Merge branches 'pm-sleep' and 'powercap'

* pm-sleep:
  PM / sleep: Print active wakeup sources when blocking on wakeup_count reads
  x86/suspend: fix false positive KASAN warning on suspend/resume
  PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag
  PM / sleep: System sleep state selection interface rework
  PM / hibernate: Verify the consistent of e820 memory map by md5 digest

* powercap:
  powercap / RAPL: Add Knights Mill CPUID
  powercap/intel_rapl: fix and tidy up error handling
  powercap/intel_rapl: Track active CPUs internally
  powercap/intel_rapl: Cleanup duplicated init code
  powercap/intel rapl: Convert to hotplug state machine
  powercap/intel_rapl: Propagate error code when registration fails
  powercap/intel_rapl: Add missing domain data update on hotplug

Documentation/ABI/testing/sysfs-power

@@ -7,30 +7,35 @@ Description:
 		subsystem.
 
 What:		/sys/power/state
-Date:		May 2014
+Date:		November 2016
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/state file controls system sleep states.
 		Reading from this file returns the available sleep state
-		labels, which may be "mem", "standby", "freeze" and "disk"
+		labels, which may be "mem" (suspend), "standby" (power-on
-		(hibernation).  The meanings of the first three labels depend on
+		suspend), "freeze" (suspend-to-idle) and "disk" (hibernation).
-		the relative_sleep_states command line argument as follows:
-		 1) relative_sleep_states = 1
-		    "mem", "standby", "freeze" represent non-hibernation sleep
-		    states from the deepest ("mem", always present) to the
-		    shallowest ("freeze").  "standby" and "freeze" may or may
-		    not be present depending on the capabilities of the
-		    platform.  "freeze" can only be present if "standby" is
-		    present.
-		 2) relative_sleep_states = 0 (default)
-		    "mem" - "suspend-to-RAM", present if supported.
-		    "standby" - "power-on suspend", present if supported.
-		    "freeze" - "suspend-to-idle", always present.
 
-		Writing to this file one of these strings causes the system to
+		Writing one of the above strings to this file causes the system
-		transition into the corresponding state, if available.  See
+		to transition into the corresponding state, if available.
-		Documentation/power/states.txt for a description of what
+
-		"suspend-to-RAM", "power-on suspend" and "suspend-to-idle" mean.
+		See Documentation/power/states.txt for more information.
+
+What:		/sys/power/mem_sleep
+Date:		November 2016
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
+Description:
+		The /sys/power/mem_sleep file controls the operating mode of
+		system suspend.  Reading from it returns the available modes
+		as "s2idle" (always present), "shallow" and "deep" (present if
+		supported).  The mode that will be used on subsequent attempts
+		to suspend the system (by writing "mem" to the /sys/power/state
+		file described above) is enclosed in square brackets.
+
+		Writing one of the above strings to this file causes the mode
+		represented by it to be used on subsequent attempts to suspend
+		the system.
+
+		See Documentation/power/states.txt for more information.
 
 What:		/sys/power/disk
 Date:		September 2006

Documentation/kernel-parameters.txt

@@ -2334,6 +2334,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			memory contents and reserves bad memory
 			regions that are detected.
 
+	mem_sleep_default=	[SUSPEND] Default system suspend mode:
+			s2idle  - Suspend-To-Idle
+			shallow - Power-On Suspend or equivalent (if supported)
+			deep    - Suspend-To-RAM or equivalent (if supported)
+			See Documentation/power/states.txt.
+
 	meye.*=		[HW] Set MotionEye Camera parameters
 			See Documentation/video4linux/meye.txt.
 
@@ -3677,13 +3683,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			[KNL, SMP] Set scheduler's default relax_domain_level.
 			See Documentation/cgroup-v1/cpusets.txt.
 
-	relative_sleep_states=
-			[SUSPEND] Use sleep state labeling where the deepest
-			state available other than hibernation is always "mem".
-			Format: { "0" | "1" }
-			0 -- Traditional sleep state labels.
-			1 -- Relative sleep state labels.
-
 	reserve=	[KNL,BUGS] Force the kernel to ignore some iomem area
 
 	reservetop=	[X86-32]

Documentation/power/states.txt

@@ -8,25 +8,43 @@ for each state.
 
 The states are represented by strings that can be read or written to the
 /sys/power/state file.  Those strings may be "mem", "standby", "freeze" and
-"disk", where the last one always represents hibernation (Suspend-To-Disk) and
+"disk", where the last three always represent Power-On Suspend (if supported),
-the meaning of the remaining ones depends on the relative_sleep_states command
+Suspend-To-Idle and hibernation (Suspend-To-Disk), respectively.
-line argument.
 
-For relative_sleep_states=1, the strings "mem", "standby" and "freeze" label the
+The meaning of the "mem" string is controlled by the /sys/power/mem_sleep file.
-available non-hibernation sleep states from the deepest to the shallowest,
+It contains strings representing the available modes of system suspend that may
-respectively.  In that case, "mem" is always present in /sys/power/state,
+be triggered by writing "mem" to /sys/power/state.  These modes are "s2idle"
-because there is at least one non-hibernation sleep state in every system.  If
+(Suspend-To-Idle), "shallow" (Power-On Suspend) and "deep" (Suspend-To-RAM).
-the given system supports two non-hibernation sleep states, "standby" is present
+The "s2idle" mode is always available, while the other ones are only available
-in /sys/power/state in addition to "mem".  If the system supports three
+if supported by the platform (if not supported, the strings representing them
-non-hibernation sleep states, "freeze" will be present in /sys/power/state in
+are not present in /sys/power/mem_sleep).  The string representing the suspend
-addition to "mem" and "standby".
+mode to be used subsequently is enclosed in square brackets.  Writing one of
+the other strings present in /sys/power/mem_sleep to it causes the suspend mode
+to be used subsequently to change to the one represented by that string.
 
-For relative_sleep_states=0, which is the default, the following descriptions
+Consequently, there are two ways to cause the system to go into the
-apply.
+Suspend-To-Idle sleep state.  The first one is to write "freeze" directly to
+/sys/power/state.  The second one is to write "s2idle" to /sys/power/mem_sleep
+and then to wrtie "mem" to /sys/power/state.  Similarly, there are two ways
+to cause the system to go into the Power-On Suspend sleep state (the strings to
+write to the control files in that case are "standby" or "shallow" and "mem",
+respectively) if that state is supported by the platform.  In turn, there is
+only one way to cause the system to go into the Suspend-To-RAM state (write
+"deep" into /sys/power/mem_sleep and "mem" into /sys/power/state).
 
-state:		Suspend-To-Idle
+The default suspend mode (ie. the one to be used without writing anything into
+/sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or
+"s2idle", but it can be overridden by the value of the "mem_sleep_default"
+parameter in the kernel command line.  On some ACPI-based systems, depending on
+the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM
+is supported.
+
+The properties of all of the sleep states are described below.
+
+
+State:		Suspend-To-Idle
 ACPI state:	S0
-Label:		"freeze"
+Label:		"s2idle" ("freeze")
 
 This state is a generic, pure software, light-weight, system sleep state.
 It allows more energy to be saved relative to runtime idle by freezing user
@@ -35,13 +53,13 @@ lower-power than available at run time), such that the processors can
 spend more time in their idle states.
 
 This state can be used for platforms without Power-On Suspend/Suspend-to-RAM
-support, or it can be used in addition to Suspend-to-RAM (memory sleep)
+support, or it can be used in addition to Suspend-to-RAM to provide reduced
-to provide reduced resume latency.  It is always supported.
+resume latency.  It is always supported.
 
 
 State:		Standby / Power-On Suspend
 ACPI State:	S1
-Label:		"standby"
+Label:		"shallow" ("standby")
 
 This state, if supported, offers moderate, though real, power savings, while
 providing a relatively low-latency transition back to a working system.  No
@@ -58,7 +76,7 @@ state.
 
 State:		Suspend-to-RAM
 ACPI State:	S3
-Label:		"mem"
+Label:		"deep"
 
 This state, if supported, offers significant power savings as everything in the
 system is put into a low-power state, except for memory, which should be placed

arch/x86/kernel/acpi/wakeup_64.S

@@ -109,6 +109,15 @@ ENTRY(do_suspend_lowlevel)
 	movq	pt_regs_r14(%rax), %r14
 	movq	pt_regs_r15(%rax), %r15
 
+#ifdef CONFIG_KASAN
+	/*
+	 * The suspend path may have poisoned some areas deeper in the stack,
+	 * which we now need to unpoison.
+	 */
+	movq	%rsp, %rdi
+	call	kasan_unpoison_task_stack_below
+#endif
+
 	xorl	%eax, %eax
 	addq	$8, %rsp
 	FRAME_END

arch/x86/power/hibernate_64.c

@@ -11,6 +11,10 @@
 #include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/suspend.h>
+#include <linux/scatterlist.h>
+#include <linux/kdebug.h>
+
+#include <crypto/hash.h>
 
 #include <asm/init.h>
 #include <asm/proto.h>
@@ -177,14 +181,86 @@ int pfn_is_nosave(unsigned long pfn)
 	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
 }
 
+#define MD5_DIGEST_SIZE 16
+
 struct restore_data_record {
 	unsigned long jump_address;
 	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
+	u8 e820_digest[MD5_DIGEST_SIZE];
 };
 
-#define RESTORE_MAGIC	0x123456789ABCDEF0UL
+#define RESTORE_MAGIC	0x23456789ABCDEF01UL
+
+#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
+/**
+ * get_e820_md5 - calculate md5 according to given e820 map
+ *
+ * @map: the e820 map to be calculated
+ * @buf: the md5 result to be stored to
+ */
+static int get_e820_md5(struct e820map *map, void *buf)
+{
+	struct scatterlist sg;
+	struct crypto_ahash *tfm;
+	int size;
+	int ret = 0;
+
+	tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return -ENOMEM;
+
+	{
+		AHASH_REQUEST_ON_STACK(req, tfm);
+		size = offsetof(struct e820map, map)
+			+ sizeof(struct e820entry) * map->nr_map;
+		ahash_request_set_tfm(req, tfm);
+		sg_init_one(&sg, (u8 *)map, size);
+		ahash_request_set_callback(req, 0, NULL, NULL);
+		ahash_request_set_crypt(req, &sg, buf, size);
+
+		if (crypto_ahash_digest(req))
+			ret = -EINVAL;
+		ahash_request_zero(req);
+	}
+	crypto_free_ahash(tfm);
+
+	return ret;
+}
+
+static void hibernation_e820_save(void *buf)
+{
+	get_e820_md5(e820_saved, buf);
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+	int ret;
+	u8 result[MD5_DIGEST_SIZE];
+
+	memset(result, 0, MD5_DIGEST_SIZE);
+	/* If there is no digest in suspend kernel, let it go. */
+	if (!memcmp(result, buf, MD5_DIGEST_SIZE))
+		return false;
+
+	ret = get_e820_md5(e820_saved, result);
+	if (ret)
+		return true;
+
+	return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
+}
+#else
+static void hibernation_e820_save(void *buf)
+{
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+	/* If md5 is not builtin for restore kernel, let it go. */
+	return false;
+}
+#endif
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -201,6 +277,9 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
+
+	hibernation_e820_save(rdr->e820_digest);
+
 	return 0;
 }
 
@@ -216,5 +295,16 @@ int arch_hibernation_header_restore(void *addr)
 	restore_jump_address = rdr->jump_address;
 	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
-	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
+
+	if (rdr->magic != RESTORE_MAGIC) {
+		pr_crit("Unrecognized hibernate image header format!\n");
+		return -EINVAL;
+	}
+
+	if (hibernation_e820_mismatch(rdr->e820_digest)) {
+		pr_crit("Hibernate inconsistent memory map detected!\n");
+		return -ENODEV;
+	}
+
+	return 0;
 }

drivers/acpi/sleep.c

@@ -674,6 +674,14 @@ static void acpi_sleep_suspend_setup(void)
 		if (acpi_sleep_state_supported(i))
 			sleep_states[i] = 1;
 
+	/*
+	 * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and
+	 * the default suspend mode was not selected from the command line.
+	 */
+	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 &&
+	    mem_sleep_default > PM_SUSPEND_MEM)
+		mem_sleep_default = PM_SUSPEND_FREEZE;
+
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
 	freeze_set_ops(&acpi_freeze_ops);

drivers/base/power/wakeup.c

@@ -811,7 +811,7 @@ void pm_print_active_wakeup_sources(void)
 	rcu_read_lock();
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
-			pr_info("active wakeup source: %s\n", ws->name);
+			pr_debug("active wakeup source: %s\n", ws->name);
 			active = 1;
 		} else if (!active &&
 			   (!last_activity_ws ||
@@ -822,7 +822,7 @@ void pm_print_active_wakeup_sources(void)
 	}
 
 	if (!active && last_activity_ws)
-		pr_info("last active wakeup source: %s\n",
+		pr_debug("last active wakeup source: %s\n",
 			last_activity_ws->name);
 	rcu_read_unlock();
 }
@@ -905,7 +905,7 @@ bool pm_get_wakeup_count(unsigned int *count, bool block)
 			split_counters(&cnt, &inpr);
 			if (inpr == 0 || signal_pending(current))
 				break;
-
+			pm_print_active_wakeup_sources();
 			schedule();
 		}
 		finish_wait(&wakeup_count_wait_queue, &wait);

drivers/powercap/intel_rapl.c

@@ -189,14 +189,13 @@ struct rapl_package {
 	unsigned int time_unit;
 	struct rapl_domain *domains; /* array of domains, sized at runtime */
 	struct powercap_zone *power_zone; /* keep track of parent zone */
-	int nr_cpus; /* active cpus on the package, topology info is lost during
-		      * cpu hotplug. so we have to track ourselves.
-		      */
 	unsigned long power_limit_irq; /* keep track of package power limit
 					* notify interrupt enable status.
 					*/
 	struct list_head plist;
 	int lead_cpu; /* one active cpu per package for access */
+	/* Track active cpus */
+	struct cpumask cpumask;
 };
 
 struct rapl_defaults {
@@ -275,18 +274,6 @@ static struct rapl_package *find_package_by_id(int id)
 	return NULL;
 }
 
-/* caller must hold cpu hotplug lock */
-static void rapl_cleanup_data(void)
-{
-	struct rapl_package *p, *tmp;
-
-	list_for_each_entry_safe(p, tmp, &rapl_packages, plist) {
-		kfree(p->domains);
-		list_del(&p->plist);
-		kfree(p);
-	}
-}
-
 static int get_energy_counter(struct powercap_zone *power_zone, u64 *energy_raw)
 {
 	struct rapl_domain *rd;
@@ -442,6 +429,7 @@ static int contraint_to_pl(struct rapl_domain *rd, int cid)
 			return i;
 		}
 	}
+	pr_err("Cannot find matching power limit for constraint %d\n", cid);
 
 	return -EINVAL;
 }
@@ -457,6 +445,10 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid,
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
+	if (id < 0) {
+		ret = id;
+		goto set_exit;
+	}
 
 	rp = rd->rp;
 
@@ -496,6 +488,11 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
+	if (id < 0) {
+		ret = id;
+		goto get_exit;
+	}
+
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		prim = POWER_LIMIT1;
@@ -512,6 +509,7 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 	else
 		*data = val;
 
+get_exit:
 	put_online_cpus();
 
 	return ret;
@@ -527,6 +525,10 @@ static int set_time_window(struct powercap_zone *power_zone, int cid,
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
+	if (id < 0) {
+		ret = id;
+		goto set_time_exit;
+	}
 
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
@@ -538,6 +540,8 @@ static int set_time_window(struct powercap_zone *power_zone, int cid,
 	default:
 		ret = -EINVAL;
 	}
+
+set_time_exit:
 	put_online_cpus();
 	return ret;
 }
@@ -552,6 +556,10 @@ static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data)
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
+	if (id < 0) {
+		ret = id;
+		goto get_time_exit;
+	}
 
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
@@ -566,6 +574,8 @@ static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data)
 	}
 	if (!ret)
 		*data = val;
+
+get_time_exit:
 	put_online_cpus();
 
 	return ret;
@@ -707,7 +717,7 @@ static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type,
 	case ENERGY_UNIT:
 		scale = ENERGY_UNIT_SCALE;
 		/* per domain unit takes precedence */
-		if (rd && rd->domain_energy_unit)
+		if (rd->domain_energy_unit)
 			units = rd->domain_energy_unit;
 		else
 			units = rp->energy_unit;
@@ -976,10 +986,20 @@ static void package_power_limit_irq_save(struct rapl_package *rp)
 	smp_call_function_single(rp->lead_cpu, power_limit_irq_save_cpu, rp, 1);
 }
 
-static void power_limit_irq_restore_cpu(void *info)
+/*
+ * Restore per package power limit interrupt enable state. Called from cpu
+ * hotplug code on package removal.
+ */
+static void package_power_limit_irq_restore(struct rapl_package *rp)
 {
-	u32 l, h = 0;
+	u32 l, h;
-	struct rapl_package *rp = (struct rapl_package *)info;
+
+	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
+		return;
+
+	/* irq enable state not saved, nothing to restore */
+	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED))
+		return;
 
 	rdmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);
 
@@ -991,19 +1011,6 @@ static void power_limit_irq_restore_cpu(void *info)
 	wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
 }
 
-/* restore per package power limit interrupt enable state */
-static void package_power_limit_irq_restore(struct rapl_package *rp)
-{
-	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
-		return;
-
-	/* irq enable state not saved, nothing to restore */
-	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED))
-		return;
-
-	smp_call_function_single(rp->lead_cpu, power_limit_irq_restore_cpu, rp, 1);
-}
-
 static void set_floor_freq_default(struct rapl_domain *rd, bool mode)
 {
 	int nr_powerlimit = find_nr_power_limit(rd);
@@ -1160,84 +1167,49 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL,	rapl_defaults_hsw_server),
+	RAPL_CPU(INTEL_FAM6_XEON_PHI_KNM,	rapl_defaults_hsw_server),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_ids);
 
-/* read once for all raw primitive data for all packages, domains */
+/* Read once for all raw primitive data for domains */
-static void rapl_update_domain_data(void)
+static void rapl_update_domain_data(struct rapl_package *rp)
 {
 	int dmn, prim;
 	u64 val;
-	struct rapl_package *rp;
 
-	list_for_each_entry(rp, &rapl_packages, plist) {
+	for (dmn = 0; dmn < rp->nr_domains; dmn++) {
-		for (dmn = 0; dmn < rp->nr_domains; dmn++) {
+		pr_debug("update package %d domain %s data\n", rp->id,
-			pr_debug("update package %d domain %s data\n", rp->id,
+			 rp->domains[dmn].name);
-				rp->domains[dmn].name);
+		/* exclude non-raw primitives */
-			/* exclude non-raw primitives */
+		for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) {
-			for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++)
+			if (!rapl_read_data_raw(&rp->domains[dmn], prim,
-				if (!rapl_read_data_raw(&rp->domains[dmn], prim,
+						rpi[prim].unit, &val))
-								rpi[prim].unit,
+				rp->domains[dmn].rdd.primitives[prim] =	val;
-								&val))
-					rp->domains[dmn].rdd.primitives[prim] =
-									val;
 		}
 	}
 
 }
 
-static int rapl_unregister_powercap(void)
+static void rapl_unregister_powercap(void)
 {
-	struct rapl_package *rp;
-	struct rapl_domain *rd, *rd_package = NULL;
-
-	/* unregister all active rapl packages from the powercap layer,
-	 * hotplug lock held
-	 */
-	list_for_each_entry(rp, &rapl_packages, plist) {
-		package_power_limit_irq_restore(rp);
-
-		for (rd = rp->domains; rd < rp->domains + rp->nr_domains;
-		     rd++) {
-			pr_debug("remove package, undo power limit on %d: %s\n",
-				rp->id, rd->name);
-			rapl_write_data_raw(rd, PL1_ENABLE, 0);
-			rapl_write_data_raw(rd, PL1_CLAMP, 0);
-			if (find_nr_power_limit(rd) > 1) {
-				rapl_write_data_raw(rd, PL2_ENABLE, 0);
-				rapl_write_data_raw(rd, PL2_CLAMP, 0);
-			}
-			if (rd->id == RAPL_DOMAIN_PACKAGE) {
-				rd_package = rd;
-				continue;
-			}
-			powercap_unregister_zone(control_type, &rd->power_zone);
-		}
-		/* do the package zone last */
-		if (rd_package)
-			powercap_unregister_zone(control_type,
-						&rd_package->power_zone);
-	}
-
 	if (platform_rapl_domain) {
 		powercap_unregister_zone(control_type,
 					 &platform_rapl_domain->power_zone);
 		kfree(platform_rapl_domain);
 	}
-
 	powercap_unregister_control_type(control_type);
-
-	return 0;
 }
 
 static int rapl_package_register_powercap(struct rapl_package *rp)
 {
 	struct rapl_domain *rd;
-	int ret = 0;
 	char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/
 	struct powercap_zone *power_zone = NULL;
-	int nr_pl;
+	int nr_pl, ret;;
+
+	/* Update the domain data of the new package */
+	rapl_update_domain_data(rp);
 
 	/* first we register package domain as the parent zone*/
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
@@ -1257,8 +1229,7 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
 			if (IS_ERR(power_zone)) {
 				pr_debug("failed to register package, %d\n",
 					rp->id);
-				ret = PTR_ERR(power_zone);
+				return PTR_ERR(power_zone);
-				goto exit_package;
 			}
 			/* track parent zone in per package/socket data */
 			rp->power_zone = power_zone;
@@ -1268,8 +1239,7 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
 	}
 	if (!power_zone) {
 		pr_err("no package domain found, unknown topology!\n");
-		ret = -ENODEV;
+		return -ENODEV;
-		goto exit_package;
 	}
 	/* now register domains as children of the socket/package*/
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
@@ -1290,11 +1260,11 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
 			goto err_cleanup;
 		}
 	}
+	return 0;
 
-exit_package:
-	return ret;
 err_cleanup:
-	/* clean up previously initialized domains within the package if we
+	/*
+	 * Clean up previously initialized domains within the package if we
 	 * failed after the first domain setup.
 	 */
 	while (--rd >= rp->domains) {
@@ -1305,7 +1275,7 @@ err_cleanup:
 	return ret;
 }
 
-static int rapl_register_psys(void)
+static int __init rapl_register_psys(void)
 {
 	struct rapl_domain *rd;
 	struct powercap_zone *power_zone;
@@ -1346,40 +1316,14 @@ static int rapl_register_psys(void)
 	return 0;
 }
 
-static int rapl_register_powercap(void)
+static int __init rapl_register_powercap(void)
 {
-	struct rapl_domain *rd;
-	struct rapl_package *rp;
-	int ret = 0;
-
 	control_type = powercap_register_control_type(NULL, "intel-rapl", NULL);
 	if (IS_ERR(control_type)) {
 		pr_debug("failed to register powercap control_type.\n");
 		return PTR_ERR(control_type);
 	}
-	/* read the initial data */
+	return 0;
-	rapl_update_domain_data();
-	list_for_each_entry(rp, &rapl_packages, plist)
-		if (rapl_package_register_powercap(rp))
-			goto err_cleanup_package;
-
-	/* Don't bail out if PSys is not supported */
-	rapl_register_psys();
-
-	return ret;
-
-err_cleanup_package:
-	/* clean up previously initialized packages */
-	list_for_each_entry_continue_reverse(rp, &rapl_packages, plist) {
-		for (rd = rp->domains; rd < rp->domains + rp->nr_domains;
-		     rd++) {
-			pr_debug("unregister zone/package %d, %s domain\n",
-				rp->id, rd->name);
-			powercap_unregister_zone(control_type, &rd->power_zone);
-		}
-	}
-
-	return ret;
 }
 
 static int rapl_check_domain(int cpu, int domain)
@@ -1452,9 +1396,8 @@ static void rapl_detect_powerlimit(struct rapl_domain *rd)
  */
 static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 {
-	int i;
-	int ret = 0;
 	struct rapl_domain *rd;
+	int i;
 
 	for (i = 0; i < RAPL_DOMAIN_MAX; i++) {
 		/* use physical package id to read counters */
@@ -1466,84 +1409,20 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	rp->nr_domains = bitmap_weight(&rp->domain_map,	RAPL_DOMAIN_MAX);
 	if (!rp->nr_domains) {
 		pr_debug("no valid rapl domains found in package %d\n", rp->id);
-		ret = -ENODEV;
+		return -ENODEV;
-		goto done;
 	}
 	pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id);
 
 	rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain),
 			GFP_KERNEL);
-	if (!rp->domains) {
+	if (!rp->domains)
-		ret = -ENOMEM;
+		return -ENOMEM;
-		goto done;
+
-	}
 	rapl_init_domains(rp);
 
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++)
 		rapl_detect_powerlimit(rd);
 
-
-
-done:
-	return ret;
-}
-
-static bool is_package_new(int package)
-{
-	struct rapl_package *rp;
-
-	/* caller prevents cpu hotplug, there will be no new packages added
-	 * or deleted while traversing the package list, no need for locking.
-	 */
-	list_for_each_entry(rp, &rapl_packages, plist)
-		if (package == rp->id)
-			return false;
-
-	return true;
-}
-
-/* RAPL interface can be made of a two-level hierarchy: package level and domain
- * level. We first detect the number of packages then domains of each package.
- * We have to consider the possiblity of CPU online/offline due to hotplug and
- * other scenarios.
- */
-static int rapl_detect_topology(void)
-{
-	int i;
-	int phy_package_id;
-	struct rapl_package *new_package, *rp;
-
-	for_each_online_cpu(i) {
-		phy_package_id = topology_physical_package_id(i);
-		if (is_package_new(phy_package_id)) {
-			new_package = kzalloc(sizeof(*rp), GFP_KERNEL);
-			if (!new_package) {
-				rapl_cleanup_data();
-				return -ENOMEM;
-			}
-			/* add the new package to the list */
-			new_package->id = phy_package_id;
-			new_package->nr_cpus = 1;
-			/* use the first active cpu of the package to access */
-			new_package->lead_cpu = i;
-			/* check if the package contains valid domains */
-			if (rapl_detect_domains(new_package, i) ||
-				rapl_defaults->check_unit(new_package, i)) {
-				kfree(new_package->domains);
-				kfree(new_package);
-				/* free up the packages already initialized */
-				rapl_cleanup_data();
-				return -ENODEV;
-			}
-			INIT_LIST_HEAD(&new_package->plist);
-			list_add(&new_package->plist, &rapl_packages);
-		} else {
-			rp = find_package_by_id(phy_package_id);
-			if (rp)
-				++rp->nr_cpus;
-		}
-	}
-
 	return 0;
 }
 
@@ -1552,12 +1431,21 @@ static void rapl_remove_package(struct rapl_package *rp)
 {
 	struct rapl_domain *rd, *rd_package = NULL;
 
+	package_power_limit_irq_restore(rp);
+
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
+		rapl_write_data_raw(rd, PL1_ENABLE, 0);
+		rapl_write_data_raw(rd, PL1_CLAMP, 0);
+		if (find_nr_power_limit(rd) > 1) {
+			rapl_write_data_raw(rd, PL2_ENABLE, 0);
+			rapl_write_data_raw(rd, PL2_CLAMP, 0);
+		}
 		if (rd->id == RAPL_DOMAIN_PACKAGE) {
 			rd_package = rd;
 			continue;
 		}
-		pr_debug("remove package %d, %s domain\n", rp->id, rd->name);
+		pr_debug("remove package, undo power limit on %d: %s\n",
+			 rp->id, rd->name);
 		powercap_unregister_zone(control_type, &rd->power_zone);
 	}
 	/* do parent zone last */
@@ -1567,20 +1455,17 @@ static void rapl_remove_package(struct rapl_package *rp)
 }
 
 /* called from CPU hotplug notifier, hotplug lock held */
-static int rapl_add_package(int cpu)
+static struct rapl_package *rapl_add_package(int cpu, int pkgid)
 {
-	int ret = 0;
-	int phy_package_id;
 	struct rapl_package *rp;
+	int ret;
 
-	phy_package_id = topology_physical_package_id(cpu);
 	rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL);
 	if (!rp)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	/* add the new package to the list */
-	rp->id = phy_package_id;
+	rp->id = pkgid;
-	rp->nr_cpus = 1;
 	rp->lead_cpu = cpu;
 
 	/* check if the package contains valid domains */
@@ -1589,17 +1474,17 @@ static int rapl_add_package(int cpu)
 		ret = -ENODEV;
 		goto err_free_package;
 	}
-	if (!rapl_package_register_powercap(rp)) {
+	ret = rapl_package_register_powercap(rp);
+	if (!ret) {
 		INIT_LIST_HEAD(&rp->plist);
 		list_add(&rp->plist, &rapl_packages);
-		return ret;
+		return rp;
 	}
 
 err_free_package:
 	kfree(rp->domains);
 	kfree(rp);
-
+	return ERR_PTR(ret);
-	return ret;
 }
 
 /* Handles CPU hotplug on multi-socket systems.
@@ -1609,55 +1494,46 @@ err_free_package:
  * associated domains. Cooling devices are handled accordingly at
  * per-domain level.
  */
-static int rapl_cpu_callback(struct notifier_block *nfb,
+static int rapl_cpu_online(unsigned int cpu)
-				unsigned long action, void *hcpu)
 {
-	unsigned long cpu = (unsigned long)hcpu;
+	int pkgid = topology_physical_package_id(cpu);
-	int phy_package_id;
+	struct rapl_package *rp;
+
+	rp = find_package_by_id(pkgid);
+	if (!rp) {
+		rp = rapl_add_package(cpu, pkgid);
+		if (IS_ERR(rp))
+			return PTR_ERR(rp);
+	}
+	cpumask_set_cpu(cpu, &rp->cpumask);
+	return 0;
+}
+
+static int rapl_cpu_down_prep(unsigned int cpu)
+{
+	int pkgid = topology_physical_package_id(cpu);
 	struct rapl_package *rp;
 	int lead_cpu;
 
-	phy_package_id = topology_physical_package_id(cpu);
+	rp = find_package_by_id(pkgid);
-	switch (action) {
+	if (!rp)
-	case CPU_ONLINE:
+		return 0;
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		rp = find_package_by_id(phy_package_id);
-		if (rp)
-			++rp->nr_cpus;
-		else
-			rapl_add_package(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		rp = find_package_by_id(phy_package_id);
-		if (!rp)
-			break;
-		if (--rp->nr_cpus == 0)
-			rapl_remove_package(rp);
-		else if (cpu == rp->lead_cpu) {
-			/* choose another active cpu in the package */
-			lead_cpu = cpumask_any_but(topology_core_cpumask(cpu), cpu);
-			if (lead_cpu < nr_cpu_ids)
-				rp->lead_cpu = lead_cpu;
-			else /* should never go here */
-				pr_err("no active cpu available for package %d\n",
-					phy_package_id);
-		}
-	}
 
-	return NOTIFY_OK;
+	cpumask_clear_cpu(cpu, &rp->cpumask);
+	lead_cpu = cpumask_first(&rp->cpumask);
+	if (lead_cpu >= nr_cpu_ids)
+		rapl_remove_package(rp);
+	else if (rp->lead_cpu == cpu)
+		rp->lead_cpu = lead_cpu;
+	return 0;
 }
 
-static struct notifier_block rapl_cpu_notifier = {
+static enum cpuhp_state pcap_rapl_online;
-	.notifier_call = rapl_cpu_callback,
-};
 
 static int __init rapl_init(void)
 {
-	int ret = 0;
 	const struct x86_cpu_id *id;
+	int ret;
 
 	id = x86_match_cpu(rapl_ids);
 	if (!id) {
@@ -1669,36 +1545,29 @@ static int __init rapl_init(void)
 
 	rapl_defaults = (struct rapl_defaults *)id->driver_data;
 
-	cpu_notifier_register_begin();
+	ret = rapl_register_powercap();
-
-	/* prevent CPU hotplug during detection */
-	get_online_cpus();
-	ret = rapl_detect_topology();
 	if (ret)
-		goto done;
+		return ret;
 
-	if (rapl_register_powercap()) {
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powercap/rapl:online",
-		rapl_cleanup_data();
+				rapl_cpu_online, rapl_cpu_down_prep);
-		ret = -ENODEV;
+	if (ret < 0)
-		goto done;
+		goto err_unreg;
-	}
+	pcap_rapl_online = ret;
-	__register_hotcpu_notifier(&rapl_cpu_notifier);
-done:
-	put_online_cpus();
-	cpu_notifier_register_done();
 
+	/* Don't bail out if PSys is not supported */
+	rapl_register_psys();
+	return 0;
+
+err_unreg:
+	rapl_unregister_powercap();
 	return ret;
 }
 
 static void __exit rapl_exit(void)
 {
-	cpu_notifier_register_begin();
+	cpuhp_remove_state(pcap_rapl_online);
-	get_online_cpus();
-	__unregister_hotcpu_notifier(&rapl_cpu_notifier);
 	rapl_unregister_powercap();
-	rapl_cleanup_data();
-	put_online_cpus();
-	cpu_notifier_register_done();
 }
 
 module_init(rapl_init);

include/linux/suspend.h

@@ -194,6 +194,8 @@ struct platform_freeze_ops {
 };
 
 #ifdef CONFIG_SUSPEND
+extern suspend_state_t mem_sleep_default;
+
 /**
  * suspend_set_ops - set platform dependent suspend operations
  * @ops: The new suspend operations to set.

kernel/power/main.c

@@ -78,6 +78,78 @@ static ssize_t pm_async_store(struct kobject *kobj, struct kobj_attribute *attr,
 
 power_attr(pm_async);
 
+#ifdef CONFIG_SUSPEND
+static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr,
+			      char *buf)
+{
+	char *s = buf;
+	suspend_state_t i;
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (mem_sleep_states[i]) {
+			const char *label = mem_sleep_states[i];
+
+			if (mem_sleep_current == i)
+				s += sprintf(s, "[%s] ", label);
+			else
+				s += sprintf(s, "%s ", label);
+		}
+
+	/* Convert the last space to a newline if needed. */
+	if (s != buf)
+		*(s-1) = '\n';
+
+	return (s - buf);
+}
+
+static suspend_state_t decode_suspend_state(const char *buf, size_t n)
+{
+	suspend_state_t state;
+	char *p;
+	int len;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	for (state = PM_SUSPEND_MIN; state < PM_SUSPEND_MAX; state++) {
+		const char *label = mem_sleep_states[state];
+
+		if (label && len == strlen(label) && !strncmp(buf, label, len))
+			return state;
+	}
+
+	return PM_SUSPEND_ON;
+}
+
+static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	suspend_state_t state;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	state = decode_suspend_state(buf, n);
+	if (state < PM_SUSPEND_MAX && state > PM_SUSPEND_ON)
+		mem_sleep_current = state;
+	else
+		error = -EINVAL;
+
+ out:
+	pm_autosleep_unlock();
+	return error ? error : n;
+}
+
+power_attr(mem_sleep);
+#endif /* CONFIG_SUSPEND */
+
 #ifdef CONFIG_PM_DEBUG
 int pm_test_level = TEST_NONE;
 
@@ -368,12 +440,16 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 	}
 
 	state = decode_state(buf, n);
-	if (state < PM_SUSPEND_MAX)
+	if (state < PM_SUSPEND_MAX) {
+		if (state == PM_SUSPEND_MEM)
+			state = mem_sleep_current;
+
 		error = pm_suspend(state);
-	else if (state == PM_SUSPEND_MAX)
+	} else if (state == PM_SUSPEND_MAX) {
 		error = hibernate();
-	else
+	} else {
 		error = -EINVAL;
+	}
 
  out:
 	pm_autosleep_unlock();
@@ -485,6 +561,9 @@ static ssize_t autosleep_store(struct kobject *kobj,
 	    && strcmp(buf, "off") && strcmp(buf, "off\n"))
 		return -EINVAL;
 
+	if (state == PM_SUSPEND_MEM)
+		state = mem_sleep_current;
+
 	error = pm_autosleep_set_state(state);
 	return error ? error : n;
 }
@@ -602,6 +681,9 @@ static struct attribute * g[] = {
 #ifdef CONFIG_PM_SLEEP
 	&pm_async_attr.attr,
 	&wakeup_count_attr.attr,
+#ifdef CONFIG_SUSPEND
+	&mem_sleep_attr.attr,
+#endif
 #ifdef CONFIG_PM_AUTOSLEEP
 	&autosleep_attr.attr,
 #endif

kernel/power/power.h

@@ -189,11 +189,15 @@ extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *);
 
 #ifdef CONFIG_SUSPEND
 /* kernel/power/suspend.c */
-extern const char *pm_labels[];
+extern const char * const pm_labels[];
 extern const char *pm_states[];
+extern const char *mem_sleep_states[];
+extern suspend_state_t mem_sleep_current;
 
 extern int suspend_devices_and_enter(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
+#define mem_sleep_current	PM_SUSPEND_ON
+
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;

kernel/power/suspend.c

@@ -32,8 +32,21 @@
 
 #include "power.h"
 
-const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
+const char * const pm_labels[] = {
+	[PM_SUSPEND_FREEZE] = "freeze",
+	[PM_SUSPEND_STANDBY] = "standby",
+	[PM_SUSPEND_MEM] = "mem",
+};
 const char *pm_states[PM_SUSPEND_MAX];
+static const char * const mem_sleep_labels[] = {
+	[PM_SUSPEND_FREEZE] = "s2idle",
+	[PM_SUSPEND_STANDBY] = "shallow",
+	[PM_SUSPEND_MEM] = "deep",
+};
+const char *mem_sleep_states[PM_SUSPEND_MAX];
+
+suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE;
+suspend_state_t mem_sleep_default = PM_SUSPEND_MAX;
 
 unsigned int pm_suspend_global_flags;
 EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
@@ -110,30 +123,32 @@ static bool valid_state(suspend_state_t state)
 	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
 }
 
-/*
- * If this is set, the "mem" label always corresponds to the deepest sleep state
- * available, the "standby" label corresponds to the second deepest sleep state
- * available (if any), and the "freeze" label corresponds to the remaining
- * available sleep state (if there is one).
- */
-static bool relative_states;
-
 void __init pm_states_init(void)
 {
+	/* "mem" and "freeze" are always present in /sys/power/state. */
+	pm_states[PM_SUSPEND_MEM] = pm_labels[PM_SUSPEND_MEM];
+	pm_states[PM_SUSPEND_FREEZE] = pm_labels[PM_SUSPEND_FREEZE];
 	/*
-	 * freeze state should be supported even without any suspend_ops,
+	 * Suspend-to-idle should be supported even without any suspend_ops,
-	 * initialize pm_states accordingly here
+	 * initialize mem_sleep_states[] accordingly here.
 	 */
-	pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
+	mem_sleep_states[PM_SUSPEND_FREEZE] = mem_sleep_labels[PM_SUSPEND_FREEZE];
 }
 
-static int __init sleep_states_setup(char *str)
+static int __init mem_sleep_default_setup(char *str)
 {
-	relative_states = !strncmp(str, "1", 1);
+	suspend_state_t state;
+
+	for (state = PM_SUSPEND_FREEZE; state <= PM_SUSPEND_MEM; state++)
+		if (mem_sleep_labels[state] &&
+		    !strcmp(str, mem_sleep_labels[state])) {
+			mem_sleep_default = state;
+			break;
+		}
+
 	return 1;
 }
-
+__setup("mem_sleep_default=", mem_sleep_default_setup);
-__setup("relative_sleep_states=", sleep_states_setup);
 
 /**
  * suspend_set_ops - Set the global suspend method table.
@@ -141,21 +156,21 @@ __setup("relative_sleep_states=", sleep_states_setup);
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
-	suspend_state_t i;
-	int j = 0;
-
 	lock_system_sleep();
 
 	suspend_ops = ops;
-	for (i = PM_SUSPEND_MEM; i >= PM_SUSPEND_STANDBY; i--)
-		if (valid_state(i)) {
-			pm_states[i] = pm_labels[j++];
-		} else if (!relative_states) {
-			pm_states[i] = NULL;
-			j++;
-		}
 
-	pm_states[PM_SUSPEND_FREEZE] = pm_labels[j];
+	if (valid_state(PM_SUSPEND_STANDBY)) {
+		mem_sleep_states[PM_SUSPEND_STANDBY] = mem_sleep_labels[PM_SUSPEND_STANDBY];
+		pm_states[PM_SUSPEND_STANDBY] = pm_labels[PM_SUSPEND_STANDBY];
+		if (mem_sleep_default == PM_SUSPEND_STANDBY)
+			mem_sleep_current = PM_SUSPEND_STANDBY;
+	}
+	if (valid_state(PM_SUSPEND_MEM)) {
+		mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
+		if (mem_sleep_default >= PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_MEM;
+	}
 
 	unlock_system_sleep();
 }

mm/kasan/kasan.c

@@ -80,7 +80,14 @@ void kasan_unpoison_task_stack(struct task_struct *task)
 /* Unpoison the stack for the current task beyond a watermark sp value. */
 asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 {
-	__kasan_unpoison_stack(current, watermark);
+	/*
+	 * Calculate the task stack base address.  Avoid using 'current'
+	 * because this function is called by early resume code which hasn't
+	 * yet set up the percpu register (%gs).
+	 */
+	void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1));
+
+	kasan_unpoison_shadow(base, watermark - base);
 }
 
 /*