[PATCH v4 0/4] cpufreq: qcom-hw: Fixes for cpu hotplug support

[PATCH v4 0/4] cpufreq: qcom-hw: Fixes for cpu hotplug support

[Dmitry Baryshkov]

This patchseries aims at fixing and improving CPU hotplug support on
Qualcomm platforms. First three patches are the fixes for the LMH
support in the cpufreq driver. The last patch adds support for
lightweight offline() and online() callbacks which are used instead of
exit() and init() each time the CPU is put offline or back online.

Patches 1-3 being pure simple fixes can be applied during the -rc
stage, while patch 4 is targeting next development cycle

Changes since v3:
- Readd throttled_freq calculation disappearing from the third patch.

Changes since v2:
- Point Fixes tag from the first patch to the correct commit
- Replace huge patch 2 with one-liner thanks to being able to use
  policy->related_cpus instead of policy->cpus

Changes since v1:
- Update commit message for the first patch to describe why dropping
  affinity hint is required (before calling free_irq()),
- Fixed commit message for the second patch to include messages
  generated using the mainline kernel w/o additional patches,
- Changed third patch to use dev_warn_ratelimited(),
- Reworked last patch to move request_irq/free_irq to online()/offline()
  to make sure that the IRQ isn't left enabled after the CPU has been
  put offline.


Dmitry Baryshkov (4):
  cpufreq: qcom-hw: drop affinity hint before freeing the IRQ
  cpufreq: qcom-hw: fix the race between LMH worker and cpuhp
  cpufreq: qcom-hw: fix the opp entries refcounting
  cpufreq: qcom-hw: provide online/offline operations

 drivers/cpufreq/qcom-cpufreq-hw.c | 45 ++++++++++++++++++++++++++-----
 1 file changed, 38 insertions(+), 7 deletions(-)

-- 
2.35.1

[PATCH v4 1/4] cpufreq: qcom-hw: drop affinity hint before freeing the IRQ

[Dmitry Baryshkov]

Drop affinity hint before freeing the throttling IRQ to fix the
following trace:

[  185.114773] ------------[ cut here ]------------
[  185.119517] WARNING: CPU: 7 PID: 43 at kernel/irq/manage.c:1887 free_irq+0x3a4/0x3dc
[  185.127474] Modules linked in:
[  185.130618] CPU: 7 PID: 43 Comm: cpuhp/7 Tainted: G S      W         5.17.0-rc6-00386-g67382a5b705d-dirty #690
[  185.147125] pstate: 604000c5 (nZCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[  185.154269] pc : free_irq+0x3a4/0x3dc
[  185.158031] lr : free_irq+0x33c/0x3dc
[  185.161792] sp : ffff80000841bc90
[  185.165195] x29: ffff80000841bc90 x28: ffffa6edc5c3d000 x27: ffff6d93729e5908
[  185.172515] x26: 0000000000000000 x25: ffff6d910109fc00 x24: ffff6d91011490e0
[  185.179838] x23: ffff6d9101149218 x22: 0000000000000080 x21: 0000000000000000
[  185.187163] x20: ffff6d9101149000 x19: ffff6d910ab61500 x18: ffffffffffffffff
[  185.194487] x17: 2e35202020202020 x16: 2020202020202020 x15: ffff80008841b9a7
[  185.201805] x14: 00000000000003c9 x13: 0000000000000001 x12: 0000000000000040
[  185.209135] x11: ffff6d91005aab58 x10: ffff6d91005aab5a x9 : ffffc6a5ad1c5408
[  185.216455] x8 : ffff6d91005adb88 x7 : 0000000000000000 x6 : ffffc6a5ab5a91f4
[  185.223776] x5 : 0000000000000000 x4 : ffff6d91011490a8 x3 : ffffc6a5ad266108
[  185.231098] x2 : 0000000013033204 x1 : ffff6d9101149000 x0 : ffff6d910a9cc000
[  185.238421] Call trace:
[  185.240932]  free_irq+0x3a4/0x3dc
[  185.244334]  qcom_cpufreq_hw_cpu_exit+0x78/0xcc
[  185.248985]  cpufreq_offline.isra.0+0x228/0x270
[  185.253639]  cpuhp_cpufreq_offline+0x10/0x20
[  185.258027]  cpuhp_invoke_callback+0x16c/0x2b0
[  185.262592]  cpuhp_thread_fun+0x190/0x250
[  185.266710]  smpboot_thread_fn+0x12c/0x230
[  185.270914]  kthread+0xfc/0x100
[  185.274145]  ret_from_fork+0x10/0x20
[  185.277820] irq event stamp: 212
[  185.281136] hardirqs last  enabled at (211): [<ffffc6a5ac57973c>] _raw_spin_unlock_irqrestore+0x8c/0xa0
[  185.290775] hardirqs last disabled at (212): [<ffffc6a5ac572100>] __schedule+0x710/0xa10
[  185.299081] softirqs last  enabled at (0): [<ffffc6a5ab50f7b0>] copy_process+0x7d0/0x1a14
[  185.307475] softirqs last disabled at (0): [<0000000000000000>] 0x0

Fixes: 3ed6dfbd3bb98 ("cpufreq: qcom-hw: Set CPU affinity of dcvsh interrupts")
Tested-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 618e436018c0..44d46e52baea 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -427,6 +427,7 @@ static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
 	mutex_unlock(&data->throttle_lock);
 
 	cancel_delayed_work_sync(&data->throttle_work);
+	irq_set_affinity_hint(data->throttle_irq, NULL);
 	free_irq(data->throttle_irq, data);
 }
 
-- 
2.35.1

[PATCH v4 2/4] cpufreq: qcom-hw: fix the race between LMH worker and cpuhp

[Dmitry Baryshkov]

The driver would disable the worker when cpu is being put offline, but
it happens closer to the end of cpufreq_offline(). The function
qcom_lmh_dcvs_poll() can be running in parallel with this, when
policy->cpus already has been updated. Read policy->related_cpus
instead.

[   37.122433] ------------[ cut here ]------------
[   37.127225] WARNING: CPU: 0 PID: 187 at drivers/base/arch_topology.c:180 topology_update_thermal_pressure+0xec/0x100
[   37.138098] Modules linked in:
[   37.141279] CPU: 0 PID: 187 Comm: kworker/0:3 Tainted: G S                5.17.0-rc6-00389-g37c83d0b8710-dirty #713
[   37.158306] Workqueue: events qcom_lmh_dcvs_poll
[   37.163095] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   37.170278] pc : topology_update_thermal_pressure+0xec/0x100
[   37.176131] lr : topology_update_thermal_pressure+0x20/0x100
[   37.181977] sp : ffff800009b6bce0
[   37.185402] x29: ffff800009b6bce0 x28: ffffd87abe92b000 x27: ffff04bd7292e205
[   37.192792] x26: ffffd87abe930af8 x25: ffffd87abe94e4c8 x24: 0000000000000000
[   37.200180] x23: ffff04bb01177018 x22: ffff04bb011770c0 x21: ffff04bb01177000
[   37.207567] x20: ffff04bb0a419000 x19: 00000000000c4e00 x18: 0000000000000000
[   37.214954] x17: 000000040044ffff x16: 004000b2b5503510 x15: 0000006aaa1326d2
[   37.222333] x14: 0000000000000232 x13: 0000000000000001 x12: 0000000000000040
[   37.229718] x11: ffff04bb00400000 x10: 968f57bd39f701c8 x9 : ffff04bb0acc8674
[   37.237095] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffffd87abd90092c
[   37.244478] x5 : 0000000000000016 x4 : 0000000000000000 x3 : 0000000000000100
[   37.251852] x2 : ffff04bb0a419020 x1 : 0000000000000100 x0 : 0000000000000100
[   37.259235] Call trace:
[   37.261771]  topology_update_thermal_pressure+0xec/0x100
[   37.267266]  qcom_lmh_dcvs_poll+0xbc/0x154
[   37.271505]  process_one_work+0x288/0x69c
[   37.275654]  worker_thread+0x74/0x470
[   37.279450]  kthread+0xfc/0x100
[   37.282712]  ret_from_fork+0x10/0x20
[   37.286417] irq event stamp: 74
[   37.289664] hardirqs last  enabled at (73): [<ffffd87abdd78af4>] _raw_spin_unlock_irq+0x44/0x80
[   37.298632] hardirqs last disabled at (74): [<ffffd87abdd71fc0>] __schedule+0x710/0xa10
[   37.306885] softirqs last  enabled at (58): [<ffffd87abcc90410>] _stext+0x410/0x588
[   37.314778] softirqs last disabled at (51): [<ffffd87abcd1bf68>] __irq_exit_rcu+0x158/0x174
[   37.323386] ---[ end trace 0000000000000000 ]---

Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 44d46e52baea..d39a0ef9ea45 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -290,7 +290,7 @@ static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
 static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 {
 	struct cpufreq_policy *policy = data->policy;
-	int cpu = cpumask_first(policy->cpus);
+	int cpu = cpumask_first(policy->related_cpus);
 	struct device *dev = get_cpu_device(cpu);
 	unsigned long freq_hz, throttled_freq;
 	struct dev_pm_opp *opp;
-- 
2.35.1

[PATCH v4 3/4] cpufreq: qcom-hw: fix the opp entries refcounting

[Dmitry Baryshkov]

The qcom_lmh_dcvs_notify() will get the dev_pm_opp instance for
throttling, but will not put it, ending up with leaking a reference
count and the following backtrace when putting the CPU offline.

Correctly put the reference count of the returned opp instance.

[   84.418025] ------------[ cut here ]------------
[   84.422770] WARNING: CPU: 7 PID: 43 at drivers/opp/core.c:1396 _opp_table_kref_release+0x188/0x190
[   84.431966] Modules linked in:
[   84.435106] CPU: 7 PID: 43 Comm: cpuhp/7 Tainted: G S                5.17.0-rc6-00388-g7cf3c0d89c44-dirty #721
[   84.451631] pstate: 82400005 (Nzcv daif +PAN -UAO +TCO -DIT -SSBS BTYPE=--)
[   84.458781] pc : _opp_table_kref_release+0x188/0x190
[   84.463878] lr : _opp_table_kref_release+0x78/0x190
[   84.468885] sp : ffff80000841bc70
[   84.472294] x29: ffff80000841bc70 x28: ffff6664afe3d000 x27: ffff1db6729e5908
[   84.479621] x26: 0000000000000000 x25: 0000000000000000 x24: ffff1db6729e58e0
[   84.486946] x23: ffff8000080a5000 x22: ffff1db40aad80e0 x21: ffff1db4002fec80
[   84.494277] x20: ffff1db40aad8000 x19: ffffb751c3186300 x18: ffffffffffffffff
[   84.501603] x17: 5300326563697665 x16: 645f676e696c6f6f x15: 00001186c1df5448
[   84.508928] x14: 00000000000002e9 x13: 0000000000000000 x12: 0000000000000000
[   84.516256] x11: ffffb751c3186368 x10: ffffb751c39a2a70 x9 : 0000000000000000
[   84.523585] x8 : ffff1db4008edf00 x7 : ffffb751c328c000 x6 : 0000000000000001
[   84.530916] x5 : 0000000000040000 x4 : 0000000000000001 x3 : ffff1db4008edf00
[   84.538247] x2 : 0000000000000000 x1 : ffff1db400aa6100 x0 : ffff1db40aad80d0
[   84.545579] Call trace:
[   84.548101]  _opp_table_kref_release+0x188/0x190
[   84.552842]  dev_pm_opp_remove_all_dynamic+0x8c/0xc0
[   84.557949]  qcom_cpufreq_hw_cpu_exit+0x30/0xdc
[   84.562608]  cpufreq_offline.isra.0+0x1b4/0x1d8
[   84.567270]  cpuhp_cpufreq_offline+0x10/0x6c
[   84.571663]  cpuhp_invoke_callback+0x16c/0x2b0
[   84.576231]  cpuhp_thread_fun+0x190/0x250
[   84.580353]  smpboot_thread_fn+0x12c/0x230
[   84.584568]  kthread+0xfc/0x100
[   84.587810]  ret_from_fork+0x10/0x20
[   84.591490] irq event stamp: 3482
[   84.594901] hardirqs last  enabled at (3481): [<ffffb751c13c3db0>] call_rcu+0x39c/0x50c
[   84.603119] hardirqs last disabled at (3482): [<ffffb751c236b518>] el1_dbg+0x24/0x8c
[   84.611074] softirqs last  enabled at (310): [<ffffb751c1290410>] _stext+0x410/0x588
[   84.619028] softirqs last disabled at (305): [<ffffb751c131bf68>] __irq_exit_rcu+0x158/0x174
[   84.627691] ---[ end trace 0000000000000000 ]---

Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support")
Reported-by: kernel test robot <lkp@intel.com>
Tested-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index d39a0ef9ea45..db67daed99a3 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -305,12 +305,18 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 
 	opp = dev_pm_opp_find_freq_floor(dev, &freq_hz);
 	if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE)
-		dev_pm_opp_find_freq_ceil(dev, &freq_hz);
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz);
 
-	throttled_freq = freq_hz / HZ_PER_KHZ;
+	if (IS_ERR(opp)) {
+		dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp);
+	} else {
+		throttled_freq = freq_hz / HZ_PER_KHZ;
+
+		/* Update thermal pressure (the boost frequencies are accepted) */
+		arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
 
-	/* Update thermal pressure (the boost frequencies are accepted) */
-	arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
+		dev_pm_opp_put(opp);
+	}
 
 	/*
 	 * In the unlikely case policy is unregistered do not enable
-- 
2.35.1

[PATCH v4 4/4] cpufreq: qcom-hw: provide online/offline operations

[Dmitry Baryshkov]

Provide lightweight online and offline operations. This saves us from
parsing and tearing down the OPP tables each time the CPU is put online
or offline.

Tested-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/cpufreq/qcom-cpufreq-hw.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index db67daed99a3..b0282898168e 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -423,10 +423,26 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
 	return 0;
 }
 
-static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+static int qcom_cpufreq_hw_cpu_online(struct cpufreq_policy *policy)
 {
+	struct qcom_cpufreq_data *data = policy->driver_data;
+	struct platform_device *pdev = cpufreq_get_driver_data();
+	int ret;
+
+	ret = irq_set_affinity_hint(data->throttle_irq, policy->cpus);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n",
+			data->irq_name, data->throttle_irq);
+
+	return ret;
+}
+
+static int qcom_cpufreq_hw_cpu_offline(struct cpufreq_policy *policy)
+{
+	struct qcom_cpufreq_data *data = policy->driver_data;
+
 	if (data->throttle_irq <= 0)
-		return;
+		return 0;
 
 	mutex_lock(&data->throttle_lock);
 	data->cancel_throttle = true;
@@ -434,6 +450,12 @@ static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
 
 	cancel_delayed_work_sync(&data->throttle_work);
 	irq_set_affinity_hint(data->throttle_irq, NULL);
+
+	return 0;
+}
+
+static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+{
 	free_irq(data->throttle_irq, data);
 }
 
@@ -590,6 +612,8 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = {
 	.get		= qcom_cpufreq_hw_get,
 	.init		= qcom_cpufreq_hw_cpu_init,
 	.exit		= qcom_cpufreq_hw_cpu_exit,
+	.online		= qcom_cpufreq_hw_cpu_online,
+	.offline	= qcom_cpufreq_hw_cpu_offline,
 	.register_em	= cpufreq_register_em_with_opp,
 	.fast_switch    = qcom_cpufreq_hw_fast_switch,
 	.name		= "qcom-cpufreq-hw",
-- 
2.35.1

Re: [PATCH v4 2/4] cpufreq: qcom-hw: fix the race between LMH worker and cpuhp

[Bjorn Andersson]

On Sat 26 Mar 08:51 PDT 2022, Dmitry Baryshkov wrote:

> The driver would disable the worker when cpu is being put offline, but
> it happens closer to the end of cpufreq_offline(). The function
> qcom_lmh_dcvs_poll() can be running in parallel with this, when
> policy->cpus already has been updated. Read policy->related_cpus
> instead.
> 
> [   37.122433] ------------[ cut here ]------------
> [   37.127225] WARNING: CPU: 0 PID: 187 at drivers/base/arch_topology.c:180 topology_update_thermal_pressure+0xec/0x100
> [   37.138098] Modules linked in:
> [   37.141279] CPU: 0 PID: 187 Comm: kworker/0:3 Tainted: G S                5.17.0-rc6-00389-g37c83d0b8710-dirty #713
> [   37.158306] Workqueue: events qcom_lmh_dcvs_poll
> [   37.163095] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
> [   37.170278] pc : topology_update_thermal_pressure+0xec/0x100
> [   37.176131] lr : topology_update_thermal_pressure+0x20/0x100
> [   37.181977] sp : ffff800009b6bce0
> [   37.185402] x29: ffff800009b6bce0 x28: ffffd87abe92b000 x27: ffff04bd7292e205
> [   37.192792] x26: ffffd87abe930af8 x25: ffffd87abe94e4c8 x24: 0000000000000000
> [   37.200180] x23: ffff04bb01177018 x22: ffff04bb011770c0 x21: ffff04bb01177000
> [   37.207567] x20: ffff04bb0a419000 x19: 00000000000c4e00 x18: 0000000000000000
> [   37.214954] x17: 000000040044ffff x16: 004000b2b5503510 x15: 0000006aaa1326d2
> [   37.222333] x14: 0000000000000232 x13: 0000000000000001 x12: 0000000000000040
> [   37.229718] x11: ffff04bb00400000 x10: 968f57bd39f701c8 x9 : ffff04bb0acc8674
> [   37.237095] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffffd87abd90092c
> [   37.244478] x5 : 0000000000000016 x4 : 0000000000000000 x3 : 0000000000000100
> [   37.251852] x2 : ffff04bb0a419020 x1 : 0000000000000100 x0 : 0000000000000100
> [   37.259235] Call trace:
> [   37.261771]  topology_update_thermal_pressure+0xec/0x100
> [   37.267266]  qcom_lmh_dcvs_poll+0xbc/0x154
> [   37.271505]  process_one_work+0x288/0x69c
> [   37.275654]  worker_thread+0x74/0x470
> [   37.279450]  kthread+0xfc/0x100
> [   37.282712]  ret_from_fork+0x10/0x20
> [   37.286417] irq event stamp: 74
> [   37.289664] hardirqs last  enabled at (73): [<ffffd87abdd78af4>] _raw_spin_unlock_irq+0x44/0x80
> [   37.298632] hardirqs last disabled at (74): [<ffffd87abdd71fc0>] __schedule+0x710/0xa10
> [   37.306885] softirqs last  enabled at (58): [<ffffd87abcc90410>] _stext+0x410/0x588
> [   37.314778] softirqs last disabled at (51): [<ffffd87abcd1bf68>] __irq_exit_rcu+0x158/0x174
> [   37.323386] ---[ end trace 0000000000000000 ]---
> 
> Fixes: 275157b367f4 ("cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support")

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>

Regards,
Bjorn

> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---
>  drivers/cpufreq/qcom-cpufreq-hw.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
> index 44d46e52baea..d39a0ef9ea45 100644
> --- a/drivers/cpufreq/qcom-cpufreq-hw.c
> +++ b/drivers/cpufreq/qcom-cpufreq-hw.c
> @@ -290,7 +290,7 @@ static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
>  static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
>  {
>  	struct cpufreq_policy *policy = data->policy;
> -	int cpu = cpumask_first(policy->cpus);
> +	int cpu = cpumask_first(policy->related_cpus);
>  	struct device *dev = get_cpu_device(cpu);
>  	unsigned long freq_hz, throttled_freq;
>  	struct dev_pm_opp *opp;
> -- 
> 2.35.1
> 

Re: [PATCH v4 0/4] cpufreq: qcom-hw: Fixes for cpu hotplug support

[Bjorn Andersson]

On Sat 26 Mar 08:51 PDT 2022, Dmitry Baryshkov wrote:

> This patchseries aims at fixing and improving CPU hotplug support on
> Qualcomm platforms. First three patches are the fixes for the LMH
> support in the cpufreq driver. The last patch adds support for
> lightweight offline() and online() callbacks which are used instead of
> exit() and init() each time the CPU is put offline or back online.
> 
> Patches 1-3 being pure simple fixes can be applied during the -rc
> stage, while patch 4 is targeting next development cycle
> 

Viresh, please consider picking up patch 1-3 for v5.18-rc.

Thanks,
Bjorn

> Changes since v3:
> - Readd throttled_freq calculation disappearing from the third patch.
> 
> Changes since v2:
> - Point Fixes tag from the first patch to the correct commit
> - Replace huge patch 2 with one-liner thanks to being able to use
>   policy->related_cpus instead of policy->cpus
> 
> Changes since v1:
> - Update commit message for the first patch to describe why dropping
>   affinity hint is required (before calling free_irq()),
> - Fixed commit message for the second patch to include messages
>   generated using the mainline kernel w/o additional patches,
> - Changed third patch to use dev_warn_ratelimited(),
> - Reworked last patch to move request_irq/free_irq to online()/offline()
>   to make sure that the IRQ isn't left enabled after the CPU has been
>   put offline.
> 
> 
> Dmitry Baryshkov (4):
>   cpufreq: qcom-hw: drop affinity hint before freeing the IRQ
>   cpufreq: qcom-hw: fix the race between LMH worker and cpuhp
>   cpufreq: qcom-hw: fix the opp entries refcounting
>   cpufreq: qcom-hw: provide online/offline operations
> 
>  drivers/cpufreq/qcom-cpufreq-hw.c | 45 ++++++++++++++++++++++++++-----
>  1 file changed, 38 insertions(+), 7 deletions(-)
> 
> -- 
> 2.35.1
> 

Re: [PATCH v4 0/4] cpufreq: qcom-hw: Fixes for cpu hotplug support

[Viresh Kumar]

On 31-03-22, 11:34, Bjorn Andersson wrote:
> On Sat 26 Mar 08:51 PDT 2022, Dmitry Baryshkov wrote:
> 
> > This patchseries aims at fixing and improving CPU hotplug support on
> > Qualcomm platforms. First three patches are the fixes for the LMH
> > support in the cpufreq driver. The last patch adds support for
> > lightweight offline() and online() callbacks which are used instead of
> > exit() and init() each time the CPU is put offline or back online.
> > 
> > Patches 1-3 being pure simple fixes can be applied during the -rc
> > stage, while patch 4 is targeting next development cycle
> > 
> 
> Viresh, please consider picking up patch 1-3 for v5.18-rc.

Applied. Thanks.

-- 
viresh