Commit Graph

182 Commits

Author SHA1 Message Date
Jesper Dangaard Brouer b8358d70ce net_sched: restore qdisc quota fairness limits after bulk dequeue
Restore the quota fairness between qdisc's, that we broke with commit
5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE").

Before that commit, the quota in __qdisc_run() were in packets as
dequeue_skb() would only dequeue a single packet, that assumption
broke with bulk dequeue.

We choose not to account for the number of packets inside the TSO/GSO
packets (accessable via "skb_gso_segs").  As the previous fairness
also had this "defect". Thus, GSO/TSO packets counts as a single
packet.

Further more, we choose to slack on accuracy, by allowing a bulk
dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only
limited by the BQL bytelimit.  This is done because BQL prefers to get
its full budget for appropriate feedback from TX completion.

In future, we might consider reworking this further and, if it allows,
switch to a time-based model, as suggested by Eric. Right now, we only
restore old semantics.

Joint work with Eric, Hannes, Daniel and Jesper.  Hannes wrote the
first patch in cooperation with Daniel and Jesper.  Eric rewrote the
patch.

Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 19:12:26 -04:00
Eric Dumazet 0287587884 net: better IFF_XMIT_DST_RELEASE support
Testing xmit_more support with netperf and connected UDP sockets,
I found strange dst refcount false sharing.

Current handling of IFF_XMIT_DST_RELEASE is not optimal.

Dropping dst in validate_xmit_skb() is certainly too late in case
packet was queued by cpu X but dequeued by cpu Y

The logical point to take care of drop/force is in __dev_queue_xmit()
before even taking qdisc lock.

As Julian Anastasov pointed out, need for skb_dst() might come from some
packet schedulers or classifiers.

This patch adds new helper to cleanly express needs of various drivers
or qdiscs/classifiers.

Drivers that need skb_dst() in their ndo_start_xmit() should call
following helper in their setup instead of the prior :

	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
->
	netif_keep_dst(dev);

Instead of using a single bit, we use two bits, one being
eventually rebuilt in bonding/team drivers.

The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being
rebuilt in bonding/team. Eventually, we could add something
smarter later.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-07 13:22:11 -04:00
Eric Dumazet 55a93b3ea7 qdisc: validate skb without holding lock
Validation of skb can be pretty expensive :

GSO segmentation and/or checksum computations.

We can do this without holding qdisc lock, so that other cpus
can queue additional packets.

Trick is that requeued packets were already validated, so we carry
a boolean so that sch_direct_xmit() can validate a fresh skb list,
or directly use an old one.

Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads
host.

Turning TSO on or off had no effect on throughput, only few more cpu
cycles. Lock contention on qdisc lock disappeared.

Same if disabling TX checksum offload.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:36:11 -07:00
Jesper Dangaard Brouer 808e7ac0bd qdisc: dequeue bulking also pickup GSO/TSO packets
The TSO and GSO segmented packets already benefit from bulking
on their own.

The TSO packets have always taken advantage of the only updating
the tailptr once for a large packet.

The GSO segmented packets have recently taken advantage of
bulking xmit_more API, via merge commit 53fda7f7f9 ("Merge
branch 'xmit_list'"), specifically via commit 7f2e870f2a ("net:
Move main gso loop out of dev_hard_start_xmit() into helper.")
allowing qdisc requeue of remaining list.  And via commit
ce93718fb7 ("net: Don't keep around original SKB when we
software segment GSO frames.").

This patch allow further bulking of TSO/GSO packets together,
when dequeueing from the qdisc.

Testing:
 Measuring HoL (Head-of-Line) blocking for TSO and GSO, with
netperf-wrapper. Bulking several TSO show no performance regressions
(requeues were in the area 32 requeues/sec).

Bulking several GSOs does show small regression or very small
improvement (requeues were in the area 8000 requeues/sec).

 Using ixgbe 10Gbit/s with GSO bulking, we can measure some additional
latency. Base-case, which is "normal" GSO bulking, sees varying
high-prio queue delay between 0.38ms to 0.47ms.  Bulking several GSOs
together, result in a stable high-prio queue delay of 0.50ms.

 Using igb at 100Mbit/s with GSO bulking, shows an improvement.
Base-case sees varying high-prio queue delay between 2.23ms to 2.35ms

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:37:06 -07:00
Jesper Dangaard Brouer 5772e9a346 qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE
Based on DaveM's recent API work on dev_hard_start_xmit(), that allows
sending/processing an entire skb list.

This patch implements qdisc bulk dequeue, by allowing multiple packets
to be dequeued in dequeue_skb().

The optimization principle for this is two fold, (1) to amortize
locking cost and (2) avoid expensive tailptr update for notifying HW.
 (1) Several packets are dequeued while holding the qdisc root_lock,
amortizing locking cost over several packet.  The dequeued SKB list is
processed under the TXQ lock in dev_hard_start_xmit(), thus also
amortizing the cost of the TXQ lock.
 (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more
API to delay HW tailptr update, which also reduces the cost per
packet.

One restriction of the new API is that every SKB must belong to the
same TXQ.  This patch takes the easy way out, by restricting bulk
dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the
qdisc only have attached a single TXQ.

Some detail about the flow; dev_hard_start_xmit() will process the skb
list, and transmit packets individually towards the driver (see
xmit_one()).  In case the driver stops midway in the list, the
remaining skb list is returned by dev_hard_start_xmit().  In
sch_direct_xmit() this returned list is requeued by dev_requeue_skb().

To avoid overshooting the HW limits, which results in requeuing, the
patch limits the amount of bytes dequeued, based on the drivers BQL
limits.  In-effect bulking will only happen for BQL enabled drivers.

Small amounts for extra HoL blocking (2x MTU/0.24ms) were
measured at 100Mbit/s, with bulking 8 packets, but the
oscillating nature of the measurement indicate something, like
sched latency might be causing this effect. More comparisons
show, that this oscillation goes away occationally. Thus, we
disregard this artifact completely and remove any "magic" bulking
limit.

For now, as a conservative approach, stop bulking when seeing TSO and
segmented GSO packets.  They already benefit from bulking on their own.
A followup patch add this, to allow easier bisect-ability for finding
regressions.

Jointed work with Hannes, Daniel and Florian.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:37:06 -07:00
John Fastabend 22e0f8b932 net: sched: make bstats per cpu and estimator RCU safe
In order to run qdisc's without locking statistics and estimators
need to be handled correctly.

To resolve bstats make the statistics per cpu. And because this is
only needed for qdiscs that are running without locks which is not
the case for most qdiscs in the near future only create percpu
stats when qdiscs set the TCQ_F_CPUSTATS flag.

Next because estimators use the bstats to calculate packets per
second and bytes per second the estimator code paths are updated
to use the per cpu statistics.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-30 01:02:26 -04:00
Eric Dumazet ab34f64808 net: sched: use __skb_queue_head_init() where applicable
pfifo_fast and htb use skb lists, without needing their spinlocks.
(They instead use the standard qdisc lock)

We can use __skb_queue_head_init() instead of skb_queue_head_init()
to be consistent.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-19 16:32:10 -04:00
John Fastabend 46e5da40ae net: qdisc: use rcu prefix and silence sparse warnings
Add __rcu notation to qdisc handling by doing this we can make
smatch output more legible. And anyways some of the cases should
be using rcu_dereference() see qdisc_all_tx_empty(),
qdisc_tx_chainging(), and so on.

Also *wake_queue() API is commonly called from driver timer routines
without rcu lock or rtnl lock. So I added rcu_read_lock() blocks
around netif_wake_subqueue and netif_tx_wake_queue.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-13 12:30:25 -04:00
Jesper Dangaard Brouer 3f3c7eec60 qdisc: exit case fixes for skb list handling in qdisc layer
More minor fixes to merge commit 53fda7f7f9 (Merge branch 'xmit_list')
that allows us to work with a list of SKBs.

Fixing exit cases in qdisc_reset() and qdisc_destroy(), where a
leftover requeued SKB (qdisc->gso_skb) can have the potential of
being a skb list, thus use kfree_skb_list().

This is a followup to commit 10770bc2d1 ("qdisc: adjustments for
API allowing skb list xmits").

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-03 20:41:42 -07:00
Jesper Dangaard Brouer 10770bc2d1 qdisc: adjustments for API allowing skb list xmits
Minor adjustments for merge commit 53fda7f7f9 (Merge branch 'xmit_list')
that allows us to work with a list of SKBs.

Update code doc to function sch_direct_xmit().

In handle_dev_cpu_collision() use kfree_skb_list() in error handling.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-02 14:06:17 -07:00
David S. Miller ce93718fb7 net: Don't keep around original SKB when we software segment GSO frames.
Just maintain the list properly by returning the head of the remaining
SKB list from dev_hard_start_xmit().

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-01 17:39:56 -07:00
David S. Miller 50cbe9ab5f net: Validate xmit SKBs right when we pull them out of the qdisc.
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-01 17:39:56 -07:00
Daniel Borkmann 10c51b5623 net: add skb_get_tx_queue() helper
Replace occurences of skb_get_queue_mapping() and follow-up
netdev_get_tx_queue() with an actual helper function.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-29 20:02:07 -07:00
Ying Xue 9bf2b8c280 net: fix some typos in comment
In commit 371121057607e3127e19b3fa094330181b5b031e("net:
QDISC_STATE_RUNNING dont need atomic bit ops") the
__QDISC_STATE_RUNNING is renamed to __QDISC___STATE_RUNNING,
but the old names existing in comment are not replaced with
the new name completely.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-01 14:20:32 -07:00
david decotigny 2d3b479df4 net-sysfs: expose number of carrier on/off changes
This allows to monitor carrier on/off transitions and detect link
flapping issues:
 - new /sys/class/net/X/carrier_changes
 - new rtnetlink IFLA_CARRIER_CHANGES (getlink)

Tested:
  - grep . /sys/class/net/*/carrier_changes
    + ip link set dev X down/up
    + plug/unplug cable
  - updated iproute2: prints IFLA_CARRIER_CHANGES
  - iproute2 20121211-2 (debian): unchanged behavior

Signed-off-by: David Decotigny <decot@googlers.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-31 16:24:52 -04:00
David S. Miller 0a379e21c5 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2014-01-14 14:42:42 -08:00
Jason Wang f663dd9aaf net: core: explicitly select a txq before doing l2 forwarding
Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The
will cause several issues:

- NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan
  instead of lower device which misses the necessary txq synchronization for
  lower device such as txq stopping or frozen required by dev watchdog or
  control path.
- dev_hard_start_xmit() was called with NULL txq which bypasses the net device
  watchdog.
- dev_hard_start_xmit() does not check txq everywhere which will lead a crash
  when tso is disabled for lower device.

Fix this by explicitly introducing a new param for .ndo_select_queue() for just
selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also
extended to accept this parameter and dev_queue_xmit_accel() was used to do l2
forwarding transmission.

With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need
to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep
a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of
dev_queue_xmit() to do the transmission.

In the future, it was also required for macvtap l2 forwarding support since it
provides a necessary synchronization method.

Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: e1000-devel@lists.sourceforge.net
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 13:23:08 -05:00
Eric Dumazet e57a784d8c pkt_sched: set root qdisc before change() in attach_default_qdiscs()
After commit 95dc19299f ("pkt_sched: give visibility to mq slave
qdiscs") we call disc_list_add() while the device qdisc might be
the noop_qdisc one.

This shows up as duplicates in "tc qdisc show", as all inactive devices
point to noop_qdisc.

Fix this by setting dev->qdisc to the new qdisc before calling
ops->change() in attach_default_qdiscs()

Add a WARN_ON_ONCE() to catch any future similar problem.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-14 01:20:06 -05:00
Yang Yingliang 82d567c266 net_sched: change "foo* bar" to "foo *bar"
"foo* bar" or "foo * bar" should be "foo *bar".

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-10 22:44:51 -05:00
John Fastabend a6cc0cfa72 net: Add layer 2 hardware acceleration operations for macvlan devices
Add a operations structure that allows a network interface to export
the fact that it supports package forwarding in hardware between
physical interfaces and other mac layer devices assigned to it (such
as macvlans). This operaions structure can be used by virtual mac
devices to bypass software switching so that forwarding can be done
in hardware more efficiently.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-07 19:11:41 -05:00
Eric W. Biederman 5cde282938 net: Separate the close_list and the unreg_list v2
Separate the unreg_list and the close_list in dev_close_many preventing
dev_close_many from permuting the unreg_list.  The permutations of the
unreg_list have resulted in cases where the loopback device is accessed
it has been freed in code such as dst_ifdown.  Resulting in subtle memory
corruption.

This is the second bug from sharing the storage between the close_list
and the unreg_list.  The issues that crop up with sharing are
apparently too subtle to show up in normal testing or usage, so let's
forget about being clever and use two separate lists.

v2: Make all callers pass in a close_list to dev_close_many

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-07 15:23:14 -04:00
Eric Dumazet 3e1e3aae1f net_sched: add u64 rate to psched_ratecfg_precompute()
Add an extra u64 rate parameter to psched_ratecfg_precompute()
so that some qdisc can opt-in for 64bit rates in the future,
to overcome the ~34 Gbits limit.

psched_ratecfg_getrate() reports a legacy structure to
tc utility, so if actual rate is above the 32bit rate field,
cap it to the 34Gbit limit.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-20 14:41:02 -04:00
stephen hemminger 34aedd3f3b qdisc: fix build with !CONFIG_NET_SCHED
Multiqueue scheduler refers to default_qdisc_ops; therefore the
variable definition needs to be moved to handle case where net
scheduler API is not available.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-31 18:09:45 -04:00
stephen hemminger d2a7f269f9 qdisc: make args to qdisc_create_default const
Fixes warnings introduced by the qdisc default patch.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-31 18:09:45 -04:00
stephen hemminger 6da7c8fcbc qdisc: allow setting default queuing discipline
By default, the pfifo_fast queue discipline has been used by default
for all devices. But we have better choices now.

This patch allow setting the default queueing discipline with sysctl.
This allows easy use of better queueing disciplines on all devices
without having to use tc qdisc scripts. It is intended to allow
an easy path for distributions to make fq_codel or sfq the default
qdisc.

This patch also makes pfifo_fast more of a first class qdisc, since
it is now possible to manually override the default and explicitly
use pfifo_fast. The behavior for systems who do not use the sysctl
is unchanged, they still get pfifo_fast

Also removes leftover random # in sysctl net core.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-31 00:32:32 -04:00
Jesper Dangaard Brouer 8a8e3d84b1 net_sched: restore "linklayer atm" handling
commit 56b765b79 ("htb: improved accuracy at high rates")
broke the "linklayer atm" handling.

 tc class add ... htb rate X ceil Y linklayer atm

The linklayer setting is implemented by modifying the rate table
which is send to the kernel.  No direct parameter were
transferred to the kernel indicating the linklayer setting.

The commit 56b765b79 ("htb: improved accuracy at high rates")
removed the use of the rate table system.

To keep compatible with older iproute2 utils, this patch detects
the linklayer by parsing the rate table.  It also supports future
versions of iproute2 to send this linklayer parameter to the
kernel directly. This is done by using the __reserved field in
struct tc_ratespec, to convey the choosen linklayer option, but
only using the lower 4 bits of this field.

Linklayer detection is limited to speeds below 100Mbit/s, because
at high rates the rtab is gets too inaccurate, so bad that
several fields contain the same values, this resembling the ATM
detect.  Fields even start to contain "0" time to send, e.g. at
1000Mbit/s sending a 96 bytes packet cost "0", thus the rtab have
been more broken than we first realized.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-15 01:43:08 -07:00
nikolay@redhat.com 07ce76aa9b net_sched: make dev_trans_start return vlan's real dev trans_start
Vlan devices are LLTX and don't update their own trans_start, so if
dev_trans_start has to be called with a vlan device then 0 or a stale
value will be returned. Currently the bonding is the only such user, and
it's needed for proper arp monitoring when the slaves are vlans.
Fix this by extracting the vlan's real device trans_start.

Suggested-by: David Miller <davem@davemloft.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Acked-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-05 12:17:42 -07:00
Eric Dumazet 130d3d68b5 net_sched: psched_ratecfg_precompute() improvements
Before allowing 64bits bytes rates, refactor
psched_ratecfg_precompute() to get better comments
and increased accuracy.

rate_bps field is renamed to rate_bytes_ps, as we only
have to worry about bytes per second.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Greear <greearb@candelatech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-11 22:39:47 -07:00
Eric Dumazet 01cb71d2d4 net_sched: restore "overhead xxx" handling
commit 56b765b79 ("htb: improved accuracy at high rates")
broke the "overhead xxx" handling, as well as the "linklayer atm"
attribute.

tc class add ... htb rate X ceil Y linklayer atm overhead 10

This patch restores the "overhead xxx" handling, for htb, tbf
and act_police

The "linklayer atm" thing needs a separate fix.

Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vimalkumar <j.vimal@gmail.com>
Cc: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-02 22:22:35 -07:00
Sergey Popovich ea872d7712 sch: add missing u64 in psched_ratecfg_precompute()
It seems that commit

commit 292f1c7ff6
Author: Jiri Pirko <jiri@resnulli.us>
Date:   Tue Feb 12 00:12:03 2013 +0000

    sch: make htb_rate_cfg and functions around that generic

adds little regression.

Before:

# tc qdisc add dev eth0 root handle 1: htb default ffff
# tc class add dev eth0 classid 1:ffff htb rate 5Gbit
# tc -s class show dev eth0
class htb 1:ffff root prio 0 rate 5000Mbit ceil 5000Mbit burst 625b cburst
625b
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 rate 0bit 0pps backlog 0b 0p requeues 0
 lended: 0 borrowed: 0 giants: 0
 tokens: 31 ctokens: 31

After:

# tc qdisc add dev eth0 root handle 1: htb default ffff
# tc class add dev eth0 classid 1:ffff htb rate 5Gbit
# tc -s class show dev eth0
class htb 1:ffff root prio 0 rate 1544Mbit ceil 1544Mbit burst 625b cburst
625b
 Sent 5073 bytes 41 pkt (dropped 0, overlimits 0 requeues 0)
 rate 1976bit 2pps backlog 0b 0p requeues 0
 lended: 41 borrowed: 0 giants: 0
 tokens: 1802 ctokens: 1802

This probably due to lost u64 cast of rate parameter in
psched_ratecfg_precompute() (net/sched/sch_generic.c).

Signed-off-by: Sergey Popovich <popovich_sergei@mail.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-27 14:06:41 -04:00
Jiri Pirko 292f1c7ff6 sch: make htb_rate_cfg and functions around that generic
As it is going to be used in tbf as well, push these to generic code.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 18:59:45 -05:00
Eric Dumazet 1abbe1394a pkt_sched: avoid requeues if possible
With BQL being deployed, we can more likely have following behavior :

We dequeue a packet from qdisc in dequeue_skb(), then we realize target
tx queue is in XOFF state in sch_direct_xmit(), and we have to hold the
skb into gso_skb for later.

This shows in stats (tc -s qdisc dev eth0) as requeues.

Problem of these requeues is that high priority packets can not be
dequeued as long as this (possibly low prio and big TSO packet) is not
removed from gso_skb.

At 1Gbps speed, a full size TSO packet is 500 us of extra latency.

In some cases, we know that all packets dequeued from a qdisc are
for a particular and known txq :

- If device is non multi queue
- For all MQ/MQPRIO slave qdiscs

This patch introduces a new qdisc flag, TCQ_F_ONETXQUEUE to mark
this capability, so that dequeue_skb() is allowed to dequeue a packet
only if the associated txq is not stopped.

This indeed reduce latencies for high prio packets (or improve fairness
with sfq/fq_codel), and almost remove qdisc 'requeues'.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-12 00:16:47 -05:00
Eric Dumazet 23d3b8bfb8 net: qdisc busylock needs lockdep annotations
It seems we need to provide ability for stacked devices
to use specific lock_class_key for sch->busylock

We could instead default l2tpeth tx_queue_len to 0 (no qdisc), but
a user might use a qdisc anyway.

(So same fixes are probably needed on non LLTX stacked drivers)

Noticed while stressing L2TPV3 setup :

======================================================
 [ INFO: possible circular locking dependency detected ]
 3.6.0-rc3+ #788 Not tainted
 -------------------------------------------------------
 netperf/4660 is trying to acquire lock:
  (l2tpsock){+.-...}, at: [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core]

 but task is already holding lock:
  (&(&sch->busylock)->rlock){+.-...}, at: [<ffffffff81596595>] dev_queue_xmit+0xd75/0xe00

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (&(&sch->busylock)->rlock){+.-...}:
        [<ffffffff810a5df0>] lock_acquire+0x90/0x200
        [<ffffffff817499fc>] _raw_spin_lock_irqsave+0x4c/0x60
        [<ffffffff81074872>] __wake_up+0x32/0x70
        [<ffffffff8136d39e>] tty_wakeup+0x3e/0x80
        [<ffffffff81378fb3>] pty_write+0x73/0x80
        [<ffffffff8136cb4c>] tty_put_char+0x3c/0x40
        [<ffffffff813722b2>] process_echoes+0x142/0x330
        [<ffffffff813742ab>] n_tty_receive_buf+0x8fb/0x1230
        [<ffffffff813777b2>] flush_to_ldisc+0x142/0x1c0
        [<ffffffff81062818>] process_one_work+0x198/0x760
        [<ffffffff81063236>] worker_thread+0x186/0x4b0
        [<ffffffff810694d3>] kthread+0x93/0xa0
        [<ffffffff81753e24>] kernel_thread_helper+0x4/0x10

 -> #0 (l2tpsock){+.-...}:
        [<ffffffff810a5288>] __lock_acquire+0x1628/0x1b10
        [<ffffffff810a5df0>] lock_acquire+0x90/0x200
        [<ffffffff817498c1>] _raw_spin_lock+0x41/0x50
        [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
        [<ffffffffa021a802>] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth]
        [<ffffffff815952b2>] dev_hard_start_xmit+0x502/0xa70
        [<ffffffff815b63ce>] sch_direct_xmit+0xfe/0x290
        [<ffffffff81595a05>] dev_queue_xmit+0x1e5/0xe00
        [<ffffffff815d9d60>] ip_finish_output+0x3d0/0x890
        [<ffffffff815db019>] ip_output+0x59/0xf0
        [<ffffffff815da36d>] ip_local_out+0x2d/0xa0
        [<ffffffff815da5a3>] ip_queue_xmit+0x1c3/0x680
        [<ffffffff815f4192>] tcp_transmit_skb+0x402/0xa60
        [<ffffffff815f4a94>] tcp_write_xmit+0x1f4/0xa30
        [<ffffffff815f5300>] tcp_push_one+0x30/0x40
        [<ffffffff815e6672>] tcp_sendmsg+0xe82/0x1040
        [<ffffffff81614495>] inet_sendmsg+0x125/0x230
        [<ffffffff81576cdc>] sock_sendmsg+0xdc/0xf0
        [<ffffffff81579ece>] sys_sendto+0xfe/0x130
        [<ffffffff81752c92>] system_call_fastpath+0x16/0x1b
  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&(&sch->busylock)->rlock);
                                lock(l2tpsock);
                                lock(&(&sch->busylock)->rlock);
   lock(l2tpsock);

  *** DEADLOCK ***

 5 locks held by netperf/4660:
  #0:  (sk_lock-AF_INET){+.+.+.}, at: [<ffffffff815e581c>] tcp_sendmsg+0x2c/0x1040
  #1:  (rcu_read_lock){.+.+..}, at: [<ffffffff815da3e0>] ip_queue_xmit+0x0/0x680
  #2:  (rcu_read_lock_bh){.+....}, at: [<ffffffff815d9ac5>] ip_finish_output+0x135/0x890
  #3:  (rcu_read_lock_bh){.+....}, at: [<ffffffff81595820>] dev_queue_xmit+0x0/0xe00
  #4:  (&(&sch->busylock)->rlock){+.-...}, at: [<ffffffff81596595>] dev_queue_xmit+0xd75/0xe00

 stack backtrace:
 Pid: 4660, comm: netperf Not tainted 3.6.0-rc3+ #788
 Call Trace:
  [<ffffffff8173dbf8>] print_circular_bug+0x1fb/0x20c
  [<ffffffff810a5288>] __lock_acquire+0x1628/0x1b10
  [<ffffffff810a334b>] ? check_usage+0x9b/0x4d0
  [<ffffffff810a3f44>] ? __lock_acquire+0x2e4/0x1b10
  [<ffffffff810a5df0>] lock_acquire+0x90/0x200
  [<ffffffffa0208db2>] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
  [<ffffffff817498c1>] _raw_spin_lock+0x41/0x50
  [<ffffffffa0208db2>] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
  [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
  [<ffffffffa021a802>] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth]
  [<ffffffff815952b2>] dev_hard_start_xmit+0x502/0xa70
  [<ffffffff81594e0e>] ? dev_hard_start_xmit+0x5e/0xa70
  [<ffffffff81595961>] ? dev_queue_xmit+0x141/0xe00
  [<ffffffff815b63ce>] sch_direct_xmit+0xfe/0x290
  [<ffffffff81595a05>] dev_queue_xmit+0x1e5/0xe00
  [<ffffffff81595820>] ? dev_hard_start_xmit+0xa70/0xa70
  [<ffffffff815d9d60>] ip_finish_output+0x3d0/0x890
  [<ffffffff815d9ac5>] ? ip_finish_output+0x135/0x890
  [<ffffffff815db019>] ip_output+0x59/0xf0
  [<ffffffff815da36d>] ip_local_out+0x2d/0xa0
  [<ffffffff815da5a3>] ip_queue_xmit+0x1c3/0x680
  [<ffffffff815da3e0>] ? ip_local_out+0xa0/0xa0
  [<ffffffff815f4192>] tcp_transmit_skb+0x402/0xa60
  [<ffffffff815fa25e>] ? tcp_md5_do_lookup+0x18e/0x1a0
  [<ffffffff815f4a94>] tcp_write_xmit+0x1f4/0xa30
  [<ffffffff815f5300>] tcp_push_one+0x30/0x40
  [<ffffffff815e6672>] tcp_sendmsg+0xe82/0x1040
  [<ffffffff81614495>] inet_sendmsg+0x125/0x230
  [<ffffffff81614370>] ? inet_create+0x6b0/0x6b0
  [<ffffffff8157e6e2>] ? sock_update_classid+0xc2/0x3b0
  [<ffffffff8157e750>] ? sock_update_classid+0x130/0x3b0
  [<ffffffff81576cdc>] sock_sendmsg+0xdc/0xf0
  [<ffffffff81162579>] ? fget_light+0x3f9/0x4f0
  [<ffffffff81579ece>] sys_sendto+0xfe/0x130
  [<ffffffff810a69ad>] ? trace_hardirqs_on+0xd/0x10
  [<ffffffff8174a0b0>] ? _raw_spin_unlock_irq+0x30/0x50
  [<ffffffff810757e3>] ? finish_task_switch+0x83/0xf0
  [<ffffffff810757a6>] ? finish_task_switch+0x46/0xf0
  [<ffffffff81752cb7>] ? sysret_check+0x1b/0x56
  [<ffffffff81752c92>] system_call_fastpath+0x16/0x1b

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-05 17:49:27 -04:00
Amerigo Wang ee89bab14e net: move and rename netif_notify_peers()
I believe net/core/dev.c is a better place for netif_notify_peers(),
because other net event notify functions also stay in this file.

And rename it to netdev_notify_peers().

Cc: David S. Miller <davem@davemloft.net>
Cc: Ian Campbell <Ian.Campbell@citrix.com>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-08-14 14:28:23 -07:00
Joe Perches e87cc4728f net: Convert net_ratelimit uses to net_<level>_ratelimited
Standardize the net core ratelimited logging functions.

Coalesce formats, align arguments.
Change a printk then vprintk sequence to use printf extension %pV.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-15 13:45:03 -04:00
David S. Miller 1b34ec43c9 pkt_sched: Stop using NLA_PUT*().
These macros contain a hidden goto, and are thus extremely error
prone and make code hard to audit.

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-01 18:11:37 -04:00
Tom Herbert 7346649826 net: Add queue state xoff flag for stack
Create separate queue state flags so that either the stack or drivers
can turn on XOFF.  Added a set of functions used in the stack to determine
if a queue is really stopped (either by stack or driver)

Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-29 12:46:19 -05:00
david decotigny ccf5ff69fb net: new counter for tx_timeout errors in sysfs
This adds the /sys/class/net/DEV/queues/Q/tx_timeout attribute
containing the total number of timeout events on the given queue. It
is always available with CONFIG_SYSFS, independently of
CONFIG_RPS/XPS.

Credits to Stephen Hemminger for a preliminary version of this patch.

Tested:
  without CONFIG_SYSFS (compilation only)
  with sysfs and without CONFIG_RPS & CONFIG_XPS
  with sysfs and without CONFIG_RPS
  with sysfs and without CONFIG_XPS
  with defaults

Signed-off-by: David Decotigny <david.decotigny@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-16 23:14:02 -05:00
Krishna Kumar f0c50c7c9a Remove redundant variable/code in __qdisc_run
Remove redundant variable "work".

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-07-15 08:08:26 -07:00
jamal d5b8aa1d24 net_sched: fix dequeuer fairness
Results on dummy device can be seen in my netconf 2011
slides. These results are for a 10Gige IXGBE intel
nic - on another i5 machine, very similar specs to
the one used in the netconf2011 results.
It turns out - this is a hell lot worse than dummy
and so this patch is even more beneficial for 10G.

Test setup:
----------

System under test sending packets out.
Additional box connected directly dropping packets.
Installed prio qdisc on the eth device and default
netdev default length of 1000 used as is.
The 3 prio bands each were set to 100 (didnt factor in
the results).

5 packet runs were made and the middle 3 picked.

results
-------

The "cpu" column indicates the which cpu the sample
was taken on,
The "Pkt runx" carries the number of packets a cpu
dequeued when forced to be in the "dequeuer" role.
The "avg" for each run is the number of times each
cpu should be a "dequeuer" if the system was fair.

3.0-rc4      (plain)
cpu         Pkt run1        Pkt run2        Pkt run3
================================================
cpu0        21853354        21598183        22199900
cpu1          431058          473476          393159
cpu2          481975          477529          458466
cpu3        23261406        23412299        22894315
avg         11506948        11490372        11486460

3.0-rc4 with patch and default weight 64
cpu 	     Pkt run1        Pkt run2        Pkt run3
================================================
cpu0        13205312        13109359        13132333
cpu1        10189914        10159127        10122270
cpu2        10213871        10124367        10168722
cpu3        13165760        13164767        13096705
avg         11693714        11639405        11630008

As you can see the system is still not perfect but
is a lot better than what it was before...

At the moment we use the old backlog weight, weight_p
which is 64 packets. It seems to be reasonably fine
with that value.
The system could be made more fair if we reduce the
weight_p (as per my presentation), but we are going
to affect the shared backlog weight. Unless deemed
necessary, I think the default value is fine. If not
we could add yet another knob.

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-27 00:14:10 -07:00
David S. Miller 3019de124b net: Rework netdev_drivername() to avoid warning.
This interface uses a temporary buffer, but for no real reason.
And now can generate warnings like:

net/sched/sch_generic.c: In function dev_watchdog
net/sched/sch_generic.c:254:10: warning: unused variable drivername

Just return driver->name directly or "".

Reported-by: Connor Hansen <cmdkhh@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-06 16:41:33 -07:00
Eric Dumazet 3137663dfb net: avoid synchronize_rcu() in dev_deactivate_many
dev_deactivate_many() issues one synchronize_rcu() call after qdiscs set
to noop_qdisc.

This call is here to make sure they are no outstanding qdisc-less
dev_queue_xmit calls before returning to caller.

But in dismantle phase, we dont have to wait, because we wont activate
again the device, and we are going to wait one rcu grace period later in
rollback_registered_many().

After this patch, device dismantle uses one synchronize_net() and one
rcu_barrier() call only, so we have a ~30% speedup and a smaller RTNL
latency.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Patrick McHardy <kaber@trash.net>,
CC: Ben Greear <greearb@candelatech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-22 21:01:20 -04:00
David S. Miller 0a0e9ae1bd Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
Conflicts:
	drivers/net/bnx2x/bnx2x.h
2011-03-03 21:27:42 -08:00
Eric Dumazet d276055c4e net_sched: reduce fifo qdisc size
Because of various alignements [SLUB / qdisc], we use 512 bytes of
memory for one {p|b}fifo qdisc, instead of 256 bytes on 64bit arches and
192 bytes on 32bit ones.

Move the "u32 limit" inside "struct Qdisc" (no impact on other qdiscs)

Change qdisc_alloc(), first trying a regular allocation before an
oversized one.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-03 11:10:02 -08:00
Eric W. Biederman 5f04d5068a net: Fix more stale on-stack list_head objects.
From: Eric W. Biederman <ebiederm@xmission.com>

In the beginning with batching unreg_list was a list that was used only
once in the lifetime of a network device (I think).  Now we have calls
using the unreg_list that can happen multiple times in the life of a
network device like dev_deactivate and dev_close that are also using the
unreg_list.  In addition in unregister_netdevice_queue we also do a
list_move because for devices like veth pairs it is possible that
unregister_netdevice_queue will be called multiple times.

So I think the change below to fix dev_deactivate which Eric D. missed
will fix this problem.  Now to go test that.

Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-20 11:49:45 -08:00
Eric Dumazet 23624935e0 net_sched: TCQ_F_CAN_BYPASS generalization
Now qdisc stab is handled before TCQ_F_CAN_BYPASS test in
__dev_xmit_skb(), we can generalize TCQ_F_CAN_BYPASS to other qdiscs
than pfifo_fast : pfifo, bfifo, pfifo_head_drop and sfq

SFQ is special because it can have external classifiers, and in these
cases, we cannot bypass queue discipline (packet could be dropped by
classifier) without admin asking it, or further changes.

Its worth doing this, especially for SFQ, avoiding dirtying memory in
case no packets are already waiting in queue.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-21 16:26:09 -08:00
Eric Dumazet a2da570d62 net_sched: RCU conversion of stab
This patch converts stab qdisc management to RCU, so that we can perform
the qdisc_calculate_pkt_len() call before getting qdisc lock.

This shortens the lock's held time in __dev_xmit_skb().

This permits more qdiscs to get TCQ_F_CAN_BYPASS status, avoiding lot of
cache misses and so reducing latencies.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Patrick McHardy <kaber@trash.net>
CC: Jesper Dangaard Brouer <hawk@diku.dk>
CC: Jarek Poplawski <jarkao2@gmail.com>
CC: Jamal Hadi Salim <hadi@cyberus.ca>
CC: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 16:59:32 -08:00
Eric Dumazet cc7ec456f8 net_sched: cleanups
Cleanup net/sched code to current CodingStyle and practices.

Reduce inline abuse

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-19 23:31:12 -08:00
John Fastabend b8970f0bfc net_sched: implement a root container qdisc sch_mqprio
This implements a mqprio queueing discipline that by default creates
a pfifo_fast qdisc per tx queue and provides the needed configuration
interface.

Using the mqprio qdisc the number of tcs currently in use along
with the range of queues alloted to each class can be configured. By
default skbs are mapped to traffic classes using the skb priority.
This mapping is configurable.

Configurable parameters,

struct tc_mqprio_qopt {
	__u8    num_tc;
	__u8    prio_tc_map[TC_BITMASK + 1];
	__u8    hw;
	__u16   count[TC_MAX_QUEUE];
	__u16   offset[TC_MAX_QUEUE];
};

Here the count/offset pairing give the queue alignment and the
prio_tc_map gives the mapping from skb->priority to tc.

The hw bit determines if the hardware should configure the count
and offset values. If the hardware bit is set then the operation
will fail if the hardware does not implement the ndo_setup_tc
operation. This is to avoid undetermined states where the hardware
may or may not control the queue mapping. Also minimal bounds
checking is done on the count/offset to verify a queue does not
exceed num_tx_queues and that queue ranges do not overlap. Otherwise
it is left to user policy or hardware configuration to create
useful mappings.

It is expected that hardware QOS schemes can be implemented by
creating appropriate mappings of queues in ndo_tc_setup().

One expected use case is drivers will use the ndo_setup_tc to map
queue ranges onto 802.1Q traffic classes. This provides a generic
mechanism to map network traffic onto these traffic classes and
removes the need for lower layer drivers to know specifics about
traffic types.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-19 23:31:11 -08:00
Octavian Purdila 443457242b net: factorize sync-rcu call in unregister_netdevice_many
Add dev_close_many and dev_deactivate_many to factorize another
sync-rcu operation on the netdevice unregister path.

$ modprobe dummy numdummies=10000
$ ip link set dev dummy* up
$ time rmmod dummy

Without the patch           With the patch

real    0m 24.63s           real    0m 5.15s
user    0m 0.00s            user    0m 0.00s
sys     0m 6.05s            sys     0m 5.14s

Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-16 14:04:44 -08:00