linux/drivers/cpuidle/cpuidle-psci.c
Ulf Hansson 36050d8984 cpuidle: psci: Fix suspicious RCU usage
The commit eb1f00237a ("lockdep,trace: Expose tracepoints"), started to
expose us for tracepoints. This lead to the following RCU splat on an ARM64
Qcom board.

[    5.529634] WARNING: suspicious RCU usage
[    5.537307] sdhci-pltfm: SDHCI platform and OF driver helper
[    5.541092] 5.9.0-rc3 #86 Not tainted
[    5.541098] -----------------------------
[    5.541105] ../include/trace/events/lock.h:37 suspicious rcu_dereference_check() usage!
[    5.541110]
[    5.541110] other info that might help us debug this:
[    5.541110]
[    5.541116]
[    5.541116] rcu_scheduler_active = 2, debug_locks = 1
[    5.541122] RCU used illegally from extended quiescent state!
[    5.541129] no locks held by swapper/0/0.
[    5.541134]
[    5.541134] stack backtrace:
[    5.541143] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.9.0-rc3 #86
[    5.541149] Hardware name: Qualcomm Technologies, Inc. APQ 8016 SBC (DT)
[    5.541157] Call trace:
[    5.568185] sdhci_msm 7864900.sdhci: Got CD GPIO
[    5.574186]  dump_backtrace+0x0/0x1c8
[    5.574206]  show_stack+0x14/0x20
[    5.574229]  dump_stack+0xe8/0x154
[    5.574250]  lockdep_rcu_suspicious+0xd4/0xf8
[    5.574269]  lock_acquire+0x3f0/0x460
[    5.574292]  _raw_spin_lock_irqsave+0x80/0xb0
[    5.574314]  __pm_runtime_suspend+0x4c/0x188
[    5.574341]  psci_enter_domain_idle_state+0x40/0xa0
[    5.574362]  cpuidle_enter_state+0xc0/0x610
[    5.646487]  cpuidle_enter+0x38/0x50
[    5.650651]  call_cpuidle+0x18/0x40
[    5.654467]  do_idle+0x228/0x278
[    5.657678]  cpu_startup_entry+0x24/0x70
[    5.661153]  rest_init+0x1a4/0x278
[    5.665061]  arch_call_rest_init+0xc/0x14
[    5.668272]  start_kernel+0x508/0x540

Following the path in pm_runtime_put_sync_suspend() from
psci_enter_domain_idle_state(), it seems like we end up using the RCU.
Therefore, let's simply silence the splat by informing the RCU about it
with RCU_NONIDLE.

Note that, this is a temporary solution. Instead we should strive to avoid
using RCU_NONIDLE (and similar), but rather push rcu_idle_enter|exit()
further down, closer to the arch specific code. However, as the CPU PM
notifiers are also using the RCU, additional rework is needed.

Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2020-09-21 15:56:53 +02:00

384 lines
8.6 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* PSCI CPU idle driver.
*
* Copyright (C) 2019 ARM Ltd.
* Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
*/
#define pr_fmt(fmt) "CPUidle PSCI: " fmt
#include <linux/cpuhotplug.h>
#include <linux/cpu_cooling.h>
#include <linux/cpuidle.h>
#include <linux/cpumask.h>
#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/psci.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <asm/cpuidle.h>
#include "cpuidle-psci.h"
#include "dt_idle_states.h"
struct psci_cpuidle_data {
u32 *psci_states;
struct device *dev;
};
static DEFINE_PER_CPU_READ_MOSTLY(struct psci_cpuidle_data, psci_cpuidle_data);
static DEFINE_PER_CPU(u32, domain_state);
static bool psci_cpuidle_use_cpuhp;
void psci_set_domain_state(u32 state)
{
__this_cpu_write(domain_state, state);
}
static inline u32 psci_get_domain_state(void)
{
return __this_cpu_read(domain_state);
}
static inline int psci_enter_state(int idx, u32 state)
{
return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, idx, state);
}
static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int idx)
{
struct psci_cpuidle_data *data = this_cpu_ptr(&psci_cpuidle_data);
u32 *states = data->psci_states;
struct device *pd_dev = data->dev;
u32 state;
int ret;
ret = cpu_pm_enter();
if (ret)
return -1;
/* Do runtime PM to manage a hierarchical CPU toplogy. */
RCU_NONIDLE(pm_runtime_put_sync_suspend(pd_dev));
state = psci_get_domain_state();
if (!state)
state = states[idx];
ret = psci_cpu_suspend_enter(state) ? -1 : idx;
RCU_NONIDLE(pm_runtime_get_sync(pd_dev));
cpu_pm_exit();
/* Clear the domain state to start fresh when back from idle. */
psci_set_domain_state(0);
return ret;
}
static int psci_idle_cpuhp_up(unsigned int cpu)
{
struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev);
if (pd_dev)
pm_runtime_get_sync(pd_dev);
return 0;
}
static int psci_idle_cpuhp_down(unsigned int cpu)
{
struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev);
if (pd_dev) {
pm_runtime_put_sync(pd_dev);
/* Clear domain state to start fresh at next online. */
psci_set_domain_state(0);
}
return 0;
}
static void psci_idle_init_cpuhp(void)
{
int err;
if (!psci_cpuidle_use_cpuhp)
return;
err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING,
"cpuidle/psci:online",
psci_idle_cpuhp_up,
psci_idle_cpuhp_down);
if (err)
pr_warn("Failed %d while setup cpuhp state\n", err);
}
static int psci_enter_idle_state(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int idx)
{
u32 *state = __this_cpu_read(psci_cpuidle_data.psci_states);
return psci_enter_state(idx, state[idx]);
}
static const struct of_device_id psci_idle_state_match[] = {
{ .compatible = "arm,idle-state",
.data = psci_enter_idle_state },
{ },
};
int psci_dt_parse_state_node(struct device_node *np, u32 *state)
{
int err = of_property_read_u32(np, "arm,psci-suspend-param", state);
if (err) {
pr_warn("%pOF missing arm,psci-suspend-param property\n", np);
return err;
}
if (!psci_power_state_is_valid(*state)) {
pr_warn("Invalid PSCI power state %#x\n", *state);
return -EINVAL;
}
return 0;
}
static int psci_dt_cpu_init_topology(struct cpuidle_driver *drv,
struct psci_cpuidle_data *data,
unsigned int state_count, int cpu)
{
/* Currently limit the hierarchical topology to be used in OSI mode. */
if (!psci_has_osi_support())
return 0;
data->dev = psci_dt_attach_cpu(cpu);
if (IS_ERR_OR_NULL(data->dev))
return PTR_ERR_OR_ZERO(data->dev);
/*
* Using the deepest state for the CPU to trigger a potential selection
* of a shared state for the domain, assumes the domain states are all
* deeper states.
*/
drv->states[state_count - 1].enter = psci_enter_domain_idle_state;
psci_cpuidle_use_cpuhp = true;
return 0;
}
static int psci_dt_cpu_init_idle(struct device *dev, struct cpuidle_driver *drv,
struct device_node *cpu_node,
unsigned int state_count, int cpu)
{
int i, ret = 0;
u32 *psci_states;
struct device_node *state_node;
struct psci_cpuidle_data *data = per_cpu_ptr(&psci_cpuidle_data, cpu);
state_count++; /* Add WFI state too */
psci_states = devm_kcalloc(dev, state_count, sizeof(*psci_states),
GFP_KERNEL);
if (!psci_states)
return -ENOMEM;
for (i = 1; i < state_count; i++) {
state_node = of_get_cpu_state_node(cpu_node, i - 1);
if (!state_node)
break;
ret = psci_dt_parse_state_node(state_node, &psci_states[i]);
of_node_put(state_node);
if (ret)
return ret;
pr_debug("psci-power-state %#x index %d\n", psci_states[i], i);
}
if (i != state_count)
return -ENODEV;
/* Initialize optional data, used for the hierarchical topology. */
ret = psci_dt_cpu_init_topology(drv, data, state_count, cpu);
if (ret < 0)
return ret;
/* Idle states parsed correctly, store them in the per-cpu struct. */
data->psci_states = psci_states;
return 0;
}
static int psci_cpu_init_idle(struct device *dev, struct cpuidle_driver *drv,
unsigned int cpu, unsigned int state_count)
{
struct device_node *cpu_node;
int ret;
/*
* If the PSCI cpu_suspend function hook has not been initialized
* idle states must not be enabled, so bail out
*/
if (!psci_ops.cpu_suspend)
return -EOPNOTSUPP;
cpu_node = of_cpu_device_node_get(cpu);
if (!cpu_node)
return -ENODEV;
ret = psci_dt_cpu_init_idle(dev, drv, cpu_node, state_count, cpu);
of_node_put(cpu_node);
return ret;
}
static void psci_cpu_deinit_idle(int cpu)
{
struct psci_cpuidle_data *data = per_cpu_ptr(&psci_cpuidle_data, cpu);
psci_dt_detach_cpu(data->dev);
psci_cpuidle_use_cpuhp = false;
}
static int psci_idle_init_cpu(struct device *dev, int cpu)
{
struct cpuidle_driver *drv;
struct device_node *cpu_node;
const char *enable_method;
int ret = 0;
cpu_node = of_cpu_device_node_get(cpu);
if (!cpu_node)
return -ENODEV;
/*
* Check whether the enable-method for the cpu is PSCI, fail
* if it is not.
*/
enable_method = of_get_property(cpu_node, "enable-method", NULL);
if (!enable_method || (strcmp(enable_method, "psci")))
ret = -ENODEV;
of_node_put(cpu_node);
if (ret)
return ret;
drv = devm_kzalloc(dev, sizeof(*drv), GFP_KERNEL);
if (!drv)
return -ENOMEM;
drv->name = "psci_idle";
drv->owner = THIS_MODULE;
drv->cpumask = (struct cpumask *)cpumask_of(cpu);
/*
* PSCI idle states relies on architectural WFI to be represented as
* state index 0.
*/
drv->states[0].enter = psci_enter_idle_state;
drv->states[0].exit_latency = 1;
drv->states[0].target_residency = 1;
drv->states[0].power_usage = UINT_MAX;
strcpy(drv->states[0].name, "WFI");
strcpy(drv->states[0].desc, "ARM WFI");
/*
* If no DT idle states are detected (ret == 0) let the driver
* initialization fail accordingly since there is no reason to
* initialize the idle driver if only wfi is supported, the
* default archictectural back-end already executes wfi
* on idle entry.
*/
ret = dt_init_idle_driver(drv, psci_idle_state_match, 1);
if (ret <= 0)
return ret ? : -ENODEV;
/*
* Initialize PSCI idle states.
*/
ret = psci_cpu_init_idle(dev, drv, cpu, ret);
if (ret) {
pr_err("CPU %d failed to PSCI idle\n", cpu);
return ret;
}
ret = cpuidle_register(drv, NULL);
if (ret)
goto deinit;
cpuidle_cooling_register(drv);
return 0;
deinit:
psci_cpu_deinit_idle(cpu);
return ret;
}
/*
* psci_idle_probe - Initializes PSCI cpuidle driver
*
* Initializes PSCI cpuidle driver for all CPUs, if any CPU fails
* to register cpuidle driver then rollback to cancel all CPUs
* registration.
*/
static int psci_cpuidle_probe(struct platform_device *pdev)
{
int cpu, ret;
struct cpuidle_driver *drv;
struct cpuidle_device *dev;
for_each_possible_cpu(cpu) {
ret = psci_idle_init_cpu(&pdev->dev, cpu);
if (ret)
goto out_fail;
}
psci_idle_init_cpuhp();
return 0;
out_fail:
while (--cpu >= 0) {
dev = per_cpu(cpuidle_devices, cpu);
drv = cpuidle_get_cpu_driver(dev);
cpuidle_unregister(drv);
psci_cpu_deinit_idle(cpu);
}
return ret;
}
static struct platform_driver psci_cpuidle_driver = {
.probe = psci_cpuidle_probe,
.driver = {
.name = "psci-cpuidle",
},
};
static int __init psci_idle_init(void)
{
struct platform_device *pdev;
int ret;
ret = platform_driver_register(&psci_cpuidle_driver);
if (ret)
return ret;
pdev = platform_device_register_simple("psci-cpuidle", -1, NULL, 0);
if (IS_ERR(pdev)) {
platform_driver_unregister(&psci_cpuidle_driver);
return PTR_ERR(pdev);
}
return 0;
}
device_initcall(psci_idle_init);