While testing upcoming Yaogong patch (converting out of order queue
into an RB tree), I hit the max reordering level of linux TCP stack.
Reordering level was limited to 127 for no good reason, and some
network setups [1] can easily reach this limit and get limited
throughput.
Allow a new max limit of 300, and add a sysctl to allow admins to even
allow bigger (or lower) values if needed.
[1] Aggregation of links, per packet load balancing, fabrics not doing
deep packet inspections, alternative TCP congestion modules...
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yaogong Wang <wygivan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Several warnings and errors of coding style rules corrected.
Compile tested.
Signed-off-by: Roberto Medina <robertoxmed@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch generalizes commit d6a4a10411 ("tcp: GSO should be TSQ
friendly") to protocols using skb_set_owner_w()
TCP uses its own destructor (tcp_wfree) and needs a more complex scheme
as explained in commit 6ff50cd555 ("tcp: gso: do not generate out of
order packets")
This allows UDP sockets using UFO to get proper backpressure,
thus avoiding qdisc drops and excessive cpu usage.
Here are performance test results (macvlan on vlan):
- Before
# netperf -t UDP_STREAM ...
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 60.00 144096 1224195 1258.56
212992 60.00 51 0.45
Average: CPU %user %nice %system %iowait %steal %idle
Average: all 0.23 0.00 25.26 0.08 0.00 74.43
- After
# netperf -t UDP_STREAM ...
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 60.00 109593 0 957.20
212992 60.00 109593 957.20
Average: CPU %user %nice %system %iowait %steal %idle
Average: all 0.18 0.00 8.38 0.02 0.00 91.43
[edumazet] Rewrote patch and changelog.
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The hardware can automatically generate pause frames when the number
of free buffers drops under a certain threshold, but in order to do this,
the address of the last free buffer needs to be written to a specific
register for each RX queue.
This has to be done in 'gfar_clean_rx_ring' which is called for each
RX queue. In order not to impact performance, by adding a register write
for each incoming packet, this operation is done only when the PAUSE frame
transmission is enabled.
Whenever the link is readjusted, this capability is turned on or off.
Signed-off-by: Matei Pavaluca <matei.pavaluca@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Local flow control options needed in order to resolve the negotiation
are incorrectly calculated.
Previously 'mii_advertise_flowctrl' was called to determine the local advertising
options, but these were determined based on FLOW_CTRL_RX/TX flags which are
never set through ethtool.
The patch simply translates from ethtool flow options to mii flow options.
Signed-off-by: Pavaluca Matei <matei.pavaluca@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The phy device supports 802.3x flow control, but the specific flags are not set
in the phy initialisation code. Flow control flags need to be added to the
supported capabilities of the phydev by the driver.
This is needed in order for ethtool to work ('ethtool -A' code checks for these
flags)
Signed-off-by: Pavaluca Matei <matei.pavaluca@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ERROR: "lockdep_ovsl_is_held" [net/openvswitch/vport-gre.ko] undefined!
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Amir Vadai says:
====================
Mellanox ethernet driver update Oct-27-2014
This patchset introduces some small bug fixes, support in get/set of
vlan offload and get/set/capabilities of the link.
First 7 patches by Saeed, add support in setting/getting link speed and getting
cable capabilities.
Next 2 patches also by Saeed, enable the user to turn rx/tx vlan offloading on
and off.
Jenni fixed a bug in error flow during device initalization.
Ido and Jack fixed some code duplication and errors discovered by static checker.
last patch by me is a fix to make ethtool report the actual rings used by
indirection QP.
Patches were applied and tested against commit 61ed53d ("Merge tag 'ntb-3.18'
of git://github.com/jonmason/ntb")
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Hardware requires the number of rings in indirection table to be a power
of 2. When setting number of channels to a non power of 2 number,
indirection table is using only the closest power of 2 rings.
Report this number in 'ethtool -x' and not the total number of rx rings.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Upon failures, destroy_netdev is called, and spinlocks/works must be
initialized before calling it. Otherwise kernel panic may occur.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is instead of calling the actual implementation of
napi_synchronize, for better encapsulation.
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
clang flagged the following. All are actually cosmetic cleanups, not really bugs:
drivers/net/ethernet/mellanox/mlx4/en_main.c:233:3: warning: Value stored to 'err' is never read
err = -ENOMEM;
^ ~~~~~~~
drivers/net/ethernet/mellanox/mlx4/en_main.c:293:3: warning: Value stored to 'err' is never read
err = -ENOMEM;
drivers/net/ethernet/mellanox/mlx4/en_netdev.c:648:16: warning: Assigned value is garbage or undefined
entry->reg_id = reg_id;
^ ~~~~~~
drivers/net/ethernet/mellanox/mlx4/en_netdev.c:659:2: warning: Function call argument is an uninitialized value
mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);
(NOTE: reg_id is only used in the device-managed flow steering path, in which is it always initialized.
This is not a bug. Cleanup here is therefore cosmetic only).
drivers/net/ethernet/mellanox/mlx4/en_rx.c:122:3: warning: Value stored to 'frag_info' is never read
frag_info = &priv->frag_info[i];
^ ~~~~~~~~~~~~~~~~~~~
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move mlx4_en_reset_config to en_netdev.c as it now serves more general purpose.
Add support for turning OFF/ON the rx/tx vlan offlad.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename mlx4_en_timestamp_config to mlx4_en_reset_config and extend it to support
choosing RX vlan offload configuration.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added Support to set speed or advertised link modes via ethtool:
ethtool -s <ifname> [speed <speed>] [advertise <link modes>]
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- If dev cap MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL is ON, query PTYS register to fill ethtool settings.
else use default values.
- Use autoneg port cap and dev backplane autoneg cap to reprort autoneg interface capbilities.
- Fix typo in mlx4_en_port_state struct field (transciver to transceiver).
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added 100M, 20G and 56G ethtool speed reporting support.
Update mlx4_en_test_speed self test with the new speeds.
Defined new link speeds in include/uapi/linux/ethtool.h:
+#define SPEED_20000 20000
+#define SPEED_40000 40000
+#define SPEED_56000 56000
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adding ACCESS REG mlx4 command and use it to implement Query method for
PTYS (Port Type and Speed Register).
Query and store eth_prot_ctrl dev cap.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added support for get_module_info/get_module_eeprom ethtool support for cable info reading.
Added new cable types enum in include/uapi/linux/ethtool.h for ethtool use.
+#define ETH_MODULE_SFF_8636 0x3
+#define ETH_MODULE_SFF_8636_LEN 256
+#define ETH_MODULE_SFF_8436 0x4
+#define ETH_MODULE_SFF_8436_LEN 256
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added new MAD_IFC command to read cable module info with attribute id (0xFF60).
Update include/linux/mlx4/device.h with function declaration (mlx4_get_module_info)
and the needed defines/enums for future use.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The original motivation for this change was to allow the helper to be used
in files other than actions.c as part of work on an odp select group
action.
It was as pointed out by Thomas Graf that this helper would be best off
living in netlink.h. Furthermore, I think that the generic nature of this
helper means it is best off in netlink.h regardless of if it is used more
than one .c file or not. Thus, I would like it considered independent of
the work on an odp select group action.
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Pravin Shelar <pshelar@nicira.com>
Cc: Andy Zhou <azhou@nicira.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Thomas Graf <tgraf@noironetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not add phy include to the board file but platform_data include
instead.
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Additional code to m88e1145_config_init function to allow the driver to
support SGMII mode.
Signed-off-by: Viet Nga Dao <vndao@altera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The internal and netdev vport remain part of openvswitch.ko. Encap
vports including vxlan, gre, and geneve can be built as separate
modules and are loaded on demand. Modules can be unloaded after use.
Datapath ports keep a reference to the vport module during their
lifetime.
Allows to remove the error prone maintenance of the global list
vport_ops_list.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Varka Bhadram says:
====================
cleanup on resource check
This series removes the duplication of sanity check for
platform_get_resource() return resource. It will be checked
with devm_ioremap_resource()
changes since v2:
- Merge #1 and #2 patches into single patch
- remove the comment
changes since v1:
- remove NULL dereference on resource_size()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
devm_ioremap_resource checks platform_get_resource() return value.
We can remove the duplicate check here.
Signed-off-by: Varka Bhadram <varkab@cdac.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
devm_ioremap_resource checks platform_get_resource() return value.
We can remove the duplicate check here.
Signed-off-by: Varka Bhadram <varkab@cdac.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
devm_ioremap_resource checks platform_get_resource() return value.
We can remove the duplicate check here.
Signed-off-by: Varka Bhadram <varkab@cdac.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
devm_ioremap_resource checks platform_get_resource() return value.
We can remove the duplicate check here.
Signed-off-by: Varka Bhadram <varkab@cdac.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
devm_ioremap_resource checks platform_get_resource() return value.
We can remove the duplicate check here.
Signed-off-by: Varka Bhadram <varkab@cdac.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
This feature is defined in IEEE Std 802.11-2012, 10.23.13. It allows
the AP devices to keep track of the hardware-address-to-IP-address
mapping of the mobile devices within the WLAN network.
The AP will learn this mapping via observing DHCP, ARP, and NS/NA
frames. When a request for such information is made (i.e. ARP request,
Neighbor Solicitation), the AP will respond on behalf of the
associated mobile device. In the process of doing so, the AP will drop
the multicast request frame that was intended to go out to the wireless
medium.
It was recommended at the LKS workshop to do this implementation in
the bridge layer. vxlan.c is already doing something very similar.
The DHCP snooping code will be added to the userspace application
(hostapd) per the recommendation.
This RFC commit is only for IPv4. A similar approach in the bridge
layer will be taken for IPv6 as well.
Signed-off-by: Kyeyoon Park <kyeyoonp@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Let compiler decide what to do with static void __ipxitf_put()
Suggested-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
use %08X instead of %08lX and remove casting.
Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
unsigned char *sha (source) was already in original git version
but was never used.
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
Frank Blaschka says:
====================
s390: network patches for net-next
looks like there was a problem with my previous posting. Hope this time
it will work. Sorry for any inconvenience. The patches are mostly
cleanups and small enhancements for net-next
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Since a single integer value is read from the supplied buffer
use the kstrto functions instead of sscanf.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since a single integer value is read from the supplied buffer
use the kstrto functions instead of sscanf.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Compile the s390 10GB ethernet device driver only when
ETHERNET has been defined in the kernel configuration file.
Right now the qeth device driver is always built regardless
of which network connectivity is active.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes 4 local functions static and removes
the prototypes from the header file.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes trace formatting issues using the
QETH_CARD_TEXT_ macro. The total size of each trace entry
is 8 bytes. Some of the sprintf formats exceed these 8
bytes (for example using abcd:%d and the converted value
needs more than 3 bytes). The solution is to shorten the
text prepending the value or use a different format (%x).
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes some global functions static and removes
the prototypes from the header file.
Also function qeth_query_card_info is not exported anymore,
there is no external user for it, this function should never
have been exported in the first place.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A full Rx ring only requires 1 MiB of memory. This is not enough
memory that it is useful to dynamically scale the number of Rx
requests in the ring based on traffic rates, because:
a) Even the full 1 MiB is a tiny fraction of a typically modern Linux
VM (for example, the AWS micro instance still has 1 GiB of memory).
b) Netfront would have used up to 1 MiB already even with moderate
data rates (there was no adjustment of target based on memory
pressure).
c) Small VMs are going to typically have one VCPU and hence only one
queue.
Keeping the ring full of Rx requests handles bursty traffic better
than trying to converge on an optimal number of requests to keep
filled.
On a 4 core host, an iperf -P 64 -t 60 run from dom0 to a 4 VCPU guest
improved from 5.1 Gbit/s to 5.6 Gbit/s. Gains with more bursty
traffic are expected to be higher.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sowmini Varadhan says:
====================
sunvnet: NAPIfy sunvnet
This patchset converts the sunvnet driver to use the NAPI framework.
Changes since v4 to Patch1:
vnet_event accumulates LDC_EVENT_* bits into rx_event.
vnet_event_napi() unrolls send_events() logic to process all rx_event bits.
Changes since v5:
Patch 1: use net_device.h definition for NAPI_POLL_WEIGHT.
Drop sparclinux changes (patch3) per David Miller feedback
Patch 1 in the series addresses the packet-receive path- all
the vnet_event() processing is moved into NAPI context.
This patch is dependant on the sparc-next commit:
"sparc64: Add vio_set_intr() to enable/disable Rx interrupts"
(sparc commit id ca605b7dd7)
Patch 2 uses RCU to fix race conditions between vnet_port_remove and
paths that access/modify port-related state, such as vnet_start_xmit.
Patch 3 leverages from the NAPIfied Rx path,
dropping superfluous usage of the irqsave/irqrestores on the vio.lock
where possible.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
After the NAPIfication of sunvnet, we no longer need to
synchronize by doing irqsave/restore on vio.lock in the
I/O fastpath.
NAPI ->poll() is non-reentrant, so all RX processing occurs
strictly in a serialized environment. TX reclaim is done in NAPI
context, so the netif_tx_lock can be used to serialize
critical sections between Tx and Rx paths.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A vnet_port_remove could be triggered as a result of an ldm-unbind
operation by the peer, module unload, or other changes to the
inter-vnet-link configuration. When this is concurrent with
vnet_start_xmit(), there are several race sequences possible,
such as
thread 1 thread 2
vnet_start_xmit
-> tx_port_find
spin_lock_irqsave(&vp->lock..)
ret = __tx_port_find(..)
spin_lock_irqrestore(&vp->lock..)
vio_remove -> ..
->vnet_port_remove
spin_lock_irqsave(&vp->lock..)
cleanup
spin_lock_irqrestore(&vp->lock..)
kfree(port)
/* attempt to use ret will bomb */
This patch adds RCU locking for port access so that vnet_port_remove
will correctly clean up port-related state.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Dwight Engen <dwight.engen@oracle.com>
Acked-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move Rx packet procssing to the NAPI poll callback.
Disable VIO interrupt and unconditioanlly go into NAPI
context from vnet_event.
Note that we want to minimize the number of LDC
STOP/START messages sent. Specifically, do not send a STOP
message if vnet_walk_rx does not read all the available descriptors
because of the NAPI budget limitation. Instead, note the end index
as part of port state, and resume from this index when the
next poll callback is triggered.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Raghuram Kothakota <raghuram.kothakota@oracle.com>
Acked-by: Dwight Engen <dwight.engen@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet
Roberto Medina
Toshiaki Makita
Matei Pavaluca
David S. Miller
Amir Vadai
Eugenia Emantayev
Ido Shamay
Jack Morgenstein
Saeed Mahameed
Simon Horman
Sebastian Hesselbarth
Viet Nga Dao
Thomas Graf
Varka Bhadram
Kyeyoon Park
Fabian Frederick
Thomas Richter
David Vrabel
Sowmini Varadhan