* [PATCH net-next v2 2/4] net: dsa: b53: Add mirror capture register definitions
From: Florian Fainelli @ 2017-01-28 1:25 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128012528.30524-1-f.fainelli@gmail.com>
Add definitions for the different Roboswitch registers relevant for
ingress and egress mirroring.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/b53/b53_regs.h | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index dac0af4e2cd0..9fd24c418fa4 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -206,6 +206,38 @@
#define BRCM_HDR_P8_EN BIT(0) /* Enable tagging on port 8 */
#define BRCM_HDR_P5_EN BIT(1) /* Enable tagging on port 5 */
+/* Mirror capture control register (16 bit) */
+#define B53_MIR_CAP_CTL 0x10
+#define CAP_PORT_MASK 0xf
+#define BLK_NOT_MIR BIT(14)
+#define MIRROR_EN BIT(15)
+
+/* Ingress mirror control register (16 bit) */
+#define B53_IG_MIR_CTL 0x12
+#define MIRROR_MASK 0x1ff
+#define DIV_EN BIT(13)
+#define MIRROR_FILTER_MASK 0x3
+#define MIRROR_FILTER_SHIFT 14
+#define MIRROR_ALL 0
+#define MIRROR_DA 1
+#define MIRROR_SA 2
+
+/* Ingress mirror divider register (16 bit) */
+#define B53_IG_MIR_DIV 0x14
+#define IN_MIRROR_DIV_MASK 0x3ff
+
+/* Ingress mirror MAC address register (48 bit) */
+#define B53_IG_MIR_MAC 0x16
+
+/* Egress mirror control register (16 bit) */
+#define B53_EG_MIR_CTL 0x1C
+
+/* Egress mirror divider register (16 bit) */
+#define B53_EG_MIR_DIV 0x1E
+
+/* Egress mirror MAC address register (48 bit) */
+#define B53_EG_MIR_MAC 0x20
+
/* Device ID register (8 or 32 bit) */
#define B53_DEVICE_ID 0x30
--
2.9.3
^ permalink raw reply related
* [PATCH net-next v2 3/4] net: dsa: b53: Add support for port mirroring
From: Florian Fainelli @ 2017-01-28 1:25 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128012528.30524-1-f.fainelli@gmail.com>
Add support for configuring port mirroring through the cls_matchall
classifier. We do a full ingress or egress capture towards the capture
port. Future improvements could include leveraging the divider to allow
less frames to be captured, as well as matching specific MAC DA/SA.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/b53/b53_common.c | 67 ++++++++++++++++++++++++++++++++++++++++
drivers/net/dsa/b53/b53_priv.h | 4 +++
2 files changed, 71 insertions(+)
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index bb210b12ad1b..052ff4c22667 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1453,6 +1453,71 @@ static enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds)
return DSA_TAG_PROTO_NONE;
}
+int b53_mirror_add(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror, bool ingress)
+{
+ struct b53_device *dev = ds->priv;
+ u16 reg, loc;
+
+ if (ingress)
+ loc = B53_IG_MIR_CTL;
+ else
+ loc = B53_EG_MIR_CTL;
+
+ b53_read16(dev, B53_MGMT_PAGE, loc, ®);
+ reg &= ~MIRROR_MASK;
+ reg |= BIT(port);
+ b53_write16(dev, B53_MGMT_PAGE, loc, reg);
+
+ b53_read16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, ®);
+ reg &= ~CAP_PORT_MASK;
+ reg |= mirror->to_local_port;
+ reg |= MIRROR_EN;
+ b53_write16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, reg);
+
+ return 0;
+}
+EXPORT_SYMBOL(b53_mirror_add);
+
+void b53_mirror_del(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror)
+{
+ struct b53_device *dev = ds->priv;
+ bool loc_disable = false, other_loc_disable = false;
+ u16 reg, loc;
+
+ if (mirror->ingress)
+ loc = B53_IG_MIR_CTL;
+ else
+ loc = B53_EG_MIR_CTL;
+
+ /* Update the desired ingress/egress register */
+ b53_read16(dev, B53_MGMT_PAGE, loc, ®);
+ reg &= ~BIT(port);
+ if (!(reg & MIRROR_MASK))
+ loc_disable = true;
+ b53_write16(dev, B53_MGMT_PAGE, loc, reg);
+
+ /* Now look at the other one to know if we can disable mirroring
+ * entirely
+ */
+ if (mirror->ingress)
+ b53_read16(dev, B53_MGMT_PAGE, B53_EG_MIR_CTL, ®);
+ else
+ b53_read16(dev, B53_MGMT_PAGE, B53_IG_MIR_CTL, ®);
+ if (!(reg & MIRROR_MASK))
+ other_loc_disable = true;
+
+ b53_read16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, ®);
+ /* Both no longer have ports, let's disable mirroring */
+ if (loc_disable && other_loc_disable) {
+ reg &= ~MIRROR_EN;
+ reg &= ~mirror->to_local_port;
+ }
+ b53_write16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, reg);
+}
+EXPORT_SYMBOL(b53_mirror_del);
+
static const struct dsa_switch_ops b53_switch_ops = {
.get_tag_protocol = b53_get_tag_protocol,
.setup = b53_setup,
@@ -1477,6 +1542,8 @@ static const struct dsa_switch_ops b53_switch_ops = {
.port_fdb_dump = b53_fdb_dump,
.port_fdb_add = b53_fdb_add,
.port_fdb_del = b53_fdb_del,
+ .port_mirror_add = b53_mirror_add,
+ .port_mirror_del = b53_mirror_del,
};
struct b53_chip_data {
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index a8031b382c55..28ffe255276f 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -408,5 +408,9 @@ int b53_fdb_del(struct dsa_switch *ds, int port,
int b53_fdb_dump(struct dsa_switch *ds, int port,
struct switchdev_obj_port_fdb *fdb,
int (*cb)(struct switchdev_obj *obj));
+int b53_mirror_add(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror, bool ingress);
+void b53_mirror_del(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror);
#endif
--
2.9.3
^ permalink raw reply related
* [PATCH net-next v2 1/4] net: dsa: Add plumbing for port mirroring
From: Florian Fainelli @ 2017-01-28 1:25 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128012528.30524-1-f.fainelli@gmail.com>
Add necessary plumbing at the slave network device level to have switch
drivers implement ndo_setup_tc() and most particularly the cls_matchall
classifier. We add support for two switch operations:
port_add_mirror and port_del_mirror() which configure, on a per-port
basis the mirror parameters requested from the cls_matchall classifier.
Code is largely borrowed from the Mellanox Spectrum switch driver.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/net/dsa.h | 36 ++++++++++++++
net/dsa/dsa_priv.h | 3 ++
net/dsa/slave.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 181 insertions(+), 1 deletion(-)
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 92fd795e9573..831a789594f1 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -20,6 +20,8 @@
#include <linux/phy_fixed.h>
#include <linux/ethtool.h>
+struct tc_action;
+
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = 0,
DSA_TAG_PROTO_DSA,
@@ -139,6 +141,31 @@ struct dsa_switch_tree {
const struct dsa_device_ops *tag_ops;
};
+enum dsa_port_mall_action_type {
+ DSA_PORT_MALL_MIRROR,
+};
+
+/*
+ * Mirroring TC entry
+ */
+struct dsa_mall_mirror_tc_entry {
+ u8 to_local_port;
+ bool ingress;
+};
+
+/*
+ * TC matchall entry
+ */
+struct dsa_mall_tc_entry {
+ struct list_head list;
+ unsigned long cookie;
+ enum dsa_port_mall_action_type type;
+ union {
+ struct dsa_mall_mirror_tc_entry mirror;
+ };
+};
+
+
struct dsa_port {
struct net_device *netdev;
struct device_node *dn;
@@ -370,6 +397,15 @@ struct dsa_switch_ops {
int (*port_mdb_dump)(struct dsa_switch *ds, int port,
struct switchdev_obj_port_mdb *mdb,
int (*cb)(struct switchdev_obj *obj));
+
+ /*
+ * TC integration
+ */
+ int (*port_mirror_add)(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror,
+ bool ingress);
+ void (*port_mirror_del)(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror);
};
struct dsa_switch_driver {
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 16194a4bb2fe..b10b03028b24 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -46,6 +46,9 @@ struct dsa_slave_priv {
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
#endif
+
+ /* TC context */
+ struct list_head mall_tc_list;
};
/* dsa.c */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index b8e58689a9a1..a5f9f1ebca2e 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -16,12 +16,17 @@
#include <linux/of_net.h>
#include <linux/of_mdio.h>
#include <linux/mdio.h>
+#include <linux/list.h>
#include <net/rtnetlink.h>
#include <net/switchdev.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_mirred.h>
#include <linux/if_bridge.h>
#include <linux/netpoll.h>
#include "dsa_priv.h"
+static bool dsa_slave_dev_check(struct net_device *dev);
+
/* slave mii_bus handling ***************************************************/
static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
{
@@ -994,6 +999,139 @@ static int dsa_slave_get_phys_port_name(struct net_device *dev,
return 0;
}
+static struct dsa_mall_tc_entry *
+dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p,
+ unsigned long cookie)
+{
+ struct dsa_mall_tc_entry *mall_tc_entry;
+
+ list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list)
+ if (mall_tc_entry->cookie == cookie)
+ return mall_tc_entry;
+
+ return NULL;
+}
+
+static int dsa_slave_add_cls_matchall(struct net_device *dev,
+ __be16 protocol,
+ struct tc_cls_matchall_offload *cls,
+ bool ingress)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_mall_tc_entry *mall_tc_entry;
+ struct dsa_switch *ds = p->parent;
+ struct net *net = dev_net(dev);
+ struct dsa_slave_priv *to_p;
+ struct net_device *to_dev;
+ const struct tc_action *a;
+ int err = -EOPNOTSUPP;
+ LIST_HEAD(actions);
+ int ifindex;
+
+ if (!ds->ops->port_mirror_add)
+ return err;
+
+ if (!tc_single_action(cls->exts)) {
+ netdev_err(dev, "only singular actions are supported\n");
+ return err;
+ }
+
+ mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
+ if (!mall_tc_entry)
+ return -ENOMEM;
+ mall_tc_entry->cookie = cls->cookie;
+
+ tcf_exts_to_list(cls->exts, &actions);
+ a = list_first_entry(&actions, struct tc_action, list);
+
+ if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) {
+ struct dsa_mall_mirror_tc_entry *mirror;
+
+ mall_tc_entry->type = DSA_PORT_MALL_MIRROR;
+ mirror = &mall_tc_entry->mirror;
+
+ ifindex = tcf_mirred_ifindex(a);
+ to_dev = __dev_get_by_index(net, ifindex);
+ if (!to_dev) {
+ err = -EINVAL;
+ goto err_add_action;
+ }
+
+ if (!dsa_slave_dev_check(to_dev)) {
+ err = -EOPNOTSUPP;
+ goto err_add_action;
+ }
+
+ to_p = netdev_priv(to_dev);
+
+ mirror->to_local_port = to_p->port;
+ mirror->ingress = ingress;
+
+ err = ds->ops->port_mirror_add(ds, p->port, mirror, ingress);
+ }
+
+ if (err)
+ goto err_add_action;
+
+ list_add_tail(&mall_tc_entry->list, &p->mall_tc_list);
+ return 0;
+
+err_add_action:
+ kfree(mall_tc_entry);
+ return err;
+}
+
+static void dsa_slave_del_cls_matchall(struct net_device *dev,
+ struct tc_cls_matchall_offload *cls)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_mall_tc_entry *mall_tc_entry;
+ struct dsa_switch *ds = p->parent;
+
+ if (!ds->ops->port_mirror_del)
+ return;
+
+ mall_tc_entry = dsa_slave_mall_tc_entry_find(p, cls->cookie);
+ if (!mall_tc_entry)
+ return;
+
+ list_del(&mall_tc_entry->list);
+
+ switch (mall_tc_entry->type) {
+ case DSA_PORT_MALL_MIRROR:
+ ds->ops->port_mirror_del(ds, p->port, &mall_tc_entry->mirror);
+ break;
+ default:
+ WARN_ON(1);
+ }
+
+ kfree(mall_tc_entry);
+}
+
+static int dsa_slave_setup_tc(struct net_device *dev, u32 handle,
+ __be16 protocol, struct tc_to_netdev *tc)
+{
+ bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS);
+ int ret = -EOPNOTSUPP;
+
+ switch (tc->type) {
+ case TC_SETUP_MATCHALL:
+ switch (tc->cls_mall->command) {
+ case TC_CLSMATCHALL_REPLACE:
+ return dsa_slave_add_cls_matchall(dev, protocol,
+ tc->cls_mall,
+ ingress);
+ case TC_CLSMATCHALL_DESTROY:
+ dsa_slave_del_cls_matchall(dev, tc->cls_mall);
+ return 0;
+ }
+ default:
+ break;
+ }
+
+ return ret;
+}
+
void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops)
{
ops->get_sset_count = dsa_cpu_port_get_sset_count;
@@ -1042,6 +1180,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
.ndo_bridge_setlink = switchdev_port_bridge_setlink,
.ndo_bridge_dellink = switchdev_port_bridge_dellink,
.ndo_get_phys_port_name = dsa_slave_get_phys_port_name,
+ .ndo_setup_tc = dsa_slave_setup_tc,
};
static const struct switchdev_ops dsa_slave_switchdev_ops = {
@@ -1257,7 +1396,8 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
if (slave_dev == NULL)
return -ENOMEM;
- slave_dev->features = master->vlan_features;
+ slave_dev->features = master->vlan_features | NETIF_F_HW_TC;
+ slave_dev->hw_features |= NETIF_F_HW_TC;
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
eth_hw_addr_inherit(slave_dev, master);
slave_dev->priv_flags |= IFF_NO_QUEUE;
@@ -1275,6 +1415,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
slave_dev->vlan_features = master->vlan_features;
p = netdev_priv(slave_dev);
+ INIT_LIST_HEAD(&p->mall_tc_list);
p->parent = ds;
p->port = port;
p->xmit = dst->tag_ops->xmit;
--
2.9.3
^ permalink raw reply related
* [PATCH net-next v2 0/4] net: dsa: Port mirroring support
From: Florian Fainelli @ 2017-01-28 1:25 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
Hi all,
This patch series adds support for port mirroring in the two
Broadcom switch drivers. The major part of the functional are actually with
the plumbing between tc and the drivers.
David, this will most likely conflict a little bit with my other series:
net: dsa: bcm_sf2: CFP support, so just let me know if that happens, and
I will provide a rebased version. Thanks!
Changes in v2:
- fixed filter removal logic to disable the ingress or egress mirroring
when there are no longer ports being monitored in ingress or egress
- removed a stray list_head in dsa_port structure that is not used
Tested using the two iproute2 examples:
# ingress
tc qdisc add dev eth1 handle ffff: ingress
tc filter add dev eth1 parent ffff: \
matchall skip_sw \
action mirred egress mirror \
dev eth2
# egress
tc qdisc add dev eth1 handle 1: root prio
tc filter add dev eth1 parent 1: \
matchall skip_sw \
action mirred egress mirror \
dev eth2
Florian Fainelli (4):
net: dsa: Add plumbing for port mirroring
net: dsa: b53: Add mirror capture register definitions
net: dsa: b53: Add support for port mirroring
net: dsa: bcm_sf2: Add support for port mirroring
drivers/net/dsa/b53/b53_common.c | 67 ++++++++++++++++++
drivers/net/dsa/b53/b53_priv.h | 4 ++
drivers/net/dsa/b53/b53_regs.h | 32 +++++++++
drivers/net/dsa/bcm_sf2.c | 2 +
include/net/dsa.h | 36 ++++++++++
net/dsa/dsa_priv.h | 3 +
net/dsa/slave.c | 143 ++++++++++++++++++++++++++++++++++++++-
7 files changed, 286 insertions(+), 1 deletion(-)
--
2.9.3
^ permalink raw reply
* Re: net: suspicious RCU usage in nf_hook
From: Cong Wang @ 2017-01-28 1:00 UTC (permalink / raw)
To: Eric Dumazet
Cc: Dmitry Vyukov, David Miller, Alexey Kuznetsov, Eric Dumazet,
James Morris, Hideaki YOSHIFUJI, Patrick McHardy, netdev, LKML,
Pablo Neira Ayuso, netfilter-devel, syzkaller
In-Reply-To: <1485560124.6360.74.camel@edumazet-glaptop3.roam.corp.google.com>
On Fri, Jan 27, 2017 at 3:35 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Oh well, I forgot to submit the official patch I think, Jan 9th.
>
> https://groups.google.com/forum/#!topic/syzkaller/BhyN5OFd7sQ
>
Hmm, but why only fragments need skb_orphan()? It seems like
any kfree_skb() inside a nf hook needs to have a preceding
skb_orphan().
Also, I am not convinced it is similar to commit 8282f27449bf15548
which is on RX path.
^ permalink raw reply
* Re: [PATCH net-next 0/4] net: dsa: Port mirroring support
From: Florian Fainelli @ 2017-01-28 0:52 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy
In-Reply-To: <20170128004035.26035-1-f.fainelli@gmail.com>
On 01/27/2017 04:40 PM, Florian Fainelli wrote:
> Hi all,
>
> This patch series adds support for port mirroring in the two
> Broadcom switch drivers. The major part of the functional are actually with
> the plumbing between tc and the drivers.
Meh, there are two issues that need fixing:
- left a stray list_head in the dsa_port structure which we do not need
- if we remove either the ingress, or egress filter, we end-up disabling
the mirroring entirely, so need to rework the b53_mirror_del logic a bit
Will re-submit shortly.
>
> David, this will most likely conflict a little bit with my other series:
> net: dsa: bcm_sf2: CFP support, so just let me know if that happens, and
> I will provide a rebased version. Thanks!
>
> Tested using the two iproute2 examples:
>
> # ingress
> tc qdisc add dev eth1 handle ffff: ingress
> tc filter add dev eth1 parent ffff: \
> matchall skip_sw \
> action mirred egress mirror \
> dev eth2
> # egress
> tc qdisc add dev eth1 handle 1: root prio
> tc filter add dev eth1 parent 1: \
> matchall skip_sw \
> action mirred egress mirror \
> dev eth2
>
>
> Florian Fainelli (4):
> net: dsa: Add plumbing for port mirroring
> net: dsa: b53: Add mirror capture register definitions
> net: dsa: b53: Add support for port mirroring
> net: dsa: bcm_sf2: Add support for port mirroring
>
> drivers/net/dsa/b53/b53_common.c | 54 +++++++++++++++
> drivers/net/dsa/b53/b53_priv.h | 4 ++
> drivers/net/dsa/b53/b53_regs.h | 32 +++++++++
> drivers/net/dsa/bcm_sf2.c | 2 +
> include/net/dsa.h | 41 +++++++++++
> net/dsa/dsa_priv.h | 3 +
> net/dsa/slave.c | 143 ++++++++++++++++++++++++++++++++++++++-
> 7 files changed, 278 insertions(+), 1 deletion(-)
>
--
Florian
^ permalink raw reply
* [PATCH net-next 4/4] net: dsa: bcm_sf2: Add support for port mirroring
From: Florian Fainelli @ 2017-01-28 0:40 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128004035.26035-1-f.fainelli@gmail.com>
We can use b53_mirror_add and b53_mirror_del because the Starfighter 2
is register compatible in that specific case.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/bcm_sf2.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 8eecfd227e06..3e514d7af218 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1036,6 +1036,8 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
.port_fdb_dump = b53_fdb_dump,
.port_fdb_add = b53_fdb_add,
.port_fdb_del = b53_fdb_del,
+ .port_mirror_add = b53_mirror_add,
+ .port_mirror_del = b53_mirror_del,
};
struct bcm_sf2_of_data {
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 3/4] net: dsa: b53: Add support for port mirroring
From: Florian Fainelli @ 2017-01-28 0:40 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128004035.26035-1-f.fainelli@gmail.com>
Add support for configuring port mirroring through the cls_matchall
classifier. We do a full ingress or egress capture towards the capture
port. Future improvements could include leveraging the divider to allow
less frames to be captured, as well as matching specific MAC DA/SA.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/b53/b53_common.c | 54 ++++++++++++++++++++++++++++++++++++++++
drivers/net/dsa/b53/b53_priv.h | 4 +++
2 files changed, 58 insertions(+)
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index bb210b12ad1b..5c9dc4bf7b22 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1453,6 +1453,58 @@ static enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds)
return DSA_TAG_PROTO_NONE;
}
+int b53_mirror_add(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror, bool ingress)
+{
+ struct b53_device *dev = ds->priv;
+ u16 reg, loc;
+
+ if (ingress)
+ loc = B53_IG_MIR_CTL;
+ else
+ loc = B53_EG_MIR_CTL;
+
+ b53_read16(dev, B53_MGMT_PAGE, loc, ®);
+ reg &= ~MIRROR_MASK;
+ reg |= BIT(port);
+ b53_write16(dev, B53_MGMT_PAGE, loc, reg);
+
+ b53_read16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, ®);
+ reg &= ~CAP_PORT_MASK;
+ reg |= mirror->to_local_port;
+ reg |= MIRROR_EN;
+ b53_write16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, reg);
+
+ return 0;
+}
+EXPORT_SYMBOL(b53_mirror_add);
+
+void b53_mirror_del(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror)
+{
+ struct b53_device *dev = ds->priv;
+ bool disable_mirror = false;
+ u16 reg, loc;
+
+ if (mirror->ingress)
+ loc = B53_IG_MIR_CTL;
+ else
+ loc = B53_EG_MIR_CTL;
+
+ b53_read16(dev, B53_MGMT_PAGE, loc, ®);
+ reg &= ~BIT(port);
+ if (!(reg & MIRROR_MASK))
+ disable_mirror = true;
+ b53_write16(dev, B53_MGMT_PAGE, loc, reg);
+
+ b53_read16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, ®);
+ if (disable_mirror)
+ reg &= ~MIRROR_EN;
+ reg &= ~mirror->to_local_port;
+ b53_write16(dev, B53_MGMT_PAGE, B53_MIR_CAP_CTL, reg);
+}
+EXPORT_SYMBOL(b53_mirror_del);
+
static const struct dsa_switch_ops b53_switch_ops = {
.get_tag_protocol = b53_get_tag_protocol,
.setup = b53_setup,
@@ -1477,6 +1529,8 @@ static const struct dsa_switch_ops b53_switch_ops = {
.port_fdb_dump = b53_fdb_dump,
.port_fdb_add = b53_fdb_add,
.port_fdb_del = b53_fdb_del,
+ .port_mirror_add = b53_mirror_add,
+ .port_mirror_del = b53_mirror_del,
};
struct b53_chip_data {
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index a8031b382c55..28ffe255276f 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -408,5 +408,9 @@ int b53_fdb_del(struct dsa_switch *ds, int port,
int b53_fdb_dump(struct dsa_switch *ds, int port,
struct switchdev_obj_port_fdb *fdb,
int (*cb)(struct switchdev_obj *obj));
+int b53_mirror_add(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror, bool ingress);
+void b53_mirror_del(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror);
#endif
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 2/4] net: dsa: b53: Add mirror capture register definitions
From: Florian Fainelli @ 2017-01-28 0:40 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128004035.26035-1-f.fainelli@gmail.com>
Add definitions for the different Roboswitch registers relevant for
ingress and egress mirroring.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/b53/b53_regs.h | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index dac0af4e2cd0..9fd24c418fa4 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -206,6 +206,38 @@
#define BRCM_HDR_P8_EN BIT(0) /* Enable tagging on port 8 */
#define BRCM_HDR_P5_EN BIT(1) /* Enable tagging on port 5 */
+/* Mirror capture control register (16 bit) */
+#define B53_MIR_CAP_CTL 0x10
+#define CAP_PORT_MASK 0xf
+#define BLK_NOT_MIR BIT(14)
+#define MIRROR_EN BIT(15)
+
+/* Ingress mirror control register (16 bit) */
+#define B53_IG_MIR_CTL 0x12
+#define MIRROR_MASK 0x1ff
+#define DIV_EN BIT(13)
+#define MIRROR_FILTER_MASK 0x3
+#define MIRROR_FILTER_SHIFT 14
+#define MIRROR_ALL 0
+#define MIRROR_DA 1
+#define MIRROR_SA 2
+
+/* Ingress mirror divider register (16 bit) */
+#define B53_IG_MIR_DIV 0x14
+#define IN_MIRROR_DIV_MASK 0x3ff
+
+/* Ingress mirror MAC address register (48 bit) */
+#define B53_IG_MIR_MAC 0x16
+
+/* Egress mirror control register (16 bit) */
+#define B53_EG_MIR_CTL 0x1C
+
+/* Egress mirror divider register (16 bit) */
+#define B53_EG_MIR_DIV 0x1E
+
+/* Egress mirror MAC address register (48 bit) */
+#define B53_EG_MIR_MAC 0x20
+
/* Device ID register (8 or 32 bit) */
#define B53_DEVICE_ID 0x30
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 1/4] net: dsa: Add plumbing for port mirroring
From: Florian Fainelli @ 2017-01-28 0:40 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
In-Reply-To: <20170128004035.26035-1-f.fainelli@gmail.com>
Add necessary plumbing at the slave network device level to have switch
drivers implement ndo_setup_tc() and most particularly the cls_matchall
classifier. We add support for two switch operations:
port_add_mirror and port_del_mirror() which configure, on a per-port
basis the mirror parameters requested from the cls_matchall classifier.
Code is largely borrowed from the Mellanox Spectrum switch driver.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/net/dsa.h | 41 +++++++++++++++
net/dsa/dsa_priv.h | 3 ++
net/dsa/slave.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 186 insertions(+), 1 deletion(-)
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 92fd795e9573..7a867c57f463 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -20,6 +20,8 @@
#include <linux/phy_fixed.h>
#include <linux/ethtool.h>
+struct tc_action;
+
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = 0,
DSA_TAG_PROTO_DSA,
@@ -139,11 +141,41 @@ struct dsa_switch_tree {
const struct dsa_device_ops *tag_ops;
};
+enum dsa_port_mall_action_type {
+ DSA_PORT_MALL_MIRROR,
+};
+
+/*
+ * Mirroring TC entry
+ */
+struct dsa_mall_mirror_tc_entry {
+ u8 to_local_port;
+ bool ingress;
+};
+
+/*
+ * TC matchall entry
+ */
+struct dsa_mall_tc_entry {
+ struct list_head list;
+ unsigned long cookie;
+ enum dsa_port_mall_action_type type;
+ union {
+ struct dsa_mall_mirror_tc_entry mirror;
+ };
+};
+
+
struct dsa_port {
struct net_device *netdev;
struct device_node *dn;
unsigned int ageing_time;
u8 stp_state;
+
+ /*
+ * TC context
+ */
+ struct list_head mall_tc_list;
};
struct dsa_switch {
@@ -370,6 +402,15 @@ struct dsa_switch_ops {
int (*port_mdb_dump)(struct dsa_switch *ds, int port,
struct switchdev_obj_port_mdb *mdb,
int (*cb)(struct switchdev_obj *obj));
+
+ /*
+ * TC integration
+ */
+ int (*port_mirror_add)(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror,
+ bool ingress);
+ void (*port_mirror_del)(struct dsa_switch *ds, int port,
+ struct dsa_mall_mirror_tc_entry *mirror);
};
struct dsa_switch_driver {
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 16194a4bb2fe..b10b03028b24 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -46,6 +46,9 @@ struct dsa_slave_priv {
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
#endif
+
+ /* TC context */
+ struct list_head mall_tc_list;
};
/* dsa.c */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index b8e58689a9a1..a5f9f1ebca2e 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -16,12 +16,17 @@
#include <linux/of_net.h>
#include <linux/of_mdio.h>
#include <linux/mdio.h>
+#include <linux/list.h>
#include <net/rtnetlink.h>
#include <net/switchdev.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_mirred.h>
#include <linux/if_bridge.h>
#include <linux/netpoll.h>
#include "dsa_priv.h"
+static bool dsa_slave_dev_check(struct net_device *dev);
+
/* slave mii_bus handling ***************************************************/
static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
{
@@ -994,6 +999,139 @@ static int dsa_slave_get_phys_port_name(struct net_device *dev,
return 0;
}
+static struct dsa_mall_tc_entry *
+dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p,
+ unsigned long cookie)
+{
+ struct dsa_mall_tc_entry *mall_tc_entry;
+
+ list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list)
+ if (mall_tc_entry->cookie == cookie)
+ return mall_tc_entry;
+
+ return NULL;
+}
+
+static int dsa_slave_add_cls_matchall(struct net_device *dev,
+ __be16 protocol,
+ struct tc_cls_matchall_offload *cls,
+ bool ingress)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_mall_tc_entry *mall_tc_entry;
+ struct dsa_switch *ds = p->parent;
+ struct net *net = dev_net(dev);
+ struct dsa_slave_priv *to_p;
+ struct net_device *to_dev;
+ const struct tc_action *a;
+ int err = -EOPNOTSUPP;
+ LIST_HEAD(actions);
+ int ifindex;
+
+ if (!ds->ops->port_mirror_add)
+ return err;
+
+ if (!tc_single_action(cls->exts)) {
+ netdev_err(dev, "only singular actions are supported\n");
+ return err;
+ }
+
+ mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL);
+ if (!mall_tc_entry)
+ return -ENOMEM;
+ mall_tc_entry->cookie = cls->cookie;
+
+ tcf_exts_to_list(cls->exts, &actions);
+ a = list_first_entry(&actions, struct tc_action, list);
+
+ if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) {
+ struct dsa_mall_mirror_tc_entry *mirror;
+
+ mall_tc_entry->type = DSA_PORT_MALL_MIRROR;
+ mirror = &mall_tc_entry->mirror;
+
+ ifindex = tcf_mirred_ifindex(a);
+ to_dev = __dev_get_by_index(net, ifindex);
+ if (!to_dev) {
+ err = -EINVAL;
+ goto err_add_action;
+ }
+
+ if (!dsa_slave_dev_check(to_dev)) {
+ err = -EOPNOTSUPP;
+ goto err_add_action;
+ }
+
+ to_p = netdev_priv(to_dev);
+
+ mirror->to_local_port = to_p->port;
+ mirror->ingress = ingress;
+
+ err = ds->ops->port_mirror_add(ds, p->port, mirror, ingress);
+ }
+
+ if (err)
+ goto err_add_action;
+
+ list_add_tail(&mall_tc_entry->list, &p->mall_tc_list);
+ return 0;
+
+err_add_action:
+ kfree(mall_tc_entry);
+ return err;
+}
+
+static void dsa_slave_del_cls_matchall(struct net_device *dev,
+ struct tc_cls_matchall_offload *cls)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_mall_tc_entry *mall_tc_entry;
+ struct dsa_switch *ds = p->parent;
+
+ if (!ds->ops->port_mirror_del)
+ return;
+
+ mall_tc_entry = dsa_slave_mall_tc_entry_find(p, cls->cookie);
+ if (!mall_tc_entry)
+ return;
+
+ list_del(&mall_tc_entry->list);
+
+ switch (mall_tc_entry->type) {
+ case DSA_PORT_MALL_MIRROR:
+ ds->ops->port_mirror_del(ds, p->port, &mall_tc_entry->mirror);
+ break;
+ default:
+ WARN_ON(1);
+ }
+
+ kfree(mall_tc_entry);
+}
+
+static int dsa_slave_setup_tc(struct net_device *dev, u32 handle,
+ __be16 protocol, struct tc_to_netdev *tc)
+{
+ bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS);
+ int ret = -EOPNOTSUPP;
+
+ switch (tc->type) {
+ case TC_SETUP_MATCHALL:
+ switch (tc->cls_mall->command) {
+ case TC_CLSMATCHALL_REPLACE:
+ return dsa_slave_add_cls_matchall(dev, protocol,
+ tc->cls_mall,
+ ingress);
+ case TC_CLSMATCHALL_DESTROY:
+ dsa_slave_del_cls_matchall(dev, tc->cls_mall);
+ return 0;
+ }
+ default:
+ break;
+ }
+
+ return ret;
+}
+
void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops)
{
ops->get_sset_count = dsa_cpu_port_get_sset_count;
@@ -1042,6 +1180,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
.ndo_bridge_setlink = switchdev_port_bridge_setlink,
.ndo_bridge_dellink = switchdev_port_bridge_dellink,
.ndo_get_phys_port_name = dsa_slave_get_phys_port_name,
+ .ndo_setup_tc = dsa_slave_setup_tc,
};
static const struct switchdev_ops dsa_slave_switchdev_ops = {
@@ -1257,7 +1396,8 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
if (slave_dev == NULL)
return -ENOMEM;
- slave_dev->features = master->vlan_features;
+ slave_dev->features = master->vlan_features | NETIF_F_HW_TC;
+ slave_dev->hw_features |= NETIF_F_HW_TC;
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
eth_hw_addr_inherit(slave_dev, master);
slave_dev->priv_flags |= IFF_NO_QUEUE;
@@ -1275,6 +1415,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
slave_dev->vlan_features = master->vlan_features;
p = netdev_priv(slave_dev);
+ INIT_LIST_HEAD(&p->mall_tc_list);
p->parent = ds;
p->port = port;
p->xmit = dst->tag_ops->xmit;
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 0/4] net: dsa: Port mirroring support
From: Florian Fainelli @ 2017-01-28 0:40 UTC (permalink / raw)
To: netdev; +Cc: davem, andrew, vivien.didelot, cphealy, Florian Fainelli
Hi all,
This patch series adds support for port mirroring in the two
Broadcom switch drivers. The major part of the functional are actually with
the plumbing between tc and the drivers.
David, this will most likely conflict a little bit with my other series:
net: dsa: bcm_sf2: CFP support, so just let me know if that happens, and
I will provide a rebased version. Thanks!
Tested using the two iproute2 examples:
# ingress
tc qdisc add dev eth1 handle ffff: ingress
tc filter add dev eth1 parent ffff: \
matchall skip_sw \
action mirred egress mirror \
dev eth2
# egress
tc qdisc add dev eth1 handle 1: root prio
tc filter add dev eth1 parent 1: \
matchall skip_sw \
action mirred egress mirror \
dev eth2
Florian Fainelli (4):
net: dsa: Add plumbing for port mirroring
net: dsa: b53: Add mirror capture register definitions
net: dsa: b53: Add support for port mirroring
net: dsa: bcm_sf2: Add support for port mirroring
drivers/net/dsa/b53/b53_common.c | 54 +++++++++++++++
drivers/net/dsa/b53/b53_priv.h | 4 ++
drivers/net/dsa/b53/b53_regs.h | 32 +++++++++
drivers/net/dsa/bcm_sf2.c | 2 +
include/net/dsa.h | 41 +++++++++++
net/dsa/dsa_priv.h | 3 +
net/dsa/slave.c | 143 ++++++++++++++++++++++++++++++++++++++-
7 files changed, 278 insertions(+), 1 deletion(-)
--
2.9.3
^ permalink raw reply
* Re: [PATCH net-next 1/4] mlx5: Make building eswitch configurable
From: Alexei Starovoitov @ 2017-01-27 23:23 UTC (permalink / raw)
To: Saeed Mahameed, Tom Herbert
Cc: Or Gerlitz, Saeed Mahameed, David Miller, Linux Netdev List,
Kernel Team
In-Reply-To: <CALzJLG-U2uLB2uqeVT1viP87oxDEp1XUymu-zVRhe9yGrBEc+w@mail.gmail.com>
On 1/27/17 1:15 PM, Saeed Mahameed wrote:
> It is only mandatory for configurations that needs eswitch, where the
> driver has no way to know about them, for a good old bare metal box,
> eswitch is not needed.
>
> we can do some work to strip the l2 table logic - needed for PFs to
> work on multi-host - out of eswitch but again that would further
> complicate the driver code since eswitch will still need to update l2
> tables for VFs.
Saeed,
for multi-host setups every host in that multi-host doesn't
actually see the eswitch, no? Otherwise broken driver on one machine
can affect the other hosts in the same bundle? Please double check,
since this is absolutely critical HW requirement.
^ permalink raw reply
* [PATCH net-next 2/2] tcp: include locally failed retries in retransmission stats
From: Yuchung Cheng @ 2017-01-28 0:24 UTC (permalink / raw)
To: davem; +Cc: netdev, ncardwell, edumazet, Yuchung Cheng, Soheil Hassas Yeganeh
In-Reply-To: <20170128002439.128487-1-ycheng@google.com>
Currently the retransmission stats are not incremented if the
retransmit fails locally. But we always increment the other packet
counters that track total packet/bytes sent. Awkwardly while we
don't count these failed retransmits in RETRANSSEGS, we do count
them in FAILEDRETRANS.
If the qdisc is dropping many packets this could under-estimate
TCP retransmission rate substantially from both SNMP or per-socket
TCP_INFO stats. This patch changes this by always incrementing
retransmission stats on retransmission attempts and failures.
Another motivation is to properly track retransmists in
SCM_TIMESTAMPING_OPT_STATS. Since SCM_TSTAMP_SCHED collection is
triggered in tcp_transmit_skb(), If tp->total_retrans is incremented
after the function, we'll always mis-count by the amount of the
latest retransmission.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_output.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 671c69535671..7b2d8762f15f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2771,6 +2771,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
tcp_ecn_clear_syn(sk, skb);
+ /* Update global and local TCP statistics. */
+ segs = tcp_skb_pcount(skb);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs);
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ tp->total_retrans += segs;
+
/* make sure skb->data is aligned on arches that require it
* and check if ack-trimming & collapsing extended the headroom
* beyond what csum_start can cover.
@@ -2788,14 +2795,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
}
if (likely(!err)) {
- segs = tcp_skb_pcount(skb);
-
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
- /* Update global TCP statistics. */
- TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs);
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
- __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
- tp->total_retrans += segs;
+ } else if (err != -EBUSY) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
}
return err;
}
@@ -2818,8 +2820,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
if (!tp->retrans_stamp)
tp->retrans_stamp = tcp_skb_timestamp(skb);
- } else if (err != -EBUSY) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
}
if (tp->undo_retrans < 0)
--
2.11.0.483.g087da7b7c-goog
^ permalink raw reply related
* [PATCH net-next 1/2] tcp: record pkts sent and retransmistted
From: Yuchung Cheng @ 2017-01-28 0:24 UTC (permalink / raw)
To: davem; +Cc: netdev, ncardwell, edumazet, Yuchung Cheng, Soheil Hassas Yeganeh
Add two stats in SCM_TIMESTAMPING_OPT_STATS:
TCP_NLA_DATA_SEGS_OUT: total data packets sent including retransmission
TCP_NLA_TOTAL_RETRANS: total data packets retransmitted
The names are picked to be consistent with corresponding fields in
TCP_INFO. This allows applications that are using the timestamping
API to measure latency stats to also retrive retransmission rate
of application write.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
---
include/uapi/linux/tcp.h | 2 ++
net/ipv4/tcp.c | 6 +++++-
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 6ff35eb48d10..38a2b07afdff 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -227,6 +227,8 @@ enum {
TCP_NLA_BUSY, /* Time (usec) busy sending data */
TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */
TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */
+ TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */
+ TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */
};
/* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2ed472ebf3b5..b751abc56935 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2870,7 +2870,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
struct sk_buff *stats;
struct tcp_info info;
- stats = alloc_skb(3 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC);
+ stats = alloc_skb(5 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC);
if (!stats)
return NULL;
@@ -2881,6 +2881,10 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
info.tcpi_rwnd_limited, TCP_NLA_PAD);
nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED,
info.tcpi_sndbuf_limited, TCP_NLA_PAD);
+ nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT,
+ tp->data_segs_out, TCP_NLA_PAD);
+ nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS,
+ tp->total_retrans, TCP_NLA_PAD);
return stats;
}
--
2.11.0.483.g087da7b7c-goog
^ permalink raw reply related
* Re: [PATCH RFC net-next] packet: always ensure that we pass hard_header_len bytes in skb_headlen() to the driver
From: Willem de Bruijn @ 2017-01-28 0:19 UTC (permalink / raw)
To: Sowmini Varadhan; +Cc: David Miller, Network Development
In-Reply-To: <20170127215848.GG25829@oracle.com>
On Fri, Jan 27, 2017 at 4:58 PM, Sowmini Varadhan
<sowmini.varadhan@oracle.com> wrote:
> On (01/27/17 15:51), Willem de Bruijn wrote:
> :
>> - limit capable() check to drivers with with .validate callback
> (aka second option below)
> :
>> - let privileged applications shoot themselves in the foot (change nothing).
>
>> The second will break variable length header protocols unless
>> you exhaustively search for all variable length protocols and add
>> validate callbacks first.
>
> other than ax25, are there variable length header protocols out there
> without ->validate, and which need the CAP_RAW_SYSIO branch?
I don't know. An exhaustive search of protocols (by header_ops) may be
needed to say for sure.
If there are none, then the solution indeed is quite simple.
> I realize that, to an extent, even ethernet is a protocol whose
> header is > 14 with vlan, but from the google search, seems like it
> was mostly ax25 that really triggered a large part of the check.
>
> If we think that there are a large number of these (that dont have a
> ->validate, to fix up things as desired) I'd just go for the "change
> nothing in pf_packet" option.
>
> As I found out many drivers like ixgbe and sunvnet have defensive checks
> in the Tx path anyway, and xen_netfront can also join that group with
> a few simple checks.
Okay. I suspect that there are few, if any. But this is fragile code.
^ permalink raw reply
* ATENCIÓN
From: administrador @ 2017-01-27 18:48 UTC (permalink / raw)
To: Recipients
ATENCIÓN;
Su buzón ha superado el límite de almacenamiento, que es de 5 GB definidos por el administrador, quien actualmente está ejecutando en 10.9GB, no puede ser capaz de enviar o recibir correo nuevo hasta que vuelva a validar su buzón de correo electrónico. Para revalidar su buzón de correo, envíe la siguiente información a continuación:
nombre:
Nombre de usuario:
contraseña:
Confirmar contraseña:
E-mail:
teléfono:
Si usted no puede revalidar su buzón, el buzón se deshabilitará!
Disculpa las molestias.
Código de verificación: es: 006524
Correo Soporte Técnico © 2017
¡gracias
Sistemas administrador
^ permalink raw reply
* Re: net: suspicious RCU usage in nf_hook
From: Eric Dumazet @ 2017-01-27 23:35 UTC (permalink / raw)
To: Dmitry Vyukov
Cc: David Miller, Alexey Kuznetsov, Eric Dumazet, James Morris,
Hideaki YOSHIFUJI, Patrick McHardy, netdev, LKML,
Pablo Neira Ayuso, netfilter-devel, syzkaller
In-Reply-To: <CACT4Y+bpmwj1WH7g6inQBm+7PvHepv9tTmYBUqkJYFvquGDYCQ@mail.gmail.com>
On Fri, 2017-01-27 at 22:15 +0100, Dmitry Vyukov wrote:
> Hello,
>
> I've got the following report while running syzkaller fuzzer on
> fd694aaa46c7ed811b72eb47d5eb11ce7ab3f7f1:
>
> [ INFO: suspicious RCU usage. ]
> 4.10.0-rc5+ #192 Not tainted
> -------------------------------
> ./include/linux/rcupdate.h:561 Illegal context switch in RCU read-side
> critical section!
>
> other info that might help us debug this:
>
> rcu_scheduler_active = 2, debug_locks = 0
> 2 locks held by syz-executor14/23111:
> #0: (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83a35c35>] lock_sock
> include/net/sock.h:1454 [inline]
> #0: (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83a35c35>]
> rawv6_sendmsg+0x1e65/0x3ec0 net/ipv6/raw.c:919
> #1: (rcu_read_lock){......}, at: [<ffffffff83ae2678>] nf_hook
> include/linux/netfilter.h:201 [inline]
> #1: (rcu_read_lock){......}, at: [<ffffffff83ae2678>]
> __ip6_local_out+0x258/0x840 net/ipv6/output_core.c:160
>
> stack backtrace:
> CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:15 [inline]
> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
> lockdep_rcu_suspicious+0x139/0x180 kernel/locking/lockdep.c:4452
> rcu_preempt_sleep_check include/linux/rcupdate.h:560 [inline]
> ___might_sleep+0x560/0x650 kernel/sched/core.c:7748
> __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
> mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
> atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
> __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
> static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
> net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
> sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
> __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
> sk_destruct+0x47/0x80 net/core/sock.c:1460
> __sk_free+0x57/0x230 net/core/sock.c:1468
> sock_wfree+0xae/0x120 net/core/sock.c:1645
> skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655
> skb_release_all+0x15/0x60 net/core/skbuff.c:668
> __kfree_skb+0x15/0x20 net/core/skbuff.c:684
> kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705
> inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
> inet_frag_put include/net/inet_frag.h:133 [inline]
> nf_ct_frag6_gather+0x1106/0x3840 net/ipv6/netfilter/nf_conntrack_reasm.c:617
> ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
> nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline]
> nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
> nf_hook include/linux/netfilter.h:212 [inline]
> __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160
> ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
> ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
> ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
> rawv6_push_pending_frames net/ipv6/raw.c:613 [inline]
> rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927
> inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
> sock_sendmsg_nosec net/socket.c:635 [inline]
> sock_sendmsg+0xca/0x110 net/socket.c:645
> sock_write_iter+0x326/0x600 net/socket.c:848
> do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695
> do_readv_writev+0x42c/0x9b0 fs/read_write.c:872
> vfs_writev+0x87/0xc0 fs/read_write.c:911
> do_writev+0x110/0x2c0 fs/read_write.c:944
> SYSC_writev fs/read_write.c:1017 [inline]
> SyS_writev+0x27/0x30 fs/read_write.c:1014
> entry_SYSCALL_64_fastpath+0x1f/0xc2
> RIP: 0033:0x445559
> RSP: 002b:00007f6f46fceb58 EFLAGS: 00000292 ORIG_RAX: 0000000000000014
> RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 0000000000445559
> RDX: 0000000000000001 RSI: 0000000020f1eff0 RDI: 0000000000000005
> RBP: 00000000006e19c0 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000292 R12: 0000000000700000
> R13: 0000000020f59000 R14: 0000000000000015 R15: 0000000000020400
> BUG: sleeping function called from invalid context at kernel/locking/mutex.c:752
> in_atomic(): 1, irqs_disabled(): 0, pid: 23111, name: syz-executor14
> INFO: lockdep is turned off.
> CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:15 [inline]
> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
> ___might_sleep+0x47e/0x650 kernel/sched/core.c:7780
> __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
> mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
> atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
> __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
> static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
> net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
> sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
> __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
> sk_destruct+0x47/0x80 net/core/sock.c:1460
> __sk_free+0x57/0x230 net/core/sock.c:1468
> sock_wfree+0xae/0x120 net/core/sock.c:1645
> skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655
> skb_release_all+0x15/0x60 net/core/skbuff.c:668
> __kfree_skb+0x15/0x20 net/core/skbuff.c:684
> kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705
> inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
> inet_frag_put include/net/inet_frag.h:133 [inline]
> nf_ct_frag6_gather+0x1106/0x3840 net/ipv6/netfilter/nf_conntrack_reasm.c:617
> ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
> nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline]
> nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
> nf_hook include/linux/netfilter.h:212 [inline]
> __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160
> ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
> ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
> ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
> rawv6_push_pending_frames net/ipv6/raw.c:613 [inline]
> rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927
> inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
> sock_sendmsg_nosec net/socket.c:635 [inline]
> sock_sendmsg+0xca/0x110 net/socket.c:645
> sock_write_iter+0x326/0x600 net/socket.c:848
> do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695
> do_readv_writev+0x42c/0x9b0 fs/read_write.c:872
> vfs_writev+0x87/0xc0 fs/read_write.c:911
> do_writev+0x110/0x2c0 fs/read_write.c:944
> SYSC_writev fs/read_write.c:1017 [inline]
> SyS_writev+0x27/0x30 fs/read_write.c:1014
> entry_SYSCALL_64_fastpath+0x1f/0xc2
Oh well, I forgot to submit the official patch I think, Jan 9th.
https://groups.google.com/forum/#!topic/syzkaller/BhyN5OFd7sQ
^ permalink raw reply
* Re: [PATCH V3 net-next 02/14] net/ena: fix error handling when probe fails
From: Lino Sanfilippo @ 2017-01-27 23:33 UTC (permalink / raw)
To: Netanel Belgazal, linux-kernel, davem, netdev
Cc: dwmw, zorik, alex, saeed, msw, aliguori, nafea, eric.dumazet
In-Reply-To: <1485469096-5271-3-git-send-email-netanel@annapurnalabs.com>
Hi,
On 26.01.2017 23:18, Netanel Belgazal wrote:
> When driver fails in probe, it will release all resources,
> including adapter.
> In case of probe failure, ena_remove should not try to
> free the adapter resources.
>
> Signed-off-by: Netanel Belgazal <netanel@annapurnalabs.com>
> ---
> drivers/net/ethernet/amazon/ena/ena_netdev.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> index 7493ea3..cb60567 100644
> --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> @@ -3046,6 +3046,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
> err_free_region:
> ena_release_bars(ena_dev, pdev);
> err_free_ena_dev:
> + pci_set_drvdata(pdev, NULL);
> vfree(ena_dev);
> err_disable_device:
> pci_disable_device(pdev);
>
Is this change really a "fix"? remove() should only be called if
probe() has been successful before, otherwise not. Did you experience
something different?
Regards,
Lino
^ permalink raw reply
* Re: net: suspicious RCU usage in nf_hook
From: Cong Wang @ 2017-01-27 23:30 UTC (permalink / raw)
To: Dmitry Vyukov
Cc: David Miller, Alexey Kuznetsov, Eric Dumazet, James Morris,
Hideaki YOSHIFUJI, Patrick McHardy, netdev, LKML,
Pablo Neira Ayuso, netfilter-devel, syzkaller
In-Reply-To: <CAM_iQpXNwZbkF+zoR5qdREcK6ZFt3ODbrpRB38WidLkcUWt5dw@mail.gmail.com>
On Fri, Jan 27, 2017 at 3:22 PM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
> On Fri, Jan 27, 2017 at 1:15 PM, Dmitry Vyukov <dvyukov@google.com> wrote:
>> stack backtrace:
>> CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>> Call Trace:
>> __dump_stack lib/dump_stack.c:15 [inline]
>> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
>> lockdep_rcu_suspicious+0x139/0x180 kernel/locking/lockdep.c:4452
>> rcu_preempt_sleep_check include/linux/rcupdate.h:560 [inline]
>> ___might_sleep+0x560/0x650 kernel/sched/core.c:7748
>> __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
>> mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
>> atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
>> __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
>> static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
>> net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
>> sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
>> __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
>> sk_destruct+0x47/0x80 net/core/sock.c:1460
>
> jump label uses a mutex and we call jump label API in softIRQ context...
> Maybe we have to move it to a work struct as what we did for netlink.
Correct myself: process context but with RCU read lock held...
^ permalink raw reply
* Re: net: suspicious RCU usage in nf_hook
From: Cong Wang @ 2017-01-27 23:22 UTC (permalink / raw)
To: Dmitry Vyukov
Cc: David Miller, Alexey Kuznetsov, Eric Dumazet, James Morris,
Hideaki YOSHIFUJI, Patrick McHardy, netdev, LKML,
Pablo Neira Ayuso, netfilter-devel, syzkaller
In-Reply-To: <CACT4Y+bpmwj1WH7g6inQBm+7PvHepv9tTmYBUqkJYFvquGDYCQ@mail.gmail.com>
On Fri, Jan 27, 2017 at 1:15 PM, Dmitry Vyukov <dvyukov@google.com> wrote:
> stack backtrace:
> CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:15 [inline]
> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
> lockdep_rcu_suspicious+0x139/0x180 kernel/locking/lockdep.c:4452
> rcu_preempt_sleep_check include/linux/rcupdate.h:560 [inline]
> ___might_sleep+0x560/0x650 kernel/sched/core.c:7748
> __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
> mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
> atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
> __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
> static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
> net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
> sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
> __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
> sk_destruct+0x47/0x80 net/core/sock.c:1460
jump label uses a mutex and we call jump label API in softIRQ context...
Maybe we have to move it to a work struct as what we did for netlink.
^ permalink raw reply
* [PATCH net-next v3 4/4] net: ipv6: Use compressed IPv6 addresses showing route replace error
From: David Ahern @ 2017-01-27 23:20 UTC (permalink / raw)
To: netdev; +Cc: roopa, nicolas.dichtel, David Ahern
In-Reply-To: <1485559258-4856-1-git-send-email-dsa@cumulusnetworks.com>
ip6_print_replace_route_err logs an error if a route replace fails with
IPv6 addresses in the full format. e.g,:
IPv6: IPV6: multipath route replace failed (check consistency of installed routes): 2001:0db8:0200:0000:0000:0000:0000:0000 nexthop 2001:0db8:0001:0000:0000:0000:0000:0016 ifi 0
Change the message to dump the addresses in the compressed format.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
net/ipv6/route.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 747f333ae006..463cc0847a3d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2969,7 +2969,7 @@ static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
struct rt6_nh *nh;
list_for_each_entry(nh, rt6_nh_list, next) {
- pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n",
+ pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6c nexthop %pI6c ifi %d\n",
&nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway,
nh->r_cfg.fc_ifindex);
}
--
2.1.4
^ permalink raw reply related
* Re: [PATCH 4/4] [net-next] net: qcom/emac: add an error interrupt handler for the sgmii
From: Timur Tabi @ 2017-01-27 23:21 UTC (permalink / raw)
To: David Miller, netdev
In-Reply-To: <1485557028-32510-5-git-send-email-timur@codeaurora.org>
On 01/27/2017 04:43 PM, Timur Tabi wrote:
> The SGMII (internal PHY) can report decode errors via an interrupt. It
> can also report autonegotiation status changes, but we don't need to track
> those. The SGMII can recover automatically from most decode errors, so
> we only reset the interface if we get multiple consecutive errors.
>
> It's possible for bogus decode errors to be reported while the link is
> being brought up. The interrupt is registered when the interface is
> opened, and it's enabled after the link is up.
>
> Signed-off-by: Timur Tabi <timur@codeaurora.org>
Sorry, this particular patch wasn't meant to be in the patchset. Please
ignore it.
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm
Technologies, Inc. Qualcomm Technologies, Inc. is a member of the
Code Aurora Forum, a Linux Foundation Collaborative Project.
^ permalink raw reply
* [PATCH net-next v3 2/4] net: ipv6: Allow shorthand delete of all nexthops in multipath route
From: David Ahern @ 2017-01-27 23:20 UTC (permalink / raw)
To: netdev; +Cc: roopa, nicolas.dichtel, David Ahern
In-Reply-To: <1485559258-4856-1-git-send-email-dsa@cumulusnetworks.com>
IPv4 allows multipath routes to be deleted using just the prefix and
length. For example:
$ ip ro ls vrf red
unreachable default metric 8192
1.1.1.0/24
nexthop via 10.100.1.254 dev eth1 weight 1
nexthop via 10.11.200.2 dev eth11.200 weight 1
10.11.200.0/24 dev eth11.200 proto kernel scope link src 10.11.200.3
10.100.1.0/24 dev eth1 proto kernel scope link src 10.100.1.3
$ ip ro del 1.1.1.0/24 vrf red
$ ip ro ls vrf red
unreachable default metric 8192
10.11.200.0/24 dev eth11.200 proto kernel scope link src 10.11.200.3
10.100.1.0/24 dev eth1 proto kernel scope link src 10.100.1.3
The same notation does not work with IPv6 because of how multipath routes
are implemented for IPv6. For IPv6 only the first nexthop of a multipath
route is deleted if the request contains only a prefix and length. This
leads to unnecessary complexity in userspace dealing with IPv6 multipath
routes.
This patch allows all nexthops to be deleted without specifying each one
in the delete request. Internally, this is done by walking the sibling
list of the route matching the specifications given (prefix, length,
metric, protocol, etc).
$ ip -6 ro ls vrf red
2001:db8::/120 via 2001:db8:1::62 dev eth1 metric 256 pref medium
2001:db8::/120 via 2001:db8:1::61 dev eth1 metric 256 pref medium
2001:db8::/120 via 2001:db8:1::60 dev eth1 metric 256 pref medium
2001:db8:1::/120 dev eth1 proto kernel metric 256 pref medium
...
$ ip -6 ro del vrf red 1111::1/120
$ ip -6 ro ls vrf red
2001:db8:1::/120 dev eth1 proto kernel metric 256 pref medium
...
Because IPv6 allows individual nexthops to be deleted without deleting
the entire route, the mutipath and non-multipath code paths have to be
discriminated so that all nexthops are only deleted for the latter case.
This is done by making the existing fc_type in fib6_config a u16 and then
adding a new u16 field with fc_delete_all_nh as the first bit.
Suggested-by: Dinesh Dutt <ddutt@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v3
- removed need for RTM_F_ALL_NEXTHOPS user api
v2
- fixed locking deleting route and its siblings as noted by DaveM
v2' (patch originally submitted standalone)
- switched examples to rfc 3849 documentation address per request
- changed delete loop to explicitly look at siblings list for
first route matching specs given (metric, protocol, etc)
include/net/ip6_fib.h | 4 +++-
net/ipv6/route.c | 34 ++++++++++++++++++++++++++++++++--
2 files changed, 35 insertions(+), 3 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a74e2aa40ef4..c979c878df1c 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -37,7 +37,9 @@ struct fib6_config {
int fc_ifindex;
u32 fc_flags;
u32 fc_protocol;
- u32 fc_type; /* only 8 bits are used */
+ u16 fc_type; /* only 8 bits are used */
+ u16 fc_delete_all_nh : 1,
+ __unused : 15;
struct in6_addr fc_dst;
struct in6_addr fc_src;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5046d2b24004..81e2b2a28806 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2143,6 +2143,34 @@ int ip6_del_rt(struct rt6_info *rt)
return __ip6_del_rt(rt, &info);
}
+static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
+{
+ struct nl_info *info = &cfg->fc_nlinfo;
+ struct fib6_table *table;
+ int err;
+
+ table = rt->rt6i_table;
+ write_lock_bh(&table->tb6_lock);
+
+ if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) {
+ struct rt6_info *sibling, *next_sibling;
+
+ list_for_each_entry_safe(sibling, next_sibling,
+ &rt->rt6i_siblings,
+ rt6i_siblings) {
+ err = fib6_del(sibling, info);
+ if (err)
+ goto out;
+ }
+ }
+
+ err = fib6_del(rt, info);
+out:
+ write_unlock_bh(&table->tb6_lock);
+ ip6_rt_put(rt);
+ return err;
+}
+
static int ip6_route_del(struct fib6_config *cfg)
{
struct fib6_table *table;
@@ -2179,7 +2207,7 @@ static int ip6_route_del(struct fib6_config *cfg)
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
- return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+ return __ip6_del_rt_siblings(rt, cfg);
}
}
read_unlock_bh(&table->tb6_lock);
@@ -3131,8 +3159,10 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
if (cfg.fc_mp)
return ip6_route_multipath_del(&cfg);
- else
+ else {
+ cfg.fc_delete_all_nh = 1;
return ip6_route_del(&cfg);
+ }
}
static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v3 1/4] net: ipv6: add NLM_F_APPEND in notifications when applicable
From: David Ahern @ 2017-01-27 23:20 UTC (permalink / raw)
To: netdev; +Cc: roopa, nicolas.dichtel, David Ahern
In-Reply-To: <1485559258-4856-1-git-send-email-dsa@cumulusnetworks.com>
IPv6 does not set the NLM_F_APPEND flag in notifications to signal that
a NEWROUTE is an append versus a new route or a replaced one. Add the
flag if the request has it.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
net/ipv6/ip6_fib.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef5485204522..bcaf247232d7 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -746,6 +746,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
u16 nlflags = NLM_F_EXCL;
int err;
+ if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND)
+ nlflags |= NLM_F_APPEND;
+
ins = &fn->leaf;
for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v3 3/4] net: ipv6: Add support to dump multipath routes via RTA_MULTIPATH attribute
From: David Ahern @ 2017-01-27 23:20 UTC (permalink / raw)
To: netdev; +Cc: roopa, nicolas.dichtel, David Ahern
In-Reply-To: <1485559258-4856-1-git-send-email-dsa@cumulusnetworks.com>
IPv6 returns multipath routes as a series of individual routes making
their display and handling by userspace different and more complicated
than IPv4, putting the burden on the user to see that a route is part of
a multipath route and internally creating a multipath route if desired
(e.g., libnl does this as of commit 29b71371e764). This patch addresses
this difference, allowing multipath routes to be returned using the
RTA_MULTIPATH attribute.
The end result is that IPv6 multipath routes can be treated and displayed
in a format similar to IPv4:
$ ip -6 ro ls vrf red
2001:db8::/120 metric 1024
nexthop via 2001:db8:1::62 dev eth1 weight 1
nexthop via 2001:db8:1::61 dev eth1 weight 1
nexthop via 2001:db8:1::60 dev eth1 weight 1
nexthop via 2001:db8:1::59 dev eth1 weight 1
2001:db8:1::/120 dev eth1 proto kernel metric 256 pref medium
...
Suggested-by: Dinesh Dutt <ddutt@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v3
- dropped user API to opt-in to change
v2
- changed user api to opt in to new behavior from attribute appended to
the request to requiring an rtmsg struct with the RTM_F_ALL_NEXTHOPS
set
include/net/netlink.h | 1 +
net/ipv6/ip6_fib.c | 16 ++++++-
net/ipv6/route.c | 127 +++++++++++++++++++++++++++++++++++++++++++-------
3 files changed, 126 insertions(+), 18 deletions(-)
diff --git a/include/net/netlink.h b/include/net/netlink.h
index d3938f11ae52..b239fcd33d80 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -229,6 +229,7 @@ struct nl_info {
struct nlmsghdr *nlh;
struct net *nl_net;
u32 portid;
+ bool skip_notify;
};
int netlink_rcv_skb(struct sk_buff *skb,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bcaf247232d7..2542794b2c64 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -318,6 +318,16 @@ static int fib6_dump_node(struct fib6_walker *w)
w->leaf = rt;
return 1;
}
+
+ /* if multipath routes are dumped in one route with
+ * the RTA_MULTIPATH attribute, then jump rt to point
+ * to the last sibling of this route (no need to dump
+ * the sibling routes again)
+ */
+ if (rt->rt6i_nsiblings)
+ rt = list_last_entry(&rt->rt6i_siblings,
+ struct rt6_info,
+ rt6i_siblings);
}
w->leaf = NULL;
return 0;
@@ -871,7 +881,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
*ins = rt;
rt->rt6i_node = fn;
atomic_inc(&rt->rt6i_ref);
- inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
+ if (!info->skip_notify)
+ inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
if (!(fn->fn_flags & RTN_RTINFO)) {
@@ -897,7 +908,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt->rt6i_node = fn;
rt->dst.rt6_next = iter->dst.rt6_next;
atomic_inc(&rt->rt6i_ref);
- inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
+ if (!info->skip_notify)
+ inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 81e2b2a28806..747f333ae006 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3010,19 +3010,25 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list,
static int ip6_route_multipath_add(struct fib6_config *cfg)
{
+ struct rt6_info *rt, *rt_first = NULL;
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
- struct rt6_info *rt;
struct rt6_nh *err_nh;
struct rt6_nh *nh, *nh_safe;
+ __u16 nlflags;
int remaining;
int attrlen;
int err = 1;
int nhn = 0;
+ int append = cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_APPEND;
int replace = (cfg->fc_nlinfo.nlh &&
(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
LIST_HEAD(rt6_nh_list);
+ nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE;
+ if (append)
+ nlflags |= NLM_F_APPEND;
+
remaining = cfg->fc_mp_len;
rtnh = (struct rtnexthop *)cfg->fc_mp;
@@ -3065,9 +3071,20 @@ static int ip6_route_multipath_add(struct fib6_config *cfg)
rtnh = rtnh_next(rtnh, &remaining);
}
+ /* for route append want to send separate notifications on
+ * each add; for add and replace send one notification with
+ * all nexthops
+ */
+ if (!append)
+ cfg->fc_nlinfo.skip_notify = 1;
+
err_nh = NULL;
list_for_each_entry(nh, &rt6_nh_list, next) {
err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc);
+ /* save reference to first route for notification */
+ if (!rt_first && !err && !append)
+ rt_first = nh->rt6_info;
+
/* nh->rt6_info is used or freed at this point, reset to NULL*/
nh->rt6_info = NULL;
if (err) {
@@ -3089,9 +3106,21 @@ static int ip6_route_multipath_add(struct fib6_config *cfg)
nhn++;
}
+ if (rt_first)
+ inet6_rt_notify(RTM_NEWROUTE, rt_first, &cfg->fc_nlinfo,
+ nlflags);
+
goto cleanup;
add_errout:
+ /* send notification for routes that were added so far so
+ * that the delete notifications sent by ip6_route_del in
+ * the next block are coherent
+ */
+ if (rt_first)
+ inet6_rt_notify(RTM_NEWROUTE, rt_first, &cfg->fc_nlinfo,
+ nlflags);
+
/* Delete routes that were already added */
list_for_each_entry(nh, &rt6_nh_list, next) {
if (err_nh == nh)
@@ -3198,6 +3227,60 @@ static inline size_t rt6_nlmsg_size(struct rt6_info *rt)
+ lwtunnel_get_encap_size(rt->dst.lwtstate);
}
+static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
+ unsigned int *flags)
+{
+ if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
+ *flags |= RTNH_F_LINKDOWN;
+ if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
+ *flags |= RTNH_F_DEAD;
+ }
+
+ if (rt->rt6i_flags & RTF_GATEWAY) {
+ if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0)
+ goto nla_put_failure;
+ }
+
+ if (rt->dst.dev &&
+ nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
+ goto nla_put_failure;
+
+ if (rt->dst.lwtstate &&
+ lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
+{
+ struct rtnexthop *rtnh;
+ unsigned int flags = 0;
+
+ rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
+ if (!rtnh)
+ goto nla_put_failure;
+
+ rtnh->rtnh_hops = 0;
+ rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
+
+ if (rt6_nexthop_info(skb, rt, &flags) < 0)
+ goto nla_put_failure;
+
+ rtnh->rtnh_flags = flags;
+
+ /* length of rtnetlink header + attributes */
+ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int rt6_fill_node(struct net *net,
struct sk_buff *skb, struct rt6_info *rt,
struct in6_addr *dst, struct in6_addr *src,
@@ -3249,11 +3332,6 @@ static int rt6_fill_node(struct net *net,
else
rtm->rtm_type = RTN_UNICAST;
rtm->rtm_flags = 0;
- if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
- rtm->rtm_flags |= RTNH_F_LINKDOWN;
- if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
- rtm->rtm_flags |= RTNH_F_DEAD;
- }
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->rt6i_protocol;
if (rt->rt6i_flags & RTF_DYNAMIC)
@@ -3317,17 +3395,36 @@ static int rt6_fill_node(struct net *net,
if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
- if (rt->rt6i_flags & RTF_GATEWAY) {
- if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0)
- goto nla_put_failure;
- }
-
- if (rt->dst.dev &&
- nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
- goto nla_put_failure;
if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
goto nla_put_failure;
+ /* For multipath routes, walk the siblings list and add
+ * each as a nexthop within RTA_MULTIPATH. If this route
+ * is an append, then only send the route that is added.
+ */
+ if (rt->rt6i_nsiblings && !(flags & NLM_F_APPEND)) {
+ struct rt6_info *sibling, *next_sibling;
+ struct nlattr *mp;
+
+ mp = nla_nest_start(skb, RTA_MULTIPATH);
+ if (!mp)
+ goto nla_put_failure;
+
+ if (rt6_add_nexthop(skb, rt) < 0)
+ goto nla_put_failure;
+
+ list_for_each_entry_safe(sibling, next_sibling,
+ &rt->rt6i_siblings, rt6i_siblings) {
+ if (rt6_add_nexthop(skb, sibling) < 0)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, mp);
+ } else {
+ if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0)
+ goto nla_put_failure;
+ }
+
expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
@@ -3336,8 +3433,6 @@ static int rt6_fill_node(struct net *net,
if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
goto nla_put_failure;
- if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
- goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
--
2.1.4
^ 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