powerpc/pseries: Add hooks to put the CPU into an appropriate offline state
When a CPU is offlined on POWER currently, we call rtas_stop_self() and hand
the CPU back to the resource pool. This path is used for DLPAR which will
cause a change in the LPAR configuration which will be visible outside.
This patch changes the default state a CPU is put into when it is offlined.
On platforms which support ceding the processor to the hypervisor with
latency hint specifier value, during a cpu offline operation,
instead of calling rtas_stop_self(), we cede the vCPU to the hypervisor
while passing a latency hint specifier value. The Hypervisor can use this hint
to provide better energy savings. Also, during the offline
operation, the control of the vCPU remains with the LPAR as oppposed to
returning it to the resource pool.
The patch achieves this by creating an infrastructure to set the
preferred_offline_state() which can be either
- CPU_STATE_OFFLINE: which is the current behaviour of calling
rtas_stop_self()
- CPU_STATE_INACTIVE: which cedes the vCPU to the hypervisor with the latency
hint specifier.
The codepath which wants to perform a DLPAR operation can set the
preferred_offline_state() of a CPU to CPU_STATE_OFFLINE before invoking
cpu_down().
The patch also provides a boot-time command line argument to disable/enable
CPU_STATE_INACTIVE.
Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index 9d620c1..4d4a644b 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -49,6 +49,12 @@
additional_cpus=n (*) Use this to limit hotpluggable cpus. This option sets
cpu_possible_map = cpu_present_map + additional_cpus
+cede_offline={"off","on"} Use this option to disable/enable putting offlined
+ processors to an extended H_CEDE state on
+ supported pseries platforms.
+ If nothing is specified,
+ cede_offline is set to "on".
+
(*) Option valid only for following architectures
- ia64
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index ebff6d9..6ea4698 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -30,6 +30,7 @@
#include <asm/pSeries_reconfig.h>
#include "xics.h"
#include "plpar_wrappers.h"
+#include "offline_states.h"
/* This version can't take the spinlock, because it never returns */
static struct rtas_args rtas_stop_self_args = {
@@ -39,6 +40,55 @@
.rets = &rtas_stop_self_args.args[0],
};
+static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
+ CPU_STATE_OFFLINE;
+static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE;
+
+static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE;
+
+static int cede_offline_enabled __read_mostly = 1;
+
+/*
+ * Enable/disable cede_offline when available.
+ */
+static int __init setup_cede_offline(char *str)
+{
+ if (!strcmp(str, "off"))
+ cede_offline_enabled = 0;
+ else if (!strcmp(str, "on"))
+ cede_offline_enabled = 1;
+ else
+ return 0;
+ return 1;
+}
+
+__setup("cede_offline=", setup_cede_offline);
+
+enum cpu_state_vals get_cpu_current_state(int cpu)
+{
+ return per_cpu(current_state, cpu);
+}
+
+void set_cpu_current_state(int cpu, enum cpu_state_vals state)
+{
+ per_cpu(current_state, cpu) = state;
+}
+
+enum cpu_state_vals get_preferred_offline_state(int cpu)
+{
+ return per_cpu(preferred_offline_state, cpu);
+}
+
+void set_preferred_offline_state(int cpu, enum cpu_state_vals state)
+{
+ per_cpu(preferred_offline_state, cpu) = state;
+}
+
+void set_default_offline_state(int cpu)
+{
+ per_cpu(preferred_offline_state, cpu) = default_offline_state;
+}
+
static void rtas_stop_self(void)
{
struct rtas_args *args = &rtas_stop_self_args;
@@ -56,11 +106,61 @@
static void pseries_mach_cpu_die(void)
{
+ unsigned int cpu = smp_processor_id();
+ unsigned int hwcpu = hard_smp_processor_id();
+ u8 cede_latency_hint = 0;
+
local_irq_disable();
idle_task_exit();
xics_teardown_cpu();
- unregister_slb_shadow(hard_smp_processor_id(), __pa(get_slb_shadow()));
- rtas_stop_self();
+
+ if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
+ set_cpu_current_state(cpu, CPU_STATE_INACTIVE);
+ cede_latency_hint = 2;
+
+ get_lppaca()->idle = 1;
+ if (!get_lppaca()->shared_proc)
+ get_lppaca()->donate_dedicated_cpu = 1;
+
+ printk(KERN_INFO
+ "cpu %u (hwid %u) ceding for offline with hint %d\n",
+ cpu, hwcpu, cede_latency_hint);
+ while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
+ extended_cede_processor(cede_latency_hint);
+ printk(KERN_INFO "cpu %u (hwid %u) returned from cede.\n",
+ cpu, hwcpu);
+ printk(KERN_INFO
+ "Decrementer value = %x Timebase value = %llx\n",
+ get_dec(), get_tb());
+ }
+
+ printk(KERN_INFO "cpu %u (hwid %u) got prodded to go online\n",
+ cpu, hwcpu);
+
+ if (!get_lppaca()->shared_proc)
+ get_lppaca()->donate_dedicated_cpu = 0;
+ get_lppaca()->idle = 0;
+ }
+
+ if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
+ unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+
+ /*
+ * NOTE: Calling start_secondary() here for now to
+ * start new context.
+ * However, need to do it cleanly by resetting the
+ * stack pointer.
+ */
+ start_secondary();
+
+ } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+
+ set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
+ unregister_slb_shadow(hard_smp_processor_id(),
+ __pa(get_slb_shadow()));
+ rtas_stop_self();
+ }
+
/* Should never get here... */
BUG();
for(;;);
@@ -106,18 +206,43 @@
return 0;
}
+/*
+ * pseries_cpu_die: Wait for the cpu to die.
+ * @cpu: logical processor id of the CPU whose death we're awaiting.
+ *
+ * This function is called from the context of the thread which is performing
+ * the cpu-offline. Here we wait for long enough to allow the cpu in question
+ * to self-destroy so that the cpu-offline thread can send the CPU_DEAD
+ * notifications.
+ *
+ * OTOH, pseries_mach_cpu_die() is called by the @cpu when it wants to
+ * self-destruct.
+ */
static void pseries_cpu_die(unsigned int cpu)
{
int tries;
- int cpu_status;
+ int cpu_status = 1;
unsigned int pcpu = get_hard_smp_processor_id(cpu);
- for (tries = 0; tries < 25; tries++) {
- cpu_status = query_cpu_stopped(pcpu);
- if (cpu_status == 0 || cpu_status == -1)
- break;
- cpu_relax();
+ if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
+ cpu_status = 1;
+ for (tries = 0; tries < 1000; tries++) {
+ if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) {
+ cpu_status = 0;
+ break;
+ }
+ cpu_relax();
+ }
+ } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+
+ for (tries = 0; tries < 25; tries++) {
+ cpu_status = query_cpu_stopped(pcpu);
+ if (cpu_status == 0 || cpu_status == -1)
+ break;
+ cpu_relax();
+ }
}
+
if (cpu_status != 0) {
printk("Querying DEAD? cpu %i (%i) shows %i\n",
cpu, pcpu, cpu_status);
@@ -252,10 +377,41 @@
.notifier_call = pseries_smp_notifier,
};
+#define MAX_CEDE_LATENCY_LEVELS 4
+#define CEDE_LATENCY_PARAM_LENGTH 10
+#define CEDE_LATENCY_PARAM_MAX_LENGTH \
+ (MAX_CEDE_LATENCY_LEVELS * CEDE_LATENCY_PARAM_LENGTH * sizeof(char))
+#define CEDE_LATENCY_TOKEN 45
+
+static char cede_parameters[CEDE_LATENCY_PARAM_MAX_LENGTH];
+
+static int parse_cede_parameters(void)
+{
+ int call_status;
+
+ memset(cede_parameters, 0, CEDE_LATENCY_PARAM_MAX_LENGTH);
+ call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+ NULL,
+ CEDE_LATENCY_TOKEN,
+ __pa(cede_parameters),
+ CEDE_LATENCY_PARAM_MAX_LENGTH);
+
+ if (call_status != 0)
+ printk(KERN_INFO "CEDE_LATENCY: \
+ %s %s Error calling get-system-parameter(0x%x)\n",
+ __FILE__, __func__, call_status);
+ else
+ printk(KERN_INFO "CEDE_LATENCY: \
+ get-system-parameter successful.\n");
+
+ return call_status;
+}
+
static int __init pseries_cpu_hotplug_init(void)
{
struct device_node *np;
const char *typep;
+ int cpu;
for_each_node_by_name(np, "interrupt-controller") {
typep = of_get_property(np, "compatible", NULL);
@@ -283,8 +439,16 @@
smp_ops->cpu_die = pseries_cpu_die;
/* Processors can be added/removed only on LPAR */
- if (firmware_has_feature(FW_FEATURE_LPAR))
+ if (firmware_has_feature(FW_FEATURE_LPAR)) {
pSeries_reconfig_notifier_register(&pseries_smp_nb);
+ cpu_maps_update_begin();
+ if (cede_offline_enabled && parse_cede_parameters() == 0) {
+ default_offline_state = CPU_STATE_INACTIVE;
+ for_each_online_cpu(cpu)
+ set_default_offline_state(cpu);
+ }
+ cpu_maps_update_done();
+ }
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h
new file mode 100644
index 0000000..22574e0
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/offline_states.h
@@ -0,0 +1,18 @@
+#ifndef _OFFLINE_STATES_H_
+#define _OFFLINE_STATES_H_
+
+/* Cpu offline states go here */
+enum cpu_state_vals {
+ CPU_STATE_OFFLINE,
+ CPU_STATE_INACTIVE,
+ CPU_STATE_ONLINE,
+ CPU_MAX_OFFLINE_STATES
+};
+
+extern enum cpu_state_vals get_cpu_current_state(int cpu);
+extern void set_cpu_current_state(int cpu, enum cpu_state_vals state);
+extern enum cpu_state_vals get_preferred_offline_state(int cpu);
+extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state);
+extern void set_default_offline_state(int cpu);
+extern int start_secondary(void);
+#endif
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 440000c..8868c01 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -48,6 +48,7 @@
#include "plpar_wrappers.h"
#include "pseries.h"
#include "xics.h"
+#include "offline_states.h"
/*
@@ -84,6 +85,9 @@
/* Fixup atomic count: it exited inside IRQ handler. */
task_thread_info(paca[lcpu].__current)->preempt_count = 0;
+ if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE)
+ goto out;
+
/*
* If the RTAS start-cpu token does not exist then presume the
* cpu is already spinning.
@@ -98,6 +102,7 @@
return 0;
}
+out:
return 1;
}
@@ -111,12 +116,16 @@
vpa_init(cpu);
cpu_clear(cpu, of_spin_map);
+ set_cpu_current_state(cpu, CPU_STATE_ONLINE);
+ set_default_offline_state(cpu);
}
#endif /* CONFIG_XICS */
static void __devinit smp_pSeries_kick_cpu(int nr)
{
+ long rc;
+ unsigned long hcpuid;
BUG_ON(nr < 0 || nr >= NR_CPUS);
if (!smp_startup_cpu(nr))
@@ -128,6 +137,16 @@
* the processor will continue on to secondary_start
*/
paca[nr].cpu_start = 1;
+
+ set_preferred_offline_state(nr, CPU_STATE_ONLINE);
+
+ if (get_cpu_current_state(nr) == CPU_STATE_INACTIVE) {
+ hcpuid = get_hard_smp_processor_id(nr);
+ rc = plpar_hcall_norets(H_PROD, hcpuid);
+ if (rc != H_SUCCESS)
+ panic("Error: Prod to wake up processor %d Ret= %ld\n",
+ nr, rc);
+ }
}
static int smp_pSeries_cpu_bootable(unsigned int nr)
