_set(struct net_device *dev,
const struct switchdev_attr *attr)
{
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 06aa7376d968..07a98b17f2ac 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -387,12 +387,6 @@ static int dsa_slave_get_port_parent_id(struct net_device *dev,
return 0;
}
-static int dsa_slave_port_attr_get(struct net_device *dev,
- struct switchdev_attr *attr)
-{
- return -EOPNOTSUPP;
-}
-
static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev,
struct sk_buff *skb)
{
@@ -1059,7 +1053,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
};
static const struct switchdev_ops dsa_slave_switchdev_ops = {
- .switchdev_port_attr_get = dsa_slave_port_attr_get,
.switchdev_port_attr_set = dsa_slave_port_attr_set,
};
--
2.17.1
^ permalink raw reply related
* [PATCH net-next v2 8/9] net: Remove SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT
From: Florian Fainelli @ 2019-02-15 22:53 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190215225313.32303-1-f.fainelli@gmail.com>
Now that we have converted the bridge code and the drivers to check for
bridge port(s) flags at the time we try to set them, there is no need
for a get() -> set() sequence anymore and
SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT therefore becomes unused.
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
Documentation/networking/switchdev.txt | 6 ++----
.../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 11 +----------
drivers/net/ethernet/rocker/rocker_main.c | 14 +-------------
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 10 +---------
include/net/switchdev.h | 2 --
net/dsa/slave.c | 10 +---------
6 files changed, 6 insertions(+), 47 deletions(-)
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index ea90243340a9..b764568deabf 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -232,10 +232,8 @@ Learning_sync attribute enables syncing of the learned/forgotten FDB entry to
the bridge's FDB. It's possible, but not optimal, to enable learning on the
device port and on the bridge port, and disable learning_sync.
-To support learning and learning_sync port attributes, the driver implements
-switchdev op switchdev_port_attr_get/set for
-SWITCHDEV_ATTR_PORT_ID_BRIDGE_FLAGS. The driver should initialize the attributes
-to the hardware defaults.
+To support learning, the driver implements switchdev op
+switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_ID_BRIDGE_FLAGS.
FDB Ageing
^^^^^^^^^^
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 8cdc0fe17a2e..2311ef8554d9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -434,16 +434,7 @@ static void mlxsw_sp_bridge_vlan_put(struct mlxsw_sp_bridge_vlan *bridge_vlan)
static int mlxsw_sp_port_attr_get(struct net_device *dev,
struct switchdev_attr *attr)
{
- switch (attr->id) {
- case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
- attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD |
- BR_MCAST_FLOOD;
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- return 0;
+ return -EOPNOTSUPP;
}
static int
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 2102e449c037..107fcbec3234 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2074,19 +2074,7 @@ static const struct net_device_ops rocker_port_netdev_ops = {
static int rocker_port_attr_get(struct net_device *dev,
struct switchdev_attr *attr)
{
- const struct rocker_port *rocker_port = netdev_priv(dev);
- int err = 0;
-
- switch (attr->id) {
- case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
- err = rocker_world_port_attr_bridge_flags_support_get(rocker_port,
- &attr->u.brport_flags_support);
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- return err;
+ return -EOPNOTSUPP;
}
static int rocker_port_attr_set(struct net_device *dev,
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 640fd6834be1..e71bc7ed363e 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -643,15 +643,7 @@ static void ethsw_teardown_irqs(struct fsl_mc_device *sw_dev)
static int swdev_port_attr_get(struct net_device *netdev,
struct switchdev_attr *attr)
{
- switch (attr->id) {
- case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
- attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD;
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- return 0;
+ return -EOPNOTSUPP;
}
static int port_attr_stp_state_set(struct net_device *netdev,
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index de72b0a3867f..0f352019ef99 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -45,7 +45,6 @@ enum switchdev_attr_id {
SWITCHDEV_ATTR_ID_UNDEFINED,
SWITCHDEV_ATTR_ID_PORT_STP_STATE,
SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
- SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS,
SWITCHDEV_ATTR_ID_PORT_MROUTER,
SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
@@ -63,7 +62,6 @@ struct switchdev_attr {
union {
u8 stp_state; /* PORT_STP_STATE */
unsigned long brport_flags; /* PORT_{PRE}_BRIDGE_FLAGS */
- unsigned long brport_flags_support; /* PORT_BRIDGE_FLAGS_SUPPORT */
bool mrouter; /* PORT_MROUTER */
clock_t ageing_time; /* BRIDGE_AGEING_TIME */
bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index d3370e840956..06aa7376d968 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -390,15 +390,7 @@ static int dsa_slave_get_port_parent_id(struct net_device *dev,
static int dsa_slave_port_attr_get(struct net_device *dev,
struct switchdev_attr *attr)
{
- switch (attr->id) {
- case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
- attr->u.brport_flags_support = 0;
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- return 0;
+ return -EOPNOTSUPP;
}
static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev,
--
2.17.1
^ permalink raw reply related
* Re: [rdma-rc PATCH 0/2] iw_cxgb4: Adjust the cq/qp mask
From: Jason Gunthorpe @ 2019-02-15 22:47 UTC (permalink / raw)
To: Raju Rangoju; +Cc: davem, linux-rdma, netdev, swise
In-Reply-To: <20190214121054.11693-1-rajur@chelsio.com>
On Thu, Feb 14, 2019 at 05:40:52PM +0530, Raju Rangoju wrote:
> Export the LLD sge_host_page_size field to ULDs via
> cxgb4_lld_info, so that iw_cxgb4 can adjust the cq/qp
> mask based on no.of bar2 pages in a host page.
>
> This series has both net(cxgb4) and rdma(iw_cxgb4) changes,
> and I would request this merge via rdma repo.
>
> I have made sure this series applies cleanly on both net-next
> and rdma-for-rc and doesn't cause any merge conflicts.
>
> Raju Rangoju (2):
> cxgb4: export sge_host_page_size to ulds
> iw_cxgb4: cq/qp mask depends on bar2 pages in a host page
As requested, applied to for-rc with some revisions to the commit
messages.
Thanks,
Jason
^ permalink raw reply
* Re: [PATCH net-next 11/12] net: sched: flower: track rtnl lock state
From: Stefano Brivio @ 2019-02-15 22:46 UTC (permalink / raw)
To: Vlad Buslov; +Cc: netdev, jhs, xiyou.wangcong, jiri, davem
In-Reply-To: <20190214074712.17846-12-vladbu@mellanox.com>
On Thu, 14 Feb 2019 09:47:11 +0200
Vlad Buslov <vladbu@mellanox.com> wrote:
> static int fl_hw_replace_filter(struct tcf_proto *tp,
> - struct cls_fl_filter *f,
> + struct cls_fl_filter *f, bool rtnl_held,
> struct netlink_ext_ack *extack)
> {
> struct tc_cls_flower_offload cls_flower = {};
> struct tcf_block *block = tp->chain->block;
> bool skip_sw = tc_skip_sw(f->flags);
> - int err;
> + int err = 0;
> +
> + if (!rtnl_held)
> + rtnl_lock();
>
> cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts));
> if (!cls_flower.rule)
return -ENOMEM;
Don't you need to:
err = -ENOMEM;
goto errout;
here?
Same...
err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts);
if (err) {
kfree(cls_flower.rule);
if (skip_sw) {
NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
return err;
here,
}
return 0;
and here.
--
Stefano
^ permalink raw reply
* Re: Three questions about busy poll
From: Willem de Bruijn @ 2019-02-15 22:46 UTC (permalink / raw)
To: Cong Wang
Cc: Alexander Duyck, Eric Dumazet, sridhar.samudrala,
Linux Kernel Network Developers
In-Reply-To: <CAM_iQpXYzPQ99foOzyN33xJDE7vdBWVg5ZNxrO6kuDAP1OLePQ@mail.gmail.com>
> > > 2. Why there is no socket option for sysctl.net.busy_poll? Clearly
> > > sysctl_net_busy_poll is global and SO_BUSY_POLL only works for
> > > sysctl.net.busy_read.
> >
> > I guess because of how sock_poll works. In that case it is not needed.
> > The poll duration applies more to the pollset than any of the
> > individual sockets, too.
>
>
> Good point, it's probably like struct eventpoll vs. struct epitem.
>
> The reason why I am looking for a per-socket tuning is to minimize
> the impact of setting busy_poll. I don't know if it is possible to somehow
> make this per-socket via epoll interfaces, perhaps fundamentally
> it is impossible?
I think it may be possible. The way busy_read and busy_poll work
in sock_poll is that the sum of all (per socket tunable) busy_read
durations on the sockets in the pollset is ~bound by (global) busy_poll.
The epoll implementation is restricted in the sense that it polls only
on one napi_id at a time. Alongside setting ep->napi_id in
ep_set_busy_poll_napi_id, we could also set a new ep field takes
the min of the global busy_poll and sk->sk_ll_usec.
Though I guess you want to be able to poll on a given pollset
without setting the global sysctl_net_busy_poll at all? That
would be a useful feature both for epoll and poll/select. But
definitely requires refining net_busy_loop_on() to optionally
take some state derived from the sockets in the (e)pollset.
^ permalink raw reply
* Re: [PATCH net-next 06/12] net: sched: flower: handle concurrent mask insertion
From: Stefano Brivio @ 2019-02-15 22:46 UTC (permalink / raw)
To: Vlad Buslov; +Cc: netdev, jhs, xiyou.wangcong, jiri, davem
In-Reply-To: <20190214074712.17846-7-vladbu@mellanox.com>
On Thu, 14 Feb 2019 09:47:06 +0200
Vlad Buslov <vladbu@mellanox.com> wrote:
> @@ -1327,19 +1330,36 @@ static int fl_check_assign_mask(struct cls_fl_head *head,
> int ret = 0;
>
> rcu_read_lock();
> - fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params);
> +
> + /* Insert mask as temporary node to prevent concurrent creation of mask
> + * with same key. Any concurrent lookups with same key will return
> + * EAGAIN because mask's refcnt is zero. It is safe to insert
Nit: -EAGAIN
--
Stefano
^ permalink raw reply
* [net PATCH 2/2] net: Do not allocate page fragments that are not skb aligned
From: Alexander Duyck @ 2019-02-15 22:44 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-mm, linux-kernel, jannh
In-Reply-To: <20190215223741.16881.84864.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
This patch addresses the fact that there are drivers, specifically tun,
that will call into the network page fragment allocators with buffer sizes
that are not cache aligned. Doing this could result in data alignment
and DMA performance issues as these fragment pools are also shared with the
skb allocator and any other devices that will use napi_alloc_frags or
netdev_alloc_frags.
Fixes: ffde7328a36d ("net: Split netdev_alloc_frag into __alloc_page_frag and add __napi_alloc_frag")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
net/core/skbuff.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 26d848484912..2415d9cb9b89 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -356,6 +356,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
*/
void *netdev_alloc_frag(unsigned int fragsz)
{
+ fragsz = SKB_DATA_ALIGN(fragsz);
+
return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(netdev_alloc_frag);
@@ -369,6 +371,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
void *napi_alloc_frag(unsigned int fragsz)
{
+ fragsz = SKB_DATA_ALIGN(fragsz);
+
return __napi_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(napi_alloc_frag);
^ permalink raw reply related
* [net PATCH 1/2] mm: Use fixed constant in page_frag_alloc instead of size + 1
From: Alexander Duyck @ 2019-02-15 22:44 UTC (permalink / raw)
To: netdev, davem; +Cc: linux-mm, linux-kernel, jannh
In-Reply-To: <20190215223741.16881.84864.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
This patch replaces the size + 1 value introduced with the recent fix for 1
byte allocs with a constant value.
The idea here is to reduce code overhead as the previous logic would have
to read size into a register, then increment it, and write it back to
whatever field was being used. By using a constant we can avoid those
memory reads and arithmetic operations in favor of just encoding the
maximum value into the operation itself.
Fixes: 2c2ade81741c ("mm: page_alloc: fix ref bias in page_frag_alloc() for 1-byte allocs")
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
mm/page_alloc.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ebb35e4d0d90..37ed14ad0b59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4857,11 +4857,11 @@ void *page_frag_alloc(struct page_frag_cache *nc,
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
- page_ref_add(page, size);
+ page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
/* reset page count bias and offset to start of new frag */
nc->pfmemalloc = page_is_pfmemalloc(page);
- nc->pagecnt_bias = size + 1;
+ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
nc->offset = size;
}
@@ -4877,10 +4877,10 @@ void *page_frag_alloc(struct page_frag_cache *nc,
size = nc->size;
#endif
/* OK, page count is 0, we can safely set it */
- set_page_count(page, size + 1);
+ set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
/* reset page count bias and offset to start of new frag */
- nc->pagecnt_bias = size + 1;
+ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
offset = size - fragsz;
}
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox