Removed oom task unconditional rescheduling every 250ms and created per
queue oom work queue for refilling buffers.
The oom task refills only if the available descriptors is fallen to 64.
There will be no packets coming in after hitting this level. So NAPI will
not run until oom task refills the buffers.
Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: Derek Chickles <derek.chickles@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Control packets are processed in tasklet when interface is down and in
NAPI when interface is up. So tasklet can be disabled when interface up
and re-enabled when interface is down.
Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: Derek Chickles <derek.chickles@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
dma_zalloc_coherent() now crashes if no dev pointer is given.
Add a dev pointer to the ltq_dma_channel structure and fill it in the
driver using it.
This fixes a bug introduced in kernel 4.19.
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
debugfs_remove_recursive has taken IS_ERR_OR_NULL into account. So just
remove the condition check before debugfs_remove_recursive.
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
debugfs_remove_recursive has taken the IS_ERR_OR_NULL into account. Just
remove the unnecessary condition check.
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The "pause" variable is only initialized on BCM5301x.
Fixes: 5e004460f8 ("net: dsa: b53: Add helper to set link parameters")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the incorrect WR_HDR field which can cause a misinterpretation
of ABORT CPL by ULDs, such as iw_cxgb4.
Fixes: a3cdaa69e4 ("cxgb4: Adds CPL support for Shared Receive Queues")
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Quectel EP06 (and EM06/EG06) supports dynamic configuration of USB
interfaces, without the device changing VID/PID or configuration number.
When the configuration is updated and interfaces are added/removed, the
interface numbers change. This means that the current code for matching
EP06 does not work.
This patch removes the current EP06 interface number match, and replaces
it with a match on class, subclass and protocol. Unfortunately, matching
on those three alone is not enough, as the diag interface exports the
same values as QMI. The other serial interfaces + adb export different
values and do not match.
The diag interface only has two endpoints, while the QMI interface has
three. I have therefore added a check for number of interfaces, and we
ignore the interface if the number of endpoints equals two.
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Dan Williams <dcbw@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch updates license to use SPDX-License-Identifier
instead of verbose license text.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eliminate the assumption that SKBs and SKB list heads can
be cast to eachother in SKB list handling code.
Signed-off-by: David S. Miller <davem@davemloft.net>
Eliminate code which assumes that SKBs and skb_queue_head objects
can be cast to eachother during list processing.
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of direct SKB list pointer accesses.
In these situations, we absolutely know that the SKB queue in question
is non-empty.
Signed-off-by: David S. Miller <davem@davemloft.net>
Use skb_queue_walk() instead.
Adjust inner loop test to utilize and skb_queue_is_first().
Unfortunately we have to keep pkt_cnt around because it is
used by a latter loop in this function.
Signed-off-by: David S. Miller <davem@davemloft.net>
A recent commit updated vlan_cmd.dropnovlan_fm but failed to remove
the older assignment. Fix this by removing the former redundant
assignment.
Detected by CoverityScan, CID#1473290 ("Unused value")
Fixes: a89cdd8e7c ("cxgb4: impose mandatory VLAN usage when non-zero TAG ID")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Added memory barriers where they were missing to support multiple
architectures, and removed redundant ones.
As part of removing the redundant memory barriers and improving
performance, we moved to more relaxed versions of memory barriers,
as well as to the more relaxed version of writel - writel_relaxed,
while maintaining correctness.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add READ_ONCE calls where necessary (for example when iterating
over a memory field that gets updated by the hardware).
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
acquire the rtnl_lock during device destruction to avoid
using partially destroyed device.
ena_remove() shares almost the same logic as ena_destroy_device(),
so use ena_destroy_device() and avoid duplications.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ena_destroy_device() can potentially be called twice.
To avoid this, check that the device is running and
only then proceed destroying it.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When ena_destroy_device() is called from ena_suspend(), the device is
still reachable from the driver. Therefore, the driver can send a command
to the device to free all resources.
However, in all other cases of calling ena_destroy_device(), the device is
potentially in an error state and unreachable from the driver. In these
cases the driver must not send commands to the device.
The current implementation does not request resource freeing from the
device even when possible. We add the graceful parameter to
ena_destroy_device() to enable resource freeing when possible, and
use it in ena_suspend().
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The buffer length field in the ena rx descriptor is 16 bit, and the
current driver passes a full page in each ena rx descriptor.
When PAGE_SIZE equals 64kB or more, the buffer length field becomes
zero.
To solve this issue, limit the ena Rx descriptor to use 16kB even
when allocating 64kB kernel pages. This change would not impact ena
device functionality, as 16kB is still larger than maximum MTU.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Starting with driver version 1.5.0, in case of a surprise device
unplug, there is a race caused by invoking ena_destroy_device()
from two different places. As a result, the readless register might
be accessed after it was destroyed.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
if failover_register failed, 'err' code should be set correctly
Fixes: cfc80d9a11 ("net: Introduce net_failover driver")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Essentially reverts commit 8fd75c58a0 ("i40e: move ethtool
stats boiler plate code to i40e_ethtool_stats.h", 2018-08-30), and
additionally moves the similar code in i40evf into i40evf_ethtool.c.
The code was intially moved from i40e_ethtool.c into i40e_ethtool_stats.h
as a way of better logically organizing the code. This has two problems.
First, we can't have an inline function with variadic arguments on all
platforms. Second, it gave the appearance that we had plans to share
code between the i40e and i40evf drivers, due to having a near copy of
the contents in the i40evf/i40e_ethtool_stats.h file.
Patches which actually attempt to combine or share code between the i40e
and i40evf drivers have not materialized, and are likely a ways off.
Rather than fixing the one function which causes build issues, just move
this code back into the i40e_ethtool.c and i40evf_ethtool.c files. Note
that we also change these functions back from static inlines to just
statics, since they're no longer in a header file.
We can revisit this if/when work is done to actually attempt to share
code between drivers. Alternatively, this stats code could be made more
generic so that it can be shared across drivers as part of ethtool
kernel work.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case B53_SRAB is enabled, but not B53_SERDES, we can get the
following linking error:
ERROR: "b53_serdes_init" [drivers/net/dsa/b53/b53_srab.ko] undefined!
We also need to ifdef the body of b53_srab_serdes_map_lane() since it
would not be used when B53_SERDES is disabled and that would produce a
warning.
Fixes: 0e01491de6 ("net: dsa: b53: Add SerDes support")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a non-zero VLAN Tag ID is passed to t4_set_vlan_acl()
then impose mandatory VLAN Usage with that VLAN ID.
I.e any other VLAN ID should result in packets getting
dropped.
Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 822fb18a82 ("xen-netfront: wait xenbus state change when load
module manually") added a new wait queue to wait on for a state change
when the module is loaded manually. Unfortunately there is no wakeup
anywhere to stop that waiting.
Instead of introducing a new wait queue rename the existing
module_unload_q to module_wq and use it for both purposes (loading and
unloading).
As any state change of the backend might be intended to stop waiting
do the wake_up_all() in any case when netback_changed() is called.
Fixes: 822fb18a82 ("xen-netfront: wait xenbus state change when load module manually")
Cc: <stable@vger.kernel.org> #4.18
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 3559d81e76 ("r8169: simplify rtl_hw_start_8169") changed order of
two register writes:
1) Caused RxConfig to be written before TX / RX is enabled,
2) Caused TxConfig to be written before TX / RX is enabled.
At least on XIDs 10000000 ("RTL8169sb/8110sb") and
18000000 ("RTL8169sc/8110sc") such writes are ignored by the chip, leaving
values in these registers intact.
Change 1) was reverted by
commit 05212ba813 ("r8169: set RxConfig after tx/rx is enabled for RTL8169sb/8110sb devices"),
however change 2) wasn't.
In practice, this caused TxConfig's "InterFrameGap time" and "Max DMA Burst
Size per Tx DMA Burst" bits to be zero dramatically reducing TX performance
(in my tests it dropped from around 500Mbps to around 50Mbps).
This patch fixes the issue by moving TxConfig register write a bit later in
the code so it happens after TX / RX is already enabled.
Fixes: 05212ba813 ("r8169: set RxConfig after tx/rx is enabled for RTL8169sb/8110sb devices")
Signed-off-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c: In function 'bnxt_tc_parse_flow':
drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c:186:6: warning:
variable 'addr_type' set but not used [-Wunused-but-set-variable]
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c: In function 'cn23xx_setup_octeon_vf_device':
drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c:619:20: warning:
variable 'ring_flag' set but not used [-Wunused-but-set-variable]
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. Provide the API to set/unset the spoof checking feature.
2. Add a function to periodically provide the count of found
packets with spoof VF MAC address.
3. Prevent VF MAC address changing while the spoofchk of the VF is
on unless the changing MAC address is issued from PF.
Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Saeed Mahameed says:
====================
mlx5e-updates-2018-09-05
This series provides updates to mlx5 ethernet driver.
1) Starting with a four patches series to optimize flow counters updates,
From Vlad Buslov:
==============================================
By default mlx5 driver updates cached counters each second. Update function
consumes noticeable amount of CPU resources. The goal of this patch series
is to optimize update function.
Investigation revealed following bottlenecks in fs counters
implementation:
1) Update code(scheduled each second) iterates over all counters twice.
(first for finding and deleting counters that are marked for deletion,
second iteration is for actually updating the counters)
2) Counters are stored in rb tree. Linear iteration over all rb tree
elements(rb_next in profiling data) consumed ~65% of time spent in
update function.
Following optimizations were implemented:
1) Instead of just marking counters for deletion, store them in
standalone list. This removes first iteration over whole counters tree.
2) Store counters in sorted list to optimize traversing them and remove
calls to rb_next.
First implementation of these changes caused degradation of performance,
instead of improving it. Investigation revealed that there first cache
line of struct mlx5_fc is full and adding anything to it causes amount
of cache misses to double. To mitigate that, following refactorings were
implemented:
- Change 'addlist' list type from double linked to single linked. This
allowes to get free space for one additional pointer that is used to
store deletion list(optimization 1)
- Substitute rb tree with idr. Idr is non-intrusive data structure and
doesn't require adding any new members to struct mlx5_fc. Use free
space that became available for double linked sorted list that is used
for traversing all counters. (optimization 2)
Described changes reduced CPU time spent in mlx5_fc_stats_work from 70%
to 44%. (global perf profile mode)
============================================
The rest of the series are misc updates:
2) From Kamal, Move mlx5e_priv_flags into en_ethtool.c, to avoid a
compilation warning.
3) From Roi Dayan, Move Q counters allocation and drop RQ to init_rx profile
function to avoid allocating Q counters when not required.
4) From Shay Agroskin, Replace PTP clock lock from RW lock to seq lock.
Almost double the packet rate when timestamping is active on multiple TX
queues.
5) From: Natali Shechtman, set ECN for received packets using CQE indication.
6) From: Alaa Hleihel, don't set CHECKSUM_COMPLETE on SCTP packets.
CHECKSUM_COMPLETE is not applicable to SCTP protocol.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This is done in order not to trig the below warning in
ieee80211_rx_napi:
WARN_ON_ONCE(softirq_count() == 0);
ieee80211_rx_napi requires that softirq's are disabled during
execution.
The High latency bus drivers (SDIO and USB) sometimes call the wmi
ep_rx_complete callback from non softirq context, resulting in a trigger
of the above warning.
Calling ieee80211_rx_ni with softirq's already disabled (e.g., from
softirq context) should be safe as the local_bh_disable and
local_bh_enable functions (called from ieee80211_rx_ni) are fully
reentrant.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Special HTT RX handling for high latency interfaces.
Since no DMA physical addresses are used in the RX ring
config message (this is not supported by the high latency
devices), no RX ring is allocated.
All RX skb's are allocated by the driver and passed directly
to mac80211 in the HTT RX indication handler.
A nice side effect of this is that no huge buffer will be
allocated with dma_alloc_coherent. On embedded systems with
limited memory resources, the allocation of the RX ring is
prone to fail.
Some tweaks made to "make it work":
Removal of protected bit in 802.11 header frame control field.
The chipset seems to do hw decryption but the frame_control
protected bit is still set.
This is necessary for mac80211 not to drop the frame.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Special HTT RX ring config message used by high latency
devices.
The main difference between HL and LL is that HL devices
do not use shared memory between device and host and thus,
no host paddr's are added to the RX config message.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Several DMA related functions (such as the dma_map_xxx functions)
are not used with high latency devices and don't need to be invoked
in this case.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
This patch makes sure the value of max_num_peers matches
num_peers in hw_params (if set to a non zero value).
hw_params->num_peers is used in the TLV WMI init command.
If ar->max_num_peers is not set to the same value, there is a risk
that the user creates more peers than the maximum number of peers
supported by the device.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
As TARGET_TLV_NUM_TIDS is calculated like this:
#define TARGET_TLV_NUM_TIDS ((TARGET_TLV_NUM_PEERS) * 2)
... it is better to use the per device hw_params.num_peers value in
the TLV init message (if set), rather than using a hard coded value.
This makes the value used in the TLV init message match the hw_param
value.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
The bus type is used together with the other hw parameters
to find a matching entry in ath10k_hw_params_list for the device.
This is necessary since HL devices can have the same dev_id and
target_version as a corresponding LL device (same chipset) and
yet use a totally different configuration.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Add dev_type parameter to struct ath10k_bus_params.
The dev type specifies if the device is a high latency device (usb and
sdio) or low latency device (pci, ahb and snoc)
The setup of high latency chips is sometimes different than
for chips using low latency interfaces.
Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
