linux-stable.git/drivers/cpufreq, branch v4.14.78 Linux kernel stable tree cpufreq: governor: Avoid accessing invalid governor_data 2018-09-09T17:55:58+00:00 Henry Willard henry.willard@oracle.com 2018-08-15T00:01:02+00:00 924383edf44c2a4190820853c6e33c0deb24d98a commit 2a3eb51e30b9ac66fe1b75877627a7e4aaeca24a upstream. If cppc_cpufreq.ko is deleted at the same time that tuned-adm is changing profiles, there is a small chance that a race can occur between cpufreq_dbs_governor_exit() and cpufreq_dbs_governor_limits() resulting in a system failure when the latter tries to use policy->governor_data that has been freed by the former. This patch uses gov_dbs_data_mutex to synchronize access. Fixes: e788892ba3cc (cpufreq: governor: Get rid of governor events) Signed-off-by: Henry Willard <henry.willard@oracle.com> [ rjw: Subject, minor white space adjustment ] Cc: 4.8+ <stable@vger.kernel.org> # 4.8+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 2a3eb51e30b9ac66fe1b75877627a7e4aaeca24a upstream.

If cppc_cpufreq.ko is deleted at the same time that tuned-adm is
changing profiles, there is a small chance that a race can occur
between cpufreq_dbs_governor_exit() and cpufreq_dbs_governor_limits()
resulting in a system failure when the latter tries to use
policy->governor_data that has been freed by the former.

This patch uses gov_dbs_data_mutex to synchronize access.

Fixes: e788892ba3cc (cpufreq: governor: Get rid of governor events)
Signed-off-by: Henry Willard <henry.willard@oracle.com>
[ rjw: Subject, minor white space adjustment ]
Cc: 4.8+ <stable@vger.kernel.org> # 4.8+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: intel_pstate: Register when ACPI PCCH is present 2018-07-25T09:25:08+00:00 Rafael J. Wysocki rafael.j.wysocki@intel.com 2018-07-18T11:38:37+00:00 dfc328156ddea2385394240c373a49bb42320b4c commit 95d6c0857e54b788982746071130d822a795026b upstream. Currently, intel_pstate doesn't register if _PSS is not present on HP Proliant systems, because it expects the firmware to take over CPU performance scaling in that case. However, if ACPI PCCH is present, the firmware expects the kernel to use it for CPU performance scaling and the pcc-cpufreq driver is loaded for that. Unfortunately, the firmware interface used by that driver is not scalable for fundamental reasons, so pcc-cpufreq is way suboptimal on systems with more than just a few CPUs. In fact, it is better to avoid using it at all. For this reason, modify intel_pstate to look for ACPI PCCH if _PSS is not present and register if it is there. Also prevent the pcc-cpufreq driver from trying to initialize itself if intel_pstate has been registered already. Fixes: fbbcdc0744da (intel_pstate: skip the driver if ACPI has power mgmt option) Reported-by: Andreas Herrmann <aherrmann@suse.com> Reviewed-by: Andreas Herrmann <aherrmann@suse.com> Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Tested-by: Andreas Herrmann <aherrmann@suse.com> Cc: 4.16+ <stable@vger.kernel.org> # 4.16+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 95d6c0857e54b788982746071130d822a795026b upstream.

Currently, intel_pstate doesn't register if _PSS is not present on
HP Proliant systems, because it expects the firmware to take over
CPU performance scaling in that case.  However, if ACPI PCCH is
present, the firmware expects the kernel to use it for CPU
performance scaling and the pcc-cpufreq driver is loaded for that.

Unfortunately, the firmware interface used by that driver is not
scalable for fundamental reasons, so pcc-cpufreq is way suboptimal
on systems with more than just a few CPUs.  In fact, it is better to
avoid using it at all.

For this reason, modify intel_pstate to look for ACPI PCCH if _PSS
is not present and register if it is there.  Also prevent the
pcc-cpufreq driver from trying to initialize itself if intel_pstate
has been registered already.

Fixes: fbbcdc0744da (intel_pstate: skip the driver if ACPI has power mgmt option)
Reported-by: Andreas Herrmann <aherrmann@suse.com>
Reviewed-by: Andreas Herrmann <aherrmann@suse.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Tested-by: Andreas Herrmann <aherrmann@suse.com>
Cc: 4.16+ <stable@vger.kernel.org> # 4.16+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq / CPPC: Set platform specific transition_delay_us 2018-07-22T12:28:42+00:00 Prashanth Prakash pprakash@codeaurora.org 2018-04-27T17:35:27+00:00 1083a7e8130ca54cef63a5b1d6c86878d4b9e61d commit d4f3388afd488ed15368fa7413b8bd6d1f98bb1d upstream. Add support to specify platform specific transition_delay_us instead of using the transition delay derived from PCC. With commit 3d41386d556d (cpufreq: CPPC: Use transition_delay_us depending transition_latency) we are setting transition_delay_us directly and not applying the LATENCY_MULTIPLIER. Because of that, on Qualcomm Centriq we can end up with a very high rate of frequency change requests when using the schedutil governor (default rate_limit_us=10 compared to an earlier value of 10000). The PCC subspace describes the rate at which the platform can accept commands on the CPPC's PCC channel. This includes read and write command on the PCC channel that can be used for reasons other than frequency transitions. Moreover the same PCC subspace can be used by multiple freq domains and deriving transition_delay_us from it as we do now can be sub-optimal. Moreover if a platform does not use PCC for desired_perf register then there is no way to compute the transition latency or the delay_us. CPPC does not have a standard defined mechanism to get the transition rate or the latency at the moment. Given the above limitations, it is simpler to have a platform specific transition_delay_us and rely on PCC derived value only if a platform specific value is not available. Signed-off-by: Prashanth Prakash <pprakash@codeaurora.org> Cc: 4.14+ <stable@vger.kernel.org> # 4.14+ Fixes: 3d41386d556d (cpufreq: CPPC: Use transition_delay_us depending transition_latency) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit d4f3388afd488ed15368fa7413b8bd6d1f98bb1d upstream.

Add support to specify platform specific transition_delay_us instead
of using the transition delay derived from PCC.

With commit 3d41386d556d (cpufreq: CPPC: Use transition_delay_us
depending transition_latency) we are setting transition_delay_us
directly and not applying the LATENCY_MULTIPLIER. Because of that,
on Qualcomm Centriq we can end up with a very high rate of frequency
change requests when using the schedutil governor (default
rate_limit_us=10 compared to an earlier value of 10000).

The PCC subspace describes the rate at which the platform can accept
commands on the CPPC's PCC channel. This includes read and write
command on the PCC channel that can be used for reasons other than
frequency transitions. Moreover the same PCC subspace can be used by
multiple freq domains and deriving transition_delay_us from it as we
do now can be sub-optimal.

Moreover if a platform does not use PCC for desired_perf register then
there is no way to compute the transition latency or the delay_us.

CPPC does not have a standard defined mechanism to get the transition
rate or the latency at the moment.

Given the above limitations, it is simpler to have a platform specific
transition_delay_us and rely on PCC derived value only if a platform
specific value is not available.

Signed-off-by: Prashanth Prakash <pprakash@codeaurora.org>
Cc: 4.14+ <stable@vger.kernel.org> # 4.14+
Fixes: 3d41386d556d (cpufreq: CPPC: Use transition_delay_us depending transition_latency)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: intel_pstate: Fix scaling max/min limits with Turbo 3.0 2018-07-03T09:24:56+00:00 Srinivas Pandruvada srinivas.pandruvada@linux.intel.com 2018-06-18T19:47:45+00:00 93e1297f9edce474df6839d5434a511cb130a4a2 commit ff7c9917143b3a6cf2fa61212a32d67cf259bf9c upstream. When scaling max/min settings are changed, internally they are converted to a ratio using the max turbo 1 core turbo frequency. This works fine when 1 core max is same irrespective of the core. But under Turbo 3.0, this will not be the case. For example: Core 0: max turbo pstate: 43 (4.3GHz) Core 1: max turbo pstate: 45 (4.5GHz) In this case 1 core turbo ratio will be maximum of all, so it will be 45 (4.5GHz). Suppose scaling max is set to 4GHz (ratio 40) for all cores ,then on core one it will be = max_state * policy->max / max_freq; = 43 * (4000000/4500000) = 38 (3.8GHz) = 38 which is 200MHz less than the desired. On core2, it will be correctly set to ratio 40 (4GHz). Same holds true for scaling min frequency limit. So this requires usage of correct turbo max frequency for core one, which in this case is 4.3GHz. So we need to adjust per CPU cpu->pstate.turbo_freq using the maximum HWP ratio of that core. This change uses the HWP capability of a core to adjust max turbo frequency. But since Broadwell HWP doesn't use ratios in the HWP capabilities, we have to use legacy max 1 core turbo ratio. This is not a problem as the HWP capabilities don't differ among cores in Broadwell. We need to check for non Broadwell CPU model for applying this change, though. Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Cc: 4.6+ <stable@vger.kernel.org> # 4.6+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit ff7c9917143b3a6cf2fa61212a32d67cf259bf9c upstream.

When scaling max/min settings are changed, internally they are converted
to a ratio using the max turbo 1 core turbo frequency. This works fine
when 1 core max is same irrespective of the core. But under Turbo 3.0,
this will not be the case. For example:
Core 0: max turbo pstate: 43 (4.3GHz)
Core 1: max turbo pstate: 45 (4.5GHz)
In this case 1 core turbo ratio will be maximum of all, so it will be
45 (4.5GHz). Suppose scaling max is set to 4GHz (ratio 40) for all cores
,then on core one it will be
 = max_state * policy->max / max_freq;
 = 43 * (4000000/4500000) = 38 (3.8GHz)
 = 38
which is 200MHz less than the desired.
On core2, it will be correctly set to ratio 40 (4GHz). Same holds true
for scaling min frequency limit. So this requires usage of correct turbo
max frequency for core one, which in this case is 4.3GHz. So we need to
adjust per CPU cpu->pstate.turbo_freq using the maximum HWP ratio of that
core.

This change uses the HWP capability of a core to adjust max turbo
frequency. But since Broadwell HWP doesn't use ratios in the HWP
capabilities, we have to use legacy max 1 core turbo ratio. This is not
a problem as the HWP capabilities don't differ among cores in Broadwell.
We need to check for non Broadwell CPU model for applying this change,
though.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: 4.6+ <stable@vger.kernel.org> # 4.6+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: governors: Fix long idle detection logic in load calculation 2018-06-26T00:06:32+00:00 Chen Yu yu.c.chen@intel.com 2018-06-08T01:07:33+00:00 1404d2e5dd3647d9bec8960c7dc90aea7cbd8b63 commit 7592019634f8473f0b0973ce79297183077bdbc2 upstream. According to current code implementation, detecting the long idle period is done by checking if the interval between two adjacent utilization update handlers is long enough. Although this mechanism can detect if the idle period is long enough (no utilization hooks invoked during idle period), it might not cover a corner case: if the task has occupied the CPU for too long which causes no context switches during that period, then no utilization handler will be launched until this high prio task is scheduled out. As a result, the idle_periods field might be calculated incorrectly because it regards the 100% load as 0% and makes the conservative governor who uses this field confusing. Change the detection to compare the idle_time with sampling_rate directly. Reported-by: Artem S. Tashkinov <t.artem@mailcity.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: All applicable <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 7592019634f8473f0b0973ce79297183077bdbc2 upstream.

According to current code implementation, detecting the long
idle period is done by checking if the interval between two
adjacent utilization update handlers is long enough. Although
this mechanism can detect if the idle period is long enough
(no utilization hooks invoked during idle period), it might
not cover a corner case: if the task has occupied the CPU
for too long which causes no context switches during that
period, then no utilization handler will be launched until this
high prio task is scheduled out. As a result, the idle_periods
field might be calculated incorrectly because it regards the
100% load as 0% and makes the conservative governor who uses
this field confusing.

Change the detection to compare the idle_time with sampling_rate
directly.

Reported-by: Artem S. Tashkinov <t.artem@mailcity.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: Fix new policy initialization during limits updates via sysfs 2018-06-26T00:06:32+00:00 Tao Wang kevin.wangtao@hisilicon.com 2018-05-26T07:16:48+00:00 c3c77b5db39350c8d64c85102138ab9ba6066815 commit c7d1f119c48f64bebf0fa1e326af577c6152fe30 upstream. If the policy limits are updated via cpufreq_update_policy() and subsequently via sysfs, the limits stored in user_policy may be set incorrectly. For example, if both min and max are set via sysfs to the maximum available frequency, user_policy.min and user_policy.max will also be the maximum. If a policy notifier triggered by cpufreq_update_policy() lowers both the min and the max at this point, that change is not reflected by the user_policy limits, so if the max is updated again via sysfs to the same lower value, then user_policy.max will be lower than user_policy.min which shouldn't happen. In particular, if one of the policy CPUs is then taken offline and back online, cpufreq_set_policy() will fail for it due to a failing limits check. To prevent that from happening, initialize the min and max fields of the new_policy object to the ones stored in user_policy that were previously set via sysfs. Signed-off-by: Kevin Wangtao <kevin.wangtao@hisilicon.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> [ rjw: Subject & changelog ] Cc: All applicable <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit c7d1f119c48f64bebf0fa1e326af577c6152fe30 upstream.

If the policy limits are updated via cpufreq_update_policy() and
subsequently via sysfs, the limits stored in user_policy may be
set incorrectly.

For example, if both min and max are set via sysfs to the maximum
available frequency, user_policy.min and user_policy.max will also
be the maximum.  If a policy notifier triggered by
cpufreq_update_policy() lowers both the min and the max at this
point, that change is not reflected by the user_policy limits, so
if the max is updated again via sysfs to the same lower value,
then user_policy.max will be lower than user_policy.min which
shouldn't happen.  In particular, if one of the policy CPUs is
then taken offline and back online, cpufreq_set_policy() will
fail for it due to a failing limits check.

To prevent that from happening, initialize the min and max fields
of the new_policy object to the ones stored in user_policy that
were previously set via sysfs.

Signed-off-by: Kevin Wangtao <kevin.wangtao@hisilicon.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
[ rjw: Subject & changelog ]
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: Reorder cpufreq_online() error code path 2018-05-30T05:52:38+00:00 Viresh Kumar viresh.kumar@linaro.org 2018-02-22T05:59:43+00:00 602234ea4466443e3b7e6272a806973e7617897c [ Upstream commit b24b6478e65f140610ab1ffaadc7bc6bf0be8aad ] Ideally the de-allocation of resources should happen in the exact opposite order in which they were allocated. It helps maintain the code in long term, even if nothing really breaks with incorrect ordering. That wasn't followed in cpufreq_online() and it has some inconsistencies. For example, the symlinks were created from within the locked region while they are removed only after putting the locks. Also ->exit() should have been called only after the symlinks are removed and the lock is dropped, as that was the case when ->init() was first called. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> [ rjw: Subject ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit b24b6478e65f140610ab1ffaadc7bc6bf0be8aad ]

Ideally the de-allocation of resources should happen in the exact
opposite order in which they were allocated. It helps maintain the code
in long term, even if nothing really breaks with incorrect ordering.

That wasn't followed in cpufreq_online() and it has some
inconsistencies.  For example, the symlinks were created from within
the locked region while they are removed only after putting the locks.
Also ->exit() should have been called only after the symlinks are
removed and the lock is dropped, as that was the case when ->init()
was first called.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
[ rjw: Subject ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: cppc_cpufreq: Fix cppc_cpufreq_init() failure path 2018-05-30T05:52:30+00:00 Chunyu Hu chuhu@redhat.com 2018-03-05T05:40:38+00:00 4a8b1c46af586914b42773b4181052cc3c7cb0d3 [ Upstream commit 55b55abc17f238c61921360e61dde90dd9a326d1 ] Kmemleak reported the below leak. When cppc_cpufreq_init went into failure path, the cpu mask is not freed. After fix, this report is gone. And to avaoid potential NULL pointer reference, check the cpu value first. unreferenced object 0xffff800fd5ea4880 (size 128): comm "swapper/0", pid 1, jiffies 4294939510 (age 668.680s) hex dump (first 32 bytes): 00 00 00 00 20 00 00 00 00 00 00 00 00 00 00 00 .... ........... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffff0000082c4ae4>] __kmalloc_node+0x278/0x634 [<ffff0000088f4a74>] alloc_cpumask_var_node+0x28/0x60 [<ffff0000088f4af0>] zalloc_cpumask_var+0x14/0x1c [<ffff000008d20254>] cppc_cpufreq_init+0xd0/0x19c [<ffff000008083828>] do_one_initcall+0xec/0x15c [<ffff000008cd1018>] kernel_init_freeable+0x1f4/0x2a4 [<ffff0000089099b0>] kernel_init+0x18/0x10c [<ffff000008084d50>] ret_from_fork+0x10/0x18 [<ffffffffffffffff>] 0xffffffffffffffff Signed-off-by: Chunyu Hu <chuhu@redhat.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 55b55abc17f238c61921360e61dde90dd9a326d1 ]

Kmemleak reported the below leak. When cppc_cpufreq_init went into
failure path, the cpu mask is not freed. After fix, this report is
gone. And to avaoid potential NULL pointer reference, check the cpu
value first.

unreferenced object 0xffff800fd5ea4880 (size 128):
  comm "swapper/0", pid 1, jiffies 4294939510 (age 668.680s)
  hex dump (first 32 bytes):
    00 00 00 00 20 00 00 00 00 00 00 00 00 00 00 00  .... ...........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffff0000082c4ae4>] __kmalloc_node+0x278/0x634
    [<ffff0000088f4a74>] alloc_cpumask_var_node+0x28/0x60
    [<ffff0000088f4af0>] zalloc_cpumask_var+0x14/0x1c
    [<ffff000008d20254>] cppc_cpufreq_init+0xd0/0x19c
    [<ffff000008083828>] do_one_initcall+0xec/0x15c
    [<ffff000008cd1018>] kernel_init_freeable+0x1f4/0x2a4
    [<ffff0000089099b0>] kernel_init+0x18/0x10c
    [<ffff000008084d50>] ret_from_fork+0x10/0x18
    [<ffffffffffffffff>] 0xffffffffffffffff

Signed-off-by: Chunyu Hu <chuhu@redhat.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: CPPC: Initialize shared perf capabilities of CPUs 2018-05-30T05:52:23+00:00 Shunyong Yang shunyong.yang@hxt-semitech.com 2018-04-06T02:43:49+00:00 96fdc64d8eda887ae1a290b4f11f67a4a942d949 [ Upstream commit 8913315e9459b146e5888ab5138e10daa061b885 ] When multiple CPUs are related in one cpufreq policy, the first online CPU will be chosen by default to handle cpufreq operations. Let's take cpu0 and cpu1 as an example. When cpu0 is offline, policy->cpu will be shifted to cpu1. cpu1's perf capabilities should be initialized. Otherwise, perf capabilities are 0s and speed change can not take effect. This patch copies perf capabilities of the first online CPU to other shared CPUs when policy shared type is CPUFREQ_SHARED_TYPE_ANY. Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Shunyong Yang <shunyong.yang@hxt-semitech.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 8913315e9459b146e5888ab5138e10daa061b885 ]

When multiple CPUs are related in one cpufreq policy, the first online
CPU will be chosen by default to handle cpufreq operations. Let's take
cpu0 and cpu1 as an example.

When cpu0 is offline, policy->cpu will be shifted to cpu1. cpu1's perf
capabilities should be initialized. Otherwise, perf capabilities are 0s
and speed change can not take effect.

This patch copies perf capabilities of the first online CPU to other
shared CPUs when policy shared type is CPUFREQ_SHARED_TYPE_ANY.

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Shunyong Yang <shunyong.yang@hxt-semitech.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cpufreq: powernv: Fix hardlockup due to synchronous smp_call in timer interrupt 2018-05-01T19:58:24+00:00 Shilpasri G Bhat shilpa.bhat@linux.vnet.ibm.com 2018-04-25T10:59:31+00:00 20b0f757da3be5a7c5f14f95250b9c8efcaee02d commit c0f7f5b6c69107ca92909512533e70258ee19188 upstream. gpstate_timer_handler() uses synchronous smp_call to set the pstate on the requested core. This causes the below hard lockup: smp_call_function_single+0x110/0x180 (unreliable) smp_call_function_any+0x180/0x250 gpstate_timer_handler+0x1e8/0x580 call_timer_fn+0x50/0x1c0 expire_timers+0x138/0x1f0 run_timer_softirq+0x1e8/0x270 __do_softirq+0x158/0x3e4 irq_exit+0xe8/0x120 timer_interrupt+0x9c/0xe0 decrementer_common+0x114/0x120 -- interrupt: 901 at doorbell_global_ipi+0x34/0x50 LR = arch_send_call_function_ipi_mask+0x120/0x130 arch_send_call_function_ipi_mask+0x4c/0x130 smp_call_function_many+0x340/0x450 pmdp_invalidate+0x98/0xe0 change_huge_pmd+0xe0/0x270 change_protection_range+0xb88/0xe40 mprotect_fixup+0x140/0x340 SyS_mprotect+0x1b4/0x350 system_call+0x58/0x6c One way to avoid this is removing the smp-call. We can ensure that the timer always runs on one of the policy-cpus. If the timer gets migrated to a cpu outside the policy then re-queue it back on the policy->cpus. This way we can get rid of the smp-call which was being used to set the pstate on the policy->cpus. Fixes: 7bc54b652f13 ("timers, cpufreq/powernv: Initialize the gpstate timer as pinned") Cc: stable@vger.kernel.org # v4.8+ Reported-by: Nicholas Piggin <npiggin@gmail.com> Reported-by: Pridhiviraj Paidipeddi <ppaidipe@linux.vnet.ibm.com> Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com> Acked-by: Nicholas Piggin <npiggin@gmail.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit c0f7f5b6c69107ca92909512533e70258ee19188 upstream.

gpstate_timer_handler() uses synchronous smp_call to set the pstate
on the requested core. This causes the below hard lockup:

  smp_call_function_single+0x110/0x180 (unreliable)
  smp_call_function_any+0x180/0x250
  gpstate_timer_handler+0x1e8/0x580
  call_timer_fn+0x50/0x1c0
  expire_timers+0x138/0x1f0
  run_timer_softirq+0x1e8/0x270
  __do_softirq+0x158/0x3e4
  irq_exit+0xe8/0x120
  timer_interrupt+0x9c/0xe0
  decrementer_common+0x114/0x120
  -- interrupt: 901 at doorbell_global_ipi+0x34/0x50
  LR = arch_send_call_function_ipi_mask+0x120/0x130
  arch_send_call_function_ipi_mask+0x4c/0x130
  smp_call_function_many+0x340/0x450
  pmdp_invalidate+0x98/0xe0
  change_huge_pmd+0xe0/0x270
  change_protection_range+0xb88/0xe40
  mprotect_fixup+0x140/0x340
  SyS_mprotect+0x1b4/0x350
  system_call+0x58/0x6c

One way to avoid this is removing the smp-call. We can ensure that the
timer always runs on one of the policy-cpus. If the timer gets
migrated to a cpu outside the policy then re-queue it back on the
policy->cpus. This way we can get rid of the smp-call which was being
used to set the pstate on the policy->cpus.

Fixes: 7bc54b652f13 ("timers, cpufreq/powernv: Initialize the gpstate timer as pinned")
Cc: stable@vger.kernel.org # v4.8+
Reported-by: Nicholas Piggin <npiggin@gmail.com>
Reported-by: Pridhiviraj Paidipeddi <ppaidipe@linux.vnet.ibm.com>
Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>