linux.git/net/core/net-sysfs.c, branch v2.6.38

net: use NUMA_NO_NODE instead of the magic number -1

2010-12-16T21:16:06+00:00

Signed-off-by: Changli Gao 
Signed-off-by: David S. Miller

net sched: use xps information for qdisc NUMA affinity

2010-12-01T20:47:42+00:00

Allocate qdisc memory according to NUMA properties of cpus included in
xps map.

To be effective, qdisc should be (re)setup after changes
of /sys/class/net/eth/queues/tx-/xps_cpus

I added a numa_node field in struct netdev_queue, containing NUMA node
if all cpus included in xps_cpus share same node, else -1.

Signed-off-by: Eric Dumazet 
Cc: Ben Hutchings 
Cc: Tom Herbert 
Signed-off-by: David S. Miller

xps: add __rcu annotations

2010-11-29T17:43:13+00:00

Avoid sparse warnings : add __rcu annotations and use
rcu_dereference_protected() where necessary.

Signed-off-by: Eric Dumazet 
Cc: Tom Herbert 
Signed-off-by: David S. Miller

xps: NUMA allocations for per cpu data

2010-11-29T17:43:13+00:00

store_xps_map() allocates maps that are used by single cpu, it makes
sense to use NUMA allocations.

Signed-off-by: Eric Dumazet 
Cc: Tom Herbert 
Signed-off-by: David S. Miller

xps: Add CONFIG_XPS

2010-11-29T02:24:14+00:00

This patch adds XPS_CONFIG option to enable and disable XPS.  This is
done in the same manner as RPS_CONFIG.  This is also fixes build
failure in XPS code when SMP is not enabled.

Signed-off-by: Tom Herbert 
Signed-off-by: David S. Miller

xps: Transmit Packet Steering

2010-11-24T19:44:20+00:00

This patch implements transmit packet steering (XPS) for multiqueue
devices.  XPS selects a transmit queue during packet transmission based
on configuration.  This is done by mapping the CPU transmitting the
packet to a queue.  This is the transmit side analogue to RPS-- where
RPS is selecting a CPU based on receive queue, XPS selects a queue
based on the CPU (previously there was an XPS patch from Eric
Dumazet, but that might more appropriately be called transmit completion
steering).

Each transmit queue can be associated with a number of CPUs which will
use the queue to send packets.  This is configured as a CPU mask on a
per queue basis in:

/sys/class/net/eth/queues/tx-/xps_cpus

The mappings are stored per device in an inverted data structure that
maps CPUs to queues.  In the netdevice structure this is an array of
num_possible_cpu structures where each structure holds and array of
queue_indexes for queues which that CPU can use.

The benefits of XPS are improved locality in the per queue data
structures.  Also, transmit completions are more likely to be done
nearer to the sending thread, so this should promote locality back
to the socket on free (e.g. UDP).  The benefits of XPS are dependent on
cache hierarchy, application load, and other factors.  XPS would
nominally be configured so that a queue would only be shared by CPUs
which are sharing a cache, the degenerative configuration woud be that
each CPU has it's own queue.

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.

bnx2x on 16 core AMD
   XPS (16 queues, 1 TX queue per CPU)  1234K at 100% CPU
   No XPS (16 queues)                   996K at 100% CPU

Signed-off-by: Tom Herbert 
Signed-off-by: David S. Miller

net: zero kobject in rx_queue_release

2010-11-17T20:27:46+00:00

netif_set_real_num_rx_queues() can decrement and increment
the number of rx queues. For example ixgbe does this as
features and offloads are toggled. Presumably this could
also happen across down/up on most devices if the available
resources changed (cpu offlined).

The kobject needs to be zero'd in this case so that the
state is not preserved across kobject_put()/kobject_init_and_add().

This resolves the following error report.

ixgbe 0000:03:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
kobject (ffff880324b83210): tried to init an initialized object, something is seriously wrong.
Pid: 1972, comm: lldpad Not tainted 2.6.37-rc18021qaz+ #169
Call Trace:
 [] kobject_init+0x3a/0x83
 [] kobject_init_and_add+0x23/0x57
 [] ? mark_lock+0x21/0x267
 [] net_rx_queue_update_kobjects+0x63/0xc6
 [] netif_set_real_num_rx_queues+0x5f/0x78
 [] ixgbe_set_num_queues+0x1c6/0x1ca [ixgbe]
 [] ixgbe_init_interrupt_scheme+0x1e/0x79c [ixgbe]
 [] ixgbe_dcbnl_set_state+0x167/0x189 [ixgbe]

Signed-off-by: John Fastabend 
Signed-off-by: David S. Miller

net: Simplify RX queue allocation

2010-11-15T18:57:28+00:00

This patch move RX queue allocation to alloc_netdev_mq and freeing of
the queues to free_netdev (symmetric to TX queue allocation).  Each
kobject RX queue takes a reference to the queue's device so that the
device can't be freed before all the kobjects have been released-- this
obviates the need for reference counts specific to RX queues.

Signed-off-by: Tom Herbert 
Signed-off-by: David S. Miller

rps: add __rcu annotations

2010-10-25T21:18:27+00:00

Add __rcu annotations to :
	(struct netdev_rx_queue)->rps_map
	(struct netdev_rx_queue)->rps_flow_table
	struct rps_sock_flow_table *rps_sock_flow_table;

And use appropriate rcu primitives.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: Fix rxq ref counting

2010-10-08T21:34:32+00:00

The rx->count reference is used to track reference counts to the
number of rx-queue kobjects created for the device.  This patch
eliminates initialization of the counter in netif_alloc_rx_queues
and instead increments the counter each time a kobject is created.
This is now symmetric with the decrement that is done when an object is
released.

Signed-off-by: Tom Herbert 
Acked-by: Eric Dumazet 
Signed-off-by: David S. Miller