More power management updates for v4.8-rc1

- Prevent the low-level assembly hibernate code on x86-64 from
    referring to __PAGE_OFFSET directly as a symbol which doesn't work
    when the kernel identity mapping base is randomized, in which case
    __PAGE_OFFSET is a variable (Rafael Wysocki).
 
  - Avoid selecting CPU_FREQ_STAT by default as the statistics are not
    required for proper cpufreq operation (Borislav Petkov).
 
  - Add Skylake-X and Broadwell-X IDs to the intel_pstate's list of
    processors where out-of-band (OBB) control of P-states is possible
    and if that is in use, intel_pstate should not attempt to manage
    P-states (Srinivas Pandruvada).
 
  - Drop some unnecessary checks from the wakeup IRQ handling code in
    the PM core (Markus Elfring).
 
  - Reduce the number operating performance point (OPP) lookups in
    one of the OPP framework's helper functions (Jisheng Zhang).
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABCAAGBQJXpKLNAAoJEILEb/54YlRx6L4P/39GR0kVB7vIyCajdWc4f3gh
 0zh5RbKC0YT4F6upebzgQ9uYS9cv4y+df7ShVwKQAea3wDReEmZhM/egOGw0Ls+8
 SS1MiJq1LSekyMIWH6cXwZsH69/V0LuWTBbzWYBgHUDbfEMlgwV5ZZMEH14/2bWw
 d4SLUUiW5P42im+IDAxpdYneKOrbJo3txj6WbOutgtIrHdPko6lF1dDouKvI1QTk
 zCBOkEB9nELq3rWN/sbPmHzbmbj/yFiiHk5+iqwuKKJZI8PQB9/C6Qmc3wvjtPpc
 GXLPI+OHqLgBMofGsiKOvm3hPQAIjf/ERsUilHLE3qOi/Mi0qj7U4dFivZrPWaCG
 j2bD+b36TffmG1r8L7NYbEKU60syeIFSRqAngbyswu6XF+NdVboaifENGcgM3tBC
 pUC1mFh/4PMKP5zW9mOwE6WSntZkw14CVR+A3fRFOuTBavNvjGdckwLi/aBsZdU3
 K4DJUFzdELF7+JdqnQV35yV2tgMbJhxQa/QBykiFBh3AyqliOZ8uBoIxxLinrGmH
 XWR3kB4ZPRBIStGI9IpG3lNhLLU7mLIdaFhGayicicAwFcLsXN7oKWVzYfUqWA9T
 1ptXApcRf6S9J1JnKHkznoQ1/D1pNYLbH+t7BOtWdK8SWBhMS2Lzo2kyKWsCFkJS
 16J8j1tcLDhN1dvcBT55
 =WvPB
 -----END PGP SIGNATURE-----

Merge tag 'pm-extra-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "A few more fixes and cleanups in the x86-64 low-level hibernation
  code, PM core, cpufreq (Kconfig and intel_pstate), and the operating
  points framework.

  Specifics:

   - Prevent the low-level assembly hibernate code on x86-64 from
     referring to __PAGE_OFFSET directly as a symbol which doesn't work
     when the kernel identity mapping base is randomized, in which case
     __PAGE_OFFSET is a variable (Rafael Wysocki).

   - Avoid selecting CPU_FREQ_STAT by default as the statistics are not
     required for proper cpufreq operation (Borislav Petkov).

   - Add Skylake-X and Broadwell-X IDs to the intel_pstate's list of
     processors where out-of-band (OBB) control of P-states is possible
     and if that is in use, intel_pstate should not attempt to manage
     P-states (Srinivas Pandruvada).

   - Drop some unnecessary checks from the wakeup IRQ handling code in
     the PM core (Markus Elfring).

   - Reduce the number operating performance point (OPP) lookups in one
     of the OPP framework's helper functions (Jisheng Zhang)"

* tag 'pm-extra-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  x86/power/64: Do not refer to __PAGE_OFFSET from assembly code
  cpufreq: Do not default-yes CPU_FREQ_STAT
  cpufreq: intel_pstate: Add more out-of-band IDs
  PM / OPP: optimize dev_pm_opp_set_rate() performance a bit
  PM-wakeup: Delete unnecessary checks before three function calls

arch/x86/power/hibernate_64.c

@@ -37,11 +37,11 @@ unsigned long jump_address_phys;
  */
 unsigned long restore_cr3 __visible;
 
-pgd_t *temp_level4_pgt __visible;
+unsigned long temp_level4_pgt __visible;
 
 unsigned long relocated_restore_code __visible;
 
-static int set_up_temporary_text_mapping(void)
+static int set_up_temporary_text_mapping(pgd_t *pgd)
 {
 	pmd_t *pmd;
 	pud_t *pud;
@@ -71,7 +71,7 @@ static int set_up_temporary_text_mapping(void)
 		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
 	set_pud(pud + pud_index(restore_jump_address),
 		__pud(__pa(pmd) | _KERNPG_TABLE));
-	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+	set_pgd(pgd + pgd_index(restore_jump_address),
 		__pgd(__pa(pud) | _KERNPG_TABLE));
 
 	return 0;
@@ -90,15 +90,16 @@ static int set_up_temporary_mappings(void)
 		.kernel_mapping = true,
 	};
 	unsigned long mstart, mend;
+	pgd_t *pgd;
 	int result;
 	int i;
 
-	temp_level4_pgt = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	pgd = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!temp_level4_pgt)
+	if (!pgd)
 		return -ENOMEM;
 
 	/* Prepare a temporary mapping for the kernel text */
-	result = set_up_temporary_text_mapping();
+	result = set_up_temporary_text_mapping(pgd);
 	if (result)
 		return result;
 
@@ -107,13 +108,12 @@ static int set_up_temporary_mappings(void)
 		mstart = pfn_mapped[i].start << PAGE_SHIFT;
 		mend   = pfn_mapped[i].end << PAGE_SHIFT;
 
-		result = kernel_ident_mapping_init(&info, temp_level4_pgt,
+		result = kernel_ident_mapping_init(&info, pgd, mstart, mend);
-						   mstart, mend);
-
 		if (result)
 			return result;
 	}
 
+	temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET;
 	return 0;
 }
 

arch/x86/power/hibernate_asm_64.S

@@ -72,8 +72,6 @@ ENTRY(restore_image)
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
 	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rcx
-	subq	%rcx, %rax
 	movq	%rax, %cr3
 	/* flush TLB */
 	movq	%rbx, %rcx

drivers/base/power/opp/core.c

@@ -402,6 +402,22 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
 
+static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
+						   unsigned long *freq)
+{
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->rate >= *freq) {
+			opp = temp_opp;
+			*freq = opp->rate;
+			break;
+		}
+	}
+
+	return opp;
+}
+
 /**
  * dev_pm_opp_find_freq_ceil() - Search for an rounded ceil freq
  * @dev:	device for which we do this operation
@@ -427,7 +443,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	opp_rcu_lockdep_assert();
 
@@ -440,15 +455,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	return _find_freq_ceil(opp_table, freq);
-		if (temp_opp->available && temp_opp->rate >= *freq) {
-			opp = temp_opp;
-			*freq = opp->rate;
-			break;
-		}
-	}
-
-	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 
@@ -612,7 +619,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return PTR_ERR(opp_table);
 	}
 
-	old_opp = dev_pm_opp_find_freq_ceil(dev, &old_freq);
+	old_opp = _find_freq_ceil(opp_table, &old_freq);
 	if (!IS_ERR(old_opp)) {
 		ou_volt = old_opp->u_volt;
 		ou_volt_min = old_opp->u_volt_min;
@@ -622,7 +629,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 			__func__, old_freq, PTR_ERR(old_opp));
 	}
 
-	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+	opp = _find_freq_ceil(opp_table, &freq);
 	if (IS_ERR(opp)) {
 		ret = PTR_ERR(opp);
 		dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n",

drivers/base/power/wakeup.c

@@ -334,10 +334,9 @@ void device_wakeup_arm_wake_irqs(void)
 	struct wakeup_source *ws;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
-		if (ws->wakeirq)
+		dev_pm_arm_wake_irq(ws->wakeirq);
-			dev_pm_arm_wake_irq(ws->wakeirq);
+
-	}
 	rcu_read_unlock();
 }
 
@@ -351,10 +350,9 @@ void device_wakeup_disarm_wake_irqs(void)
 	struct wakeup_source *ws;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
-		if (ws->wakeirq)
+		dev_pm_disarm_wake_irq(ws->wakeirq);
-			dev_pm_disarm_wake_irq(ws->wakeirq);
+
-	}
 	rcu_read_unlock();
 }
 
@@ -390,9 +388,7 @@ int device_wakeup_disable(struct device *dev)
 		return -EINVAL;
 
 	ws = device_wakeup_detach(dev);
-	if (ws)
+	wakeup_source_unregister(ws);
-		wakeup_source_unregister(ws);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(device_wakeup_disable);

drivers/cpufreq/Kconfig

@@ -32,7 +32,6 @@ config CPU_FREQ_BOOST_SW
 
 config CPU_FREQ_STAT
 	bool "CPU frequency transition statistics"
-	default y
 	help
 	  Export CPU frequency statistics information through sysfs.
 

drivers/cpufreq/intel_pstate.c

@@ -1374,6 +1374,8 @@ MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
 
 static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
+	ICPU(INTEL_FAM6_BROADWELL_X, core_params),
+	ICPU(INTEL_FAM6_SKYLAKE_X, core_params),
 	{}
 };