More power management updates for 6.4-rc1

- Make test_resume work again after the changes that made hibernation
    open the snapshot device in exclusive mode (Chen Yu).
 
  - Clean up code in several places in intel_idle (Artem Bityutskiy).
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEE4fcc61cGeeHD/fCwgsRv/nhiVHEFAmRSbLgSHHJqd0Byand5
 c29ja2kubmV0AAoJEILEb/54YlRxbvUP/3WeXEfulhN2FRuqmfqLtWNrpMwsoFpd
 9BQRokAQdKL3V2Q+YgdEH22+cB2LNAo5ty1+SHXjzsiExxBYWbKd6/AwOwwmFVPq
 I8uHS5pSqYQrZLI7eA1ZhFiTotePOpLyHpsHO3lezxXMlvEw30tY8g09WTH1F2Cz
 uzgTB1NTHRZaHWObrjvPkq3IERAbtF1xAQVPMtyWzs7IoCOlLxsKtHpfLBwGFYpZ
 1U7dbAFoGuQYjCUE9i1wbQdee9elRhPDJ6TGCx8rqtRRybxPZOdz1M947K/N5Q23
 OtK1HHfTIFHoi36sjwfEdZC89RGr7CI3hc5CAgexxwtsCw4gpIgvFoNXjCKW1q0J
 +C5ztCntxTGzWi37pnriV3I0NlTjTdEAoS2VDNRGlj0Vvrrx5S5H35qjoqD66N3a
 +zJ9eEYl5WGJlmZWxUvycJmS0PdPp755tmxrBRWqm7nr+oVJWKY8j2OKjlADCgoG
 k74zf1dp4zZJHIml1QpaRp0EsueiHs66Xu52VoFKyrAp0+ytYtnC1/SeKoYF4jDg
 PoTJmIT5ve8Nq8vwYbrg/z497J3bKHfbf1LPxDPNHVB6gx4Nv254qUNaM8oyic9j
 aHNwna6IAl+BshickaR0lUccJLnBAgPWyxnwFlfHaDbAGVtLNLSVFYlwr7xiUvlo
 t9eB4FZNGKMU
 =CwBd
 -----END PGP SIGNATURE-----

Merge tag 'pm-6.4-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These fix a hibernation test mode regression and clean up the
  intel_idle driver.

  Specifics:

   - Make test_resume work again after the changes that made hibernation
     open the snapshot device in exclusive mode (Chen Yu)

   - Clean up code in several places in intel_idle (Artem Bityutskiy)"

* tag 'pm-6.4-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  intel_idle: mark few variables as __read_mostly
  intel_idle: do not sprinkle module parameter definitions around
  intel_idle: fix confusing message
  intel_idle: improve C-state flags handling robustness
  intel_idle: further intel_idle_init_cstates_icpu() cleanup
  intel_idle: clean up intel_idle_init_cstates_icpu()
  intel_idle: use pr_info() instead of printk()
  PM: hibernate: Do not get block device exclusively in test_resume mode
  PM: hibernate: Turn snapshot_test into global variable

drivers/idle/intel_idle.c

@@ -66,8 +66,9 @@ static struct cpuidle_driver intel_idle_driver = {
 };
 /* intel_idle.max_cstate=0 disables driver */
 static int max_cstate = CPUIDLE_STATE_MAX - 1;
-static unsigned int disabled_states_mask;
+static unsigned int disabled_states_mask __read_mostly;
-static unsigned int preferred_states_mask;
+static unsigned int preferred_states_mask __read_mostly;
+static bool force_irq_on __read_mostly;
 
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
@@ -1838,9 +1839,6 @@ static bool __init intel_idle_verify_cstate(unsigned int mwait_hint)
 	return true;
 }
 
-static bool force_irq_on __read_mostly;
-module_param(force_irq_on, bool, 0444);
-
 static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 {
 	int cstate;
@@ -1871,6 +1869,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 	}
 
 	for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
+		struct cpuidle_state *state;
 		unsigned int mwait_hint;
 
 		if (intel_idle_max_cstate_reached(cstate))
@@ -1893,29 +1892,39 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 
 		/* Structure copy. */
 		drv->states[drv->state_count] = cpuidle_state_table[cstate];
+		state = &drv->states[drv->state_count];
 
-		if ((cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) {
+		if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) {
-			printk("intel_idle: forced intel_idle_irq for state %d\n", cstate);
+			/*
-			drv->states[drv->state_count].enter = intel_idle_irq;
+			 * Combining with XSTATE with IBRS or IRQ_ENABLE flags
+			 * is not currently supported but this driver.
+			 */
+			WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IBRS);
+			WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
+			state->enter = intel_idle_xstate;
+		} else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
+			   state->flags & CPUIDLE_FLAG_IBRS) {
+			/*
+			 * IBRS mitigation requires that C-states are entered
+			 * with interrupts disabled.
+			 */
+			WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
+			state->enter = intel_idle_ibrs;
+		} else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) {
+			state->enter = intel_idle_irq;
+		} else if (force_irq_on) {
+			pr_info("forced intel_idle_irq for state %d\n", cstate);
+			state->enter = intel_idle_irq;
 		}
 
-		if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
-		    cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IBRS) {
-			WARN_ON_ONCE(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE);
-			drv->states[drv->state_count].enter = intel_idle_ibrs;
-		}
-
-		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE)
-			drv->states[drv->state_count].enter = intel_idle_xstate;
-
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&
-		     !(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_ALWAYS_ENABLE)))
+		     !(state->flags & CPUIDLE_FLAG_ALWAYS_ENABLE)))
-			drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF;
+			state->flags |= CPUIDLE_FLAG_OFF;
 
-		if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count]))
+		if (intel_idle_state_needs_timer_stop(state))
-			drv->states[drv->state_count].flags |= CPUIDLE_FLAG_TIMER_STOP;
+			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
 
 		drv->state_count++;
 	}
@@ -2146,3 +2155,9 @@ MODULE_PARM_DESC(states_off, "Mask of disabled idle states");
  */
 module_param_named(preferred_cstates, preferred_states_mask, uint, 0444);
 MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states");
+/*
+ * Debugging option that forces the driver to enter all C-states with
+ * interrupts enabled. Does not apply to C-states with
+ * 'CPUIDLE_FLAG_INIT_XSTATE' and 'CPUIDLE_FLAG_IBRS' flags.
+ */
+module_param(force_irq_on, bool, 0444);

kernel/power/hibernate.c

@@ -64,6 +64,7 @@ enum {
 static int hibernation_mode = HIBERNATION_SHUTDOWN;
 
 bool freezer_test_done;
+bool snapshot_test;
 
 static const struct platform_hibernation_ops *hibernation_ops;
 
@@ -687,18 +688,22 @@ static int load_image_and_restore(void)
 {
 	int error;
 	unsigned int flags;
+	fmode_t mode = FMODE_READ;
+
+	if (snapshot_test)
+		mode |= FMODE_EXCL;
 
 	pm_pr_dbg("Loading hibernation image.\n");
 
 	lock_device_hotplug();
 	error = create_basic_memory_bitmaps();
 	if (error) {
-		swsusp_close(FMODE_READ | FMODE_EXCL);
+		swsusp_close(mode);
 		goto Unlock;
 	}
 
 	error = swsusp_read(&flags);
-	swsusp_close(FMODE_READ | FMODE_EXCL);
+	swsusp_close(mode);
 	if (!error)
 		error = hibernation_restore(flags & SF_PLATFORM_MODE);
 
@@ -716,7 +721,6 @@ static int load_image_and_restore(void)
  */
 int hibernate(void)
 {
-	bool snapshot_test = false;
 	unsigned int sleep_flags;
 	int error;
 
@@ -744,6 +748,9 @@ int hibernate(void)
 	if (error)
 		goto Exit;
 
+	/* protected by system_transition_mutex */
+	snapshot_test = false;
+
 	lock_device_hotplug();
 	/* Allocate memory management structures */
 	error = create_basic_memory_bitmaps();
@@ -940,6 +947,8 @@ static int software_resume(void)
 	 */
 	mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
 
+	snapshot_test = false;
+
 	if (swsusp_resume_device)
 		goto Check_image;
 

kernel/power/power.h

@@ -59,6 +59,7 @@ asmlinkage int swsusp_save(void);
 
 /* kernel/power/hibernate.c */
 extern bool freezer_test_done;
+extern bool snapshot_test;
 
 extern int hibernation_snapshot(int platform_mode);
 extern int hibernation_restore(int platform_mode);

kernel/power/swap.c

@@ -1518,9 +1518,13 @@ int swsusp_check(void)
 {
 	int error;
 	void *holder;
+	fmode_t mode = FMODE_READ;
+
+	if (snapshot_test)
+		mode |= FMODE_EXCL;
 
 	hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device,
-					    FMODE_READ | FMODE_EXCL, &holder);
+					    mode, &holder);
 	if (!IS_ERR(hib_resume_bdev)) {
 		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		clear_page(swsusp_header);
@@ -1547,7 +1551,7 @@ int swsusp_check(void)
 
 put:
 		if (error)
-			blkdev_put(hib_resume_bdev, FMODE_READ | FMODE_EXCL);
+			blkdev_put(hib_resume_bdev, mode);
 		else
 			pr_debug("Image signature found, resuming\n");
 	} else {