reimplement softnet_data.output_queue as a FIFO queue to keep the
fairness among the qdiscs rescheduled.
Signed-off-by: NChangli Gao <xiaosuo@gmail.com>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>
----
 include/linux/netdevice.h |    1 +
 net/core/dev.c            |   22 ++++++++++++----------
 2 files changed, 13 insertions(+), 10 deletions(-)
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

struct softnet_data holds many queues, so consistent use "sd" name
instead of "queue" is better.

Adds a rps_ipi_queued() helper to cleanup enqueue_to_backlog()

Adds a _and_irq_disable suffix to net_rps_action() name, as David
suggested.

incr_input_queue_head() becomes input_queue_head_incr()
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net_rps_action() is a bit expensive on NR_CPUS=64..4096 kernels, even if
RPS is not active.

Tom Herbert used two bitmasks to hold information needed to send IPI,
but a single LIFO list seems more appropriate.

Move all RPS logic into net_rps_action() to cleanup net_rx_action() code
(remove two ifdefs)

Move rps_remote_softirq_cpus into softnet_data to share its first cache
line, filling an existing hole.

In a future patch, we could call net_rps_action() from process_backlog()
to make sure we send IPI before handling this cpu backlog.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch implements receive flow steering (RFS).  RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running.  RFS is an
extension of Receive Packet Steering (RPS).

The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure.  The rxhash is passed in skb's received on
the connection from netif_receive_skb.  For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.

The convolution of the simple approach is that it would potentially
allow OOO packets.  If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.

To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.

rps_sock_table is a global hash table.  Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.

rps_dev_flow_table is specific to each device queue.  Each entry
contains a CPU and a tail queue counter.  The CPU is the "current"
CPU for a matching flow.  The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.

Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length.  When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.

And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted.  When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:

- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table.  This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.

Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality.  2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.

This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.

There are two configuration parameters for RFS.  The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue.  Both are rounded to power of two.

The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).

The benefits of RFS are dependent on cache hierarchy, application
load, and other factors.  On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation.  However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.

Below are some benchmark results which show the potential benfit of
this patch.  The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp.  The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.

e1000e on 8 core Intel
   No RFS or RPS		104K tps at 30% CPU
   No RFS (best RPS config):    290K tps at 63% CPU
   RFS				303K tps at 61% CPU

RPC test	tps	CPU%	50/90/99% usec latency	Latency StdDev
  No RFS/RPS	103K	48%	757/900/3185		4472.35
  RPS only:	174K	73%	415/993/2468		491.66
  RFS		223K	73%	379/651/1382		315.61
Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NChangli Gao <xiaosuo@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

skb_bond_should_drop() is too big to be inlined.

This patch reduces kernel text size, and its compilation time as well
(shrinking include/linux/netdevice.h)
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The first argument should be called ha, not mclist.  All callers use the
name "ha", but if they used a different name, there would be a compile
error.
Signed-off-by: NPavel Roskin <proski@gnu.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Converts the list and the core manipulating with it to be the same as uc_list.

+uses two functions for adding/removing mc address (normal and "global"
 variant) instead of a function parameter.
+removes dev_mcast.c completely.
+exposes netdev_hw_addr_list_* macros along with __hw_addr_* functions for
 manipulation with lists on a sandbox (used in bonding and 80211 drivers)
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

+little renaming of unicast functions to be smooth with multicast ones
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This adds ethtool and device feature flag to allow control
of receive hashing offload.
Signed-off-by: NStephen Hemminger <shemminger@vyatta.com>
Acked-by: NJeff Garzik <jgarzik@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RPS currently depends on SMP and SYSFS

Adding a CONFIG_RPS makes sense in case this requirement changes in the
future. This patch saves about 1500 bytes of kernel text in case SMP is
on but SYSFS is off.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After the type change, addresses in unicast and multicast lists wouldn't make
sense, not to mention possible different lenghts. So flush both lists here.

Note "dev_addr_discard" will be very soon replaced by "dev_mc_flush" (once
mc_list conversion will be done).
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When doing "ifenslave -d bond0 eth0", there is chance to get NULL
dereference in netif_receive_skb(), because dev->master suddenly becomes
NULL after we tested it.

We should use ACCESS_ONCE() to avoid this (or rcu_dereference())
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds the possibility to refuse the bonding type change for
other subsystems (such as for example bridge, vlan, etc.)
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NTom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch implements software receive side packet steering (RPS).  RPS
distributes the load of received packet processing across multiple CPUs.

Problem statement: Protocol processing done in the NAPI context for received
packets is serialized per device queue and becomes a bottleneck under high
packet load.  This substantially limits pps that can be achieved on a single
queue NIC and provides no scaling with multiple cores.

This solution queues packets early on in the receive path on the backlog queues
of other CPUs.   This allows protocol processing (e.g. IP and TCP) to be
performed on packets in parallel.   For each device (or each receive queue in
a multi-queue device) a mask of CPUs is set to indicate the CPUs that can
process packets. A CPU is selected on a per packet basis by hashing contents
of the packet header (e.g. the TCP or UDP 4-tuple) and using the result to index
into the CPU mask.  The IPI mechanism is used to raise networking receive
softirqs between CPUs.  This effectively emulates in software what a multi-queue
NIC can provide, but is generic requiring no device support.

Many devices now provide a hash over the 4-tuple on a per packet basis
(e.g. the Toeplitz hash).  This patch allow drivers to set the HW reported hash
in an skb field, and that value in turn is used to index into the RPS maps.
Using the HW generated hash can avoid cache misses on the packet when
steering it to a remote CPU.

The CPU mask is set on a per device and per queue basis in the sysfs variable
/sys/class/net/<device>/queues/rx-<n>/rps_cpus.  This is a set of canonical
bit maps for receive queues in the device (numbered by <n>).  If a device
does not support multi-queue, a single variable is used for the device (rx-0).

Generally, we have found this technique increases pps capabilities of a single
queue device with good CPU utilization.  Optimal settings for the CPU mask
seem to depend on architectures and cache hierarcy.  Below are some results
running 500 instances of netperf TCP_RR test with 1 byte req. and resp.
Results show cumulative transaction rate and system CPU utilization.

e1000e on 8 core Intel
   Without RPS: 108K tps at 33% CPU
   With RPS:    311K tps at 64% CPU

forcedeth on 16 core AMD
   Without RPS: 156K tps at 15% CPU
   With RPS:    404K tps at 49% CPU

bnx2x on 16 core AMD
   Without RPS  567K tps at 61% CPU (4 HW RX queues)
   Without RPS  738K tps at 96% CPU (8 HW RX queues)
   With RPS:    854K tps at 76% CPU (4 HW RX queues)

Caveats:
- The benefits of this patch are dependent on architecture and cache hierarchy.
Tuning the masks to get best performance is probably necessary.
- This patch adds overhead in the path for processing a single packet.  In
a lightly loaded server this overhead may eliminate the advantages of
increased parallelism, and possibly cause some relative performance degradation.
We have found that masks that are cache aware (share same caches with
the interrupting CPU) mitigate much of this.
- The RPS masks can be changed dynamically, however whenever the mask is changed
this introduces the possibility of generating out of order packets.  It's
probably best not change the masks too frequently.
Signed-off-by: NTom Herbert <therbert@google.com>

 include/linux/netdevice.h |   32 ++++-
 include/linux/skbuff.h    |    3 +
 net/core/dev.c            |  335 +++++++++++++++++++++++++++++++++++++--------
 net/core/net-sysfs.c      |  225 ++++++++++++++++++++++++++++++-
 net/core/skbuff.c         |    2 +
 5 files changed, 538 insertions(+), 59 deletions(-)
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Split dev_change_flags() into two functions: __dev_change_flags() to
perform the actual changes and __dev_notify_flags() to invoke netdevice
notifiers. This will be used by rtnl_link to defer netlink notifications
until the device has been fully configured.

This changes ordering of some operations, in particular:

- netlink notifications are sent after all changes have been performed.
  As a side effect this surpresses one unnecessary netlink message when
  the IFF_UP and other flags are changed simultaneously.

- The NETDEV_UP/NETDEV_DOWN and NETDEV_CHANGE notifiers are invoked
  after all changes have been performed. Their relative is unchanged.

- net_dmaengine_put() is invoked before the NETDEV_DOWN notifier instead
  of afterwards. This should not make any difference since both RX and TX
  are already shut down at this point.
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In order to support specifying device flags during device creation,
we must be able to roll back device registration in case setting the
flags fails without sending any notifications related to the device
to userspace.

This patch changes rollback_registered_many() and register_netdevice()
to manually send netlink notifications for devices not handled by
rtnl_link and allows to defer notifications for devices handled by
rtnl_link until setup is complete.
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In "wireless: remove WLAN_80211 and WLAN_PRE80211 from Kconfig" I
inadvertantly missed a line in include/linux/netdevice.h.  I thereby
effectively reverted "net: Set LL_MAX_HEADER properly for wireless." by
accident. :-(  Now we should check there for CONFIG_WLAN instead.
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Reported-by: NChristoph Egger <siccegge@stud.informatik.uni-erlangen.de>
Cc: stable@kernel.org

Add netdev ops for configuring SR-IOV VF devices through the PF driver.
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add macros to test a private structure for msg_enable bits
and the netif_msg_##bit to test and call netdev_printk if set

Simplifies logic in callers and adds message logging consistency
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These netdev_printk routines take a struct net_device * and emit
dev_printk logging messages adding "%s: " ... netdev->dev.parent
to the dev_printk format and arguments.

This can create some uniformity in the output message log.

These helpers should not be used until a successful alloc_netdev.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patchset enables the ethtool layer to program n-tuple
filters to an underlying device.  The idea is to allow capable
hardware to have static rules applied that can assist steering
flows into appropriate queues.

Hardware that is known to support these types of filters today
are ixgbe and niu.
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces the similar helpers as those already done for uc list.
However multicast lists are no list_head lists but "mademanually". The three
macros added by this patch will make the transition of mc_list to list_head
smooth in two steps:

1) convert all drivers to use these macros (with the original iterator of type
   "struct dev_mc_list")
2) once all drivers are converted, convert list type and iterators to "struct
   netdev_hw_addr" in one patch.

>From now on, drivers can (and should) use "netdev_for_each_mc_addr" to iterate
over the addresses with iterator of type "struct netdev_hw_addr". Also macros
"netdev_mc_count" and "netdev_mc_empty" to read list's length. This is the state
which should be reached in all drivers.
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the vlan and macvlan drivers, the start_xmit function forwards
data to the dev_queue_xmit function for another device, which may
potentially belong to a different namespace.

To make sure that classification stays within a single namespace,
this resets the potentially critical fields.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces three macros to work with uc list from net drivers.
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After netdev_ops compat code HAVE_* macros aren't needed, in fact
they _will_ result in compile breakage for out of tree drivers.
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Nothing outside of net/core/dev.c uses it.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Provide common routine for the transition of operational state for a leaf
device during a root device transition.
Signed-off-by: NPatrick Mullaney <pmullaney@novell.com>
Acked-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I will need this shortly to implement network namespace shutdown
batching.  For sanity sake network devices should be removed in
the reverse order they were created in.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The veth driver contains code to forward an skb
from the start_xmit function of one network
device into the receive path of another device.

Moving that code into a common location lets us
reuse the code for direct forwarding of data
between macvlan ports, and possibly in other
drivers.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Acked-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Herbert Xu a écrit :
> On Tue, Nov 17, 2009 at 04:26:04AM -0800, David Miller wrote:
>> Really, the link watch stuff is just due for a redesign.  I don't
>> think a simple hack is going to cut it this time, sorry Eric :-)
>
> I have no objections against any redesigns, but since the only
> caller of linkwatch_forget_dev runs in process context with the
> RTNL, it could also legally emit those events.

Thanks guys, here an updated version then, before linkwatch surgery ?

In this version, I force the event to be sent synchronously.

[PATCH net-next-2.6] linkwatch: linkwatch_forget_dev() to speedup device dismantle

time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105

real	0m0.266s
user	0m0.000s
sys	0m0.001s

real	0m0.770s
user	0m0.000s
sys	0m0.000s

real	0m1.022s
user	0m0.000s
sys	0m0.000s

One problem of current schem in vlan dismantle phase is the
holding of device done by following chain :

vlan_dev_stop() ->
	netif_carrier_off(dev) ->
		linkwatch_fire_event(dev) ->
			dev_hold() ...

And __linkwatch_run_queue() runs up to one second later...

A generic fix to this problem is to add a linkwatch_forget_dev() method
to unlink the device from the list of watched devices.

dev->link_watch_next becomes dev->link_watch_list (and use a bit more memory),
to be able to unlink device in O(1).

After patch :
time ip link del eth3.103 ; time ip link del eth3.104 ; time ip link del eth3.105

real    0m0.024s
user    0m0.000s
sys     0m0.000s

real    0m0.032s
user    0m0.000s
sys     0m0.001s

real    0m0.033s
user    0m0.000s
sys     0m0.000s
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some drivers ndo_get_stats() method need to perform txqueue stats folding.

Move folding from dev_get_stats() to a new dev_txq_stats_fold() function
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Recent changes in the TX error propagation require additional checking
and masking of values returned from hard_start_xmit(), mainly to
separate cases where skb was consumed. This aim can be simplified by
changing the order of NETDEV_TX and NET_XMIT codes, because the latter
are treated similarly to negative (ERRNO) values.

After this change much simpler dev_xmit_complete() is also used in
sch_direct_xmit(), so it is moved to netdevice.h.

Additionally NET_RX definitions in netdevice.h are moved up from
between TX codes to avoid confusion while reading the TX comment.
Signed-off-by: NJarek Poplawski <jarkao2@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No longer need read_lock(&dev_base_lock), use RCU instead.
We also can avoid taking references on inet6_dev structs.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the ->ndo_hard_start_xmit() callbacks are only permitted to return
one of the NETDEV_TX codes. This prevents any kind of error propagation for
virtual devices, like queue congestion of the underlying device in case of
layered devices, or unreachability in case of tunnels.

This patches changes the NET_XMIT codes to avoid clashes with the NETDEV_TX
codes and changes the two callers of dev_hard_start_xmit() to expect either
errno codes, NET_XMIT codes or NETDEV_TX codes as return value.

In case of qdisc_restart(), all non NETDEV_TX codes are mapped to NETDEV_TX_OK
since no error propagation is possible when using qdiscs. In case of
dev_queue_xmit(), the error is propagated upwards.
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This adds an RCU macro for continuing search, useful for some
network devices like vlan.
Signed-off-by: NStephen Hemminger <shemminger@vyatta.com>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This cleanup patch puts struct/union/enum opening braces,
in first line to ease grep games.

struct something
{

becomes :

struct something {
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds RCU management to the list of netdevices.

Convert some for_each_netdev() users to RCU version, if
it can avoid read_lock-ing dev_base_lock

Ie:
	read_lock(&dev_base_loack);
	for_each_netdev(net, dev)
		some_action();
	read_unlock(&dev_base_lock);

becomes :

	rcu_read_lock();
	for_each_netdev_rcu(net, dev)
		some_action();
	rcu_read_unlock();
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some workloads hit dev_base_lock rwlock pretty hard.
We can use RCU lookups to avoid touching this rwlock
(and avoid touching netdevice refcount)

netdevices are already freed after a RCU grace period, so this patch
adds no penalty at device dismantle time.

However, it adds a synchronize_rcu() call in dev_change_name()
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>