powerpc/idle: Store PURR snapshot in a per-cpu global variable

Currently when CPU goes idle, we take a snapshot of PURR via
pseries_idle_prolog() which is used at the CPU idle exit to compute
the idle PURR cycles via the function pseries_idle_epilog().  Thus,
the value of idle PURR cycle thus read before pseries_idle_prolog() and
after pseries_idle_epilog() is always correct.

However, if we were to read the idle PURR cycles from an interrupt
context between pseries_idle_prolog() and pseries_idle_epilog() (this
will be done in a future patch), then, the value of the idle PURR thus
read will not include the cycles spent in the most recent idle period.
Thus, in that interrupt context, we will need access to the snapshot
of the PURR before going idle, in order to compute the idle PURR
cycles for the latest idle duration.

In this patch, we save the snapshot of PURR in pseries_idle_prolog()
in a per-cpu variable, instead of on the stack, so that it can be
accessed from an interrupt context.

Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1586249263-14048-3-git-send-email-ego@linux.vnet.ibm.com

arch/powerpc/include/asm/idle.h

@@ -5,10 +5,27 @@
 #include <asm/paca.h>
 
 #ifdef CONFIG_PPC_PSERIES
-static inline void pseries_idle_prolog(unsigned long *in_purr)
+DECLARE_PER_CPU(u64, idle_entry_purr_snap);
+
+static inline void snapshot_purr_idle_entry(void)
+{
+	*this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR);
+}
+
+static inline void update_idle_purr_accounting(void)
+{
+	u64 wait_cycles;
+	u64 in_purr = *this_cpu_ptr(&idle_entry_purr_snap);
+
+	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+	wait_cycles += mfspr(SPRN_PURR) - in_purr;
+	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+}
+
+static inline void pseries_idle_prolog(void)
 {
 	ppc64_runlatch_off();
-	*in_purr = mfspr(SPRN_PURR);
+	snapshot_purr_idle_entry();
 	/*
 	 * Indicate to the HV that we are idle. Now would be
 	 * a good time to find other work to dispatch.
@@ -16,16 +33,12 @@ static inline void pseries_idle_prolog(unsigned long *in_purr)
 	get_lppaca()->idle = 1;
 }
 
-static inline void pseries_idle_epilog(unsigned long in_purr)
+static inline void pseries_idle_epilog(void)
 {
-	u64 wait_cycles;
-
-	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
-	wait_cycles += mfspr(SPRN_PURR) - in_purr;
-	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+	update_idle_purr_accounting();
 	get_lppaca()->idle = 0;
-
 	ppc64_runlatch_on();
 }
+
 #endif /* CONFIG_PPC_PSERIES */
 #endif

arch/powerpc/platforms/pseries/setup.c

@@ -318,10 +318,9 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 machine_early_initcall(pseries, alloc_dispatch_log_kmem_cache);
 
+DEFINE_PER_CPU(u64, idle_entry_purr_snap);
 static void pseries_lpar_idle(void)
 {
-	unsigned long in_purr;
-
 	/*
 	 * Default handler to go into low thread priority and possibly
 	 * low power mode by ceding processor to hypervisor
@@ -331,7 +330,7 @@ static void pseries_lpar_idle(void)
 		return;
 
 	/* Indicate to hypervisor that we are idle. */
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 
 	/*
 	 * Yield the processor to the hypervisor.  We return if
@@ -342,7 +341,7 @@ static void pseries_lpar_idle(void)
 	 */
 	cede_processor();
 
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 }
 
 /*

drivers/cpuidle/cpuidle-pseries.c

@@ -36,12 +36,11 @@ static int snooze_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
-	unsigned long in_purr;
 	u64 snooze_exit_time;
 
 	set_thread_flag(TIF_POLLING_NRFLAG);
 
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 	local_irq_enable();
 	snooze_exit_time = get_tb() + snooze_timeout;
 
@@ -65,7 +64,7 @@ static int snooze_loop(struct cpuidle_device *dev,
 
 	local_irq_disable();
 
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 
 	return index;
 }
@@ -91,9 +90,8 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv,
 				int index)
 {
-	unsigned long in_purr;
 
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 	get_lppaca()->donate_dedicated_cpu = 1;
 
 	HMT_medium();
@@ -102,7 +100,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
 	local_irq_disable();
 	get_lppaca()->donate_dedicated_cpu = 0;
 
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 
 	return index;
 }
@@ -111,9 +109,8 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
-	unsigned long in_purr;
 
-	pseries_idle_prolog(&in_purr);
+	pseries_idle_prolog();
 
 	/*
 	 * Yield the processor to the hypervisor.  We return if
@@ -125,7 +122,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
 	check_and_cede_processor();
 
 	local_irq_disable();
-	pseries_idle_epilog(in_purr);
+	pseries_idle_epilog();
 
 	return index;
 }