On Mon, Jan 16, 2023 at 04:59:04PM +0000, Mark Rutland wrote:
> I'm sorry to have to bear some bad news on that front. :(
Moo, something had to give..
> IIUC what's happenign here is the PSCI cpuidle driver has entered idle and RCU
> is no longer watching when arm64's cpu_suspend() manipulates DAIF. Our
> local_daif_*() helpers poke lockdep and tracing, hence the call to
> trace_hardirqs_off() and the RCU usage.
Right, strictly speaking not needed at this point, IRQs should have been
traced off a long time ago.
> I think we need RCU to be watching all the way down to cpu_suspend(), and it's
> cpu_suspend() that should actually enter/exit idle context. That and we need to
> make cpu_suspend() and the low-level PSCI invocation noinstr.
>
> I'm not sure whether 32-bit will have a similar issue or not.
I'm not seeing 32bit or Risc-V have similar issues here, but who knows,
maybe I missed somsething.
In any case, the below ought to cure the ARM64 case and remove that last
known RCU_NONIDLE() user as a bonus.
---
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 41974a1a229a..42e19fff40ee 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -67,10 +67,10 @@ __cpuidle int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
u32 state = lpi->address;
if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
- return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter,
+ return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM_RCU(psci_cpu_suspend_enter,
lpi->index, state);
else
- return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter,
+ return CPU_PM_CPU_IDLE_ENTER_PARAM_RCU(psci_cpu_suspend_enter,
lpi->index, state);
}
#endif
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index e7163f31f716..0fbdf5fe64d8 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -4,6 +4,7 @@
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/pgtable.h>
+#include <linux/cpuidle.h>
#include <asm/alternative.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
@@ -104,6 +105,10 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
* From this point debug exceptions are disabled to prevent
* updates to mdscr register (saved and restored along with
* general purpose registers) from kernel debuggers.
+ *
+ * Strictly speaking the trace_hardirqs_off() here is superfluous,
+ * hardirqs should be firmly off by now. This really ought to use
+ * something like raw_local_daif_save().
*/
flags = local_daif_save();
@@ -120,6 +125,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
*/
arm_cpuidle_save_irq_context(&context);
+ ct_cpuidle_enter();
+
if (__cpu_suspend_enter(&state)) {
/* Call the suspend finisher */
ret = fn(arg);
@@ -133,8 +140,11 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
*/
if (!ret)
ret = -EOPNOTSUPP;
+
+ ct_cpuidle_exit();
} else {
- RCU_NONIDLE(__cpu_suspend_exit());
+ ct_cpuidle_exit();
+ __cpu_suspend_exit();
}
arm_cpuidle_restore_irq_context(&context);
diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c
index 4fc4e0381944..312a34ef28dc 100644
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -69,16 +69,12 @@ static __cpuidle int __psci_enter_domain_idle_state(struct cpuidle_device *dev,
else
pm_runtime_put_sync_suspend(pd_dev);
- ct_cpuidle_enter();
-
state = psci_get_domain_state();
if (!state)
state = states[idx];
ret = psci_cpu_suspend_enter(state) ? -1 : idx;
- ct_cpuidle_exit();
-
if (s2idle)
dev_pm_genpd_resume(pd_dev);
else
@@ -192,7 +188,7 @@ static __cpuidle int psci_enter_idle_state(struct cpuidle_device *dev,
{
u32 *state = __this_cpu_read(psci_cpuidle_data.psci_states);
- return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, idx, state[idx]);
+ return CPU_PM_CPU_IDLE_ENTER_PARAM_RCU(psci_cpu_suspend_enter, idx, state[idx]);
}
static const struct of_device_id psci_idle_state_match[] = {
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index e7bcfca4159f..f3a044fa4652 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -462,11 +462,22 @@ int psci_cpu_suspend_enter(u32 state)
if (!psci_power_state_loses_context(state)) {
struct arm_cpuidle_irq_context context;
+ ct_cpuidle_enter();
arm_cpuidle_save_irq_context(&context);
ret = psci_ops.cpu_suspend(state, 0);
arm_cpuidle_restore_irq_context(&context);
+ ct_cpuidle_exit();
} else {
+ /*
+ * ARM64 cpu_suspend() wants to do ct_cpuidle_*() itself.
+ */
+ if (!IS_ENABLED(CONFIG_ARM64))
+ ct_cpuidle_enter();
+
ret = cpu_suspend(state, psci_suspend_finisher);
+
+ if (!IS_ENABLED(CONFIG_ARM64))
+ ct_cpuidle_exit();
}
return ret;
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 630c879143c7..3183aeb7f5b4 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -307,7 +307,7 @@ extern s64 cpuidle_governor_latency_req(unsigned int cpu);
#define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, \
idx, \
state, \
- is_retention) \
+ is_retention, is_rcu) \
({ \
int __ret = 0; \
\
@@ -319,9 +319,11 @@ extern s64 cpuidle_governor_latency_req(unsigned int cpu);
if (!is_retention) \
__ret = cpu_pm_enter(); \
if (!__ret) { \
- ct_cpuidle_enter(); \
+ if (!is_rcu) \
+ ct_cpuidle_enter(); \
__ret = low_level_idle_enter(state); \
- ct_cpuidle_exit(); \
+ if (!is_rcu) \
+ ct_cpuidle_exit(); \
if (!is_retention) \
cpu_pm_exit(); \
} \
@@ -330,15 +332,21 @@ extern s64 cpuidle_governor_latency_req(unsigned int cpu);
})
#define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx) \
- __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, idx, 0)
+ __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, idx, 0, 0)
#define CPU_PM_CPU_IDLE_ENTER_RETENTION(low_level_idle_enter, idx) \
- __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, idx, 1)
+ __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, idx, 1, 0)
#define CPU_PM_CPU_IDLE_ENTER_PARAM(low_level_idle_enter, idx, state) \
- __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 0)
+ __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 0, 0)
+
+#define CPU_PM_CPU_IDLE_ENTER_PARAM_RCU(low_level_idle_enter, idx, state) \
+ __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 0, 1)
#define CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(low_level_idle_enter, idx, state) \
- __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 1)
+ __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 1, 0)
+
+#define CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM_RCU(low_level_idle_enter, idx, state) \
+ __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, state, 1, 1)
#endif /* _LINUX_CPUIDLE_H */
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
