Commit b49e4969 authored by Zhang Rui's avatar Zhang Rui Committed by Wang, Xiaolong
Browse files

powercap: intel_rapl: Fix locking in TPMI RAPL 

mainline inclusion
from mainline-v6.9-rc1
commit 1aa09b9379a7a644cd2f75ae0bac82b8783df600
category: bugfix
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/IA85P6
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=1aa09b9379a7a644cd2f75ae0bac82b8783df600



--------------------------------

The RAPL framework uses CPU hotplug locking to protect the rapl_packages
list and rp->lead_cpu to guarantee that

 1. the RAPL package device is not unprobed and freed
 2. the cached rp->lead_cpu is always valid

for operations like powercap sysfs accesses.

Current RAPL APIs assume being called from CPU hotplug callbacks which
hold the CPU hotplug lock, but TPMI RAPL driver invokes the APIs in the
driver's .probe() function without acquiring the CPU hotplug lock.

Fix the problem by providing both locked and lockless versions of RAPL
APIs.

Intel-SIG: commit 1aa09b9379a7 powercap: intel_rapl: Fix locking in TPMI RAPL
Backport Intel RAPL driver bugfixes up to upstream v6.9.
Change the locks from guard macros to cpus_read_lock()/cpus_read_unlock() function pairs to avoid backporting the cleanup framework.

Fixes: 9eef7f9d ("powercap: intel_rapl: Introduce RAPL TPMI interface driver")
Signed-off-by: default avatarZhang Rui <rui.zhang@intel.com>
Cc: 6.5+ <stable@vger.kernel.org> # 6.5+
Signed-off-by: default avatarRafael J. Wysocki <rafael.j.wysocki@intel.com>
[ Xiaolong Wang: solve conflicts and amend commit log ]
Signed-off-by: default avatarXiaolong Wang <xiaolong.wang@intel.com>
parent 0070ed8c

drivers/powercap/intel_rapl_common.c

+32 −3
Original line number Diff line number Diff line
@@ -1488,7 +1488,7 @@ static int rapl_detect_domains(struct rapl_package *rp) 
}



/* called from CPU hotplug notifier, hotplug lock held */

void rapl_remove_package(struct rapl_package *rp)

void rapl_remove_package_cpuslocked(struct rapl_package *rp)

{

	struct rapl_domain *rd, *rd_package = NULL;
@@ -1517,10 +1517,19 @@ void rapl_remove_package(struct rapl_package *rp) 
	list_del(&rp->plist);

	kfree(rp);

}

EXPORT_SYMBOL_GPL(rapl_remove_package_cpuslocked);



void rapl_remove_package(struct rapl_package *rp)

{

	cpus_read_lock();

	rapl_remove_package_cpuslocked(rp);

	cpus_read_unlock();

}

EXPORT_SYMBOL_GPL(rapl_remove_package);



/* caller to ensure CPU hotplug lock is held */

struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu)

struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv,

							 bool id_is_cpu)

{

	struct rapl_package *rp;

	int uid;
@@ -1538,10 +1547,20 @@ struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, 


	return NULL;

}

EXPORT_SYMBOL_GPL(rapl_find_package_domain_cpuslocked);



struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu)

{

	struct rapl_package *rp;

	cpus_read_lock();

	rp = rapl_find_package_domain_cpuslocked(id, priv, id_is_cpu);

	cpus_read_unlock();

	return rp;

}

EXPORT_SYMBOL_GPL(rapl_find_package_domain);



/* called from CPU hotplug notifier, hotplug lock held */

struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu)

struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *priv, bool id_is_cpu)

{

	struct rapl_package *rp;

	int ret;
@@ -1587,6 +1606,16 @@ struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id 
	kfree(rp);

	return ERR_PTR(ret);

}

EXPORT_SYMBOL_GPL(rapl_add_package_cpuslocked);



struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu)

{

	struct rapl_package *rp;

	cpus_read_lock();

	rp = rapl_add_package_cpuslocked(id, priv, id_is_cpu);

	cpus_read_unlock();

	return rp;

}

EXPORT_SYMBOL_GPL(rapl_add_package);



static void power_limit_state_save(void)

drivers/powercap/intel_rapl_msr.c

+4 −4
Original line number Diff line number Diff line
@@ -73,9 +73,9 @@ static int rapl_cpu_online(unsigned int cpu) 
{

	struct rapl_package *rp;



	rp = rapl_find_package_domain(cpu, rapl_msr_priv, true);

	rp = rapl_find_package_domain_cpuslocked(cpu, rapl_msr_priv, true);

	if (!rp) {

		rp = rapl_add_package(cpu, rapl_msr_priv, true);

		rp = rapl_add_package_cpuslocked(cpu, rapl_msr_priv, true);

		if (IS_ERR(rp))

			return PTR_ERR(rp);

	}
@@ -88,14 +88,14 @@ static int rapl_cpu_down_prep(unsigned int cpu) 
	struct rapl_package *rp;

	int lead_cpu;



	rp = rapl_find_package_domain(cpu, rapl_msr_priv, true);

	rp = rapl_find_package_domain_cpuslocked(cpu, rapl_msr_priv, true);

	if (!rp)

		return 0;



	cpumask_clear_cpu(cpu, &rp->cpumask);

	lead_cpu = cpumask_first(&rp->cpumask);

	if (lead_cpu >= nr_cpu_ids)

		rapl_remove_package(rp);

		rapl_remove_package_cpuslocked(rp);

	else if (rp->lead_cpu == cpu)

		rp->lead_cpu = lead_cpu;

	return 0;

drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c

+4 −4
Original line number Diff line number Diff line
@@ -27,9 +27,9 @@ static int rapl_mmio_cpu_online(unsigned int cpu) 
	if (topology_physical_package_id(cpu))

		return 0;



	rp = rapl_find_package_domain(cpu, &rapl_mmio_priv, true);

	rp = rapl_find_package_domain_cpuslocked(cpu, &rapl_mmio_priv, true);

	if (!rp) {

		rp = rapl_add_package(cpu, &rapl_mmio_priv, true);

		rp = rapl_add_package_cpuslocked(cpu, &rapl_mmio_priv, true);

		if (IS_ERR(rp))

			return PTR_ERR(rp);

	}
@@ -42,14 +42,14 @@ static int rapl_mmio_cpu_down_prep(unsigned int cpu) 
	struct rapl_package *rp;

	int lead_cpu;



	rp = rapl_find_package_domain(cpu, &rapl_mmio_priv, true);

	rp = rapl_find_package_domain_cpuslocked(cpu, &rapl_mmio_priv, true);

	if (!rp)

		return 0;



	cpumask_clear_cpu(cpu, &rp->cpumask);

	lead_cpu = cpumask_first(&rp->cpumask);

	if (lead_cpu >= nr_cpu_ids)

		rapl_remove_package(rp);

		rapl_remove_package_cpuslocked(rp);

	else if (rp->lead_cpu == cpu)

		rp->lead_cpu = lead_cpu;

	return 0;

include/linux/intel_rapl.h

+6 −0
Original line number Diff line number Diff line
@@ -178,6 +178,12 @@ struct rapl_package { 
	struct rapl_if_priv *priv;

};



struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv,

						       bool id_is_cpu);

struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *priv,

						 bool id_is_cpu);

void rapl_remove_package_cpuslocked(struct rapl_package *rp);



struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu);

struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu);

void rapl_remove_package(struct rapl_package *rp);