| Age | Commit message (Collapse) | Author |
|---|
|
Arguments are supposed to be ordered high then low.
Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
The PCIe PHY initialization requires the attached device to be present,
which is primarily achieved by the PCI controller driver. So move the
logic from init/exit to power_on/power_off.
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: John Stultz <john.stultz@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Since this phy is shared by multiple devices including USB and PCIe,
it is necessary to determine which device use this phy.
This patch adds SoC-dependent functions to determine a device using
this phy.
When there is 'socionext,syscon' property in the pcie-phy node,
the driver calls SoC-dependt function instead of checking .has_syscon
in SoC-dependent data. The function configures the system controller
to use phy for PCIe.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add legacy SoC support that needs to manage gio clock and reset and to skip
setting unimplemented phy parameters. This supports Pro5.
This specifies only 1 port use because Pro5 doesn't set it in the power-on
sequence.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
In case of using default parameters, communication failure might occur
in rare cases. This sets Rx sync mode parameter to avoid the issue.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add legacy SoC support that needs to manage gio clock and reset.
This supports Pro5.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Pro5 SoC has same scheme of USB3 ss-phy as Pro4, so the data for Pro5 is
equivalent to Pro4.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
This adds compatible string for Pro5 SoC that needs to manage gio clock
and reset. And Pro4 SoC uses USB2 PHY instead of USB3 HS-PHY, so this
removes Pro4 description from usb3-hsphy.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Use devm_platform_ioremap_resource() to simplify the code.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
The support for the 14nm MSM8996 UFS PHY is currently handled by the
UFS-specific 14nm QMP driver, due to the earlier need for additional
operations beyond the standard PHY API.
Add support for this PHY to the common QMP driver, to allow us to remove
the old driver.
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Implement single link subnode support to the phy driver.
Add reset support including PHY reset and individual lane reset.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add platform dependent initialization data for Torrent PHY used in TI's
J721E SoC.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Use regmap to read and write DPTX specific PHY registers.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Use regmap for accessing Torrent PHY registers. Modify register offsets
as defined in Torrent PHY user guide. Abstract address calculation
using regmap APIs.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add support for PHY configuration APIs. These will mainly reconfigure
link rate, number of lanes, voltage swing and pre-emphasis values.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add configuration functions for 19.2 MHz refclock support.
Add register configurations for SSC support.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add a separate function to set different power state values.
Use uniform polling timeout value. Also check return values
of functions for proper error handling.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add wrapper functions to read, write DisplayPort specific PHY registers to
improve code readability.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add a wrapper function to write Torrent PHY registers to improve
code readability.
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
- Change private data struct cdns_dp_phy to cdns_torrent_phy
- Change module description and registration accordingly
- Generic torrent functions have prefix cdns_torrent_phy_*
- Functions specific to Torrent phy for DisplayPort are prefixed as
cdns_torrent_dp_*
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Rename Cadence DP PHY driver from phy-cadence-dp to phy-cadence-torrent
to make it more generic for future use. Modifiy Makefile and Kconfig
accordingly. Also, change driver compatible from "cdns,dp-phy" to
"cdns,torrent-phy".This will not affect ABI as the driver has never
been functional, and therefore do not exist in any active use case.
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
- Add Cadence MHDP PHY bindings in YAML format.
- Add Torrent PHY reference clock bindings.
- Add sub-node bindings for each group of PHY lanes based on PHY type.
Each sub-node includes properties such as master lane number, link reset,
phy type, number of lanes etc.
- Add reset support including PHY reset and individual lane reset.
- Add a new compatible string used for TI SoCs using Torrent PHY.
This will not affect ABI as the driver has never been functional,
and therefore do not exist in any active use case.
Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
|
|
Add touchscreen info for the Chuwi Vi8 Plus tablet. This tablet uses a
Chipone ICN8505 touchscreen controller, with the firmware used by the
touchscreen embedded in the EFI firmware.
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200115163554.101315-11-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Sofar we have been unable to get permission from the vendors to put the
firmware for touchscreens listed in touchscreen_dmi in linux-firmware.
Some of the tablets with such a touchscreen have a touchscreen driver, and
thus a copy of the firmware, as part of their EFI code.
This commit adds the necessary info for the new EFI embedded-firmware code
to extract these firmwares, making the touchscreen work OOTB without the
user needing to manually add the firmware.
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200115163554.101315-10-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Unfortunately sofar we have been unable to get permission to redistribute
icn8505 touchscreen firmwares in linux-firmware. This means that people
need to find and install the firmware themselves before the touchscreen
will work
Some UEFI/x86 tablets with an icn8505 touchscreen have a copy of the fw
embedded in their UEFI boot-services code.
This commit makes the icn8505 driver use the new firmware_request_platform
function, which will fallback to looking for such an embedded copy when
direct filesystem lookup fails. This will make the touchscreen work OOTB
on devices where there is a fw copy embedded in the UEFI code.
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200115163554.101315-9-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Unfortunately sofar we have been unable to get permission to redistribute
Silead touchscreen firmwares in linux-firmware. This means that people
need to find and install the firmware themselves before the touchscreen
will work
Some UEFI/x86 tablets with a Silead touchscreen have a copy of the fw
embedded in their UEFI boot-services code.
This commit makes the silead driver use the new firmware_request_platform
function, which will fallback to looking for such an embedded copy when
direct filesystem lookup fails. This will make the touchscreen work OOTB
on devices where there is a fw copy embedded in the UEFI code.
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200115163554.101315-8-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Add tests cases for checking the new firmware_request_platform api.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20200115163554.101315-7-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Add support for testing firmware_request_platform through a new
trigger_request_platform trigger.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20200115163554.101315-6-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
In some cases the platform's main firmware (e.g. the UEFI fw) may contain
an embedded copy of device firmware which needs to be (re)loaded into the
peripheral. Normally such firmware would be part of linux-firmware, but in
some cases this is not feasible, for 2 reasons:
1) The firmware is customized for a specific use-case of the chipset / use
with a specific hardware model, so we cannot have a single firmware file
for the chipset. E.g. touchscreen controller firmwares are compiled
specifically for the hardware model they are used with, as they are
calibrated for a specific model digitizer.
2) Despite repeated attempts we have failed to get permission to
redistribute the firmware. This is especially a problem with customized
firmwares, these get created by the chip vendor for a specific ODM and the
copyright may partially belong with the ODM, so the chip vendor cannot
give a blanket permission to distribute these.
This commit adds a new platform fallback mechanism to the firmware loader
which will try to lookup a device fw copy embedded in the platform's main
firmware if direct filesystem lookup fails.
Drivers which need such embedded fw copies can enable this fallback
mechanism by using the new firmware_request_platform() function.
Note that for now this is only supported on EFI platforms and even on
these platforms firmware_fallback_platform() only works if
CONFIG_EFI_EMBEDDED_FIRMWARE is enabled (this gets selected by drivers
which need this), in all other cases firmware_fallback_platform() simply
always returns -ENOENT.
Reported-by: Dave Olsthoorn <dave@bewaar.me>
Suggested-by: Peter Jones <pjones@redhat.com>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200115163554.101315-5-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi into driver-core-next
Ard writes:
Stable shared branch between EFI and driver tree
Stable shared branch to ease the integration of Hans's series to support
device firmware loaded from EFI boot service memory regions.
[PATCH v12 00/10] efi/firmware/platform-x86: Add EFI embedded fw support
https://lore.kernel.org/linux-efi/20200115163554.101315-1-hdegoede@redhat.com/
* tag 'stable-shared-branch-for-driver-tree' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi:
efi: Add embedded peripheral firmware support
efi: Export boot-services code and data as debugfs-blobs
|
|
This feature should not be enabled in release but can be useful for
developers who need to monitor register accesses at some specific places.
Helped me identify a bug in u-boot, by comparing the register accesses
from the linux driver with the ones from its u-boot variant.
Signed-off-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20200320065058.891221-1-tudor.ambarus@microchip.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
nmi_enter() does lockdep_off() and hence lockdep ignores everything.
And NMI context makes it impossible to do full IN-NMI tracking like we
do IN-HARDIRQ, that could result in graph_lock recursion.
However, since look_up_lock_class() is lockless, we can find the class
of a lock that has prior use and detect IN-NMI after USED, just not
USED after IN-NMI.
NOTE: By shifting the lockdep_off() recursion count to bit-16, we can
easily differentiate between actual recursion and off.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Link: https://lkml.kernel.org/r/20200221134215.090538203@infradead.org
|
|
A few sites want to assert we own the graph_lock/lockdep_lock, provide
a more conventional lock interface for it with a number of trivial
debug checks.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200313102107.GX12561@hirez.programming.kicks-ass.net
|
|
There were two patterns for lockdep_recursion:
Pattern-A:
if (current->lockdep_recursion)
return
current->lockdep_recursion = 1;
/* do stuff */
current->lockdep_recursion = 0;
Pattern-B:
current->lockdep_recursion++;
/* do stuff */
current->lockdep_recursion--;
But a third pattern has emerged:
Pattern-C:
current->lockdep_recursion = 1;
/* do stuff */
current->lockdep_recursion = 0;
And while this isn't broken per-se, it is highly dangerous because it
doesn't nest properly.
Get rid of all Pattern-C instances and shore up Pattern-A with a
warning.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200313093325.GW12561@hirez.programming.kicks-ass.net
|
|
Qian Cai reported a bug when PROVE_RCU_LIST=y, and read on /proc/lockdep
triggered a warning:
[ ] DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)
...
[ ] Call Trace:
[ ] lock_is_held_type+0x5d/0x150
[ ] ? rcu_lockdep_current_cpu_online+0x64/0x80
[ ] rcu_read_lock_any_held+0xac/0x100
[ ] ? rcu_read_lock_held+0xc0/0xc0
[ ] ? __slab_free+0x421/0x540
[ ] ? kasan_kmalloc+0x9/0x10
[ ] ? __kmalloc_node+0x1d7/0x320
[ ] ? kvmalloc_node+0x6f/0x80
[ ] __bfs+0x28a/0x3c0
[ ] ? class_equal+0x30/0x30
[ ] lockdep_count_forward_deps+0x11a/0x1a0
The warning got triggered because lockdep_count_forward_deps() call
__bfs() without current->lockdep_recursion being set, as a result
a lockdep internal function (__bfs()) is checked by lockdep, which is
unexpected, and the inconsistency between the irq-off state and the
state traced by lockdep caused the warning.
Apart from this warning, lockdep internal functions like __bfs() should
always be protected by current->lockdep_recursion to avoid potential
deadlocks and data inconsistency, therefore add the
current->lockdep_recursion on-and-off section to protect __bfs() in both
lockdep_count_forward_deps() and lockdep_count_backward_deps()
Reported-by: Qian Cai <cai@lca.pw>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200312151258.128036-1-boqun.feng@gmail.com
|
|
The IMC uncore unit in Ice Lake server can only be accessed by MMIO,
which is similar as Snow Ridge.
Factor out __snr_uncore_mmio_init_box which can be shared with Ice Lake
server in the following patch.
No functional changes.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1584470314-46657-2-git-send-email-kan.liang@linux.intel.com
|
|
The offset between uncore boxes of free-running counters varies, e.g.
IIO free-running counters on Ice Lake server.
Add box_offsets, an array of offsets between adjacent uncore boxes.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1584470314-46657-1-git-send-email-kan.liang@linux.intel.com
|
|
This NULL check is reversed so it leads to a Smatch warning and
presumably a NULL dereference.
kernel/events/core.c:1598 perf_event_groups_less()
error: we previously assumed 'right->cgrp->css.cgroup' could be null
(see line 1590)
Fixes: 95ed6c707f26 ("perf/cgroup: Order events in RB tree by cgroup id")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200312105637.GA8960@mwanda
|
|
Kan and Andi reported that we fail to kill rotation when the flexible
events go empty, but the context does not. XXX moar
Fixes: fd7d55172d1e ("perf/cgroups: Don't rotate events for cgroups unnecessarily")
Reported-by: Andi Kleen <ak@linux.intel.com>
Reported-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200305123851.GX2596@hirez.programming.kicks-ass.net
|
|
While looking at an objtool UACCESS warning, it suddenly occurred to me
that it is entirely possible to have an OPTPROBE right in the middle of
an UACCESS region.
In this case we must of course clear FLAGS.AC while running the KPROBE.
Luckily the trampoline already saves/restores [ER]FLAGS, so all we need
to do is inject a CLAC. Unfortunately we cannot use ALTERNATIVE() in the
trampoline text, so we have to frob that manually.
Fixes: ca0bbc70f147 ("sched/x86_64: Don't save flags on context switch")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20200305092130.GU2596@hirez.programming.kicks-ass.net
|
|
In update_sg_wakeup_stats(), the comment says:
Computing avg_load makes sense only when group is fully
busy or overloaded.
But, the code below this comment does not check like this.
From reading the code about avg_load in other functions, I
confirm that avg_load should be calculated in fully busy or
overloaded case. The comment is correct and the checking
condition is wrong. So, change that condition.
Fixes: 57abff067a08 ("sched/fair: Rework find_idlest_group()")
Signed-off-by: Tao Zhou <ouwen210@hotmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lkml.kernel.org/r/Message-ID:
|
|
If we failed to find a fitting CPU, in cpupri_find(), we only fallback
to the level we found a hit at.
But Steve suggested to fallback to a second full scan instead as this
could be a better effort.
https://lore.kernel.org/lkml/20200304135404.146c56eb@gandalf.local.home/
We trigger the 2nd search unconditionally since the argument about
triggering a full search is that the recorded fall back level might have
become empty by then. Which means storing any data about what happened
would be meaningless and stale.
I had a humble try at timing it and it seemed okay for the small 6 CPUs
system I was running on
https://lore.kernel.org/lkml/20200305124324.42x6ehjxbnjkklnh@e107158-lin.cambridge.arm.com/
On large system this second full scan could be expensive. But there are
no users outside capacity awareness for this fitness function at the
moment. Heterogeneous systems tend to be small with 8cores in total.
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20200310142219.syxzn5ljpdxqtbgx@e107158-lin.cambridge.arm.com
|
|
when we create a kthread with ktrhead_create_on_cpu(),the child thread
entry is ktread.c:ktrhead() which will be preempted by the parent after
call complete(done) while schedule() is not called yet,then the parent
will call wait_task_inactive(child) but the child is still on the runqueue,
so the parent will schedule_hrtimeout() for 1 jiffy,it will waste a lot of
time,especially on startup.
parent child
ktrhead_create_on_cpu()
wait_fo_completion(&done) -----> ktread.c:ktrhead()
|----- complete(done);--wakeup and preempted by parent
kthread_bind() <------------| |-> schedule();--dequeue here
wait_task_inactive(child) |
schedule_hrtimeout(1 jiffy) -|
So we hope the child just wakeup parent but not preempted by parent, and the
child is going to call schedule() soon,then the parent will not call
schedule_hrtimeout(1 jiffy) as the child is already dequeue.
The same issue for ktrhead_park()&&kthread_parkme().
This patch can save 120ms on rk312x startup with CONFIG_HZ=300.
Signed-off-by: Liang Chen <cl@rock-chips.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20200306070133.18335-2-cl@rock-chips.com
|
|
During load_balancing, a group with spare capacity will try to pull some
utilizations from an overloaded group. In such case, the load balance
looks for the runqueue with the highest utilization. Nevertheless, it
should also ensure that there are some pending tasks to pull otherwise
the load balance will fail to pull a task and the spread of the load will
be delayed.
This situation is quite transient but it's possible to highlight the
effect with a short run of sysbench test so the time to spread task impacts
the global result significantly.
Below are the average results for 15 iterations on an arm64 octo core:
sysbench --test=cpu --num-threads=8 --max-requests=1000 run
tip/sched/core +patchset
total time: 172ms 158ms
per-request statistics:
avg: 1.337ms 1.244ms
max: 21.191ms 10.753ms
The average max doesn't fully reflect the wide spread of the value which
ranges from 1.350ms to more than 41ms for the tip/sched/core and from
1.350ms to 21ms with the patch.
Other factors like waiting for an idle load balance or cache hotness
can delay the spreading of the tasks which explains why we can still
have up to 21ms with the patch.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200312165429.990-1-vincent.guittot@linaro.org
|
|
During our testing, we found a case that shares no longer
working correctly, the cgroup topology is like:
/sys/fs/cgroup/cpu/A (shares=102400)
/sys/fs/cgroup/cpu/A/B (shares=2)
/sys/fs/cgroup/cpu/A/B/C (shares=1024)
/sys/fs/cgroup/cpu/D (shares=1024)
/sys/fs/cgroup/cpu/D/E (shares=1024)
/sys/fs/cgroup/cpu/D/E/F (shares=1024)
The same benchmark is running in group C & F, no other tasks are
running, the benchmark is capable to consumed all the CPUs.
We suppose the group C will win more CPU resources since it could
enjoy all the shares of group A, but it's F who wins much more.
The reason is because we have group B with shares as 2, since
A->cfs_rq.load.weight == B->se.load.weight == B->shares/nr_cpus,
so A->cfs_rq.load.weight become very small.
And in calc_group_shares() we calculate shares as:
load = max(scale_load_down(cfs_rq->load.weight), cfs_rq->avg.load_avg);
shares = (tg_shares * load) / tg_weight;
Since the 'cfs_rq->load.weight' is too small, the load become 0
after scale down, although 'tg_shares' is 102400, shares of the se
which stand for group A on root cfs_rq become 2.
While the se of D on root cfs_rq is far more bigger than 2, so it
wins the battle.
Thus when scale_load_down() scale real weight down to 0, it's no
longer telling the real story, the caller will have the wrong
information and the calculation will be buggy.
This patch add check in scale_load_down(), so the real weight will
be >= MIN_SHARES after scale, after applied the group C wins as
expected.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Michael Wang <yun.wang@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/38e8e212-59a1-64b2-b247-b6d0b52d8dc1@linux.alibaba.com
|
|
The task->flags is a 32-bits flag, in which 31 bits have already been
consumed. So it is hardly to introduce other new per process flag.
Currently there're still enough spaces in the bit-field section of
task_struct, so we can define the memstall state as a single bit in
task_struct instead.
This patch also removes an out-of-date comment pointed by Matthew.
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/1584408485-1921-1-git-send-email-laoar.shao@gmail.com
|
|
Add a maintainer section for psi, as it's a user-visible, configurable
kernel feature.
The patches are still routed through the scheduler tree due to the
close integration with that code, but get_maintainers.pl does the
right thing and makes sure everybody gets CCd:
$ ./scripts/get_maintainer.pl -f kernel/sched/psi.c
Johannes Weiner <hannes@cmpxchg.org> (maintainer:PRESSURE STALL INFORMATION (PSI))
Ingo Molnar <mingo@redhat.com> (maintainer:SCHEDULER)
Peter Zijlstra <peterz@infradead.org> (maintainer:SCHEDULER)
...
Reported-by: Ivan Babrou <ivan@cloudflare.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200316191333.115523-4-hannes@cmpxchg.org
|
|
When switching tasks running on a CPU, the psi state of a cgroup
containing both of these tasks does not change. Right now, we don't
exploit that, and can perform many unnecessary state changes in nested
hierarchies, especially when most activity comes from one leaf cgroup.
This patch implements an optimization where we only update cgroups
whose state actually changes during a task switch. These are all
cgroups that contain one task but not the other, up to the first
shared ancestor. When both tasks are in the same group, we don't need
to update anything at all.
We can identify the first shared ancestor by walking the groups of the
incoming task until we see TSK_ONCPU set on the local CPU; that's the
first group that also contains the outgoing task.
The new psi_task_switch() is similar to psi_task_change(). To allow
code reuse, move the task flag maintenance code into a new function
and the poll/avg worker wakeups into the shared psi_group_change().
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200316191333.115523-3-hannes@cmpxchg.org
|
|
For simplicity, cpu pressure is defined as having more than one
runnable task on a given CPU. This works on the system-level, but it
has limitations in a cgrouped reality: When cpu.max is in use, it
doesn't capture the time in which a task is not executing on the CPU
due to throttling. Likewise, it doesn't capture the time in which a
competing cgroup is occupying the CPU - meaning it only reflects
cgroup-internal competitive pressure, not outside pressure.
Enable tracking of currently executing tasks, and then change the
definition of cpu pressure in a cgroup from
NR_RUNNING > 1
to
NR_RUNNING > ON_CPU
which will capture the effects of cpu.max as well as competition from
outside the cgroup.
After this patch, a cgroup running `stress -c 1` with a cpu.max
setting of 5000 10000 shows ~50% continuous CPU pressure.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200316191333.115523-2-hannes@cmpxchg.org
|
|
Currently, when updating the affinity of tasks via either cpusets.cpus,
or, sched_setaffinity(); tasks not currently running within the newly
specified mask will be arbitrarily assigned to the first CPU within the
mask.
This (particularly in the case that we are restricting masks) can
result in many tasks being assigned to the first CPUs of their new
masks.
This:
1) Can induce scheduling delays while the load-balancer has a chance to
spread them between their new CPUs.
2) Can antogonize a poor load-balancer behavior where it has a
difficult time recognizing that a cross-socket imbalance has been
forced by an affinity mask.
This change adds a new cpumask interface to allow iterated calls to
distribute within the intersection of the provided masks.
The cases that this mainly affects are:
- modifying cpuset.cpus
- when tasks join a cpuset
- when modifying a task's affinity via sched_setaffinity(2)
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Tested-by: Qais Yousef <qais.yousef@arm.com>
Link: https://lkml.kernel.org/r/20200311010113.136465-1-joshdon@google.com
|
