For arm-memlat and bimc-hwmon platform driver does not
support the manual bind / unbind feature through sysfs,
when the governor is registered and started.
Suppress the bind / unbind calls using driver attribute.
Change-Id: I8287012e1e6931d80953382f3d625223315cec85
Signed-off-by: Santosh Mardi <gsantosh@codeaurora.org>
commit d1bf2d30728f310f72296b54f0651ecdb09cbb12 upstream.
Propagate the error of devfreq_add_device() in devm_devfreq_add_device()
rather than statically returning ENOMEM. This makes it slightly faster
to pinpoint the cause of a returned error.
Fixes: 8cd84092d3 ("PM / devfreq: Add resource-managed function for devfreq device")
Cc: stable@vger.kernel.org
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add null terminator to end of buffered copied from user to prevent
over reading.
Change-Id: I80cfcb087ea2c335fd65d8fcdaf372c7d34a533d
Signed-off-by: David Dai <daidavid1@codeaurora.org>
Caller of tz_handler() is having the NULL check for devfreq,So
we don’t need unnecessary NULL pointer check.
CRs-Fixed: 2046922
Change-Id: I42eb70ab19b4a5af193521d77bca86447a1ecdb8
Signed-off-by: Hareesh Gundu <hareeshg@codeaurora.org>
Protect polling interval update event in the governor
with mutex lock.
This will avoid parallel execution of update interval event
on different cores, resulting in memory poison overwritten.
CRs-Fixed: 2035633
Change-Id: Ib919d9774317bc01e3cf581c169c5d18555f484f
Signed-off-by: Santosh Mardi <gsantosh@codeaurora.org>
Terminate the interrupts triggered before the intitalisation
itself.
Change-Id: I7c005134ecbdae38b58e4312f9e294f5b59c2510
Signed-off-by: Dilip Kota <dkota@codeaurora.org>
Signed-off-by: Kiran Gunda <kgunda@codeaurora.org>
Current tz_buf pointer type is causing the end address calcultion
of tz_buf to go wrong. "end_addr = tz_buf + PAGE_ALIGN(size)" is
resulting in an end address way beyond the allocated range because
tz_buf is of type unsigned int. This change changes the tz_buf
pointer type to u8 to fix this issue.
Change-Id: I16db09c565801b56c0c0ee8a8184f6e276512fa3
Signed-off-by: Deepak Kumar <dkumar@codeaurora.org>
If the acc_total value is zero then kernel would crash on
div-by-zero. Add better input validation in gpu_load_show()
to avoid divide by zero problem.
CRs-Fixed: 1092584
Change-Id: I7affbd797bf4b0025f718c757043b36f392dae5b
Signed-off-by: Sudeep Yedalapure <sudeepy@codeaurora.org>
If the new governor fails to start, switch back to old governor so that the
devfreq state is not left in some weird limbo.
Change-Id: I7cf1e6ceb63d27ce08b2d17b97a9844d257464ce
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
This adds the freq_map device attribute to the mem_latency governor in
order to display a given device's core frequency to device bandwidth.
The output should be printed in the formatted in the same way as the
example:
Core freq (MHz) Device BW
300 1525
480 3143
900 4173
1017 7759
1296 9887
1555 11863
1804 13763
Change-Id: I6bef33a1239329f0687ee3983c2c02d84e984284
Signed-off-by: David Keitel <dkeitel@codeaurora.org>
During certain code execution paths dev_ab can be assigned
not initialized value.
CRs-Fixed: 1074208
Change-Id: I330a50f6d171497e5b6d3e44e8ce2b09f2d644e3
Signed-off-by: Oleg Perelet <operelet@codeaurora.org>
Fix rounding error that occurs when converting from byte to MB.
Change-Id: Id507e0ae73c42ad5995af0153c3255ad69fde9df
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
The version 4 of the BIMC BWMON hardware now has provisions for
counting bytes transferred at a high sampling rate.
Modify the existing driver and governor algorithm to
take advantage of that.
Change-Id: I5080297aef7e310d5c1a19098c177ddecb729c25
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Signed-off-by: David Keitel <dkeitel@codeaurora.org>
Some HW monitors can do a better job of the sampling and the threshold
checking than the SW implementation in the governor. Update the governor's
API to add support for them.
Change-Id: Id4b5593a5ed3290684ba43ebebe2466ba0b730b6
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
Signed-off-by: David Keitel <dkeitel@codeaurora.org>
Add a core to memory frequency mapping table, which establishes
a relationship between the core frequency and its corresponding
bandwidth vote.
The governor expects a "qcom,core-dev-table" table as part of a given
memlat hardware monitor's device tree node.
This table is read upon registration of the memlat governor. The table
is then used to determine the memory bandwidth vote corresponding to the
maximum of the core frequencies.
CRs-Fixed: 1054146
Change-Id: I9df118da1433125b02c937bf1799a0944b110fac
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Signed-off-by: David Keitel <dkeitel@codeaurora.org>
Suggested-by: Saravana Kannan <skannan@codeaurora.org>
Memory allocated with devm_kzalloc() is automatically freed if
the probe function fails and returns an error code. So there
is no need to free cpu_grp explicitly for the failure cases
that might come up after it is allocated. Additionally calls to
devm_kzalloc() must be accompanied by devm_kfree() if memory
deallocation is necessary.
For these reasons remove the kfree(cpu_grp) from the probe
function.
Change-Id: Ic4838fd58d40d283ac301facc64b06813eb3bd7d
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Enable dev_freq SPDM support in order to increase BIMC
vote based on bus rejection rate. Make cci_clk an optional
property as it's not always a relevant indicator of cpu performance.
CRs-Fixed: 1025515
Change-Id: I713cc396c8d563735981547e0dc18a63f6f15180
Signed-off-by: David Dai <daidavid1@codeaurora.org>
When start_hwmon() runs with another thread trying to hotplug a
CPU the two threads can enter a deadlock situation as follows:
Thread A (start_hwmon()) Thread B (CPU down)
get_online_cpus()
|
atomic_inc(&cpu_hotplug.refcount)
CPU down
|
mutex_lock(&cpu_add_remove_lock)
|
cpu_hotplug_begin() waits on
cpu_hotplug.refcount to reset
register_cpu_notifier()
|
mutex_lock(&cpu_add_remove_lock)
With this change the notifers are registered and unregistered per
device rather than having a common notifier block for all the memlat
devices and unregistration only happens on stop_hwmon. This makes it
possible to move the registration outside the hotplug lock without
any race between multiple memlat devices.
Change-Id: I6ad561fe4967042e45190aea2c9b7fcfe05bafdd
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Substitute 'MSM' in the devfreq device/config names to 'QCOM' to
comply with the current standards.
Change-Id: I156ba6e2b5f8e06a28540ca5def5b178c3604512
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
When the polling interval is updated, the delayed workqueue is cancelled
and requeued with the new polling interval. However, the bw_hwmon IRQ can
come at the same time and try to stop and restart the delayed work (in the
IRQ thread). This can cause a race where the work might be queued twice or
canceled twice and cause a crash.
Fix this race condition by suspending and resuming the HW monitor when we
are updating the polling interval. This entirely avoids the race because
suspending the HW monitor also avoid the possibility of the IRQ coming
during the polling interval update.
CRs-Fixed: 954082
Change-Id: Ic7baf2a3da4ed8f8a9023617059e22fd81c3ba45
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
Add support to use context aware dcvs, if it is supported
by TZ. Context aware dcvs helps in handling sudden workload
scenarios.
Change-Id: I5e6e6003a5c61eacb4f5af91910994919a5a7684
Signed-off-by: Deepak Kumar <dkumar@codeaurora.org>
Signed-off-by: Divya Ponnusamy <pdivya@codeaurora.org>
Add a devicetree property disable-busy-time-burst to
disable ceiling threshold in the governor. The ceiling threshold
cause busy time burst that switch power level for
large frames based on busy time.
Change-Id: I44f8a51e0aa49bb0b2210703f57874fd5f219c18
Signed-off-by: Divya Ponnusamy <pdivya@codeaurora.org>
Fix some variable initializations which would otherwise cause
forbidden warnings.
Signed-off-by: Rohit Vaswani <rvaswani@codeaurora.org>
Signed-off-by: David Keitel <dkeitel@codeaurora.org>
ARCH_MSM has been replaced by ARCH_QCOM. Fix Kconfig for various
devfreq governors and devices.
Change-Id: Ifa85494785cea7eb03be6c02d5664ee6bb2110c6
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
The return value of kstrtouint is erroneously checked while setting
the tunables for mem_latency governor due to which the tunables
cannot be changed from their default values.
This change rectifies that behavior.
Change-Id: Ief7dda4638ede2c97b26229f1188a1559b238920
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Currently stop_hwmon only releases the perf events for each CPU
in the memlat device group. This leaves out the perf_event_attrs
that are not needed anymore leading to memory leaks.
This patch frees perf_event_attrs right after the perf events are
created because they are copied into the perf_event structure
when it is created for a particular event and hence do not need
to exist beyond that point.
Change-Id: If0871739ef477dfbcbbfc6ab2a631ce25deaf71c
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
If any of the CPUs monitored by a memlat device is offline while
trying to register for perf events, the registration fails
returning an error code to the governor's start_monitor function
which then fails the setting of governor and leaves the system in
a bad state.
To avoid this scenario, this patch allows for initialization errors
while registering for perf events and remembers the failing offline
CPUs. Perf event registration is tried for the failing CPUs when they
come back online. Once all the CPUs have registered for perf events
hotplug notifiers callbacks are unregistered.
Change-Id: I36c33d9dc627f60ab9d7db41913661927938e850
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
clk_set_rate is failing for some of the frequencies due to higher
precision introduced in clock driver. Hence call the clk_round_rate
again in dev_target to make sure we send the correct frequency to
clk_set_rate.
Change-Id: I3e40690bf794d99debbcecdcaf05aaac3363caa8
Signed-off-by: Hanumath Prasad <hpprasad@codeaurora.org>
The of_node_put(of_child) call was put in to balance the of_node_get()
that's done inside for_each_child_of_node(). But that's not the right thing
to do because for_each_child_of_node() already takes care of doing
of_node_put(). So, delete the unnecessary of_node_put(of_child) call. We
still need the of_node_put(of_par) though.
Change-Id: Iff7744839cfcf01d5a472449f74859e9030b7e16
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
Currently arm-memlat-mon driver uses cpu_coregroup_mask to get
the sibling CPUs for the first CPU specified during the probe.
However if any of the CPUs in a cluster isn't hotplugged in
even once before the probe runs then the call to cpu_coregroup_mask
might not give the updated list of all the sibling CPUs for the
specified CPU.
With this change the initialization of the cpumask for the memlat
device is obtained from the list of CPU phandles specified in the
dtsi file.
Change-Id: Ide97d60d9eecbbe1d33deda72a13951059822896
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
[junjiew@codeaurora.org: dropped changes in dtsi files.]
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
Use performance counters to detect the memory latency sensitivity
of CPU workloads and vote for higher DDR frequency if required.
Change-Id: Ie77a3523bc5713fc0315bd0abc3913f485a96e0e
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Suggested-by: Saravana Kannan <skannan@codeaurora.org>
[junjiew@codeaurora.org: dropped changes in arch/arm64/Kconfig]
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
Newer versions of bimc-bwmon counters have the capability to fake
higher byte count than what's actually transferred between a bus
master and DDR if the bus master is being throttled by QoS hardware
logic. Add support to set the throttle adjust field that comes with
this newer version of bimc-bwmon.
Change-Id: I33376c825fb11ab2e378f828b1d2ae46dd582836
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
[junjiew@codeaurora.org: dropped changes in dtsi.]
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
When doing over-voting due to an UP_WAKE event, the governor
pre-initialized the max_mbps value for the next decision window. This was
done to prevent a dropping the vote below the original measurement in case
a DOWN_WAKE event comes before the decision window is complete. This has
the undesirable side-effect of keeping the votes high for two decision
windows following an UP_WAKE event.
Also, DOWN_WAKE event is currently disabled for any decision windows that
didn't do over-voting because doing so had significant performance impacts.
However, with historic max tracking, pattern detection and hysteresis, and
mbps zones awareness that were added later on, the above concerns aren't
really valid anymore. So, simply delete the pre-initialization of the
max_mbps so that one decision window isn't unnecessarily voting higher than
necessary. As part of the change, also fix down_cnt logic to allow it to
work for all decision windows if enabled.
Change-Id: I600e3783da617ed4efef5b05156016d88c301cea
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
Currently the lower limit for setting up_scale is 100. Change it
to 0 so that over-voting for spikes in measured bandwidth can be
disabled by setting up_scale to 0.
Change-Id: I1e5e3d51c625163b38074fb1eda26763455ea6c5
Signed-off-by: Rohit Gupta <rohgup@codeaurora.org>
Using debug logs for the short samples would result in excessive logging
and also have an impact on CPU power and performance. The tracepoint that's
already there is a much better alternative. So, delete the debug logs.
Change-Id: Idd1d634f510381d14637f3b84588a118572f3f16
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
The IRQ registration on the resume path was not updated properly when the
high sampling rate algorithm was implemented. Update it so that the IRQ
registration is done correctly.
Change-Id: I17a016dd9c0b50c7b415beda21368cb4586d203c
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
Replace measured mrps and frequency vote debug prints with trace
events.
Change-Id: I78370b068e3819a57635cbabaf5cdd053ebabce4
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
Change the sequence of registering and freeing the interrupt
handler in suspend/resume. Freeirq needs a guarantee that the
IRQ can't come anymore before we call it. So, we disable the IRQ
before calling freeirq.And register the handler before enabling
the irq to avoid the interrupt getting unhandled.
Change-Id: I3945202d049e16f64a16e456f914f7602b763c89
Signed-off-by: Hanumath Prasad <hpprasad@codeaurora.org>
Due to the way the short samples are triggered, when the traffic is very
low, we could have a decision window where no sample is taken. Fix this by
forcing a sample at the end of every decision window as long as that is the
first sample for that decision window or the sample window won't be smaller
than the sample_ms tunable.
Change-Id: Ia33b59fbff9ff4058c06e24208d1e037d6e9eda9
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
With the rewrite of the algorithm, some tunables are not used. Remove those
tunables. Other tunables don't make a lot of sense to be turned on by
default. Change their default state to be disabled.
Change-Id: I228d275a21765986a7117b335a669deebf590f29
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
When the decision window is terminated early by an IRQ and the frequency
voted by the governor is the max_freq allowed for that device, the AB vote
can be lower than the measured value. This really shouldn't affect power or
performance since the device frequency is already maxed out, but fix it
anyway so that the logs don't look suspicious.
Signed-off-by: Saravana Kannan <skannan@codeaurora.org>
Change-Id: I1788cbb1af026f1c54f9acc4806cb29cd6069e04
M4M counters are only 28-bit instead of 32-bit. Fix limit calculation
to use the right max value.
Change-Id: I91078842b72da80f6b6755bf8d808ff4b4142f10
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
Enable cycle counter along with other counters when m4m_hwmon is
started.
Change-Id: Idd86b99c21e21f64bb91db9b1e64597fbfb2306a
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
Some targets have a single irq line which is shared among all
the cci hwmon counters. Enhance the driver to support shared interrupt
handling.
Change-Id: I5fdaecfaa14fa47e8f393fe51c538e5000e6ad5b
Signed-off-by: Arun KS <arunks@codeaurora.org>
Signed-off-by: Hanumath Prasad <hpprasad@codeaurora.org>
For certain implementation, device clock needs to be prepared before
rate voting taking effect. Add support for preparing device clock
during initialization.
Change-Id: Ib22e83952187118342ff2546d4c79d3970a288f9
Signed-off-by: Junjie Wu <junjiew@codeaurora.org>
