| Age | Commit message (Collapse) | Author |
|---|
|
consecutive lines
Change the RACPREFDATA(x) setting to prefetch the next 256-byte line
after 4 consecutive lines have been used, instead of after 2 consecutive
lines. This does improve the synthetic memcpy benchmark by an additional
+0.5% on top of the previous change for Cortex-A72 CPUs.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
Change the RAC prefetch distance from +/- 1 to +/- 2 for Cortex-A72 CPUs
since this provides an average of a 3.8% performance increase for
synthetic memcpy benchmarks.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
72165 uses a Brahma-B53 CPU and its Bus Interface Unit, tune it
according to the existing values we have.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
72164 uses a Brahma-B53 CPU and its Bus Interface Unit, tune it
according to the existing values we have.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
Brahma-B53 and Cortex-A72 CPUs integrated on Broadcom STB SoCs feature a
read-ahead cache that performs cache line size adaptation between the
bus interface unit and the memory controller.
On 32-bit ARM kernels we have to resort to a full featured read-ahead
cache driver under arch/arm/mm/cache-b15-rac.c (CONFIG_CACHE_B15_RAC)
because there are still cache maintenance operations by set/ways/index
that cannot be transparently handled by the ARM Coherency Extension that
the read-ahead cache interfaces to.
The 64-bit ARM kernel however has long deprecated all of those, so this
is simply a one time configuration.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
Add a matching entry for 7211 which can be programmed with the same
BIUCTRL settings as other Brahma-B53 based SoCs. While at it, rename the
function to include a72 in the name to reflect this applies to both
types of 64-bit capable CPUs that we support (Brahma-B53 and
Cortex-A72).
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
The BIUCTRL layout is a little different on 7211 which is equipped with
a Cortex-A72, account for those register offset differences. We will
match 7211 specifically in a subsequent commit.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
7255 and 7216 are some of the latest chips that were produced and
support the full register range configuration for the BIU, add the two
entries to get the expected programming.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
7260A0 and B0 are both supported, and 7260A0 has a small difference in
that it does not support the write-back control register, which is why
we have a different array of registers. Update the comment above
b53_cpubiuctrl_no_wb_regs to denote that difference.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
https://github.com/Broadcom/stblinux into fixes
This pull request contains Broadcom ARM/ARM64/MIPS SoCs device drivers
fixes for 5.2-rc1, please pull the following:
- Florian fixes the biuctrl driver not to create an error condition/path
upon unsupported CPU and also fixes the biuctrl driver writes to used
a data barrier which is necessary given the HW block design
* tag 'arm-soc/for-5.2/drivers-fixes' of https://github.com/Broadcom/stblinux:
soc: bcm: brcmstb: biuctrl: Register writes require a barrier
soc: brcmstb: Fix error path for unsupported CPUs
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
Based on 1 normalized pattern(s):
this program is free software you can redistribute it and or modify
it under the terms of the gnu general public license version 2 as
published by the free software foundation this program is
distributed in the hope that it will be useful but without any
warranty without even the implied warranty of merchantability or
fitness for a particular purpose see the gnu general public license
for more details
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 655 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Richard Fontana <rfontana@redhat.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190527070034.575739538@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
The BIUCTRL register writes require that a data barrier be inserted
after comitting the write to the register for the block to latch in the
recently written values. Reads have no such requirement and are not
changed.
Fixes: 34642650e5bc ("soc: Move brcmstb to bcm/brcmstb")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
In case setup_hifcpubiuctrl_regs() returns an error, because of e.g:
an unsupported CPU type, just catch that error and return instead of
blindly continuing with the initialization. This fixes a NULL pointer
de-reference with the code continuing without having a proper array of
registers to use.
Fixes: 22f7a9116eba ("soc: brcmstb: Correct CPU_CREDIT_REG offset for Brahma-B53 CPUs")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
Currently if this driver is included, we get the following warning
on any platforms irrespective of whether it's brcmstb platform or not.
"
brcmstb: biuctrl: missing BIU control node
brcmstb: biuctrl: MCP: Unable to disable write pairing!
"
This patch allows to exit early without any warning messages on non
brcmstb platforms as it's meaningless for them.
Cc: Brian Norris <computersforpeace@gmail.com>
Cc: Gregory Fong <gregory.0xf0@gmail.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: bcm-kernel-feedback-list@broadcom.com
Fixes: f780429adfbc ("soc: brcmstb: biuctrl: Move to early_initcall")
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
[florian: Add fixes tag, make initcall non fatal]
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
Being called during early_initcall() is early enough that it occurs
before SMP initialization, which is all we care about for the Bus
Interface Unit configuration.
This solves lack of BIU initialization on ARM64 platforms where we do
not have an anchor where to put the BIU initialization (since there are
no machine descriptors).
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
In order to achieve expected MCP bus throughput on 3 particular chips:
7268, 7271 and 7278, do the appropriate programming of the MCP
interface: increase number of MCP write credits, turn on write-back
throttling when present.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
Add definitions for B53 systems register: CPU_MCP_FLOW_REG and
CPU_WRITEBACK_CTRL_REG. These register will be saved and restored
accordingly.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
In preparation for saving/restoring additional registers required on
some newer platforms (7268, 7271, 7278), migrate the code to use enums
and helper functions to access registers.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
On Broadcom Brahma-B53 CPUs, the CPU_CREDIT_REG offset got moved to
0x0b0 instead of 0x184, correct this such that we correcty
enable/disable write-pairing for these chips.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
In preparation for fixing and changing values in the CPU_CREDIT_REG
register for B53-based systems, make the offset parameterized.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
The brcmstb_biuctrl_init() is defined in the soc specific header
file, but wasn't included in the driver file. Fix the following
warning by including <linux/soc/brcmstb/brcmstb.h> in the driver:
drivers/soc/brcmstb/biuctrl.c:101:13: warning: symbol 'brcmstb_biuctrl_init' was not declared. Should it be static?
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
|
Unify the different Broadcom SoCs directory and have everybody live
under drivers/soc/bcm/*.
Acked-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
|
