The concept of Relaxed Ordering in the PCI Express environment allows
switches in the path between the Requester and Completer to reorder some
transactions just received before others that were previously enqueued.
In ETH driver, there is no question of write integrity since each memory
segment is written only once per cycle. In addition, the driver doesn't
access the memory shared with the hardware until the corresponding CQE
arrives indicating all PCI transactions are done.
Running TCP single stream over ConnectX-4 LX, ARM CPU on remote-numa has
300% improvement in the bandwidth.
With relaxed ordering turned off: BW:10 [GB/s]
With relaxed ordering turned on: BW:40 [GB/s]
The driver turns relaxed ordering with respect to the firmware
capabilities and the return value from pcie_relaxed_ordering_enabled().
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Use the indirect call wrapper API macros for declaration and scope
of the RX post WQEs functions.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Instead of exposing the RQ datapath handlers (from en_rx.c) so that
they are set in the control path (in en_main.c), wrap this logic
in a single function in en_rx.c and expose it alone.
Every profile will now have a pointer to the new mlx5e_rx_handlers
structure, instead of directly pointing to the previously-exposed
RQ handlers.
This significantly improves locality and modularity of the driver,
and allows many functions in en_rx.c to become static.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently PF and VF representors are exposed as virtual device.
They are not linked to its parent PCI device like how uplink
representor is linked.
Due to this, PF and VF representors cannot benefit of the
systemd defined naming scheme. This requires special handling
by the users.
Hence, link the PF and VF representors to their parent PCI device
similar to existing uplink representor netdevice.
Example:
udevadm output before linking to PCI device:
$ udevadm test-builtin net_id /sys/class/net/eth6
Load module index
Network interface NamePolicy= disabled on kernel command line, ignoring.
Parsed configuration file /usr/lib/systemd/network/99-default.link
Created link configuration context.
Using default interface naming scheme 'v243'.
ID_NET_NAMING_SCHEME=v243
Unload module index
Unloaded link configuration context.
udevadm output after linking to PCI device:
$ udevadm test-builtin net_id /sys/class/net/eth6
Load module index
Network interface NamePolicy= disabled on kernel command line, ignoring.
Parsed configuration file /usr/lib/systemd/network/99-default.link
Created link configuration context.
Using default interface naming scheme 'v243'.
ID_NET_NAMING_SCHEME=v243
ID_NET_NAME_PATH=enp0s8f0npf0vf0
Unload module index
Unloaded link configuration context.
In past there was little concern over seeing 10,000 lines output
showing up at thread [1] is not applicable as ndo ops for VF
handling is not exposed for all the 100 repesentors for mlx5 devices.
Additionally alternative device naming [2] to overcome shorter device
naming is also part of the latest systemd release v245.
[1] https://marc.info/?l=linux-netdev&m=152657949117904&w=2
[2] https://lwn.net/Articles/814068/
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Currently steering table and rx group initialization helper
routines works on the total_vports passed as input parameter.
Both eswitch helpers work on the mlx5_eswitch and thereby have access
to esw->total_vports. Hence use it directly instead of passing it
via function input arguments.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Total e-switch vports are already stored in mlx5_eswitch total_vports.
Avoid copy of it in nvports and reuse existing total_vports calculation.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
When eswitch is enabled, VFs might not be enabled. Hence, consider
maximum number of VFs.
This further closes the gap between handling VF vports between ECPF and
PF.
Fixes: ea2128fd63 ("net/mlx5: E-switch, Reduce dependency on num_vfs during mode set")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add function ID to reclaim pages debug log for better user visibility.
Signed-off-by: Avihu Hagag <avihuh@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Per page request event, FW request to allocated or release pages for a
single function. Driver maintains FW pages object per function, so there
is no need to hold one global page data-base. Instead, have a page
data-base per function, which will improve performance release flow in all
cases, especially for "release all pages".
As the range of function IDs is large and not sequential, use xarray to
store a per function ID page data-base, where the function ID is the key.
Upon first allocation of a page to a function ID, create the page
data-base per function. This data-base will be released only at pagealloc
mechanism cleanup.
NIC: ConnectX-4 Lx
CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
Test case: 32 VFs, measure release pages on one VF as part of FLR
Before: 0.021 Sec
After: 0.014 Sec
The improvement depends on amount of VFs and memory utilization
by them. Time measurements above were taken from idle system.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Add a section to the Thinkpad ACPI extras driver documentation detailing
the provided features that may be used to modify battery charge related state.
As of yet, only charge_control_{start,end}_threshold attributes are supported
and documented.
Signed-off-by: Barnabás Pőcze <pobrn@protonmail.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.
Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Helge Deller <deller@gmx.de>
The /proc/meminfo file reports physically broken memory pages in the
HardwareCorrupted field. When the parisc kernel boots report physically
bad pages which were recorded in the page deallocation table (PDT) as
HardwareCorrupted too.
Signed-off-by: Helge Deller <deller@gmx.de>
Adds initial support for the 70mai midrive d08 dash camera.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
BreadBee is an opensource development board based on the
MStar msc313(e) SoC.
Hardware details, schematics and so on can be found at:
https://github.com/breadbee/breadbee
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
This adds a family level dtsi for the mercury5 and then a
chip level dtsi for the ssc8336n chip.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
This adds two family level dtsis for the infinity and infinity3
and then adds a chip level dtsi each for a chip in those families.
infinity3.dtsi includes infinity.dtsi as these SoCs share most of
their memory map and we would have a lot of duplication otherwise.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Adds initial dtsi for the base MStar/Sigmastar Armv7 SoCs.
These SoCs have very similar memory maps and this will avoid
duplicating nodes across multiple dtsis.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
This adds a YAML description of the l3bridge node needed by the
platform code for the MStar/SigmaStar Armv7 SoCs.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Initial support for the MStar/Sigmastar Armv7 based IP camera
and dashcam SoCs.
These chips are interesting in that they contain a Cortex-A7,
peripherals and system memory in a single tiny QFN package that
can be hand soldered allowing almost anyone to embed Linux
in their projects.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
This adds a DPLL clock to the Sparx5 SoC. It is used to generate clock
to misc peripherals, specifically the SDHCI/eMMC controller.
Link: https://lore.kernel.org/r/20200615133242.24911-10-lars.povlsen@microchip.com
Signed-off-by: Lars Povlsen <lars.povlsen@microchip.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
When merging name events, fsids of the two involved events have to
match. Otherwise we could merge events from two different filesystems
and thus effectively loose the second event.
Backporting note: Although the commit cacfb956d4 introducing this bug
was merged for 5.7, the relevant code didn't get used in the end until
7e8283af6e ("fanotify: report parent fid + name + child fid") which
will be merged with this patch. So there's no need for backporting this.
Fixes: cacfb956d4 ("fanotify: record name info for FAN_DIR_MODIFY event")
Reported-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Currently lockdep_types.h includes list.h without actually using any
of its macros or functions. All it needs are the type definitions
which were moved into types.h long ago. This potentially causes
inclusion loops because both are included by many core header
files.
This patch moves the list.h inclusion into lockdep.h. Note that
we could probably remove it completely but that could potentially
result in compile failures should any end users not include list.h
directly and also be unlucky enough to not get list.h via some other
header file.
Reported-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Petr Mladek <pmladek@suse.com>
Link: https://lkml.kernel.org/r/20200716063649.GA23065@gondor.apana.org.au
It's been reported that, when neither nouveau nor Nvidia graphics
driver is used, the screen starts flickering. And, after comparing
between the working case (stable 4.4.x) and the broken case, it turned
out that the problem comes from the audio component binding. The
Nvidia and AMD audio binding code clears the bus->keep_power flag
whenever snd_hdac_acomp_init() succeeds. But this doesn't mean that
the component is actually bound, but it merely indicates that it's
ready for binding. So, when both nouveau and Nvidia are blacklisted
or not ready, the driver keeps running without the audio component but
also with bus->keep_power = false. This made the driver runtime PM
kicked in and powering down when unused, which results in flickering
in the graphics side, as it seems.
For fixing the bug, this patch moves the bus->keep_power flag change
into generic_acomp_notifier_set() that is the function called from the
master_bind callback of component ops; i.e. it's guaranteed that the
binding succeeded.
BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208609
Fixes: 5a858e79c9 ("ALSA: hda - Disable audio component for legacy Nvidia HDMI codecs")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20200728082033.23933-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The ROUT (right channel output of audio codec) was connected to INL
(left channel of audio amplifier) instead of INR (right channel of audio
amplifier).
Fixes: 8ddebad15e ("MIPS: qi_lb60: Migrate to devicetree")
Cc: stable@vger.kernel.org # v5.3
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
The CONFIG_MIPS_MACHINE option is dead code that hasn't been used in
years. The Kconfig option is not selected anywhere, and the
<asm/mips_machine.h> is not included anywhere either.
To make things worse, for years it co-existed with a separate MIPS
machine implementation as <asm/machine.h>. The two defined the
'mips_machine' structure with different fields, and the 'MIPS_MACHINE'
macro with different parameters. The two used the same memory area
(defined by the linker script) to store data, and you could totally use
the two at the same time for all kinds of funny results.
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Since commit 3a77e0d75e ("MIPS: ath79: drop machfiles"), this header
is not used anymore.
Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
The variable authmode can be uninitialized. The danger would be if
it equals to _WPA_IE_ID_ (0xdd) or _WPA2_IE_ID_ (0x33). We can avoid
this by setting it to zero instead. This is the approach that was
used in the rtl8723bs driver.
Fixes: 7b464c9fa5 ("staging: r8188eu: Add files for new driver - part 4")
Co-developed-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20200728072153.9202-1-dinghao.liu@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Thanks to Okash's latest work, the TODO list is essentially empty, so
the way out from staging now seems open.
The status of the remaining issue mentioned in TODO is not clear, we
asked the speakup user mailing list for reproducer cases, but didn't get
a really specific scenario. One serious bug was fixed by 9d32c0cde4
("staging/speakup: fix get_word non-space look-ahead"), which does not
seem to really be related to the bug mentioned in TODO. Possibly the bug
mentioned in TODO has been fixed long ago and people have been thinking
that it was not because they can not distinguish the symptoms mentioned
in TODO from the symptoms of the bug fixed by 9d32c0cde4.
Signed-off-by: Samuel Thibault <samuel.thibault@ens-lyon.org>
Link: https://lore.kernel.org/r/20200726165452.qhos3wrjcm6jmcmx@function
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
rtw_aes_decrypt, rtw_tkip_decrypt, rtw_wep_decrypt, rtw_aes_encrypt,
rtw_tkip_encrypt, rtw_wep_encrypt are takes (u8 *) second argiment and
always uses it as (struct recv_frame *) or (struct xmit_frame *).
This is causes a lot of unnecessary type casts
and complicates refactoring.
Signed-off-by: Ivan Safonov <insafonov@gmail.com>
Link: https://lore.kernel.org/r/20200726210246.68633-1-insafonov@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This makes the driver use the irqchip template to assign
properties to the gpio_irq_chip instead of using the
explicit calls to gpiochip_irqchip_add(). The irqchip is
instead added while adding the gpiochip.
Cc: Nishad Kamdar <nishadkamdar@gmail.com>
Cc: Johan Hovold <johan@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20200722074414.48457-1-linus.walleij@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Aya Levin