Resguardo inicial

linux-7.2.3/arch/x86/kernel/acpi/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_ACPI)		+= boot.o
+obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
+obj-$(CONFIG_ACPI_APEI)		+= apei.o
+obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc.o
+obj-$(CONFIG_ACPI_MADT_WAKEUP)	+= madt_wakeup.o madt_playdead.o
+
+ifneq ($(CONFIG_ACPI_PROCESSOR),)
+obj-y				+= cstate.o
+endif
+

linux-7.2.3/arch/x86/kernel/acpi/apei.c

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Arch-specific APEI-related functions.
+ */
+
+#include <acpi/apei.h>
+
+#include <asm/mce.h>
+#include <asm/tlbflush.h>
+
+int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data)
+{
+#ifdef CONFIG_X86_MCE
+	int i;
+	struct acpi_hest_ia_corrected *cmc;
+	struct acpi_hest_ia_error_bank *mc_bank;
+
+	cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+	if (!cmc->enabled)
+		return 0;
+
+	mce_save_apei_thr_limit(cmc->notify.error_threshold_value);
+
+	/*
+	 * We expect HEST to provide a list of MC banks that report errors
+	 * in firmware first mode. Otherwise, return non-zero value to
+	 * indicate that we are done parsing HEST.
+	 */
+	if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) ||
+	    !cmc->num_hardware_banks)
+		return 1;
+
+	pr_info("HEST: Enabling Firmware First mode for corrected errors.\n");
+
+	mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
+	for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+		mce_disable_bank(mc_bank->bank_number);
+#endif
+	return 1;
+}
+
+void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
+{
+#ifdef CONFIG_X86_MCE
+	apei_mce_report_mem_error(sev, mem_err);
+#endif
+}
+
+int arch_apei_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
+{
+	return apei_smca_report_x86_error(ctx_info, lapic_id);
+}

linux-7.2.3/arch/x86/kernel/acpi/cppc.c

@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * cppc.c: CPPC Interface for x86
+ * Copyright (c) 2016, Intel Corporation.
+ */
+
+#include <linux/bitfield.h>
+
+#include <acpi/cppc_acpi.h>
+#include <asm/msr.h>
+#include <asm/processor.h>
+#include <asm/topology.h>
+
+#define CPPC_HIGHEST_PERF_PERFORMANCE	196
+#define CPPC_HIGHEST_PERF_PREFCORE	166
+
+enum amd_pref_core {
+	AMD_PREF_CORE_UNKNOWN = 0,
+	AMD_PREF_CORE_SUPPORTED,
+	AMD_PREF_CORE_UNSUPPORTED,
+};
+static enum amd_pref_core amd_pref_core_detected;
+static u64 boost_numerator;
+
+/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
+
+bool cpc_supported_by_cpu(void)
+{
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
+		if (boot_cpu_data.x86 == 0x19 && ((boot_cpu_data.x86_model <= 0x0f) ||
+		    (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f)))
+			return true;
+		else if (boot_cpu_data.x86 == 0x17 &&
+			 boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f)
+			return true;
+		return boot_cpu_has(X86_FEATURE_CPPC);
+	}
+	return false;
+}
+
+bool cpc_ffh_supported(void)
+{
+	return true;
+}
+
+int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
+{
+	int err;
+
+	err = rdmsrq_safe_on_cpu(cpunum, reg->address, val);
+	if (!err) {
+		u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
+				       reg->bit_offset);
+
+		*val &= mask;
+		*val >>= reg->bit_offset;
+	}
+	return err;
+}
+
+int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
+{
+	u64 rd_val;
+	int err;
+
+	err = rdmsrq_safe_on_cpu(cpunum, reg->address, &rd_val);
+	if (!err) {
+		u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
+				       reg->bit_offset);
+
+		val <<= reg->bit_offset;
+		val &= mask;
+		rd_val &= ~mask;
+		rd_val |= val;
+		err = wrmsrq_safe_on_cpu(cpunum, reg->address, rd_val);
+	}
+	return err;
+}
+
+static void amd_set_max_freq_ratio(void)
+{
+	struct cppc_perf_caps perf_caps;
+	u64 numerator, nominal_perf;
+	u64 perf_ratio;
+	int rc;
+
+	rc = cppc_get_perf_caps(0, &perf_caps);
+	if (rc) {
+		pr_debug("Could not retrieve perf counters (%d)\n", rc);
+		return;
+	}
+
+	rc = amd_get_boost_ratio_numerator(0, &numerator);
+	if (rc) {
+		pr_debug("Could not retrieve highest performance (%d)\n", rc);
+		return;
+	}
+	nominal_perf = perf_caps.nominal_perf;
+
+	if (!nominal_perf) {
+		pr_debug("Could not retrieve nominal performance\n");
+		return;
+	}
+
+	/* midpoint between max_boost and max_P */
+	perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1;
+
+	freq_invariance_set_perf_ratio(perf_ratio, false);
+}
+
+static DEFINE_MUTEX(freq_invariance_lock);
+
+static inline void init_freq_invariance_cppc(void)
+{
+	static bool init_done;
+
+	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+		return;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return;
+
+	mutex_lock(&freq_invariance_lock);
+	if (!init_done)
+		amd_set_max_freq_ratio();
+	init_done = true;
+	mutex_unlock(&freq_invariance_lock);
+}
+
+void acpi_processor_init_invariance_cppc(void)
+{
+	init_freq_invariance_cppc();
+}
+
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address for highest performance value.
+ *
+ * Return: 0 for success, negative error code otherwise.
+ */
+int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
+{
+	u64 val;
+	int ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
+		ret = rdmsrq_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
+		if (ret)
+			goto out;
+
+		val = FIELD_GET(AMD_CPPC_HIGHEST_PERF_MASK, val);
+	} else {
+		ret = cppc_get_highest_perf(cpu, &val);
+		if (ret)
+			goto out;
+	}
+
+	WRITE_ONCE(*highest_perf, (u32)val);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+
+/**
+ * amd_detect_prefcore: Detect if CPUs in the system support preferred cores
+ * @detected: Output variable for the result of the detection.
+ *
+ * Determine whether CPUs in the system support preferred cores. On systems
+ * that support preferred cores, different highest perf values will be found
+ * on different cores. On other systems, the highest perf value will be the
+ * same on all cores.
+ *
+ * The result of the detection will be stored in the 'detected' parameter.
+ *
+ * Return: 0 for success, negative error code otherwise
+ */
+int amd_detect_prefcore(bool *detected)
+{
+	int cpu, count = 0;
+	u64 highest_perf[2] = {0};
+
+	if (WARN_ON(!detected))
+		return -EINVAL;
+
+	switch (amd_pref_core_detected) {
+	case AMD_PREF_CORE_SUPPORTED:
+		*detected = true;
+		return 0;
+	case AMD_PREF_CORE_UNSUPPORTED:
+		*detected = false;
+		return 0;
+	default:
+		break;
+	}
+
+	for_each_online_cpu(cpu) {
+		u32 tmp;
+		int ret;
+
+		ret = amd_get_highest_perf(cpu, &tmp);
+		if (ret)
+			return ret;
+
+		if (!count || (count == 1 && tmp != highest_perf[0]))
+			highest_perf[count++] = tmp;
+
+		if (count == 2)
+			break;
+	}
+
+	*detected = (count == 2);
+	boost_numerator = highest_perf[0];
+
+	amd_pref_core_detected = *detected ? AMD_PREF_CORE_SUPPORTED :
+					     AMD_PREF_CORE_UNSUPPORTED;
+
+	pr_debug("AMD CPPC preferred core is %ssupported (highest perf: 0x%llx)\n",
+		 *detected ? "" : "un", highest_perf[0]);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(amd_detect_prefcore);
+
+/**
+ * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation
+ * @cpu: CPU to get numerator for.
+ * @numerator: Output variable for numerator.
+ *
+ * Determine the numerator to use for calculating the boost ratio on
+ * a CPU. On systems that support preferred cores, this will be a hardcoded
+ * value. On other systems this will the highest performance register value.
+ *
+ * If booting the system with amd-pstate enabled but preferred cores disabled then
+ * the correct boost numerator will be returned to match hardware capabilities
+ * even if the preferred cores scheduling hints are not enabled.
+ *
+ * Return: 0 for success, negative error code otherwise.
+ */
+int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
+{
+	enum x86_topology_cpu_type core_type = get_topology_cpu_type(&cpu_data(cpu));
+	bool prefcore;
+	int ret;
+	u32 tmp;
+
+	ret = amd_detect_prefcore(&prefcore);
+	if (ret)
+		return ret;
+
+	/* without preferred cores, return the highest perf register value */
+	if (!prefcore) {
+		*numerator = boost_numerator;
+		return 0;
+	}
+
+	/*
+	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
+	 * the highest performance level is set to 196.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_ZEN4)) {
+		switch (boot_cpu_data.x86_model) {
+		case 0x70 ... 0x7f:
+			*numerator = CPPC_HIGHEST_PERF_PERFORMANCE;
+			return 0;
+		default:
+			break;
+		}
+	}
+
+	/* detect if running on heterogeneous design */
+	if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES)) {
+		switch (core_type) {
+		case TOPO_CPU_TYPE_UNKNOWN:
+			pr_warn("Undefined core type found for cpu %d\n", cpu);
+			break;
+		case TOPO_CPU_TYPE_PERFORMANCE:
+			/* use the max scale for performance cores */
+			*numerator = CPPC_HIGHEST_PERF_PERFORMANCE;
+			return 0;
+		case TOPO_CPU_TYPE_EFFICIENCY:
+			/* use the highest perf value for efficiency cores */
+			ret = amd_get_highest_perf(cpu, &tmp);
+			if (ret)
+				return ret;
+			*numerator = tmp;
+			return 0;
+		}
+	}
+
+	*numerator = CPPC_HIGHEST_PERF_PREFCORE;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(amd_get_boost_ratio_numerator);

linux-7.2.3/arch/x86/kernel/acpi/cstate.c

@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005 Intel Corporation
+ * 	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ * 	- Added _PDC for SMP C-states on Intel CPUs
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+
+#include <acpi/processor.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cpuid/api.h>
+#include <asm/mwait.h>
+#include <asm/special_insns.h>
+#include <asm/smp.h>
+
+/*
+ * Initialize bm_flags based on the CPU cache properties
+ * On SMP it depends on cache configuration
+ * - When cache is not shared among all CPUs, we flush cache
+ *   before entering C3.
+ * - When cache is shared among all CPUs, we use bm_check
+ *   mechanism as in UP case
+ *
+ * This routine is called only after all the CPUs are online
+ */
+void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
+					unsigned int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	flags->bm_check = 0;
+	if (num_online_cpus() == 1)
+		flags->bm_check = 1;
+	else if (c->x86_vendor == X86_VENDOR_INTEL) {
+		/*
+		 * Today all MP CPUs that support C3 share cache.
+		 * And caches should not be flushed by software while
+		 * entering C3 type state.
+		 */
+		flags->bm_check = 1;
+	}
+
+	/*
+	 * On all recent Intel platforms, ARB_DISABLE is a nop.
+	 * So, set bm_control to zero to indicate that ARB_DISABLE
+	 * is not required while entering C3 type state.
+	 */
+	if (c->x86_vendor == X86_VENDOR_INTEL &&
+	    (c->x86 > 15 || (c->x86_vfm >= INTEL_CORE2_MEROM && c->x86_vfm <= INTEL_FAM6_LAST)))
+		flags->bm_control = 0;
+
+	if (c->x86_vendor == X86_VENDOR_CENTAUR) {
+		if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
+		    c->x86_stepping >= 0x0e)) {
+			/*
+			 * For all recent Centaur CPUs, the ucode will make sure that each
+			 * core can keep cache coherence with each other while entering C3
+			 * type state. So, set bm_check to 1 to indicate that the kernel
+			 * doesn't need to execute a cache flush operation (WBINVD) when
+			 * entering C3 type state.
+			 */
+			flags->bm_check = 1;
+			/*
+			 * For all recent Centaur platforms, ARB_DISABLE is a nop.
+			 * Set bm_control to zero to indicate that ARB_DISABLE is
+			 * not required while entering C3 type state.
+			 */
+			flags->bm_control = 0;
+		}
+	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All Zhaoxin CPUs that support C3 share cache.
+		 * And caches should not be flushed by software while
+		 * entering C3 type state.
+		 */
+		flags->bm_check = 1;
+		/*
+		 * On all recent Zhaoxin platforms, ARB_DISABLE is a nop.
+		 * So, set bm_control to zero to indicate that ARB_DISABLE
+		 * is not required while entering C3 type state.
+		 */
+		flags->bm_control = 0;
+	}
+	if (cpu_feature_enabled(X86_FEATURE_ZEN)) {
+		/*
+		 * For all AMD Zen or newer CPUs that support C3, caches
+		 * should not be flushed by software while entering C3
+		 * type state. Set bm->check to 1 so that kernel doesn't
+		 * need to execute cache flush operation.
+		 */
+		flags->bm_check = 1;
+		/*
+		 * In current AMD C state implementation ARB_DIS is no longer
+		 * used. So set bm_control to zero to indicate ARB_DIS is not
+		 * required while entering C3 type state.
+		 */
+		flags->bm_control = 0;
+	}
+}
+EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
+
+/* The code below handles cstate entry with monitor-mwait pair on Intel*/
+
+struct cstate_entry {
+	struct {
+		unsigned int eax;
+		unsigned int ecx;
+	} states[ACPI_PROCESSOR_MAX_POWER];
+};
+static struct cstate_entry __percpu *cpu_cstate_entry;	/* per CPU ptr */
+
+static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
+
+#define NATIVE_CSTATE_BEYOND_HALT	(2)
+
+static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
+{
+	struct acpi_processor_cx *cx = _cx;
+	long retval;
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int edx_part;
+	unsigned int cstate_type; /* C-state type and not ACPI C-state type */
+	unsigned int num_cstate_subtype;
+
+	cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx);
+
+	/* Check whether this particular cx_type (in CST) is supported or not */
+	cstate_type = (((cx->address >> MWAIT_SUBSTATE_SIZE) &
+			MWAIT_CSTATE_MASK) + 1) & MWAIT_CSTATE_MASK;
+	edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE);
+	num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
+
+	retval = 0;
+	/* If the HW does not support any sub-states in this C-state */
+	if (num_cstate_subtype == 0) {
+		pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n",
+				cx->address, edx_part);
+		retval = -1;
+		goto out;
+	}
+
+	/* mwait ecx extensions INTERRUPT_BREAK should be supported for C2/C3 */
+	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
+	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK)) {
+		retval = -1;
+		goto out;
+	}
+
+	if (!mwait_supported[cstate_type]) {
+		mwait_supported[cstate_type] = 1;
+		printk(KERN_DEBUG
+			"Monitor-Mwait will be used to enter C-%d state\n",
+			cx->type);
+	}
+	snprintf(cx->desc,
+			ACPI_CX_DESC_LEN, "ACPI FFH MWAIT 0x%x",
+			cx->address);
+out:
+	return retval;
+}
+
+int acpi_processor_ffh_cstate_probe(unsigned int cpu,
+		struct acpi_processor_cx *cx, struct acpi_power_register *reg)
+{
+	struct cstate_entry *percpu_entry;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	long retval;
+
+	if (!cpu_cstate_entry || c->cpuid_level < CPUID_LEAF_MWAIT)
+		return -1;
+
+	if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT)
+		return -1;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	percpu_entry->states[cx->index].eax = 0;
+	percpu_entry->states[cx->index].ecx = 0;
+
+	/* Make sure we are running on right CPU */
+
+	retval = call_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx,
+			     false);
+	if (retval == 0) {
+		/* Use the hint in CST */
+		percpu_entry->states[cx->index].eax = cx->address;
+		percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
+	}
+
+	/*
+	 * For _CST FFH on Intel, if GAS.access_size bit 1 is cleared,
+	 * then we should skip checking BM_STS for this C-state.
+	 * ref: "Intel Processor Vendor-Specific ACPI Interface Specification"
+	 */
+	if ((c->x86_vendor == X86_VENDOR_INTEL) && !(reg->access_size & 0x2))
+		cx->bm_sts_skip = 1;
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
+
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_play_dead(percpu_entry->states[cx->index].eax);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_play_dead);
+
+void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_idle_with_hints(percpu_entry->states[cx->index].eax,
+	                      percpu_entry->states[cx->index].ecx);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter);
+
+static int __init ffh_cstate_init(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (c->x86_vendor != X86_VENDOR_INTEL &&
+	    c->x86_vendor != X86_VENDOR_AMD &&
+	    c->x86_vendor != X86_VENDOR_HYGON)
+		return -1;
+
+	cpu_cstate_entry = alloc_percpu(struct cstate_entry);
+	return 0;
+}
+
+static void __exit ffh_cstate_exit(void)
+{
+	free_percpu(cpu_cstate_entry);
+	cpu_cstate_entry = NULL;
+}
+
+arch_initcall(ffh_cstate_init);
+__exitcall(ffh_cstate_exit);

linux-7.2.3/arch/x86/kernel/acpi/madt_playdead.S

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+
+	.text
+	.align PAGE_SIZE
+
+/*
+ * asm_acpi_mp_play_dead() - Hand over control of the CPU to the BIOS
+ *
+ * rdi: Address of the ACPI MADT MPWK ResetVector
+ * rsi: PGD of the identity mapping
+ */
+SYM_FUNC_START(asm_acpi_mp_play_dead)
+	ANNOTATE_NOENDBR
+	/* Turn off global entries. Following CR3 write will flush them. */
+	movq	%cr4, %rdx
+	andq	$~(X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4
+
+	/* Switch to identity mapping */
+	movq	%rsi, %cr3
+
+	/* Jump to reset vector */
+	ANNOTATE_RETPOLINE_SAFE
+	jmp	*%rdi
+SYM_FUNC_END(asm_acpi_mp_play_dead)

linux-7.2.3/arch/x86/kernel/acpi/madt_wakeup.c

@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/acpi.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/kexec.h>
+#include <linux/memblock.h>
+#include <linux/pgtable.h>
+#include <linux/sched/hotplug.h>
+#include <asm/apic.h>
+#include <asm/barrier.h>
+#include <asm/init.h>
+#include <asm/intel_pt.h>
+#include <asm/nmi.h>
+#include <asm/processor.h>
+#include <asm/reboot.h>
+
+/* Physical address of the Multiprocessor Wakeup Structure mailbox */
+static u64 acpi_mp_wake_mailbox_paddr __ro_after_init;
+
+/* Virtual address of the Multiprocessor Wakeup Structure mailbox */
+static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox;
+
+static u64 acpi_mp_pgd __ro_after_init;
+static u64 acpi_mp_reset_vector_paddr __ro_after_init;
+
+static void acpi_mp_stop_this_cpu(void)
+{
+	asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd);
+}
+
+static void acpi_mp_play_dead(void)
+{
+	play_dead_common();
+	asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd);
+}
+
+static void acpi_mp_cpu_die(unsigned int cpu)
+{
+	u32 apicid = per_cpu(x86_cpu_to_apicid, cpu);
+	unsigned long timeout;
+
+	/*
+	 * Use TEST mailbox command to prove that BIOS got control over
+	 * the CPU before declaring it dead.
+	 *
+	 * BIOS has to clear 'command' field of the mailbox.
+	 */
+	acpi_mp_wake_mailbox->apic_id = apicid;
+	smp_store_release(&acpi_mp_wake_mailbox->command,
+			  ACPI_MP_WAKE_COMMAND_TEST);
+
+	/* Don't wait longer than a second. */
+	timeout = USEC_PER_SEC;
+	while (READ_ONCE(acpi_mp_wake_mailbox->command) && --timeout)
+		udelay(1);
+
+	if (!timeout)
+		pr_err("Failed to hand over CPU %d to BIOS\n", cpu);
+}
+
+/* The argument is required to match type of x86_mapping_info::alloc_pgt_page */
+static void __init *alloc_pgt_page(void *dummy)
+{
+	return memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static void __init free_pgt_page(void *pgt, void *dummy)
+{
+	return memblock_free(pgt, PAGE_SIZE);
+}
+
+static int __init acpi_mp_setup_reset(u64 reset_vector)
+{
+	struct x86_mapping_info info = {
+		.alloc_pgt_page = alloc_pgt_page,
+		.free_pgt_page	= free_pgt_page,
+		.page_flag      = __PAGE_KERNEL_LARGE_EXEC,
+		.kernpg_flag    = _KERNPG_TABLE_NOENC,
+	};
+	unsigned long mstart, mend;
+	pgd_t *pgd;
+
+	pgd = alloc_pgt_page(NULL);
+	if (!pgd)
+		return -ENOMEM;
+
+	for (int i = 0; i < nr_pfn_mapped; i++) {
+		mstart = pfn_mapped[i].start << PAGE_SHIFT;
+		mend   = pfn_mapped[i].end << PAGE_SHIFT;
+		if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
+			kernel_ident_mapping_free(&info, pgd);
+			return -ENOMEM;
+		}
+	}
+
+	mstart = PAGE_ALIGN_DOWN(reset_vector);
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
+		kernel_ident_mapping_free(&info, pgd);
+		return -ENOMEM;
+	}
+
+	/*
+	 * Make sure asm_acpi_mp_play_dead() is present in the identity mapping
+	 * at the same place as in the kernel page tables.
+	 * asm_acpi_mp_play_dead() switches to the identity mapping and the
+	 * function must be present at the same spot in the virtual address space
+	 * before and after switching page tables.
+	 */
+	info.offset = __START_KERNEL_map - phys_base;
+	mstart = PAGE_ALIGN_DOWN(__pa(asm_acpi_mp_play_dead));
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
+		kernel_ident_mapping_free(&info, pgd);
+		return -ENOMEM;
+	}
+
+	smp_ops.play_dead = acpi_mp_play_dead;
+	smp_ops.stop_this_cpu = acpi_mp_stop_this_cpu;
+	smp_ops.cpu_die = acpi_mp_cpu_die;
+
+	acpi_mp_reset_vector_paddr = reset_vector;
+	acpi_mp_pgd = __pa(pgd);
+
+	return 0;
+}
+
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip, unsigned int cpu)
+{
+	if (!acpi_mp_wake_mailbox_paddr) {
+		pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n");
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * Remap mailbox memory only for the first call to acpi_wakeup_cpu().
+	 *
+	 * Wakeup of secondary CPUs is fully serialized in the core code.
+	 * No need to protect acpi_mp_wake_mailbox from concurrent accesses.
+	 */
+	if (!acpi_mp_wake_mailbox) {
+		acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr,
+						sizeof(*acpi_mp_wake_mailbox),
+						MEMREMAP_WB);
+	}
+
+	/*
+	 * Mailbox memory is shared between the firmware and OS. Firmware will
+	 * listen on mailbox command address, and once it receives the wakeup
+	 * command, the CPU associated with the given apicid will be booted.
+	 *
+	 * The value of 'apic_id' and 'wakeup_vector' must be visible to the
+	 * firmware before the wakeup command is visible.  smp_store_release()
+	 * ensures ordering and visibility.
+	 */
+	acpi_mp_wake_mailbox->apic_id	    = apicid;
+	acpi_mp_wake_mailbox->wakeup_vector = start_ip;
+	smp_store_release(&acpi_mp_wake_mailbox->command,
+			  ACPI_MP_WAKE_COMMAND_WAKEUP);
+
+	/*
+	 * Wait for the CPU to wake up.
+	 *
+	 * The CPU being woken up is essentially in a spin loop waiting to be
+	 * woken up. It should not take long for it wake up and acknowledge by
+	 * zeroing out ->command.
+	 *
+	 * ACPI specification doesn't provide any guidance on how long kernel
+	 * has to wait for a wake up acknowledgment. It also doesn't provide
+	 * a way to cancel a wake up request if it takes too long.
+	 *
+	 * In TDX environment, the VMM has control over how long it takes to
+	 * wake up secondary. It can postpone scheduling secondary vCPU
+	 * indefinitely. Giving up on wake up request and reporting error opens
+	 * possible attack vector for VMM: it can wake up a secondary CPU when
+	 * kernel doesn't expect it. Wait until positive result of the wake up
+	 * request.
+	 */
+	while (READ_ONCE(acpi_mp_wake_mailbox->command))
+		cpu_relax();
+
+	return 0;
+}
+
+static void acpi_mp_disable_offlining(struct acpi_madt_multiproc_wakeup *mp_wake)
+{
+	cpu_hotplug_disable_offlining();
+
+	/*
+	 * ACPI MADT doesn't allow to offline a CPU after it was onlined. This
+	 * limits kexec: the second kernel won't be able to use more than one CPU.
+	 *
+	 * To prevent a kexec kernel from onlining secondary CPUs invalidate the
+	 * mailbox address in the ACPI MADT wakeup structure which prevents a
+	 * kexec kernel to use it.
+	 *
+	 * This is safe as the booting kernel has the mailbox address cached
+	 * already and acpi_wakeup_cpu() uses the cached value to bring up the
+	 * secondary CPUs.
+	 *
+	 * Note: This is a Linux specific convention and not covered by the
+	 *       ACPI specification.
+	 */
+	mp_wake->mailbox_address = 0;
+}
+
+int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
+			      const unsigned long end)
+{
+	struct acpi_madt_multiproc_wakeup *mp_wake;
+
+	mp_wake = (struct acpi_madt_multiproc_wakeup *)header;
+
+	/*
+	 * Cannot use the standard BAD_MADT_ENTRY() to sanity check the @mp_wake
+	 * entry.  'sizeof (struct acpi_madt_multiproc_wakeup)' can be larger
+	 * than the actual size of the MP wakeup entry in ACPI table because the
+	 * 'reset_vector' is only available in the V1 MP wakeup structure.
+	 */
+	if (!mp_wake)
+		return -EINVAL;
+	if (end - (unsigned long)mp_wake < ACPI_MADT_MP_WAKEUP_SIZE_V0)
+		return -EINVAL;
+	if (mp_wake->header.length < ACPI_MADT_MP_WAKEUP_SIZE_V0)
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(&header->common);
+
+	acpi_mp_wake_mailbox_paddr = mp_wake->mailbox_address;
+
+	if (mp_wake->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1 &&
+	    mp_wake->header.length >= ACPI_MADT_MP_WAKEUP_SIZE_V1) {
+		if (acpi_mp_setup_reset(mp_wake->reset_vector)) {
+			pr_warn("Failed to setup MADT reset vector\n");
+			acpi_mp_disable_offlining(mp_wake);
+		}
+	} else {
+		/*
+		 * CPU offlining requires version 1 of the ACPI MADT wakeup
+		 * structure.
+		 */
+		acpi_mp_disable_offlining(mp_wake);
+	}
+
+	apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu);
+
+	return 0;
+}
+
+void __init acpi_setup_mp_wakeup_mailbox(u64 mailbox_paddr)
+{
+	acpi_mp_wake_mailbox_paddr = mailbox_paddr;
+	apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu);
+}
+
+struct acpi_madt_multiproc_wakeup_mailbox *acpi_get_mp_wakeup_mailbox(void)
+{
+	return acpi_mp_wake_mailbox;
+}
+
+u64 acpi_get_mp_wakeup_mailbox_paddr(void)
+{
+	return acpi_mp_wake_mailbox_paddr;
+}

linux-7.2.3/arch/x86/kernel/acpi/sleep.c

@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * sleep.c - x86-specific ACPI sleep support.
+ *
+ *  Copyright (C) 2001-2003 Patrick Mochel
+ *  Copyright (C) 2001-2003 Pavel Machek <pavel@ucw.cz>
+ */
+
+#include <linux/acpi.h>
+#include <linux/memblock.h>
+#include <linux/dmi.h>
+#include <linux/cpumask.h>
+#include <linux/pgtable.h>
+#include <asm/segment.h>
+#include <asm/desc.h>
+#include <asm/cacheflush.h>
+#include <asm/realmode.h>
+#include <asm/hypervisor.h>
+#include <asm/msr.h>
+#include <asm/smp.h>
+
+#include <linux/ftrace.h>
+#include "../../realmode/rm/wakeup.h"
+#include "sleep.h"
+
+unsigned long acpi_realmode_flags;
+
+#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
+static char temp_stack[4096];
+#endif
+
+/**
+ * acpi_get_wakeup_address - provide physical address for S3 wakeup
+ *
+ * Returns the physical address where the kernel should be resumed after the
+ * system awakes from S3, e.g. for programming into the firmware waking vector.
+ */
+unsigned long acpi_get_wakeup_address(void)
+{
+	return ((unsigned long)(real_mode_header->wakeup_start));
+}
+
+/**
+ * x86_acpi_enter_sleep_state - enter sleep state
+ * @state: Sleep state to enter.
+ *
+ * Wrapper around acpi_enter_sleep_state() to be called by assembly.
+ */
+asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state)
+{
+	return acpi_enter_sleep_state(state);
+}
+
+/**
+ * x86_acpi_suspend_lowlevel - save kernel state
+ *
+ * Create an identity mapped page table and copy the wakeup routine to
+ * low memory.
+ */
+int x86_acpi_suspend_lowlevel(void)
+{
+	struct wakeup_header *header =
+		(struct wakeup_header *) __va(real_mode_header->wakeup_header);
+
+	if (header->signature != WAKEUP_HEADER_SIGNATURE) {
+		printk(KERN_ERR "wakeup header does not match\n");
+		return -EINVAL;
+	}
+
+	header->video_mode = saved_video_mode;
+
+	header->pmode_behavior = 0;
+
+#ifndef CONFIG_64BIT
+	native_store_gdt((struct desc_ptr *)&header->pmode_gdt);
+
+	/*
+	 * We have to check that we can write back the value, and not
+	 * just read it.  At least on 90 nm Pentium M (Family 6, Model
+	 * 13), reading an invalid MSR is not guaranteed to trap, see
+	 * Erratum X4 in "Intel Pentium M Processor on 90 nm Process
+	 * with 2-MB L2 Cache and Intel® Processor A100 and A110 on 90
+	 * nm process with 512-KB L2 Cache Specification Update".
+	 */
+	if (!rdmsr_safe(MSR_EFER,
+			&header->pmode_efer_low,
+			&header->pmode_efer_high) &&
+	    !wrmsr_safe(MSR_EFER,
+			header->pmode_efer_low,
+			header->pmode_efer_high))
+		header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER);
+#endif /* !CONFIG_64BIT */
+
+	header->pmode_cr0 = read_cr0();
+	if (__this_cpu_read(cpu_info.cpuid_level) >= 0) {
+		header->pmode_cr4 = __read_cr4();
+		header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4);
+	}
+	if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
+			&header->pmode_misc_en_low,
+			&header->pmode_misc_en_high) &&
+	    !wrmsr_safe(MSR_IA32_MISC_ENABLE,
+			header->pmode_misc_en_low,
+			header->pmode_misc_en_high))
+		header->pmode_behavior |=
+			(1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE);
+	header->realmode_flags = acpi_realmode_flags;
+	header->real_magic = 0x12345678;
+
+#ifndef CONFIG_64BIT
+	header->pmode_entry = (u32)&wakeup_pmode_return;
+	header->pmode_cr3 = (u32)__pa_symbol(initial_page_table);
+	saved_magic = 0x12345678;
+#else /* CONFIG_64BIT */
+#ifdef CONFIG_SMP
+	/*
+	 * As each CPU starts up, it will find its own stack pointer
+	 * from its current_task->thread.sp. Typically that will be
+	 * the idle thread for a newly-started AP, or even the boot
+	 * CPU which will find it set to &init_task in the static
+	 * per-cpu data.
+	 *
+	 * Make the resuming CPU use the temporary stack at startup
+	 * by setting current->thread.sp to point to that. The true
+	 * %rsp will be restored with the rest of the CPU context,
+	 * by do_suspend_lowlevel(). And unwinders don't care about
+	 * the abuse of ->thread.sp because it's a dead variable
+	 * while the thread is running on the CPU anyway; the true
+	 * value is in the actual %rsp register.
+	 */
+	current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
+	/*
+	 * Ensure the CPU knows which one it is when it comes back, if
+	 * it isn't in parallel mode and expected to work that out for
+	 * itself.
+	 */
+	if (!(smpboot_control & STARTUP_PARALLEL_MASK))
+		smpboot_control = smp_processor_id();
+#endif
+	initial_code = (unsigned long)wakeup_long64;
+	saved_magic = 0x123456789abcdef0L;
+#endif /* CONFIG_64BIT */
+
+	/*
+	 * Pause/unpause graph tracing around do_suspend_lowlevel as it has
+	 * inconsistent call/return info after it jumps to the wakeup vector.
+	 */
+	pause_graph_tracing();
+	do_suspend_lowlevel();
+	unpause_graph_tracing();
+	return 0;
+}
+
+static int __init acpi_sleep_setup(char *str)
+{
+	while ((str != NULL) && (*str != '\0')) {
+		if (strncmp(str, "s3_bios", 7) == 0)
+			acpi_realmode_flags |= 1;
+		if (strncmp(str, "s3_mode", 7) == 0)
+			acpi_realmode_flags |= 2;
+		if (strncmp(str, "s3_beep", 7) == 0)
+			acpi_realmode_flags |= 4;
+#ifdef CONFIG_HIBERNATION
+		if (strncmp(str, "s4_hwsig", 8) == 0)
+			acpi_check_s4_hw_signature = 1;
+		if (strncmp(str, "s4_nohwsig", 10) == 0)
+			acpi_check_s4_hw_signature = 0;
+#endif
+		if (strncmp(str, "nonvs", 5) == 0)
+			acpi_nvs_nosave();
+		if (strncmp(str, "nonvs_s3", 8) == 0)
+			acpi_nvs_nosave_s3();
+		if (strncmp(str, "old_ordering", 12) == 0)
+			acpi_old_suspend_ordering();
+		if (strncmp(str, "nobl", 4) == 0)
+			acpi_sleep_no_blacklist();
+		str = strchr(str, ',');
+		if (str != NULL)
+			str += strspn(str, ", \t");
+	}
+	return 1;
+}
+
+__setup("acpi_sleep=", acpi_sleep_setup);
+
+#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HYPERVISOR_GUEST)
+static int __init init_s4_sigcheck(void)
+{
+	/*
+	 * If running on a hypervisor, honour the ACPI specification
+	 * by default and trigger a clean reboot when the hardware
+	 * signature in FACS is changed after hibernation.
+	 */
+	if (acpi_check_s4_hw_signature == -1 &&
+	    !hypervisor_is_type(X86_HYPER_NATIVE))
+		acpi_check_s4_hw_signature = 1;
+
+	return 0;
+}
+/* This must happen before acpi_init() which is a subsys initcall */
+arch_initcall(init_s4_sigcheck);
+#endif

linux-7.2.3/arch/x86/kernel/acpi/sleep.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *	Variables and functions used by the code in sleep.c
+ */
+
+#include <linux/linkage.h>
+
+extern unsigned long saved_video_mode;
+extern long saved_magic;
+
+extern int wakeup_pmode_return;
+
+extern u8 wake_sleep_flags;
+
+extern void wakeup_long64(void);
+
+extern void do_suspend_lowlevel(void);
+
+extern int x86_acpi_suspend_lowlevel(void);
+
+asmlinkage acpi_status x86_acpi_enter_sleep_state(u8 state);

linux-7.2.3/arch/x86/kernel/acpi/wakeup_32.S

@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+	.text
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page_types.h>
+
+# Copyright 2003, 2008 Pavel Machek <pavel@suse.cz
+
+	.code32
+	ALIGN
+
+SYM_CODE_START(wakeup_pmode_return)
+	movw	$__KERNEL_DS, %ax
+	movw	%ax, %ss
+	movw	%ax, %fs
+	movw	%ax, %gs
+
+	movw	$__USER_DS, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+
+	# reload the gdt, as we need the full 32 bit address
+	lidt	saved_idt
+	lldt	saved_ldt
+	ljmp	$(__KERNEL_CS), $1f
+1:
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+	wbinvd
+
+	# and restore the stack ... but you need gdt for this to work
+	movl	saved_context_esp, %esp
+
+	movl	%cs:saved_magic, %eax
+	cmpl	$0x12345678, %eax
+	jne	bogus_magic
+
+	# jump to place where we left off
+	movl	saved_eip, %eax
+	jmp	*%eax
+SYM_CODE_END(wakeup_pmode_return)
+
+bogus_magic:
+	jmp	bogus_magic
+
+
+
+save_registers:
+	sidt	saved_idt
+	sldt	saved_ldt
+	str	saved_tss
+
+	leal	4(%esp), %eax
+	movl	%eax, saved_context_esp
+	movl	%ebx, saved_context_ebx
+	movl	%ebp, saved_context_ebp
+	movl	%esi, saved_context_esi
+	movl	%edi, saved_context_edi
+	pushfl
+	popl	saved_context_eflags
+
+	movl	$ret_point, saved_eip
+	RET
+
+
+restore_registers:
+	movl	saved_context_ebp, %ebp
+	movl	saved_context_ebx, %ebx
+	movl	saved_context_esi, %esi
+	movl	saved_context_edi, %edi
+	pushl	saved_context_eflags
+	popfl
+	RET
+
+SYM_CODE_START(do_suspend_lowlevel)
+	call	save_processor_state
+	call	save_registers
+	pushl	$3
+	call	x86_acpi_enter_sleep_state
+	addl	$4, %esp
+
+#	In case of S3 failure, we'll emerge here.  Jump
+# 	to ret_point to recover
+	jmp	ret_point
+	.p2align 4,,7
+ret_point:
+	call	restore_registers
+	call	restore_processor_state
+	RET
+SYM_CODE_END(do_suspend_lowlevel)
+
+.data
+ALIGN
+SYM_DATA(saved_magic,	.long 0)
+saved_eip:		.long 0
+
+# saved registers
+saved_idt:	.long	0,0
+saved_ldt:	.long	0
+saved_tss:	.long	0
+

linux-7.2.3/arch/x86/kernel/acpi/wakeup_64.S

@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+.text
+#include <linux/linkage.h>
+#include <linux/objtool.h>
+#include <asm/segment.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
+#include <asm/msr.h>
+#include <asm/asm-offsets.h>
+#include <asm/frame.h>
+#include <asm/nospec-branch.h>
+
+# Copyright 2003 Pavel Machek <pavel@suse.cz
+
+.code64
+	/*
+	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
+	 */
+SYM_FUNC_START(wakeup_long64)
+	ANNOTATE_NOENDBR
+	movq	saved_magic(%rip), %rax
+	movq	$0x123456789abcdef0, %rdx
+	cmpq	%rdx, %rax
+	je	2f
+
+	/* stop here on a saved_magic mismatch */
+	movq $0xbad6d61676963, %rcx
+1:
+	jmp 1b
+2:
+	movw	$__KERNEL_DS, %ax
+	movw	%ax, %ss	
+	movw	%ax, %ds
+	movw	%ax, %es
+	movw	%ax, %fs
+	movw	%ax, %gs
+	movq	saved_rsp(%rip), %rsp
+
+	movq	saved_rbx(%rip), %rbx
+	movq	saved_rdi(%rip), %rdi
+	movq	saved_rsi(%rip), %rsi
+	movq	saved_rbp(%rip), %rbp
+
+	movq	saved_rip(%rip), %rax
+	ANNOTATE_RETPOLINE_SAFE
+	jmp	*%rax
+SYM_FUNC_END(wakeup_long64)
+
+SYM_FUNC_START(do_suspend_lowlevel)
+	FRAME_BEGIN
+	subq	$8, %rsp
+	xorl	%eax, %eax
+	call	save_processor_state
+
+	movq	$saved_context, %rax
+	movq	%rsp, pt_regs_sp(%rax)
+	movq	%rbp, pt_regs_bp(%rax)
+	movq	%rsi, pt_regs_si(%rax)
+	movq	%rdi, pt_regs_di(%rax)
+	movq	%rbx, pt_regs_bx(%rax)
+	movq	%rcx, pt_regs_cx(%rax)
+	movq	%rdx, pt_regs_dx(%rax)
+	movq	%r8, pt_regs_r8(%rax)
+	movq	%r9, pt_regs_r9(%rax)
+	movq	%r10, pt_regs_r10(%rax)
+	movq	%r11, pt_regs_r11(%rax)
+	movq	%r12, pt_regs_r12(%rax)
+	movq	%r13, pt_regs_r13(%rax)
+	movq	%r14, pt_regs_r14(%rax)
+	movq	%r15, pt_regs_r15(%rax)
+	pushfq
+	popq	pt_regs_flags(%rax)
+
+	movq	$.Lresume_point, saved_rip(%rip)
+
+	movq	%rsp, saved_rsp(%rip)
+	movq	%rbp, saved_rbp(%rip)
+	movq	%rbx, saved_rbx(%rip)
+	movq	%rdi, saved_rdi(%rip)
+	movq	%rsi, saved_rsi(%rip)
+
+	addq	$8, %rsp
+	movl	$3, %edi
+	xorl	%eax, %eax
+	call	x86_acpi_enter_sleep_state
+	/* in case something went wrong, restore the machine status and go on */
+	jmp	.Lresume_point
+
+	.align 4
+.Lresume_point:
+	ANNOTATE_NOENDBR
+	/* We don't restore %rax, it must be 0 anyway */
+	movq	$saved_context, %rax
+	movq	saved_context_cr4(%rax), %rbx
+	movq	%rbx, %cr4
+	movq	saved_context_cr3(%rax), %rbx
+	movq	%rbx, %cr3
+	movq	saved_context_cr2(%rax), %rbx
+	movq	%rbx, %cr2
+	movq	saved_context_cr0(%rax), %rbx
+	movq	%rbx, %cr0
+	pushq	pt_regs_flags(%rax)
+	popfq
+	movq	pt_regs_sp(%rax), %rsp
+	movq	pt_regs_bp(%rax), %rbp
+	movq	pt_regs_si(%rax), %rsi
+	movq	pt_regs_di(%rax), %rdi
+	movq	pt_regs_bx(%rax), %rbx
+	movq	pt_regs_cx(%rax), %rcx
+	movq	pt_regs_dx(%rax), %rdx
+	movq	pt_regs_r8(%rax), %r8
+	movq	pt_regs_r9(%rax), %r9
+	movq	pt_regs_r10(%rax), %r10
+	movq	pt_regs_r11(%rax), %r11
+	movq	pt_regs_r12(%rax), %r12
+	movq	pt_regs_r13(%rax), %r13
+	movq	pt_regs_r14(%rax), %r14
+	movq	pt_regs_r15(%rax), %r15
+
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
+	/*
+	 * 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
+	jmp	restore_processor_state
+SYM_FUNC_END(do_suspend_lowlevel)
+STACK_FRAME_NON_STANDARD do_suspend_lowlevel
+
+.data
+saved_rbp:		.quad	0
+saved_rsi:		.quad	0
+saved_rdi:		.quad	0
+saved_rbx:		.quad	0
+
+saved_rip:		.quad	0
+saved_rsp:		.quad	0
+
+SYM_DATA(saved_magic,	.quad	0)