* [PATCH net-next v12 2/5] netvsc: refactor notifier/event handling code to use the failover framework
From: Sridhar Samudrala @ 2018-05-24 16:55 UTC (permalink / raw)
To: mst, stephen, davem, netdev, virtualization, virtio-dev,
jesse.brandeburg, alexander.h.duyck, kubakici, sridhar.samudrala,
jasowang, loseweigh, jiri, aaron.f.brown, anjali.singhai
In-Reply-To: <1527180917-39737-1-git-send-email-sridhar.samudrala@intel.com>
Use the registration/notification framework supported by the generic
failover infrastructure.
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
drivers/net/hyperv/Kconfig | 1 +
drivers/net/hyperv/hyperv_net.h | 2 +
drivers/net/hyperv/netvsc_drv.c | 222 +++++++++++-----------------------------
3 files changed, 60 insertions(+), 165 deletions(-)
diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig
index 0765d5f61714..23a2d145813a 100644
--- a/drivers/net/hyperv/Kconfig
+++ b/drivers/net/hyperv/Kconfig
@@ -2,5 +2,6 @@ config HYPERV_NET
tristate "Microsoft Hyper-V virtual network driver"
depends on HYPERV
select UCS2_STRING
+ select FAILOVER
help
Select this option to enable the Hyper-V virtual network driver.
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 1be34d2e3563..99d8e7398a5b 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -932,6 +932,8 @@ struct net_device_context {
u32 vf_alloc;
/* Serial number of the VF to team with */
u32 vf_serial;
+
+ struct failover *failover;
};
/* Per channel data */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index da07ccdf84bf..62eb136c5e73 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -43,6 +43,7 @@
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
+#include <net/failover.h>
#include "hyperv_net.h"
@@ -1763,46 +1764,6 @@ static void netvsc_link_change(struct work_struct *w)
rtnl_unlock();
}
-static struct net_device *get_netvsc_bymac(const u8 *mac)
-{
- struct net_device *dev;
-
- ASSERT_RTNL();
-
- for_each_netdev(&init_net, dev) {
- if (dev->netdev_ops != &device_ops)
- continue; /* not a netvsc device */
-
- if (ether_addr_equal(mac, dev->perm_addr))
- return dev;
- }
-
- return NULL;
-}
-
-static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
-{
- struct net_device *dev;
-
- ASSERT_RTNL();
-
- for_each_netdev(&init_net, dev) {
- struct net_device_context *net_device_ctx;
-
- if (dev->netdev_ops != &device_ops)
- continue; /* not a netvsc device */
-
- net_device_ctx = netdev_priv(dev);
- if (!rtnl_dereference(net_device_ctx->nvdev))
- continue; /* device is removed */
-
- if (rtnl_dereference(net_device_ctx->vf_netdev) == vf_netdev)
- return dev; /* a match */
- }
-
- return NULL;
-}
-
/* Called when VF is injecting data into network stack.
* Change the associated network device from VF to netvsc.
* note: already called with rcu_read_lock
@@ -1825,46 +1786,6 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
return RX_HANDLER_ANOTHER;
}
-static int netvsc_vf_join(struct net_device *vf_netdev,
- struct net_device *ndev)
-{
- struct net_device_context *ndev_ctx = netdev_priv(ndev);
- int ret;
-
- ret = netdev_rx_handler_register(vf_netdev,
- netvsc_vf_handle_frame, ndev);
- if (ret != 0) {
- netdev_err(vf_netdev,
- "can not register netvsc VF receive handler (err = %d)\n",
- ret);
- goto rx_handler_failed;
- }
-
- ret = netdev_master_upper_dev_link(vf_netdev, ndev,
- NULL, NULL, NULL);
- if (ret != 0) {
- netdev_err(vf_netdev,
- "can not set master device %s (err = %d)\n",
- ndev->name, ret);
- goto upper_link_failed;
- }
-
- /* set slave flag before open to prevent IPv6 addrconf */
- vf_netdev->flags |= IFF_SLAVE;
-
- schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
-
- call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
-
- netdev_info(vf_netdev, "joined to %s\n", ndev->name);
- return 0;
-
-upper_link_failed:
- netdev_rx_handler_unregister(vf_netdev);
-rx_handler_failed:
- return ret;
-}
-
static void __netvsc_vf_setup(struct net_device *ndev,
struct net_device *vf_netdev)
{
@@ -1915,85 +1836,95 @@ static void netvsc_vf_setup(struct work_struct *w)
rtnl_unlock();
}
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_pre_register_vf(struct net_device *vf_netdev,
+ struct net_device *ndev)
{
- struct net_device *ndev;
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
- if (vf_netdev->addr_len != ETH_ALEN)
- return NOTIFY_DONE;
-
- /*
- * We will use the MAC address to locate the synthetic interface to
- * associate with the VF interface. If we don't find a matching
- * synthetic interface, move on.
- */
- ndev = get_netvsc_bymac(vf_netdev->perm_addr);
- if (!ndev)
- return NOTIFY_DONE;
-
net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
- return NOTIFY_DONE;
+ return -ENODEV;
+
+ return 0;
+}
+
+static int netvsc_register_vf(struct net_device *vf_netdev,
+ struct net_device *ndev)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
- if (netvsc_vf_join(vf_netdev, ndev) != 0)
- return NOTIFY_DONE;
+ /* set slave flag before open to prevent IPv6 addrconf */
+ vf_netdev->flags |= IFF_SLAVE;
- netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
+ schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+
+ call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
+
+ netdev_info(vf_netdev, "joined to %s\n", ndev->name);
dev_hold(vf_netdev);
- rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
- return NOTIFY_OK;
+ rcu_assign_pointer(ndev_ctx->vf_netdev, vf_netdev);
+
+ return 0;
}
/* VF up/down change detected, schedule to change data path */
-static int netvsc_vf_changed(struct net_device *vf_netdev)
+static int netvsc_vf_changed(struct net_device *vf_netdev,
+ struct net_device *ndev)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
- struct net_device *ndev;
bool vf_is_up = netif_running(vf_netdev);
- ndev = get_netvsc_byref(vf_netdev);
- if (!ndev)
- return NOTIFY_DONE;
-
net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev)
- return NOTIFY_DONE;
+ return -ENODEV;
netvsc_switch_datapath(ndev, vf_is_up);
netdev_info(ndev, "Data path switched %s VF: %s\n",
vf_is_up ? "to" : "from", vf_netdev->name);
- return NOTIFY_OK;
+ return 0;
}
-static int netvsc_unregister_vf(struct net_device *vf_netdev)
+static int netvsc_pre_unregister_vf(struct net_device *vf_netdev,
+ struct net_device *ndev)
{
- struct net_device *ndev;
struct net_device_context *net_device_ctx;
- ndev = get_netvsc_byref(vf_netdev);
- if (!ndev)
- return NOTIFY_DONE;
-
net_device_ctx = netdev_priv(ndev);
cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
+ return 0;
+}
+
+static int netvsc_unregister_vf(struct net_device *vf_netdev,
+ struct net_device *ndev)
+{
+ struct net_device_context *net_device_ctx;
+
+ net_device_ctx = netdev_priv(ndev);
+
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
- netdev_rx_handler_unregister(vf_netdev);
- netdev_upper_dev_unlink(vf_netdev, ndev);
RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
dev_put(vf_netdev);
- return NOTIFY_OK;
+ return 0;
}
+static struct failover_ops netvsc_failover_ops = {
+ .slave_pre_register = netvsc_pre_register_vf,
+ .slave_register = netvsc_register_vf,
+ .slave_pre_unregister = netvsc_pre_unregister_vf,
+ .slave_unregister = netvsc_unregister_vf,
+ .slave_link_change = netvsc_vf_changed,
+ .slave_handle_frame = netvsc_vf_handle_frame,
+};
+
static int netvsc_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id)
{
@@ -2083,8 +2014,14 @@ static int netvsc_probe(struct hv_device *dev,
goto register_failed;
}
+ net_device_ctx->failover = failover_register(net, &netvsc_failover_ops);
+ if (IS_ERR(net_device_ctx->failover))
+ goto err_failover;
+
return ret;
+err_failover:
+ unregister_netdev(net);
register_failed:
rndis_filter_device_remove(dev, nvdev);
rndis_failed:
@@ -2125,13 +2062,15 @@ static int netvsc_remove(struct hv_device *dev)
rtnl_lock();
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (vf_netdev)
- netvsc_unregister_vf(vf_netdev);
+ failover_slave_unregister(vf_netdev);
if (nvdev)
rndis_filter_device_remove(dev, nvdev);
unregister_netdevice(net);
+ failover_unregister(ndev_ctx->failover);
+
rtnl_unlock();
rcu_read_unlock();
@@ -2158,54 +2097,8 @@ static struct hv_driver netvsc_drv = {
.remove = netvsc_remove,
};
-/*
- * On Hyper-V, every VF interface is matched with a corresponding
- * synthetic interface. The synthetic interface is presented first
- * to the guest. When the corresponding VF instance is registered,
- * we will take care of switching the data path.
- */
-static int netvsc_netdev_event(struct notifier_block *this,
- unsigned long event, void *ptr)
-{
- struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
-
- /* Skip our own events */
- if (event_dev->netdev_ops == &device_ops)
- return NOTIFY_DONE;
-
- /* Avoid non-Ethernet type devices */
- if (event_dev->type != ARPHRD_ETHER)
- return NOTIFY_DONE;
-
- /* Avoid Vlan dev with same MAC registering as VF */
- if (is_vlan_dev(event_dev))
- return NOTIFY_DONE;
-
- /* Avoid Bonding master dev with same MAC registering as VF */
- if ((event_dev->priv_flags & IFF_BONDING) &&
- (event_dev->flags & IFF_MASTER))
- return NOTIFY_DONE;
-
- switch (event) {
- case NETDEV_REGISTER:
- return netvsc_register_vf(event_dev);
- case NETDEV_UNREGISTER:
- return netvsc_unregister_vf(event_dev);
- case NETDEV_UP:
- case NETDEV_DOWN:
- return netvsc_vf_changed(event_dev);
- default:
- return NOTIFY_DONE;
- }
-}
-
-static struct notifier_block netvsc_netdev_notifier = {
- .notifier_call = netvsc_netdev_event,
-};
-
static void __exit netvsc_drv_exit(void)
{
- unregister_netdevice_notifier(&netvsc_netdev_notifier);
vmbus_driver_unregister(&netvsc_drv);
}
@@ -2225,7 +2118,6 @@ static int __init netvsc_drv_init(void)
if (ret)
return ret;
- register_netdevice_notifier(&netvsc_netdev_notifier);
return 0;
}
--
2.14.3
^ permalink raw reply related
* [PATCH net-next 2/5] qede: Validate unsupported configurations
From: Manish Chopra @ 2018-05-24 16:54 UTC (permalink / raw)
To: davem; +Cc: netdev, ariel.elior, michal.kalderon
In-Reply-To: <20180524165453.11852-1-manish.chopra@cavium.com>
Validate and prevent some of the configurations for
unsupported [by firmware] inputs [for example - mac ext,
vlans, masks/prefix, tos/tclass] via ethtool -N/-U.
Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
---
drivers/net/ethernet/qlogic/qede/qede_filter.c | 73 ++++++++++++++++++++++++++
1 file changed, 73 insertions(+)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index bd5b4e4..43ed420 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1560,10 +1560,63 @@ static void qede_flow_build_ipv6_hdr(struct qede_arfs_tuple *t,
ports[1] = t->dst_port;
}
+/* Validate fields which are set and not accepted by the driver */
+static int qede_flow_spec_validate_unused(struct qede_dev *edev,
+ struct ethtool_rx_flow_spec *fs)
+{
+ if (fs->flow_type & FLOW_MAC_EXT) {
+ DP_INFO(edev, "Don't support MAC extensions\n");
+ return -EOPNOTSUPP;
+ }
+
+ if ((fs->flow_type & FLOW_EXT) &&
+ (fs->h_ext.vlan_etype || fs->h_ext.vlan_tci)) {
+ DP_INFO(edev, "Don't support vlan-based classification\n");
+ return -EOPNOTSUPP;
+ }
+
+ if ((fs->flow_type & FLOW_EXT) &&
+ (fs->h_ext.data[0] || fs->h_ext.data[1])) {
+ DP_INFO(edev, "Don't support user defined data\n");
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
struct qede_arfs_tuple *t,
struct ethtool_rx_flow_spec *fs)
{
+ if ((fs->h_u.tcp_ip4_spec.ip4src &
+ fs->m_u.tcp_ip4_spec.ip4src) != fs->h_u.tcp_ip4_spec.ip4src) {
+ DP_INFO(edev, "Don't support IP-masks\n");
+ return -EOPNOTSUPP;
+ }
+
+ if ((fs->h_u.tcp_ip4_spec.ip4dst &
+ fs->m_u.tcp_ip4_spec.ip4dst) != fs->h_u.tcp_ip4_spec.ip4dst) {
+ DP_INFO(edev, "Don't support IP-masks\n");
+ return -EOPNOTSUPP;
+ }
+
+ if ((fs->h_u.tcp_ip4_spec.psrc &
+ fs->m_u.tcp_ip4_spec.psrc) != fs->h_u.tcp_ip4_spec.psrc) {
+ DP_INFO(edev, "Don't support port-masks\n");
+ return -EOPNOTSUPP;
+ }
+
+ if ((fs->h_u.tcp_ip4_spec.pdst &
+ fs->m_u.tcp_ip4_spec.pdst) != fs->h_u.tcp_ip4_spec.pdst) {
+ DP_INFO(edev, "Don't support port-masks\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (fs->h_u.tcp_ip4_spec.tos) {
+ DP_INFO(edev, "Don't support tos\n");
+ return -EOPNOTSUPP;
+ }
+
t->eth_proto = htons(ETH_P_IP);
t->src_ipv4 = fs->h_u.tcp_ip4_spec.ip4src;
t->dst_ipv4 = fs->h_u.tcp_ip4_spec.ip4dst;
@@ -1619,6 +1672,23 @@ static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
p = &zero_addr;
memset(p, 0, sizeof(zero_addr));
+ if ((fs->h_u.tcp_ip6_spec.psrc &
+ fs->m_u.tcp_ip6_spec.psrc) != fs->h_u.tcp_ip6_spec.psrc) {
+ DP_INFO(edev, "Don't support port-masks\n");
+ return -EOPNOTSUPP;
+ }
+
+ if ((fs->h_u.tcp_ip6_spec.pdst &
+ fs->m_u.tcp_ip6_spec.pdst) != fs->h_u.tcp_ip6_spec.pdst) {
+ DP_INFO(edev, "Don't support port-masks\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (fs->h_u.tcp_ip6_spec.tclass) {
+ DP_INFO(edev, "Don't support tclass\n");
+ return -EOPNOTSUPP;
+ }
+
t->eth_proto = htons(ETH_P_IPV6);
memcpy(&t->src_ipv6, &fs->h_u.tcp_ip6_spec.ip6src,
sizeof(struct in6_addr));
@@ -1673,6 +1743,9 @@ static int qede_flow_spec_to_tuple(struct qede_dev *edev,
{
memset(t, 0, sizeof(*t));
+ if (qede_flow_spec_validate_unused(edev, fs))
+ return -EOPNOTSUPP;
+
switch ((fs->flow_type & ~FLOW_EXT)) {
case TCP_V4_FLOW:
return qede_flow_spec_to_tuple_tcpv4(edev, t, fs);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next v12 3/5] net: Introduce net_failover driver
From: Sridhar Samudrala @ 2018-05-24 16:55 UTC (permalink / raw)
To: mst, stephen, davem, netdev, virtualization, virtio-dev,
jesse.brandeburg, alexander.h.duyck, kubakici, sridhar.samudrala,
jasowang, loseweigh, jiri, aaron.f.brown, anjali.singhai
In-Reply-To: <1527180917-39737-1-git-send-email-sridhar.samudrala@intel.com>
The net_failover driver provides an automated failover mechanism via APIs
to create and destroy a failover master netdev and manages a primary and
standby slave netdevs that get registered via the generic failover
infrastructure.
The failover netdev acts a master device and controls 2 slave devices. The
original paravirtual interface gets registered as 'standby' slave netdev and
a passthru/vf device with the same MAC gets registered as 'primary' slave
netdev. Both 'standby' and 'failover' netdevs are associated with the same
'pci' device. The user accesses the network interface via 'failover' netdev.
The 'failover' netdev chooses 'primary' netdev as default for transmits when
it is available with link up and running.
This can be used by paravirtual drivers to enable an alternate low latency
datapath. It also enables hypervisor controlled live migration of a VM with
direct attached VF by failing over to the paravirtual datapath when the VF
is unplugged.
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
Documentation/networking/net_failover.rst | 26 +
MAINTAINERS | 8 +
drivers/net/Kconfig | 12 +
drivers/net/Makefile | 1 +
drivers/net/net_failover.c | 836 ++++++++++++++++++++++++++++++
include/net/net_failover.h | 40 ++
6 files changed, 923 insertions(+)
create mode 100644 Documentation/networking/net_failover.rst
create mode 100644 drivers/net/net_failover.c
create mode 100644 include/net/net_failover.h
diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst
new file mode 100644
index 000000000000..d4513ad31809
--- /dev/null
+++ b/Documentation/networking/net_failover.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+NET_FAILOVER
+============
+
+Overview
+========
+
+The net_failover driver provides an automated failover mechanism via APIs
+to create and destroy a failover master netdev and mananges a primary and
+standby slave netdevs that get registered via the generic failover
+infrastructrure.
+
+The failover netdev acts a master device and controls 2 slave devices. The
+original paravirtual interface is registered as 'standby' slave netdev and
+a passthru/vf device with the same MAC gets registered as 'primary' slave
+netdev. Both 'standby' and 'failover' netdevs are associated with the same
+'pci' device. The user accesses the network interface via 'failover' netdev.
+The 'failover' netdev chooses 'primary' netdev as default for transmits when
+it is available with link up and running.
+
+This can be used by paravirtual drivers to enable an alternate low latency
+datapath. It also enables hypervisor controlled live migration of a VM with
+direct attached VF by failing over to the paravirtual datapath when the VF
+is unplugged.
diff --git a/MAINTAINERS b/MAINTAINERS
index ee0ce10b2a8d..0cc6a5bb0b60 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9642,6 +9642,14 @@ S: Maintained
F: Documentation/hwmon/nct6775
F: drivers/hwmon/nct6775.c
+NET_FAILOVER MODULE
+M: Sridhar Samudrala <sridhar.samudrala@intel.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: driver/net/net_failover.c
+F: include/net/net_failover.h
+F: Documentation/networking/net_failover.rst
+
NETEFFECT IWARP RNIC DRIVER (IW_NES)
M: Faisal Latif <faisal.latif@intel.com>
L: linux-rdma@vger.kernel.org
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index a029b27fd002..2cdaff90a9ec 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -510,4 +510,16 @@ config NETDEVSIM
To compile this driver as a module, choose M here: the module
will be called netdevsim.
+config NET_FAILOVER
+ tristate "Failover driver"
+ select FAILOVER
+ help
+ This provides an automated failover mechanism via APIs to create
+ and destroy a failover master netdev and manages a primary and
+ standby slave netdevs that get registered via the generic failover
+ infrastructure. This can be used by paravirtual drivers to enable
+ an alternate low latency datapath. It alsoenables live migration of
+ a VM with direct attached VF by failing over to the paravirtual
+ datapath when the VF is unplugged.
+
endif # NETDEVICES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 91e67e375dd4..21cde7e78621 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -78,3 +78,4 @@ obj-$(CONFIG_FUJITSU_ES) += fjes/
thunderbolt-net-y += thunderbolt.o
obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
obj-$(CONFIG_NETDEVSIM) += netdevsim/
+obj-$(CONFIG_NET_FAILOVER) += net_failover.o
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
new file mode 100644
index 000000000000..8b508e2cf29b
--- /dev/null
+++ b/drivers/net/net_failover.c
@@ -0,0 +1,836 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+/* This provides a net_failover interface for paravirtual drivers to
+ * provide an alternate datapath by exporting APIs to create and
+ * destroy a upper 'net_failover' netdev. The upper dev manages the
+ * original paravirtual interface as a 'standby' netdev and uses the
+ * generic failover infrastructure to register and manage a direct
+ * attached VF as a 'primary' netdev. This enables live migration of
+ * a VM with direct attached VF by failing over to the paravirtual
+ * datapath when the VF is unplugged.
+ *
+ * Some of the netdev management routines are based on bond/team driver as
+ * this driver provides active-backup functionality similar to those drivers.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/netpoll.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <linux/pci.h>
+#include <net/sch_generic.h>
+#include <uapi/linux/if_arp.h>
+#include <net/net_failover.h>
+
+static bool net_failover_xmit_ready(struct net_device *dev)
+{
+ return netif_running(dev) && netif_carrier_ok(dev);
+}
+
+static int net_failover_open(struct net_device *dev)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *primary_dev, *standby_dev;
+ int err;
+
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ if (primary_dev) {
+ err = dev_open(primary_dev);
+ if (err)
+ goto err_primary_open;
+ }
+
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+ if (standby_dev) {
+ err = dev_open(standby_dev);
+ if (err)
+ goto err_standby_open;
+ }
+
+ if ((primary_dev && net_failover_xmit_ready(primary_dev)) ||
+ (standby_dev && net_failover_xmit_ready(standby_dev))) {
+ netif_carrier_on(dev);
+ netif_tx_wake_all_queues(dev);
+ }
+
+ return 0;
+
+err_standby_open:
+ dev_close(primary_dev);
+err_primary_open:
+ netif_tx_disable(dev);
+ return err;
+}
+
+static int net_failover_close(struct net_device *dev)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *slave_dev;
+
+ netif_tx_disable(dev);
+
+ slave_dev = rtnl_dereference(nfo_info->primary_dev);
+ if (slave_dev)
+ dev_close(slave_dev);
+
+ slave_dev = rtnl_dereference(nfo_info->standby_dev);
+ if (slave_dev)
+ dev_close(slave_dev);
+
+ return 0;
+}
+
+static netdev_tx_t net_failover_drop_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ atomic_long_inc(&dev->tx_dropped);
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+}
+
+static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *xmit_dev;
+
+ /* Try xmit via primary netdev followed by standby netdev */
+ xmit_dev = rcu_dereference_bh(nfo_info->primary_dev);
+ if (!xmit_dev || !net_failover_xmit_ready(xmit_dev)) {
+ xmit_dev = rcu_dereference_bh(nfo_info->standby_dev);
+ if (!xmit_dev || !net_failover_xmit_ready(xmit_dev))
+ return net_failover_drop_xmit(skb, dev);
+ }
+
+ skb->dev = xmit_dev;
+ skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+
+ return dev_queue_xmit(skb);
+}
+
+static u16 net_failover_select_queue(struct net_device *dev,
+ struct sk_buff *skb, void *accel_priv,
+ select_queue_fallback_t fallback)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *primary_dev;
+ u16 txq;
+
+ primary_dev = rcu_dereference(nfo_info->primary_dev);
+ if (primary_dev) {
+ const struct net_device_ops *ops = primary_dev->netdev_ops;
+
+ if (ops->ndo_select_queue)
+ txq = ops->ndo_select_queue(primary_dev, skb,
+ accel_priv, fallback);
+ else
+ txq = fallback(primary_dev, skb);
+
+ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+
+ return txq;
+ }
+
+ txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
+
+ /* Save the original txq to restore before passing to the driver */
+ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+
+ if (unlikely(txq >= dev->real_num_tx_queues)) {
+ do {
+ txq -= dev->real_num_tx_queues;
+ } while (txq >= dev->real_num_tx_queues);
+ }
+
+ return txq;
+}
+
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void net_failover_fold_stats(struct rtnl_link_stats64 *_res,
+ const struct rtnl_link_stats64 *_new,
+ const struct rtnl_link_stats64 *_old)
+{
+ const u64 *new = (const u64 *)_new;
+ const u64 *old = (const u64 *)_old;
+ u64 *res = (u64 *)_res;
+ int i;
+
+ for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+ u64 nv = new[i];
+ u64 ov = old[i];
+ s64 delta = nv - ov;
+
+ /* detects if this particular field is 32bit only */
+ if (((nv | ov) >> 32) == 0)
+ delta = (s64)(s32)((u32)nv - (u32)ov);
+
+ /* filter anomalies, some drivers reset their stats
+ * at down/up events.
+ */
+ if (delta > 0)
+ res[i] += delta;
+ }
+}
+
+static void net_failover_get_stats(struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ const struct rtnl_link_stats64 *new;
+ struct rtnl_link_stats64 temp;
+ struct net_device *slave_dev;
+
+ spin_lock(&nfo_info->stats_lock);
+ memcpy(stats, &nfo_info->failover_stats, sizeof(*stats));
+
+ rcu_read_lock();
+
+ slave_dev = rcu_dereference(nfo_info->primary_dev);
+ if (slave_dev) {
+ new = dev_get_stats(slave_dev, &temp);
+ net_failover_fold_stats(stats, new, &nfo_info->primary_stats);
+ memcpy(&nfo_info->primary_stats, new, sizeof(*new));
+ }
+
+ slave_dev = rcu_dereference(nfo_info->standby_dev);
+ if (slave_dev) {
+ new = dev_get_stats(slave_dev, &temp);
+ net_failover_fold_stats(stats, new, &nfo_info->standby_stats);
+ memcpy(&nfo_info->standby_stats, new, sizeof(*new));
+ }
+
+ rcu_read_unlock();
+
+ memcpy(&nfo_info->failover_stats, stats, sizeof(*stats));
+ spin_unlock(&nfo_info->stats_lock);
+}
+
+static int net_failover_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *primary_dev, *standby_dev;
+ int ret = 0;
+
+ primary_dev = rcu_dereference(nfo_info->primary_dev);
+ if (primary_dev) {
+ ret = dev_set_mtu(primary_dev, new_mtu);
+ if (ret)
+ return ret;
+ }
+
+ standby_dev = rcu_dereference(nfo_info->standby_dev);
+ if (standby_dev) {
+ ret = dev_set_mtu(standby_dev, new_mtu);
+ if (ret) {
+ if (primary_dev)
+ dev_set_mtu(primary_dev, dev->mtu);
+ return ret;
+ }
+ }
+
+ dev->mtu = new_mtu;
+
+ return 0;
+}
+
+static void net_failover_set_rx_mode(struct net_device *dev)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *slave_dev;
+
+ rcu_read_lock();
+
+ slave_dev = rcu_dereference(nfo_info->primary_dev);
+ if (slave_dev) {
+ dev_uc_sync_multiple(slave_dev, dev);
+ dev_mc_sync_multiple(slave_dev, dev);
+ }
+
+ slave_dev = rcu_dereference(nfo_info->standby_dev);
+ if (slave_dev) {
+ dev_uc_sync_multiple(slave_dev, dev);
+ dev_mc_sync_multiple(slave_dev, dev);
+ }
+
+ rcu_read_unlock();
+}
+
+static int net_failover_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
+ u16 vid)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *primary_dev, *standby_dev;
+ int ret = 0;
+
+ primary_dev = rcu_dereference(nfo_info->primary_dev);
+ if (primary_dev) {
+ ret = vlan_vid_add(primary_dev, proto, vid);
+ if (ret)
+ return ret;
+ }
+
+ standby_dev = rcu_dereference(nfo_info->standby_dev);
+ if (standby_dev) {
+ ret = vlan_vid_add(standby_dev, proto, vid);
+ if (ret)
+ if (primary_dev)
+ vlan_vid_del(primary_dev, proto, vid);
+ }
+
+ return ret;
+}
+
+static int net_failover_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+ u16 vid)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *slave_dev;
+
+ slave_dev = rcu_dereference(nfo_info->primary_dev);
+ if (slave_dev)
+ vlan_vid_del(slave_dev, proto, vid);
+
+ slave_dev = rcu_dereference(nfo_info->standby_dev);
+ if (slave_dev)
+ vlan_vid_del(slave_dev, proto, vid);
+
+ return 0;
+}
+
+static const struct net_device_ops failover_dev_ops = {
+ .ndo_open = net_failover_open,
+ .ndo_stop = net_failover_close,
+ .ndo_start_xmit = net_failover_start_xmit,
+ .ndo_select_queue = net_failover_select_queue,
+ .ndo_get_stats64 = net_failover_get_stats,
+ .ndo_change_mtu = net_failover_change_mtu,
+ .ndo_set_rx_mode = net_failover_set_rx_mode,
+ .ndo_vlan_rx_add_vid = net_failover_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = net_failover_vlan_rx_kill_vid,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_features_check = passthru_features_check,
+};
+
+#define FAILOVER_NAME "net_failover"
+#define FAILOVER_VERSION "0.1"
+
+static void nfo_ethtool_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ strlcpy(drvinfo->driver, FAILOVER_NAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, FAILOVER_VERSION, sizeof(drvinfo->version));
+}
+
+static int nfo_ethtool_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *slave_dev;
+
+ slave_dev = rtnl_dereference(nfo_info->primary_dev);
+ if (!slave_dev || !net_failover_xmit_ready(slave_dev)) {
+ slave_dev = rtnl_dereference(nfo_info->standby_dev);
+ if (!slave_dev || !net_failover_xmit_ready(slave_dev)) {
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+ cmd->base.port = PORT_OTHER;
+ cmd->base.speed = SPEED_UNKNOWN;
+
+ return 0;
+ }
+ }
+
+ return __ethtool_get_link_ksettings(slave_dev, cmd);
+}
+
+static const struct ethtool_ops failover_ethtool_ops = {
+ .get_drvinfo = nfo_ethtool_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = nfo_ethtool_get_link_ksettings,
+};
+
+/* Called when slave dev is injecting data into network stack.
+ * Change the associated network device from lower dev to failover dev.
+ * note: already called with rcu_read_lock
+ */
+static rx_handler_result_t net_failover_handle_frame(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct net_device *dev = rcu_dereference(skb->dev->rx_handler_data);
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *primary_dev, *standby_dev;
+
+ primary_dev = rcu_dereference(nfo_info->primary_dev);
+ standby_dev = rcu_dereference(nfo_info->standby_dev);
+
+ if (primary_dev && skb->dev == standby_dev)
+ return RX_HANDLER_EXACT;
+
+ skb->dev = dev;
+
+ return RX_HANDLER_ANOTHER;
+}
+
+static void net_failover_compute_features(struct net_device *dev)
+{
+ u32 vlan_features = FAILOVER_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
+ netdev_features_t enc_features = FAILOVER_ENC_FEATURES;
+ unsigned short max_hard_header_len = ETH_HLEN;
+ unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
+ IFF_XMIT_DST_RELEASE_PERM;
+ struct net_failover_info *nfo_info = netdev_priv(dev);
+ struct net_device *primary_dev, *standby_dev;
+
+ primary_dev = rcu_dereference(nfo_info->primary_dev);
+ if (primary_dev) {
+ vlan_features =
+ netdev_increment_features(vlan_features,
+ primary_dev->vlan_features,
+ FAILOVER_VLAN_FEATURES);
+ enc_features =
+ netdev_increment_features(enc_features,
+ primary_dev->hw_enc_features,
+ FAILOVER_ENC_FEATURES);
+
+ dst_release_flag &= primary_dev->priv_flags;
+ if (primary_dev->hard_header_len > max_hard_header_len)
+ max_hard_header_len = primary_dev->hard_header_len;
+ }
+
+ standby_dev = rcu_dereference(nfo_info->standby_dev);
+ if (standby_dev) {
+ vlan_features =
+ netdev_increment_features(vlan_features,
+ standby_dev->vlan_features,
+ FAILOVER_VLAN_FEATURES);
+ enc_features =
+ netdev_increment_features(enc_features,
+ standby_dev->hw_enc_features,
+ FAILOVER_ENC_FEATURES);
+
+ dst_release_flag &= standby_dev->priv_flags;
+ if (standby_dev->hard_header_len > max_hard_header_len)
+ max_hard_header_len = standby_dev->hard_header_len;
+ }
+
+ dev->vlan_features = vlan_features;
+ dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL;
+ dev->hard_header_len = max_hard_header_len;
+
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ if (dst_release_flag == (IFF_XMIT_DST_RELEASE |
+ IFF_XMIT_DST_RELEASE_PERM))
+ dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+
+ netdev_change_features(dev);
+}
+
+static void net_failover_lower_state_changed(struct net_device *slave_dev,
+ struct net_device *primary_dev,
+ struct net_device *standby_dev)
+{
+ struct netdev_lag_lower_state_info info;
+
+ if (netif_carrier_ok(slave_dev))
+ info.link_up = true;
+ else
+ info.link_up = false;
+
+ if (slave_dev == primary_dev) {
+ if (netif_running(primary_dev))
+ info.tx_enabled = true;
+ else
+ info.tx_enabled = false;
+ } else {
+ if ((primary_dev && netif_running(primary_dev)) ||
+ (!netif_running(standby_dev)))
+ info.tx_enabled = false;
+ else
+ info.tx_enabled = true;
+ }
+
+ netdev_lower_state_changed(slave_dev, &info);
+}
+
+static int net_failover_slave_pre_register(struct net_device *slave_dev,
+ struct net_device *failover_dev)
+{
+ struct net_device *standby_dev, *primary_dev;
+ struct net_failover_info *nfo_info;
+ bool slave_is_standby;
+
+ nfo_info = netdev_priv(failover_dev);
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ slave_is_standby = slave_dev->dev.parent == failover_dev->dev.parent;
+ if (slave_is_standby ? standby_dev : primary_dev) {
+ netdev_err(failover_dev, "%s attempting to register as slave dev when %s already present\n",
+ slave_dev->name,
+ slave_is_standby ? "standby" : "primary");
+ return -EINVAL;
+ }
+
+ /* We want to allow only a direct attached VF device as a primary
+ * netdev. As there is no easy way to check for a VF device, restrict
+ * this to a pci device.
+ */
+ if (!slave_is_standby && (!slave_dev->dev.parent ||
+ !dev_is_pci(slave_dev->dev.parent)))
+ return -EINVAL;
+
+ if (failover_dev->features & NETIF_F_VLAN_CHALLENGED &&
+ vlan_uses_dev(failover_dev)) {
+ netdev_err(failover_dev, "Device %s is VLAN challenged and failover device has VLAN set up\n",
+ failover_dev->name);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int net_failover_slave_register(struct net_device *slave_dev,
+ struct net_device *failover_dev)
+{
+ struct net_device *standby_dev, *primary_dev;
+ struct net_failover_info *nfo_info;
+ bool slave_is_standby;
+ u32 orig_mtu;
+ int err;
+
+ /* Align MTU of slave with failover dev */
+ orig_mtu = slave_dev->mtu;
+ err = dev_set_mtu(slave_dev, failover_dev->mtu);
+ if (err) {
+ netdev_err(failover_dev, "unable to change mtu of %s to %u register failed\n",
+ slave_dev->name, failover_dev->mtu);
+ goto done;
+ }
+
+ dev_hold(slave_dev);
+
+ if (netif_running(failover_dev)) {
+ err = dev_open(slave_dev);
+ if (err && (err != -EBUSY)) {
+ netdev_err(failover_dev, "Opening slave %s failed err:%d\n",
+ slave_dev->name, err);
+ goto err_dev_open;
+ }
+ }
+
+ netif_addr_lock_bh(failover_dev);
+ dev_uc_sync_multiple(slave_dev, failover_dev);
+ dev_uc_sync_multiple(slave_dev, failover_dev);
+ netif_addr_unlock_bh(failover_dev);
+
+ err = vlan_vids_add_by_dev(slave_dev, failover_dev);
+ if (err) {
+ netdev_err(failover_dev, "Failed to add vlan ids to device %s err:%d\n",
+ slave_dev->name, err);
+ goto err_vlan_add;
+ }
+
+ nfo_info = netdev_priv(failover_dev);
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ slave_is_standby = slave_dev->dev.parent == failover_dev->dev.parent;
+
+ if (slave_is_standby) {
+ rcu_assign_pointer(nfo_info->standby_dev, slave_dev);
+ standby_dev = slave_dev;
+ dev_get_stats(standby_dev, &nfo_info->standby_stats);
+ } else {
+ rcu_assign_pointer(nfo_info->primary_dev, slave_dev);
+ primary_dev = slave_dev;
+ dev_get_stats(primary_dev, &nfo_info->primary_stats);
+ failover_dev->min_mtu = slave_dev->min_mtu;
+ failover_dev->max_mtu = slave_dev->max_mtu;
+ }
+
+ net_failover_lower_state_changed(slave_dev, primary_dev, standby_dev);
+ net_failover_compute_features(failover_dev);
+
+ call_netdevice_notifiers(NETDEV_JOIN, slave_dev);
+
+ netdev_info(failover_dev, "failover %s slave:%s registered\n",
+ slave_is_standby ? "standby" : "primary", slave_dev->name);
+
+ return 0;
+
+err_vlan_add:
+ dev_uc_unsync(slave_dev, failover_dev);
+ dev_mc_unsync(slave_dev, failover_dev);
+ dev_close(slave_dev);
+err_dev_open:
+ dev_put(slave_dev);
+ dev_set_mtu(slave_dev, orig_mtu);
+done:
+ return err;
+}
+
+static int net_failover_slave_pre_unregister(struct net_device *slave_dev,
+ struct net_device *failover_dev)
+{
+ struct net_device *standby_dev, *primary_dev;
+ struct net_failover_info *nfo_info;
+
+ nfo_info = netdev_priv(failover_dev);
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+
+ if (slave_dev != primary_dev && slave_dev != standby_dev)
+ return -ENODEV;
+
+ return 0;
+}
+
+static int net_failover_slave_unregister(struct net_device *slave_dev,
+ struct net_device *failover_dev)
+{
+ struct net_device *standby_dev, *primary_dev;
+ struct net_failover_info *nfo_info;
+ bool slave_is_standby;
+
+ nfo_info = netdev_priv(failover_dev);
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+
+ vlan_vids_del_by_dev(slave_dev, failover_dev);
+ dev_uc_unsync(slave_dev, failover_dev);
+ dev_mc_unsync(slave_dev, failover_dev);
+ dev_close(slave_dev);
+
+ nfo_info = netdev_priv(failover_dev);
+ dev_get_stats(failover_dev, &nfo_info->failover_stats);
+
+ slave_is_standby = slave_dev->dev.parent == failover_dev->dev.parent;
+ if (slave_is_standby) {
+ RCU_INIT_POINTER(nfo_info->standby_dev, NULL);
+ } else {
+ RCU_INIT_POINTER(nfo_info->primary_dev, NULL);
+ if (standby_dev) {
+ failover_dev->min_mtu = standby_dev->min_mtu;
+ failover_dev->max_mtu = standby_dev->max_mtu;
+ }
+ }
+
+ dev_put(slave_dev);
+
+ net_failover_compute_features(failover_dev);
+
+ netdev_info(failover_dev, "failover %s slave:%s unregistered\n",
+ slave_is_standby ? "standby" : "primary", slave_dev->name);
+
+ return 0;
+}
+
+static int net_failover_slave_link_change(struct net_device *slave_dev,
+ struct net_device *failover_dev)
+{
+ struct net_device *primary_dev, *standby_dev;
+ struct net_failover_info *nfo_info;
+
+ nfo_info = netdev_priv(failover_dev);
+
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+
+ if (slave_dev != primary_dev && slave_dev != standby_dev)
+ return -ENODEV;
+
+ if ((primary_dev && net_failover_xmit_ready(primary_dev)) ||
+ (standby_dev && net_failover_xmit_ready(standby_dev))) {
+ netif_carrier_on(failover_dev);
+ netif_tx_wake_all_queues(failover_dev);
+ } else {
+ dev_get_stats(failover_dev, &nfo_info->failover_stats);
+ netif_carrier_off(failover_dev);
+ netif_tx_stop_all_queues(failover_dev);
+ }
+
+ net_failover_lower_state_changed(slave_dev, primary_dev, standby_dev);
+
+ return 0;
+}
+
+static int net_failover_slave_name_change(struct net_device *slave_dev,
+ struct net_device *failover_dev)
+{
+ struct net_device *primary_dev, *standby_dev;
+ struct net_failover_info *nfo_info;
+
+ nfo_info = netdev_priv(failover_dev);
+
+ primary_dev = rtnl_dereference(nfo_info->primary_dev);
+ standby_dev = rtnl_dereference(nfo_info->standby_dev);
+
+ if (slave_dev != primary_dev && slave_dev != standby_dev)
+ return -ENODEV;
+
+ /* We need to bring up the slave after the rename by udev in case
+ * open failed with EBUSY when it was registered.
+ */
+ dev_open(slave_dev);
+
+ return 0;
+}
+
+static struct failover_ops net_failover_ops = {
+ .slave_pre_register = net_failover_slave_pre_register,
+ .slave_register = net_failover_slave_register,
+ .slave_pre_unregister = net_failover_slave_pre_unregister,
+ .slave_unregister = net_failover_slave_unregister,
+ .slave_link_change = net_failover_slave_link_change,
+ .slave_name_change = net_failover_slave_name_change,
+ .slave_handle_frame = net_failover_handle_frame,
+};
+
+/**
+ * net_failover_create - Create and register a failover instance
+ *
+ * @dev: standby netdev
+ *
+ * Creates a failover netdev and registers a failover instance for a standby
+ * netdev. Used by paravirtual drivers that use 3-netdev model.
+ * The failover netdev acts as a master device and controls 2 slave devices -
+ * the original standby netdev and a VF netdev with the same MAC gets
+ * registered as primary netdev.
+ *
+ * Return: pointer to failover instance
+ */
+struct failover *net_failover_create(struct net_device *standby_dev)
+{
+ struct device *dev = standby_dev->dev.parent;
+ struct net_device *failover_dev;
+ struct failover *failover;
+ int err;
+
+ /* Alloc at least 2 queues, for now we are going with 16 assuming
+ * that VF devices being enslaved won't have too many queues.
+ */
+ failover_dev = alloc_etherdev_mq(sizeof(struct net_failover_info), 16);
+ if (!failover_dev) {
+ dev_err(dev, "Unable to allocate failover_netdev!\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ dev_net_set(failover_dev, dev_net(standby_dev));
+ SET_NETDEV_DEV(failover_dev, dev);
+
+ failover_dev->netdev_ops = &failover_dev_ops;
+ failover_dev->ethtool_ops = &failover_ethtool_ops;
+
+ /* Initialize the device options */
+ failover_dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
+ failover_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE |
+ IFF_TX_SKB_SHARING);
+
+ /* don't acquire failover netdev's netif_tx_lock when transmitting */
+ failover_dev->features |= NETIF_F_LLTX;
+
+ /* Don't allow failover devices to change network namespaces. */
+ failover_dev->features |= NETIF_F_NETNS_LOCAL;
+
+ failover_dev->hw_features = FAILOVER_VLAN_FEATURES |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_CTAG_FILTER;
+
+ failover_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
+ failover_dev->features |= failover_dev->hw_features;
+
+ memcpy(failover_dev->dev_addr, standby_dev->dev_addr,
+ failover_dev->addr_len);
+
+ failover_dev->min_mtu = standby_dev->min_mtu;
+ failover_dev->max_mtu = standby_dev->max_mtu;
+
+ err = register_netdev(failover_dev);
+ if (err) {
+ dev_err(dev, "Unable to register failover_dev!\n");
+ goto err_register_netdev;
+ }
+
+ netif_carrier_off(failover_dev);
+
+ failover = failover_register(failover_dev, &net_failover_ops);
+ if (IS_ERR(failover))
+ goto err_failover_register;
+
+ return failover;
+
+err_failover_register:
+ unregister_netdev(failover_dev);
+err_register_netdev:
+ free_netdev(failover_dev);
+
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(net_failover_create);
+
+/**
+ * net_failover_destroy - Destroy a failover instance
+ *
+ * @failover: pointer to failover instance
+ *
+ * Unregisters any slave netdevs associated with the failover instance by
+ * calling failover_slave_unregister().
+ * unregisters the failover instance itself and finally frees the failover
+ * netdev. Used by paravirtual drivers that use 3-netdev model.
+ *
+ */
+void net_failover_destroy(struct failover *failover)
+{
+ struct net_failover_info *nfo_info;
+ struct net_device *failover_dev;
+ struct net_device *slave_dev;
+
+ if (!failover)
+ return;
+
+ failover_dev = rcu_dereference(failover->failover_dev);
+ nfo_info = netdev_priv(failover_dev);
+
+ netif_device_detach(failover_dev);
+
+ rtnl_lock();
+
+ slave_dev = rtnl_dereference(nfo_info->primary_dev);
+ if (slave_dev)
+ failover_slave_unregister(slave_dev);
+
+ slave_dev = rtnl_dereference(nfo_info->standby_dev);
+ if (slave_dev)
+ failover_slave_unregister(slave_dev);
+
+ failover_unregister(failover);
+
+ unregister_netdevice(failover_dev);
+
+ rtnl_unlock();
+
+ free_netdev(failover_dev);
+}
+EXPORT_SYMBOL_GPL(net_failover_destroy);
+
+static __init int
+net_failover_init(void)
+{
+ return 0;
+}
+module_init(net_failover_init);
+
+static __exit
+void net_failover_exit(void)
+{
+}
+module_exit(net_failover_exit);
+
+MODULE_DESCRIPTION("Failover driver for Paravirtual drivers");
+MODULE_LICENSE("GPL v2");
diff --git a/include/net/net_failover.h b/include/net/net_failover.h
new file mode 100644
index 000000000000..b12a1c469d1c
--- /dev/null
+++ b/include/net/net_failover.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _NET_FAILOVER_H
+#define _NET_FAILOVER_H
+
+#include <net/failover.h>
+
+/* failover state */
+struct net_failover_info {
+ /* primary netdev with same MAC */
+ struct net_device __rcu *primary_dev;
+
+ /* standby netdev */
+ struct net_device __rcu *standby_dev;
+
+ /* primary netdev stats */
+ struct rtnl_link_stats64 primary_stats;
+
+ /* standby netdev stats */
+ struct rtnl_link_stats64 standby_stats;
+
+ /* aggregated stats */
+ struct rtnl_link_stats64 failover_stats;
+
+ /* spinlock while updating stats */
+ spinlock_t stats_lock;
+};
+
+struct failover *net_failover_create(struct net_device *standby_dev);
+void net_failover_destroy(struct failover *failover);
+
+#define FAILOVER_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
+ NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+ NETIF_F_HIGHDMA | NETIF_F_LRO)
+
+#define FAILOVER_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
+ NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
+
+#endif /* _NET_FAILOVER_H */
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v12 4/5] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit
From: Sridhar Samudrala @ 2018-05-24 16:55 UTC (permalink / raw)
To: mst, stephen, davem, netdev, virtualization, virtio-dev,
jesse.brandeburg, alexander.h.duyck, kubakici, sridhar.samudrala,
jasowang, loseweigh, jiri, aaron.f.brown, anjali.singhai
In-Reply-To: <1527180917-39737-1-git-send-email-sridhar.samudrala@intel.com>
This feature bit can be used by hypervisor to indicate virtio_net device to
act as a standby for another device with the same MAC address.
VIRTIO_NET_F_STANDBY is defined as bit 62 as it is a device feature bit.
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
drivers/net/virtio_net.c | 2 +-
include/uapi/linux/virtio_net.h | 3 +++
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f34794a76c4d..213fddc70fd0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2999,7 +2999,7 @@ static struct virtio_device_id id_table[] = {
VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
VIRTIO_NET_F_CTRL_MAC_ADDR, \
VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
- VIRTIO_NET_F_SPEED_DUPLEX
+ VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY
static unsigned int features[] = {
VIRTNET_FEATURES,
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 5de6ed37695b..a3715a3224c1 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -57,6 +57,9 @@
* Steering */
#define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */
+#define VIRTIO_NET_F_STANDBY 62 /* Act as standby for another device
+ * with the same MAC.
+ */
#define VIRTIO_NET_F_SPEED_DUPLEX 63 /* Device set linkspeed and duplex */
#ifndef VIRTIO_NET_NO_LEGACY
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v12 5/5] virtio_net: Extend virtio to use VF datapath when available
From: Sridhar Samudrala @ 2018-05-24 16:55 UTC (permalink / raw)
To: mst, stephen, davem, netdev, virtualization, virtio-dev,
jesse.brandeburg, alexander.h.duyck, kubakici, sridhar.samudrala,
jasowang, loseweigh, jiri, aaron.f.brown, anjali.singhai
In-Reply-To: <1527180917-39737-1-git-send-email-sridhar.samudrala@intel.com>
This patch enables virtio_net to switch over to a VF datapath when STANDBY
feature is enabled and a VF netdev is present with the same MAC address.
It allows live migration of a VM with a direct attached VF without the need
to setup a bond/team between a VF and virtio net device in the guest.
It uses the API that is exported by the net_failover driver to create and
and destroy a master failover netdev. When STANDBY feature is enabled, an
additional netdev(failover netdev) is created that acts as a master device
and tracks the state of the 2 lower netdevs. The original virtio_net netdev
is marked as 'standby' netdev and a passthru device with the same MAC is
registered as 'primary' netdev.
The hypervisor needs to unplug the VF device from the guest on the source
host and reset the MAC filter of the VF to initiate failover of datapath
to virtio before starting the migration. After the migration is completed,
the destination hypervisor sets the MAC filter on the VF and plugs it back
to the guest to switch over to VF datapath.
This patch is based on the discussion initiated by Jesse on this thread.
https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
Documentation/networking/net_failover.rst | 90 +++++++++++++++++++++++++++++++
drivers/net/Kconfig | 1 +
drivers/net/virtio_net.c | 38 ++++++++++++-
3 files changed, 128 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst
index d4513ad31809..70ca2f5800c4 100644
--- a/Documentation/networking/net_failover.rst
+++ b/Documentation/networking/net_failover.rst
@@ -24,3 +24,93 @@ This can be used by paravirtual drivers to enable an alternate low latency
datapath. It also enables hypervisor controlled live migration of a VM with
direct attached VF by failing over to the paravirtual datapath when the VF
is unplugged.
+
+virtio-net accelerated datapath: STANDBY mode
+=============================================
+
+net_failover enables hypervisor controlled accelerated datapath to virtio-net
+enabled VMs in a transparent manner with no/minimal guest userspace chanages.
+
+To support this, the hypervisor needs to enable VIRTIO_NET_F_STANDBY
+feature on the virtio-net interface and assign the same MAC address to both
+virtio-net and VF interfaces.
+
+Here is an example XML snippet that shows such configuration.
+
+ <interface type='network'>
+ <mac address='52:54:00:00:12:53'/>
+ <source network='enp66s0f0_br'/>
+ <target dev='tap01'/>
+ <model type='virtio'/>
+ <driver name='vhost' queues='4'/>
+ <link state='down'/>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x0a' function='0x0'/>
+ </interface>
+ <interface type='hostdev' managed='yes'>
+ <mac address='52:54:00:00:12:53'/>
+ <source>
+ <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
+ </source>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
+ </interface>
+
+Booting a VM with the above configuration will result in the following 3
+netdevs created in the VM.
+
+4: ens10: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
+ link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+ inet 192.168.12.53/24 brd 192.168.12.255 scope global dynamic ens10
+ valid_lft 42482sec preferred_lft 42482sec
+ inet6 fe80::97d8:db2:8c10:b6d6/64 scope link
+ valid_lft forever preferred_lft forever
+5: ens10nsby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel master ens10 state UP group default qlen 1000
+ link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+7: ens11: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq master ens10 state UP group default qlen 1000
+ link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+
+ens10 is the 'failover' master netdev, ens10nsby and ens11 are the slave
+'standby' and 'primary' netdevs respectively.
+
+Live Migration of a VM with SR-IOV VF & virtio-net in STANDBY mode
+==================================================================
+
+net_failover also enables hypervisor controlled live migration to be supported
+with VMs that have direct attached SR-IOV VF devices by automatic failover to
+the paravirtual datapath when the VF is unplugged.
+
+Here is a sample script that shows the steps to initiate live migration on
+the source hypervisor.
+
+# cat vf_xml
+<interface type='hostdev' managed='yes'>
+ <mac address='52:54:00:00:12:53'/>
+ <source>
+ <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
+ </source>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
+</interface>
+
+# Source Hypervisor
+#!/bin/bash
+
+DOMAIN=fedora27-tap01
+PF=enp66s0f0
+VF_NUM=5
+TAP_IF=tap01
+VF_XML=
+
+MAC=52:54:00:00:12:53
+ZERO_MAC=00:00:00:00:00:00
+
+virsh domif-setlink $DOMAIN $TAP_IF up
+bridge fdb del $MAC dev $PF master
+virsh detach-device $DOMAIN $VF_XML
+ip link set $PF vf $VF_NUM mac $ZERO_MAC
+
+virsh migrate --live $DOMAIN qemu+ssh://$REMOTE_HOST/system
+
+# Destination Hypervisor
+#!/bin/bash
+
+virsh attach-device $DOMAIN $VF_XML
+virsh domif-setlink $DOMAIN $TAP_IF down
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 2cdaff90a9ec..d03775100f7d 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -332,6 +332,7 @@ config VETH
config VIRTIO_NET
tristate "Virtio network driver"
depends on VIRTIO
+ select NET_FAILOVER
---help---
This is the virtual network driver for virtio. It can be used with
QEMU based VMMs (like KVM or Xen). Say Y or M.
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 213fddc70fd0..370828c3d114 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -30,8 +30,11 @@
#include <linux/cpu.h>
#include <linux/average.h>
#include <linux/filter.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
#include <net/route.h>
#include <net/xdp.h>
+#include <net/net_failover.h>
static int napi_weight = NAPI_POLL_WEIGHT;
module_param(napi_weight, int, 0444);
@@ -210,6 +213,9 @@ struct virtnet_info {
u32 speed;
unsigned long guest_offloads;
+
+ /* failover when STANDBY feature enabled */
+ struct failover *failover;
};
struct padded_vnet_hdr {
@@ -1523,6 +1529,9 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
struct sockaddr *addr;
struct scatterlist sg;
+ if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
+ return -EOPNOTSUPP;
+
addr = kmemdup(p, sizeof(*addr), GFP_KERNEL);
if (!addr)
return -ENOMEM;
@@ -2306,6 +2315,22 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
}
}
+static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
+ size_t len)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ int ret;
+
+ if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
+ return -EOPNOTSUPP;
+
+ ret = snprintf(buf, len, "sby");
+ if (ret >= len)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
static const struct net_device_ops virtnet_netdev = {
.ndo_open = virtnet_open,
.ndo_stop = virtnet_close,
@@ -2323,6 +2348,7 @@ static const struct net_device_ops virtnet_netdev = {
.ndo_xdp_xmit = virtnet_xdp_xmit,
.ndo_xdp_flush = virtnet_xdp_flush,
.ndo_features_check = passthru_features_check,
+ .ndo_get_phys_port_name = virtnet_get_phys_port_name,
};
static void virtnet_config_changed_work(struct work_struct *work)
@@ -2876,10 +2902,16 @@ static int virtnet_probe(struct virtio_device *vdev)
virtnet_init_settings(dev);
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) {
+ vi->failover = net_failover_create(vi->dev);
+ if (IS_ERR(vi->failover))
+ goto free_vqs;
+ }
+
err = register_netdev(dev);
if (err) {
pr_debug("virtio_net: registering device failed\n");
- goto free_vqs;
+ goto free_failover;
}
virtio_device_ready(vdev);
@@ -2916,6 +2948,8 @@ static int virtnet_probe(struct virtio_device *vdev)
vi->vdev->config->reset(vdev);
unregister_netdev(dev);
+free_failover:
+ net_failover_destroy(vi->failover);
free_vqs:
cancel_delayed_work_sync(&vi->refill);
free_receive_page_frags(vi);
@@ -2950,6 +2984,8 @@ static void virtnet_remove(struct virtio_device *vdev)
unregister_netdev(vi->dev);
+ net_failover_destroy(vi->failover);
+
remove_vq_common(vi);
free_netdev(vi->dev);
--
2.14.3
^ permalink raw reply related
* [PATCH net-next 4/5] qede: Support flow classification to the VFs.
From: Manish Chopra @ 2018-05-24 16:54 UTC (permalink / raw)
To: davem; +Cc: netdev, ariel.elior, michal.kalderon
In-Reply-To: <20180524165453.11852-1-manish.chopra@cavium.com>
With the supported classification modes [4 tuples based,
udp port based, src-ip based], flows can be classified
to the VFs as well. With this patch, flows can be re-directed
to the requested VF provided in "action" field of command.
Please note that driver doesn't really care about the queue bits
in "action" field for the VFs. Since queue will be still chosen
by FW using RSS hash. [I.e., the classification would be done
according to vport-only]
For examples -
ethtool -N p5p1 flow-type udp4 dst-port 8000 action 0x100000000
ethtool -N p5p1 flow-type tcp4 src-ip 192.16.6.10 action 0x200000000
ethtool -U p5p1 flow-type tcp4 src-ip 192.168.40.100 dst-ip \
192.168.40.200 src-port 6660 dst-port 5550 \
action 0x100000000
Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
---
drivers/net/ethernet/qlogic/qede/qede_filter.c | 34 +++++++++++++++++++++++---
1 file changed, 30 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index 9b84f0c..6c02c21 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -86,6 +86,7 @@ struct qede_arfs_fltr_node {
u16 sw_id;
u16 rxq_id;
u16 next_rxq_id;
+ u8 vfid;
bool filter_op;
bool used;
u8 fw_rc;
@@ -125,14 +126,19 @@ static void qede_configure_arfs_fltr(struct qede_dev *edev,
params.qid = rxq_id;
params.b_is_add = add_fltr;
+ if (n->vfid) {
+ params.b_is_vf = true;
+ params.vf_id = n->vfid - 1;
+ }
+
if (n->tuple.stringify) {
char tuple_buffer[QEDE_FILTER_PRINT_MAX_LEN];
n->tuple.stringify(&n->tuple, tuple_buffer);
DP_VERBOSE(edev, NETIF_MSG_RX_STATUS,
- "%s sw_id[0x%x]: %s [queue %d]\n",
+ "%s sw_id[0x%x]: %s [vf %u queue %d]\n",
add_fltr ? "Adding" : "Deleting",
- n->sw_id, tuple_buffer, rxq_id);
+ n->sw_id, tuple_buffer, n->vfid, rxq_id);
}
n->used = true;
@@ -1435,6 +1441,10 @@ int qede_get_cls_rule_entry(struct qede_dev *edev, struct ethtool_rxnfc *cmd)
fsp->ring_cookie = fltr->rxq_id;
+ if (fltr->vfid) {
+ fsp->ring_cookie |= ((u64)fltr->vfid) <<
+ ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+ }
unlock:
__qede_unlock(edev);
return rc;
@@ -1806,6 +1816,9 @@ static int qede_flow_spec_validate(struct qede_dev *edev,
return -EINVAL;
}
+ if (ethtool_get_flow_spec_ring_vf(fs->ring_cookie))
+ return 0;
+
if (fs->ring_cookie >= QEDE_RSS_COUNT(edev)) {
DP_INFO(edev, "Queue out-of-bounds\n");
return -EINVAL;
@@ -1835,6 +1848,19 @@ static int qede_flow_spec_validate(struct qede_dev *edev,
return NULL;
}
+static void qede_flow_set_destination(struct qede_dev *edev,
+ struct qede_arfs_fltr_node *n,
+ struct ethtool_rx_flow_spec *fs)
+{
+ n->vfid = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+ n->rxq_id = ethtool_get_flow_spec_ring(fs->ring_cookie);
+ n->next_rxq_id = n->rxq_id;
+
+ if (n->vfid)
+ DP_VERBOSE(edev, QED_MSG_SP,
+ "Configuring N-tuple for VF 0x%02x\n", n->vfid - 1);
+}
+
int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
{
struct ethtool_rx_flow_spec *fsp = &info->fs;
@@ -1881,11 +1907,11 @@ int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
n->sw_id = fsp->location;
set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap);
n->buf_len = min_hlen;
- n->rxq_id = fsp->ring_cookie;
- n->next_rxq_id = n->rxq_id;
memcpy(&n->tuple, &t, sizeof(n->tuple));
+ qede_flow_set_destination(edev, n, fsp);
+
/* Build a minimal header according to the flow */
n->tuple.build_hdr(&n->tuple, n->data);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 5/5] qed*: Support drop action classification
From: Manish Chopra @ 2018-05-24 16:54 UTC (permalink / raw)
To: davem; +Cc: netdev, ariel.elior, michal.kalderon
In-Reply-To: <20180524165453.11852-1-manish.chopra@cavium.com>
With this patch, User can configure for the supported
flows to be dropped. Added a stat "gft_filter_drop"
as well to be populated in ethtool for the dropped flows.
For example -
ethtool -N p5p1 flow-type udp4 dst-port 8000 action -1
ethtool -N p5p1 flow-type tcp4 scr-ip 192.168.8.1 action -1
Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
---
drivers/net/ethernet/qlogic/qed/qed_l2.c | 35 ++++++++++++++-----------
drivers/net/ethernet/qlogic/qede/qede.h | 1 +
drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 1 +
drivers/net/ethernet/qlogic/qede/qede_filter.c | 14 ++++++++++
drivers/net/ethernet/qlogic/qede/qede_main.c | 1 +
include/linux/qed/qed_eth_if.h | 3 +++
include/linux/qed/qed_if.h | 1 +
7 files changed, 41 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 3cb8a80..1c0d0c2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -1677,6 +1677,8 @@ static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
HILO_64_REGPAIR(tstats.mftag_filter_discard);
p_stats->common.mac_filter_discards +=
HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
+ p_stats->common.gft_filter_drop +=
+ HILO_64_REGPAIR(tstats.eth_gft_drop_pkt);
}
static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn,
@@ -2015,16 +2017,6 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn,
u8 abs_vport_id = 0;
int rc = -EINVAL;
- rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id);
- if (rc)
- return rc;
-
- if (p_params->qid != QED_RFS_NTUPLE_QID_RSS) {
- rc = qed_fw_l2_queue(p_hwfn, p_params->qid, &abs_rx_q_id);
- if (rc)
- return rc;
- }
-
/* Get SPQ entry */
memset(&init_data, 0, sizeof(init_data));
init_data.cid = qed_spq_get_cid(p_hwfn);
@@ -2049,15 +2041,28 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn,
DMA_REGPAIR_LE(p_ramrod->pkt_hdr_addr, p_params->addr);
p_ramrod->pkt_hdr_length = cpu_to_le16(p_params->length);
- if (p_params->qid != QED_RFS_NTUPLE_QID_RSS) {
- p_ramrod->rx_qid_valid = 1;
- p_ramrod->rx_qid = cpu_to_le16(abs_rx_q_id);
+ if (p_params->b_is_drop) {
+ p_ramrod->vport_id = cpu_to_le16(ETH_GFT_TRASHCAN_VPORT);
+ } else {
+ rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id);
+ if (rc)
+ return rc;
+
+ if (p_params->qid != QED_RFS_NTUPLE_QID_RSS) {
+ rc = qed_fw_l2_queue(p_hwfn, p_params->qid,
+ &abs_rx_q_id);
+ if (rc)
+ return rc;
+
+ p_ramrod->rx_qid_valid = 1;
+ p_ramrod->rx_qid = cpu_to_le16(abs_rx_q_id);
+ }
+
+ p_ramrod->vport_id = cpu_to_le16((u16)abs_vport_id);
}
p_ramrod->flow_id_valid = 0;
p_ramrod->flow_id = 0;
-
- p_ramrod->vport_id = cpu_to_le16((u16)abs_vport_id);
p_ramrod->filter_action = p_params->b_is_add ? GFT_ADD_FILTER
: GFT_DELETE_FILTER;
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 2d3f09e..81c5c8df 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -75,6 +75,7 @@ struct qede_stats_common {
u64 rx_bcast_pkts;
u64 mftag_filter_discards;
u64 mac_filter_discards;
+ u64 gft_filter_drop;
u64 tx_ucast_bytes;
u64 tx_mcast_bytes;
u64 tx_bcast_bytes;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 8c6fdad..6906e04 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -161,6 +161,7 @@
QEDE_STAT(no_buff_discards),
QEDE_PF_STAT(mftag_filter_discards),
QEDE_PF_STAT(mac_filter_discards),
+ QEDE_PF_STAT(gft_filter_drop),
QEDE_STAT(tx_err_drop_pkts),
QEDE_STAT(ttl0_discard),
QEDE_STAT(packet_too_big_discard),
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index 6c02c21..e9e088d 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -90,6 +90,7 @@ struct qede_arfs_fltr_node {
bool filter_op;
bool used;
u8 fw_rc;
+ bool b_is_drop;
struct hlist_node node;
};
@@ -125,6 +126,7 @@ static void qede_configure_arfs_fltr(struct qede_dev *edev,
params.length = n->buf_len;
params.qid = rxq_id;
params.b_is_add = add_fltr;
+ params.b_is_drop = n->b_is_drop;
if (n->vfid) {
params.b_is_vf = true;
@@ -1445,6 +1447,9 @@ int qede_get_cls_rule_entry(struct qede_dev *edev, struct ethtool_rxnfc *cmd)
fsp->ring_cookie |= ((u64)fltr->vfid) <<
ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
}
+
+ if (fltr->b_is_drop)
+ fsp->ring_cookie = RX_CLS_FLOW_DISC;
unlock:
__qede_unlock(edev);
return rc;
@@ -1816,6 +1821,10 @@ static int qede_flow_spec_validate(struct qede_dev *edev,
return -EINVAL;
}
+ /* If drop requested then no need to validate other data */
+ if (fs->ring_cookie == RX_CLS_FLOW_DISC)
+ return 0;
+
if (ethtool_get_flow_spec_ring_vf(fs->ring_cookie))
return 0;
@@ -1852,6 +1861,11 @@ static void qede_flow_set_destination(struct qede_dev *edev,
struct qede_arfs_fltr_node *n,
struct ethtool_rx_flow_spec *fs)
{
+ if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
+ n->b_is_drop = true;
+ return;
+ }
+
n->vfid = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
n->rxq_id = ethtool_get_flow_spec_ring(fs->ring_cookie);
n->next_rxq_id = n->rxq_id;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 9e70f71..d118771 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -347,6 +347,7 @@ void qede_fill_by_demand_stats(struct qede_dev *edev)
p_common->rx_bcast_pkts = stats.common.rx_bcast_pkts;
p_common->mftag_filter_discards = stats.common.mftag_filter_discards;
p_common->mac_filter_discards = stats.common.mac_filter_discards;
+ p_common->gft_filter_drop = stats.common.gft_filter_drop;
p_common->tx_ucast_bytes = stats.common.tx_ucast_bytes;
p_common->tx_mcast_bytes = stats.common.tx_mcast_bytes;
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 557e86e1..2978fa4 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -89,6 +89,9 @@ struct qed_ntuple_filter_params {
/* true iff this filter is to be added. Else to be removed */
bool b_is_add;
+
+ /* If flow needs to be dropped */
+ bool b_is_drop;
};
struct qed_dev_eth_info {
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 44af652..ac991a3 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1129,6 +1129,7 @@ struct qed_eth_stats_common {
u64 rx_bcast_pkts;
u64 mftag_filter_discards;
u64 mac_filter_discards;
+ u64 gft_filter_drop;
u64 tx_ucast_bytes;
u64 tx_mcast_bytes;
u64 tx_bcast_bytes;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v3 net] stmmac: Added support for 802.1ad S-TAG stripping
From: Elad Nachman @ 2018-05-24 16:56 UTC (permalink / raw)
To: Jose Abreu, Florian Fainelli, David Miller
Cc: makita.toshiaki, netdev, peppe.cavallaro, alexandre.torgue,
eladv6
In-Reply-To: <252246d7-04b9-36f7-a3c2-fcc525e4640f@synopsys.com>
stmmac reception handler calls stmmac_rx_vlan() to strip the vlan before calling napi_gro_receive().
The function assumes VLAN tagged frames are always tagged with 802.1Q protocol,
and assigns ETH_P_8021Q to the skb by hard-coding the parameter on call to __vlan_hwaccel_put_tag() .
This causes packets not to be passed to the VLAN slave if it was created with 802.1AD protocol
(ip link add link eth0 eth0.100 type vlan proto 802.1ad id 100).
This fix passes the protocol from the VLAN header into __vlan_hwaccel_put_tag()
instead of using the hard-coded value of ETH_P_8021Q.
NETIF_F_HW_VLAN_STAG_RX was added to the net device features to reflect this new support.
Signed-off-by: Elad Nachman <eladn@gilat.com>
---
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b65e2d1..2d2f37f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3293,17 +3293,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb)
{
- struct ethhdr *ehdr;
+ struct vlan_ethhdr *veth;
u16 vlanid;
+ __be16 vlan_proto;
- if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) ==
- NETIF_F_HW_VLAN_CTAG_RX &&
+ if ((dev->features & (NETIF_F_HW_VLAN_CTAG_RX|NETIF_F_HW_VLAN_STAG_RX)) ==
+ (NETIF_F_HW_VLAN_CTAG_RX|NETIF_F_HW_VLAN_STAG_RX) &&
!__vlan_get_tag(skb, &vlanid)) {
/* pop the vlan tag */
- ehdr = (struct ethhdr *)skb->data;
- memmove(skb->data + VLAN_HLEN, ehdr, ETH_ALEN * 2);
+ veth = (struct vlan_ethhdr *)skb->data;
+ vlan_proto = veth->h_vlan_proto;
+ memmove(skb->data + VLAN_HLEN, veth, ETH_ALEN * 2);
skb_pull(skb, VLAN_HLEN);
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlanid);
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vlanid);
}
}
@@ -4344,7 +4346,7 @@ int stmmac_dvr_probe(struct device *device,
ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
#ifdef STMMAC_VLAN_TAG_USED
/* Both mac100 and gmac support receive VLAN tag detection */
- ndev->features |= NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->features |= (NETIF_F_HW_VLAN_CTAG_RX|NETIF_F_HW_VLAN_STAG_RX);
#endif
priv->msg_enable = netif_msg_init(debug, default_msg_level);
--
2.7.4
^ permalink raw reply related
* Re: [PATCH 1/6] ravb: remove custom .nway_reset from ethtool ops
From: Sergei Shtylyov @ 2018-05-24 17:01 UTC (permalink / raw)
To: Andrew Lunn
Cc: Vladimir Zapolskiy, Vladimir Zapolskiy, David S. Miller, netdev,
linux-renesas-soc
In-Reply-To: <20180524164422.GI5128@lunn.ch>
On 05/24/2018 07:44 PM, Andrew Lunn wrote:
>>>>> The change fixes a sleep in atomic context issue, which can be
>>>>> always triggered by running 'ethtool -r' command, because
>>>>> phy_start_aneg() protects phydev fields by a mutex.
>>
>> You don't say that *not* grabbing the spinlock is safe...
>
> For it to be unsafe, i think that would mean phylib would need to call
> back into the MAC driver? The only way that could happen is via the
> adjust_link call. And that will deadlock, since it takes the same
> lock.
>
> Or am i/we missing something?
It doesn't take any locks currently, only patches #3/#6 makes it do so...
> Andrew
MBR, Sergei
^ permalink raw reply
* Re: [PATCH net] packet: in packet_snd start writing at link layer allocation
From: Willem de Bruijn @ 2018-05-24 17:01 UTC (permalink / raw)
To: Tariq Toukan
Cc: David Miller, Network Development, Eric Dumazet, Willem de Bruijn,
Maor Gottlieb
In-Reply-To: <CAF=yD-+DV3Z0+++=gUzSWy1ogsNXOjwKP9-H9XqGjuNJJ03SoQ@mail.gmail.com>
On Thu, May 24, 2018 at 11:17 AM, Willem de Bruijn
<willemdebruijn.kernel@gmail.com> wrote:
> On Thu, May 24, 2018 at 11:07 AM, Tariq Toukan <tariqt@mellanox.com> wrote:
>>
>>
>> On 14/05/2018 3:20 AM, David Miller wrote:
>>>
>>> From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
>>> Date: Fri, 11 May 2018 13:24:25 -0400
>>>
>>>> From: Willem de Bruijn <willemb@google.com>
>>>>
>>>> Packet sockets allow construction of packets shorter than
>>>> dev->hard_header_len to accommodate protocols with variable length
>>>> link layer headers. These packets are padded to dev->hard_header_len,
>>>> because some device drivers interpret that as a minimum packet size.
>>>>
>>>> packet_snd reserves dev->hard_header_len bytes on allocation.
>>>> SOCK_DGRAM sockets call skb_push in dev_hard_header() to ensure that
>>>> link layer headers are stored in the reserved range. SOCK_RAW sockets
>>>> do the same in tpacket_snd, but not in packet_snd.
>>>>
>>>> Syzbot was able to send a zero byte packet to a device with massive
>>>> 116B link layer header, causing padding to cross over into skb_shinfo.
>>>> Fix this by writing from the start of the llheader reserved range also
>>>> in the case of packet_snd/SOCK_RAW.
>>>>
>>>> Update skb_set_network_header to the new offset. This also corrects
>>>> it for SOCK_DGRAM, where it incorrectly double counted reserve due to
>>>> the skb_push in dev_hard_header.
>>>>
>>>> Fixes: 9ed988cd5915 ("packet: validate variable length ll headers")
>>>> Reported-by: syzbot+71d74a5406d02057d559@syzkaller.appspotmail.com
>>>> Signed-off-by: Willem de Bruijn <willemb@google.com>
>>>
>>>
>>> Applied and queued up for -stable, thanks Willem.
>>>
>>
>> Hi,
>>
>> One of our regression tests started failing. Once this patch is reverted,
>> test passes.
>>
>> The tests add flow steering rules in the receiver side and in the sender
>> side it send the packet with some RAW socket applications. Then received
>> side gets completion with error.
>>
>> Our verification team compared the packets between the stable and the broken
>> version, in the broken version we have some extra bytes at the end of the
>> packet.
>>
>> It looks like some bad push to the SKB, maybe the conditional reserved
>> addition should be more strict?
>>
>> Any idea?
>
> Thanks for reporting, sorry for the breakage.
>
> I think I might. This skb_push moves back the start of skb->data in the
> same way that tpacket_snd does. But it does not reduce the length
> passed to skb_put, so this might double count hard_header_len.
>
> Let me construct a test.
Indeed.
Still verifying, but this almost certainly has to be
@@ -2911,7 +2912,7 @@ static int packet_snd(struct socket *sock,
struct msghdr *msg, size_t len)
if (unlikely(offset < 0))
goto out_free;
} else if (reserve) {
- skb_push(skb, reserve);
+ skb_reserve(skb, -reserve);
}
to move the start of the packet without changing its length.
^ permalink raw reply
* Re: [PATCH net-next 0/8] nfp: offload LAG for tc flower egress
From: Or Gerlitz @ 2018-05-24 17:04 UTC (permalink / raw)
To: Jakub Kicinski
Cc: David Miller, Linux Netdev List, oss-drivers, Jiri Pirko,
Jay Vosburgh, Veaceslav Falico, Andy Gospodarek
In-Reply-To: <20180524022255.18548-1-jakub.kicinski@netronome.com>
On Thu, May 24, 2018 at 5:22 AM, Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
> Hi!
>
> This series from John adds bond offload to the nfp driver. Patch 5
> exposes the hash type for NETDEV_LAG_TX_TYPE_HASH to make sure nfp
> hashing matches that of the software LAG. This may be unnecessarily
> conservative, let's see what LAG maintainers think :)
>
> John says:
>
> This patchset sets up the infrastructure and offloads output actions for
> when a TC flower rule attempts to egress a packet to a LAG port.
>
> Firstly it adds some of the infrastructure required to the flower app and
> to the nfp core. This includes the ability to change the MAC address of a
> repr, a function for combining lookup and write to a FW symbol, and the
> addition of private data to a repr on a per app basis.
>
> Patch 6 continues by implementing notifiers that track Linux bonds and
> communicates to the FW those which enslave reprs, along with the current
> state of reprs within the bond.
>
> Patch 7 ensures bonds are synchronised with FW by receiving and acting
> upon cmsgs sent to the kernel. These may request that a bond message is
> retransmitted when FW can process it, or may request a full sync of the
> bonds defined in the kernel.
>
> Patch 8 offloads a flower action when that action requires egressing to a
> pre-defined Linux bond.
Does this apply also to non-uplink representors? if yes, what is the use case?
We are looking on supporting uplink lag in sriov switchdev scheme - we refer to
it as "vf lag" -- b/c the netdev and rdma devices seen by the VF are actually
subject to HA and/or LAG - I wasn't sure if/how you limit this series
to uplink reprs
^ permalink raw reply
* Re: [PATCH net-next 8/8] nfp: flower: compute link aggregation action
From: Or Gerlitz @ 2018-05-24 17:09 UTC (permalink / raw)
To: Jakub Kicinski; +Cc: David Miller, Linux Netdev List, oss-drivers, John Hurley
In-Reply-To: <20180524022255.18548-9-jakub.kicinski@netronome.com>
On Thu, May 24, 2018 at 5:22 AM, Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
> From: John Hurley <john.hurley@netronome.com>
>
> If the egress device of an offloaded rule is a LAG port, then encode the
> output port to the NFP with a LAG identifier and the offloaded group ID.
>
> A prelag action is also offloaded which must be the first action of the
> series (although may appear after other pre-actions - e.g. tunnels). This
> causes the FW to check that it has the necessary information to output to
> the requested LAG port. If it does not, the packet is sent to the kernel
> before any other actions are applied to it.
Offload decision typically also looks if both devices have the same
switchdev ID.
In your case, do both reprs gets the same switchdev ID automatically when being
put into the same team/bond instance? I wasn't sure to see here
changes for that matter
^ permalink raw reply
* Re: [PATCH net-next 0/7] net: bridge: Notify about bridge VLANs
From: Florian Fainelli @ 2018-05-24 17:20 UTC (permalink / raw)
To: Petr Machata, netdev, devel, bridge
Cc: andrew, nikolay, gregkh, vivien.didelot, idosch, jiri,
razvan.stefanescu, davem
In-Reply-To: <cover.1527173527.git.petrm@mellanox.com>
Hi Petr,
On 05/24/2018 08:09 AM, Petr Machata wrote:
> In commit 946a11e7408e ("mlxsw: spectrum_span: Allow bridge for gretap
> mirror"), mlxsw got support for offloading mirror-to-gretap such that
> the underlay packet path involves a bridge. In that case, the offload is
> also influenced by PVID setting of said bridge. However, changes to VLAN
> configuration of the bridge itself do not generate switchdev
> notifications, so there's no mechanism to prod mlxsw to update the
> offload when these settings change.
>
> In this patchset, the problem is resolved by distributing the switchdev
> notification SWITCHDEV_OBJ_ID_PORT_VLAN also for configuration changes
> on bridge VLANs. Since stacked devices distribute the notification to
> lower devices, such event eventually reaches the driver, which can
> determine whether it's a bridge or port VLAN by inspecting orig_dev.
>
> To keep things consistent, the newly-distributed notifications observe
> the same protocol as the existing ones: dual prepare/commit, with
> -EOPNOTSUPP indicating lack of support, even though there's currently
> nothing to prepare for and nothing to support. Correspondingly, all
> switchdev drivers have been updated to return -EOPNOTSUPP for bridge
> VLAN notifications.
You seem to have approached the bridge changes a little differently from
this series:
https://lists.linux-foundation.org/pipermail/bridge/2016-November/010112.html
Both have the same intent that by targeting the bridge device itself,
you can propagate that through switchdev to the switch drivers, and in
turn create configurations where for instance, you have:
- CPU/management port present in specific VLANs that is a subset or
superset of the VLANs configured on front-panel ports
- CPU/management port tagged/untagged in specific VLANs which can be a
different setting from the front-panel ports
One problem we have in DSA at the moment is that we always add the CPU
port to the VLANs configured to the front-panel port but we do this with
the same attributes as the front panel ports! For instance, if you add
Port 0 to VLAN1 untagged, the the CPU port also gets added to that
VLAN1, also untagged. As long as there is just one VLAN untagged, this
is not much of a problem. Now do this with another VLAN or another port,
and the CPU can no longer differentiate the traffic from which VLAN it
is coming from, no bueno.
I had specifically changed b53 to always add the CPU port as tagged,
because that would always allow for differentiating traffic, but I would
rather have the capability to configure that at the bridge layer, which
you series seem to allow.
For the record, here is what the first commit in the series intended to
let an user do:
The following happens now (assuming bridge master device is already
created):
bridge vlan add vid 2 dev port0 pvid untagged
-> port0 (e.g: switch port 0) gets programmed
-> CPU port gets programmed
bridge vlan add vid 2 dev br0 self
-> CPU port gets programmed
bridge vlan add vid 2 dev port0
-> port0 (switch port 0) gets programmed
Are these use cases possible with your series? It seems to me like it is
if we drop the netif_is_bridge_master() checks and resolve orig_dev as
being a hint for the CPU/management port.
Thanks for reading me :)
>
> In patch #1, the code to send notifications for adding and deleting is
> factored out into two named functions.
>
> In patches #2-#5, respectively for mlxsw, rocker, DSA and DPAA2 ethsw,
> the new notifications (which are not enabled yet) are ignored to
> maintain the current behavior.
>
> In patch #6, the notification is actually enabled.
>
> In patch #7, mlxsw is changed to update offloads of mirror-to-gre also
> for bridge-related notifications.
>
> Petr Machata (7):
> net: bridge: Extract boilerplate around switchdev_port_obj_*()
> mlxsw: spectrum_switchdev: Ignore bridge VLAN events
> rocker: rocker_main: Ignore bridge VLAN events
> dsa: port: Ignore bridge VLAN events
> staging: fsl-dpaa2: ethsw: Ignore bridge VLAN events
> net: bridge: Notify about bridge VLANs
> mlxsw: spectrum_switchdev: Schedule respin during trans prepare
>
> .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 8 ++-
> drivers/net/ethernet/rocker/rocker_main.c | 6 +++
> drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 6 +++
> net/bridge/br_vlan.c | 58 ++++++++++++++--------
> net/dsa/port.c | 6 +++
> 5 files changed, 62 insertions(+), 22 deletions(-)
>
--
Florian
^ permalink raw reply
* Re: [net-next 1/6] net/dcb: Add dcbnl buffer attribute
From: Ido Schimmel @ 2018-05-24 17:13 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Huy Nguyen, Saeed Mahameed, David S. Miller, netdev, Jiri Pirko,
Or Gerlitz, Parav Pandit, Ido Schimmel
In-Reply-To: <20180523022314.783e47fa@cakuba>
Hi Jakub,
On Wed, May 23, 2018 at 02:23:14AM -0700, Jakub Kicinski wrote:
> Are you referring to XOFF/XON thresholds? I don't think the "threshold
> type" in devlink API implies we are setting XON/XOFF thresholds
> directly :S If PFC is enabled we may be setting them indirectly,
> obviously.
>
> My understanding is that for static threshold type the size parameter
> specifies the max amount of memory given pool can consume.
Correct.
> Yes, we must have a different definitions of "shared buffer" :) That
> link, however, didn't clarify much for me... In mlx5 you seem to have a
> buffer which is shared between priorities, even if it's not what would
> be referred to as shared buffer in switch context.
The following link is my attempt at explaining the above concepts:
https://github.com/Mellanox/mlxsw/wiki/Quality-of-Service
Please let me know if something is not clear.
Basically, we use devlink-sb and dcbl to configure two different
buffers:
* devlink-sb is used to configure the switch's shared buffer which is
shared between all the ports and thus can't take a netdev as an handle
* dcbnl is used to configure per-port buffers (also called headroom
buffers) where received packets are stored while going through the
switch's pipeline before being admitted to the shared buffer and
awaiting transmission
Note that in Huy's case the buffers are of the second type (per-port)
and thus using dcbnl instead of devlink-sb makes sense.
> DCBNL seems to carry standard-based information, which this is not.
> mlxsw supports DCBNL, will it also support this buffer configuration
> mechanism?
I believe so, it's just a matter of doing the work. The hardware
supports this and the interface is identical to the NIC (same
registers).
> > > How does one query the total size of the buffer to be carved?
> > [HQN] This is not necessary. If the total size is too big, error will
> > be return via DCB netlink interface.
>
> Right, I'm not saying it's a bug :) It's just nice when user can be
> told the total size without having to probe for it :)
+1
^ permalink raw reply
* Re: [PATCH 1/6] ravb: remove custom .nway_reset from ethtool ops
From: Andrew Lunn @ 2018-05-24 17:23 UTC (permalink / raw)
To: Sergei Shtylyov
Cc: Vladimir Zapolskiy, Vladimir Zapolskiy, David S. Miller, netdev,
linux-renesas-soc
In-Reply-To: <f6e0b8c5-7fb9-babe-0114-350e7d6b2186@cogentembedded.com>
> > For it to be unsafe, i think that would mean phylib would need to call
> > back into the MAC driver? The only way that could happen is via the
> > adjust_link call. And that will deadlock, since it takes the same
> > lock.
> >
> > Or am i/we missing something?
>
> It doesn't take any locks currently, only patches #3/#6 makes it do so...
Ah, yes.
You should not be holding any spinlocks when calling into phylib.
It does its own locking, which is mutex based.
The code in this patch is not touching the MAC, so looks safe to me.
Andrew
^ permalink raw reply
* Re: [PATCH 0/6] ravb/sh_eth: fix sleep in atomic by reusing shared ethtool handlers
From: Sergei Shtylyov @ 2018-05-24 17:24 UTC (permalink / raw)
To: Vladimir Zapolskiy, David S. Miller; +Cc: netdev, linux-renesas-soc
In-Reply-To: <6ffa0c08-2210-379c-50f0-d5bf43ab569e@cogentembedded.com>
On 05/24/2018 07:40 PM, Sergei Shtylyov wrote:
>> For ages trivial changes to RAVB and SuperH ethernet links by means of
>> standard 'ethtool' trigger a 'sleeping function called from invalid
>> context' bug, to visualize it on r8a7795 ULCB:
>>
>> % ethtool -r eth0
>> BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747
>> in_atomic(): 1, irqs_disabled(): 128, pid: 554, name: ethtool
>> INFO: lockdep is turned off.
>> irq event stamp: 0
>> hardirqs last enabled at (0): [<0000000000000000>] (null)
>> hardirqs last disabled at (0): [<ffff0000080e1d3c>] copy_process.isra.7.part.8+0x2cc/0x1918
>> softirqs last enabled at (0): [<ffff0000080e1d3c>] copy_process.isra.7.part.8+0x2cc/0x1918
>> softirqs last disabled at (0): [<0000000000000000>] (null)
>> CPU: 5 PID: 554 Comm: ethtool Not tainted 4.17.0-rc4-arm64-renesas+ #33
>> Hardware name: Renesas H3ULCB board based on r8a7795 ES2.0+ (DT)
>> Call trace:
>> dump_backtrace+0x0/0x198
>> show_stack+0x24/0x30
>> dump_stack+0xb8/0xf4
>> ___might_sleep+0x1c8/0x1f8
>> __might_sleep+0x58/0x90
>> __mutex_lock+0x50/0x890
>> mutex_lock_nested+0x3c/0x50
>> phy_start_aneg_priv+0x38/0x180
>> phy_start_aneg+0x24/0x30
>> ravb_nway_reset+0x3c/0x68
>> dev_ethtool+0x3dc/0x2338
>> dev_ioctl+0x19c/0x490
>> sock_do_ioctl+0xe0/0x238
>> sock_ioctl+0x254/0x460
>> do_vfs_ioctl+0xb0/0x918
>> ksys_ioctl+0x50/0x80
>> sys_ioctl+0x34/0x48
>> __sys_trace_return+0x0/0x4
>>
>> The root cause is that an attempt to modify ECMR and GECMR registers
>> only when RX/TX function is disabled was too overcomplicated in its
>> original implementation, also processing of an optional Link Change
>> interrupt added even more complexity, as a result the implementation
>> was error prone.
>>
>> The new locking scheme is confirmed to be correct by dumping driver
>> specific and generic PHY framework function calls with aid of ftrace
>> while running more or less advanced tests.
>>
>> Please note that sh_eth patches from the series were built-tested only.
>>
>> On purpose I do not add Fixes tags, the reused PHY handlers were added
>> way later than the fixed problems were firstly found in the drivers.
>
> I think you went one step too far with these fixes. On the first glance,
> the real fixes are to remove grabbing/releasing the spinlock for the duration
> of the phylib calls. Am I right? If so, making use of the new phylib APIs
> would be a further enhancement, it's not needed for fixing the splats per se...
Note that I hadn't looked at the patches #3/#6 at the time of writing this;
those seem to be more complicated than the rest.
MBR, Sergei
^ permalink raw reply
* Re: [PATCH net-next 8/8] nfp: flower: compute link aggregation action
From: John Hurley @ 2018-05-24 17:36 UTC (permalink / raw)
To: Or Gerlitz; +Cc: Jakub Kicinski, David Miller, Linux Netdev List, oss-drivers
In-Reply-To: <CAJ3xEMiNn+k8b0ixYgL2M6X=7WLMM=i1gEoLcdEYkztjsphi=g@mail.gmail.com>
On Thu, May 24, 2018 at 6:09 PM, Or Gerlitz <gerlitz.or@gmail.com> wrote:
> On Thu, May 24, 2018 at 5:22 AM, Jakub Kicinski
> <jakub.kicinski@netronome.com> wrote:
>> From: John Hurley <john.hurley@netronome.com>
>>
>> If the egress device of an offloaded rule is a LAG port, then encode the
>> output port to the NFP with a LAG identifier and the offloaded group ID.
>>
>> A prelag action is also offloaded which must be the first action of the
>> series (although may appear after other pre-actions - e.g. tunnels). This
>> causes the FW to check that it has the necessary information to output to
>> the requested LAG port. If it does not, the packet is sent to the kernel
>> before any other actions are applied to it.
>
> Offload decision typically also looks if both devices have the same
> switchdev ID.
>
> In your case, do both reprs gets the same switchdev ID automatically when being
> put into the same team/bond instance? I wasn't sure to see here
> changes for that matter
Hi Or,
Yes, you are correct.
We essentially substituted the switchdev ID check for a repr app check.
So an app runs per card and spawns the reprs for that card - each repr
has a backpointer to its creating app.
When deciding if we can offload a bond, we ensure that all bond ports
are reprs and belong to the same app and so same card/switchdev_id.
^ permalink raw reply
* Re: [PATCH net-next] tcp: use data length instead of skb->len in tcp_probe
From: Song Liu @ 2018-05-24 17:44 UTC (permalink / raw)
To: Yafang Shao
Cc: davem@davemloft.net, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <1527166097-10908-1-git-send-email-laoar.shao@gmail.com>
> On May 24, 2018, at 5:48 AM, Yafang Shao <laoar.shao@gmail.com> wrote:
>
> skb->len is meaningless to user.
> data length could be more helpful, with which we can easily filter out
> the packet without payload.
>
> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> ---
> include/trace/events/tcp.h | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
> index c1a5284..259b991 100644
> --- a/include/trace/events/tcp.h
> +++ b/include/trace/events/tcp.h
> @@ -261,7 +261,7 @@
> __entry->dport = ntohs(inet->inet_dport);
> __entry->mark = skb->mark;
>
> - __entry->length = skb->len;
> + __entry->length = skb->len - tcp_hdrlen(skb);
We should also rename __entry->length to __entry->data_len, so that whoever
using this field will notice the change.
Thanks,
Song
> __entry->snd_nxt = tp->snd_nxt;
> __entry->snd_una = tp->snd_una;
> __entry->snd_cwnd = tp->snd_cwnd;
> @@ -272,7 +272,7 @@
> __entry->sock_cookie = sock_gen_cookie(sk);
> ),
>
> - TP_printk("src=%pISpc dest=%pISpc mark=%#x length=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx",
> + TP_printk("src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx",
> __entry->saddr, __entry->daddr, __entry->mark,
> __entry->length, __entry->snd_nxt, __entry->snd_una,
> __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd,
> --
> 1.8.3.1
>
^ permalink raw reply
* Re: [PATCH bpf-next v3 01/15] net: initial AF_XDP skeleton
From: Alexei Starovoitov @ 2018-05-24 17:57 UTC (permalink / raw)
To: Stephen Hemminger
Cc: Björn Töpel, magnus.karlsson, alexander.h.duyck,
alexander.duyck, john.fastabend, ast, brouer,
willemdebruijn.kernel, daniel, mst, netdev, Björn Töpel,
michael.lundkvist, jesse.brandeburg, anjali.singhai, qi.z.zhang
In-Reply-To: <20180523155047.6c136279@xeon-e3>
On Wed, May 23, 2018 at 03:50:47PM -0700, Stephen Hemminger wrote:
> Most distributions will want it to be a module so that it is not loaded
> unless used, and AF_XDP could be also be disabled by blacklisting the module.
I think the opposite will be the case. Anyone who cares about performance
would want AF_XDP code to be builtin, since builtin vs module gives additional
performance. All our NIC drivers are builtin, since we see noticeable
perf gains on production workloads.
Hence I'd rather see us spending time on improving AF_XDP instead
of making it a module and forever struggling with maintaining it as a module.
More so I think it's time to get rid of IPV6=m for good. The kernel
is full of ugly hacks and performance degradation due to indirect calls
just because IPV6=m is still supported.
Folks that care about vmlinux size should be using kconfig to compile it out.
^ permalink raw reply
* [PATCH bpf-next v5 1/7] perf/core: add perf_get_event() to return perf_event given a struct file
From: Yonghong Song @ 2018-05-24 18:21 UTC (permalink / raw)
To: peterz, ast, daniel, netdev; +Cc: kernel-team
In-Reply-To: <20180524182111.454612-1-yhs@fb.com>
A new extern function, perf_get_event(), is added to return a perf event
given a struct file. This function will be used in later patches.
Signed-off-by: Yonghong Song <yhs@fb.com>
---
include/linux/perf_event.h | 5 +++++
kernel/events/core.c | 8 ++++++++
2 files changed, 13 insertions(+)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e71e99e..eec302b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -868,6 +868,7 @@ extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
extern struct file *perf_event_get(unsigned int fd);
+extern const struct perf_event *perf_get_event(struct file *file);
extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
@@ -1289,6 +1290,10 @@ static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
+static inline const struct perf_event *perf_get_event(struct file *file)
+{
+ return ERR_PTR(-EINVAL);
+}
static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
{
return ERR_PTR(-EINVAL);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 67612ce..6eeab86 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11212,6 +11212,14 @@ struct file *perf_event_get(unsigned int fd)
return file;
}
+const struct perf_event *perf_get_event(struct file *file)
+{
+ if (file->f_op != &perf_fops)
+ return ERR_PTR(-EINVAL);
+
+ return file->private_data;
+}
+
const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
{
if (!event)
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v5 2/7] bpf: introduce bpf subcommand BPF_TASK_FD_QUERY
From: Yonghong Song @ 2018-05-24 18:21 UTC (permalink / raw)
To: peterz, ast, daniel, netdev; +Cc: kernel-team
In-Reply-To: <20180524182111.454612-1-yhs@fb.com>
Currently, suppose a userspace application has loaded a bpf program
and attached it to a tracepoint/kprobe/uprobe, and a bpf
introspection tool, e.g., bpftool, wants to show which bpf program
is attached to which tracepoint/kprobe/uprobe. Such attachment
information will be really useful to understand the overall bpf
deployment in the system.
There is a name field (16 bytes) for each program, which could
be used to encode the attachment point. There are some drawbacks
for this approaches. First, bpftool user (e.g., an admin) may not
really understand the association between the name and the
attachment point. Second, if one program is attached to multiple
places, encoding a proper name which can imply all these
attachments becomes difficult.
This patch introduces a new bpf subcommand BPF_TASK_FD_QUERY.
Given a pid and fd, if the <pid, fd> is associated with a
tracepoint/kprobe/uprobe perf event, BPF_TASK_FD_QUERY will return
. prog_id
. tracepoint name, or
. k[ret]probe funcname + offset or kernel addr, or
. u[ret]probe filename + offset
to the userspace.
The user can use "bpftool prog" to find more information about
bpf program itself with prog_id.
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
---
include/linux/trace_events.h | 17 ++++++
include/uapi/linux/bpf.h | 26 +++++++++
kernel/bpf/syscall.c | 131 +++++++++++++++++++++++++++++++++++++++++++
kernel/trace/bpf_trace.c | 48 ++++++++++++++++
kernel/trace/trace_kprobe.c | 29 ++++++++++
kernel/trace/trace_uprobe.c | 22 ++++++++
6 files changed, 273 insertions(+)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2bde3ef..d34144a 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -473,6 +473,9 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info);
int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
+int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
+ u32 *fd_type, const char **buf,
+ u64 *probe_offset, u64 *probe_addr);
#else
static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
@@ -504,6 +507,13 @@ static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name
{
return NULL;
}
+static inline int bpf_get_perf_event_info(const struct perf_event *event,
+ u32 *prog_id, u32 *fd_type,
+ const char **buf, u64 *probe_offset,
+ u64 *probe_addr)
+{
+ return -EOPNOTSUPP;
+}
#endif
enum {
@@ -560,10 +570,17 @@ extern void perf_trace_del(struct perf_event *event, int flags);
#ifdef CONFIG_KPROBE_EVENTS
extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe);
extern void perf_kprobe_destroy(struct perf_event *event);
+extern int bpf_get_kprobe_info(const struct perf_event *event,
+ u32 *fd_type, const char **symbol,
+ u64 *probe_offset, u64 *probe_addr,
+ bool perf_type_tracepoint);
#endif
#ifdef CONFIG_UPROBE_EVENTS
extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe);
extern void perf_uprobe_destroy(struct perf_event *event);
+extern int bpf_get_uprobe_info(const struct perf_event *event,
+ u32 *fd_type, const char **filename,
+ u64 *probe_offset, bool perf_type_tracepoint);
#endif
extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
char *filter_str);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e95fec9..9b8c6e3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -97,6 +97,7 @@ enum bpf_cmd {
BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
BPF_BTF_GET_FD_BY_ID,
+ BPF_TASK_FD_QUERY,
};
enum bpf_map_type {
@@ -380,6 +381,22 @@ union bpf_attr {
__u32 btf_log_size;
__u32 btf_log_level;
};
+
+ struct {
+ __u32 pid; /* input: pid */
+ __u32 fd; /* input: fd */
+ __u32 flags; /* input: flags */
+ __u32 buf_len; /* input/output: buf len */
+ __aligned_u64 buf; /* input/output:
+ * tp_name for tracepoint
+ * symbol for kprobe
+ * filename for uprobe
+ */
+ __u32 prog_id; /* output: prod_id */
+ __u32 fd_type; /* output: BPF_FD_TYPE_* */
+ __u64 probe_offset; /* output: probe_offset */
+ __u64 probe_addr; /* output: probe_addr */
+ } task_fd_query;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -2557,4 +2574,13 @@ struct bpf_fib_lookup {
__u8 dmac[6]; /* ETH_ALEN */
};
+enum bpf_task_fd_type {
+ BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_UPROBE, /* filename + offset */
+ BPF_FD_TYPE_URETPROBE, /* filename + offset */
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 788456c..388d4fe 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -18,7 +18,9 @@
#include <linux/vmalloc.h>
#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
+#include <linux/fdtable.h>
#include <linux/file.h>
+#include <linux/fs.h>
#include <linux/license.h>
#include <linux/filter.h>
#include <linux/version.h>
@@ -2178,6 +2180,132 @@ static int bpf_btf_get_fd_by_id(const union bpf_attr *attr)
return btf_get_fd_by_id(attr->btf_id);
}
+static int bpf_task_fd_query_copy(const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ u32 prog_id, u32 fd_type,
+ const char *buf, u64 probe_offset,
+ u64 probe_addr)
+{
+ char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf);
+ u32 len = buf ? strlen(buf) : 0, input_len;
+ int err = 0;
+
+ if (put_user(len, &uattr->task_fd_query.buf_len))
+ return -EFAULT;
+ input_len = attr->task_fd_query.buf_len;
+ if (input_len && ubuf) {
+ if (!len) {
+ /* nothing to copy, just make ubuf NULL terminated */
+ char zero = '\0';
+
+ if (put_user(zero, ubuf))
+ return -EFAULT;
+ } else if (input_len >= len + 1) {
+ /* ubuf can hold the string with NULL terminator */
+ if (copy_to_user(ubuf, buf, len + 1))
+ return -EFAULT;
+ } else {
+ /* ubuf cannot hold the string with NULL terminator,
+ * do a partial copy with NULL terminator.
+ */
+ char zero = '\0';
+
+ err = -ENOSPC;
+ if (copy_to_user(ubuf, buf, input_len - 1))
+ return -EFAULT;
+ if (put_user(zero, ubuf + input_len - 1))
+ return -EFAULT;
+ }
+ }
+
+ if (put_user(prog_id, &uattr->task_fd_query.prog_id) ||
+ put_user(fd_type, &uattr->task_fd_query.fd_type) ||
+ put_user(probe_offset, &uattr->task_fd_query.probe_offset) ||
+ put_user(probe_addr, &uattr->task_fd_query.probe_addr))
+ return -EFAULT;
+
+ return err;
+}
+
+#define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr
+
+static int bpf_task_fd_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ pid_t pid = attr->task_fd_query.pid;
+ u32 fd = attr->task_fd_query.fd;
+ const struct perf_event *event;
+ struct files_struct *files;
+ struct task_struct *task;
+ struct file *file;
+ int err;
+
+ if (CHECK_ATTR(BPF_TASK_FD_QUERY))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (attr->task_fd_query.flags != 0)
+ return -EINVAL;
+
+ task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+ if (!task)
+ return -ENOENT;
+
+ files = get_files_struct(task);
+ put_task_struct(task);
+ if (!files)
+ return -ENOENT;
+
+ err = 0;
+ spin_lock(&files->file_lock);
+ file = fcheck_files(files, fd);
+ if (!file)
+ err = -EBADF;
+ else
+ get_file(file);
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+
+ if (err)
+ goto out;
+
+ if (file->f_op == &bpf_raw_tp_fops) {
+ struct bpf_raw_tracepoint *raw_tp = file->private_data;
+ struct bpf_raw_event_map *btp = raw_tp->btp;
+
+ err = bpf_task_fd_query_copy(attr, uattr,
+ raw_tp->prog->aux->id,
+ BPF_FD_TYPE_RAW_TRACEPOINT,
+ btp->tp->name, 0, 0);
+ goto put_file;
+ }
+
+ event = perf_get_event(file);
+ if (!IS_ERR(event)) {
+ u64 probe_offset, probe_addr;
+ u32 prog_id, fd_type;
+ const char *buf;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
+ &buf, &probe_offset,
+ &probe_addr);
+ if (!err)
+ err = bpf_task_fd_query_copy(attr, uattr, prog_id,
+ fd_type, buf,
+ probe_offset,
+ probe_addr);
+ goto put_file;
+ }
+
+ err = -ENOTSUPP;
+put_file:
+ fput(file);
+out:
+ return err;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -2264,6 +2392,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_BTF_GET_FD_BY_ID:
err = bpf_btf_get_fd_by_id(&attr);
break;
+ case BPF_TASK_FD_QUERY:
+ err = bpf_task_fd_query(&attr, uattr);
+ break;
default:
err = -EINVAL;
break;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ce2cbbf..81fdf2f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -14,6 +14,7 @@
#include <linux/uaccess.h>
#include <linux/ctype.h>
#include <linux/kprobes.h>
+#include <linux/syscalls.h>
#include <linux/error-injection.h>
#include "trace_probe.h"
@@ -1163,3 +1164,50 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
mutex_unlock(&bpf_event_mutex);
return err;
}
+
+int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
+ u32 *fd_type, const char **buf,
+ u64 *probe_offset, u64 *probe_addr)
+{
+ bool is_tracepoint, is_syscall_tp;
+ struct bpf_prog *prog;
+ int flags, err = 0;
+
+ prog = event->prog;
+ if (!prog)
+ return -ENOENT;
+
+ /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */
+ if (prog->type == BPF_PROG_TYPE_PERF_EVENT)
+ return -EOPNOTSUPP;
+
+ *prog_id = prog->aux->id;
+ flags = event->tp_event->flags;
+ is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT;
+ is_syscall_tp = is_syscall_trace_event(event->tp_event);
+
+ if (is_tracepoint || is_syscall_tp) {
+ *buf = is_tracepoint ? event->tp_event->tp->name
+ : event->tp_event->name;
+ *fd_type = BPF_FD_TYPE_TRACEPOINT;
+ *probe_offset = 0x0;
+ *probe_addr = 0x0;
+ } else {
+ /* kprobe/uprobe */
+ err = -EOPNOTSUPP;
+#ifdef CONFIG_KPROBE_EVENTS
+ if (flags & TRACE_EVENT_FL_KPROBE)
+ err = bpf_get_kprobe_info(event, fd_type, buf,
+ probe_offset, probe_addr,
+ event->attr.type == PERF_TYPE_TRACEPOINT);
+#endif
+#ifdef CONFIG_UPROBE_EVENTS
+ if (flags & TRACE_EVENT_FL_UPROBE)
+ err = bpf_get_uprobe_info(event, fd_type, buf,
+ probe_offset,
+ event->attr.type == PERF_TYPE_TRACEPOINT);
+#endif
+ }
+
+ return err;
+}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 02aed76..daa8157 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1287,6 +1287,35 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
head, NULL);
}
NOKPROBE_SYMBOL(kretprobe_perf_func);
+
+int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
+ const char **symbol, u64 *probe_offset,
+ u64 *probe_addr, bool perf_type_tracepoint)
+{
+ const char *pevent = trace_event_name(event->tp_event);
+ const char *group = event->tp_event->class->system;
+ struct trace_kprobe *tk;
+
+ if (perf_type_tracepoint)
+ tk = find_trace_kprobe(pevent, group);
+ else
+ tk = event->tp_event->data;
+ if (!tk)
+ return -EINVAL;
+
+ *fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
+ : BPF_FD_TYPE_KPROBE;
+ if (tk->symbol) {
+ *symbol = tk->symbol;
+ *probe_offset = tk->rp.kp.offset;
+ *probe_addr = 0;
+ } else {
+ *symbol = NULL;
+ *probe_offset = 0;
+ *probe_addr = (unsigned long)tk->rp.kp.addr;
+ }
+ return 0;
+}
#endif /* CONFIG_PERF_EVENTS */
/*
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index ac89287..bf89a51 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1161,6 +1161,28 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
{
__uprobe_perf_func(tu, func, regs, ucb, dsize);
}
+
+int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
+ const char **filename, u64 *probe_offset,
+ bool perf_type_tracepoint)
+{
+ const char *pevent = trace_event_name(event->tp_event);
+ const char *group = event->tp_event->class->system;
+ struct trace_uprobe *tu;
+
+ if (perf_type_tracepoint)
+ tu = find_probe_event(pevent, group);
+ else
+ tu = event->tp_event->data;
+ if (!tu)
+ return -EINVAL;
+
+ *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE
+ : BPF_FD_TYPE_UPROBE;
+ *filename = tu->filename;
+ *probe_offset = tu->offset;
+ return 0;
+}
#endif /* CONFIG_PERF_EVENTS */
static int
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v5 0/7] bpf: implement BPF_TASK_FD_QUERY
From: Yonghong Song @ 2018-05-24 18:21 UTC (permalink / raw)
To: peterz, ast, daniel, netdev; +Cc: kernel-team
Currently, suppose a userspace application has loaded a bpf program
and attached it to a tracepoint/kprobe/uprobe, and a bpf
introspection tool, e.g., bpftool, wants to show which bpf program
is attached to which tracepoint/kprobe/uprobe. Such attachment
information will be really useful to understand the overall bpf
deployment in the system.
There is a name field (16 bytes) for each program, which could
be used to encode the attachment point. There are some drawbacks
for this approaches. First, bpftool user (e.g., an admin) may not
really understand the association between the name and the
attachment point. Second, if one program is attached to multiple
places, encoding a proper name which can imply all these
attachments becomes difficult.
This patch introduces a new bpf subcommand BPF_TASK_FD_QUERY.
Given a pid and fd, this command will return bpf related information
to user space. Right now it only supports tracepoint/kprobe/uprobe
perf event fd's. For such a fd, BPF_TASK_FD_QUERY will return
. prog_id
. tracepoint name, or
. k[ret]probe funcname + offset or kernel addr, or
. u[ret]probe filename + offset
to the userspace.
The user can use "bpftool prog" to find more information about
bpf program itself with prog_id.
Patch #1 adds function perf_get_event() in kernel/events/core.c.
Patch #2 implements the bpf subcommand BPF_TASK_FD_QUERY.
Patch #3 syncs tools bpf.h header and also add bpf_task_fd_query()
in the libbpf library for samples/selftests/bpftool to use.
Patch #4 adds ksym_get_addr() utility function.
Patch #5 add a test in samples/bpf for querying k[ret]probes and
u[ret]probes.
Patch #6 add a test in tools/testing/selftests/bpf for querying
raw_tracepoint and tracepoint.
Patch #7 add a new subcommand "perf" to bpftool.
Changelogs:
v4 -> v5:
. return strlen(buf) instead of strlen(buf) + 1
in the attr.buf_len. As long as user provides
non-empty buffer, it will be filed with empty
string, truncated string, or full string
based on the buffer size and the length of
to-be-copied string.
v3 -> v4:
. made attr buf_len input/output. The length of
actual buffter is written to buf_len so user space knows
what is actually needed. If user provides a buffer
with length >= 1 but less than required, do partial
copy and return -ENOSPC.
. code simplification with put_user.
. changed query result attach_info to fd_type.
. add tests at selftests/bpf to test zero len, null buf and
insufficient buf.
v2 -> v3:
. made perf_get_event() return perf_event pointer const.
this was to ensure that event fields are not meddled.
. detect whether newly BPF_TASK_FD_QUERY is supported or
not in "bpftool perf" and warn users if it is not.
v1 -> v2:
. changed bpf subcommand name from BPF_PERF_EVENT_QUERY
to BPF_TASK_FD_QUERY.
. fixed various "bpftool perf" issues and added documentation
and auto-completion.
Yonghong Song (7):
perf/core: add perf_get_event() to return perf_event given a struct
file
bpf: introduce bpf subcommand BPF_TASK_FD_QUERY
tools/bpf: sync kernel header bpf.h and add bpf_task_fd_query in
libbpf
tools/bpf: add ksym_get_addr() in trace_helpers
samples/bpf: add a samples/bpf test for BPF_TASK_FD_QUERY
tools/bpf: add two BPF_TASK_FD_QUERY tests in test_progs
tools/bpftool: add perf subcommand
include/linux/perf_event.h | 5 +
include/linux/trace_events.h | 17 +
include/uapi/linux/bpf.h | 26 ++
kernel/bpf/syscall.c | 131 ++++++++
kernel/events/core.c | 8 +
kernel/trace/bpf_trace.c | 48 +++
kernel/trace/trace_kprobe.c | 29 ++
kernel/trace/trace_uprobe.c | 22 ++
samples/bpf/Makefile | 4 +
samples/bpf/task_fd_query_kern.c | 19 ++
samples/bpf/task_fd_query_user.c | 382 +++++++++++++++++++++++
tools/bpf/bpftool/Documentation/bpftool-perf.rst | 81 +++++
tools/bpf/bpftool/Documentation/bpftool.rst | 5 +-
tools/bpf/bpftool/bash-completion/bpftool | 9 +
tools/bpf/bpftool/main.c | 3 +-
tools/bpf/bpftool/main.h | 1 +
tools/bpf/bpftool/perf.c | 246 +++++++++++++++
tools/include/uapi/linux/bpf.h | 26 ++
tools/lib/bpf/bpf.c | 23 ++
tools/lib/bpf/bpf.h | 3 +
tools/testing/selftests/bpf/test_progs.c | 158 ++++++++++
tools/testing/selftests/bpf/trace_helpers.c | 12 +
tools/testing/selftests/bpf/trace_helpers.h | 1 +
23 files changed, 1257 insertions(+), 2 deletions(-)
create mode 100644 samples/bpf/task_fd_query_kern.c
create mode 100644 samples/bpf/task_fd_query_user.c
create mode 100644 tools/bpf/bpftool/Documentation/bpftool-perf.rst
create mode 100644 tools/bpf/bpftool/perf.c
--
2.9.5
^ permalink raw reply
* [PATCH bpf-next v5 4/7] tools/bpf: add ksym_get_addr() in trace_helpers
From: Yonghong Song @ 2018-05-24 18:21 UTC (permalink / raw)
To: peterz, ast, daniel, netdev; +Cc: kernel-team
In-Reply-To: <20180524182111.454612-1-yhs@fb.com>
Given a kernel function name, ksym_get_addr() will return the kernel
address for this function, or 0 if it cannot find this function name
in /proc/kallsyms. This function will be used later when a kernel
address is used to initiate a kprobe perf event.
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
---
tools/testing/selftests/bpf/trace_helpers.c | 12 ++++++++++++
tools/testing/selftests/bpf/trace_helpers.h | 1 +
2 files changed, 13 insertions(+)
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 8fb4fe8..3868dcb 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -72,6 +72,18 @@ struct ksym *ksym_search(long key)
return &syms[0];
}
+long ksym_get_addr(const char *name)
+{
+ int i;
+
+ for (i = 0; i < sym_cnt; i++) {
+ if (strcmp(syms[i].name, name) == 0)
+ return syms[i].addr;
+ }
+
+ return 0;
+}
+
static int page_size;
static int page_cnt = 8;
static struct perf_event_mmap_page *header;
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 36d90e3..3b4bcf7 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -11,6 +11,7 @@ struct ksym {
int load_kallsyms(void);
struct ksym *ksym_search(long key);
+long ksym_get_addr(const char *name);
typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size);
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v5 3/7] tools/bpf: sync kernel header bpf.h and add bpf_task_fd_query in libbpf
From: Yonghong Song @ 2018-05-24 18:21 UTC (permalink / raw)
To: peterz, ast, daniel, netdev; +Cc: kernel-team
In-Reply-To: <20180524182111.454612-1-yhs@fb.com>
Sync kernel header bpf.h to tools/include/uapi/linux/bpf.h and
implement bpf_task_fd_query() in libbpf. The test programs
in samples/bpf and tools/testing/selftests/bpf, and later bpftool
will use this libbpf function to query kernel.
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
---
tools/include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++
tools/lib/bpf/bpf.c | 23 +++++++++++++++++++++++
tools/lib/bpf/bpf.h | 3 +++
3 files changed, 52 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e95fec9..9b8c6e3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -97,6 +97,7 @@ enum bpf_cmd {
BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
BPF_BTF_GET_FD_BY_ID,
+ BPF_TASK_FD_QUERY,
};
enum bpf_map_type {
@@ -380,6 +381,22 @@ union bpf_attr {
__u32 btf_log_size;
__u32 btf_log_level;
};
+
+ struct {
+ __u32 pid; /* input: pid */
+ __u32 fd; /* input: fd */
+ __u32 flags; /* input: flags */
+ __u32 buf_len; /* input/output: buf len */
+ __aligned_u64 buf; /* input/output:
+ * tp_name for tracepoint
+ * symbol for kprobe
+ * filename for uprobe
+ */
+ __u32 prog_id; /* output: prod_id */
+ __u32 fd_type; /* output: BPF_FD_TYPE_* */
+ __u64 probe_offset; /* output: probe_offset */
+ __u64 probe_addr; /* output: probe_addr */
+ } task_fd_query;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -2557,4 +2574,13 @@ struct bpf_fib_lookup {
__u8 dmac[6]; /* ETH_ALEN */
};
+enum bpf_task_fd_type {
+ BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_UPROBE, /* filename + offset */
+ BPF_FD_TYPE_URETPROBE, /* filename + offset */
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 442b4cd..9ddc89d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -643,3 +643,26 @@ int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
return fd;
}
+
+int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
+ __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
+ __u64 *probe_addr)
+{
+ union bpf_attr attr = {};
+ int err;
+
+ attr.task_fd_query.pid = pid;
+ attr.task_fd_query.fd = fd;
+ attr.task_fd_query.flags = flags;
+ attr.task_fd_query.buf = ptr_to_u64(buf);
+ attr.task_fd_query.buf_len = *buf_len;
+
+ err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));
+ *buf_len = attr.task_fd_query.buf_len;
+ *prog_id = attr.task_fd_query.prog_id;
+ *fd_type = attr.task_fd_query.fd_type;
+ *probe_offset = attr.task_fd_query.probe_offset;
+ *probe_addr = attr.task_fd_query.probe_addr;
+
+ return err;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index d12344f..0639a30 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -107,4 +107,7 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
int bpf_raw_tracepoint_open(const char *name, int prog_fd);
int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
bool do_log);
+int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
+ __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
+ __u64 *probe_addr);
#endif
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next v5 5/7] samples/bpf: add a samples/bpf test for BPF_TASK_FD_QUERY
From: Yonghong Song @ 2018-05-24 18:21 UTC (permalink / raw)
To: peterz, ast, daniel, netdev; +Cc: kernel-team
This is mostly to test kprobe/uprobe which needs kernel headers.
Signed-off-by: Yonghong Song <yhs@fb.com>
---
samples/bpf/Makefile | 4 +
samples/bpf/task_fd_query_kern.c | 19 ++
samples/bpf/task_fd_query_user.c | 382 +++++++++++++++++++++++++++++++++++++++
3 files changed, 405 insertions(+)
create mode 100644 samples/bpf/task_fd_query_kern.c
create mode 100644 samples/bpf/task_fd_query_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 62d1aa1..7dc85ed 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -51,6 +51,7 @@ hostprogs-y += cpustat
hostprogs-y += xdp_adjust_tail
hostprogs-y += xdpsock
hostprogs-y += xdp_fwd
+hostprogs-y += task_fd_query
# Libbpf dependencies
LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -105,6 +106,7 @@ cpustat-objs := bpf_load.o cpustat_user.o
xdp_adjust_tail-objs := xdp_adjust_tail_user.o
xdpsock-objs := bpf_load.o xdpsock_user.o
xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
+task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -160,6 +162,7 @@ always += cpustat_kern.o
always += xdp_adjust_tail_kern.o
always += xdpsock_kern.o
always += xdp_fwd_kern.o
+always += task_fd_query_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -175,6 +178,7 @@ HOSTCFLAGS_offwaketime_user.o += -I$(srctree)/tools/lib/bpf/
HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/
HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
HOST_LOADLIBES += $(LIBBPF) -lelf
HOSTLOADLIBES_tracex4 += -lrt
diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c
new file mode 100644
index 0000000..f4b0a9e
--- /dev/null
+++ b/samples/bpf/task_fd_query_kern.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("kprobe/blk_start_request")
+int bpf_prog1(struct pt_regs *ctx)
+{
+ return 0;
+}
+
+SEC("kretprobe/blk_account_io_completion")
+int bpf_prog2(struct pt_regs *ctx)
+{
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
new file mode 100644
index 0000000..8381d79
--- /dev/null
+++ b/samples/bpf/task_fd_query_user.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <stdint.h>
+#include <fcntl.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.h>
+#include <sys/resource.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "libbpf.h"
+#include "bpf_load.h"
+#include "bpf_util.h"
+#include "perf-sys.h"
+#include "trace_helpers.h"
+
+#define CHECK_PERROR_RET(condition) ({ \
+ int __ret = !!(condition); \
+ if (__ret) { \
+ printf("FAIL: %s:\n", __func__); \
+ perror(" "); \
+ return -1; \
+ } \
+})
+
+#define CHECK_AND_RET(condition) ({ \
+ int __ret = !!(condition); \
+ if (__ret) \
+ return -1; \
+})
+
+static __u64 ptr_to_u64(void *ptr)
+{
+ return (__u64) (unsigned long) ptr;
+}
+
+#define PMU_TYPE_FILE "/sys/bus/event_source/devices/%s/type"
+static int bpf_find_probe_type(const char *event_type)
+{
+ char buf[256];
+ int fd, ret;
+
+ ret = snprintf(buf, sizeof(buf), PMU_TYPE_FILE, event_type);
+ CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+
+ fd = open(buf, O_RDONLY);
+ CHECK_PERROR_RET(fd < 0);
+
+ ret = read(fd, buf, sizeof(buf));
+ close(fd);
+ CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+
+ errno = 0;
+ ret = (int)strtol(buf, NULL, 10);
+ CHECK_PERROR_RET(errno);
+ return ret;
+}
+
+#define PMU_RETPROBE_FILE "/sys/bus/event_source/devices/%s/format/retprobe"
+static int bpf_get_retprobe_bit(const char *event_type)
+{
+ char buf[256];
+ int fd, ret;
+
+ ret = snprintf(buf, sizeof(buf), PMU_RETPROBE_FILE, event_type);
+ CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+
+ fd = open(buf, O_RDONLY);
+ CHECK_PERROR_RET(fd < 0);
+
+ ret = read(fd, buf, sizeof(buf));
+ close(fd);
+ CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+ CHECK_PERROR_RET(strlen(buf) < strlen("config:"));
+
+ errno = 0;
+ ret = (int)strtol(buf + strlen("config:"), NULL, 10);
+ CHECK_PERROR_RET(errno);
+ return ret;
+}
+
+static int test_debug_fs_kprobe(int prog_fd_idx, const char *fn_name,
+ __u32 expected_fd_type)
+{
+ __u64 probe_offset, probe_addr;
+ __u32 len, prog_id, fd_type;
+ char buf[256];
+ int err;
+
+ len = sizeof(buf);
+ err = bpf_task_fd_query(getpid(), event_fd[prog_fd_idx], 0, buf, &len,
+ &prog_id, &fd_type, &probe_offset,
+ &probe_addr);
+ if (err < 0) {
+ printf("FAIL: %s, for event_fd idx %d, fn_name %s\n",
+ __func__, prog_fd_idx, fn_name);
+ perror(" :");
+ return -1;
+ }
+ if (strcmp(buf, fn_name) != 0 ||
+ fd_type != expected_fd_type ||
+ probe_offset != 0x0 || probe_addr != 0x0) {
+ printf("FAIL: bpf_trace_event_query(event_fd[%d]):\n",
+ prog_fd_idx);
+ printf("buf: %s, fd_type: %u, probe_offset: 0x%llx,"
+ " probe_addr: 0x%llx\n",
+ buf, fd_type, probe_offset, probe_addr);
+ return -1;
+ }
+ return 0;
+}
+
+static int test_nondebug_fs_kuprobe_common(const char *event_type,
+ const char *name, __u64 offset, __u64 addr, bool is_return,
+ char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
+ __u64 *probe_offset, __u64 *probe_addr)
+{
+ int is_return_bit = bpf_get_retprobe_bit(event_type);
+ int type = bpf_find_probe_type(event_type);
+ struct perf_event_attr attr = {};
+ int fd;
+
+ if (type < 0 || is_return_bit < 0) {
+ printf("FAIL: %s incorrect type (%d) or is_return_bit (%d)\n",
+ __func__, type, is_return_bit);
+ return -1;
+ }
+
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
+ if (is_return)
+ attr.config |= 1 << is_return_bit;
+
+ if (name) {
+ attr.config1 = ptr_to_u64((void *)name);
+ attr.config2 = offset;
+ } else {
+ attr.config1 = 0;
+ attr.config2 = addr;
+ }
+ attr.size = sizeof(attr);
+ attr.type = type;
+
+ fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
+ CHECK_PERROR_RET(fd < 0);
+
+ CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) < 0);
+ CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0);
+ CHECK_PERROR_RET(bpf_task_fd_query(getpid(), fd, 0, buf, buf_len,
+ prog_id, fd_type, probe_offset, probe_addr) < 0);
+
+ return 0;
+}
+
+static int test_nondebug_fs_probe(const char *event_type, const char *name,
+ __u64 offset, __u64 addr, bool is_return,
+ __u32 expected_fd_type,
+ __u32 expected_ret_fd_type,
+ char *buf, __u32 buf_len)
+{
+ __u64 probe_offset, probe_addr;
+ __u32 prog_id, fd_type;
+ int err;
+
+ err = test_nondebug_fs_kuprobe_common(event_type, name,
+ offset, addr, is_return,
+ buf, &buf_len, &prog_id,
+ &fd_type, &probe_offset,
+ &probe_addr);
+ if (err < 0) {
+ printf("FAIL: %s, "
+ "for name %s, offset 0x%llx, addr 0x%llx, is_return %d\n",
+ __func__, name ? name : "", offset, addr, is_return);
+ perror(" :");
+ return -1;
+ }
+ if ((is_return && fd_type != expected_ret_fd_type) ||
+ (!is_return && fd_type != expected_fd_type)) {
+ printf("FAIL: %s, incorrect fd_type %u\n",
+ __func__, fd_type);
+ return -1;
+ }
+ if (name) {
+ if (strcmp(name, buf) != 0) {
+ printf("FAIL: %s, incorrect buf %s\n", __func__, buf);
+ return -1;
+ }
+ if (probe_offset != offset) {
+ printf("FAIL: %s, incorrect probe_offset 0x%llx\n",
+ __func__, probe_offset);
+ return -1;
+ }
+ } else {
+ if (buf_len != 0) {
+ printf("FAIL: %s, incorrect buf %p\n",
+ __func__, buf);
+ return -1;
+ }
+
+ if (probe_addr != addr) {
+ printf("FAIL: %s, incorrect probe_addr 0x%llx\n",
+ __func__, probe_addr);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return)
+{
+ const char *event_type = "uprobe";
+ struct perf_event_attr attr = {};
+ char buf[256], event_alias[256];
+ __u64 probe_offset, probe_addr;
+ __u32 len, prog_id, fd_type;
+ int err, res, kfd, efd;
+ ssize_t bytes;
+
+ snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/%s_events",
+ event_type);
+ kfd = open(buf, O_WRONLY | O_APPEND, 0);
+ CHECK_PERROR_RET(kfd < 0);
+
+ res = snprintf(event_alias, sizeof(event_alias), "test_%d", getpid());
+ CHECK_PERROR_RET(res < 0 || res >= sizeof(event_alias));
+
+ res = snprintf(buf, sizeof(buf), "%c:%ss/%s %s:0x%lx",
+ is_return ? 'r' : 'p', event_type, event_alias,
+ binary_path, offset);
+ CHECK_PERROR_RET(res < 0 || res >= sizeof(buf));
+ CHECK_PERROR_RET(write(kfd, buf, strlen(buf)) < 0);
+
+ close(kfd);
+ kfd = -1;
+
+ snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/events/%ss/%s/id",
+ event_type, event_alias);
+ efd = open(buf, O_RDONLY, 0);
+ CHECK_PERROR_RET(efd < 0);
+
+ bytes = read(efd, buf, sizeof(buf));
+ CHECK_PERROR_RET(bytes <= 0 || bytes >= sizeof(buf));
+ close(efd);
+ buf[bytes] = '\0';
+
+ attr.config = strtol(buf, NULL, 0);
+ attr.type = PERF_TYPE_TRACEPOINT;
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
+ kfd = sys_perf_event_open(&attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+ CHECK_PERROR_RET(kfd < 0);
+ CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0);
+ CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_ENABLE, 0) < 0);
+
+ len = sizeof(buf);
+ err = bpf_task_fd_query(getpid(), kfd, 0, buf, &len,
+ &prog_id, &fd_type, &probe_offset,
+ &probe_addr);
+ if (err < 0) {
+ printf("FAIL: %s, binary_path %s\n", __func__, binary_path);
+ perror(" :");
+ return -1;
+ }
+ if ((is_return && fd_type != BPF_FD_TYPE_URETPROBE) ||
+ (!is_return && fd_type != BPF_FD_TYPE_UPROBE)) {
+ printf("FAIL: %s, incorrect fd_type %u\n", __func__,
+ fd_type);
+ return -1;
+ }
+ if (strcmp(binary_path, buf) != 0) {
+ printf("FAIL: %s, incorrect buf %s\n", __func__, buf);
+ return -1;
+ }
+ if (probe_offset != offset) {
+ printf("FAIL: %s, incorrect probe_offset 0x%llx\n", __func__,
+ probe_offset);
+ return -1;
+ }
+
+ close(kfd);
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {1024*1024, RLIM_INFINITY};
+ extern char __executable_start;
+ char filename[256], buf[256];
+ __u64 uprobe_file_offset;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
+
+ if (load_kallsyms()) {
+ printf("failed to process /proc/kallsyms\n");
+ return 1;
+ }
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ /* test two functions in the corresponding *_kern.c file */
+ CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_start_request",
+ BPF_FD_TYPE_KPROBE));
+ CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_completion",
+ BPF_FD_TYPE_KRETPROBE));
+
+ /* test nondebug fs kprobe */
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x0, 0x0,
+ false, BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ buf, sizeof(buf)));
+#ifdef __x86_64__
+ /* set a kprobe on "bpf_check + 0x5", which is x64 specific */
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x5, 0x0,
+ false, BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ buf, sizeof(buf)));
+#endif
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x0, 0x0,
+ true, BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ buf, sizeof(buf)));
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+ ksym_get_addr("bpf_check"), false,
+ BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ buf, sizeof(buf)));
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+ ksym_get_addr("bpf_check"), false,
+ BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ NULL, 0));
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+ ksym_get_addr("bpf_check"), true,
+ BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ buf, sizeof(buf)));
+ CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+ ksym_get_addr("bpf_check"), true,
+ BPF_FD_TYPE_KPROBE,
+ BPF_FD_TYPE_KRETPROBE,
+ 0, 0));
+
+ /* test nondebug fs uprobe */
+ /* the calculation of uprobe file offset is based on gcc 7.3.1 on x64
+ * and the default linker script, which defines __executable_start as
+ * the start of the .text section. The calculation could be different
+ * on different systems with different compilers. The right way is
+ * to parse the ELF file. We took a shortcut here.
+ */
+ uprobe_file_offset = (__u64)main - (__u64)&__executable_start;
+ CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0],
+ uprobe_file_offset, 0x0, false,
+ BPF_FD_TYPE_UPROBE,
+ BPF_FD_TYPE_URETPROBE,
+ buf, sizeof(buf)));
+ CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0],
+ uprobe_file_offset, 0x0, true,
+ BPF_FD_TYPE_UPROBE,
+ BPF_FD_TYPE_URETPROBE,
+ buf, sizeof(buf)));
+
+ /* test debug fs uprobe */
+ CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset,
+ false));
+ CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset,
+ true));
+
+ return 0;
+}
--
2.9.5
^ 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