| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1453926098-40181-1-git-send-email-jarod@redhat.com>
Date: Wed, 27 Jan 2016 15:21:34 -0500
From: Jarod Wilson <jarod@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: Jarod Wilson <jarod@...hat.com>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jiri Pirko <jiri@...lanox.com>,
Daniel Borkmann <daniel@...earbox.net>,
Tom Herbert <tom@...bertland.com>,
Jay Vosburgh <j.vosburgh@...il.com>,
Veaceslav Falico <vfalico@...il.com>,
Andy Gospodarek <gospo@...ulusnetworks.com>,
netdev@...r.kernel.org
Subject: [PATCH net 0/4] net: add rx_unhandled stat counter
The network core tries to keep track of dropped packets, but some packets
you wouldn't really call dropped, so much as intentionally ignored, under
certain circumstances. One such case is that of bonding and team device
slaves that are currently inactive. Their respective rx_handler functions
return RX_HANDLER_EXACT (the only places in the kernel that return that),
which ends up tracking into the network core's __netif_receive_skb_core()
function's drop path, with no pt_prev set. On a noisy network, this can
result in a very rapidly incrementing rx_dropped counter, not only on the
inactive slave(s), but also on the master device, such as the following:
Inter-| Receive | Transmit
face |bytes packets errs drop fifo frame compressed multicast|bytes packets errs drop fifo colls carrier compressed
p7p1: 14783346 140430 0 140428 0 0 0 2040 680 8 0 0 0 0 0 0
p7p2: 14805198 140648 0 0 0 0 0 2034 0 0 0 0 0 0 0 0
bond0: 53365248 532798 0 421160 0 0 0 115151 2040 24 0 0 0 0 0 0
lo: 5420 54 0 0 0 0 0 0 5420 54 0 0 0 0 0 0
p5p1: 19292195 196197 0 140368 0 0 0 56564 680 8 0 0 0 0 0 0
p5p2: 19289707 196171 0 140364 0 0 0 56547 680 8 0 0 0 0 0 0
em3: 20996626 158214 0 0 0 0 0 383 0 0 0 0 0 0 0 0
em2: 14065122 138462 0 0 0 0 0 310 0 0 0 0 0 0 0 0
em1: 14063162 138440 0 0 0 0 0 308 0 0 0 0 0 0 0 0
em4: 21050830 158729 0 0 0 0 0 385 71662 469 0 0 0 0 0 0
ib0: 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
In this scenario, p5p1, p5p2 and p7p1 are all inactive slaves in an
active-backup bond0, and you can see that all three have high drop counts,
with the master bond0 showing a tally of all three.
I know that this was previously discussed some here:
http://www.spinics.net/lists/netdev/msg226341.html
It seems additional counters never came to fruition, so this is a first
attempt at creating one of them, so that we stop calling these drops,
which for users monitoring rx_dropped, causes great alarm, and renders the
counter much less useful for them.
This adds a sysfs statistics node and copies the counter out via netlink,
procfs additions will be handled separately, as I'm unsure if the current
output should be considered a stable interface...
Additionally, I'm not certain if this set qualifies for net, or if it
should be put aside and resubmitted for net-next after 4.5 is put to
bed, but I do have users who consider this an important bugfix.
CC: "David S. Miller" <davem@...emloft.net>
CC: Eric Dumazet <edumazet@...gle.com>
CC: Jiri Pirko <jiri@...lanox.com>
CC: Daniel Borkmann <daniel@...earbox.net>
CC: Tom Herbert <tom@...bertland.com>
CC: Jay Vosburgh <j.vosburgh@...il.com>
CC: Veaceslav Falico <vfalico@...il.com>
CC: Andy Gospodarek <gospo@...ulusnetworks.com>
CC: netdev@...r.kernel.org
Signed-off-by: Jarod Wilson <jarod@...hat.com>
---
include/linux/netdevice.h | 4 ++++
include/uapi/linux/if_link.h | 4 ++++
net/core/dev.c | 6 +++++-
net/core/net-sysfs.c | 2 ++
net/core/rtnetlink.c | 2 ++
5 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 289c231..7973ab5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -180,6 +180,7 @@ struct net_device_stats {
unsigned long tx_window_errors;
unsigned long rx_compressed;
unsigned long tx_compressed;
+ unsigned long rx_unhandled;
};
@@ -1397,6 +1398,8 @@ enum netdev_priv_flags {
* do not use this in drivers
* @tx_dropped: Dropped packets by core network,
* do not use this in drivers
+ * @rx_unhandled: Unhandled dropped packets by core network on
+ * inactive devices, do not use this in drivers
*
* @wireless_handlers: List of functions to handle Wireless Extensions,
* instead of ioctl,
@@ -1611,6 +1614,7 @@ struct net_device {
atomic_long_t rx_dropped;
atomic_long_t tx_dropped;
+ atomic_long_t rx_unhandled;
#ifdef CONFIG_WIRELESS_EXT
const struct iw_handler_def * wireless_handlers;
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index a30b780..533639d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -35,6 +35,8 @@ struct rtnl_link_stats {
/* for cslip etc */
__u32 rx_compressed;
__u32 tx_compressed;
+
+ __u32 rx_unhandled; /* dropped, no handler found */
};
/* The main device statistics structure */
@@ -68,6 +70,8 @@ struct rtnl_link_stats64 {
/* for cslip etc */
__u64 rx_compressed;
__u64 tx_compressed;
+
+ __u64 rx_unhandled; /* dropped, no handler found */
};
/* The struct should be in sync with struct ifmap */
diff --git a/net/core/dev.c b/net/core/dev.c
index 8cba3d8..7700ca6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4154,7 +4154,10 @@ ncls:
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
drop:
- atomic_long_inc(&skb->dev->rx_dropped);
+ if (!deliver_exact)
+ atomic_long_inc(&skb->dev->rx_dropped);
+ else
+ atomic_long_inc(&skb->dev->rx_unhandled);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
@@ -7300,6 +7303,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
}
storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
+ storage->rx_unhandled += atomic_long_read(&dev->rx_unhandled);
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index b6c8a66..fd22276 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -574,6 +574,7 @@ NETSTAT_ENTRY(tx_heartbeat_errors);
NETSTAT_ENTRY(tx_window_errors);
NETSTAT_ENTRY(rx_compressed);
NETSTAT_ENTRY(tx_compressed);
+NETSTAT_ENTRY(rx_unhandled);
static struct attribute *netstat_attrs[] = {
&dev_attr_rx_packets.attr,
@@ -599,6 +600,7 @@ static struct attribute *netstat_attrs[] = {
&dev_attr_tx_window_errors.attr,
&dev_attr_rx_compressed.attr,
&dev_attr_tx_compressed.attr,
+ &dev_attr_rx_unhandled.attr,
NULL
};
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d735e85..2e0f656 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -804,6 +804,8 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
a->rx_compressed = b->rx_compressed;
a->tx_compressed = b->tx_compressed;
+
+ a->rx_unhandled = b->rx_unhandled;
}
static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b)
--
1.8.3.1
Jarod Wilson (4):
net: add rx_unhandled counter for tracking inactive slave drops
net-procfs: show rx_unhandled counters
team: track sum of rx_unhandled for all slaves
bond: track sum of rx_unhandled for all slaves
drivers/net/bonding/bond_main.c | 1 +
drivers/net/team/team.c | 10 +++++++---
include/linux/if_team.h | 1 +
include/linux/netdevice.h | 4 ++++
include/uapi/linux/if_link.h | 4 ++++
net/core/dev.c | 6 +++++-
net/core/net-procfs.c | 11 ++++++-----
net/core/net-sysfs.c | 2 ++
net/core/rtnetlink.c | 2 ++
9 files changed, 32 insertions(+), 9 deletions(-)
--
1.8.3.1
Powered by blists - more mailing lists