Add a description to the vxlan module, helping save the world
from the minions of destruction and confusion.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Somehow I transposed these two while bringing the original statistics
support upstream.
Fixes: 99691c4ac1 ('sfc: Add PTP counters to ethtool stats')
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Shradha Shah <sshah@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
PORT_RESET MC command was NOP in the ef10 firmware hence we are using
ENTITY_RESET to make sure all resource allocations are reset.
Signed-off-by: Shradha Shah <sshah@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When timestamping is enabled, stmmac_tx_clean will call
stmmac_get_tx_hwtstamp to get tx TS.
But the skb can be NULL because the last of its tx_skbuff is NULL
if this packet frame is filled in more than one descriptors.
To fix the issue, change the code:
- Store TX skb to the tx_skbuff[] of frame's last segment.
- Check skb is not NULL in stmmac_get_tx_hwtstamp.
Signed-off-by: Bruce Liu <damuzi000@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Allwinner A20 has an ethernet controller that seems to be
an early version of Synopsys DesignWare MAC 10/100/1000 Universal,
which is supported by the stmmac driver.
Allwinner's GMAC requires setting additional registers in the SoC's
clock control unit.
The exact version of the DWMAC IP that Allwinner uses is unknown,
thus the exact feature set is unknown.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The stmmac driver core allows passing feature flags and callbacks via
platform data. Add a similar stmmac_of_data to pass flags and callbacks
tied to compatible strings. This allows us to extend stmmac with glue
layers for different SoCs.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The snps,phy-addr device tree property is non-standard, and should be
removed in favor of proper phy node support. Remove it from the binding
documents and warn if the property is still used.
Most PHYs respond to address 0, but a few don't, so auto-detect PHY
address by default, to make up for the lack of explicit address selection.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
"snps,force_sf_dma_mode" is documented in stmmac device tree bindings,
but is never handled by the driver.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current .init and .exit callbacks requires access to driver
private data structures. This is not a good seperation and abstraction.
Instead, we add a new .setup callback for allocating private data, and
pass the returned pointer to the other callbacks.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The DWMAC has a reset assert line, which is used on some SoCs. Add an
optional reset control to stmmac driver core.
To support reset control deferred probing, this patch changes the driver
probe function to return the actual error, instead of just -EINVAL.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The stmmac driver does not enable the main clock during the probe phase.
If the clock was not enabled by the boot loader or was disabled by the
kernel, hardware features and the MDIO bus would not be probed properly.
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Code should avoid needless exports, don't export something unless it used.
Make local functions static and remove unused stubs.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previous patch changed prototypes, but forgot functions.
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
net/ipv4/tcp_metrics.c
Overlapping changes between the "don't create two tcp metrics objects
with the same key" race fix in net and the addition of the destination
address in the lookup key in net-next.
Minor overlapping changes in bnx2x driver.
Signed-off-by: David S. Miller <davem@davemloft.net>
This change merges the ixgbevf_tx_map call and the ixgbevf_tx_queue call
into a single function. In order to make room for this setting of cmd_type
and olinfo flags is done in separate functions.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch takes advantage of the dma buffer always being present in the
first descriptor and mapped as single. As such we can call dma_unmap_single
and don't need to check for DMA mapping in ixgbevf_clean_tx_irq().
In addition this patch makes use of the DMA API.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change makes it so that the first tx_buffer structure acts as a
central storage location for most of the info about the skb we are about
to transmit.
In addition this patch makes tx_flags part of the ixgbevf_tx_buffer struct.
This allows us to use the flags directly from the stucture and as result
removes the tx_flags parameter from some functions. Also as a cleanup
mapped_as_page is folded into tx_flags and some unused flags were removed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds counters for tx_restart_queue and tx_timeout_count.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes the Tx/Rx counters for checksum offload.
The Tx counter was never updated and the Rx counter is of limited use.
This is in effort to clean up the counters and make them consistent
with the counters shown by ixgbe.
Also this patch removes some members of the adapter structure that were
never used and shuffles others to reduce number of holes.
before:
/* size: 1568, cachelines: 25, members: 48 */
/* sum members: 1519, holes: 10, sum holes: 43 */
/* padding: 6 */
/* last cacheline: 32 bytes */
after:
/* size: 1480, cachelines: 24, members: 43 */
/* sum members: 1479, holes: 1, sum holes: 1 */
/* last cacheline: 8 bytes */
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves hot-path specific statistics into the ring structure.
This allows us to drop the adapter structure in some functions and should
help with performance.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch cleans up the code by removing the adapter structure as
parameter from multiple functions. The adapter structure was previously
being used to access the dev pointer, but this can also be done via the
ixgbevf_ring structure. This way we can drop the adapter as parameter from
these functions.
This patch also includes small cleanups in some error code paths.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rework the device ID #defines to follow the _DEV_ID convention
already established in the other Intel drivers.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow compiling DCB related files if I40E_DCB option
is supported in the kernel configuration.
DCB is disabled by default.
Signed-off-by: Neerav Parikh <Neerav.Parikh@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Tested-By: Jack Morgan<jack.morgan@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds capability to configure DCB on i40e network
interfaces using Intel XL710 adapter firmware APIs.
By default all VSIs are only enabled for the default traffic
class enabled by firmware for any given PF. The driver would
query the firmware for the traffic classes that are enabled for
the port and reconfigure the LAN VSI to match to the port traffic
class settings. All other VSIs are only enabled for the default
traffic class settings for now.
The driver registers and listens to firmware events that may
require change in the DCB settings. It may reconfigure the VSI
settings based on these events.
This patch exposes IEEE DCBNL interfaces for the i40e driver to
allow any application to query the DCB settings on the adapter.
Signed-off-by: Neerav Parikh <Neerav.Parikh@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-By: Jack Morgan<jack.morgan@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Intel XL710 series of adapters support QoS as per the
IEEE 802.1 DCB (Data Center Bridging) standard.
This is supported in conjuction with:
- Enhanced Transmission Selection (ETS) - IEEE 802.1Qaz
- Priority Flow Control (PFC) - IEEE 802.1Qbb
- DCB eXchange Protocol (DCBX) - IEEE 802.1Qaz
On Intel XL710 adapters DCBX is performed by the adapter
firmware. The firmware runs DCBX in willing mode and configures
the port as per the DCB settings recommended by it's link
partner.
By default in absence of any DCBX; firmware would configure the
port with a single traffic class and all of the port bandwith
will be allocated to that traffic class.
This patch adds functions and calls to support querying and
configuring DCB using firmware APIs.
Signed-off-by: Neerav Parikh <Neerav.Parikh@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-By: Jack Morgan<jack.morgan@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The i40e hardware was generating some inconsistent results
when using current programming methods. This refactor
fixes the inconsistencies that were preventing clean
unloads of the driver, and moves the queues for handling
flow director errors into their own hardware VSI.
This patch also implements a corrected version of the
basic ethtool add ntuple rule, which will disable
the driver's automatic flow programming. A future patch
adds remove/replay/list support for ntuple.
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The FLAG_FDIR_* defines can be renamed to be more descriptive.
This patch is in preparation for the following where the fdir
code is refactored.
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix more whitespace issues, including making some locals declared
in a nicer order.
Also update Copyright string printed when the driver loads.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove a workaround that is no longer necessary and implement
a better understanding of what firmware is returning in the MSI-X
vector count. This makes it so that the driver ends up with the
right amount of queues when using all available MSI-X vectors.
Change-ID: I34e60cc71dcfb1b5412f37df956fedcc49ade187
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Compile testing with higher warning levels found this complaint:
i40e_nvm.c: warning: 'checksum_local' may be used uninitialized in
this function
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit ab7db91705 ("virtio-net: auto-tune mergeable rx buffer size for
improved performance") introduced a virtio-net dependency on EWMA.
The inclusion of EWMA is controlled by CONFIG_AVERAGE. Fix build error
when CONFIG_AVERAGE is not enabled by adding select AVERAGE to
virtio-net's Kconfig entry.
Build failure reported using config make ARCH=s390 defconfig.
Signed-off-by: Michael Dalton <mwdalton@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bump the version number to better match functionality provided with out of
tree driver of the same version.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bump the version number to better match functionality provided with out
of tree driver of the same version.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds braces around the ixgbe_qv_lock_* calls which previously only
had braces around the if portion. Kernel style guidelines for this require
parenthesis around all conditions if they are required around one. In addition
the comment while not illegal C syntax makes the code look wrong at a cursory
glance. This patch corrects the style and adds braces so that the full if-else
block is uniform.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to get correct drop monitor notifications for dropped
packets, we should call kfree_skb() instead of dev_kfree_skb()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If link is IFF_SLAVE, extend link dev netlink attributes to include
slave attributes with new IFLA_SLAVE nest. Add netlink notification
(RTM_NEWLINK) when slave status changes from backup to active, or
visa-versa.
Adds new ndo_get_slave op to net_device_ops to fill skb with IFLA_SLAVE
attributes. Currently only used by bonding driver, but could be
used by other aggregating devices with slaves.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add sub-directory under /sys/class/net/<interface>/slave with
read-only attributes for slave. Directory only appears when
<interface> is a slave.
$ tree /sys/class/net/eth2/slave/
/sys/class/net/eth2/slave/
├── ad_aggregator_id
├── link_failure_count
├── mii_status
├── perm_hwaddr
├── queue_id
└── state
$ cat /sys/class/net/eth2/slave/*
2
0
up
40:02:10:ef:06:01
0
active
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesse Brandeburg reported that commit acaf4e7099 caused a panic
when adding a network namespace while vxlan module was present in
the system:
[<ffffffff814d0865>] vxlan_lowerdev_event+0xf5/0x100
[<ffffffff816e9e5d>] notifier_call_chain+0x4d/0x70
[<ffffffff810912be>] __raw_notifier_call_chain+0xe/0x10
[<ffffffff810912d6>] raw_notifier_call_chain+0x16/0x20
[<ffffffff815d9610>] call_netdevice_notifiers_info+0x40/0x70
[<ffffffff815d9656>] call_netdevice_notifiers+0x16/0x20
[<ffffffff815e1bce>] register_netdevice+0x1be/0x3a0
[<ffffffff815e1dce>] register_netdev+0x1e/0x30
[<ffffffff814cb94a>] loopback_net_init+0x4a/0xb0
[<ffffffffa016ed6e>] ? lockd_init_net+0x6e/0xb0 [lockd]
[<ffffffff815d6bac>] ops_init+0x4c/0x150
[<ffffffff815d6d23>] setup_net+0x73/0x110
[<ffffffff815d725b>] copy_net_ns+0x7b/0x100
[<ffffffff81090e11>] create_new_namespaces+0x101/0x1b0
[<ffffffff81090f45>] copy_namespaces+0x85/0xb0
[<ffffffff810693d5>] copy_process.part.26+0x935/0x1500
[<ffffffff811d5186>] ? mntput+0x26/0x40
[<ffffffff8106a15c>] do_fork+0xbc/0x2e0
[<ffffffff811b7f2e>] ? ____fput+0xe/0x10
[<ffffffff81089c5c>] ? task_work_run+0xac/0xe0
[<ffffffff8106a406>] SyS_clone+0x16/0x20
[<ffffffff816ee689>] stub_clone+0x69/0x90
[<ffffffff816ee329>] ? system_call_fastpath+0x16/0x1b
Apparently loopback device is being registered first and thus we
receive an event notification when vxlan_net is not ready. Hence,
when we call net_generic() and request vxlan_net_id, we seem to
access garbage at that point in time. In setup_net() where we set
up a newly allocated network namespace, we traverse the list of
pernet ops ...
list_for_each_entry(ops, &pernet_list, list) {
error = ops_init(ops, net);
if (error < 0)
goto out_undo;
}
... and loopback_net_init() is invoked first here, so in the middle
of setup_net() we get this notification in vxlan. As currently we
only care about devices that unregister, move access through
net_generic() there. Fix is based on Cong Wang's proposal, but
only changes what is needed here. It sucks a bit as we only work
around the actual cure: right now it seems the only way to check if
a netns actually finished traversing all init ops would be to check
if it's part of net_namespace_list. But that I find quite expensive
each time we go through a notifier callback. Anyway, did a couple
of tests and it seems good for now.
Fixes: acaf4e7099 ("net: vxlan: when lower dev unregisters remove vxlan dev as well")
Reported-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Tested-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit 43dc4e01 Limit number of reported VFs to device
specific value It doesn't work and always returns -EBUSY because VFs are
already enabled.
ixgbe_enable_sriov()
pci_enable_sriov()
sriov_enable()
{
... ..
iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
pci_cfg_access_lock(dev);
... ...
}
pci_sriov_set_totalvfs()
{
... ...
if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
return -EBUSY;
...
}
So should set driver_max_VFs with pci_sriov_set_totalvfs() before
enable VFs with ixgbe_enable_sriov().
V2: revised for net-next tree.
Signed-off-by: Ethan Zhao <ethan.kernel@gmail.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Because ixgbe driver limit the max number of VF
functions could be enabled to 63, so define one macro IXGBE_MAX_VFS_DRV_LIMIT
and cleanup the const 63 in code.
v3: revised for net-next tree.
Signed-off-by: Ethan Zhao <ethan.kernel@gmail.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The r7s72100 SoC includes a fast ethernet controller.
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Return a boolean from sh_eth_is_gether() and refactor it as a one-liner.
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove function qlcnic_enable_eswitch which was defined
but never used in current code.
Compile tested only.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Functions only used in one file should be static.
Found by running make namespacecheck
Compile tested only.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add initial support for per-rx queue sysfs attributes to virtio-net. If
mergeable packet buffers are enabled, adds a read-only mergeable packet
buffer size sysfs attribute for each RX queue.
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 2613af0ed1 ("virtio_net: migrate mergeable rx buffers to page frag
allocators") changed the mergeable receive buffer size from PAGE_SIZE to
MTU-size, introducing a single-stream regression for benchmarks with large
average packet size. There is no single optimal buffer size for all
workloads. For workloads with packet size <= MTU bytes, MTU + virtio-net
header-sized buffers are preferred as larger buffers reduce the TCP window
due to SKB truesize. However, single-stream workloads with large average
packet sizes have higher throughput if larger (e.g., PAGE_SIZE) buffers
are used.
This commit auto-tunes the mergeable receiver buffer packet size by
choosing the packet buffer size based on an EWMA of the recent packet
sizes for the receive queue. Packet buffer sizes range from MTU_SIZE +
virtio-net header len to PAGE_SIZE. This improves throughput for
large packet workloads, as any workload with average packet size >=
PAGE_SIZE will use PAGE_SIZE buffers.
These optimizations interact positively with recent commit
ba27524103 ("virtio-net: coalesce rx frags when possible during rx"),
which coalesces adjacent RX SKB fragments in virtio_net. The coalescing
optimizations benefit buffers of any size.
Benchmarks taken from an average of 5 netperf 30-second TCP_STREAM runs
between two QEMU VMs on a single physical machine. Each VM has two VCPUs
with all offloads & vhost enabled. All VMs and vhost threads run in a
single 4 CPU cgroup cpuset, using cgroups to ensure that other processes
in the system will not be scheduled on the benchmark CPUs. Trunk includes
SKB rx frag coalescing.
net-next w/ virtio_net before 2613af0ed1 (PAGE_SIZE bufs): 14642.85Gb/s
net-next (MTU-size bufs): 13170.01Gb/s
net-next + auto-tune: 14555.94Gb/s
Jason Wang also reported a throughput increase on mlx4 from 22Gb/s
using MTU-sized buffers to about 26Gb/s using auto-tuning.
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The virtio-net driver currently uses netdev_alloc_frag() for GFP_ATOMIC
mergeable rx buffer allocations. This commit migrates virtio-net to use
per-receive queue page frags for GFP_ATOMIC allocation. This change unifies
mergeable rx buffer memory allocation, which now will use skb_refill_frag()
for both atomic and GFP-WAIT buffer allocations.
To address fragmentation concerns, if after buffer allocation there
is too little space left in the page frag to allocate a subsequent
buffer, the remaining space is added to the current allocated buffer
so that the remaining space can be used to store packet data.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It looks like there's no need for those two fields:
- Unless there's a failure for the first refill try, rq->max should be always
equal to the vring size.
- rq->num is only used to determine the condition that we need to do the refill,
we could check vq->num_free instead.
- rq->num was required to be increased or decreased explicitly after each
get/put which results a bad API.
So this patch removes them both to make the code simpler.
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes following sparse warning
davinci_mdio.c:85:27: warning: symbol 'default_pdata' was not declared. Should it be static?
Also makes the default_pdata as a constant.
Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Acked-by: Mugunthan V N <mugunthanvnm@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, if a slave's name change, we just pass it by. However, if the
slave is a current primary_slave, then we end up with using a slave, whose
name != params.primary, for primary_slave. And vice-versa, if we don't have
a primary_slave but have params.primary set - we will not detected a new
primary_slave.
Fix this by catching the NETDEV_CHANGENAME event and setting primary_slave
accordingly. Also, if the primary_slave was changed, issue a reselection of
the active slave, cause the priorities have changed.
Reported-by: Ding Tianhong <dingtianhong@huawei.com>
CC: Ding Tianhong <dingtianhong@huawei.com>
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Acked-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Refinements to cloud support in the Firmware API.
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Check that the descriptors were allocated before trying to dump
them to the logfile. While we're there, de-trick-ify the code
so as to be easier to read and not abusing the types and unions.
Change-ID: I22898f4b22cecda3582d4d9e4018da9cd540f177
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now it catches the NETDEV_CHANGEMTU notification, which is signaled after
the actual change happened on the device, and returns NOTIFY_BAD, so that
the change on the device is reverted.
This might be quite costly and messy, so use the new NETDEV_PRECHANGEMTU to
catch the MTU change before the actual change happens and signal that it's
forbidden to do it.
CC: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ever since this driver was merged the following code was included:
if (skb->len < MISR)
skb->len = MISR;
MISR is defined to 0x3C which is also equivalent to ETH_ZLEN, but use
ETH_ZLEN directly which is exactly what we want to be checking for.
Reported-by: Marc Volovic <marcv@ezchip.com>
Signed-off-by: Florian Fainelli <florian@openwrt.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
On newer and faster machines (Vortex X86DX) using the r6040 driver, it
was noticed that the driver was returning an error during probing traced
down to being the MDIO bus probing and the inability to complete a MDIO
read operation in time. It turns out that the MDIO operations on these
faster machines usually complete after ~2140 iterations which is bigger
than 2048 (MAC_DEF_TIMEOUT) and results in spurious timeouts depending
on the system load.
Update r6040_phy_read() and r6040_phy_write() to include a 1
micro second delay in each busy-looping iteration of the loop which is a
much safer operation than incrementing MAC_DEF_TIMEOUT.
Reported-by: Nils Koehler <nils.koehler@ibt-interfaces.de>
Reported-by: Daniel Goertzen <daniel.goertzen@gmail.com>
Signed-off-by: Florian Fainelli <florian@openwrt.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for IPv6 checksum offload and GSO when those
features are available in the backend.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove unused function vxge_hw_vpath_vid_get
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use 'make namespacecheck' to code that could be declared static.
After that remove code that is not being used.
Compile tested only.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
recently, dm9000 codes have many checkpatch errors and warnings:
WARNING: please, no space before tabs
3: FILE: dm9000.c:3:
+ * ^ICopyright (C) 1997 Sten Wang$
WARNING: please, no space before tabs
5: FILE: dm9000.c:5:
+ * ^IThis program is free software; you can redistribute it and/or$
WARNING: please, no space before tabs
6: FILE: dm9000.c:6:
+ * ^Imodify it under the terms of the GNU General Public License$
WARNING: please, no space before tabs
7: FILE: dm9000.c:7:
+ * ^Ias published by the Free Software Foundation; either version 2$
WARNING: please, no space before tabs
8: FILE: dm9000.c:8:
+ * ^Iof the License, or (at your option) any later version.$
WARNING: please, no space before tabs
10: FILE: dm9000.c:10:
+ * ^IThis program is distributed in the hope that it will be useful,$
WARNING: please, no space before tabs
11: FILE: dm9000.c:11:
+ * ^Ibut WITHOUT ANY WARRANTY; without even the implied warranty of$
WARNING: please, no space before tabs
12: FILE: dm9000.c:12:
+ * ^IMERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the$
WARNING: please, no space before tabs
13: FILE: dm9000.c:13:
+ * ^IGNU General Public License for more details.$
WARNING: do not add new typedefs
97: FILE: dm9000.c:97:
+typedef struct board_info {
ERROR: spaces prohibited around that ':' (ctx:WxV)
113: FILE: dm9000.c:113:
+ unsigned int in_suspend :1;
^
ERROR: spaces prohibited around that ':' (ctx:WxV)
114: FILE: dm9000.c:114:
+ unsigned int wake_supported :1;
^
This patch fixes important errors in it.
Signed-off-by: Barry Song <Baohua.Song@csr.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes: 9d8bf54 ("i40e: associate VMDq queue with VM type")
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Building resource_tracker.o triggers a GCC warning:
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mlx4_HW2SW_SRQ_wrapper':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3202:17: warning: 'srq' may be used uninitialized in this function [-Wmaybe-uninitialized]
atomic_dec(&srq->mtt->ref_count);
^
This is a false positive. But a cleanup of srq_res_start_move_to() can
help GCC here. The code currently uses a switch statement where a plain
if/else would do, since only two of the switch's four cases can ever
occur. Dropping that switch makes the warning go away.
While we're at it, add some missing braces, and convert state to the
correct type.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Building resource_tracker.o triggers a GCC warning:
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mlx4_HW2SW_CQ_wrapper':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3019:16: warning: 'cq' may be used uninitialized in this function [-Wmaybe-uninitialized]
atomic_dec(&cq->mtt->ref_count);
^
This is a false positive. But a cleanup of cq_res_start_move_to() can
help GCC here. The code currently uses a switch statement where an
if/else construct would do too, since only two of the switch's four
cases can ever occur. Dropping that switch makes the warning go away.
While we're at it, add some missing braces.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 7509963c70 (e1000e: Fix a compile flag mis-match for
suspend/resume) moved suspend and resume hooks to be available when
CONFIG_PM is set. However, it can be set even if CONFIG_PM_SLEEP is not set
causing following warnings to be emitted:
drivers/net/ethernet/intel/e1000e/netdev.c:6178:12: warning:
‘e1000_suspend’ defined but not used [-Wunused-function]
drivers/net/ethernet/intel/e1000e/netdev.c:6185:12: warning:
‘e1000_resume’ defined but not used [-Wunused-function]
To fix this make the hooks to be available only when CONFIG_PM_SLEEP is set
and remove CONFIG_PM wrapping from driver ops because this is already
handled by SET_SYSTEM_SLEEP_PM_OPS() and SET_RUNTIME_PM_OPS().
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Dave Ertman <davidx.m.ertman@intel.com>
Cc: Aaron Brown <aaron.f.brown@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In this code we wanted to set the bit in IXGBE_SFF_SOFT_RS_SELECT_MASK to
the value in rs. So we really needed a logical or rather than an and, this
patch makes that change.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch creates new functions for ring initialization,
ixgbevf_configure_tx_ring() and ixgbevf_configure_rx_ring(). The work done
in these function previously was spread between several other functions and
this change should hopefully lead to greater readability and make the code
more like ixgbe. This patch also moves the placement of some older functions
to avoid having to write prototypes. It also promotes a couple of debug
messages to errors.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This will change how we store rings arrays in the adapter sturct.
We use to have a pointer to an array now we will be using an array
of pointers. This will allow us to support multiple queues on
muliple nodes at some point we would be able to reallocate the rings
so that each is on a local node if needed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We had set the pci driver-specific data in ixgbevf_probe() as a type of
struct net_device, so we should use it as netdev in ixgbevf_suspend().
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ixgbevf_qv_disable function used by CONFIG_NET_RX_BUSY_POLL is broken,
because it does not properly set the IXGBEVF_QV_STATE_DISABLED bit, indicating
that the q_vector should be disabled (and preventing future locks from
obtaining the vector). This patch corrects the issue by setting the disable
state.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ixgbe_service_task() is calling ixgbe_reinit_locked() without
the rtnl_lock being held. This is because it is being called
from a worker thread and not a rtnl netlink or dcbnl path.
Add rtnl_{un}lock() semantics. I found this during code review.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In PM_SUSPEND_FREEZE and WOL(Wakeup On Lan) case, when the driver gets a
wakeup event, either the driver or platform specific PM code should notify
the pm core about it, so that the system can wakeup from low power.
In cases where there is no involvement of platform specific PM, it
becomes driver responsibility to notify the PM core to wakeup the
system.
Without this WOL with PM_SUSPEND_FREEZE does not work on STi based SOCs.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds code to restore default pinstate of the pins when it
comes back from low power state. Without this patch the state of the
pins would be unknown and the driver would not work.
This patch also adds code to put the pins in to sleep state when the
driver enters low power state.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In hibernation freeze case the driver just releases the resources like
dma buffers, irqs, unregisters the drivers and during restore it does
register, request the resources. This is not really necessary, as part
of power management all the data structures are intact, all the
previously allocated resources can be used after coming out of low
power.
This patch uses the suspend and resume callbacks for freeze and
restore which initializes the hardware correctly without unregistering
or releasing the resources, this should also help in reducing the time
to restore.
Also this patch fixes a bug in stmmac_pltfr_restore and
stmmac_pltfr_freeze where it tries to get hold of platform data via
dev_get_platdata call, which would return NULL in device tree cases and
the next if statement would crash as there is no NULL check.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver PM resume assumes that the IP is still powered up and the
all the register contents are not disturbed when it comes out of low
power suspend case. This assumption is wrong, basically the driver
should not consider any state of registers after it comes out of low
power. However driver can keep the part of the IP powered up if its a
wake up source. But it can not assume the register state of the IP. Also
its possible that SOC glue layer can take the power off the IP if its
not wake-up source to reduce the power consumption.
This patch re initializes hardware by calling stmmac_hw_setup function in
resume case.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch promotes stmmac_mdio_reset function from static to
non-static, so that power management functions can decide to reset if
the IP comes out from lowe power state specially hibernation cases.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves hardware setup part of the code in stmmac_open to a new
function stmmac_hw_setup, the reason for doing this is to make hw
initialization independent function so that PM functions can re-use it to
re-initialize the IP after returning from low power state.
This will also avoid code duplication across stmmac_resume/restore and
stmmac_open.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves dma resource allocation to a new function
alloc_dma_desc_resources, the reason for moving this to a new function
is to keep the memory allocations in a separate function. One more reason
it to get suspend and hibernation cases working without releasing and
allocating these resources during suspend-resume and freeze-restore
cases.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes gpio_free for reset line of the phy, driver stores
the gpio number in its private data-structure to use in future. As the
driver uses this pin in future this pin should not be freed.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support to "max-speed" property which is a standard
Ethernet device tree property. max-speed specifies maximum speed
(specified in megabits per second) supported the device.
Depending on the clocking schemes some of the boards can only support
few link speeds, so having a way to limit the link speed in the mac
driver would allow such setups to work reliably.
Without this patch there is no way to tell the driver to limit the
link speed.
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function return parameter is not used in mvneta_tx_done_gbe(),
where the function is called. This patch makes the function return
void.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
mvneta_tx_done_gbe() return value and third parameter are no more
used. This patch changes the function prototype and removes a useless
variable where the function is called.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
calling dma_map_single()/dma_unmap_single() is quite expensive compared
to copying a small packet. So let's copy short frames and keep the buffers
mapped. We set the limit to 256 bytes which seems to give good results both
on the XP-GP board and on the AX3/4.
The Rx small packet rate increased by 16.4% doing this, from 486kpps to
573kpps. It is worth noting that even the call to the function
dma_sync_single_range_for_cpu() is expensive (300 ns) although less
than dma_unmap_single(). Without it, the packet rate raises to 711kpps
(+24% more). Thus on systems where coherency from device to CPU is
guaranteed by a snoop control unit, this patch should provide even more
gains, and probably rx_copybreak could be increased.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make use of build_skb() to allocate frags on the RX path. When frag size
is lower than a page size, we can use netdev_alloc_frag(), and we fall back
to kmalloc() for larger sizes. The frag size is stored into the mvneta_port
struct. The alloc/free functions check the frag size to decide what alloc/
free method to use. MTU changes are safe because the MTU change function
stops the device and clears the queues before applying the change.
With this patch, I observed a reproducible 2% performance improvement on
HTTP-based benchmarks, and 5% on small packet RX rate.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, the mvneta driver tries to prefetch the current Rx
descriptor during read. Tests have shown that prefetching the
next one instead increases general performance by about 1% on
HTTP traffic.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
At several places, we already know the value of the rx status but
we call functions which dereference the pointer again to get it
and don't need the descriptor for anything else. Simplify this
task by replacing the rx desc pointer by the status word itself.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make mvneta_rxq_fill() use mvneta_rx_refill() instead of using
duplicate code.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, mvneta_txq_bufs_free() calls mvneta_tx_done_policy() with
a non-null cause to retrieve the pointer to the next queue to process.
There are useless tests on the return queue number and on the pointer,
all of which are well defined within a known limited set. This code
path is fast, although not critical. Removing 3 tests here that the
compiler could not optimize (verified) is always desirable.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Right now the mvneta driver doesn't handle Tx IRQ, and relies on two
mechanisms to flush Tx descriptors : a flush at the end of mvneta_tx()
and a timer. If a burst of packets is emitted faster than the device
can send them, then the queue is stopped until next wake-up of the
timer 10ms later. This causes jerky output traffic with bursts and
pauses, making it difficult to reach line rate with very few streams.
A test on UDP traffic shows that it's not possible to go beyond 134
Mbps / 12 kpps of outgoing traffic with 1500-bytes IP packets. Routed
traffic tends to observe pauses as well if the traffic is bursty,
making it even burstier after the wake-up.
It seems that this feature was inherited from the original driver but
nothing there mentions any reason for not using the interrupt instead,
which the chip supports.
Thus, this patch enables Tx interrupts and removes the timer. It does
the two at once because it's not really possible to make the two
mechanisms coexist, so a split patch doesn't make sense.
First tests performed on a Mirabox (Armada 370) show that less CPU
seems to be used when sending traffic. One reason might be that we now
call the mvneta_tx_done_gbe() with a mask indicating which queues have
been done instead of looping over all of them.
The same UDP test above now happily reaches 987 Mbps / 87.7 kpps.
Single-stream TCP traffic can now more easily reach line rate. HTTP
transfers of 1 MB objects over a single connection went from 730 to
840 Mbps. It is even possible to go significantly higher (>900 Mbps)
by tweaking tcp_tso_win_divisor.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Cc: Arnaud Ebalard <arno@natisbad.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Marvell has not published the chip's datasheet yet, so it's very hard
to find the relevant bits to manipulate to change the IRQ behaviour.
Fortunately, these bits are described in the proprietary LSP patch set
which is publicly available here :
http://www.plugcomputer.org/downloads/mirabox/
So let's put them back in the driver in order to reduce the burden of
current and future maintenance.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a queue timeout is reported, we can oops because of some
schedules while the caller is atomic, as shown below :
mvneta d0070000.ethernet eth0: tx timeout
BUG: scheduling while atomic: bash/1528/0x00000100
Modules linked in: slhttp_ethdiv(C) [last unloaded: slhttp_ethdiv]
CPU: 2 PID: 1528 Comm: bash Tainted: G WC 3.13.0-rc4-mvebu-nf #180
[<c0011bd9>] (unwind_backtrace+0x1/0x98) from [<c000f1ab>] (show_stack+0xb/0xc)
[<c000f1ab>] (show_stack+0xb/0xc) from [<c02ad323>] (dump_stack+0x4f/0x64)
[<c02ad323>] (dump_stack+0x4f/0x64) from [<c02abe67>] (__schedule_bug+0x37/0x4c)
[<c02abe67>] (__schedule_bug+0x37/0x4c) from [<c02ae261>] (__schedule+0x325/0x3ec)
[<c02ae261>] (__schedule+0x325/0x3ec) from [<c02adb97>] (schedule_timeout+0xb7/0x118)
[<c02adb97>] (schedule_timeout+0xb7/0x118) from [<c0020a67>] (msleep+0xf/0x14)
[<c0020a67>] (msleep+0xf/0x14) from [<c01dcbe5>] (mvneta_stop_dev+0x21/0x194)
[<c01dcbe5>] (mvneta_stop_dev+0x21/0x194) from [<c01dcfe9>] (mvneta_tx_timeout+0x19/0x24)
[<c01dcfe9>] (mvneta_tx_timeout+0x19/0x24) from [<c024afc7>] (dev_watchdog+0x18b/0x1c4)
[<c024afc7>] (dev_watchdog+0x18b/0x1c4) from [<c0020b53>] (call_timer_fn.isra.27+0x17/0x5c)
[<c0020b53>] (call_timer_fn.isra.27+0x17/0x5c) from [<c0020cad>] (run_timer_softirq+0x115/0x170)
[<c0020cad>] (run_timer_softirq+0x115/0x170) from [<c001ccb9>] (__do_softirq+0xbd/0x1a8)
[<c001ccb9>] (__do_softirq+0xbd/0x1a8) from [<c001cfad>] (irq_exit+0x61/0x98)
[<c001cfad>] (irq_exit+0x61/0x98) from [<c000d4bf>] (handle_IRQ+0x27/0x60)
[<c000d4bf>] (handle_IRQ+0x27/0x60) from [<c000843b>] (armada_370_xp_handle_irq+0x33/0xc8)
[<c000843b>] (armada_370_xp_handle_irq+0x33/0xc8) from [<c000fba9>] (__irq_usr+0x49/0x60)
Ben Hutchings attempted to propose a better fix consisting in using a
scheduled work for this, but while it fixed this panic, it caused other
random freezes and panics proving that the reset sequence in the driver
is unreliable and that additional fixes should be investigated.
When sending multiple streams over a link limited to 100 Mbps, Tx timeouts
happen from time to time, and the driver correctly recovers only when the
function is disabled.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stats writers are mvneta_rx() and mvneta_tx(). They don't lock anything
when they update the stats, and as a result, it randomly happens that
the stats freeze on SMP if two updates happen during stats retrieval.
This is very easily reproducible by starting two HTTP servers and binding
each of them to a different CPU, then consulting /proc/net/dev in loops
during transfers, the interface should immediately lock up. This issue
also randomly happens upon link state changes during transfers, because
the stats are collected in this situation, but it takes more attempts to
reproduce it.
The comments in netdevice.h suggest using per_cpu stats instead to get
rid of this issue.
This patch implements this. It merges both rx_stats and tx_stats into
a single "stats" member with a single syncp. Both mvneta_rx() and
mvneta_rx() now only update the a single CPU's counters.
In turn, mvneta_get_stats64() does the summing by iterating over all CPUs
to get their respective stats.
With this change, stats are still correct and no more lockup is encountered.
Note that this bug was present since the first import of the mvneta
driver. It might make sense to backport it to some stable trees. If
so, it depends on "d33dc73 net: mvneta: increase the 64-bit rx/tx stats
out of the hot path".
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Better count packets and bytes in the stack and on 32 bit then
accumulate them at the end for once. This saves two memory writes
and two memory barriers per packet. The incoming packet rate was
increased by 4.7% on the Openblocks AX3 thanks to this.
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Gregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Arnaud Ebalard <arno@natisbad.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch will also change behavior of rx_beacons statistic.
Instead of collecting all received beacons, it will collect only
ours. This, IMO make more sense, since for troubleshooting we will
need to know count of our beacons, or both.
Signed-off-by: Oleksij Rempel <linux@rempel-privat.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
this function is used by most ath driver, so it can be moved here.
Signed-off-by: Oleksij Rempel <linux@rempel-privat.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
While registering the driver with cfg80211, update the threshold
value and retry limit to cfg80211.
Signed-off-by: Ujjal Roy <royujjal@gmail.com>
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
bit 14 is actually reserved and bit 12 & 13 should be used for
11ac capability in fw_cap_info.
Cc: <stable@vger.kernel.org> # 3.9+
Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
