More power management updates for 7.0-rc1

- Fix the handling of package-scope MSRs in the intel_rapl power
    capping driver when called from the PMU subsystem and make it add all
    package CPUs to the PMU cpumask to allow tools to read RAPL events
    from any CPU in the package (Kuppuswamy Satharayananyan)
 
  - Rework the invalid version check in the intel_rapl_tpmi power capping
    driver to account for the fact that on partitioned systems, multiple
    TPMI instances may exist per package, but RAPL registers are only
    valid on one instance (Kuppuswamy Satharayananyan)
 
  - Describe the new intel_idle.table command line option in the
    admin-guide intel_idle documentation (Artem Bityutskiy)
 
  - Fix a crash in the ladder cpuidle governor on systems with only one
    (polling) idle state available by making the cpuidle core bypass the
    governor in those cases and adjust the other existing governors to
    that change (Aboorva Devarajan, Christian Loehle)
 
  - Update kerneldoc comments for wake IRQ management functions that
    have not been matching the code (Wang Jiayue)
 -----BEGIN PGP SIGNATURE-----
 
 iQFGBAABCAAwFiEEcM8Aw/RY0dgsiRUR7l+9nS/U47UFAmmWDssSHHJqd0Byand5
 c29ja2kubmV0AAoJEO5fvZ0v1OO1D5wH/j5drstZAsRqL4IwWPWBry0vhKGwr0vu
 f8/sRuiAm/dRpi0Ro5XDiJbR4ZBLDp+4dDBOsR47Ss9a+B57iCftzmXcx5QBzUid
 75W41IQ182Z/aGFQpU2kUPoRuNTUSmpUGVeon+SW4U24nCDaxOl4c2n8lWzgiznS
 oJEN6Y9JfYV+fnLoxWmwyniR9USp2UFXS7tugDBMX1e1+sfrNbAUyuEKCs6R6u65
 O7GTr2kA9lcM/hONBbXXpZNhtm23Jj0YS77lsELXoR9YWXTPJVTKVXmD11wrbWvE
 quYefGoWCNcxQG3lYfw2vLdKMT3OYeRaq+DT3+9odaooHOJ6f4FqAzQ=
 =cjJd
 -----END PGP SIGNATURE-----

Merge tag 'pm-7.0-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These are mostly fixes on top of the power management updates merged
  recently in cpuidle governors, in the Intel RAPL power capping driver
  and in the wake IRQ management code:

   - Fix the handling of package-scope MSRs in the intel_rapl power
     capping driver when called from the PMU subsystem and make it add
     all package CPUs to the PMU cpumask to allow tools to read RAPL
     events from any CPU in the package (Kuppuswamy Satharayananyan)

   - Rework the invalid version check in the intel_rapl_tpmi power
     capping driver to account for the fact that on partitioned systems,
     multiple TPMI instances may exist per package, but RAPL registers
     are only valid on one instance (Kuppuswamy Satharayananyan)

   - Describe the new intel_idle.table command line option in the
     admin-guide intel_idle documentation (Artem Bityutskiy)

   - Fix a crash in the ladder cpuidle governor on systems with only one
     (polling) idle state available by making the cpuidle core bypass
     the governor in those cases and adjust the other existing governors
     to that change (Aboorva Devarajan, Christian Loehle)

   - Update kerneldoc comments for wake IRQ management functions that
     have not been matching the code (Wang Jiayue)"

* tag 'pm-7.0-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpuidle: menu: Remove single state handling
  cpuidle: teo: Remove single state handling
  cpuidle: haltpoll: Remove single state handling
  cpuidle: Skip governor when only one idle state is available
  powercap: intel_rapl_tpmi: Remove FW_BUG from invalid version check
  PM: sleep: wakeirq: Update outdated documentation comments
  Documentation: PM: Document intel_idle.table command line option
  powercap: intel_rapl: Expose all package CPUs in PMU cpumask
  powercap: intel_rapl: Remove incorrect CPU check in PMU context

Documentation/admin-guide/pm/intel_idle.rst

@@ -260,6 +260,17 @@ mode to off when the CPU is in any one of the available idle states.  This may
 help performance of a sibling CPU at the expense of a slightly higher wakeup
 latency for the idle CPU.
 
+The ``table`` argument allows customization of idle state latency and target
+residency. The syntax is a comma-separated list of ``name:latency:residency``
+entries, where ``name`` is the idle state name, ``latency`` is the exit latency
+in microseconds, and ``residency`` is the target residency in microseconds. It
+is not necessary to specify all idle states; only those to be customized. For
+example, ``C1:1:3,C6:50:100`` sets the exit latency and target residency for
+C1 and C6 to 1/3 and 50/100 microseconds, respectively. Remaining idle states
+keep their default values. The driver verifies that deeper idle states have
+higher latency and target residency than shallower ones. Also, target
+residency cannot be smaller than exit latency. If any of these conditions is
+not met, the driver ignores the entire ``table`` parameter.
 
 .. _intel-idle-core-and-package-idle-states:
 

drivers/base/power/wakeirq.c

@@ -273,8 +273,10 @@ EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq_reverse);
  * otherwise try to disable already disabled wakeirq. The wake-up interrupt
  * starts disabled with IRQ_NOAUTOEN set.
  *
- * Should be only called from rpm_suspend() and rpm_resume() path.
- * Caller must hold &dev->power.lock to change wirq->status
+ * Should be called from rpm_suspend(), rpm_resume(),
+ * pm_runtime_force_suspend() or pm_runtime_force_resume().
+ * Caller must hold &dev->power.lock or disable runtime PM to change
+ * wirq->status.
  */
 void dev_pm_enable_wake_irq_check(struct device *dev,
 				  bool can_change_status)
@@ -306,7 +308,8 @@ enable:
  * @cond_disable: if set, also check WAKE_IRQ_DEDICATED_REVERSE
  *
  * Disables wake-up interrupt conditionally based on status.
- * Should be only called from rpm_suspend() and rpm_resume() path.
+ * Should be called from rpm_suspend(), rpm_resume(),
+ * pm_runtime_force_suspend() or pm_runtime_force_resume().
  */
 void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable)
 {
@@ -332,7 +335,7 @@ void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable)
  * enable wake IRQ after running ->runtime_suspend() which depends on
  * WAKE_IRQ_DEDICATED_REVERSE.
  *
- * Should be only called from rpm_suspend() path.
+ * Should be called from rpm_suspend() or pm_runtime_force_suspend().
  */
 void dev_pm_enable_wake_irq_complete(struct device *dev)
 {

drivers/cpuidle/cpuidle.c

@@ -359,6 +359,16 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev,
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		   bool *stop_tick)
 {
+	/*
+	 * If there is only a single idle state (or none), there is nothing
+	 * meaningful for the governor to choose. Skip the governor and
+	 * always use state 0 with the tick running.
+	 */
+	if (drv->state_count <= 1) {
+		*stop_tick = false;
+		return 0;
+	}
+
 	return cpuidle_curr_governor->select(drv, dev, stop_tick);
 }
 

drivers/cpuidle/governors/haltpoll.c

@@ -50,9 +50,7 @@ static int haltpoll_select(struct cpuidle_driver *drv,
 			   struct cpuidle_device *dev,
 			   bool *stop_tick)
 {
-	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
-
-	if (!drv->state_count || latency_req == 0) {
+	if (cpuidle_governor_latency_req(dev->cpu) == 0) {
 		*stop_tick = false;
 		return 0;
 	}

drivers/cpuidle/governors/menu.c

@@ -281,7 +281,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		data->bucket = BUCKETS - 1;
 	}
 
-	if (drv->state_count <= 1 || latency_req == 0 ||
+	if (latency_req == 0 ||
 	    ((data->next_timer_ns < drv->states[1].target_residency_ns ||
 	      latency_req < drv->states[1].exit_latency_ns) &&
 	     !dev->states_usage[0].disable)) {

drivers/cpuidle/governors/teo.c

@@ -338,12 +338,6 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 */
 	cpu_data->sleep_length_ns = KTIME_MAX;
 
-	/* Check if there is any choice in the first place. */
-	if (drv->state_count < 2) {
-		idx = 0;
-		goto out_tick;
-	}
-
 	if (!dev->states_usage[0].disable)
 		idx = 0;
 

drivers/powercap/intel_rapl_common.c

@@ -254,7 +254,7 @@ static void rapl_init_domains(struct rapl_package *rp);
 static int rapl_read_data_raw(struct rapl_domain *rd,
 			      enum rapl_primitives prim,
 			      bool xlate, u64 *data,
-			      bool atomic);
+			      bool pmu_ctx);
 static int rapl_write_data_raw(struct rapl_domain *rd,
 			       enum rapl_primitives prim,
 			       unsigned long long value);
@@ -832,7 +832,7 @@ prim_fixups(struct rapl_domain *rd, enum rapl_primitives prim)
  */
 static int rapl_read_data_raw(struct rapl_domain *rd,
 			      enum rapl_primitives prim, bool xlate, u64 *data,
-			      bool atomic)
+			      bool pmu_ctx)
 {
 	u64 value;
 	enum rapl_primitives prim_fixed = prim_fixups(rd, prim);
@@ -854,7 +854,7 @@ static int rapl_read_data_raw(struct rapl_domain *rd,
 
 	ra.mask = rpi->mask;
 
-	if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra, atomic)) {
+	if (rd->rp->priv->read_raw(get_rid(rd->rp), &ra, pmu_ctx)) {
 		pr_debug("failed to read reg 0x%llx for %s:%s\n", ra.reg.val, rd->rp->name, rd->name);
 		return -EIO;
 	}
@@ -1590,23 +1590,21 @@ static struct rapl_pmu rapl_pmu;
 
 /* PMU helpers */
 
-static int get_pmu_cpu(struct rapl_package *rp)
+static void set_pmu_cpumask(struct rapl_package *rp, cpumask_var_t mask)
 {
 	int cpu;
 
 	if (!rp->has_pmu)
-		return nr_cpu_ids;
+		return;
 
 	/* Only TPMI & MSR RAPL are supported for now */
 	if (rp->priv->type != RAPL_IF_TPMI && rp->priv->type != RAPL_IF_MSR)
-		return nr_cpu_ids;
+		return;
 
 	/* TPMI/MSR RAPL uses any CPU in the package for PMU */
 	for_each_online_cpu(cpu)
 		if (topology_physical_package_id(cpu) == rp->id)
-			return cpu;
-
-	return nr_cpu_ids;
+			cpumask_set_cpu(cpu, mask);
 }
 
 static bool is_rp_pmu_cpu(struct rapl_package *rp, int cpu)
@@ -1883,7 +1881,6 @@ static ssize_t cpumask_show(struct device *dev,
 {
 	struct rapl_package *rp;
 	cpumask_var_t cpu_mask;
-	int cpu;
 	int ret;
 
 	if (!alloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -1895,9 +1892,7 @@ static ssize_t cpumask_show(struct device *dev,
 
 	/* Choose a cpu for each RAPL Package */
 	list_for_each_entry(rp, &rapl_packages, plist) {
-		cpu = get_pmu_cpu(rp);
-		if (cpu < nr_cpu_ids)
-			cpumask_set_cpu(cpu, cpu_mask);
+		set_pmu_cpumask(rp, cpu_mask);
 	}
 	cpus_read_unlock();
 

drivers/powercap/intel_rapl_msr.c

@@ -110,16 +110,14 @@ static int rapl_cpu_down_prep(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_msr_read_raw(int cpu, struct reg_action *ra, bool atomic)
+static int rapl_msr_read_raw(int cpu, struct reg_action *ra, bool pmu_ctx)
 {
 	/*
-	 * When called from atomic-context (eg PMU event handler)
-	 * perform MSR read directly using rdmsrq().
+	 * When called from PMU context, perform MSR read directly using
+	 * rdmsrq() without IPI overhead. Package-scoped MSRs are readable
+	 * from any CPU in the package.
 	 */
-	if (atomic) {
-		if (unlikely(smp_processor_id() != cpu))
-			return -EIO;
-
+	if (pmu_ctx) {
 		rdmsrq(ra->reg.msr, ra->value);
 		goto out;
 	}

drivers/powercap/intel_rapl_tpmi.c

@@ -157,7 +157,7 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset)
 	tpmi_domain_flags = tpmi_domain_header >> 32 & 0xffff;
 
 	if (tpmi_domain_version == TPMI_VERSION_INVALID) {
-		pr_warn(FW_BUG "Invalid version\n");
+		pr_debug("Invalid version, other instances may be valid\n");
 		return -ENODEV;
 	}
 

include/linux/intel_rapl.h

@@ -152,7 +152,7 @@ struct rapl_if_priv {
 	union rapl_reg reg_unit;
 	union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
 	int limits[RAPL_DOMAIN_MAX];
-	int (*read_raw)(int id, struct reg_action *ra, bool atomic);
+	int (*read_raw)(int id, struct reg_action *ra, bool pmu_ctx);
 	int (*write_raw)(int id, struct reg_action *ra);
 	void *defaults;
 	void *rpi;