powernv/cpuidle: Redesign idle states management

Deep idle states like sleep and winkle are per core idle states. A core
enters these states only when all the threads enter either the
particular idle state or a deeper one. There are tasks like fastsleep
hardware bug workaround and hypervisor core state save which have to be
done only by the last thread of the core entering deep idle state and
similarly tasks like timebase resync, hypervisor core register restore
that have to be done only by the first thread waking up from these
state.

The current idle state management does not have a way to distinguish the
first/last thread of the core waking/entering idle states. Tasks like
timebase resync are done for all the threads. This is not only is
suboptimal, but can cause functionality issues when subcores and kvm is
involved.

This patch adds the necessary infrastructure to track idle states of
threads in a per-core structure. It uses this info to perform tasks like
fastsleep workaround and timebase resync only once per core.

Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Originally-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: linux-pm@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 86 insertions, 3 deletions

diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 2111e08d406b..78289ed7058c 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -158,6 +158,43 @@ opal_tracepoint_return:
 	blr
 #endif
 
+/*
+ * Make opal call in realmode. This is a generic function to be called
+ * from realmode. It handles endianness.
+ *
+ * r13 - paca pointer
+ * r1  - stack pointer
+ * r0  - opal token
+ */
+_GLOBAL(opal_call_realmode)
+	mflr	r12
+	std	r12,PPC_LR_STKOFF(r1)
+	ld	r2,PACATOC(r13)
+	/* Set opal return address */
+	LOAD_REG_ADDR(r12,return_from_opal_call)
+	mtlr	r12
+
+	mfmsr	r12
+#ifdef __LITTLE_ENDIAN__
+	/* Handle endian-ness */
+	li	r11,MSR_LE
+	andc	r12,r12,r11
+#endif
+	mtspr	SPRN_HSRR1,r12
+	LOAD_REG_ADDR(r11,opal)
+	ld	r12,8(r11)
+	ld	r2,0(r11)
+	mtspr	SPRN_HSRR0,r12
+	hrfid
+
+return_from_opal_call:
+#ifdef __LITTLE_ENDIAN__
+	FIXUP_ENDIAN
+#endif
+	ld	r12,PPC_LR_STKOFF(r1)
+	mtlr	r12
+	blr
+
 OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
 OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
 OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 88e579e62a73..2e9b53bb73e2 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -36,6 +36,9 @@
 #include <asm/opal.h>
 #include <asm/kexec.h>
 #include <asm/smp.h>
+#include <asm/cputhreads.h>
+#include <asm/cpuidle.h>
+#include <asm/code-patching.h>
 
 #include "powernv.h"
 
@@ -290,10 +293,45 @@ static void __init pnv_setup_machdep_rtas(void)
 
 static u32 supported_cpuidle_states;
 
+static void pnv_alloc_idle_core_states(void)
+{
+	int i, j;
+	int nr_cores = cpu_nr_cores();
+	u32 *core_idle_state;
+
+	/*
+	 * core_idle_state - First 8 bits track the idle state of each thread
+	 * of the core. The 8th bit is the lock bit. Initially all thread bits
+	 * are set. They are cleared when the thread enters deep idle state
+	 * like sleep and winkle. Initially the lock bit is cleared.
+	 * The lock bit has 2 purposes
+	 * a. While the first thread is restoring core state, it prevents
+	 * other threads in the core from switching to process context.
+	 * b. While the last thread in the core is saving the core state, it
+	 * prevents a different thread from waking up.
+	 */
+	for (i = 0; i < nr_cores; i++) {
+		int first_cpu = i * threads_per_core;
+		int node = cpu_to_node(first_cpu);
+
+		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
+		*core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
+
+		for (j = 0; j < threads_per_core; j++) {
+			int cpu = first_cpu + j;
+
+			paca[cpu].core_idle_state_ptr = core_idle_state;
+			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
+			paca[cpu].thread_mask = 1 << j;
+		}
+	}
+}
+
 u32 pnv_get_supported_cpuidle_states(void)
 {
 	return supported_cpuidle_states;
 }
+EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
 
 static int __init pnv_init_idle_states(void)
 {
@@ -330,13 +368,20 @@ static int __init pnv_init_idle_states(void)
 		flags = be32_to_cpu(idle_state_flags[i]);
 		supported_cpuidle_states |= flags;
 	}
-
+	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_entry,
+			PPC_INST_NOP);
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_exit,
+			PPC_INST_NOP);
+	}
+	pnv_alloc_idle_core_states();
 	return 0;
 }
 
 subsys_initcall(pnv_init_idle_states);
 
-
 static int __init pnv_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 83299ef2dc3d..c0691d0fb385 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -168,7 +168,8 @@ static void pnv_smp_cpu_kill_self(void)
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
 		ppc64_runlatch_off();
-		if (idle_states & OPAL_PM_SLEEP_ENABLED)
+		if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
+				(idle_states & OPAL_PM_SLEEP_ENABLED_ER1))
 			srr1 = power7_sleep();
 		else
 			srr1 = power7_nap(1);