diff mbox series

[PATCHv4,net-next] dropwatch: Support monitoring of dropped frames

Message ID 20201023042943.563284-1-izabela.bakollari@gmail.com
State New
Headers show
Series [PATCHv4,net-next] dropwatch: Support monitoring of dropped frames | expand

Commit Message

Izabela Bakollari Oct. 23, 2020, 4:29 a.m. UTC 
From: Izabela Bakollari <izabela.bakollari@gmail.com>

Dropwatch is a utility that monitors dropped frames by having userspace
record them over the dropwatch protocol over a file. This augument
allows live monitoring of dropped frames using tools like tcpdump.

With this feature, dropwatch allows two additional commands (start and
stop interface) which allows the assignment of a net_device to the
dropwatch protocol. When assinged, dropwatch will clone dropped frames,
and receive them on the assigned interface, allowing tools like tcpdump
to monitor for them.

With this feature, create a dummy ethernet interface (ip link add dev
dummy0 type dummy), assign it to the dropwatch kernel subsystem, by using
these new commands, and then monitor dropped frames in real time by
running tcpdump -i dummy0.

Signed-off-by: Izabela Bakollari <izabela.bakollari@gmail.com>
---
 include/uapi/linux/net_dropmon.h |   3 +
 net/core/drop_monitor.c          | 120 +++++++++++++++++++++++++++++++
 2 files changed, 123 insertions(+)

Comments

Jakub Kicinski Oct. 23, 2020, 6:20 p.m. UTC | #1 
On Fri, 23 Oct 2020 06:29:43 +0200 izabela.bakollari@gmail.com wrote:
> From: Izabela Bakollari <izabela.bakollari@gmail.com>

> 

> Dropwatch is a utility that monitors dropped frames by having userspace

> record them over the dropwatch protocol over a file. This augument

> allows live monitoring of dropped frames using tools like tcpdump.

> 

> With this feature, dropwatch allows two additional commands (start and

> stop interface) which allows the assignment of a net_device to the

> dropwatch protocol. When assinged, dropwatch will clone dropped frames,

> and receive them on the assigned interface, allowing tools like tcpdump

> to monitor for them.

> 

> With this feature, create a dummy ethernet interface (ip link add dev

> dummy0 type dummy), assign it to the dropwatch kernel subsystem, by using

> these new commands, and then monitor dropped frames in real time by

> running tcpdump -i dummy0.

> 

> Signed-off-by: Izabela Bakollari <izabela.bakollari@gmail.com>


Doesn't seem to apply to net-next, also the tree is closed during the
merge window so please rebase and repost after the weekend.
diff mbox series

Patch

diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h
index 67e31f329190..e8e861e03a8a 100644
--- a/include/uapi/linux/net_dropmon.h
+++ b/include/uapi/linux/net_dropmon.h
@@ -58,6 +58,8 @@  enum {
 	NET_DM_CMD_CONFIG_NEW,
 	NET_DM_CMD_STATS_GET,
 	NET_DM_CMD_STATS_NEW,
+	NET_DM_CMD_START_IFC,
+	NET_DM_CMD_STOP_IFC,
 	_NET_DM_CMD_MAX,
 };
 
@@ -93,6 +95,7 @@  enum net_dm_attr {
 	NET_DM_ATTR_SW_DROPS,			/* flag */
 	NET_DM_ATTR_HW_DROPS,			/* flag */
 	NET_DM_ATTR_FLOW_ACTION_COOKIE,		/* binary */
+	NET_DM_ATTR_IFNAME,			/* string */
 
 	__NET_DM_ATTR_MAX,
 	NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 8e33cec9fc4e..dea85291808b 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -30,6 +30,7 @@ 
 #include <net/genetlink.h>
 #include <net/netevent.h>
 #include <net/flow_offload.h>
+#include <net/sock.h>
 
 #include <trace/events/skb.h>
 #include <trace/events/napi.h>
@@ -46,6 +47,7 @@ 
  */
 static int trace_state = TRACE_OFF;
 static bool monitor_hw;
+struct net_device *interface;
 
 /* net_dm_mutex
  *
@@ -54,6 +56,8 @@  static bool monitor_hw;
  */
 static DEFINE_MUTEX(net_dm_mutex);
 
+static DEFINE_SPINLOCK(interface_lock);
+
 struct net_dm_stats {
 	u64 dropped;
 	struct u64_stats_sync syncp;
@@ -217,6 +221,7 @@  static void trace_drop_common(struct sk_buff *skb, void *location)
 	struct nlattr *nla;
 	int i;
 	struct sk_buff *dskb;
+	struct sk_buff *nskb = NULL;
 	struct per_cpu_dm_data *data;
 	unsigned long flags;
 
@@ -255,6 +260,20 @@  static void trace_drop_common(struct sk_buff *skb, void *location)
 
 out:
 	spin_unlock_irqrestore(&data->lock, flags);
+	spin_lock_irqsave(&interface_lock, flags);
+	if (interface && interface != skb->dev) {
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			goto free;
+		nskb->dev = interface;
+	}
+	spin_unlock_irqrestore(&interface_lock, flags);
+	if (nskb)
+		netif_receive_skb(nskb);
+
+free:
+	spin_unlock_irqrestore(&interface_lock, flags);
+	return;
 }
 
 static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
@@ -1315,6 +1334,89 @@  static int net_dm_cmd_trace(struct sk_buff *skb,
 	return -EOPNOTSUPP;
 }
 
+static bool is_dummy_dev(struct net_device *dev)
+{
+	struct ethtool_drvinfo drvinfo;
+
+	if (dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) {
+		memset(&drvinfo, 0, sizeof(drvinfo));
+		dev->ethtool_ops->get_drvinfo(dev, &drvinfo);
+
+		if (strcmp(drvinfo.driver, "dummy"))
+			return false;
+		return true;
+	}
+	return false;
+}
+
+static int net_dm_interface_start(struct net *net, const char *ifname)
+{
+	struct net_device *dev = dev_get_by_name(net, ifname);
+	unsigned long flags;
+	int rc = -EBUSY;
+
+	if (!dev)
+		return -ENODEV;
+
+	if (!is_dummy_dev(dev)) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	spin_lock_irqsave(&interface_lock, flags);
+	if (!interface) {
+		interface = dev;
+		rc = 0;
+	}
+	spin_unlock_irqrestore(&interface_lock, flags);
+
+	goto out;
+
+out:
+	dev_put(dev);
+	return rc;
+}
+
+static int net_dm_interface_stop(struct net *net, const char *ifname)
+{
+	unsigned long flags;
+	int rc = -ENODEV;
+
+	spin_lock_irqsave(&interface_lock, flags);
+	if (interface && interface->name == ifname) {
+		dev_put(interface);
+		interface = NULL;
+		rc = 0;
+	}
+	spin_unlock_irqrestore(&interface_lock, flags);
+
+	return rc;
+}
+
+static int net_dm_cmd_ifc_trace(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = sock_net(skb->sk);
+	char ifname[IFNAMSIZ];
+
+	if (net_dm_is_monitoring())
+		return -EBUSY;
+
+	if (!info->attrs[NET_DM_ATTR_IFNAME])
+		return -EINVAL;
+
+	memset(ifname, 0, IFNAMSIZ);
+	nla_strlcpy(ifname, info->attrs[NET_DM_ATTR_IFNAME], IFNAMSIZ - 1);
+
+	switch (info->genlhdr->cmd) {
+	case NET_DM_CMD_START_IFC:
+		return net_dm_interface_start(net, ifname);
+	case NET_DM_CMD_STOP_IFC:
+		return net_dm_interface_stop(net, ifname);
+	}
+
+	return 0;
+}
+
 static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info)
 {
 	void *hdr;
@@ -1503,6 +1605,7 @@  static int dropmon_net_event(struct notifier_block *ev_block,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct dm_hw_stat_delta *new_stat = NULL;
 	struct dm_hw_stat_delta *tmp;
+	unsigned long flags;
 
 	switch (event) {
 	case NETDEV_REGISTER:
@@ -1529,6 +1632,12 @@  static int dropmon_net_event(struct notifier_block *ev_block,
 				}
 			}
 		}
+		spin_lock_irqsave(&interface_lock, flags);
+		if (interface && interface == dev) {
+			dev_put(interface);
+			interface = NULL;
+		}
+		spin_unlock_irqrestore(&interface_lock, flags);
 		mutex_unlock(&net_dm_mutex);
 		break;
 	}
@@ -1543,6 +1652,7 @@  static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = {
 	[NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 },
 	[NET_DM_ATTR_SW_DROPS]	= {. type = NLA_FLAG },
 	[NET_DM_ATTR_HW_DROPS]	= {. type = NLA_FLAG },
+	[NET_DM_ATTR_IFNAME] = {. type = NLA_STRING, .len = IFNAMSIZ },
 };
 
 static const struct genl_ops dropmon_ops[] = {
@@ -1570,6 +1680,16 @@  static const struct genl_ops dropmon_ops[] = {
 		.cmd = NET_DM_CMD_STATS_GET,
 		.doit = net_dm_cmd_stats_get,
 	},
+	{
+		.cmd = NET_DM_CMD_START_IFC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = net_dm_cmd_ifc_trace,
+	},
+	{
+		.cmd = NET_DM_CMD_STOP_IFC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = net_dm_cmd_ifc_trace,
+	},
 };
 
 static int net_dm_nl_pre_doit(const struct genl_ops *ops,